fix(lock): reject force-released acquisitions before registration

.agents/references/implementation.md

@@ -18,7 +18,6 @@ These implementation, style, and quality rules apply to all contributions, regar
 - Do not include agent, tool, contributor, account, or organization names in branch names.
 - Push to the user-requested remote or the repository's configured push remote. Do not hard-code or infer a remote from an account name.
 - Check free space before artifact-heavy builds, tests, coverage, or downloads. Re-check before a broad gate when space is tight.
-- Before handoff, remove the Cargo target directories and temporary worktrees the task created unless they stay intentionally or hold unmerged work. Identify build output by Cargo's markers (`.rustc_info.json`, `CACHEDIR.TAG`), not by directory name: `target` is also a source directory here.
 - Remove only task-owned temporary/build artifacts. Never delete another task's worktree or uncommitted data.
 - At handoff, mention disk or cleanup details only when they affected execution or artifacts/worktrees remain intentionally.
 - For Docker verification, ensure the tested image contains the intended binary. `buildx build` without `--load` leaves the image in the build cache; use the Makefile's loaded image and rebuild without cache only when stale artifacts are evidenced.

.config/ci-plan.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "rollout": "enforced",
+  "rollout": "shadow",
   "core_packages": ["rustfs", "rustfs-ecstore", "rustfs-filemeta", "rustfs-iam", "rustfs-policy"],
   "connect_packages": [
     "rustfs-credentials", "rustfs-config", "rustfs-common", "rustfs-crypto",

.config/e2e-distributed-selection.txt

@@ -1,2 +1,2 @@
-sha256-linux=2f97cbbeb2dbf52919b704a3d07336c162a41f95079d941d74251f9279c494e6
-sha256-darwin=2f97cbbeb2dbf52919b704a3d07336c162a41f95079d941d74251f9279c494e6
+sha256-linux=eb33067d90ee66c0a97e8f3658e46c152e47f897d2fbfdc6cb5ad93cfa55414b
+sha256-darwin=eb33067d90ee66c0a97e8f3658e46c152e47f897d2fbfdc6cb5ad93cfa55414b

.config/e2e-full-selection.txt

@@ -1,2 +1,2 @@
-sha256-darwin=7c705942d3a9e583ebaa85845daa21c4f81fdbf36def24db931aaef38636c53e
-sha256-linux=5c33dc395233671cb77452f8fb12900ecdbeb368632222b96835d310bce1aab8
+sha256-darwin=67251cb7d9978d38e899268cac4d7898297ff7e5b5c48c9c1546dc760b93568d
+sha256-linux=673da76c2e5710c4622fe2fa32d2b297730895769487fcf1152ee1c2366f32f4

.config/e2e-smoke-selection.txt

@@ -1 +1 @@
-sha256=00f8a56b75990b487a594b97c36610b94476a6944ba00473e37187ea654d42bf
+sha256=e9dc896774122a304e2b8b90f28c82d4d4e0af8ded36a82b147b30945ec994e3

.config/make/tests.mak

@@ -61,7 +61,6 @@ script-tests: ## Run shell script tests
 	$(RUSTFS_PYTHON_BIN) ./scripts/ci_gate.py --self-test
 	$(RUSTFS_PYTHON_BIN) ./scripts/check_connect_release_boundary.py --self-test
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_ci_test_artifact.py
-	$(RUSTFS_PYTHON_BIN) ./scripts/test_ci_test_shards.py
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_ci_merge_queue.py
 	$(RUSTFS_PYTHON_BIN) -m unittest discover -s scripts/ci -p 'test_*.py'
 	$(RUSTFS_PYTHON_BIN) ./scripts/check_security_coverage.py --self-test

.config/nextest.toml

@@ -234,7 +234,7 @@ test-group = 'embedded-test-ports'
 # processes cannot exhaust those budgets. Keep deadlines and assertions intact.
 # The short HTTP fixtures are tracked in rustfs/backlog#2714.
 [[profile.default.overrides]]
-filter = 'package(rustfs) & (binary(/^connect_registration$/) | binary(connect_inventory) | binary(connect_perf_drive) | (binary(connect_perf_client) & test(=configured_proxy_and_direct_endpoint_failures_are_distinct)) | (binary(connect_perf_object) & test(/^(real_rustfs_endpoint_and_production_cli_support_bounded_get_and_put|cleanup_uses_a_budget_independent_of_the_measurement_window|cleanup_accepts_missing_object_and_still_deletes_the_bucket|cleanup_diagnostics_identify_each_disconnected_transport_stage|cleanup_diagnostics_identify_each_failed_http_stage_without_private_context|cleanup_diagnostics_identify_timeouts_without_resetting_the_shared_deadline|oversized_response_is_rejected_without_buffering_it)$/)))'
+filter = 'package(rustfs) & (binary(/^connect_registration$/) | binary(connect_inventory) | binary(connect_perf_drive) | (binary(connect_perf_client) & test(=configured_proxy_and_direct_endpoint_failures_are_distinct)) | (binary(connect_perf_object) & test(/^(real_rustfs_endpoint_and_production_cli_support_bounded_get_and_put|cleanup_uses_a_budget_independent_of_the_measurement_window|oversized_response_is_rejected_without_buffering_it)$/)))'
 threads-required = "num-test-threads"
 
 # This cancellation probe hashes the serving executable before acquiring its
@@ -548,7 +548,7 @@ filter = 'package(rustfs) & (binary(/^embedded.*_test$/) | binary(admin_diagnost
 test-group = 'embedded-test-ports'
 
 [[profile.ci.overrides]]
-filter = 'package(rustfs) & (binary(/^connect_registration$/) | binary(connect_inventory) | binary(connect_perf_drive) | (binary(connect_perf_client) & test(=configured_proxy_and_direct_endpoint_failures_are_distinct)) | (binary(connect_perf_object) & test(/^(real_rustfs_endpoint_and_production_cli_support_bounded_get_and_put|cleanup_uses_a_budget_independent_of_the_measurement_window|cleanup_accepts_missing_object_and_still_deletes_the_bucket|cleanup_diagnostics_identify_each_disconnected_transport_stage|cleanup_diagnostics_identify_each_failed_http_stage_without_private_context|cleanup_diagnostics_identify_timeouts_without_resetting_the_shared_deadline|oversized_response_is_rejected_without_buffering_it)$/)))'
+filter = 'package(rustfs) & (binary(/^connect_registration$/) | binary(connect_inventory) | binary(connect_perf_drive) | (binary(connect_perf_client) & test(=configured_proxy_and_direct_endpoint_failures_are_distinct)) | (binary(connect_perf_object) & test(/^(real_rustfs_endpoint_and_production_cli_support_bounded_get_and_put|cleanup_uses_a_budget_independent_of_the_measurement_window|oversized_response_is_rejected_without_buffering_it)$/)))'
 threads-required = "num-test-threads"
 
 # Preserve the cancellation probe's startup budget and assertions in CI too.
@@ -827,7 +827,7 @@ slow-timeout = { period = "120s", terminate-after = 12, grace-period = "10s" }
 # ---------------------------------------------------------------------------
 # e2e-distributed profile — 4-node 4-disk Actions suite
 # ---------------------------------------------------------------------------
-# Nightly and manual-dispatch lane owned by
+# Storage-sensitive PR / nightly / dispatch lane owned by
 # .github/workflows/e2e-distributed.yml.
 # Each case starts four rustfs processes (and for site replication, two
 # clusters). Upgrade cases also require RUSTFS_UPGRADE_SOURCE_BINARY.
@@ -976,12 +976,6 @@ test-group = 'e2e-vault'
 filter = 'package(e2e_test) & (test(/^list_objects_v2_pagination_test::tests::(test_list_objects_v2_delimiter_small_page_traverses_all|test_list_objects_v2_max_keys_above_limit_returns_token|test_list_objects_v2_maxkeys_above_limit_with_delimiter)$/) | test(=reliant::tiering::test_hermetic_transition_restore_failure_expiry_and_retry))'
 threads-required = "num-test-threads"
 
-# The mc fixture uploads hundreds of objects concurrently before measuring listing.
-# Reserve the runner so other server fixtures do not starve its disk operations.
-[[profile.e2e-full.overrides]]
-filter = 'package(e2e_test) & test(=mc_mirror_small_bucket_test::test_mc_mirror_small_bucket_completes_without_list_timeout)'
-threads-required = "num-test-threads"
-
 # Fixed, small contract for every executable server change. These existing
 # scenarios exercise write/read, anonymous denial and retained bytes on restart.
 [profile.core-contract]

.config/release-validation-plan.json

@@ -1,77 +0,0 @@
-{
-  "schema_version": 1,
-  "plan_id": "rustfs-release-validation",
-  "description": "Versioned certification plan for every public RustFS release exit (rustfs/backlog#2662, R01). preview, prerelease and stable all require this explicit plan. Scripts/release/release_gate.py fail-closes publication on any missing, duplicate, stale, substituted or non-PASS required item.",
-  "release_types": ["preview", "prerelease", "stable"],
-  "targets": [
-    {"os": "linux", "arch": "x86_64", "abi": "musl"},
-    {"os": "linux", "arch": "aarch64", "abi": "musl"},
-    {"os": "linux", "arch": "x86_64", "abi": "gnu"},
-    {"os": "linux", "arch": "aarch64", "abi": "gnu"},
-    {"os": "macos", "arch": "aarch64", "abi": "none"},
-    {"os": "windows", "arch": "x86_64", "abi": "msvc"}
-  ],
-  "targets_basis": "Platform matrix of .github/workflows/build.yml (prepare-platform-matrix). gnu and macOS targets build with the pyroscope feature; musl and Windows targets build with no extra features.",
-  "features": ["pyroscope"],
-  "trusted_workflows": [
-    {"repository": "rustfs/s3chaos", "workflow_id": "release-gate.yml"}
-  ],
-  "trusted_workflows_basis": "The shared evidence envelope producer lives in rustfs/s3chaos (G01, fault/release_gate.rs) and its plan/live split workflow is .github/workflows/release-gate.yml there. Only results from these identities may enter a release certification; PR-uploaded JSON never gains release authority. R02 must extend this list when additional verifier workflows land, never widen it to untrusted sources.",
-  "lanes": [
-    {
-      "lane": "identity",
-      "harness_repository": "rustfs/s3chaos",
-      "harness_sha": "9a48f55c1d6d58ce63a8fb1ea7317e024f32f11d",
-      "harness_basis": "Fixed G01 evidence-envelope producer revision (rustfs/s3chaos PR #102 head recorded in rustfs/backlog#2658). R02 re-pins this when the live verifier ships.",
-      "timeout_seconds": 1800,
-      "environment_capabilities": ["process-exec"],
-      "cases": ["artifact-identity", "startup"],
-      "applies_to": {
-        "release_types": ["preview", "prerelease", "stable"],
-        "platforms": "all"
-      },
-      "applies_basis": "Artifact identity and startup checks are mandatory for every release type, preview included, on every shipped target (rustfs/backlog#2662 frozen design item 5)."
-    },
-    {
-      "lane": "upgrade",
-      "harness_repository": "rustfs/s3chaos",
-      "harness_sha": "9a48f55c1d6d58ce63a8fb1ea7317e024f32f11d",
-      "harness_basis": "Same fixed envelope producer as the identity lane; the workflow SHA and the product build SHA are bound separately and need not be equal.",
-      "timeout_seconds": 5400,
-      "environment_capabilities": ["process-exec", "previous-release-artifact"],
-      "cases": [
-        "direct-upgrade",
-        "mixed-version-upgrade",
-        "bucket-config-upgrade",
-        "bucket-config-rollback",
-        "multipart-layout-upgrade",
-        "multipart-layout-baseline"
-      ],
-      "cases_basis": "Case IDs of the pinned previous-release matrix in .github/workflows/e2e-upgrade.yml (source.version/asset/sha256 and the case list mapped there).",
-      "applies_to": {
-        "release_types": ["prerelease", "stable"],
-        "platforms": [{"os": "linux", "arch": "x86_64", "abi": "gnu"}]
-      },
-      "applies_basis": "preview releases use the pre-declared smaller set (identity lane only). The upgrade lane is only exercised on linux-x86_64-gnu, the platform of the pinned source assets."
-    }
-  ],
-  "upgrade_sources": {
-    "basis": "Exactly the two previous-release sources pinned in .github/workflows/e2e-upgrade.yml are exercised today (source.version / source.asset / source.sha256). No other N-1/N-2 compatibility is claimed, and these digests are not inferred from tags.",
-    "sources": [
-      {
-        "version": "1.0.1",
-        "role": "N-1",
-        "artifact_name": "rustfs-linux-x86_64-gnu-v1.0.1.zip",
-        "artifact_sha256": "9742e183cb0dfb0d48fa909797af572fe47b7f827569036baa4156e0d3958ee5"
-      },
-      {
-        "version": "1.0.0-rc.5",
-        "role": "N-2",
-        "artifact_name": "rustfs-linux-x86_64-gnu-v1.0.0-rc.5.zip",
-        "artifact_sha256": "3ee8df71e8edcfada533be452c4135868f697bc515460ae97b027313eade7a3d"
-      }
-    ],
-    "rollback_supported": false,
-    "rollback_basis": "Only the bucket-config-rollback case (rollback_to_previous_release_reads_current_bucket_metadata) is exercised. Full data-plane rollback is not certified and is never a default claim."
-  }
-}

.github/dependabot.yml

@@ -32,8 +32,6 @@ updates:
       - "overtrue"
       - "majinghe"
     ignore:
-      - dependency-name: "pulsar"
-        versions: [ "6.9.x" ]
       - dependency-name: "object_store"
         versions: [ "0.13.x" ]
       - dependency-name: "libunftp"

.github/scheduled-validations.json

@@ -296,32 +296,6 @@
       "origin": "baseline",
       "alert_contract": "scheduled-validation"
     },
-    {
-      "workflow": ".github/workflows/rustfs-validation-sweep.yml",
-      "name": "RustFS Validation Sweep",
-      "roles": [
-        "periodic",
-        "manual"
-      ],
-      "events": [
-        "schedule",
-        "workflow_dispatch"
-      ],
-      "cadence": "nightly",
-      "timezone": "UTC",
-      "schedule": [
-        "30 19 * * *"
-      ],
-      "owner": "@overtrue",
-      "policy": "active",
-      "monitor": "workflow",
-      "max_age_hours": 60,
-      "result_owner": "rustfs-validation-sweep.yml",
-      "disposition": "canonical validation cases executed in rotating batches",
-      "failure_owner": "workflow",
-      "origin": "baseline",
-      "alert_contract": "scheduled-validation"
-    },
     {
       "workflow": ".github/workflows/btf-prototype-reference.yml",
       "name": "BTF prototype reference",
@@ -769,10 +743,12 @@
       "workflow": ".github/workflows/e2e-distributed.yml",
       "name": "e2e-distributed",
       "roles": [
+        "pr",
         "periodic",
         "manual"
       ],
       "events": [
+        "pull_request",
         "workflow_dispatch",
         "schedule"
       ],
@@ -847,11 +823,12 @@
       "workflow": ".github/workflows/e2e-upgrade.yml",
       "name": "Upgrade Compatibility",
       "roles": [
+        "pr",
         "periodic",
-        "manual",
-        "release"
+        "manual"
       ],
       "events": [
+        "pull_request",
         "push",
         "schedule",
         "workflow_dispatch"

.github/workflows/build.yml

@@ -814,18 +814,13 @@ jobs:
           export AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY"
           export AWS_DEFAULT_REGION="auto"
 
-          # Determine upload path based on build type. Release and prerelease
-          # builds only stage their bytes here: the official
-          # artifacts/rustfs/release/ path is written solely by the
-          # certification-gated promote-release-artifacts job, from these same
-          # staged objects. Development builds keep the uncertified dev channel
-          # and never touch official or latest channels.
+          # Determine upload path based on build type
           if [[ "$BUILD_TYPE" == "development" ]]; then
             R2_PATH="s3://${R2_BUCKET}/artifacts/rustfs/dev/"
             echo "📤 Uploading development build to R2 dev directory"
           else
-            R2_PATH="s3://${R2_BUCKET}/artifacts/rustfs/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}/"
-            echo "📤 Staging release build for certification-gated promotion"
+            R2_PATH="s3://${R2_BUCKET}/artifacts/rustfs/release/"
+            echo "📤 Uploading release build to R2 release directory"
           fi
 
           # Upload all rustfs zip files to R2 using S3-compatible API
@@ -874,221 +869,6 @@ jobs:
             echo "This run does not trigger Docker publishing."
           fi
 
-  # Aggregate the parent candidate batch. This job always collects results and
-  # retains its evidence, including on failure, and every publication job
-  # below requires its success. Missing, stale, substituted or non-PASS
-  # evidence fails closed here: only the trusted verification sources
-  # (rustfs/s3chaos release-gate envelopes, rustfs/backlog#2658) can satisfy
-  # it, so a PR-uploaded JSON set never gains release authority.
-  release-certification:
-    name: Release Certification
-    needs: [ build-check, build-rustfs ]
-    if: ${{ !cancelled() && needs.build-check.outputs.should_publish == 'true' && startsWith(github.ref, 'refs/tags/') }}
-    runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Download all build artifacts
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          path: ./artifacts
-          pattern: rustfs-*
-          merge-multiple: true
-
-      - name: Write candidate and collect trusted validation results
-        env:
-          # Cross-repo read of the trusted verification run. Falls back to the
-          # workflow token, which cannot read rustfs/s3chaos; a missing token
-          # therefore fail-closes instead of certifying.
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          PRODUCT_COMMIT: ${{ github.sha }}
-          VERSION: ${{ needs.build-check.outputs.version }}
-          BUILD_TYPE: ${{ needs.build-check.outputs.build_type }}
-          FEATURES: ${{ needs.build-check.outputs.build_type == 'development' && '' || 'pyroscope' }}
-        shell: bash
-        run: |
-          set -euo pipefail
-
-          mkdir -p results release-gate-output
-          PLAN_SHA256=$(python3 -c "import hashlib,json,sys; sys.path.insert(0,'scripts/release'); import release_gate; print(release_gate.canonical_sha256(json.load(open('.config/release-validation-plan.json'))))")
-
-          python3 - "$PLAN_SHA256" > candidate.json <<'PY'
-          import hashlib, json, os, sys, zipfile
-
-          plan_sha256 = sys.argv[1]
-          profile = {"release": "stable", "prerelease": "prerelease", "preview": "preview"}.get(os.environ["BUILD_TYPE"])
-          if profile is None:
-              raise SystemExit("release certification only covers preview, prerelease and stable builds")
-
-          def sha256(path):
-              digest = hashlib.sha256()
-              with open(path, "rb") as handle:
-                  for chunk in iter(lambda: handle.read(1024 * 1024), b""):
-                      digest.update(chunk)
-              return digest.hexdigest()
-
-          deliverables = []
-          for name in sorted(os.listdir("artifacts")):
-              if not name.startswith("rustfs-") or not name.endswith(".zip"):
-                  continue
-              path = os.path.join("artifacts", name)
-              members = zipfile.ZipFile(path).namelist()
-              binary_name = "rustfs.exe" if "rustfs.exe" in members else "rustfs"
-              with zipfile.ZipFile(path) as archive:
-                  binary_bytes = archive.read(binary_name)
-              import tempfile
-              with tempfile.NamedTemporaryFile() as handle:
-                  handle.write(binary_bytes)
-                  handle.flush()
-                  binary_sha = sha256(handle.name)
-              deliverables.append({
-                  "kind": "zip",
-                  "name": name,
-                  "location": "https://github.com/rustfs/rustfs/releases/download/{}/{}".format(os.environ["VERSION"], name),
-                  "sha256": sha256(path),
-                  "size": os.path.getsize(path),
-                  "binary_sha256": binary_sha,
-              })
-          if not deliverables:
-              raise SystemExit("no built deliverables found to certify")
-          candidate = {
-              "schema_version": 1,
-              "product_commit": os.environ["PRODUCT_COMMIT"],
-              "version": os.environ["VERSION"],
-              "release_profile": profile,
-              "features": [f for f in os.environ.get("FEATURES", "").split(",") if f],
-              "plan_sha256": plan_sha256,
-              "validation_batch": {"run_id": os.environ["GITHUB_RUN_ID"], "run_attempt": int(os.environ["GITHUB_RUN_ATTEMPT"])},
-              "deliverables": deliverables,
-          }
-          json.dump(candidate, sys.stdout, indent=2, sort_keys=True)
-          print()
-          PY
-
-          # Trusted verification evidence only: the release-gate envelopes of
-          # rustfs/s3chaos for this exact product commit. Absence blocks below.
-          TRUSTED_REPO="rustfs/s3chaos"
-          TRUSTED_WORKFLOW="release-gate.yml"
-          TRUSTED_RUN=$(gh api "repos/${TRUSTED_REPO}/actions/workflows/${TRUSTED_WORKFLOW}/runs?head_sha=${PRODUCT_COMMIT}&status=success&per_page=1" --jq '.workflow_runs[0].id // empty' || true)
-          if [[ -z "$TRUSTED_RUN" ]]; then
-            echo "❌ No trusted verification run of ${TRUSTED_REPO}/${TRUSTED_WORKFLOW} for ${PRODUCT_COMMIT}; refusing to certify" >&2
-          else
-            gh run download "$TRUSTED_RUN" -R "$TRUSTED_REPO" -n release-validation-evidence -D results || \
-              echo "❌ Trusted verification run ${TRUSTED_RUN} published no release-validation-evidence artifact" >&2
-          fi
-
-          python3 scripts/release/release_gate.py validate \
-            --plan .config/release-validation-plan.json \
-            --candidate candidate.json \
-            --results results \
-            --output release-gate-output
-
-      - name: Upload certification evidence
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: release-certification
-          path: |
-            candidate.json
-            results/
-            release-gate-output/
-          if-no-files-found: warn
-          retention-days: 30
-
-  # The only writer of the official R2 release path. Promotion re-checks the
-  # exact bytes about to be published against the passed certification list
-  # and copies the staged objects byte-for-byte: no rebuild-after-verify.
-  promote-release-artifacts:
-    name: Promote Release Artifacts
-    needs: [ build-check, build-rustfs, release-certification ]
-    # Target-channel lock for the official R2 release path.
-    concurrency:
-      group: release-channel-r2-release
-      cancel-in-progress: false
-    if: needs.build-check.outputs.should_publish == 'true' && startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    env:
-      R2_ACCESS_KEY_ID: ${{ secrets.R2_ACCESS_KEY_ID }}
-      R2_SECRET_ACCESS_KEY: ${{ secrets.R2_SECRET_ACCESS_KEY }}
-      R2_ENDPOINT: ${{ secrets.R2_ENDPOINT }}
-      R2_BUCKET: ${{ secrets.R2_BUCKET }}
-      AWS_EC2_METADATA_DISABLED: true
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Download build and certification artifacts
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          path: ./artifacts
-          pattern: rustfs-*
-          merge-multiple: true
-
-      - name: Download certification evidence
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: release-certification
-          path: ./certification
-
-      - name: Verify and promote staged release artifacts
-        shell: bash
-        run: |
-          set -euo pipefail
-
-          if [[ -z "$R2_ACCESS_KEY_ID" || -z "$R2_SECRET_ACCESS_KEY" || -z "$R2_ENDPOINT" || -z "$R2_BUCKET" ]]; then
-            echo "❌ R2 credentials missing; refusing to promote to the official channel" >&2
-            exit 1
-          fi
-
-          for zip_file in artifacts/rustfs-*.zip; do
-            [[ -f "$zip_file" ]] || continue
-            name="$(basename "$zip_file")"
-            python3 scripts/release/release_gate.py verify-promotion \
-              --plan .config/release-validation-plan.json \
-              --candidate certification/candidate.json \
-              --summary certification/release-gate-output \
-              --artifact "$zip_file" \
-              --artifact-name "$name"
-          done
-
-          if ! command -v aws >/dev/null 2>&1; then
-            sudo apt-get update && sudo apt-get install -y awscli
-          fi
-          export AWS_ACCESS_KEY_ID="$R2_ACCESS_KEY_ID"
-          export AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY"
-          export AWS_DEFAULT_REGION="auto"
-
-          STAGING_PATH="s3://${R2_BUCKET}/artifacts/rustfs/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}/"
-          RELEASE_PATH="s3://${R2_BUCKET}/artifacts/rustfs/release/"
-          for zip_file in artifacts/rustfs-*.zip; do
-            [[ -f "$zip_file" ]] || continue
-            name="$(basename "$zip_file")"
-            staged="$(mktemp)"
-            aws s3 cp "${STAGING_PATH}${name}" "$staged" --endpoint-url "$R2_ENDPOINT" --only-show-errors
-            staged_sha="$(sha256sum "$staged" | awk '{print $1}')"
-            built_sha="$(sha256sum "$zip_file" | awk '{print $1}')"
-            if [[ "$staged_sha" != "$built_sha" ]]; then
-              echo "❌ Staged object ${name} does not match the verified bytes" >&2
-              exit 1
-            fi
-            aws s3 cp "$staged" "${RELEASE_PATH}${name}" --endpoint-url "$R2_ENDPOINT" --only-show-errors
-            rm -f "$staged"
-            echo "✅ Promoted ${name} (${built_sha})"
-          done
-
   # Create GitHub Release for every valid release tag, including previews
   create-release:
     name: Create GitHub Release
@@ -1248,10 +1028,6 @@ jobs:
   update-latest-version:
     name: Update Latest Version
     needs: [ build-check, publish-release ]
-    # Target-channel lock for the latest.json version pointer.
-    concurrency:
-      group: release-channel-oss-latest
-      cancel-in-progress: false
     if: needs.build-check.outputs.should_publish == 'true' && startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
     runs-on: ubuntu-latest
     timeout-minutes: 30
@@ -1292,45 +1068,6 @@ jobs:
           rm -rf "$OSSUTIL_DIR" "$OSSUTIL_ZIP"
           chmod +x "$OSSUTIL_BIN"
 
-          # Candidate/pointer ordering: an older candidate must never overwrite
-          # a newer pointer, even if its promotion job finishes later.
-          CURRENT_LATEST="${RUNNER_TEMP}/current-latest.json"
-          if "$OSSUTIL_BIN" cp oss://rustfs-version/latest.json "$CURRENT_LATEST" 2>/dev/null; then
-            python3 - "$CURRENT_LATEST" "$VERSION" <<'PY'
-          import json
-          import re
-          import sys
-
-          def key(version):
-              match = re.match(r"^(\d+)\.(\d+)\.(\d+)(?:-([0-9A-Za-z.-]+))?$", version)
-              if not match:
-                  raise SystemExit(3)
-              core = tuple(int(part) for part in match.groups()[:3])
-              prerelease = match.group(4)
-              if prerelease is None:
-                  return core + (1,)
-              return core + (0, tuple(int(p) if p.isdigit() else p for p in re.split(r"[.-]", prerelease)))
-
-          try:
-              current = json.load(open(sys.argv[1], encoding="utf-8")).get("version", "")
-              proposed = sys.argv[2]
-              if current and key(current) > key(proposed):
-                  raise SystemExit(1)
-          except SystemExit:
-              raise
-          except (OSError, ValueError, TypeError):
-              raise SystemExit(3)
-          PY
-            guard_status=$?
-            if [[ "$guard_status" -eq 1 ]]; then
-              echo "Current latest.json points at a newer version; refusing to downgrade" >&2
-              exit 0
-            elif [[ "$guard_status" -ne 0 ]]; then
-              echo "Existing latest.json is unparsable; refusing to overwrite it blindly" >&2
-              exit 1
-            fi
-          fi
-
           # Create latest.json
           cat > latest.json << EOF
           {
@@ -1347,59 +1084,16 @@ jobs:
 
           echo "✅ Updated latest.json for ${RELEASE_TYPE} release $VERSION"
 
-  # Publish release (remove draft status). Requires the release-certification
-  # aggregate: without a complete legal success there is no public write.
+  # Publish release (remove draft status)
   publish-release:
     name: Publish Release
-    needs: [ build-check, create-release, upload-release-assets, release-certification ]
-    # Target-channel lock: concurrent releases serialize on this channel so an
-    # older candidate cannot interleave its publish with a newer one.
-    concurrency:
-      group: release-channel-github-release
-      cancel-in-progress: false
+    needs: [ build-check, create-release, upload-release-assets ]
     if: needs.build-check.outputs.should_publish == 'true' && startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'preview' || needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
     runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
     timeout-minutes: 30
     permissions:
       contents: write
-      actions: read
     steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Download certification evidence
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: release-certification
-          path: ./certification
-
-      - name: Verify release assets against certification
-        env:
-          GH_TOKEN: ${{ github.token }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          TAG="${{ needs.build-check.outputs.version }}"
-          mkdir -p "$RUNNER_TEMP/promotion-assets"
-          gh release download "$TAG" --dir "$RUNNER_TEMP/promotion-assets" --pattern '*.zip'
-          found=0
-          for zip_file in "$RUNNER_TEMP"/promotion-assets/*.zip; do
-            [[ -f "$zip_file" ]] || continue
-            found=1
-            python3 scripts/release/release_gate.py verify-promotion \
-              --plan .config/release-validation-plan.json \
-              --candidate certification/candidate.json \
-              --summary certification/release-gate-output \
-              --artifact "$zip_file" \
-              --artifact-name "$(basename "$zip_file")"
-          done
-          if [[ "$found" -ne 1 ]]; then
-            echo "No release zip assets to verify against the certification" >&2
-            exit 1
-          fi
-
       - name: Publish release
         env:
           GH_TOKEN: ${{ github.token }}

.github/workflows/cache-warm.yml

@@ -96,7 +96,7 @@ env:
   RUST_BACKTRACE: 1
 
 jobs:
-  # Readers: workspace-lint-and-build, workspace-tests (workspace and ILM), build-rustfs-debug-binary,
+  # Readers: test-and-lint (workspace and ILM), build-rustfs-debug-binary,
   # e2e-tests, e2e-full.
   warm-ci-dev:
     name: Warm ci-dev
@@ -146,7 +146,7 @@ jobs:
           if-no-files-found: error
 
       # --all-targets covers the test binaries nextest builds, including
-      # e2e_test, which the workspace run excludes. The second build adds
+      # e2e_test, which test-and-lint's own run excludes. The second build adds
       # the e2e-test-hooks feature resolution that build-rustfs-debug-binary uses
       # and that no lint lane enables.
       - name: Build ci-dev superset

.github/workflows/ci.yml

@@ -44,11 +44,6 @@ on:
   schedule:
     - cron: "11 0 * * *" # Nightly 00:11 UTC, after the 22:41 UTC cache-warm run
   workflow_dispatch:
-    inputs:
-      rehearse_workspace_shards:
-        description: Compare one full execution with at most two resource-safe shards of the same archive
-        type: boolean
-        default: false
 
 permissions:
   contents: read
@@ -92,7 +87,6 @@ jobs:
       connect: ${{ steps.scope.outputs.connect || 'true' }}
       packages: ${{ steps.scope.outputs.packages }}
       full_validation: ${{ steps.scope.outputs.full_validation || 'true' }}
-      rehearse_shards: ${{ steps.scope.outputs.rehearse_shards || 'false' }}
     steps:
       - uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
         with:
@@ -103,7 +97,6 @@ jobs:
         env:
           CI_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.merge_group.base_sha || github.event.before }}
           CI_EVENT_ACTION: ${{ github.event.action }}
-          CI_REHEARSE_SHARDS: ${{ inputs.rehearse_workspace_shards && 'true' || 'false' }}
         run: |
           if [[ "$GITHUB_EVENT_NAME" != "pull_request" ]]; then
             python3 -I scripts/ci_gate.py select
@@ -113,9 +106,9 @@ jobs:
             printf '%s\n' 'mode=full' >> "$GITHUB_OUTPUT"
             echo "Base CI policy unavailable; running the full matrix."
           fi
-          if ! grep -q '^plan=' "$GITHUB_OUTPUT" || ! grep -q '^plan_contract=3$' "$GITHUB_OUTPUT"; then
-            printf '%s\n' 'mode=full' 'connect=true' 'full_validation=true' 'rehearse_shards=false' 'packages=' 'plan=' >> "$GITHUB_OUTPUT"
-            echo "Base policy does not cover this workflow contract; retaining the full matrix."
+          if ! grep -q '^plan=' "$GITHUB_OUTPUT"; then
+            printf '%s\n' 'mode=full' 'connect=true' 'full_validation=true' >> "$GITHUB_OUTPUT"
+            echo "Legacy policy has no verification plan; retaining the full matrix."
           fi
       - name: Retain verification plan
         if: steps.scope.outputs.plan != ''
@@ -160,7 +153,7 @@ jobs:
       - name: Run shared quick checks
         uses: ./.github/actions/quick-checks
 
-  workspace-lint-and-build:
+  test-and-lint:
     name: Workspace Lint and Build
     if: contains(fromJSON('["full", "e2e"]'), needs.classify-changes.outputs.mode) && (github.event_name != 'pull_request' || github.event.action != 'closed')
     needs: [ quick-checks, classify-changes ]
@@ -193,13 +186,13 @@ jobs:
 
       - name: Prepare test evidence
         run: |
-          mkdir -p artifacts/workspace
+          mkdir -p artifacts/test-and-lint
           {
             echo "run_id=${GITHUB_RUN_ID}"
             echo "job=${GITHUB_JOB}"
             echo "runner=${RUNNER_NAME}"
             echo "started_at=$(date --utc --iso-8601=seconds)"
-          } > artifacts/workspace/run-metadata.txt
+          } > artifacts/test-and-lint/run-metadata.txt
 
       # Clippy gates every event, pull requests included. When it ran only after
       # merge, a lint regression merged freely and then failed every main run
@@ -224,8 +217,7 @@ jobs:
       - name: Upload workspace test binaries
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: workspace-test-binaries
-          overwrite: true
+          name: workspace-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}/workspace-tests.tar.zst*
           compression-level: 0
           if-no-files-found: error
@@ -233,11 +225,11 @@ jobs:
 
       - name: Run documentation tests
         run: |
-          mkdir -p artifacts/workspace
+          mkdir -p artifacts/test-and-lint
           set +e
           timeout --verbose --signal=TERM --kill-after=30s 15m \
             python3 scripts/ci_test_artifact.py cargo doc --configuration workspace \
-            2>&1 | tee artifacts/workspace/doctest.log
+            2>&1 | tee artifacts/test-and-lint/doctest.log
           status=${PIPESTATUS[0]}
           {
             echo "command=cargo test --all --exclude e2e_test --doc"
@@ -246,7 +238,7 @@ jobs:
             echo
             echo "Remaining test-related processes:"
             pgrep -af 'cargo|rustdoc|target/.*/deps/' || true
-          } > artifacts/workspace/doctest-diagnostics.txt
+          } > artifacts/test-and-lint/doctest-diagnostics.txt
           exit "${status}"
 
       - name: Upload test reports and diagnostics
@@ -255,7 +247,7 @@ jobs:
         with:
           name: junit-test-and-lint-${{ github.run_number }}-${{ github.run_attempt }}
           path: |
-            artifacts/workspace
+            artifacts/test-and-lint
           retention-days: 3
           if-no-files-found: error
 
@@ -268,13 +260,11 @@ jobs:
 
   workspace-tests:
     name: Workspace tests
-    needs: [ workspace-lint-and-build, classify-changes ]
+    needs: [ test-and-lint, classify-changes ]
     # The archive retains compile-time fixture paths and the large test set
     # requires the same runner image until the hosted-runtime pilot passes.
     runs-on: sm-standard-4
     timeout-minutes: 90
-    outputs:
-      workspace_shards: ${{ steps.shards.outputs.workspace_shards || '[]' }}
     env:
       CI_PACKAGES: ${{ needs.classify-changes.outputs.packages }}
     steps:
@@ -286,21 +276,21 @@ jobs:
         run: chmod go-w "$(realpath "$HOME")"
       - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: workspace-test-binaries
+          name: workspace-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}
       - name: Verify workspace archive identity
         run: python3 scripts/ci_test_artifact.py verify --configuration workspace --archive "$RUNNER_TEMP/workspace-tests.tar.zst"
 
       - name: Extract and list workspace tests
         run: |
-          mkdir -p artifacts/workspace
+          mkdir -p artifacts/test-and-lint
           cargo nextest list --profile ci --archive-file "$RUNNER_TEMP/workspace-tests.tar.zst" --workspace-remap "$GITHUB_WORKSPACE" --extract-to "$GITHUB_WORKSPACE" --extract-overwrite --message-format json \
-            > artifacts/workspace/core-test-listing.json
-          python3 scripts/check_test_wiring.py --check-core artifacts/workspace/core-test-listing.json
+            > artifacts/test-and-lint/core-test-listing.json
+          python3 scripts/check_test_wiring.py --check-core artifacts/test-and-lint/core-test-listing.json
 
       - name: Run nextest tests
         run: |
-          mkdir -p artifacts/workspace
+          mkdir -p artifacts/test-and-lint
           rm -f target/nextest/ci/junit.xml
           ./scripts/ci/resource_sampler.sh start nextest
           trap './scripts/ci/resource_sampler.sh stop' EXIT
@@ -309,7 +299,7 @@ jobs:
             cargo nextest run --profile ci --cargo-metadata target/nextest/cargo-metadata.json --binaries-metadata target/nextest/binaries-metadata.json \
             --workspace-remap "$GITHUB_WORKSPACE" --target-dir-remap "$GITHUB_WORKSPACE/target" \
             --status-level all --final-status-level all \
-            2>&1 | tee artifacts/workspace/nextest.log
+            2>&1 | tee artifacts/test-and-lint/nextest.log
           status=${PIPESTATUS[0]}
           {
             echo "command=workspace archive execution"
@@ -321,13 +311,13 @@ jobs:
             echo
             echo "Kernel OOM / kill events:"
             dmesg -T 2>/dev/null | grep -iE 'oom|out of memory|killed process' | tail -20 || true
-          } > artifacts/workspace/nextest-diagnostics.txt
+          } > artifacts/test-and-lint/nextest-diagnostics.txt
           exit "${status}"
 
       - name: Verify workspace execution completeness
         run: |
-          python3 scripts/ci_test_artifact.py evidence artifacts/workspace/core-test-listing.json target/nextest/ci/junit.xml
-          ./scripts/check_migration_gate_count.sh evidence artifacts/workspace/core-test-listing.json target/nextest/ci/junit.xml
+          python3 scripts/ci_test_artifact.py evidence artifacts/test-and-lint/core-test-listing.json target/nextest/ci/junit.xml
+          ./scripts/check_migration_gate_count.sh evidence artifacts/test-and-lint/core-test-listing.json target/nextest/ci/junit.xml
 
       - name: Run ignored ILM integration tests serially
         if: needs.classify-changes.outputs.mode == 'full'
@@ -358,98 +348,14 @@ jobs:
           name: workspace-test-evidence-${{ github.run_attempt }}
           path: |
             target/nextest/ci/junit.xml
-            artifacts/workspace
+            artifacts/test-and-lint
             artifacts/ilm-integration
           retention-days: 3
           if-no-files-found: error
 
-      - name: Prepare bounded shards from this candidate's observed durations
-        id: shards
-        if: needs.classify-changes.outputs.rehearse_shards == 'true'
-        run: |
-          python3 scripts/ci_test_shards.py prepare \
-            --listing artifacts/workspace/core-test-listing.json \
-            --junit target/nextest/ci/junit.xml --output artifacts/workspace-shard-plan
-      - name: Upload same-run shard plan
-        if: needs.classify-changes.outputs.rehearse_shards == 'true'
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: workspace-shard-plan-${{ github.run_attempt }}
-          path: artifacts/workspace-shard-plan
-          retention-days: 3
-          if-no-files-found: error
-
-  workspace-shards:
-    name: Workspace shards (${{ matrix.shard }})
-    if: needs.classify-changes.outputs.rehearse_shards == 'true'
-    needs: [classify-changes, workspace-tests]
-    # Reuse the producer image and checkout path for the full RustFS archive.
-    runs-on: sm-standard-4
-    timeout-minutes: 90
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-      matrix:
-        shard: ${{ fromJSON(needs.workspace-tests.outputs.workspace_shards || '[]') }}
-    env:
-      CI_PACKAGES: ${{ needs.classify-changes.outputs.packages }}
-    steps:
-      - uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-      - uses: ./.github/actions/test-runtime
-      - name: Protect Connect test home
-        run: chmod go-w "$(realpath "$HOME")"
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: workspace-test-binaries-${{ github.run_attempt }}
-          path: ${{ runner.temp }}
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: workspace-shard-plan-${{ github.run_attempt }}
-          path: artifacts/workspace-shard-plan
-      - name: Verify and execute this shard without compilation
-        env:
-          SHARD_INDEX: ${{ matrix.shard }}
-        run: |
-          python3 scripts/ci_test_artifact.py verify --configuration workspace --archive "$RUNNER_TEMP/workspace-tests.tar.zst"
-          python3 scripts/ci_test_shards.py execute --plan artifacts/workspace-shard-plan \
-            --archive "$RUNNER_TEMP/workspace-tests.tar.zst" --index "$SHARD_INDEX" --output artifacts/workspace-shard-result
-      - name: Retain shard evidence including failures
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: workspace-shard-result-${{ matrix.shard }}-${{ github.run_attempt }}
-          path: artifacts/workspace-shard-result
-          retention-days: 3
-          if-no-files-found: error
-
-  workspace-shard-evidence:
-    name: Workspace shard completeness
-    if: always() && needs.classify-changes.outputs.rehearse_shards == 'true'
-    needs: [classify-changes, workspace-tests, workspace-shards]
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    steps:
-      - uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: workspace-shard-plan-${{ github.run_attempt }}
-          path: artifacts/workspace-shard-plan
-      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          pattern: workspace-shard-result-*-${{ github.run_attempt }}
-          path: artifacts/workspace-shards
-      - name: Require the exact union of successful shard executions
-        run: |
-          python3 scripts/ci_test_shards.py verify --plan artifacts/workspace-shard-plan --evidence artifacts/workspace-shards
-          ./scripts/check_migration_gate_count.sh evidence artifacts/workspace-shard-plan/listing.json artifacts/workspace-shards/combined.xml
-
   connect-feature-boundaries:
     name: Connect Feature Boundaries
-    if: needs.classify-changes.outputs.mode == 'full' && needs.classify-changes.outputs.connect != 'false' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
+    if: needs.classify-changes.outputs.mode == 'full' && needs.classify-changes.outputs.connect != 'false' && (github.event_name != 'pull_request' || github.event.action != 'closed')
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -497,72 +403,13 @@ jobs:
       - name: Check offline enrollment E2E root boundary
         run: ./scripts/check_offline_enrollment_e2e.sh
 
-  fips-provider:
-    name: FIPS provider boundaries
-    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
-    needs: [ quick-checks, classify-changes ]
-    # This builds the RustFS library test target, which exceeds hosted-runner disk capacity.
-    runs-on: sm-standard-4
-    timeout-minutes: 90
-    strategy:
-      fail-fast: false
-      matrix:
-        mode: [default, fips]
-    env:
-      FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
-      CARGO_BUILD_JOBS: "2"
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Setup Rust environment
-        uses: ./.github/actions/setup
-        with:
-          rust-version: stable
-          cache-shared-key: ci-fips-provider
-          cache-save-if: 'false'
-          install-build-packaging-tools: 'false'
-
-      - name: Install FIPS build tools
-        if: matrix.mode == 'fips'
-        run: sudo apt-get install -y cmake golang clang libclang-dev
-
-      - name: Verify provider installation
-        shell: bash
-        run: |
-          args=()
-          if [[ '${{ matrix.mode }}' == 'fips' ]]; then
-            args+=(--features fips)
-          fi
-          cargo nextest run --locked -p rustfs-tls-runtime --lib "${args[@]}" --no-tests fail -E 'test(provider_policy_isolated)'
-          cargo nextest run --locked -p rustfs-s3-client --lib "${args[@]}" --no-tests fail -E 'test(overflowing_closed_range_is_rejected_before_network_io)'
-          cargo nextest run --locked -p rustfs-targets --lib "${args[@]}" --no-tests fail -E 'test(validate_pulsar)'
-          cargo nextest run --locked -p rustfs-targets --lib "${args[@]}" --no-tests fail -E 'test(webhook_provider_policy_isolated)'
-          if [[ '${{ matrix.mode }}' == 'fips' ]]; then
-            cargo nextest run --locked -p rustfs-protocols --lib --features ftps,webdav,fips --no-tests fail -E 'test(protocols_reject_incompatible_host_provider)'
-            cargo nextest run --locked -p rustfs-targets --lib --features fips --no-tests fail -E 'test(fips_postgres_rejects_incompatible_host_provider)'
-            cargo nextest run --locked -p rustfs-s3-client --lib --features fips --no-tests fail -E 'test(fips_transition_rejects_incompatible_host_provider)'
-          fi
-          tests=(provider_installation_isolated prepared_generation_shares_crypto_and_serves_sni_with_mtls)
-          if [[ '${{ matrix.mode }}' == 'fips' ]]; then
-            tests+=(fips_provider_builds_fips_tls_configs fips_provider_tls_handshake_accepts_and_rejects_algorithms)
-          fi
-          for test_name in "${tests[@]}"; do
-            cargo nextest run --locked -p rustfs --lib "${args[@]}" --no-tests fail -E "test($test_name)"
-          done
-          cargo clippy --locked -p rustfs --lib "${args[@]}" -- -D warnings
-
   test-and-lint-rio-v2:
     name: Test and Lint (rio-v2)
-    # Specialized boundary, hardware and alternate-feature lanes run only on
-    # the nightly schedule and manual dispatch. They do not gate a merge: the
-    # nightly run reports a regression within a day, and repeating these builds
-    # on every PR revision and merge group bought no earlier signal worth the
-    # runner occupancy. Workspace lint and tests, the core contract, the debug
-    # build, E2E smoke and the S3 lanes remain the pull-request gate.
-    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
+    # Alternate feature configurations run on the nightly schedule, merge
+    # groups and manual dispatch. The default workspace remains the PR gate and
+    # the per-push main baseline: repeating four feature builds on every merge
+    # bought nothing the nightly run does not report within a day.
+    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["merge_group", "schedule", "workflow_dispatch"]'), github.event_name)
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -599,12 +446,12 @@ jobs:
           # --profile ci so the quarantine list (and its junit flaky markers)
           # covers this leg too; the default profile is the local no-retry
           # profile and silently ignored quarantined flakes here (rustfs#6703).
-          mkdir -p artifacts/workspace
+          mkdir -p artifacts/test-and-lint
           rm -f target/nextest/ci/junit.xml
           ./scripts/ci/resource_sampler.sh start nextest-rio-v2
           trap './scripts/ci/resource_sampler.sh stop' EXIT
           cargo nextest run --profile ci -p rustfs -p rustfs-ecstore --features rio-v2 \
-            2>&1 | tee artifacts/workspace/nextest.log
+            2>&1 | tee artifacts/test-and-lint/nextest.log
           cargo test -p rustfs --doc --features rio-v2
 
       - name: Upload rio-v2 test reports and diagnostics
@@ -614,14 +461,14 @@ jobs:
           name: junit-test-and-lint-rio-v2-${{ github.run_number }}-${{ github.run_attempt }}
           path: |
             target/nextest/ci/junit.xml
-            artifacts/workspace
+            artifacts/test-and-lint
           retention-days: 3
           if-no-files-found: error
 
   test-and-lint-protocols:
     name: "Test and Lint (${{ matrix.features.name }})"
     # Same cadence as test-and-lint-rio-v2 above.
-    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
+    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["merge_group", "schedule", "workflow_dispatch"]'), github.event_name)
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -690,7 +537,7 @@ jobs:
           path: |
             target/nextest/ci/junit.xml
             artifacts/protocol-tests
-            artifacts/workspace
+            artifacts/test-and-lint
           retention-days: 3
           if-no-files-found: warn
 
@@ -766,8 +613,7 @@ jobs:
       - name: Upload debug binary
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: rustfs-debug-binary
-          overwrite: true
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: |
             target/debug/rustfs
             target/debug/rustfs.e2e.json
@@ -786,8 +632,7 @@ jobs:
       - name: Upload E2E test binaries
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: e2e-test-binaries
-          overwrite: true
+          name: e2e-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}/e2e-tests.tar.zst*
           compression-level: 0
           if-no-files-found: error
@@ -826,8 +671,7 @@ jobs:
       - name: Upload debug binary
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
-          name: rustfs-debug-binary-rio-v2
-          overwrite: true
+          name: rustfs-debug-binary-rio-v2-${{ github.run_attempt }}
           path: |
             target/debug/rustfs
             target/debug/rustfs.e2e.json
@@ -842,7 +686,7 @@ jobs:
     # job had neither, so each closed/merged PR really ran the whole io_uring
     # suite (measured 4m17s / 7m19s / 7m31s on runs 30678272341 / 30678117601 /
     # 30662728539) and kept the cancellation run in progress for minutes.
-    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
+    if: needs.classify-changes.outputs.mode == 'full' && (github.event_name != 'pull_request' || github.event.action != 'closed')
     needs: [ quick-checks, classify-changes ]
     # GitHub-hosted ubuntu-latest runs a recent kernel with io_uring and, unlike
     # a container, applies no seccomp filter that would block io_uring_setup — so
@@ -923,11 +767,11 @@ jobs:
       - uses: ./.github/actions/test-runtime
       - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: target/debug
       - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: e2e-test-binaries
+          name: e2e-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}
       - name: Run core storage and authorization contract
         env:
@@ -968,7 +812,7 @@ jobs:
       - name: Download E2E test binaries
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: e2e-test-binaries
+          name: e2e-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}
 
       - name: Verify E2E archive identity
@@ -992,7 +836,7 @@ jobs:
       - name: Download debug binary
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: target/debug
 
       - name: Make binary executable
@@ -1037,7 +881,7 @@ jobs:
           path: |
             ${{ runner.temp }}/rustfs-e2e-smoke-logs/
             ${{ runner.temp }}/rustfs-e2e-smoke-list.json
-            artifacts/workspace
+            artifacts/test-and-lint
           if-no-files-found: warn
 
       - name: Upload e2e smoke JUnit report
@@ -1104,7 +948,7 @@ jobs:
       - name: Download E2E test binaries
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: e2e-test-binaries
+          name: e2e-test-binaries-${{ github.run_attempt }}
           path: ${{ runner.temp }}
 
       - name: Verify E2E archive identity
@@ -1166,7 +1010,7 @@ jobs:
       - name: Download debug binary
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: target/debug
 
       - name: Make binary executable
@@ -1278,7 +1122,7 @@ jobs:
       - name: Download debug binary
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary-rio-v2
+          name: rustfs-debug-binary-rio-v2-${{ github.run_attempt }}
           path: target/debug
 
       - name: Make binary executable
@@ -1329,7 +1173,7 @@ jobs:
       - name: Download debug binary
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: target/debug
 
       - name: Make binary executable
@@ -1403,7 +1247,7 @@ jobs:
       - name: Download debug binary
         uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
-          name: rustfs-debug-binary
+          name: rustfs-debug-binary-${{ github.run_attempt }}
           path: target/debug
 
       - name: Make binary executable
@@ -1448,13 +1292,10 @@ jobs:
       - classify-changes
       - typos
       - quick-checks
-      - workspace-lint-and-build
+      - test-and-lint
       - workspace-tests
-      - workspace-shards
-      - workspace-shard-evidence
       - core-contract
       - connect-feature-boundaries
-      - fips-provider
       - test-and-lint-rio-v2
       - test-and-lint-protocols
       - build-rustfs-debug-binary
@@ -1482,11 +1323,10 @@ jobs:
     needs:
       - classify-changes
       - connect-feature-boundaries
-      - fips-provider
       - required-checks
       - typos
       - quick-checks
-      - workspace-lint-and-build
+      - test-and-lint
       - workspace-tests
       - core-contract
       - test-and-lint-rio-v2

.github/workflows/docker.yml

@@ -329,75 +329,13 @@ jobs:
           echo "  - Create latest: $create_latest"
           echo "  - Source ref: $source_ref"
 
-  # Consume the trusted release certification for the exact version this
-  # workflow wraps and verify the certified input digests. A manual dispatch
-  # without that certification fails here and pushes no official tag; only
-  # results from the trusted verification sources carry release authority.
-  release-certification:
-    name: Release Certification
-    needs: build-check
-    if: needs.build-check.outputs.should_build == 'true'
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-          ref: ${{ needs.build-check.outputs.source_ref }}
-
-      - name: Download and verify release certification
-        env:
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          TRIGGERING_RUN_ID: ${{ github.event.workflow_run.id }}
-          VERSION: ${{ needs.build-check.outputs.version }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          mkdir -p certification
-          run_id="$TRIGGERING_RUN_ID"
-          if [[ -z "$run_id" ]]; then
-            run_id="$(gh api --method GET \
-              "repos/${GITHUB_REPOSITORY}/actions/workflows/build.yml/runs" \
-              -f branch="$VERSION" -f status=success -F per_page=1 \
-              --jq '.workflow_runs[0].id // empty' || true)"
-          fi
-          if [[ -z "$run_id" ]]; then
-            echo "No certified Build and Release run found for ${VERSION}; failing closed" >&2
-            exit 1
-          fi
-          if ! gh run download "$run_id" -n release-certification -D certification; then
-            echo "Build run ${run_id} published no release-certification artifact; failing closed" >&2
-            exit 1
-          fi
-          python3 scripts/release/release_gate.py verify-promotion \
-            --plan .config/release-validation-plan.json \
-            --candidate certification/candidate.json \
-            --summary certification/release-gate-output \
-            --artifact-sha256 "$(jq -r '.deliverables[0].sha256' certification/candidate.json)" \
-            --artifact-name "$(jq -r '.deliverables[0].name' certification/candidate.json)"
-
-          # Input digest binding: every zip this image wraps must be the
-          # certified byte-for-byte content, never a mutable latest pointer.
-          while IFS=$'\t' read -r name location expected; do
-            echo "Verifying certified input ${name}"
-            actual="$(curl -fsSL "$location" | sha256sum | awk '{print $1}')"
-            if [[ "$actual" != "$expected" ]]; then
-              echo "Certified input ${name} does not match its recorded digest" >&2
-              exit 1
-            fi
-          done < <(jq -r '.deliverables[] | select(.name | contains("linux")) | [.name, .location, .sha256] | @tsv' certification/candidate.json)
-
   # Build multi-arch Docker images
   # Strategy: Build images using pre-built binaries from dl.rustfs.com
   # Supports both release and dev channel binaries based on build context
   # Only runs when should_build is true (which includes workflow success check)
   build-docker:
     name: Build Docker Images
-    needs: [ build-check, release-certification ]
+    needs: build-check
     if: needs.build-check.outputs.should_build == 'true'
     runs-on: ubuntu-latest
     timeout-minutes: 60
@@ -505,14 +443,6 @@ jobs:
           # Output tags
           echo "tags=$TAGS" >> "$GITHUB_OUTPUT"
 
-          # Staging identity for this run's promotion: official tags are only
-          # created after the staged image verifies against the certification,
-          # and they point at this same digest (no rebuild-after-verify).
-          STAGING_TAG="staging-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}${VARIANT_SUFFIX}"
-          STAGING_TAGS="${{ env.REGISTRY_DOCKERHUB }}:${STAGING_TAG},${{ env.REGISTRY_GHCR }}:${STAGING_TAG},${{ env.REGISTRY_QUAY }}:${STAGING_TAG}"
-          echo "staging_tags=$STAGING_TAGS" >> "$GITHUB_OUTPUT"
-          echo "staging_tag=$STAGING_TAG" >> "$GITHUB_OUTPUT"
-
           # Generate labels
           LABELS="org.opencontainers.image.title=RustFS"
           LABELS="$LABELS,org.opencontainers.image.description=RustFS distributed object storage system"
@@ -537,9 +467,7 @@ jobs:
           file: ${{ matrix.file }}
           platforms: ${{ env.DOCKER_PLATFORMS }}
           push: ${{ needs.build-check.outputs.should_push == 'true' }}
-          # Push to staging tags only: official tags are created by the
-          # certification-gated promotion step below from this same digest.
-          tags: ${{ steps.meta.outputs.staging_tags }}
+          tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
           # No layer cache. This build compiles nothing — it downloads a
           # release zip and runs apk/apt — so the cache could only save the
@@ -565,114 +493,6 @@ jobs:
           no-cache: false
           pull: true
 
-      # A later-built wrapper: the staged image must complete this platform's
-      # own binary identity verification before any official tag is written.
-      # It may not inherit an unverified package's conclusion.
-      - name: Verify staged image against certification
-        if: needs.build-check.outputs.should_push == 'true'
-        env:
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          TRIGGERING_RUN_ID: ${{ github.event.workflow_run.id }}
-          VERSION: ${{ needs.build-check.outputs.version }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          mkdir -p certification
-          run_id="$TRIGGERING_RUN_ID"
-          if [[ -z "$run_id" ]]; then
-            run_id="$(gh api --method GET \
-              "repos/${GITHUB_REPOSITORY}/actions/workflows/build.yml/runs" \
-              -f branch="$VERSION" -f status=success -F per_page=1 \
-              --jq '.workflow_runs[0].id // empty' || true)"
-          fi
-          gh run download "$run_id" -n release-certification -D certification
-
-          STAGING_REF="${{ env.REGISTRY_DOCKERHUB }}:staging-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}${{ matrix.suffix }}"
-          case "${{ matrix.variant }}" in
-            musl) libc="musl" ;;
-            glibc) libc="gnu" ;;
-          esac
-          for platform in linux/amd64 linux/arm64; do
-            case "$platform" in
-              linux/amd64) arch_sub="x86_64" ;;
-              linux/arm64) arch_sub="aarch64" ;;
-            esac
-            docker pull --platform "$platform" "$STAGING_REF"
-            container="$(docker create --platform "$platform" "$STAGING_REF")"
-            docker cp "$container:/usr/bin/rustfs" "$RUNNER_TEMP/staged-rustfs"
-            docker rm "$container" >/dev/null
-            actual="$(sha256sum "$RUNNER_TEMP/staged-rustfs" | awk '{print $1}')"
-            expected="$(jq -r --arg needle "linux-${arch_sub}-${libc}" \
-              '[.deliverables[] | select(.name | contains($needle)) | .binary_sha256][0] // empty' \
-              certification/candidate.json)"
-            if [[ -z "$expected" || "$actual" != "$expected" ]]; then
-              echo "Staged image binary for ${platform} does not match the certified binary digest" >&2
-              exit 1
-            fi
-            python3 scripts/release/release_gate.py verify-promotion \
-              --plan .config/release-validation-plan.json \
-              --candidate certification/candidate.json \
-              --summary certification/release-gate-output \
-              --artifact "$RUNNER_TEMP/staged-rustfs" \
-              --artifact-role binary
-          done
-
-      - name: Promote staged image to official tags
-        if: needs.build-check.outputs.should_push == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-          STAGING_REF="${{ env.REGISTRY_DOCKERHUB }}:staging-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}${{ matrix.suffix }}"
-          IFS=',' read -r -a official_tags <<< "${{ steps.meta.outputs.tags }}"
-          for tag in "${official_tags[@]}"; do
-            docker buildx imagetools create -t "$tag" "$STAGING_REF"
-            echo "Promoted $tag -> $STAGING_REF"
-          done
-
-      # Downstream consumers (Helm) verify this record instead of inheriting
-      # an unverified wrapper's conclusion.
-      - name: Record image promotion
-        if: needs.build-check.outputs.should_push == 'true'
-        shell: bash
-        env:
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          TRIGGERING_RUN_ID: ${{ github.event.workflow_run.id }}
-          VERSION: ${{ needs.build-check.outputs.version }}
-        run: |
-          set -euo pipefail
-          mkdir -p certification
-          run_id="$TRIGGERING_RUN_ID"
-          if [[ -z "$run_id" ]]; then
-            run_id="$(gh api --method GET \
-              "repos/${GITHUB_REPOSITORY}/actions/workflows/build.yml/runs" \
-              -f branch="$VERSION" -f status=success -F per_page=1 \
-              --jq '.workflow_runs[0].id // empty' || true)"
-          fi
-          gh run download "$run_id" -n release-certification -D certification
-          STAGING_REF="${{ env.REGISTRY_DOCKERHUB }}:staging-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}${{ matrix.suffix }}"
-          digest="$(docker buildx imagetools inspect "$STAGING_REF" --format '{{json .Manifest}}' | jq -r '.digest')"
-          candidate_sha="$(python3 -c "import json,hashlib,sys; sys.path.insert(0,'scripts/release'); import release_gate; print(release_gate.canonical_sha256(json.load(open('certification/candidate.json'))))")"
-          jq -n \
-            --arg version "$VERSION" \
-            --arg digest "$digest" \
-            --arg staging_ref "$STAGING_REF" \
-            --arg candidate_sha256 "$candidate_sha" \
-            --arg tags "${{ steps.meta.outputs.tags }}" \
-            --slurpfile candidate certification/candidate.json \
-            '{schema_version: 1, version: $version, image_digest: $digest, staging_ref: $staging_ref,
-              promoted_tags: ($tags | split(",")), candidate_sha256: $candidate_sha256,
-              binary_sha256s: ($candidate[0].deliverables | map(.binary_sha256) | unique)}' \
-            > image-promotion-record.json
-
-      - name: Upload image promotion record
-        if: needs.build-check.outputs.should_push == 'true'
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: image-promotion-record${{ matrix.suffix }}
-          path: image-promotion-record.json
-          if-no-files-found: error
-          retention-days: 30
-
   # Note: Manifest creation is no longer needed as we only build one variant
   # Multi-arch manifests are automatically created by docker/build-push-action
 

.github/workflows/e2e-distributed.yml

@@ -17,8 +17,8 @@
 # Each selected test starts a real localhost cluster via
 # `RustFSTestClusterEnvironment` (4 processes; 4 drives per node unless the
 # case is a two-site 4-node 1-drive pair or a 4-node upgrade). Membership is
-# `[profile.e2e-distributed]` in `.config/nextest.toml`. The nightly schedule
-# and manual dispatches execute the same fail-closed suite.
+# `[profile.e2e-distributed]` in `.config/nextest.toml`. Storage-sensitive PRs,
+# nightly runs, and manual dispatches all execute the same fail-closed suite.
 # Upgrade cases download the same pinned previous release as e2e-upgrade.yml.
 #
 # Isolated pool filesystems: expand/decommission/rebalance cases require
@@ -33,6 +33,32 @@
 name: e2e-distributed
 
 on:
+  pull_request:
+    paths:
+      - "Cargo.lock"
+      - "Cargo.toml"
+      - ".config/nextest.toml"
+      - ".config/e2e-distributed-selection.txt"
+      - ".github/workflows/e2e-distributed.yml"
+      - "crates/audit/**"
+      - "crates/common/**"
+      - "crates/config/**"
+      - "crates/e2e_test/**"
+      - "crates/ecstore/**"
+      - "crates/filemeta/**"
+      - "crates/heal/**"
+      - "crates/iam/**"
+      - "crates/lock/**"
+      - "crates/madmin/**"
+      - "crates/notify/**"
+      - "crates/replication/**"
+      - "crates/s3-client/**"
+      - "crates/s3-ops/**"
+      - "crates/s3-types/**"
+      - "crates/scanner/**"
+      - "crates/storage-api/**"
+      - "crates/utils/**"
+      - "rustfs/**"
   workflow_dispatch:
     inputs:
       filter:

.github/workflows/e2e-upgrade.yml

@@ -12,19 +12,30 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Single-node upgrade and rollback lane.
-#
-# The weekly Monday schedule, version tags, and workflow_dispatch run this
-# suite. Distributed upgrade cases stay on the nightly e2e-distributed lane.
-
 name: Upgrade Compatibility
 
 on:
+  pull_request:
+    paths:
+      - ".github/workflows/e2e-upgrade.yml"
+      - "crates/e2e_test/src/common.rs"
+      - "crates/e2e_test/src/distributed/**"
+      - "crates/e2e_test/src/fake_s3_target/**"
+      - "crates/e2e_test/src/lib.rs"
+      - "crates/e2e_test/src/replication_extension_test.rs"
+      - "crates/e2e_test/src/rpc_fault_proxy.rs"
+      - "crates/e2e_test/src/upgrade_compatibility_test.rs"
+      - "crates/ecstore/**"
+      - "crates/filemeta/**"
+      - "crates/heal/**"
+      - "crates/kms/**"
+      - "crates/storage-api/**"
+      - "rustfs/**"
+      - "Cargo.lock"
   push:
     tags:
       - "[0-9]*.[0-9]*.[0-9]*"
   schedule:
-    # 03:17 UTC every Monday.
     - cron: "17 3 * * 1"
   workflow_dispatch:
 
@@ -33,7 +44,7 @@ permissions:
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: false
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
 
 env:
   CARGO_TERM_COLOR: always

.github/workflows/helm-package.yml

@@ -30,102 +30,9 @@ permissions:
   contents: read
 
 jobs:
-  # Consume the same trusted release certification as every other publication
-  # exit and verify the image promotion record of the Docker workflow. The
-  # chart wraps no binary of its own, so it may only reference an image whose
-  # platform verification already passed; it must not inherit an unverified
-  # package's conclusion. A run without that evidence fails closed here and
-  # never reaches the chart repository.
-  release-certification:
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    outputs:
-      version: ${{ steps.version.outputs.raw_tag }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Normalize release version
-        id: version
-        env:
-          RAW_INPUT: ${{ github.event.inputs.version }}
-          RAW_BRANCH: ${{ github.event.workflow_run.head_branch }}
-        run: |
-          set -euo pipefail
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            RAW="$RAW_INPUT"
-          else
-            RAW="$RAW_BRANCH"
-          fi
-          case "$RAW" in
-            refs/tags/*) RAW_TAG="${RAW#refs/tags/}" ;;
-            *) RAW_TAG="$RAW" ;;
-          esac
-          echo "raw_tag=$RAW_TAG" >> "$GITHUB_OUTPUT"
-
-      - name: Download and verify release certification and image record
-        env:
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          TRIGGERING_RUN_ID: ${{ github.event.workflow_run.id }}
-          RAW_TAG: ${{ steps.version.outputs.raw_tag }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          mkdir -p certification image-record
-
-          build_run="$TRIGGERING_RUN_ID"
-          if [[ -z "$build_run" ]]; then
-            build_run="$(gh api --method GET \
-              "repos/${GITHUB_REPOSITORY}/actions/workflows/build.yml/runs" \
-              -f branch="$RAW_TAG" -f status=success -F per_page=1 \
-              --jq '.workflow_runs[0].id // empty' || true)"
-          fi
-          if [[ -z "$build_run" ]]; then
-            echo "No certified Build and Release run found for ${RAW_TAG}; failing closed" >&2
-            exit 1
-          fi
-          if ! gh run download "$build_run" -n release-certification -D certification; then
-            echo "Build run ${build_run} published no release-certification artifact; failing closed" >&2
-            exit 1
-          fi
-          python3 scripts/release/release_gate.py verify-promotion \
-            --plan .config/release-validation-plan.json \
-            --candidate certification/candidate.json \
-            --summary certification/release-gate-output \
-            --artifact-sha256 "$(jq -r '.deliverables[0].sha256' certification/candidate.json)" \
-            --artifact-name "$(jq -r '.deliverables[0].name' certification/candidate.json)"
-
-          docker_run="$(gh api --method GET \
-            "repos/${GITHUB_REPOSITORY}/actions/workflows/docker.yml/runs" \
-            -f branch="$RAW_TAG" -f status=success -F per_page=1 \
-            --jq '.workflow_runs[0].id // empty' || true)"
-          if [[ -z "$docker_run" ]] || ! gh run download "$docker_run" -n image-promotion-record -D image-record; then
-            echo "No image promotion record for ${RAW_TAG}; a chart may not wrap an unverified image" >&2
-            exit 1
-          fi
-          candidate_sha="$(python3 -c "import json,hashlib,sys; sys.path.insert(0,'scripts/release'); import release_gate; print(release_gate.canonical_sha256(json.load(open('certification/candidate.json'))))")"
-          record_sha="$(jq -r '.candidate_sha256 // empty' image-record/image-promotion-record.json)"
-          if [[ "$record_sha" != "$candidate_sha" ]]; then
-            echo "Image promotion record does not belong to this certification" >&2
-            exit 1
-          fi
-          overlap="$(jq -r --slurpfile candidate certification/candidate.json \
-            '[.binary_sha256s[]] - ($candidate[0].deliverables | map(.binary_sha256)) | length' \
-            image-record/image-promotion-record.json)"
-          if [[ "$overlap" -ne 0 ]]; then
-            echo "Image promotion record carries binary digests outside the certification" >&2
-            exit 1
-          fi
-
   build-helm-package:
     runs-on: ubuntu-latest
     timeout-minutes: 30
-    needs: [ release-certification ]
     if: |
       (github.event_name == 'workflow_dispatch' && !contains(github.event.inputs.version, '-preview')) ||
       (

.github/workflows/nightly-gnu.yml

@@ -346,12 +346,12 @@ jobs:
           path: ${{ steps.publish.outputs.candidate_file }}
           if-no-files-found: error
 
+      # Publish the deb/rpm pair to the auto-testing repo's `assets` branch so
+      # engineers can download and install the nightly directly. The branch is
+      # a single-commit orphan rewritten on every build, which keeps the repo
+      # small while the latest files stay reachable at stable raw URLs.
       # Publish the deb/rpm pair as assets of the rolling `nightly` release on
       # rustfs/auto-testing (see scripts/release/publish_nightly_assets.sh).
-      # The dispatch below runs only after this upload and the immutable R2
-      # candidate both succeed. It does not replace rustfs-functional-chain.yml,
-      # which still starts from this workflow's workflow_run completion.
-      # kms-vault-lane and kms-vault-ha-failover stay parallel with this job.
       - name: Publish packages to auto-testing release assets
         env:
           ASSETS_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
@@ -360,90 +360,6 @@ jobs:
           DEB_DATE: ${{ steps.deb.outputs.deb_date }}
           BUILD_REF: ${{ env.NIGHTLY_BUILD_REF }}
         run: bash scripts/release/publish_nightly_assets.sh
-
-      # Cross-repo repository_dispatch cannot use GITHUB_TOKEN. The secret is a
-      # PAT or GitHub App token for rustfs/auto-testing: classic `repo` scope,
-      # or fine-grained Contents write (the permission GitHub checks for
-      # POST /repos/{owner}/{repo}/dispatches). A dispatch failure fails this
-      # step, and therefore this job, so the scheduled failure alert fires.
-      # GitHub allows at most 10 top-level client_payload properties, so the
-      # schema 2 candidate object is nested under `candidate` and the release
-      # fields sit beside it.
-      - name: Dispatch nightly candidate to auto-testing
-        if: ${{ steps.publish.outputs.candidate_file != '' }}
-        env:
-          DISPATCH_TOKEN: ${{ secrets.AUTO_TESTING_DISPATCH_TOKEN }}
-          CANDIDATE_FILE: ${{ steps.publish.outputs.candidate_file }}
-          DEB_DATE: ${{ steps.deb.outputs.deb_date }}
-          SOURCE_REPO: ${{ github.repository }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          : "${DISPATCH_TOKEN:?AUTO_TESTING_DISPATCH_TOKEN is required to dispatch rustfs/auto-testing}"
-          : "${CANDIDATE_FILE:?nightly candidate manifest is required}"
-          : "${DEB_DATE:?DEB_DATE is required}"
-          [[ "${DEB_DATE}" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]
-          [[ "${SOURCE_REPO}" == "rustfs/rustfs" ]]
-
-          payload="${RUNNER_TEMP}/nightly-candidate-dispatch-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}.json"
-          jq -n --slurpfile candidate "${CANDIDATE_FILE}" \
-            --arg event_type "nightly-candidate-ready" \
-            --arg source_repo "${SOURCE_REPO}" \
-            --arg latest_alias_url "https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb" \
-            --arg auto_testing_release "https://github.com/rustfs/auto-testing/releases/tag/nightly" \
-            --arg channel "nightly" \
-            --arg deb_date "${DEB_DATE}" \
-            --arg nightly_workflow ".github/workflows/nightly-gnu.yml" \
-            '{
-              event_type: $event_type,
-              source_repo: $source_repo,
-              latest_alias_url: $latest_alias_url,
-              auto_testing_release: $auto_testing_release,
-              channel: $channel,
-              deb_date: $deb_date,
-              nightly_workflow: $nightly_workflow,
-              candidate: $candidate[0]
-            }' > "${payload}"
-          if ! jq -e '
-            .event_type == "nightly-candidate-ready"
-            and .source_repo == "rustfs/rustfs"
-            and .channel == "nightly"
-            and .deb_date == env.DEB_DATE
-            and .nightly_workflow == ".github/workflows/nightly-gnu.yml"
-            and .latest_alias_url == "https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb"
-            and .auto_testing_release == "https://github.com/rustfs/auto-testing/releases/tag/nightly"
-            and .candidate.schema == 2
-            and ((.candidate | keys | sort) == ["build_run_attempt","build_run_id","package_sha256","package_url","schema","source_ref","source_sha","workflow_sha"])
-            and ((keys | sort) == ["auto_testing_release","candidate","channel","deb_date","event_type","latest_alias_url","nightly_workflow","source_repo"])
-          ' "${payload}" >/dev/null; then
-            echo "nightly dispatch payload does not match the nightly-candidate-ready contract" >&2
-            exit 1
-          fi
-
-          body="${RUNNER_TEMP}/nightly-candidate-dispatch-body-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}.json"
-          jq -n --slurpfile client_payload "${payload}" \
-            '{event_type: "nightly-candidate-ready", client_payload: $client_payload[0]}' > "${body}"
-          response="${RUNNER_TEMP}/nightly-candidate-dispatch-response-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}.txt"
-          status="$(curl -sS --retry 3 --connect-timeout 15 --max-time 60 \
-            -o "${response}" -w '%{http_code}' \
-            -X POST \
-            -H "Authorization: Bearer ${DISPATCH_TOKEN}" \
-            -H "Accept: application/vnd.github+json" \
-            -H "X-GitHub-Api-Version: 2022-11-28" \
-            -H "Content-Type: application/json" \
-            --data-binary @"${body}" \
-            https://api.github.com/repos/rustfs/auto-testing/dispatches)" || {
-            echo "repository_dispatch request to rustfs/auto-testing failed before an HTTP status" >&2
-            exit 1
-          }
-          if [[ "${status}" != "204" ]]; then
-            echo "repository_dispatch to rustfs/auto-testing failed: HTTP ${status}" >&2
-            if [[ -s "${response}" ]]; then
-              cat "${response}" >&2
-            fi
-            exit 1
-          fi
-          echo "dispatched nightly-candidate-ready to rustfs/auto-testing (deb_date=${DEB_DATE}, run=${GITHUB_RUN_ID}, attempt=${GITHUB_RUN_ATTEMPT})"
   # Live-Vault lane for the rustfs-kms suite (rustfs/backlog#1774).
   #
   # RUSTFS_KMS_VAULT_TOKEN is the single switch that adds the Vault KV2 and

.github/workflows/package.yml

@@ -225,57 +225,10 @@ jobs:
           echo "  Build run ID: $BUILD_RUN_ID"
           echo "  Build run number: $RUN_NUMBER"
 
-  # Consume the trusted release certification of the resolved build run and
-  # verify the certified input digests before any package is wrapped. A run
-  # without that certification fails closed here; packages built later must
-  # complete their own verification and cannot inherit an unverified
-  # conclusion.
-  release-certification:
-    name: Release Certification
-    needs: resolve
-    if: needs.resolve.result == 'success'
-    runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Download and verify release certification
-        env:
-          GH_TOKEN: ${{ secrets.RELEASE_VALIDATION_TOKEN || github.token }}
-          BUILD_RUN_ID: ${{ needs.resolve.outputs.build_run_id }}
-          BUILD_TYPE: ${{ needs.resolve.outputs.build_type }}
-        shell: bash
-        run: |
-          set -euo pipefail
-          mkdir -p certification
-          if [[ "$BUILD_TYPE" == "development" ]]; then
-            # Development artifacts are explicitly uncertified and never touch
-            # official or latest channels; only the staging/dev paths remain.
-            jq -n '{schema_version: 1, certified: false, reason: "development artifacts are explicitly uncertified"}' \
-              > certification/development-uncertified.json
-            exit 0
-          fi
-          if ! gh run download "$BUILD_RUN_ID" -n release-certification -D certification; then
-            echo "Build run ${BUILD_RUN_ID} published no release-certification artifact; failing closed" >&2
-            exit 1
-          fi
-          python3 scripts/release/release_gate.py verify-promotion \
-            --plan .config/release-validation-plan.json \
-            --candidate certification/candidate.json \
-            --summary certification/release-gate-output \
-            --artifact-sha256 "$(jq -r '.deliverables[0].sha256' certification/candidate.json)" \
-            --artifact-name "$(jq -r '.deliverables[0].name' certification/candidate.json)"
-
   # Build DEB and RPM packages for each architecture and libc variant
   package:
     name: Package (${{ matrix.arch }}-${{ matrix.libc }})
-    needs: [ resolve, release-certification ]
+    needs: resolve
     runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
     timeout-minutes: 30
     strategy:
@@ -541,55 +494,6 @@ jobs:
           echo "rpm_file=$RPM_FILE" >> "$GITHUB_OUTPUT"
           echo "✅ RPM built: $RPM_FILE"
 
-      - name: Download certification evidence
-        if: needs.resolve.outputs.build_type != 'development'
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: release-certification
-          path: ./certification
-
-      # Later-built wrapper verification: the binary inside each package must
-      # match the certified binary digest for this platform before anything is
-      # uploaded, and the package itself stays on staging until promotion.
-      - name: Verify wrapped binary against certification
-        if: needs.resolve.outputs.build_type != 'development'
-        shell: bash
-        env:
-          DEB_FILE: ${{ steps.deb.outputs.deb_file }}
-          RPM_FILE: ${{ steps.rpm.outputs.rpm_file }}
-          ARTIFACT_NAME: ${{ matrix.artifact_name }}
-        run: |
-          set -euo pipefail
-          expected="$(jq -r --arg needle "$ARTIFACT_NAME" \
-            '[.deliverables[] | select(.name | contains($needle)) | .binary_sha256][0] // empty' \
-            certification/candidate.json)"
-          if [[ -z "$expected" ]]; then
-            echo "No certified binary digest recorded for ${ARTIFACT_NAME}" >&2
-            exit 1
-          fi
-          if ! command -v rpm2cpio >/dev/null 2>&1; then
-            sudo apt-get update && sudo apt-get install -y rpm2cpio
-          fi
-          if ! command -v cpio >/dev/null 2>&1; then
-            sudo apt-get update && sudo apt-get install -y cpio
-          fi
-          for package_file in "$DEB_FILE" "$RPM_FILE"; do
-            case "$package_file" in
-              *.deb)
-                dpkg-deb --fsys-tarfile "$package_file" | tar -xOf - ./usr/bin/rustfs > "$RUNNER_TEMP/wrapped-rustfs"
-                ;;
-              *.rpm)
-                rpm2cpio "$package_file" | cpio -i --to-stdout ./usr/bin/rustfs > "$RUNNER_TEMP/wrapped-rustfs"
-                ;;
-            esac
-            python3 scripts/release/release_gate.py verify-promotion \
-              --plan .config/release-validation-plan.json \
-              --candidate certification/candidate.json \
-              --summary certification/release-gate-output \
-              --artifact "$RUNNER_TEMP/wrapped-rustfs" \
-              --artifact-role binary
-          done
-
       - name: Upload packages to artifacts
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
@@ -627,14 +531,10 @@ jobs:
           export AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY"
           export AWS_DEFAULT_REGION="auto"
 
-          # Build-phase writes stay on staging for release types: the official
-          # packages/release and packages/latest paths are written only by the
-          # certification-gated promote-packages job, from these same staged
-          # objects. Development packages keep the uncertified dev channel.
           if [[ "$BUILD_TYPE" == "development" ]]; then
             R2_PREFIX="artifacts/rustfs/packages/dev"
           else
-            R2_PREFIX="artifacts/rustfs/packages/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}"
+            R2_PREFIX="artifacts/rustfs/packages/release"
           fi
           R2_PATH="s3://${R2_BUCKET}/${R2_PREFIX}/"
 
@@ -649,6 +549,18 @@ jobs:
 
           echo "✅ Upload complete"
 
+          # Also upload as latest for release/prerelease
+          if [[ "$BUILD_TYPE" == "release" || "$BUILD_TYPE" == "prerelease" ]]; then
+            LATEST_PATH="s3://${R2_BUCKET}/artifacts/rustfs/packages/latest/"
+            for f in "$DEB_FILE" "$RPM_FILE"; do
+              if [[ -n "$f" && -f "$f" ]]; then
+                echo "Uploading latest: $(basename "$f")"
+                aws s3 cp "$f" "$LATEST_PATH" --endpoint-url "$R2_ENDPOINT" --only-show-errors
+              fi
+            done
+            echo "✅ Latest packages updated"
+          fi
+
       - name: Upload packages to GitHub Release
         if: needs.resolve.outputs.tag != ''
         env:
@@ -702,114 +614,6 @@ jobs:
 
           echo "✅ GitHub release assets updated"
 
-  # The only writer of the official packages/release and packages/latest R2
-  # paths. Promotion re-checks each package's wrapped binary against the
-  # passed certification list and copies the staged objects byte-for-byte:
-  # no rebuild-after-verify, no mutable latest resolution downstream.
-  promote-packages:
-    name: Promote Packages
-    needs: [ resolve, package, release-certification ]
-    # Target-channel lock for the official package paths.
-    concurrency:
-      group: release-channel-r2-packages
-      cancel-in-progress: false
-    if: needs.resolve.outputs.tag != '' && (needs.resolve.outputs.build_type == 'release' || needs.resolve.outputs.build_type == 'prerelease')
-    runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
-    timeout-minutes: 30
-    permissions:
-      contents: read
-      actions: read
-    env:
-      R2_ACCESS_KEY_ID: ${{ secrets.R2_ACCESS_KEY_ID }}
-      R2_SECRET_ACCESS_KEY: ${{ secrets.R2_SECRET_ACCESS_KEY }}
-      R2_ENDPOINT: ${{ secrets.R2_ENDPOINT }}
-      R2_BUCKET: ${{ secrets.R2_BUCKET }}
-      AWS_EC2_METADATA_DISABLED: true
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Download packages and certification
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          path: ./packages
-          pattern: packages-*
-          merge-multiple: true
-
-      - name: Download certification evidence
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: release-certification
-          path: ./certification
-
-      - name: Verify and promote staged packages
-        shell: bash
-        run: |
-          set -euo pipefail
-
-          if [[ -z "$R2_ACCESS_KEY_ID" || -z "$R2_SECRET_ACCESS_KEY" || -z "$R2_ENDPOINT" || -z "$R2_BUCKET" ]]; then
-            echo "❌ R2 credentials missing; refusing to promote to the official channel" >&2
-            exit 1
-          fi
-
-          STAGING_PREFIX="s3://${R2_BUCKET}/artifacts/rustfs/packages/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}/"
-          RELEASE_PATH="s3://${R2_BUCKET}/artifacts/rustfs/packages/release/"
-          LATEST_PATH="s3://${R2_BUCKET}/artifacts/rustfs/packages/latest/"
-
-          if ! command -v aws >/dev/null 2>&1; then
-            sudo apt-get update && sudo apt-get install -y awscli
-          fi
-          export AWS_ACCESS_KEY_ID="$R2_ACCESS_KEY_ID"
-          export AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY"
-          export AWS_DEFAULT_REGION="auto"
-
-          if ! command -v rpm2cpio >/dev/null 2>&1; then
-            sudo apt-get install -y rpm2cpio
-          fi
-          if ! command -v cpio >/dev/null 2>&1; then
-            sudo apt-get install -y cpio
-          fi
-
-          promoted=0
-          for package_file in packages/*.deb packages/*.rpm; do
-            [[ -f "$package_file" ]] || continue
-            name="$(basename "$package_file")"
-            case "$package_file" in
-              *.deb)
-                dpkg-deb --fsys-tarfile "$package_file" | tar -xOf - ./usr/bin/rustfs > "$RUNNER_TEMP/wrapped-rustfs"
-                ;;
-              *.rpm)
-                rpm2cpio "$package_file" | cpio -i --to-stdout ./usr/bin/rustfs > "$RUNNER_TEMP/wrapped-rustfs"
-                ;;
-            esac
-            python3 scripts/release/release_gate.py verify-promotion \
-              --plan .config/release-validation-plan.json \
-              --candidate certification/candidate.json \
-              --summary certification/release-gate-output \
-              --artifact "$RUNNER_TEMP/wrapped-rustfs" \
-              --artifact-role binary
-
-            staged="$(mktemp)"
-            aws s3 cp "${STAGING_PREFIX}${name}" "$staged" --endpoint-url "$R2_ENDPOINT" --only-show-errors
-            staged_sha="$(sha256sum "$staged" | awk '{print $1}')"
-            built_sha="$(sha256sum "$package_file" | awk '{print $1}')"
-            if [[ "$staged_sha" != "$built_sha" ]]; then
-              echo "❌ Staged package ${name} does not match the verified bytes" >&2
-              exit 1
-            fi
-            aws s3 cp "$staged" "${RELEASE_PATH}${name}" --endpoint-url "$R2_ENDPOINT" --only-show-errors
-            aws s3 cp "$staged" "${LATEST_PATH}${name}" --endpoint-url "$R2_ENDPOINT" --only-show-errors
-            rm -f "$staged"
-            promoted=$((promoted + 1))
-            echo "✅ Promoted ${name} (${built_sha})"
-          done
-          if [[ "$promoted" -eq 0 ]]; then
-            echo "No staged packages found to promote" >&2
-            exit 1
-          fi
-
   # Summary
   summary:
     name: Summary

.github/workflows/rustfs-fault-tolerance-test.yml

@@ -197,21 +197,21 @@ jobs:
           jq -e --arg testing_sha "${AUTO_TESTING_SHA}" '
             .schema_version == 1 and
             .auto_testing_sha == $testing_sha and
-            .selected_scenarios == ["A", "B", "C", "C2", "D", "E", "F"] and
+            .selected_scenarios == ["A", "B", "C", "C2", "D", "E"] and
             .complete == true and
-            .counts.expected == 54 and
-            .counts.seen == 54 and
+            .counts.expected == 44 and
+            .counts.seen == 44 and
             .counts.harness_errors == 0 and
-            (.expected_cases | length) == 54 and
-            (.expected_cases | unique | length) == 54 and
-            (.seen_cases | length) == 54 and
-            (.seen_cases | unique | length) == 54 and
+            (.expected_cases | length) == 44 and
+            (.expected_cases | unique | length) == 44 and
+            (.seen_cases | length) == 44 and
+            (.seen_cases | unique | length) == 44 and
             (.seen_cases | sort) == (.expected_cases | sort) and
             (.missing_cases | length) == 0 and
             (.harness_errors | length) == 0 and
-            (.cases | length) == 54 and
+            (.cases | length) == 44 and
             ([.cases[].case_id] | sort) == (.expected_cases | sort) and
-            ([.cases[].case_id] | unique | length) == 54 and
+            ([.cases[].case_id] | unique | length) == 44 and
             all(.cases[]; .verdict == "pass" or .verdict == "known-divergence" or .verdict == "UNEXPECTED") and
             .counts.unexpected == ([.cases[] | select(.verdict == "UNEXPECTED")] | length) and
             .counts.known_divergence == ([.cases[] | select(.verdict == "known-divergence")] | length)

.github/workflows/rustfs-functional-chain.yml

@@ -281,20 +281,12 @@ jobs:
           GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
           PERFORMANCE_OPTIONAL: ${{ contains(fromJSON(steps.selection.outputs.optional_suites), 'performance') }}
         run: |
-          # TEMPORARY: the pf-testing environment is broken, so the
-          # performance lane is disabled until it is repaired. Forcing
-          # offline keeps the chain on its designed skip path: the lane job
-          # is skipped, aggregate receives --allow-skipped performance
-          # (required=false in scheduled-validations.json), and the report
-          # records the optional-lane skip with its reason.
-          # Restore the probe below once the environment is healthy again.
-          # if python3 scripts/check_functional_runners.py pf-testing; then
-          #   echo "performance_ready=online" >> "$GITHUB_OUTPUT"
-          # else
-          #   echo "performance_ready=offline" >> "$GITHUB_OUTPUT"
-          #   test "$PERFORMANCE_OPTIONAL" = true
-          # fi
-          echo "performance_ready=offline" >> "$GITHUB_OUTPUT"
+          if python3 scripts/check_functional_runners.py pf-testing; then
+            echo "performance_ready=online" >> "$GITHUB_OUTPUT"
+          else
+            echo "performance_ready=offline" >> "$GITHUB_OUTPUT"
+            test "$PERFORMANCE_OPTIONAL" = true
+          fi
 
   validation:
     if: ${{ github.event_name == 'workflow_dispatch' && !inputs.validation_runner_inspect_only && inputs.validation_retain_evidence_run_id == '' && inputs.validation_package_sha == '' && (inputs.validation_case != '' || inputs.validation_tools_only || inputs.validation_native_tools || inputs.validation_shared_tools || inputs.validation_manager_tools || inputs.validation_cleanup_run_id != '' || inputs.validation_cleanup_retained_evidence) }}

.github/workflows/rustfs-heal-test.yml

@@ -55,8 +55,7 @@ env:
 jobs:
   heal-test:
     runs-on: smoke-testing
-    # 90-minute heal run (see the step below) plus setup, report and cleanup.
-    timeout-minutes: 120
+    timeout-minutes: 60
     # Standalone manual run, or one link of the nightly functional chain
     # (storage -> heal -> pool). Pool expansion no longer re-runs heal.
     if: ${{ inputs.chain_manifest != '' || github.event_name == 'workflow_dispatch' }}
@@ -155,7 +154,7 @@ jobs:
           ./auto-testing/rustfs_heal_test.sh "${ARGS[@]}" --log-file "${LOG_FILE}"
 
       - name: Run heal test (write -> outage -> heal -> verify)
-        timeout-minutes: 90
+        timeout-minutes: 45
         id: test
         # Collect reports and backlog evidence before the final suite verdict.
         continue-on-error: true

.github/workflows/rustfs-validation-sweep.yml

@@ -1,457 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#      http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-name: RustFS Validation Sweep
-
-# Executes the migrated canonical validation cases (rustfs/auto-testing#113)
-# on the shared functional fleet. Everything with a lane executor is swept in
-# rotating nightly batches so the whole set is covered roughly weekly; a
-# single case or one module can be dispatched manually. That is the
-# implemented catalog (66 today) plus the eight planned cases whose dedicated
-# executors already exist and have live PASS evidence - fresh nightly
-# evidence feeds their acceptance review. heal.* cases stay on the
-# interactive validation flow: they require reviewed native/tool collectors
-# built by separate validation-tools runs before fleet execution.
-
-on:
-  schedule:
-    # After the nightly functional chain settles (chain starts ~16:48 UTC and
-    # runs for about two hours).
-    - cron: "30 19 * * *"
-  workflow_dispatch:
-    inputs:
-      case:
-        description: 'Single canonical validation case id (overrides module and rotation), e.g. pool.decommission'
-        type: string
-        required: false
-        default: ''
-      module:
-        description: 'Restrict the sweep to one catalog module, e.g. bucket-replication'
-        type: string
-        required: false
-        default: ''
-      limit:
-        description: 'Maximum cases per sweep (0 = run everything selected)'
-        type: number
-        required: false
-        default: 12
-      build_run_id:
-        description: 'Successful nightly package run; empty resolves the latest'
-        type: string
-        required: false
-        default: ''
-      build_run_attempt:
-        description: 'Attempt of that package run'
-        type: string
-        required: false
-        default: '1'
-
-permissions:
-  contents: read
-
-concurrency:
-  group: rustfs-validation-sweep
-  cancel-in-progress: false
-
-env:
-  RUSTFS_NODES: ${{ secrets.RUSTFS_NODES || vars.RUSTFS_NODES || 'vm000 vm001 vm002 vm003' }}
-  RUSTFS_SSH_USER: ${{ secrets.RUSTFS_SSH_USER || vars.RUSTFS_SSH_USER || 'azureuser' }}
-  RUSTFS_ACCESS_KEY: ${{ secrets.RUSTFS_ACCESS_KEY }}
-  RUSTFS_SECRET_KEY: ${{ secrets.RUSTFS_SECRET_KEY }}
-  RUSTFS_NIGHTLY_PACKAGE_URL: ${{ vars.RUSTFS_NIGHTLY_PACKAGE_URL || 'https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb' }}
-  PF_TESTING_GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
-
-jobs:
-  sweep:
-    if: github.repository == 'rustfs/rustfs'
-    runs-on: smoke-testing
-    timeout-minutes: 150
-    steps:
-      - name: Checkout chain tooling
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Resolve nightly candidate
-        id: candidate
-        env:
-          GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
-          BUILD_RUN_ID: ${{ inputs.build_run_id }}
-          BUILD_RUN_ATTEMPT: ${{ inputs.build_run_attempt }}
-          CHAIN_OUTPUT: ${{ runner.temp }}/validation-sweep-candidate.json
-        run: |
-          set -euo pipefail
-          # Scheduled runs carry no inputs and the resolver only derives a
-          # build from a workflow_run payload (which a schedule cannot
-          # provide), so resolve the newest successful nightly build
-          # explicitly before invoking it.
-          if [ -z "${BUILD_RUN_ID:-}" ]; then
-            LATEST="$(gh api "repos/rustfs/rustfs/actions/workflows/nightly-gnu.yml/runs?branch=main&status=success&per_page=1" --jq '.workflow_runs[0]')"
-            BUILD_RUN_ID="$(printf '%s' "${LATEST}" | jq -r '.id')"
-            BUILD_RUN_ATTEMPT="$(printf '%s' "${LATEST}" | jq -r '.run_attempt')"
-            export BUILD_RUN_ID BUILD_RUN_ATTEMPT
-            echo "scheduled sweep pinned to nightly ${BUILD_RUN_ID} attempt ${BUILD_RUN_ATTEMPT}"
-          fi
-          python3 scripts/resolve_functional_candidate.py
-          python3 - <<'PY'
-          import json
-          import os
-          from pathlib import Path
-          root = Path(os.environ["RUNNER_TEMP"]) / "validation-sweep"
-          root.mkdir(parents=True, exist_ok=True)
-          chain = json.loads((Path(os.environ["RUNNER_TEMP"]) / "validation-sweep-candidate.json").read_text())
-          manifest = chain["candidate"]["manifest"]
-          (root / "candidate.json").write_text(json.dumps({
-              "package_url": manifest["package_url"],
-              "package_sha256": manifest["package_sha256"],
-              "source_sha": manifest["source_sha"],
-          }, sort_keys=True) + "\n")
-          with open(os.environ["GITHUB_OUTPUT"], "a") as output:
-              output.write("testing_sha=" + chain["testing_sha"] + "\n")
-              output.write("package_url=" + manifest["package_url"] + "\n")
-              output.write("source_sha=" + manifest["source_sha"] + "\n")
-          PY
-
-      - name: Checkout auto-testing scripts
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          repository: rustfs/auto-testing
-          ref: ${{ steps.candidate.outputs.testing_sha }}
-          token: ${{ secrets.PF_TESTING_GH_TOKEN }}
-          path: auto-testing
-          persist-credentials: false
-
-      - name: Prepare validation Python runtime
-        # The pool / ilm / replication validation runners require a managed
-        # Python, exactly like the chain's validation job provides.
-        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
-        with:
-          python-version: "3.12"
-
-      - name: Install validation Python requirements
-        # Case scripts call python3 and import boto3 at startup. Install the
-        # functional chain's client into a per-run env so that interpreter
-        # sees it without changing the runner's shared Python.
-        run: |
-          set -euo pipefail
-          validation_python="${RUNNER_TEMP}/rustfs-validation-python-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
-          test ! -e "${validation_python}"
-          python3 -m venv "${validation_python}"
-          "${validation_python}/bin/python" -m pip install \
-            -r auto-testing/scripts/validation_ilm/requirements.txt
-          printf '%s\n' "${validation_python}/bin" >> "${GITHUB_PATH}"
-
-      - name: Select sweep cases
-        id: select
-        env:
-          SELECTED_CASE: ${{ inputs.case }}
-          SELECTED_MODULE: ${{ inputs.module }}
-          CASE_LIMIT: ${{ inputs.limit }}
-          SWEEP_EVENT: ${{ github.event_name }}
-          SWEEP_ROOT: ${{ runner.temp }}/validation-sweep
-        run: |
-          set -euo pipefail
-          python3 - <<'PY'
-          import datetime
-          import json
-          import os
-          from pathlib import Path
-          sweep_root = Path(os.environ["SWEEP_ROOT"])
-
-          catalog = json.loads(Path("auto-testing/validation-cases.json").read_text())
-          def sweepable(case):
-              status = case.get("source_status")
-              if status == "implemented":
-                  return True
-              # The remaining planned non-heal cases route to the lane
-              # executors and already have live PASS evidence; sweeping them
-              # nightly produces fresh evidence for their acceptance review.
-              return status == "planned" and not case["id"].startswith("heal.")
-
-          selected = [(case["id"], module["id"]) for module in catalog["modules"]
-                      for case in module["cases"]
-                      if sweepable(case)]
-          if not selected:
-              raise SystemExit("catalog has no sweepable cases")
-
-          one_case = os.environ.get("SELECTED_CASE", "").strip()
-          module_filter = os.environ.get("SELECTED_MODULE", "").strip()
-          known = {case_id for case_id, _ in selected}
-          modules = {module_id for _, module_id in selected}
-          if one_case:
-              if one_case not in known:
-                  raise SystemExit(f"unknown case or no lane executor for it: {one_case}")
-              selected = [(one_case, dict(selected)[one_case])]
-          elif module_filter:
-              if module_filter not in modules:
-                  raise SystemExit(f"unknown module or no implemented cases: {module_filter}")
-              selected = [pair for pair in selected if pair[1] == module_filter]
-          elif os.environ.get("SWEEP_EVENT") == "schedule":
-              # Stateless rotation: every night take one window of the catalog
-              # so a full sweep needs len(selected)/limit nights and no state
-              # has to be carried between runs.
-              limit = max(1, int(os.environ.get("CASE_LIMIT") or 12))
-              day = datetime.datetime.now(datetime.timezone.utc).timetuple().tm_yday
-              start = (day * limit) % len(selected)
-              selected = (selected[start:] + selected[:start])[:limit]
-          limit = int(os.environ.get("CASE_LIMIT") or 0)
-          if one_case or module_filter or (not os.environ.get("SWEEP_EVENT") == "schedule"):
-              if limit > 0:
-                  selected = selected[:limit]
-
-          (sweep_root / "sweep-cases.txt").write_text("".join(f"{case_id}\n" for case_id, _ in selected))
-          with open(os.environ["GITHUB_OUTPUT"], "a") as output:
-              output.write(f"count={len(selected)}\n")
-          print(f"selected {len(selected)} case(s):", ", ".join(c for c, _ in selected))
-          PY
-
-      - name: Admit clean shared environment
-        id: environment
-        timeout-minutes: 5
-        env:
-          FUNCTIONAL_ENVIRONMENT_RECEIPT: ${{ runner.temp }}/environment-validation-sweep.json
-        run: python3 scripts/functional_environment.py enter --suite heal
-
-      - name: Run validation cases
-        id: run_cases
-        timeout-minutes: 120
-        env:
-          AUTO_TESTING_SHA: ${{ steps.candidate.outputs.testing_sha }}
-          SWEEP_ROOT: ${{ runner.temp }}/validation-sweep
-        run: |
-          set -uo pipefail
-          mkdir -p "${SWEEP_ROOT}/results"
-          : > "${SWEEP_ROOT}/results.txt"
-          while read -r CASE_ID; do
-            [ -n "${CASE_ID}" ] || continue
-            echo "::group::case ${CASE_ID}"
-            rm -rf "${SWEEP_ROOT}/run"
-            if ./auto-testing/scripts/run_validation_case.sh \
-                 "${CASE_ID}" "${SWEEP_ROOT}/candidate.json" \
-                 "${AUTO_TESTING_SHA}" "${SWEEP_ROOT}/run" \
-                 > "${SWEEP_ROOT}/results/${CASE_ID//\//_}.log" 2>&1; then
-              printf '%s\tPASS\n' "${CASE_ID}" >> "${SWEEP_ROOT}/results.txt"
-              echo "case ${CASE_ID}: PASS"
-            else
-              printf '%s\tFAIL\n' "${CASE_ID}" >> "${SWEEP_ROOT}/results.txt"
-              echo "case ${CASE_ID}: FAIL (log retained in the sweep artifact)"
-            fi
-            if [ -f "${SWEEP_ROOT}/run/report.md" ]; then
-              cp "${SWEEP_ROOT}/run/report.md" "${SWEEP_ROOT}/results/${CASE_ID//\//_}.report.md" 2>/dev/null || true
-            fi
-            echo "::endgroup::"
-            # Fleet hygiene between cases: the case runners set up their own
-            # topology, this purge guarantees the next case starts clean even
-            # when the previous one died mid-run.
-            for node in ${RUSTFS_NODES}; do
-              # -n keeps ssh from consuming the case list this loop reads from stdin
-              ssh -n -o BatchMode=yes -o ConnectTimeout=10 "${RUSTFS_SSH_USER}@${node}" '
-                SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
-                ${SUDO} systemctl stop rustfs 2>/dev/null || true
-                if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
-                  ${SUDO} dpkg -P rustfs
-                fi
-                for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
-                ${SUDO} rm -f /etc/default/rustfs
-              ' || echo "inter-case cleanup failed on ${node} (continuing)"
-            done
-          done < "${SWEEP_ROOT}/sweep-cases.txt"
-          echo "sweep finished: $(wc -l < "${SWEEP_ROOT}/results.txt") case(s) executed"
-
-      - name: Generate sweep report
-        if: ${{ always() && steps.environment.outcome == 'success' }}
-        env:
-          SWEEP_ROOT: ${{ runner.temp }}/validation-sweep
-          PACKAGE_URL: ${{ steps.candidate.outputs.package_url }}
-          SOURCE_SHA: ${{ steps.candidate.outputs.source_sha }}
-          AUTO_TESTING_SHA: ${{ steps.candidate.outputs.testing_sha }}
-        run: |
-          set -euo pipefail
-          python3 - <<'PY'
-          import json
-          import os
-          from pathlib import Path
-
-          root = Path(os.environ["SWEEP_ROOT"])
-          catalog = json.loads(Path("auto-testing/validation-cases.json").read_text())
-          module_of = {case["id"]: module["id"] for module in catalog["modules"] for case in module["cases"]}
-          rows = []
-          for line in (root / "results.txt").read_text().splitlines():
-            if not line:
-                continue
-            case_id, status = line.split("\t")
-            rows.append((case_id, module_of.get(case_id, "?"), status))
-          passed = sum(1 for _, _, s in rows if s == "PASS")
-          failed = len(rows) - passed
-          run_url = (f"{os.environ.get('GITHUB_SERVER_URL', 'https://github.com')}/"
-                     f"{os.environ.get('GITHUB_REPOSITORY', 'rustfs/rustfs')}/actions/runs/"
-                     f"{os.environ.get('GITHUB_RUN_ID', '')}")
-
-          report = [
-              "# RustFS validation sweep report", "",
-              f"- Run: {run_url}",
-              f"- Attempt: {os.environ.get('GITHUB_RUN_ATTEMPT', '')}",
-              f"- Trigger: {os.environ.get('GITHUB_EVENT_NAME', '')}",
-              f"- Package: {os.environ.get('PACKAGE_URL', 'nightly (R2 latest)')}",
-              f"- Source SHA: {os.environ.get('SOURCE_SHA', '')}",
-              f"- auto-testing: {os.environ.get('AUTO_TESTING_SHA', '')}", "",
-              "Canonical validation cases (rustfs/auto-testing#113) executed by the sweep, grouped by catalog module.", "",
-          ]
-          # Group the executed cases by catalog module (the major category:
-          # pool lifecycle, heal, ILM expiration, bucket/site replication, kms,
-          # data services, identity, s3 compatibility). Per-module subtotals
-          # deliberately use "- Subtotal:" so the dashboard overview regexes
-          # (which anchor on "- Total:") keep reading the grand totals below.
-          by_module = {}
-          module_order = []
-          for case_id, module, status in rows:
-              if module not in by_module:
-                  by_module[module] = []
-                  module_order.append(module)
-              by_module[module].append((case_id, status))
-          report += ["## Case Summary", ""]
-          for module in module_order:
-              cases = by_module[module]
-              mod_pass = sum(1 for _, st in cases if st == "PASS")
-              mod_fail = len(cases) - mod_pass
-              report += [f"### {module} ({len(cases)})", "",
-                         "| Case | Status |", "| --- | --- |"]
-              report += [f"| {case_id} | {status} |" for case_id, status in cases]
-              report += ["", f"- Subtotal: {mod_pass} passed, {mod_fail} failed", ""]
-          report += [
-              "## Totals", "",
-              f"- Total: {len(rows)}",
-              f"- PASS: {passed}",
-              f"- FAIL: {failed}",
-              "- UNSUPPORTED: 0", "",
-              "Failing cases keep this workflow red only as a report; the sweep artifact",
-              "retains every case log and per-case report for diagnosis.", "",
-          ]
-          (root / "report.md").write_text("\n".join(report))
-          (root / "cases.md").write_text("\n".join(f"| {c} | {m} | {s} |" for c, m, s in rows) + "\n")
-          PY
-          cat "${SWEEP_ROOT}/report.md" >> "${GITHUB_STEP_SUMMARY}"
-
-      - name: Upload functional report to dashboard
-        if: ${{ always() && steps.environment.outcome == 'success' }}
-        timeout-minutes: 2
-        continue-on-error: true
-        env:
-          GH_TOKEN: ${{ env.PF_TESTING_GH_TOKEN }}
-          REPORT_FILE: ${{ runner.temp }}/validation-sweep/report.md
-          SUITE: validation
-        run: |
-          set -euo pipefail
-          if [ -z "${GH_TOKEN:-}" ]; then
-            echo "PF_TESTING_GH_TOKEN is not configured; skipping dashboard upload"
-            exit 0
-          fi
-          DATE="$(date -u +%Y-%m-%d)"
-          REPORT_PATH="functional-reports/${SUITE}/${DATE}.md"
-          B64_FILE="$(mktemp)"
-          python3 -c 'import base64,sys;print(base64.b64encode(open(sys.argv[1],"rb").read()).decode())' "${REPORT_FILE}" > "${B64_FILE}"
-          SHA="$(gh api "repos/rustfs/dashboard/contents/${REPORT_PATH}" -q '.sha' 2>/dev/null || true)"
-          if [ -n "${SHA}" ]; then
-            jq -n --arg msg "report(${SUITE}): ${DATE}" --rawfile content "${B64_FILE}" --arg sha "${SHA}" \
-              '{message:$msg, content:($content|rtrimstr("\n")), sha:$sha}' \
-              | gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
-          else
-            jq -n --arg msg "report(${SUITE}): ${DATE}" --rawfile content "${B64_FILE}" \
-              '{message:$msg, content:($content|rtrimstr("\n"))}' \
-              | gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
-          fi
-          echo "dashboard updated: ${REPORT_PATH}"
-
-      - name: Retain sweep evidence
-        if: ${{ always() }}
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: rustfs-validation-sweep-${{ github.run_id }}-${{ github.run_attempt }}
-          path: |
-            ${{ runner.temp }}/validation-sweep/report.md
-            ${{ runner.temp }}/validation-sweep/results.txt
-            ${{ runner.temp }}/validation-sweep/sweep-cases.txt
-            ${{ runner.temp }}/validation-sweep/candidate.json
-            ${{ runner.temp }}/validation-sweep/results/
-            ${{ runner.temp }}/validation-sweep/run/
-          # warn (not error): an early infra failure legitimately leaves no
-          # per-case evidence, and the failing step is already red.
-          if-no-files-found: warn
-          retention-days: 30
-
-      - name: Cleanup environment (after)
-        id: environment_cleanup
-        timeout-minutes: 5
-        if: ${{ always() && steps.environment.outcome == 'success' }}
-        run: |
-          set -uo pipefail
-          cleanup_status=0
-          for node in ${RUSTFS_NODES}; do
-            ssh -o BatchMode=yes -o ConnectTimeout=10 "${RUSTFS_SSH_USER}@${node}" '
-              set -euo pipefail
-              SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
-              ${SUDO} systemctl stop rustfs 2>/dev/null || true
-              if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
-                ${SUDO} dpkg -P rustfs
-              fi
-              for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
-              ${SUDO} rm -f /etc/default/rustfs
-            ' || cleanup_status=$?
-          done
-          exit "${cleanup_status}"
-
-      - name: Release environment only after successful cleanup
-        if: ${{ always() && steps.environment.outcome == 'success' }}
-        timeout-minutes: 5
-        env:
-          FUNCTIONAL_ENVIRONMENT_RECEIPT: ${{ runner.temp }}/environment-validation-sweep.json
-          CLEANUP_OUTCOME: ${{ steps.environment_cleanup.outcome }}
-        run: python3 scripts/functional_environment.py finish --suite heal --cleanup-outcome "$CLEANUP_OUTCOME"
-
-      - name: Notify on failure
-        if: failure()
-        run: echo "RustFS validation sweep failed (harness/environment breakdown); see the sweep artifact for case logs."
-
-      - name: Enforce sweep result
-        if: ${{ always() && steps.environment.outcome == 'success' }}
-        env:
-          SWEEP_ROOT: ${{ runner.temp }}/validation-sweep
-        run: |
-          set -euo pipefail
-          if grep -q $'\tFAIL$' "${SWEEP_ROOT}/results.txt"; then
-            echo "validation sweep has failing cases:"
-            grep $'\tFAIL$' "${SWEEP_ROOT}/results.txt"
-            exit 1
-          fi
-
-  alert-on-failure:
-    name: Alert on scheduled failure
-    # A scheduled sweep failure usually means a canonical validation case
-    # regressed or the fleet environment broke; surface it as a tracking
-    # issue instead of leaving it in the Actions tab.
-    needs: [sweep]
-    if: github.repository == 'rustfs/rustfs' && (always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure'))
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    permissions:
-      contents: read
-      issues: write
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v5.0.0
-        with:
-          persist-credentials: false
-      - name: Open or update failure-tracking issue
-        uses: ./.github/actions/schedule-failure-issue
-        with:
-          github-token: ${{ secrets.BACKLOG_ISSUE_TOKEN }}

Cargo.toml

@@ -147,7 +147,7 @@ rustfs-zip = { path = "./crates/zip", version = "1.0.2" }
 async-channel = "2.5.0"
 async_zip = { default-features = false, version = "0.0.19" }
 mysql_async = { default-features = false, version = "0.37.1" }
-async-compression = { version = "0.4.52" }
+async-compression = { version = "0.4.51" }
 async-trait = "0.1.92"
 async-nats = { version = "0.51.0", default-features = false }
 axum = "0.8.9"
@@ -175,9 +175,9 @@ tokio-rustls = { default-features = false, version = "0.26.6" }
 tokio-stream = { version = "0.1.19" }
 tokio-test = "0.4.6"
 tokio-util = { version = "0.7.20" }
-tonic = { version = "0.14.9" }
-tonic-prost = { version = "0.14.9" }
-tonic-prost-build = { version = "0.14.9" }
+tonic = { version = "0.14.8" }
+tonic-prost = { version = "0.14.8" }
+tonic-prost-build = { version = "0.14.8" }
 tower = { version = "0.5.3" }
 tower-http = { version = "0.7.1" }
 h3 = "0.0.8"
@@ -212,13 +212,12 @@ serde_urlencoded = "0.7.1"
 # releases.
 aes-gcm = { version = "0.11.1" }
 argon2 = { version = "0.6.0" }
-aws-lc-rs = { version = "1.18.0", default-features = false }
 blake2 = "0.11.0"
 chacha20poly1305 = { version = "0.11.0" }
 crc-fast = "1.10.0"
 hmac = { version = "0.13.0" }
 jsonwebtoken = { version = "11.1.0" }
-openidconnect = { default-features = false, version = "4.1.0" }
+openidconnect = { default-features = false, version = "4.0" }
 pbkdf2 = "0.13.0"
 p256 = { version = "0.14.0", features = ["ecdsa", "pkcs8"] }
 rsa = { version = "=0.10.0-rc.18" }
@@ -254,9 +253,9 @@ atoi = "3.1.1"
 atomic_enum = "0.3.0"
 aws-config = { version = "1.13.0" }
 aws-credential-types = { version = "1.3.1" }
-aws-sdk-kms = { default-features = false, version = "1.129.0" }
-aws-sdk-s3 = { default-features = false, version = "1.157.0" }
-aws-sdk-sts = { default-features = false, version = "1.124.0" }
+aws-sdk-kms = { default-features = false, version = "1.128.0" }
+aws-sdk-s3 = { default-features = false, version = "1.156.0" }
+aws-sdk-sts = { default-features = false, version = "1.123.0" }
 aws-smithy-async = { version = "1.3.1" }
 aws-smithy-http-client = { default-features = false, version = "1.5.2" }
 aws-smithy-runtime-api = { version = "1.19.2" }
@@ -320,7 +319,7 @@ rustfs-erasure-codec = { version = "9.0.0" }
 reed-solomon-simd = "3.1.0"
 regex = { version = "1.13.1" }
 rumqttc = { package = "rumqttc-next", version = "0.34.0" }
-redis = { version = "1.8.1" }
+redis = { version = "1.8.0" }
 rustify = { version = "0.7", default-features = false }
 rustix = { version = "1.1.6" }
 rust-embed = { version = "8.13.0" }
@@ -335,10 +334,10 @@ compact_str = "0.10.0"
 snap = "1.1.2"
 starshard = { version = "2.4.0" }
 strum = { version = "0.28.0" }
-sysinfo = "0.40.1"
+sysinfo = "0.40.0"
 temp-env = "0.3.6"
 tempfile = "3.27.0"
-test-case = "3.4.1"
+test-case = "3.4.0"
 thiserror = "2.0.21"
 tracing = { version = "0.1.44" }
 tracing-appender = "0.2.5"
@@ -357,7 +356,7 @@ winapi-util = "0.1.11"
 windows = { version = "0.62.2" }
 windows-sys = "0.61.2"
 xxhash-rust = { version = "0.8.19" }
-zip = "9.2.2"
+zip = "9.1.3"
 zstd = "0.14.3"
 
 # Observability and Metrics
@@ -385,9 +384,9 @@ russh-sftp = "3.0.1"
 dav-server = "0.11.0"
 
 # Performance Analysis and Memory Profiling
-rustfs-mimalloc = { version = "0.7.3" }
+rustfs-mimalloc = { version = "0.7.2" }
 # Preserve Unicode focus filters until rustfs/backlog#2302 is resolved.
-hotpath = { version = "0.30.3", default-features = false }
+hotpath = { version = "0.30.1", default-features = false }
 # Snapshot testing for output format regression detection
 insta = { version = "1.49" }
 
@@ -428,3 +427,7 @@ strip = "none"
 # Pin upstream fixes until compatible crates.io releases are available.
 [patch.crates-io]
 zstd = { path = "crates/zstd-compat" }
+# Preserve RustFS OIDC flows while migrating the old elliptic-curve dependency chain.
+# Upstream: openidconnect-rs#244 and oauth2-rs#352.
+openidconnect = { git = "https://github.com/ramosbugs/openidconnect-rs", rev = "2f77ee73bc4554e1cb6279adb386005429fb4e41" }
+oauth2 = { git = "https://github.com/ramosbugs/oauth2-rs", rev = "89585f4a280afd7b285eaf1c9be0068874e03d22" }

crates/concurrency/src/adaptive.rs

@@ -10,10 +10,6 @@ use std::time::Duration;
 use tokio::sync::{Notify, Semaphore};
 use tokio::time::Instant;
 
-pub mod permit_set;
-
-const MAX_PERMIT_REFERENCES: usize = usize::MAX / 2;
-
 /// A resource owner publishes a capacity; running units retain their permits
 /// after a reduction. Lease slots are reserved once, with no per-unit Arc
 /// allocation. Tokio wait queues may lazily initialize platform mutex storage
@@ -40,7 +36,6 @@ pub struct AdaptiveAdmission {
     maximum: u32,
     slots: Box<[PermitSlots]>,
     next_chunk: AtomicUsize,
-    completed: AtomicU64,
 }
 
 struct PermitSlots {
@@ -66,12 +61,10 @@ pub struct AdaptivePermit {
 
 impl Clone for AdaptivePermit {
     fn clone(&self) -> Self {
-        // Subset carriers can retain slot references through a shared owner,
-        // so the slot count needs its own bound in addition to Arc's guard.
+        // Every slot reference owns a strong owner reference. Clone the Arc
+        // first, so its overflow protection also bounds the slot refcount.
         let owner = Arc::clone(&self.owner);
-        if owner.slots[self.slot / 64].references[self.slot % 64].fetch_add(1, Ordering::Relaxed) >= MAX_PERMIT_REFERENCES {
-            std::process::abort();
-        }
+        owner.slots[self.slot / 64].references[self.slot % 64].fetch_add(1, Ordering::Relaxed);
         Self { owner, slot: self.slot }
     }
 }
@@ -121,22 +114,11 @@ impl NodeAdmission {
 
     /// Publish feedback with this owner's actual completed-work counter.
     pub fn update(&self, controller: &mut FeedbackController, observation: Option<FeedbackObservation>) -> FeedbackDecision {
-        self.update_with_probe(controller, observation, true)
-    }
-
-    /// Coordinate growth with other resource controllers in the same window.
-    /// Protective reductions never depend on permission to probe.
-    pub fn update_with_probe(
-        &self,
-        controller: &mut FeedbackController,
-        observation: Option<FeedbackObservation>,
-        allow_probe: bool,
-    ) -> FeedbackDecision {
         let observation = observation.map(|mut observation| {
             observation.completed_units = self.completed();
             observation
         });
-        controller.update_with_probe(&self.capacity, observation, allow_probe)
+        controller.update(&self.capacity, observation)
     }
 
     /// Current leased scheduling cap and held async units.
@@ -267,31 +249,16 @@ impl FeedbackController {
     /// Consume one sample and publish a three-second lease to the same gate.
     /// If this function stops being called, admission expires independently.
     pub fn update(&mut self, gate: &AdaptiveAdmission, observation: Option<FeedbackObservation>) -> FeedbackDecision {
-        self.update_with_probe(gate, observation, true)
-    }
-
-    /// Allow at most the sampling owner's selected controller to probe upward.
-    pub fn update_with_probe(
-        &mut self,
-        gate: &AdaptiveAdmission,
-        observation: Option<FeedbackObservation>,
-        allow_probe: bool,
-    ) -> FeedbackDecision {
         let observation = observation.map(|mut observation| {
             observation.max_concurrency = observation.max_concurrency.min(gate.maximum);
             observation
         });
-        let decision = self.decide_with_probe(Instant::now(), observation, allow_probe);
+        let decision = self.decide(Instant::now(), observation);
         gate.set_sampled_limit(decision.limit, Duration::from_secs(3));
         decision
     }
 
-    fn decide_with_probe(
-        &mut self,
-        now: Instant,
-        observation: Option<FeedbackObservation>,
-        allow_probe: bool,
-    ) -> FeedbackDecision {
+    fn decide(&mut self, now: Instant, observation: Option<FeedbackObservation>) -> FeedbackDecision {
         let Some(observation) = observation else {
             self.previous = None;
             self.stable_since = None;
@@ -336,8 +303,7 @@ impl FeedbackController {
             FeedbackReason::NewBaseline
         } else {
             let since = *self.stable_since.get_or_insert(now);
-            if allow_probe
-                && advanced
+            if advanced
                 && now.saturating_duration_since(since) >= Duration::from_secs(8)
                 && now.saturating_duration_since(self.last_change) >= Duration::from_secs(8)
                 && self.limit < observation.max_concurrency
@@ -359,13 +325,6 @@ impl FeedbackController {
 }
 
 impl AdaptiveAdmission {
-    /// Successful async operations using this physical owner. Native clones
-    /// retain capacity but never count another completion.
-    pub fn completed(&self) -> Option<u64> {
-        let value = self.completed.load(Ordering::Acquire);
-        (value != u64::MAX).then_some(value)
-    }
-
     /// Construct a bounded owner, with zero initial capacity allowed for unknown
     /// input. The immutable maximum reserves at most 65,535 lease slots once;
     /// acquiring or cloning a permit does not allocate a per-unit Arc.
@@ -392,7 +351,6 @@ impl AdaptiveAdmission {
             maximum: maximum_u32,
             slots,
             next_chunk: AtomicUsize::new(0),
-            completed: AtomicU64::new(0),
         })
     }
 
@@ -508,21 +466,6 @@ impl AdaptiveAdmission {
         self.slots[slot / 64].free.fetch_or(1_u64 << (slot % 64), Ordering::Release);
     }
 
-    fn release_reference(&self, slot: usize) {
-        self.release_reference_with(slot, || {});
-    }
-
-    fn release_reference_with(&self, slot: usize, before_release: impl FnOnce()) {
-        if self.slots[slot / 64].references[slot % 64].fetch_sub(1, Ordering::AcqRel) != 1 {
-            return;
-        }
-        before_release();
-        // Publish the free slot before exposing another admission capacity.
-        self.release_slot(slot);
-        self.state.fetch_sub(1, Ordering::AcqRel);
-        self.changed.notify_one();
-    }
-
     /// Wait for capacity. The future owns no permit until it returns; dropping
     /// a pending future leaves capacity untouched. Wrap in the caller's existing
     /// cancellation/deadline select before acquiring any storage commit locks.
@@ -550,7 +493,13 @@ impl AdaptiveAdmission {
 
 impl Drop for AdaptivePermit {
     fn drop(&mut self) {
-        self.owner.release_reference(self.slot);
+        if self.owner.slots[self.slot / 64].references[self.slot % 64].fetch_sub(1, Ordering::AcqRel) != 1 {
+            return;
+        }
+        // Publish the free slot before exposing another admission capacity.
+        self.owner.release_slot(self.slot);
+        self.owner.state.fetch_sub(1, Ordering::AcqRel);
+        self.owner.changed.notify_one();
     }
 }
 
@@ -912,24 +861,6 @@ mod tests {
         }
     }
 
-    #[tokio::test(start_paused = true)]
-    async fn shared_probe_permission_blocks_growth_but_never_protective_cuts() {
-        let gate = AdaptiveAdmission::new(NonZeroU16::new(8).expect("bound"), 0);
-        let mut controller = FeedbackController::new();
-        controller.update_with_probe(&gate, Some(healthy(0)), false);
-        for completed in 1..=20 {
-            tokio::time::advance(Duration::from_secs(1)).await;
-            assert_eq!(controller.update_with_probe(&gate, Some(healthy(completed)), false).limit, 1);
-        }
-        tokio::time::advance(Duration::from_secs(1)).await;
-        assert_eq!(controller.update_with_probe(&gate, Some(healthy(21)), true).reason, FeedbackReason::Probe);
-        assert_eq!(gate.snapshot().limit, 2);
-        let mut busy = healthy(22);
-        busy.pressure = ResourcePressure::Busy;
-        assert_eq!(controller.update_with_probe(&gate, Some(busy), false).limit, 1);
-        assert_eq!(controller.update_with_probe(&gate, None, false).limit, 0);
-    }
-
     #[tokio::test(start_paused = true)]
     async fn controller_grows_one_unit_per_cooldown_and_cuts_pressure_immediately() {
         let gate = AdaptiveAdmission::new(NonZeroU16::new(8).expect("bounded test owner"), 0);

crates/config/src/constants/env.rs

@@ -30,16 +30,6 @@ pub const COMMENT_KEY: &str = "comment";
 pub const ENV_AUDIT_ENABLE: &str = "RUSTFS_AUDIT_ENABLE";
 /// Global switch for enabling the notify module.
 pub const ENV_NOTIFY_ENABLE: &str = "RUSTFS_NOTIFY_ENABLE";
-/// Maximum audit entries per second for authorization denials of authenticated callers.
-/// `0` disables denial auditing for that class of caller.
-pub const ENV_AUDIT_DENIAL_RATE: &str = "RUSTFS_AUDIT_DENIAL_RATE";
-/// Maximum audit entries per second for authorization denials of anonymous callers.
-/// `0` disables denial auditing for that class of caller.
-pub const ENV_AUDIT_DENIAL_ANONYMOUS_RATE: &str = "RUSTFS_AUDIT_DENIAL_ANONYMOUS_RATE";
-/// Default denial audit rate for authenticated callers (entries per second).
-pub const DEFAULT_AUDIT_DENIAL_RATE: u64 = 50;
-/// Default denial audit rate for anonymous callers (entries per second).
-pub const DEFAULT_AUDIT_DENIAL_ANONYMOUS_RATE: u64 = 5;
 /// Default global audit switch (disabled by default).
 pub const DEFAULT_AUDIT_ENABLE: bool = false;
 /// Default global notify switch (disabled by default).
@@ -338,7 +328,5 @@ mod tests {
     fn test_global_audit_notify_switch_constants() {
         assert_eq!(ENV_AUDIT_ENABLE, "RUSTFS_AUDIT_ENABLE");
         assert_eq!(ENV_NOTIFY_ENABLE, "RUSTFS_NOTIFY_ENABLE");
-        assert_eq!(ENV_AUDIT_DENIAL_RATE, "RUSTFS_AUDIT_DENIAL_RATE");
-        assert_eq!(ENV_AUDIT_DENIAL_ANONYMOUS_RATE, "RUSTFS_AUDIT_DENIAL_ANONYMOUS_RATE");
     }
 }

crates/data-usage/src/data_usage.rs

@@ -24,14 +24,6 @@ use std::{
     time::{Duration, SystemTime},
 };
 
-/// Copy an existing cache-model value without including surrounding work.
-#[inline]
-pub fn clone_cache_value<T: ToOwned + ?Sized>(source: &T) -> T::Owned {
-    #[cfg(feature = "hotpath-alloc")]
-    let _copy_scope = hotpath::MeasurementGuardSync::new("cache_model.owned_copy", false, false);
-    source.to_owned()
-}
-
 /// Maximum amount a persisted `last_update` may lead the local wall clock before the
 /// persisted timestamp is treated as untrustworthy.
 ///
@@ -350,7 +342,7 @@ impl UnknownTierStats {
                     self.diagnostics_dropped = checked_saturating_add(1, self.diagnostics_dropped, &mut self.counter_overflowed);
                     continue;
                 }
-                self.diagnostics.push(clone_cache_value(diagnostic));
+                self.diagnostics.push(diagnostic.clone());
             }
         }
         if !self.diagnostics.is_empty() {
@@ -375,7 +367,7 @@ impl UnknownTierStats {
         if !self.fits_add(other) {
             return None;
         }
-        let mut merged = clone_cache_value(self);
+        let mut merged = self.clone();
         merged.merge(other);
         Some(merged)
     }
@@ -415,7 +407,7 @@ impl AllTierStats {
             if st.is_empty() {
                 continue;
             }
-            let entry = self.tiers.entry(clone_cache_value(tier)).or_default();
+            let entry = self.tiers.entry(tier.clone()).or_default();
             *entry = entry.add(st);
         }
     }
@@ -445,7 +437,7 @@ impl AllTierStats {
             .tiers
             .keys()
             .filter(|tier| tier.as_str() != "STANDARD" && tier.as_str() != "REDUCED_REDUNDANCY" && !known.contains(tier.as_str()))
-            .map(clone_cache_value)
+            .cloned()
             .collect();
         for tier in retired_tiers {
             if let Some(stats) = self.tiers.remove(&tier) {
@@ -1245,10 +1237,10 @@ impl DataUsageEntry {
     }
 
     pub fn add_child(&mut self, hash: &DataUsageHash) {
-        if self.children.contains(&clone_cache_value(&hash.0)) {
+        if self.children.contains(&hash.key()) {
             return;
         }
-        self.children.insert(clone_cache_value(&hash.0));
+        self.children.insert(hash.key());
     }
 
     pub fn merge(&mut self, other: &DataUsageEntry) {
@@ -1265,7 +1257,7 @@ impl DataUsageEntry {
             s_rep.replica_size += o_rep.replica_size;
             s_rep.replica_count += o_rep.replica_count;
             for (arn, stat) in o_rep.targets.iter() {
-                let st = s_rep.targets.entry(clone_cache_value(arn)).or_default();
+                let st = s_rep.targets.entry(arn.clone()).or_default();
                 st.pending_size += stat.pending_size;
                 st.replicated_size += stat.replicated_size;
                 st.failed_size += stat.failed_size;
@@ -1459,7 +1451,7 @@ pub fn prefix_usage_in_cache(
     } else {
         format!("{bucket}/{prefix}")
     };
-    let entry = clone_cache_value(cache.get(&clone_cache_value(&hash_path(&root).0))?);
+    let entry = cache.get(&hash_path(&root).key())?.clone();
 
     let usage = PrefixUsageSummary::from_entry(&flatten_entry(cache, &entry, 0)?);
 
@@ -1602,38 +1594,38 @@ pub struct DataUsageCache {
 impl DataUsageCache {
     pub fn replace(&mut self, path: &str, parent: &str, e: DataUsageEntry) {
         let hash = hash_path(path);
-        self.cache.insert(clone_cache_value(&hash.0), e);
+        self.cache.insert(hash.key(), e);
         if !parent.is_empty() {
             let phash = hash_path(parent);
             let p = {
-                let p = self.cache.entry(clone_cache_value(&phash.0)).or_default();
+                let p = self.cache.entry(phash.key()).or_default();
                 p.add_child(&hash);
-                clone_cache_value(p)
+                p.clone()
             };
-            self.cache.insert(clone_cache_value(&phash.0), p);
+            self.cache.insert(phash.key(), p);
         }
     }
 
     pub fn replace_hashed(&mut self, hash: &DataUsageHash, parent: &Option<DataUsageHash>, e: &DataUsageEntry) {
-        self.cache.insert(clone_cache_value(&hash.0), clone_cache_value(e));
+        self.cache.insert(hash.key(), e.clone());
         if let Some(parent) = parent {
-            self.cache.entry(clone_cache_value(&parent.0)).or_default().add_child(hash);
+            self.cache.entry(parent.key()).or_default().add_child(hash);
         }
     }
 
     pub fn find(&self, path: &str) -> Option<DataUsageEntry> {
-        self.cache.get(&clone_cache_value(&hash_path(path).0)).map(clone_cache_value)
+        self.cache.get(&hash_path(path).key()).cloned()
     }
 
     pub fn find_children_copy(&mut self, h: DataUsageHash) -> DataUsageHashMap {
-        clone_cache_value(&self.cache.entry(clone_cache_value(&h.0)).or_default().children)
+        self.cache.entry(h.string()).or_default().children.clone()
     }
 
     pub fn flatten(&self, root: &DataUsageEntry) -> DataUsageEntry {
-        let mut root = clone_cache_value(root);
-        for id in clone_cache_value(&root.children).iter() {
+        let mut root = root.clone();
+        for id in root.children.clone().iter() {
             if let Some(e) = self.cache.get(id) {
-                let mut e = clone_cache_value(e);
+                let mut e = e.clone();
                 if !e.children.is_empty() {
                     e = self.flatten(&e);
                 }
@@ -1645,16 +1637,16 @@ impl DataUsageCache {
     }
 
     pub fn copy_with_children(&mut self, src: &DataUsageCache, hash: &DataUsageHash, parent: &Option<DataUsageHash>) {
-        if let Some(e) = src.cache.get(&clone_cache_value(&hash.0)) {
-            self.cache.insert(clone_cache_value(&hash.0), clone_cache_value(e));
+        if let Some(e) = src.cache.get(&hash.string()) {
+            self.cache.insert(hash.key(), e.clone());
             for ch in e.children.iter() {
-                if *ch == clone_cache_value(&hash.0) {
+                if *ch == hash.key() {
                     return;
                 }
-                self.copy_with_children(src, &DataUsageHash(clone_cache_value(ch)), &Some(clone_cache_value(hash)));
+                self.copy_with_children(src, &DataUsageHash(ch.to_string()), &Some(hash.clone()));
             }
             if let Some(parent) = parent {
-                let p = self.cache.entry(clone_cache_value(&parent.0)).or_default();
+                let p = self.cache.entry(parent.key()).or_default();
                 p.add_child(hash);
             }
         }
@@ -1662,14 +1654,14 @@ impl DataUsageCache {
 
     pub fn delete_recursive(&mut self, hash: &DataUsageHash) {
         let mut need_remove = Vec::new();
-        if let Some(v) = self.cache.get(&clone_cache_value(&hash.0)) {
+        if let Some(v) = self.cache.get(&hash.string()) {
             for child in v.children.iter() {
-                need_remove.push(clone_cache_value(child));
+                need_remove.push(child.clone());
             }
         }
-        self.cache.remove(&clone_cache_value(&hash.0));
+        self.cache.remove(&hash.string());
         need_remove.iter().for_each(|child| {
-            self.delete_recursive(&DataUsageHash(clone_cache_value(child)));
+            self.delete_recursive(&DataUsageHash(child.to_string()));
         });
     }
 
@@ -1690,7 +1682,7 @@ impl DataUsageCache {
     }
 
     pub fn search_parent(&self, hash: &DataUsageHash) -> Option<DataUsageHash> {
-        let want = clone_cache_value(&hash.0);
+        let want = hash.key();
         if let Some(last_index) = want.rfind('/')
             && let Some(v) = self.find(&want[0..last_index])
             && v.children.contains(&want)
@@ -1701,7 +1693,7 @@ impl DataUsageCache {
 
         for (k, v) in self.cache.iter() {
             if v.children.contains(&want) {
-                let found = DataUsageHash(clone_cache_value(k));
+                let found = DataUsageHash(k.clone());
                 return Some(found);
             }
         }
@@ -1709,7 +1701,7 @@ impl DataUsageCache {
     }
 
     pub fn is_compacted(&self, hash: &DataUsageHash) -> bool {
-        match self.cache.get(&clone_cache_value(&hash.0)) {
+        match self.cache.get(&hash.key()) {
             Some(due) => due.compacted,
             None => false,
         }
@@ -1734,7 +1726,7 @@ impl DataUsageCache {
         if self.cache.len() < limit {
             return;
         }
-        let top = clone_cache_value(&hash_path(&self.info.name).0);
+        let top = hash_path(&self.info.name).key();
         let top_e = match self.find(&top) {
             Some(e) => e,
             None => return,
@@ -1761,7 +1753,7 @@ impl DataUsageCache {
     }
 
     pub fn reduce_children_of(&mut self, path: &DataUsageHash, limit: usize, compact_self: bool) {
-        let e = match self.cache.get(&clone_cache_value(&path.0)) {
+        let e = match self.cache.get(&path.key()) {
             Some(e) => e,
             None => return,
         };
@@ -1771,13 +1763,13 @@ impl DataUsageCache {
         }
 
         if e.children.len() > limit && compact_self {
-            let mut flat = self.size_recursive(&clone_cache_value(&path.0)).unwrap_or_default();
+            let mut flat = self.size_recursive(&path.key()).unwrap_or_default();
             flat.compacted = true;
             self.delete_recursive(path);
             self.replace_hashed(path, &None, &flat);
             return;
         }
-        let total = self.total_children_rec(&clone_cache_value(&path.0));
+        let total = self.total_children_rec(&path.key());
         if total < limit {
             return;
         }
@@ -1790,12 +1782,12 @@ impl DataUsageCache {
         let mut candidate_index = 0;
         while remove > 0 && candidate_index < candidates.len() {
             let e = &candidates[candidate_index];
-            let candidate = clone_cache_value(&e.path);
+            let candidate = e.path.clone();
             if candidate == *path && !compact_self {
                 break;
             }
-            let removing = self.total_children_rec(&clone_cache_value(&candidate.0));
-            let mut flat = match self.size_recursive(&clone_cache_value(&candidate.0)) {
+            let removing = self.total_children_rec(&candidate.key());
+            let mut flat = match self.size_recursive(&candidate.key()) {
                 Some(flat) => flat,
                 None => {
                     candidate_index += 1;
@@ -1832,7 +1824,7 @@ impl DataUsageCache {
             if o.root().is_none() {
                 return;
             }
-            *self = clone_cache_value(o);
+            *self = o.clone();
             return;
         };
 
@@ -1845,8 +1837,7 @@ impl DataUsageCache {
         }
 
         existing_root.merge(&other_root);
-        self.cache
-            .insert(clone_cache_value(&hash_path(&self.info.name).0), existing_root);
+        self.cache.insert(hash_path(&self.info.name).key(), existing_root);
 
         let root_hash = self.root_hash();
         for key in other_root.children.iter() {
@@ -1857,7 +1848,7 @@ impl DataUsageCache {
             if let Some(existing) = self.cache.get_mut(key) {
                 existing.merge(&flat);
             } else {
-                self.replace_hashed(&DataUsageHash(clone_cache_value(key)), &Some(clone_cache_value(&root_hash)), &flat);
+                self.replace_hashed(&DataUsageHash(key.clone()), &Some(root_hash.clone()), &flat);
             }
         }
     }
@@ -1901,7 +1892,7 @@ impl DataUsageCache {
 
                 for (arn, stat) in rs.targets.iter() {
                     bui.replication_info.insert(
-                        clone_cache_value(arn),
+                        arn.clone(),
                         BucketTargetUsageInfo {
                             replication_pending_size: stat.pending_size,
                             replicated_size: stat.replicated_size,
@@ -1914,7 +1905,7 @@ impl DataUsageCache {
                     );
                 }
             }
-            buckets_usage.insert(clone_cache_value(bucket_name), bui);
+            buckets_usage.insert(bucket_name.clone(), bui);
         }
 
         DataUsageInfo {
@@ -1946,20 +1937,20 @@ struct Inner {
 }
 
 fn add(data_usage_cache: &DataUsageCache, path: &DataUsageHash, candidates: &mut Vec<Inner>) -> usize {
-    let e = match data_usage_cache.cache.get(&clone_cache_value(&path.0)) {
+    let e = match data_usage_cache.cache.get(&path.key()) {
         Some(e) => e,
         None => return 0,
     };
     let mut objects = e.objects;
     for ch in e.children.iter() {
-        objects += add(data_usage_cache, &DataUsageHash(clone_cache_value(ch)), candidates);
+        objects += add(data_usage_cache, &DataUsageHash(ch.clone()), candidates);
     }
     // Collect internal nodes (with children) as compaction candidates.
     // Leaf nodes have no children to remove, so compacting them is a no-op.
     if !e.children.is_empty() {
         candidates.push(Inner {
             objects,
-            path: clone_cache_value(path),
+            path: path.clone(),
         });
     }
     objects
@@ -1967,7 +1958,7 @@ fn add(data_usage_cache: &DataUsageCache, path: &DataUsageHash, candidates: &mut
 
 fn mark(duc: &DataUsageCache, entry: &DataUsageEntry, found: &mut HashSet<String>) {
     for k in entry.children.iter() {
-        found.insert(clone_cache_value(k));
+        found.insert(k.to_string());
         if let Some(ch) = duc.cache.get(k) {
             mark(duc, ch, found);
         }
@@ -2417,11 +2408,11 @@ impl SizeSummary {
         }
 
         for entry in &other.size_reconciliation {
-            self.record_size_reconciliation(clone_cache_value(entry));
+            self.record_size_reconciliation(entry.clone());
         }
         self.size_reconciliation_truncated |= other.size_reconciliation_truncated;
         for scope in &other.reconciliation_scopes {
-            self.record_reconciliation_scope_with(&scope.bucket, &scope.object, || clone_cache_value(scope));
+            self.record_reconciliation_scope(&scope.bucket, &scope.object);
         }
     }
 
@@ -2446,13 +2437,6 @@ impl SizeSummary {
     /// Mark one object scope as refreshed. Duplicate scopes are suppressed so
     /// merging summaries remains bounded and deterministic.
     pub fn record_reconciliation_scope(&mut self, bucket: &str, object: &str) {
-        self.record_reconciliation_scope_with(bucket, object, || SizeReconciliationScope {
-            bucket: bucket.to_string(),
-            object: object.to_string(),
-        });
-    }
-
-    fn record_reconciliation_scope_with(&mut self, bucket: &str, object: &str, build: impl FnOnce() -> SizeReconciliationScope) {
         if !self
             .reconciliation_scopes
             .iter()
@@ -2462,7 +2446,10 @@ impl SizeSummary {
                 self.size_reconciliation_truncated = true;
                 return;
             }
-            self.reconciliation_scopes.push(build());
+            self.reconciliation_scopes.push(SizeReconciliationScope {
+                bucket: bucket.to_string(),
+                object: object.to_string(),
+            });
         }
     }
 }
@@ -3417,42 +3404,6 @@ mod tests {
         assert_eq!(summary1.versions, 15);
     }
 
-    #[test]
-    fn test_reconciliation_scope_builds_only_after_admission() {
-        let mut summary = SizeSummary::new();
-        let builds = std::cell::Cell::new(0);
-        let build = || {
-            builds.set(builds.get() + 1);
-            SizeReconciliationScope {
-                bucket: "bucket".to_string(),
-                object: "object".to_string(),
-            }
-        };
-
-        summary.record_reconciliation_scope_with("bucket", "object", build);
-        assert_eq!(builds.get(), 1, "an admitted scope is copied once");
-        assert_eq!(summary.reconciliation_scopes.len(), 1);
-        assert_eq!(summary.reconciliation_scopes[0].bucket, "bucket");
-        assert_eq!(summary.reconciliation_scopes[0].object, "object");
-
-        summary.record_reconciliation_scope_with("bucket", "object", build);
-        assert_eq!(builds.get(), 1, "duplicate scopes must not be copied");
-        assert_eq!(summary.reconciliation_scopes.len(), 1);
-        assert!(!summary.size_reconciliation_truncated);
-
-        for index in 1..1024 {
-            summary.record_reconciliation_scope("bucket", &index.to_string());
-        }
-        summary.record_reconciliation_scope_with("bucket", "object", build);
-        assert_eq!(builds.get(), 1, "a duplicate at capacity must not be copied");
-        assert!(!summary.size_reconciliation_truncated);
-
-        summary.record_reconciliation_scope_with("bucket", "overflow", build);
-        assert_eq!(builds.get(), 1, "a rejected scope must not be copied");
-        assert_eq!(summary.reconciliation_scopes.len(), 1024);
-        assert!(summary.size_reconciliation_truncated);
-    }
-
     #[test]
     fn test_size_histogram_compat_rollup_sums_all_sub_buckets() {
         let mut hist = SizeHistogram::default();

crates/e2e_test/Cargo.toml

@@ -25,7 +25,6 @@ workspace = true
 
 [features]
 default = []
-scanner-peer-mixed-version = []
 hotpath = [
     "hotpath/hotpath",
     "hotpath/tokio",

crates/e2e_test/README.md

@@ -26,7 +26,7 @@ Registered in [`src/lib.rs`](src/lib.rs). Grouped by concern:
 | **protocols** | [`src/protocols/`](src/protocols) | FTPS, WebDAV, SFTP compliance. Fixed ports, own guide: [`src/protocols/README.md`](src/protocols/README.md) |
 | **reliant** | [`src/reliant/`](src/reliant) | Tests that reuse an **externally started** server (SQL/select, conditional writes, lifecycle, deleted-object reads, node-interact). Run via [`scripts/run_e2e_tests.sh`](../../scripts/run_e2e_tests.sh); see [`src/reliant/README.md`](src/reliant/README.md) |
 | **cluster** | `cluster_concurrency_test`, `stale_multipart_cleanup_cluster_test`, `namespace_lock_quorum_test`, `admin_timeout_regression_test`, `object_lambda_test`, `replication_extension_test`, `tier_stats_cluster_test` | Multi-node scenarios via `RustFSTestClusterEnvironment` |
-| **distributed 4×4** | [`src/distributed/`](src/distributed) | Nightly `e2e-distributed` lane: S3, object lock/WORM, versioning, bucket/site replication, quota, expand/decommission/rebalance, concurrency, chaos, 4-node upgrade of historical data and IAM AK/SK. Map: [`docs/testing/distributed-e2e.md`](../../docs/testing/distributed-e2e.md) |
+| **distributed 4×4** | [`src/distributed/`](src/distributed) | Storage-sensitive PR and nightly `e2e-distributed` lane: S3, object lock/WORM, versioning, bucket/site replication, quota, expand/decommission/rebalance, concurrency, chaos, 4-node upgrade of historical data and IAM AK/SK. Map: [`docs/testing/distributed-e2e.md`](../../docs/testing/distributed-e2e.md) |
 | **chaos / reliability** | [`src/chaos.rs`](src/chaos.rs), `reliability_disk_fault_test`, `heal_erasure_disk_rebuild_test`, `server_startup_failfast_test` | Disk offline/replace/corrupt, EC rebuild, heal, fail-fast startup |
 | **upgrade compatibility** | `upgrade_compatibility_test` | Pinned previous-release writes followed by current-build reads on the same data directory |
 
@@ -64,25 +64,6 @@ Each build/run holds an exclusive `rustfs.e2e.lock` marker beside the binary; co
 
 The protocols suite has its own fixed-port and single-worker contract in [`src/protocols/README.md`](src/protocols/README.md). Use its command under [Troubleshooting](#troubleshooting).
 
-### Scanner mixed-version gate
-
-The Linux N/O scanner gate needs a separately qualified `33482bb` server, which supports scoped ACKs. Set `RUSTFS_SCANNER_COMPAT_OLD_BINARY` to that executable and `RUSTFS_SCANNER_COMPAT_OLD_SHA256` to its independently verified digest. The release binary used by ordinary upgrade CI is a different baseline. Missing or mismatched inputs fail the test.
-
-Enable the harness-only `scanner-peer-mixed-version` feature explicitly; keep the server wrapper features identical between build and run:
-
-```bash
-python3 scripts/e2e_binary.py build --features e2e-test-hooks
-python3 scripts/e2e_binary.py run --features e2e-test-hooks -- \
-  cargo nextest run --profile e2e-distributed -p e2e_test \
-  --features scanner-peer-mixed-version --ignore-default-filter \
-  -E 'test(=distributed::scanner_peer_bucket_test::scanner_peer_bucket_new_coordinator_certifies_old_peers_and_scopes_next_cycle)' \
-  --test-threads 1 --retries 0 --no-tests=fail
-```
-
-The separate `scanner_peer_bucket_new_coordinator_certifies_old_worker_peers_and_scopes_next_cycle` case uses the same feature and qualified old binary inputs. Select its exact name in the command above. It keeps the original N process enabled and starts the three official O replacements with `RUSTFS_SCANNER_ENABLED=false`: their autonomous scanner loops are disabled, while real S3 dirty tracking, authenticated snapshots, publication leases, scoped ACKs, and N-dispatched RemoteScanner workers remain active. It records each node's actual scanner status and retains the same identity, durability, root, ACK, data-conservation, and physical-walk requirements. This fixed-role case does not validate autonomous O scanning or all-enabled election behavior. The original all-enabled N/O test remains separate and has not passed acceptance; a fixed-role result cannot satisfy that gate.
-
-For this fixed-role case, the `e2e-test-hooks` server also records the N client's complete bounded worker inventory. Requests are observed before opening the normal stream and paired only after authenticated source/plan validation and terminal EOF. Closed manifests and final health receipts must bind both cycles to their actual candidate/root; the next cycle needs exactly four sets of hot-only execution and at least one positive-progress worker mapped to a measured official O process. A zero-progress Current response, missing/extra request, unhealthy recorder, or missing physical coverage fails the gate. The recorder does not add O hooks or change any protocol or timeout. Final health reads check immutable closed-cycle evidence, not current N liveness.
-
 ### `#[ignore]` semantics
 
 Ignored tests are excluded from the default `cargo nextest run` pass because
@@ -194,9 +175,9 @@ the same profile for membership and execution with one nightly worker.
 | `s3s-e2e` black-box | `e2e-tests` + `e2e-tests-rio-v2` jobs | **Active** (external conformance tool) |
 | ILM / lifecycle (ignored) | `test-ilm-integration-serial` lane, `-j1` | **Active** (backlog#1148 ilm-1) |
 | KMS suite | `e2e-full` job, merge queue + main | **Active** |
-| Direct and mixed-version rolling upgrades from pinned previous release | `e2e-upgrade.yml`, release tags + weekly schedule + manual dispatch | **Active** |
+| Direct and mixed-version rolling upgrades from pinned previous release | `e2e-upgrade.yml`, storage-sensitive PRs + release tags + weekly | **Active** |
 | Cluster faults (`e2e-nightly` profile) | consolidated nightly workflow | **Active** (backlog#1149 ci-7) |
-| Distributed 4-node 4-disk (`e2e-distributed` profile) | `.github/workflows/e2e-distributed.yml` | **Active** (nightly / dispatch) |
+| Distributed 4-node 4-disk (`e2e-distributed` profile) | `.github/workflows/e2e-distributed.yml` | **Active** (storage-sensitive PR / nightly / dispatch) |
 | Protocols (FTPS/WebDAV/SFTP) | consolidated nightly workflow, serial | **Active** (backlog#1149 ci-7) |
 | Replication (fast subset) | `e2e-smoke` profile, `e2e-tests` job, every PR | **Active** (backlog#1147 repl-1) |
 | Replication (slow + multi-node) | `e2e-repl-nightly` profile, consolidated nightly workflow | **Active** (backlog#1147 repl-1) |

crates/e2e_test/src/delete_marker_migration_semantics_test.rs

@@ -16,193 +16,8 @@
 mod tests {
     use crate::common::{RustFSTestEnvironment, init_logging};
     use aws_sdk_s3::Client;
-    use aws_sdk_s3::config::http::HttpResponse;
-    use aws_sdk_s3::error::{ProvideErrorMetadata, SdkError};
     use aws_sdk_s3::primitives::ByteStream;
-    use aws_sdk_s3::types::{BucketVersioningStatus, CompletedMultipartUpload, CompletedPart, VersioningConfiguration};
-
-    fn assert_not_found<E: ProvideErrorMetadata + std::fmt::Debug>(error: &SdkError<E, HttpResponse>) {
-        assert_eq!(error.raw_response().map(|r| r.status().as_u16()), Some(404), "{error:?}");
-        assert_eq!(
-            error.as_service_error().and_then(ProvideErrorMetadata::code),
-            Some("NoSuchKey"),
-            "{error:?}"
-        );
-    }
-
-    #[tokio::test]
-    async fn conditional_writes_cannot_replace_delete_marker_with_if_match() {
-        init_logging();
-        let mut env = RustFSTestEnvironment::new().await.expect("create test environment");
-        env.start_rustfs_server(vec![]).await.expect("start RustFS");
-        let client = env.create_s3_client();
-        let bucket = "conditional-delete-marker-proof";
-        create_versioned_bucket(&client, bucket).await;
-        client
-            .put_object()
-            .bucket(bucket)
-            .key("source")
-            .body(ByteStream::from_static(b"source"))
-            .send()
-            .await
-            .expect("write copy source");
-
-        for operation in ["put", "copy", "multipart"] {
-            let old = client
-                .put_object()
-                .bucket(bucket)
-                .key(operation)
-                .body(ByteStream::from_static(b"old"))
-                .send()
-                .await
-                .expect("write historical version");
-            let old_etag = old.e_tag().expect("historical ETag");
-            let marker = client
-                .delete_object()
-                .bucket(bucket)
-                .key(operation)
-                .send()
-                .await
-                .expect("create delete marker");
-            let marker_id = marker.version_id().expect("delete marker version");
-
-            let (upload_id, completed) = if operation == "multipart" {
-                let upload = client
-                    .create_multipart_upload()
-                    .bucket(bucket)
-                    .key(operation)
-                    .send()
-                    .await
-                    .expect("initiate multipart upload");
-                let upload_id = upload.upload_id().expect("upload ID").to_owned();
-                let part = client
-                    .upload_part()
-                    .bucket(bucket)
-                    .key(operation)
-                    .upload_id(&upload_id)
-                    .part_number(1)
-                    .body(ByteStream::from_static(b"new"))
-                    .send()
-                    .await
-                    .expect("upload part");
-                let completed = CompletedMultipartUpload::builder()
-                    .parts(
-                        CompletedPart::builder()
-                            .part_number(1)
-                            .set_e_tag(part.e_tag().map(str::to_owned))
-                            .build(),
-                    )
-                    .build();
-                (Some(upload_id), Some(completed))
-            } else {
-                (None, None)
-            };
-
-            for etag in [old_etag, "\"00000000000000000000000000000000\""] {
-                match operation {
-                    "put" => {
-                        let err = client
-                            .put_object()
-                            .bucket(bucket)
-                            .key(operation)
-                            .if_match(etag)
-                            .body(ByteStream::from_static(b"new"))
-                            .send()
-                            .await
-                            .expect_err("If-Match must reject marker");
-                        assert_not_found(&err);
-                    }
-                    "copy" => {
-                        let err = client
-                            .copy_object()
-                            .bucket(bucket)
-                            .key(operation)
-                            .copy_source(format!("{bucket}/source"))
-                            .if_match(etag)
-                            .send()
-                            .await
-                            .expect_err("If-Match copy must reject marker");
-                        assert_not_found(&err);
-                    }
-                    _ => {
-                        let err = client
-                            .complete_multipart_upload()
-                            .bucket(bucket)
-                            .key(operation)
-                            .upload_id(upload_id.as_deref().expect("upload ID"))
-                            .multipart_upload(completed.clone().expect("completed parts"))
-                            .if_match(etag)
-                            .send()
-                            .await
-                            .expect_err("If-Match completion must reject marker");
-                        assert_not_found(&err);
-                    }
-                }
-                let versions = client
-                    .list_object_versions()
-                    .bucket(bucket)
-                    .prefix(operation)
-                    .send()
-                    .await
-                    .expect("list versions after rejected write");
-                assert_eq!(versions.versions().len(), 1, "{operation}: failed write created a version");
-                assert_eq!(versions.delete_markers().len(), 1);
-                assert_eq!(versions.delete_markers()[0].version_id(), Some(marker_id));
-                assert_eq!(versions.delete_markers()[0].is_latest(), Some(true));
-            }
-
-            match operation {
-                "put" => {
-                    client
-                        .put_object()
-                        .bucket(bucket)
-                        .key(operation)
-                        .if_none_match("*")
-                        .body(ByteStream::from_static(b"new"))
-                        .send()
-                        .await
-                        .expect("If-None-Match PUT over marker");
-                }
-                "copy" => {
-                    client
-                        .copy_object()
-                        .bucket(bucket)
-                        .key(operation)
-                        .copy_source(format!("{bucket}/source"))
-                        .if_none_match("*")
-                        .send()
-                        .await
-                        .expect("If-None-Match copy over marker");
-                }
-                _ => {
-                    client
-                        .complete_multipart_upload()
-                        .bucket(bucket)
-                        .key(operation)
-                        .upload_id(upload_id.as_deref().expect("upload ID"))
-                        .multipart_upload(completed.expect("completed parts"))
-                        .if_none_match("*")
-                        .send()
-                        .await
-                        .expect("If-None-Match completion over marker");
-                }
-            }
-            let current = client
-                .get_object()
-                .bucket(bucket)
-                .key(operation)
-                .send()
-                .await
-                .expect("read successful conditional write")
-                .body
-                .collect()
-                .await
-                .expect("read object body")
-                .into_bytes();
-            let expected: &[u8] = if operation == "copy" { b"source" } else { b"new" };
-            assert_eq!(current.as_ref(), expected, "{operation}: unexpected current object");
-        }
-    }
+    use aws_sdk_s3::types::{BucketVersioningStatus, VersioningConfiguration};
 
     async fn create_versioned_bucket(client: &Client, bucket: &str) {
         client

crates/e2e_test/src/distributed/concurrency_stability_test.rs

@@ -12,249 +12,11 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use super::harness::{DistCluster, DistLayout, TestResult, payload_for, s3_probe_client, sha256_hex, unique_bucket};
+use super::harness::{DistCluster, DistLayout, TestResult, assert_object_bytes, payload_for, put_object, unique_bucket};
 use crate::common::init_logging;
-use aws_sdk_s3::{
-    Client,
-    error::{ProvideErrorMetadata, SdkError},
-    primitives::ByteStream,
-};
-use std::any::TypeId;
 use std::collections::BTreeSet;
-use std::fmt::Debug;
-use std::future::Future;
 use std::sync::Arc;
-use std::time::Duration;
 use tokio::sync::Barrier;
-use tokio::time::Instant;
-
-const LOCK_ADMISSION_BUDGET: Duration = Duration::from_secs(45);
-
-async fn after_lock_contention<T, E, F, Fut>(operation: &str, mut call: F) -> TestResult<Result<T, SdkError<E>>>
-where
-    E: Debug + ProvideErrorMetadata + 'static,
-    F: FnMut() -> Fut,
-    Fut: Future<Output = Result<T, SdkError<E>>>,
-{
-    let started = Instant::now();
-    let mut attempts = 0;
-    // The workload uses unique unversioned keys. Repeat only explicitly
-    // advertised lock backpressure; every step still needs its real result.
-    let outcome = tokio::time::timeout(LOCK_ADMISSION_BUDGET, async {
-        loop {
-            attempts += 1;
-            let result = call().await;
-            let retry = result.as_ref().err().is_some_and(|error| {
-                let Some(response) = error.raw_response() else {
-                    return false;
-                };
-                let Some(service_error) = error.as_service_error() else {
-                    return false;
-                };
-                // HEAD has no XML error body, so its SDK service error can
-                // lack a code even when the server supplies retry headers.
-                let namespace_code = service_error.code() == Some("ServiceUnavailable")
-                    || (service_error.code().is_none()
-                        && TypeId::of::<E>() == TypeId::of::<aws_sdk_s3::operation::head_object::HeadObjectError>());
-                response.status().as_u16() == 503
-                    && namespace_code
-                    && response.headers().get("x-rustfs-error-cause") == Some("namespace_lock_timeout")
-                    && response.headers().get("retry-after") == Some("1")
-            });
-            if !retry {
-                return result;
-            }
-            tokio::time::sleep(Duration::from_secs(1)).await;
-        }
-    })
-    .await;
-    if attempts > 1 || !matches!(&outcome, Ok(Ok(_))) {
-        eprintln!(
-            "mixed workload request: operation={operation}, attempts={attempts}, elapsed={:?}",
-            started.elapsed()
-        );
-    }
-    outcome.map_err(|_| {
-        format!("{operation} exceeded its {LOCK_ADMISSION_BUDGET:?} request budget after {attempts} attempts").into()
-    })
-}
-
-async fn assert_workload_bytes(client: &Client, bucket: &str, key: &str, expected: &[u8]) -> TestResult {
-    let output = after_lock_contention(&format!("GET {key}"), || client.get_object().bucket(bucket).key(key).send()).await??;
-    let actual = output.body.collect().await?.into_bytes();
-    if actual.as_ref() != expected {
-        return Err(format!(
-            "object {key} bytes mismatch: expected {} bytes sha256={} got {} bytes sha256={}",
-            expected.len(),
-            sha256_hex(expected),
-            actual.len(),
-            sha256_hex(&actual)
-        )
-        .into());
-    }
-    Ok(())
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use aws_smithy_http_client::test_util::infallible_client_fn;
-    use aws_smithy_types::body::SdkBody;
-    use std::sync::atomic::{AtomicUsize, Ordering};
-
-    type Reply = (u16, &'static str, Option<&'static str>, Option<&'static str>, &'static str);
-
-    fn client(respond: impl Fn(usize) -> Reply + Send + Sync + 'static) -> (Client, Arc<AtomicUsize>) {
-        let requests = Arc::new(AtomicUsize::new(0));
-        let seen = Arc::clone(&requests);
-        let transport = infallible_client_fn(move |_| {
-            let (status, code, cause, retry_after, body) = respond(seen.fetch_add(1, Ordering::SeqCst));
-            let body = if code.is_empty() {
-                body.to_string()
-            } else {
-                format!("<Error><Code>{code}</Code></Error>")
-            };
-            let mut response = http::Response::builder()
-                .status(status)
-                .header("content-type", "application/xml")
-                .header("content-length", body.len());
-            if let Some(cause) = cause {
-                response = response.header("x-rustfs-error-cause", cause);
-            }
-            if let Some(retry_after) = retry_after {
-                response = response.header("retry-after", retry_after);
-            }
-            response.body(SdkBody::from(body)).expect("scripted S3 response")
-        });
-        let config = crate::common::build_test_s3_config(
-            "http://contention.example.invalid",
-            "synthetic-access",
-            "synthetic-secret",
-            None,
-            "contention-test",
-        );
-        let client = Client::from_conf(config.to_builder().http_client(transport).build());
-        (s3_probe_client(&client), requests)
-    }
-
-    fn contention() -> Reply {
-        (503, "ServiceUnavailable", Some("namespace_lock_timeout"), Some("1"), "")
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn advertised_contention_recovers_after_standard_sdk_attempts_are_exhausted() -> TestResult {
-        let (client, requests) = client(|attempt| {
-            if attempt < 3 {
-                contention()
-            } else {
-                (200, "", None, None, "")
-            }
-        });
-        let standard = Client::from_conf(
-            client
-                .config()
-                .to_builder()
-                .retry_config(aws_sdk_s3::config::retry::RetryConfig::standard().with_max_attempts(3))
-                .build(),
-        );
-        standard
-            .put_object()
-            .bucket("bucket")
-            .key("key")
-            .body(ByteStream::from_static(b"body"))
-            .send()
-            .await
-            .expect_err("three advertised lock responses exhaust the standard SDK policy");
-        assert_eq!(requests.load(Ordering::SeqCst), 3);
-        requests.store(0, Ordering::SeqCst);
-        let started = Instant::now();
-        after_lock_contention("PUT recovery", || {
-            client
-                .put_object()
-                .bucket("bucket")
-                .key("key")
-                .body(ByteStream::from_static(b"body"))
-                .send()
-        })
-        .await??;
-        assert_eq!(requests.load(Ordering::SeqCst), 4);
-        assert!(started.elapsed() >= Duration::from_secs(3), "honor each Retry-After response");
-        Ok(())
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn bodyless_head_contention_uses_explicit_retry_headers() -> TestResult {
-        let (client, requests) = client(|attempt| {
-            if attempt == 0 {
-                (503, "", Some("namespace_lock_timeout"), Some("1"), "")
-            } else {
-                (200, "", None, None, "")
-            }
-        });
-        after_lock_contention("HEAD recovery", || client.head_object().bucket("bucket").key("key").send()).await??;
-        assert_eq!(requests.load(Ordering::SeqCst), 2);
-        Ok(())
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn unrelated_or_malformed_responses_are_not_retried() -> TestResult {
-        for reply in [
-            (500, "InternalError", Some("namespace_lock_timeout"), Some("1"), ""),
-            (403, "AccessDenied", None, None, ""),
-            (404, "NoSuchKey", None, None, ""),
-            (503, "ServiceUnavailable", Some("storage_write_quorum"), None, ""),
-            (503, "ServiceUnavailable", Some("namespace_lock_unavailable"), Some("1"), ""),
-            (503, "InternalError", Some("namespace_lock_timeout"), Some("1"), ""),
-            (503, "", Some("namespace_lock_timeout"), Some("1"), ""),
-            (503, "ServiceUnavailable", None, Some("1"), ""),
-            (503, "ServiceUnavailable", Some("namespace_lock_timeout"), None, ""),
-            (503, "ServiceUnavailable", Some("namespace_lock_timeout"), Some("2"), ""),
-        ] {
-            let (client, requests) = client(move |_| reply);
-            let result = after_lock_contention("PUT fatal response", || {
-                client
-                    .put_object()
-                    .bucket("bucket")
-                    .key("key")
-                    .body(ByteStream::from_static(b"body"))
-                    .send()
-            })
-            .await?;
-            assert!(result.is_err(), "fatal response cannot become success: {reply:?}");
-            assert_eq!(requests.load(Ordering::SeqCst), 1, "fatal response must remain visible: {reply:?}");
-        }
-        Ok(())
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn persistent_lock_contention_exhausts_the_request_budget() {
-        let (client, requests) = client(|_| contention());
-        let started = Instant::now();
-        let result = after_lock_contention("PUT unavailable", || {
-            client
-                .put_object()
-                .bucket("bucket")
-                .key("key")
-                .body(ByteStream::from_static(b"body"))
-                .send()
-        })
-        .await;
-        assert!(result.is_err(), "persistent contention cannot acknowledge an operation");
-        assert!(started.elapsed() >= LOCK_ADMISSION_BUDGET);
-        assert!(requests.load(Ordering::SeqCst) > 1);
-        assert!(requests.load(Ordering::SeqCst) <= LOCK_ADMISSION_BUDGET.as_secs() as usize + 1);
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn acknowledged_wrong_bytes_fail_without_retry() {
-        let (client, requests) = client(|_| (200, "", None, None, "wrong bytes"));
-        let error = assert_workload_bytes(&client, "bucket", "key", b"expected bytes")
-            .await
-            .expect_err("a successful but incorrect read is a consistency failure");
-        assert!(error.to_string().contains("bytes mismatch"));
-        assert_eq!(requests.load(Ordering::SeqCst), 1);
-    }
-}
 
 #[tokio::test]
 async fn four_node_high_concurrency_mixed_workload_is_consistent_on_every_node() -> TestResult {
@@ -262,9 +24,7 @@ async fn four_node_high_concurrency_mixed_workload_is_consistent_on_every_node()
     let dist = DistCluster::start(DistLayout::FourByFour).await?;
     let bucket = unique_bucket("conc");
     dist.create_bucket(&bucket).await?;
-    // This consistency probe owns its admission policy; unrelated responses
-    // must not be hidden by the SDK's general-purpose retries.
-    let clients = Arc::new(dist.clients()?.iter().map(s3_probe_client).collect::<Vec<_>>());
+    let clients = Arc::new(dist.clients()?);
     let worker_count = 24;
     let rounds = 4;
     let barrier = Arc::new(Barrier::new(worker_count));
@@ -284,46 +44,31 @@ async fn four_node_high_concurrency_mixed_workload_is_consistent_on_every_node()
                 let key = format!("source/worker-{idx:02}-round-{round}.bin");
                 let copy_key = format!("retained/worker-{idx:02}-round-{round}.bin");
                 let body = payload_for(&key, 64 * 1024);
-                let context = format!("worker={idx} round={round}");
-                after_lock_contention(&format!("{context} PUT source"), || {
-                    writer
-                        .put_object()
-                        .bucket(&bucket)
-                        .key(&key)
-                        .body(ByteStream::from(body.clone()))
-                        .send()
-                })
-                .await??;
+                put_object(writer, &bucket, &key, body.clone()).await?;
 
-                let head = after_lock_contention(&format!("{context} HEAD source"), || {
-                    reader.head_object().bucket(&bucket).key(&key).send()
-                })
-                .await??;
+                let head = reader.head_object().bucket(&bucket).key(&key).send().await?;
                 if head.content_length() != Some(body.len() as i64) {
                     return Err(format!("HEAD returned the wrong size for {key}: {head:?}").into());
                 }
-                assert_workload_bytes(reader, &bucket, &key, &body).await?;
+                assert_object_bytes(reader, &bucket, &key, &body).await?;
 
-                after_lock_contention(&format!("{context} COPY retained"), || {
-                    copier
-                        .copy_object()
-                        .bucket(&bucket)
-                        .key(&copy_key)
-                        .copy_source(format!("{bucket}/{key}"))
-                        .send()
-                })
-                .await??;
-                assert_workload_bytes(writer, &bucket, &copy_key, &body).await?;
+                copier
+                    .copy_object()
+                    .bucket(&bucket)
+                    .key(&copy_key)
+                    .copy_source(format!("{bucket}/{key}"))
+                    .send()
+                    .await?;
+                assert_object_bytes(writer, &bucket, &copy_key, &body).await?;
 
-                after_lock_contention(&format!("{context} DELETE source"), || {
-                    writer.delete_object().bucket(&bucket).key(&key).send()
-                })
-                .await??;
-                let missing = after_lock_contention(&format!("{context} HEAD deleted source"), || {
-                    reader.head_object().bucket(&bucket).key(&key).send()
-                })
-                .await?
-                .expect_err("deleted source key must not remain visible");
+                writer.delete_object().bucket(&bucket).key(&key).send().await?;
+                let missing = reader
+                    .head_object()
+                    .bucket(&bucket)
+                    .key(&key)
+                    .send()
+                    .await
+                    .expect_err("deleted source key must not remain visible");
                 if missing.raw_response().map(|response| response.status().as_u16()) != Some(404) {
                     return Err(format!("deleted source {key} returned an unexpected result: {missing:?}").into());
                 }
@@ -337,22 +82,14 @@ async fn four_node_high_concurrency_mixed_workload_is_consistent_on_every_node()
     for handle in handles {
         inventory.extend(handle.await??);
     }
-    assert_eq!(
-        inventory.len(),
-        worker_count * rounds,
-        "every worker round must retain its acknowledged copy"
-    );
 
     let expected_keys: BTreeSet<_> = inventory.iter().map(|(key, _)| key.as_str()).collect();
     for (node_idx, client) in clients.iter().enumerate() {
-        let listed = after_lock_contention(&format!("node={node_idx} LIST retained"), || {
-            client.list_objects_v2().bucket(&bucket).prefix("retained/").send()
-        })
-        .await??;
+        let listed = client.list_objects_v2().bucket(&bucket).prefix("retained/").send().await?;
         let listed_keys: BTreeSet<_> = listed.contents().iter().filter_map(|object| object.key()).collect();
         assert_eq!(listed_keys, expected_keys, "node {node_idx} returned a divergent retained-key listing");
         for (key, body) in &inventory {
-            assert_workload_bytes(client, &bucket, key, body)
+            assert_object_bytes(client, &bucket, key, body)
                 .await
                 .map_err(|error| format!("node {node_idx} failed to read {key}: {error}"))?;
         }

crates/e2e_test/src/distributed/mod.rs

@@ -39,8 +39,6 @@ mod s3_during_data_movement_test;
 mod scanner_heal_topology_fixture;
 mod scanner_heal_topology_test;
 mod scanner_heal_topology_tier_test;
-mod scanner_peer_bucket_fixture;
-mod scanner_peer_bucket_test;
 mod site_replication_test;
 mod table_catalog_test;
 mod upgrade_test;

crates/e2e_test/src/distributed/multipart_fence_acceptance_test.rs

@@ -18,7 +18,7 @@ use super::harness::{
 };
 use crate::common::{ClusterTopology, RustFSTestClusterEnvironment};
 use crate::rpc_fault_proxy::{RpcFaultProxy, RpcPause};
-use crate::storage_api::multipart_fence_acceptance::{LOCK_DIAGNOSTICS_FILTER, RUSTFS_META_MULTIPART_BUCKET};
+use crate::storage_api::multipart_fence_acceptance::RUSTFS_META_MULTIPART_BUCKET;
 use aws_sdk_s3::{
     Client,
     config::retry::RetryConfig,
@@ -38,16 +38,14 @@ const DEADLINE: Duration = Duration::from_secs(45);
 async fn fixture(
     drives_per_node: usize,
     storage_class: &str,
-    lock_diagnostics: bool,
 ) -> TestResult<(RustFSTestClusterEnvironment, Vec<RpcFaultProxy>, Vec<Client>, String)> {
-    fixture_from_binary(drives_per_node, storage_class, None, lock_diagnostics).await
+    fixture_from_binary(drives_per_node, storage_class, None).await
 }
 
 async fn fixture_from_binary(
     drives_per_node: usize,
     storage_class: &str,
     binary: Option<&std::path::Path>,
-    lock_diagnostics: bool,
 ) -> TestResult<(RustFSTestClusterEnvironment, Vec<RpcFaultProxy>, Vec<Client>, String)> {
     let mut cluster =
         RustFSTestClusterEnvironment::with_topology(ClusterTopology::single_pool_multidrive(4, drives_per_node)).await?;
@@ -92,10 +90,6 @@ async fn fixture_from_binary(
     ] {
         cluster.set_env(name, value);
     }
-    if lock_diagnostics {
-        cluster.set_env("RUST_LOG", LOCK_DIAGNOSTICS_FILTER);
-        cluster.set_env("RUSTFS_OBJECT_LOCK_DIAG_ENABLE", "true");
-    }
     let mut proxies = Vec::new();
     if binary.is_none() {
         for node in 0..4 {
@@ -369,120 +363,26 @@ fn upload_path_scope(bucket: &str, key: &str, upload_id: &str) -> TestResult<Str
     ))
 }
 
-async fn with_paused_peers<T, E>(
+async fn with_paused_peers<T: Send + 'static>(
     proxies: &[RpcFaultProxy],
     methods: &[&'static str],
     limits: &[usize],
     scope: &str,
-    request: impl std::future::Future<Output = Result<T, SdkError<E>>> + Send + 'static,
-) -> TestResult<Result<T, SdkError<E>>>
-where
-    T: Send + 'static,
-    E: std::error::Error + ProvideErrorMetadata + Send + Sync + 'static,
-{
-    let deadline = tokio::time::Instant::now() + DEADLINE;
+    request: impl std::future::Future<Output = T> + Send + 'static,
+) -> TestResult<T> {
     let pauses: Vec<_> = proxies[1..=limits.len()]
         .iter()
         .zip(limits)
         .map(|(proxy, limit)| proxy.pause(methods, *limit, Some(scope)))
         .collect::<Result<_, _>>()?;
-    let mut task = tokio::spawn(request);
-    let mut joined = None;
-    let mut deadline_expired = false;
-    let mut barrier_result = {
-        let faults = wait_for_faults(&pauses, methods);
-        tokio::pin!(faults);
-        match tokio::time::timeout_at(deadline, async {
-            tokio::select! {
-                result = &mut faults => result,
-                result = &mut task => {
-                    joined = Some(result);
-                    // A ready request is not evidence that every selected fault
-                    // was reached. Poll the original barrier once for that proof.
-                    match futures::poll!(faults.as_mut()) {
-                        std::task::Poll::Ready(result) => result,
-                        std::task::Poll::Pending => Err("SDK request completed before the selected RPC fault barrier".into()),
-                    }
-                }
-            }
-        })
-        .await
-        {
-            Ok(result) => result,
-            Err(error) => {
-                deadline_expired = true;
-                Err(std::io::Error::new(std::io::ErrorKind::TimedOut, error).into())
-            }
-        }
-    };
-    // Tokio's timeout polls an already-ready inner future before its timer.
-    // A late observation cannot certify the original absolute deadline.
-    deadline_expired |= tokio::time::Instant::now() >= deadline;
-    if deadline_expired {
-        barrier_result = Err(std::io::Error::new(
-            std::io::ErrorKind::TimedOut,
-            "selected RPC fault proof observed after the absolute MPU deadline",
-        )
-        .into());
-    }
-    if barrier_result.is_err() {
-        for pause in &pauses {
-            pause.discard_pending();
-        }
-    }
-    let mut client_task_aborted = false;
-    let request_result = match joined {
-        Some(result) => result,
-        None => match tokio::time::timeout_at(deadline, &mut task).await {
-            Ok(result) => result,
-            Err(error) => {
-                deadline_expired = true;
-                for pause in &pauses {
-                    pause.discard_pending();
-                }
-                barrier_result = Err(std::io::Error::new(std::io::ErrorKind::TimedOut, error).into());
-                // This owns only the test's SDK request, not server/native work.
-                // Retire the client task without granting another operation budget.
-                client_task_aborted = true;
-                task.abort();
-                task.await
-            }
-        },
-    };
-    deadline_expired |= tokio::time::Instant::now() >= deadline;
-    if deadline_expired {
-        barrier_result = Err(std::io::Error::new(
-            std::io::ErrorKind::TimedOut,
-            "SDK request result observed after the absolute MPU deadline",
-        )
-        .into());
-    }
-    let hits: Vec<_> = pauses.iter().map(RpcPause::hits).collect();
+    let task = tokio::spawn(request);
+    wait_for_faults(&pauses, methods).await?;
+    let result = tokio::time::timeout(DEADLINE, task).await??;
     for pause in &pauses {
         pause.discard_pending();
     }
     drop(pauses);
-    if barrier_result.is_err() {
-        let sdk_error = request_result.as_ref().ok().and_then(|result| result.as_ref().err());
-        let response = sdk_error.and_then(SdkError::raw_response);
-        eprintln!(
-            "MPU fault barrier failed: methods={methods:?}, hits={hits:?}, client_task_aborted={client_task_aborted}, deadline_expired={deadline_expired}, sdk_code={:?}, cause={:?}, request_id={:?}",
-            sdk_error
-                .and_then(|error| error.as_service_error())
-                .and_then(|error| error.meta().code()),
-            response.and_then(|response| response.headers().get("x-rustfs-error-cause")),
-            response.and_then(|response| response.headers().get("x-amz-request-id")),
-        );
-    }
-    match (barrier_result, request_result) {
-        // Preserve the actual SDK source instead of replacing an early service
-        // failure with an unrelated fault-wait timeout. The outer Err stays red.
-        (Err(_), Ok(Err(error))) => Err(Box::new(error)),
-        (Err(_), Err(error)) if !client_task_aborted => Err(Box::new(error)),
-        (Err(error), _) => Err(error),
-        (Ok(()), Ok(result)) => Ok(result),
-        (Ok(()), Err(error)) => Err(Box::new(error)),
-    }
+    Ok(result)
 }
 
 fn quorum_outcome<T: std::fmt::Debug, E: std::fmt::Debug + ProvideErrorMetadata>(
@@ -1418,7 +1318,7 @@ async fn concurrent_capped_parts_respect_limit_on_distinct_nodes(clients: &[Clie
 
 #[tokio::test]
 async fn metadata_delay_preserves_write_quorum_and_rejects_quorum_minus_one() -> TestResult {
-    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", true).await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
     list_parts_disk_loss_after_metadata_read(&cluster, &proxies, &clients, &bucket).await?;
     concurrent_capped_parts_respect_limit_on_distinct_nodes(&clients, &bucket).await?;
     phase_quorum_matrix(&cluster, &proxies, &clients, &bucket, false, 1, 3).await
@@ -1426,13 +1326,13 @@ async fn metadata_delay_preserves_write_quorum_and_rejects_quorum_minus_one() ->
 
 #[tokio::test]
 async fn lock_delay_preserves_admission_quorum_and_reports_timeout() -> TestResult {
-    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
     phase_quorum_matrix(&cluster, &proxies, &clients, &bucket, true, 1, 3).await
 }
 
 #[tokio::test]
 async fn sixteen_shard_multipart_metadata_requires_twelve_votes() -> TestResult {
-    let (cluster, proxies, clients, bucket) = fixture(4, "EC:4", false).await?;
+    let (cluster, proxies, clients, bucket) = fixture(4, "EC:4").await?;
     let storage = cluster_admin_ok(&cluster, http::Method::GET, "/rustfs/admin/v3/storageinfo", None).await?;
     let storage: serde_json::Value = serde_json::from_str(&storage)?;
     let storage: rustfs_madmin::StorageInfo = serde_json::from_value(storage["info"].clone())?;
@@ -1446,7 +1346,7 @@ async fn sixteen_shard_multipart_metadata_requires_twelve_votes() -> TestResult
 #[tokio::test]
 async fn mixed_version_failed_complete_requires_current_coordinator_for_abort() -> TestResult {
     let previous = super::upgrade_test::source_binary()?;
-    let (mut cluster, mut proxies, clients, bucket) = fixture_from_binary(4, "EC:4", Some(&previous), false).await?;
+    let (mut cluster, mut proxies, clients, bucket) = fixture_from_binary(4, "EC:4", Some(&previous)).await?;
     assert!(
         proxies.is_empty(),
         "the genuine previous fleet boots and seeds through its normal direct transport"
@@ -1649,7 +1549,7 @@ async fn native_certified_partial_abort_retry_reclaims_survivors_below_metadata_
         capability_sha256: Option<[u8; 32]>,
         abort: Option<AbortRef>,
     }
-    let (mut cluster, proxies, clients, bucket) = fixture(4, "EC:4", false).await?;
+    let (mut cluster, proxies, clients, bucket) = fixture(4, "EC:4").await?;
     let key = "partial-abort";
     let committed = payload_for("committed-before-abort", 4096);
     clients[0]
@@ -1865,7 +1765,7 @@ async fn native_certified_partial_abort_retry_reclaims_survivors_below_metadata_
 #[tokio::test]
 async fn late_complete_packets_cannot_publish_after_abort_and_bucket_recreation() -> TestResult {
     for size in [0, 8 * 1024 * 1024] {
-        let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+        let (cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
         let key = "late-complete";
         let upload = clients[0].create_multipart_upload().bucket(&bucket).key(key).send().await?;
         let upload_id = upload.upload_id().ok_or("missing upload ID")?;
@@ -1992,7 +1892,7 @@ async fn late_complete_packets_cannot_publish_after_abort_and_bucket_recreation(
 async fn late_part_packets_preserve_retired_and_fresh_uploads() -> TestResult {
     for (method, settles) in [("PreparePartTransaction", false), ("SettlePartTransaction", true)] {
         for recreate_bucket in [false, true] {
-            let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+            let (cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
             let key = "late-part-transaction";
             let previous = payload_for("committed-before-late-part", 4096);
             clients[0]
@@ -2175,7 +2075,7 @@ async fn late_part_packets_preserve_retired_and_fresh_uploads() -> TestResult {
 
 #[tokio::test]
 async fn cancelled_metadata_wait_releases_fence_for_bucket_recreation() -> TestResult {
-    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
     let pauses: Vec<_> = proxies[1..]
         .iter()
         .map(|proxy| proxy.pause(&["WriteMetadata"], usize::MAX, Some(&bucket)))
@@ -2198,7 +2098,7 @@ async fn cancelled_metadata_wait_releases_fence_for_bucket_recreation() -> TestR
 async fn part_resend_owner_serializes_complete_and_abort_after_client_cancellation() -> TestResult {
     use md5::{Digest as _, Md5};
 
-    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
     for cancel_waiter in [false, true] {
         for complete in [false, true] {
             let key = format!("resend-{cancel_waiter}-{complete}");
@@ -2686,7 +2586,7 @@ async fn resume_at_rpc<T: Send + 'static>(
 
 #[tokio::test]
 async fn each_multipart_phase_resumes_after_metadata_and_lock_delays() -> TestResult {
-    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
+    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2").await?;
     for locks in [false, true] {
         let key = format!("phase-{locks}");
         let client = clients[0].clone();

crates/e2e_test/src/replication_extension_test.rs

@@ -31,8 +31,8 @@ use aws_sdk_s3::error::ProvideErrorMetadata;
 use aws_sdk_s3::operation::list_object_versions::ListObjectVersionsOutput;
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::{
-    BucketVersioningStatus, CompletedMultipartUpload, CompletedPart, Delete, DeleteMarkerEntry, ObjectIdentifier, ObjectVersion,
-    ServerSideEncryption, VersioningConfiguration,
+    BucketVersioningStatus, CompletedMultipartUpload, CompletedPart, DeleteMarkerEntry, ObjectVersion, ServerSideEncryption,
+    VersioningConfiguration,
 };
 use base64_simd::STANDARD as BASE64_STANDARD;
 use bytes::Bytes;
@@ -3729,8 +3729,6 @@ async fn test_bucket_replication_converges_delete_marker_and_version_purge() ->
     init_logging();
 
     let mut source_env = RustFSTestEnvironment::new().await?;
-    let source_log = format!("{}/source.log", source_env.temp_dir);
-    source_env.capture_log_path = Some(source_log.clone());
     let mut source_env_vars = replication_fast_env();
     source_env_vars.extend_from_slice(LOOPBACK_REPLICATION_TARGET_ENV);
     source_env.start_rustfs_server_with_env(vec![], &source_env_vars).await?;
@@ -3793,66 +3791,19 @@ async fn test_bucket_replication_converges_delete_marker_and_version_purge() ->
         "target did not preserve the source delete-marker version ID"
     );
 
-    let wait_for_source_writeback = || async {
-        let metrics_url = format!("{}/{source_bucket}?replication-metrics", source_env.url);
-        timeout(Duration::from_secs(30), async {
-            loop {
-                let response = signed_request(
-                    http::Method::GET,
-                    &metrics_url,
-                    &source_env.access_key,
-                    &source_env.secret_key,
-                    None,
-                    None,
-                )
-                .await?;
-                let metrics: serde_json::Value = response.error_for_status()?.json().await?;
-                let queued = metrics["queued"]["curr"]["count"]
-                    .as_f64()
-                    .ok_or("missing replication queue count")?;
-                if metrics["provider_available"] == true && queued == 0.0 {
-                    return Ok::<(), Box<dyn Error + Send + Sync>>(());
-                }
-                sleep(Duration::from_millis(50)).await;
-            }
-        })
-        .await?
-    };
-    wait_for_source_writeback().await?;
-
-    let purged = source_client
-        .delete_objects()
+    source_client
+        .delete_object()
         .bucket(source_bucket)
-        .delete(
-            Delete::builder()
-                .objects(
-                    ObjectIdentifier::builder()
-                        .key(object_key)
-                        .version_id(&purged_version_id)
-                        .build()?,
-                )
-                .objects(
-                    ObjectIdentifier::builder()
-                        .key(object_key)
-                        .version_id(delete_marker_version_id)
-                        .build()?,
-                )
-                .build()?,
-        )
+        .key(object_key)
+        .version_id(&purged_version_id)
         .send()
         .await?;
-    assert!(purged.errors().is_empty(), "batch version purge failed: {:?}", purged.errors());
-    assert_eq!(purged.deleted().len(), 2, "both the data version and marker must be purged");
     assert_replication_converged(&source_client, source_bucket, &target_client, target_bucket).await?;
     let target_state = list_replication_state(&target_client, target_bucket).await?;
     assert!(
         target_state.iter().all(|entry| entry.version_id != purged_version_id),
         "target retained the explicitly purged object version"
     );
-    assert!(
-        target_state.iter().all(|entry| entry.version_id != delete_marker_version_id),
-        "target retained the explicitly purged delete marker"
-    );
     assert!(
         target_state
             .iter()
@@ -3868,19 +3819,6 @@ async fn test_bucket_replication_converges_delete_marker_and_version_purge() ->
         .await?;
     assert_eq!(retained.body.collect().await?.into_bytes().as_ref(), b"versioned replication payload v2");
 
-    // Wait for the source workers to finish their final writeback, which runs
-    // after the remote purge has already become visible (rustfs#9121).
-    wait_for_source_writeback().await?;
-    let logs = fs::read_to_string(source_log).await?;
-    let writeback_failures: Vec<_> = logs
-        .lines()
-        .filter(|line| line.contains("apply_replication_delete_state"))
-        .collect();
-    assert!(
-        writeback_failures.is_empty(),
-        "a completed batch purge must not report a source writeback failure: {writeback_failures:?}"
-    );
-
     Ok(())
 }
 

crates/e2e_test/src/rpc_fault_proxy.rs

@@ -28,8 +28,7 @@ use hyper_util::{
 use prost::Message as _;
 use rustfs_protos::proto_gen::node_service::{
     BatchGenerallyLockRequest, DeleteRequest, GenerallyLockRequest, PreparePartTransactionResponse, ReadVersionRequest,
-    RecoverMultipartSourceRequest, RenameDataResponse, ScannerScopedDirtyUsageAckRequest, SettlePartTransactionRequest,
-    SettlePartTransactionResponse,
+    RecoverMultipartSourceRequest, RenameDataResponse, SettlePartTransactionRequest, SettlePartTransactionResponse,
 };
 use std::{
     collections::HashSet,
@@ -50,9 +49,6 @@ use tokio::{
 type ProxyBody = BoxBody<Bytes, io::Error>;
 type ProxyClient = Client<HttpConnector, ProxyBody>;
 
-mod scoped_ack;
-pub(crate) use scoped_ack::{ScopedAckFault, ScopedAckQueue, ScopedAckScope};
-
 #[derive(Clone, Copy, PartialEq, Eq)]
 enum Disposition {
     Hold,
@@ -125,8 +121,7 @@ impl RpcPause {
         self.state.blocked.load(Ordering::SeqCst)
     }
 
-    /// Selected RPCs with successful HTTP/gRPC response headers, excluding
-    /// discarded packets. This does not prove a successful gRPC trailer or ACK apply.
+    /// Selected RPCs with successful HTTP/gRPC headers, excluding discarded packets.
     pub(crate) fn forwarded(&self) -> usize {
         self.state.forwarded.load(Ordering::SeqCst)
     }
@@ -238,7 +233,6 @@ pub(crate) struct RpcFaultProxy {
     address: SocketAddr,
     slot: PauseSlot,
     lock_slot: PauseSlot,
-    scoped_ack: scoped_ack::QueueSlot,
     task: JoinHandle<()>,
     late_requests: LateRequests,
 }
@@ -251,8 +245,6 @@ impl RpcFaultProxy {
         let active = slot.clone();
         let lock_slot: PauseSlot = Arc::new(Mutex::new(None));
         let active_lock = lock_slot.clone();
-        let scoped_ack = scoped_ack::empty_slot();
-        let active_ack = scoped_ack.clone();
         let late_requests: LateRequests = Arc::new(Mutex::new(Some(Vec::new())));
         let late = late_requests.clone();
         let task = tokio::spawn(async move {
@@ -267,7 +259,6 @@ impl RpcFaultProxy {
                         let h2 = h2.clone();
                         let active = active.clone();
                         let active_lock = active_lock.clone();
-                        let active_ack = active_ack.clone();
                         let late = late.clone();
                         connections.spawn(async move {
                             let service = service_fn(move |request: Request<Incoming>| {
@@ -281,7 +272,6 @@ impl RpcFaultProxy {
                                     None
                                 };
                                 let pause = owner_pause.or_else(|| active.lock().expect("RPC pause slot").clone());
-                                let ack = active_ack.lock().expect("scoped ACK queue slot").clone();
                                 let retain = pause.as_ref().is_some_and(|pause| {
                                     pause.retain_after_disconnect
                                         && request.uri().path().strip_prefix("/node_service.NodeService/")
@@ -290,11 +280,11 @@ impl RpcFaultProxy {
                                 let late = late.clone();
                                 async move {
                                     if !retain {
-                                        return forward_request(request, client, target, pause, ack).await;
+                                        return forward_request(request, client, target, pause).await;
                                     }
                                     // This opt-in fault owns the packet after client cancellation.
                                     // Proxy teardown still aborts every retained request.
-                                    let task = tokio::spawn(forward_request(request, client, target, pause, ack));
+                                    let task = tokio::spawn(forward_request(request, client, target, pause));
                                     {
                                         let mut requests = late.lock().expect("late RPC ownership");
                                         if let Some(requests) = requests.as_mut() {
@@ -319,7 +309,6 @@ impl RpcFaultProxy {
             address,
             slot,
             lock_slot,
-            scoped_ack,
             task,
             late_requests,
         })
@@ -329,11 +318,6 @@ impl RpcFaultProxy {
         self.address
     }
 
-    /// Retain only genuine scoped ACKs for one receiver/session and bucket set.
-    pub(crate) fn scoped_ack_queue(&self, scope: ScopedAckScope, capacity: usize) -> io::Result<ScopedAckQueue> {
-        ScopedAckQueue::arm(self.scoped_ack.clone(), scope, capacity)
-    }
-
     /// Pause at most limit requests to the named unary methods; other streams
     /// on the same HTTP/2 connection continue forwarding.
     pub(crate) fn pause(&self, methods: &[&'static str], limit: usize, scope: Option<&str>) -> io::Result<RpcPause> {
@@ -485,9 +469,6 @@ fn unary_payload(body: &[u8]) -> io::Result<&[u8]> {
 }
 
 fn scope_matches(method: &str, body: &[u8], scope: &[u8]) -> io::Result<bool> {
-    if method == "ScannerScopedDirtyUsageAck" {
-        return scoped_ack_matches(body, Some(scope));
-    }
     if method == "RecoverMultipartSource" {
         let request = RecoverMultipartSourceRequest::decode(unary_payload(body)?).map_err(io::Error::other)?;
         if request.protocol_version != u32::from(MULTIPART_SOURCE_PROTOCOL_VERSION) || request.path.as_bytes() != scope {
@@ -544,9 +525,7 @@ fn scoped_lock_owners(method: &str, body: &[u8], scope: &[u8]) -> io::Result<Vec
     let args = match method {
         "Lock" => vec![GenerallyLockRequest::decode(payload).map_err(io::Error::other)?.args],
         "LockBatch" => BatchGenerallyLockRequest::decode(payload).map_err(io::Error::other)?.args,
-        _ => {
-            return Err(io::Error::new(io::ErrorKind::InvalidInput, "lock observer requires a lock method"));
-        }
+        _ => return Err(io::Error::new(io::ErrorKind::InvalidInput, "lock observer requires a lock method")),
     };
     args.into_iter()
         .filter(|args| args.as_bytes().windows(scope.len()).any(|window| window == scope))
@@ -561,39 +540,18 @@ fn scoped_lock_owners(method: &str, body: &[u8], scope: &[u8]) -> io::Result<Vec
         .collect()
 }
 
-fn scoped_ack_matches(body: &[u8], scope: Option<&[u8]>) -> io::Result<bool> {
-    let request = ScannerScopedDirtyUsageAckRequest::decode(unary_payload(body)?).map_err(io::Error::other)?;
-    Ok(!request.probe_only && scope.is_none_or(|scope| request.entries.iter().any(|entry| entry.bucket.as_bytes() == scope)))
-}
-
 async fn forward_request(
     request: Request<Incoming>,
     client: ProxyClient,
     target: SocketAddr,
     pause: Option<Arc<PauseState>>,
-    ack: Option<Arc<scoped_ack::QueueState>>,
 ) -> io::Result<hyper::Response<ProxyBody>> {
-    let request = request.map(|body| body.map_err(io::Error::other).boxed());
-    let request = if let Some(ack) = ack
-        && request.uri().path() == "/node_service.ScannerControlService/ScannerScopedDirtyUsageAck"
-    {
-        match scoped_ack::intercept(request, client.clone(), target, ack).await? {
-            scoped_ack::Interception::Pass(request) => request,
-            scoped_ack::Interception::Handled(response) => return Ok(response),
-        }
-    } else {
-        request
-    };
-    let (parts, body) = request.into_parts();
-    let mut body = body;
+    let (mut parts, body) = request.into_parts();
+    let mut body = body.map_err(io::Error::other).boxed();
     let mut observed = None;
     let mut inspection = None;
     if let Some(pause) = pause {
-        let method = parts
-            .uri
-            .path()
-            .strip_prefix("/node_service.NodeService/")
-            .or_else(|| parts.uri.path().strip_prefix("/node_service.ScannerControlService/"));
+        let method = parts.uri.path().strip_prefix("/node_service.NodeService/");
         if let Some(method) = method.filter(|name| pause.methods.contains(name)) {
             let mut route = None;
             let mut lock_owners = Vec::new();
@@ -641,16 +599,6 @@ async fn forward_request(
                     .with_trailers(async move { trailers.map(Ok::<_, io::Error>) })
                     .boxed();
                 matches
-            } else if method == "ScannerScopedDirtyUsageAck" {
-                let collected = Limited::new(body, 1024 * 1024).collect().await.map_err(io::Error::other)?;
-                let trailers = collected.trailers().cloned();
-                let bytes = collected.to_bytes();
-                let matches = scoped_ack_matches(&bytes, None)?;
-                body = Full::new(bytes)
-                    .map_err(|never| match never {})
-                    .with_trailers(async move { trailers.map(Ok::<_, io::Error>) })
-                    .boxed();
-                matches
             } else {
                 true
             };
@@ -694,7 +642,24 @@ async fn forward_request(
             }
         }
     }
-    let response = forward_to_backend(Request::from_parts(parts, body), client, target).await?;
+    if !parts.headers.contains_key(http::header::HOST)
+        && let Some(authority) = parts.uri.authority()
+    {
+        parts.headers.insert(
+            http::header::HOST,
+            http::HeaderValue::from_str(authority.as_str()).map_err(io::Error::other)?,
+        );
+    }
+    parts.uri = http::Uri::builder()
+        .scheme("http")
+        .authority(target.to_string())
+        .path_and_query(parts.uri.path_and_query().map_or("/", |value| value.as_str()))
+        .build()
+        .map_err(io::Error::other)?;
+    let response = client
+        .request(Request::from_parts(parts, body))
+        .await
+        .map_err(io::Error::other)?;
     if let Some((pause, disk)) = inspection
         && response.status().is_success()
         && response.headers().get("grpc-status").is_some_and(|status| status == "12")
@@ -747,32 +712,6 @@ async fn forward_request(
     Ok(response.map(|body| body.map_err(io::Error::other).boxed()))
 }
 
-async fn forward_to_backend(
-    request: Request<ProxyBody>,
-    client: ProxyClient,
-    target: SocketAddr,
-) -> io::Result<hyper::Response<Incoming>> {
-    let (mut parts, body) = request.into_parts();
-    if !parts.headers.contains_key(http::header::HOST)
-        && let Some(authority) = parts.uri.authority()
-    {
-        parts.headers.insert(
-            http::header::HOST,
-            http::HeaderValue::from_str(authority.as_str()).map_err(io::Error::other)?,
-        );
-    }
-    parts.uri = http::Uri::builder()
-        .scheme("http")
-        .authority(target.to_string())
-        .path_and_query(parts.uri.path_and_query().map_or("/", |value| value.as_str()))
-        .build()
-        .map_err(io::Error::other)?;
-    client
-        .request(Request::from_parts(parts, body))
-        .await
-        .map_err(io::Error::other)
-}
-
 impl Drop for RpcFaultProxy {
     fn drop(&mut self) {
         if let Some(requests) = self.late_requests.lock().expect("late RPC ownership").take() {
@@ -792,7 +731,6 @@ mod tests {
 
     struct Backend {
         received: Arc<AtomicUsize>,
-        auth_headers: Arc<Mutex<Vec<(String, String)>>>,
         address: SocketAddr,
         task: JoinHandle<()>,
     }
@@ -816,8 +754,6 @@ mod tests {
         let address = listener.local_addr()?;
         let received = Arc::new(AtomicUsize::new(0));
         let received_task = received.clone();
-        let auth_headers = Arc::new(Mutex::new(Vec::new()));
-        let backend_auth = auth_headers.clone();
         let task = tokio::spawn(async move {
             let mut children = JoinSet::new();
             loop {
@@ -825,12 +761,10 @@ mod tests {
                     accepted = listener.accept() => {
                         let Ok((socket, _)) = accepted else { break };
                         let received = received_task.clone();
-                        let backend_auth = backend_auth.clone();
                         let reply = reply.clone();
                         children.spawn(async move {
                             let service = service_fn(move |request: Request<Incoming>| {
                                 let received = received.clone();
-                                let backend_auth = backend_auth.clone();
                                 let reply = reply.clone();
                                 async move {
                                 received.fetch_add(1, Ordering::SeqCst);
@@ -839,10 +773,6 @@ mod tests {
                                         http::HeaderValue::from_str(authority.as_str()).expect("valid HTTP authority")
                                     })
                                 });
-                                if let (Some(nonce), Some(signature)) = (request.headers().get("x-rustfs-rpc-nonce"), request.headers().get("x-rustfs-rpc-signature-v2")) {
-                                    backend_auth.lock().expect("backend auth header observations").push((
-                                        nonce.to_str().expect("test nonce").to_string(), signature.to_str().expect("test signature").to_string()));
-                                }
                                 let body = request.into_body().collect().await?.to_bytes();
                                 let body = reply.unwrap_or(body);
                                 let mut trailers = http::HeaderMap::new();
@@ -865,12 +795,7 @@ mod tests {
                 }
             }
         });
-        Ok(Backend {
-            received,
-            auth_headers,
-            address,
-            task,
-        })
+        Ok(Backend { received, address, task })
     }
 
     async fn call(client: &ProxyClient, address: SocketAddr, method: &str) -> io::Result<hyper::Response<Incoming>> {
@@ -884,14 +809,9 @@ mod tests {
         bytes: Bytes,
     ) -> io::Result<hyper::Response<Incoming>> {
         let body: ProxyBody = Full::new(bytes).map_err(|never| match never {}).boxed();
-        let service = if method == "ScannerScopedDirtyUsageAck" {
-            "ScannerControlService"
-        } else {
-            "NodeService"
-        };
         let request = Request::builder()
             .method("POST")
-            .uri(format!("http://{address}/node_service.{service}/{method}"))
+            .uri(format!("http://{address}/node_service.NodeService/{method}"))
             .header(http::header::TE, "trailers")
             .body(body)
             .map_err(io::Error::other)?;
@@ -906,353 +826,6 @@ mod tests {
         frame.into()
     }
 
-    const ACK_OWNER: &str = "11111111-1111-1111-1111-111111111111";
-    const ACK_INSTANCE: &str = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
-
-    fn ack_scope() -> ScopedAckScope {
-        ScopedAckScope {
-            nonce: uuid::Uuid::new_v4().to_string(),
-            owner_id: ACK_OWNER.to_string(),
-            instance_id: ACK_INSTANCE.to_string(),
-            buckets: std::collections::BTreeSet::from(["cold-bucket".to_string()]),
-        }
-    }
-
-    fn ack_request(bucket: &str, generation: u64) -> ScannerScopedDirtyUsageAckRequest {
-        ScannerScopedDirtyUsageAckRequest {
-            challenge: vec![7; 16].into(),
-            protocol_version: 1,
-            owner_id: ACK_OWNER.to_string(),
-            instance_id: ACK_INSTANCE.to_string(),
-            scope: 1,
-            probe_only: false,
-            entries: vec![rustfs_protos::proto_gen::node_service::ScannerScopedDirtyUsageEntry {
-                bucket: bucket.to_string(),
-                bucket_incarnation: vec![4; 16].into(),
-                generation,
-            }],
-        }
-    }
-
-    fn ack_frame(request: &ScannerScopedDirtyUsageAckRequest) -> Bytes {
-        let payload = request.encode_to_vec();
-        let mut frame = vec![0];
-        frame.extend_from_slice(&u32::try_from(payload.len()).expect("bounded test frame").to_be_bytes());
-        frame.extend_from_slice(&payload);
-        Bytes::from(frame)
-    }
-
-    fn ack_hash(bytes: &[u8]) -> String {
-        use sha2::Digest as _;
-        hex_simd::encode_to_string(&sha2::Sha256::digest(bytes)[..], hex_simd::AsciiCase::Lower)
-    }
-
-    // Transport-only fixtures: the distributed tests supply production signatures.
-    async fn call_ack_frame(
-        client: &ProxyClient,
-        address: SocketAddr,
-        frame: Bytes,
-        nonce: &str,
-    ) -> io::Result<hyper::Response<Incoming>> {
-        let request = Request::builder()
-            .method("POST")
-            .uri(format!("http://{address}/node_service.ScannerControlService/ScannerScopedDirtyUsageAck"))
-            .header(http::header::TE, "trailers")
-            .header("x-rustfs-rpc-nonce", nonce)
-            .header("x-rustfs-rpc-signature-v2", format!("opaque-signature-{nonce}"))
-            .body(Full::new(frame).map_err(|never| match never {}).boxed())
-            .map_err(io::Error::other)?;
-        client.request(request).await.map_err(io::Error::other)
-    }
-
-    #[tokio::test]
-    async fn scoped_ack_queue_loss_preserves_backend_boundary() {
-        tokio::time::timeout(Duration::from_secs(10), async {
-            for fault in [ScopedAckFault::RequestLoss, ScopedAckFault::ResponseLoss] {
-                let backend = backend().await.expect("backend");
-                let proxy = RpcFaultProxy::start_on("127.0.0.1:0".parse().expect("loopback"), backend.address)
-                    .await
-                    .expect("proxy");
-                let queue = proxy.scoped_ack_queue(ack_scope(), 1).expect("ACK queue");
-                let client: ProxyClient = Client::builder(TokioExecutor::new()).http2_only(true).build_http();
-                let frame = ack_frame(&ack_request("cold-bucket", 7));
-                let address = proxy.local_addr();
-                let body = frame.clone();
-                let caller = tokio::spawn(async move { call_ack_frame(&client, address, body, "loss").await });
-                queue.wait_for_packets(1).await.expect("captured ACK");
-                assert_eq!(backend.received.load(Ordering::SeqCst), 0, "retention must precede backend dispatch");
-                queue.settle(0, fault).expect("settle actual retained packet");
-                assert!(
-                    caller.await.expect("caller task").is_err(),
-                    "the caller must observe the injected transport failure"
-                );
-                let receipt = queue.wait_for_completion(0).await.expect("complete fault receipt");
-                let response_loss = fault == ScopedAckFault::ResponseLoss;
-                assert_eq!(receipt["forwarded"], response_loss);
-                assert_eq!(receipt["backend_complete"], response_loss);
-                assert_eq!(backend.received.load(Ordering::SeqCst), usize::from(response_loss));
-                if response_loss {
-                    assert_eq!(receipt["outcome"], "response_lost");
-                    assert_eq!(receipt["response"]["grpc_status"], "0", "status exists only in real backend trailers");
-                    assert_eq!(receipt["response"]["bytes"], frame.len());
-                    assert_eq!(receipt["response"]["sha256"], ack_hash(&frame));
-                    assert!(
-                        receipt["response"]["trailers_sha256"]
-                            .as_str()
-                            .is_some_and(|value| value.len() == 64)
-                    );
-                } else {
-                    assert_eq!(receipt["outcome"], "request_lost");
-                }
-            }
-        })
-        .await
-        .expect("bounded ACK loss checks");
-    }
-
-    #[tokio::test]
-    async fn scoped_ack_queue_keeps_cancelled_packets_and_releases_out_of_order() {
-        tokio::time::timeout(Duration::from_secs(10), async {
-            let backend = backend().await.expect("backend");
-            let proxy = RpcFaultProxy::start_on("127.0.0.1:0".parse().expect("loopback"), backend.address)
-                .await
-                .expect("proxy");
-            let queue = proxy.scoped_ack_queue(ack_scope(), 2).expect("two-packet ACK queue");
-            let client: ProxyClient = Client::builder(TokioExecutor::new()).http2_only(true).build_http();
-            let first = ack_frame(&ack_request("cold-bucket", 7));
-            let second = ack_frame(&ack_request("cold-bucket", 9));
-            let address = proxy.local_addr();
-            let old_client = client.clone();
-            let old_body = first.clone();
-            let old_caller = tokio::spawn(async move { call_ack_frame(&old_client, address, old_body, "first").await });
-            queue.wait_for_packets(1).await.expect("first retained packet");
-            old_caller.abort();
-            assert!(old_caller.await.expect_err("cancel original caller").is_cancelled());
-            let new_body = second.clone();
-            let new_caller = tokio::spawn(async move { call_ack_frame(&client, address, new_body, "second").await });
-            queue.wait_for_packets(2).await.expect("second retained packet");
-            assert_eq!(backend.received.load(Ordering::SeqCst), 0);
-            queue.settle(1, ScopedAckFault::Forward).expect("release newer packet first");
-            let response = new_caller
-                .await
-                .expect("new caller task")
-                .expect("new response")
-                .into_body()
-                .collect()
-                .await
-                .expect("complete body");
-            assert_eq!(response.trailers().expect("response trailers")["x-proof"], "unchanged-proof");
-            assert_eq!(response.to_bytes(), second);
-            queue.wait_for_completion(1).await.expect("new packet complete");
-            queue
-                .settle(0, ScopedAckFault::Forward)
-                .expect("release old packet after its caller disappeared");
-            let old = queue.wait_for_completion(0).await.expect("detached old packet complete");
-            assert_eq!(old["backend_complete"], true);
-            assert_eq!(old["request_sha256"], ack_hash(&first));
-            assert_eq!(old["response"]["sha256"], ack_hash(&first));
-            assert_eq!(backend.received.load(Ordering::SeqCst), 2);
-            assert_eq!(
-                *backend.auth_headers.lock().expect("backend header observations"),
-                vec![
-                    ("second".to_string(), "opaque-signature-second".to_string()),
-                    ("first".to_string(), "opaque-signature-first".to_string())
-                ]
-            );
-            assert!(
-                queue.settle(0, ScopedAckFault::Forward).is_err(),
-                "one original packet may only be forwarded once"
-            );
-        })
-        .await
-        .expect("bounded detached retention check");
-    }
-
-    #[tokio::test]
-    async fn scoped_ack_queue_bounds_capacity_and_excludes_other_scopes() {
-        tokio::time::timeout(Duration::from_secs(10), async {
-            let backend = backend().await.expect("backend");
-            let proxy = RpcFaultProxy::start_on("127.0.0.1:0".parse().expect("loopback"), backend.address)
-                .await
-                .expect("proxy");
-            assert!(proxy.scoped_ack_queue(ack_scope(), 0).is_err());
-            assert!(proxy.scoped_ack_queue(ack_scope(), 5).is_err());
-            let mut invalid = ack_scope();
-            invalid.nonce.clear();
-            assert!(proxy.scoped_ack_queue(invalid, 1).is_err());
-            let mut scope = ack_scope();
-            scope.buckets.insert("cold-bucket-z".to_string());
-            let queue = proxy.scoped_ack_queue(scope, 1).expect("bounded ACK queue");
-            let client: ProxyClient = Client::builder(TokioExecutor::new()).http2_only(true).build_http();
-            let mut probe = ack_request("cold-bucket", 7);
-            probe.probe_only = true;
-            let mut other_peer = ack_request("cold-bucket", 7);
-            other_peer.owner_id = uuid::Uuid::new_v4().to_string();
-            let mut other_instance = ack_request("cold-bucket", 7);
-            other_instance.instance_id = "b".repeat(32);
-            let mut invalid_challenge = ack_request("cold-bucket", 7);
-            invalid_challenge.challenge = vec![7; 15].into();
-            let mut noncanonical_entries = ack_request("cold-bucket-z", 7);
-            noncanonical_entries.entries.extend(ack_request("cold-bucket", 7).entries);
-            let unselected = [
-                probe,
-                other_peer,
-                other_instance,
-                ack_request("cold-bucket-other", 7),
-                ack_request("cold-bucket", u64::MAX),
-                invalid_challenge,
-                noncanonical_entries,
-            ];
-            let unselected_count = unselected.len();
-            for (index, request) in unselected.into_iter().enumerate() {
-                let body = ack_frame(&request);
-                let response = call_ack_frame(&client, proxy.local_addr(), body.clone(), "unselected")
-                    .await
-                    .expect("unselected ACK progresses");
-                assert_eq!(response.into_body().collect().await.expect("unselected body").to_bytes(), body);
-                assert!(queue.receipts().is_empty(), "unselected or protocol-invalid ACK must not consume a slot");
-                assert_eq!(backend.received.load(Ordering::SeqCst), index + 1);
-            }
-            assert!(queue.receipts().is_empty());
-            let address = proxy.local_addr();
-            let held_client = client.clone();
-            let valid_frame = ack_frame(&ack_request("cold-bucket", 7));
-            let held_body = valid_frame.clone();
-            let held = tokio::spawn(async move { call_ack_frame(&held_client, address, held_body, "held").await });
-            queue.wait_for_packets(1).await.expect("one matching packet");
-            assert!(!held.is_finished(), "the subsequent valid ACK must be retained");
-            assert_eq!(queue.receipts()[0]["request_sha256"], ack_hash(&valid_frame));
-            assert_eq!(backend.received.load(Ordering::SeqCst), unselected_count);
-            let extra = call_ack_frame(&client, address, ack_frame(&ack_request("cold-bucket", 8)), "beyond-capacity")
-                .await
-                .expect("capacity overflow passes without retention");
-            extra.into_body().collect().await.expect("overflow response");
-            assert_eq!(queue.receipts().len(), 1);
-            assert_eq!(backend.received.load(Ordering::SeqCst), unselected_count + 1);
-            drop(queue);
-            assert!(
-                held.await.expect("held caller").is_err(),
-                "dropping the session must cancel its retained packet"
-            );
-            assert_eq!(
-                backend.received.load(Ordering::SeqCst),
-                unselected_count + 1,
-                "session drop must never forward the held packet"
-            );
-        })
-        .await
-        .expect("bounded scope and lifecycle checks");
-    }
-
-    #[tokio::test]
-    async fn scoped_ack_queue_expiry_never_forwards_retained_packet() {
-        let (backend, _proxy, queue, caller) = tokio::time::timeout(Duration::from_secs(10), async {
-            let backend = backend().await.expect("backend");
-            let proxy = RpcFaultProxy::start_on("127.0.0.1:0".parse().expect("loopback"), backend.address)
-                .await
-                .expect("proxy");
-            let queue = proxy.scoped_ack_queue(ack_scope(), 1).expect("ACK queue");
-            let client: ProxyClient = Client::builder(TokioExecutor::new()).http2_only(true).build_http();
-            let address = proxy.local_addr();
-            let caller = tokio::spawn(async move {
-                call_ack_frame(&client, address, ack_frame(&ack_request("cold-bucket", 7)), "expires").await
-            });
-            queue.wait_for_packets(1).await.expect("retained packet");
-            (backend, proxy, queue, caller)
-        })
-        .await
-        .expect("bounded queue setup");
-        tokio::time::pause();
-        tokio::time::advance(Duration::from_secs(120)).await;
-        tokio::time::resume();
-        assert!(
-            tokio::time::timeout(Duration::from_secs(10), caller)
-                .await
-                .expect("expiry completes caller")
-                .expect("caller task")
-                .is_err()
-        );
-        let receipt = queue.receipts().into_iter().next().expect("expired receipt");
-        assert_eq!(receipt["completed"], true);
-        assert_eq!(receipt["forwarded"], false);
-        assert_eq!(receipt["backend_complete"], false);
-        assert_eq!(backend.received.load(Ordering::SeqCst), 0);
-        assert_eq!(
-            queue
-                .settle(0, ScopedAckFault::Forward)
-                .expect_err("expired packet cannot be released")
-                .kind(),
-            io::ErrorKind::TimedOut
-        );
-    }
-
-    #[tokio::test]
-    async fn scanner_ack_fault_matches_exact_bucket_and_excludes_probes() {
-        use rustfs_protos::proto_gen::node_service::ScannerScopedDirtyUsageEntry;
-
-        tokio::time::timeout(Duration::from_secs(10), async {
-            let backend = backend().await.expect("backend listener");
-            let proxy = RpcFaultProxy::start_on("127.0.0.1:0".parse().expect("loopback"), backend.address)
-                .await
-                .expect("proxy listener");
-            let client: ProxyClient = Client::builder(TokioExecutor::new()).http2_only(true).build_http();
-            let pause = proxy
-                .pause(&["ScannerScopedDirtyUsageAck"], 1, Some("cold-bucket"))
-                .expect("scoped ACK fault");
-            let frame = |bucket: &str, probe_only: bool| {
-                let payload = ScannerScopedDirtyUsageAckRequest {
-                    challenge: vec![3; 16].into(),
-                    protocol_version: 1,
-                    owner_id: "11111111-1111-1111-1111-111111111111".to_string(),
-                    instance_id: "a".repeat(32),
-                    scope: 1,
-                    probe_only,
-                    entries: vec![ScannerScopedDirtyUsageEntry {
-                        bucket: bucket.to_string(),
-                        bucket_incarnation: vec![4; 16].into(),
-                        generation: 17,
-                    }],
-                }
-                .encode_to_vec();
-                let mut frame = vec![0];
-                frame.extend_from_slice(&u32::try_from(payload.len()).expect("small ACK frame").to_be_bytes());
-                frame.extend_from_slice(&payload);
-                Bytes::from(frame)
-            };
-            for bytes in [frame("cold-bucket", true), frame("cold-bucket-other", false)] {
-                let response = call_body(&client, proxy.local_addr(), "ScannerScopedDirtyUsageAck", bytes.clone())
-                    .await
-                    .expect("probe and other bucket must progress");
-                assert_eq!(response.into_body().collect().await.expect("unselected response").to_bytes(), bytes);
-            }
-            assert_eq!(pause.hits(), 0);
-            let signed_bytes = frame("cold-bucket", false);
-            let task_bytes = signed_bytes.clone();
-            let address = proxy.local_addr();
-            let blocked =
-                tokio::spawn(async move { call_body(&client, address, "ScannerScopedDirtyUsageAck", task_bytes).await });
-            pause
-                .wait_for_hits(1)
-                .await
-                .expect("real ScannerControlService method must reach the fault");
-            assert!(!blocked.is_finished());
-            assert_eq!(backend.received.load(Ordering::SeqCst), 2, "held ACK must not apply at the backend");
-            pause.release();
-            let collected = blocked
-                .await
-                .expect("ACK task")
-                .expect("released ACK")
-                .into_body()
-                .collect()
-                .await
-                .expect("ACK body and trailers");
-            assert_eq!(collected.trailers().expect("ACK trailers")["x-proof"], "unchanged-proof");
-            assert_eq!(collected.to_bytes(), signed_bytes, "proxy must preserve the complete signed ACK frame");
-        })
-        .await
-        .expect("scanner ACK fault deadline");
-    }
-
     fn native_abort_request(path: &str) -> RecoverMultipartSourceRequest {
         use crate::storage_api::multipart_source_rpc::{
             MultipartAbortCertificate, MultipartAbortProof, MultipartAbortProofKind, MultipartAbortRound, MultipartSourcePhase,
@@ -2146,4 +1719,3 @@ mod tests {
         );
     }
 }
-// event-drill: isolated harness-only change

crates/e2e_test/src/rpc_fault_proxy/scoped_ack.rs

@@ -1,404 +0,0 @@
-// Copyright 2026 RustFS Team
-// SPDX-License-Identifier: Apache-2.0
-
-//! Bounded retention of original scoped ACK frames, independent of caller cancellation.
-
-use super::{ProxyBody, ProxyClient, forward_to_backend, unary_payload};
-use bytes::Bytes;
-use http_body_util::{BodyExt as _, Full, Limited};
-use hyper::{Request, Response};
-use prost::Message as _;
-use rustfs_protos::proto_gen::node_service::{ScannerScopedDirtyUsageAckRequest, ScannerScopedDirtyUsageAckResponse};
-use rustfs_protos::scoped_dirty_usage::validate_scoped_dirty_usage_request;
-use serde_json::{Value, json};
-use sha2::{Digest as _, Sha256};
-use std::{
-    collections::BTreeSet,
-    io,
-    net::SocketAddr,
-    sync::{
-        Arc, Mutex,
-        atomic::{AtomicBool, Ordering},
-    },
-    time::Duration,
-};
-use tokio::{
-    sync::{Notify, oneshot, watch},
-    task::AbortHandle,
-    time::Instant,
-};
-
-const MAX_RETAINED: usize = 4;
-const MAX_BYTES: usize = 1024 * 1024;
-const RETENTION: Duration = Duration::from_secs(120);
-
-pub(crate) struct ScopedAckScope {
-    pub nonce: String,
-    pub owner_id: String,
-    pub instance_id: String,
-    pub buckets: BTreeSet<String>,
-}
-
-impl ScopedAckScope {
-    fn validate(&self) -> io::Result<()> {
-        let valid_uuid = |value: &str| uuid::Uuid::parse_str(value).is_ok_and(|value| !value.is_nil());
-        if !valid_uuid(&self.nonce)
-            || !valid_uuid(&self.owner_id)
-            || self.instance_id.is_empty()
-            || self.instance_id.len() > 128
-            || self.buckets.is_empty()
-            || self.buckets.len() > 16
-            || self.buckets.iter().any(|bucket| bucket.is_empty() || bucket.len() > 63)
-        {
-            return Err(io::Error::new(
-                io::ErrorKind::InvalidInput,
-                "scoped ACK queue needs a bounded session, receiver and bucket scope",
-            ));
-        }
-        Ok(())
-    }
-
-    fn matches(&self, request: &ScannerScopedDirtyUsageAckRequest) -> bool {
-        !request.probe_only
-            && validate_scoped_dirty_usage_request(request).is_ok()
-            && request.owner_id == self.owner_id
-            && request.instance_id == self.instance_id
-            && request.entries.iter().all(|entry| self.buckets.contains(&entry.bucket))
-    }
-}
-
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
-pub(crate) enum ScopedAckFault {
-    Forward,
-    RequestLoss,
-    ResponseLoss,
-}
-
-struct Packet {
-    action: watch::Sender<Option<ScopedAckFault>>,
-    receipt: Mutex<Value>,
-    task: Mutex<Option<AbortHandle>>,
-}
-
-pub(super) struct QueueState {
-    scope: ScopedAckScope,
-    capacity: usize,
-    started: Instant,
-    deadline: Instant,
-    closed: AtomicBool,
-    // The packet inventory lock is released before any packet lock or await.
-    packets: Mutex<Vec<Arc<Packet>>>,
-    changed: Notify,
-}
-
-pub(super) type QueueSlot = Arc<Mutex<Option<Arc<QueueState>>>>;
-
-pub(super) fn empty_slot() -> QueueSlot {
-    Arc::new(Mutex::new(None))
-}
-
-pub(crate) struct ScopedAckQueue {
-    state: Arc<QueueState>,
-    slot: QueueSlot,
-}
-
-impl ScopedAckQueue {
-    pub(super) fn arm(slot: QueueSlot, scope: ScopedAckScope, capacity: usize) -> io::Result<Self> {
-        scope.validate()?;
-        if !(1..=MAX_RETAINED).contains(&capacity) {
-            return Err(io::Error::new(io::ErrorKind::InvalidInput, "scoped ACK capacity must be 1..=4"));
-        }
-        let mut active = slot.lock().expect("scoped ACK queue slot");
-        if active.is_some() {
-            return Err(io::Error::new(io::ErrorKind::AlreadyExists, "scoped ACK queue is already armed"));
-        }
-        let started = Instant::now();
-        let state = Arc::new(QueueState {
-            scope,
-            capacity,
-            started,
-            deadline: started + RETENTION,
-            closed: AtomicBool::new(false),
-            packets: Mutex::new(Vec::new()),
-            changed: Notify::new(),
-        });
-        *active = Some(state.clone());
-        drop(active);
-        Ok(Self { state, slot })
-    }
-
-    pub(crate) fn receipts(&self) -> Vec<Value> {
-        let packets = self.state.packets.lock().expect("scoped ACK packets").clone();
-        packets
-            .iter()
-            .map(|packet| packet.receipt.lock().expect("scoped ACK receipt").clone())
-            .collect()
-    }
-
-    pub(crate) async fn wait_for_packets(&self, count: usize) -> io::Result<()> {
-        self.wait_until(|| self.receipts().len() >= count).await
-    }
-
-    pub(crate) async fn wait_for_completion(&self, id: usize) -> io::Result<Value> {
-        self.wait_until(|| {
-            self.receipts()
-                .get(id)
-                .is_some_and(|receipt| receipt["completed"].as_bool() == Some(true))
-        })
-        .await?;
-        self.receipts()
-            .get(id)
-            .cloned()
-            .ok_or_else(|| io::Error::other("scoped ACK receipt disappeared"))
-    }
-
-    async fn wait_until(&self, ready: impl Fn() -> bool) -> io::Result<()> {
-        tokio::time::timeout_at(self.state.deadline, async {
-            loop {
-                let changed = self.state.changed.notified();
-                if ready() {
-                    return;
-                }
-                changed.await;
-            }
-        })
-        .await
-        .map_err(|_| io::Error::new(io::ErrorKind::TimedOut, "scoped ACK queue lifetime elapsed"))
-    }
-
-    pub(crate) fn settle(&self, id: usize, fault: ScopedAckFault) -> io::Result<()> {
-        if Instant::now() >= self.state.deadline {
-            return Err(io::Error::new(io::ErrorKind::TimedOut, "scoped ACK retention expired"));
-        }
-        let packet = self
-            .state
-            .packets
-            .lock()
-            .expect("scoped ACK packets")
-            .get(id)
-            .cloned()
-            .ok_or_else(|| io::Error::new(io::ErrorKind::NotFound, "scoped ACK packet is not retained"))?;
-        if !packet.action.send_if_modified(|current| {
-            if current.is_none() {
-                *current = Some(fault);
-                true
-            } else {
-                false
-            }
-        }) {
-            return Err(io::Error::new(io::ErrorKind::AlreadyExists, "scoped ACK packet was already settled"));
-        }
-        Ok(())
-    }
-}
-
-impl Drop for ScopedAckQueue {
-    fn drop(&mut self) {
-        self.state.closed.store(true, Ordering::SeqCst);
-        let mut slot = self.slot.lock().expect("scoped ACK queue slot");
-        if slot.as_ref().is_some_and(|current| Arc::ptr_eq(current, &self.state)) {
-            *slot = None;
-        }
-        drop(slot);
-        let packets = self.state.packets.lock().expect("scoped ACK packets").clone();
-        for packet in packets {
-            if let Some(task) = packet.task.lock().expect("scoped ACK task").take() {
-                task.abort();
-            }
-        }
-    }
-}
-
-pub(super) enum Interception {
-    Pass(Request<ProxyBody>),
-    Handled(Response<ProxyBody>),
-}
-
-fn restored_body(bytes: Bytes, trailers: Option<http::HeaderMap>) -> ProxyBody {
-    Full::new(bytes)
-        .map_err(|never| match never {})
-        .with_trailers(async move { trailers.map(Ok::<_, io::Error>) })
-        .boxed()
-}
-
-fn hash(bytes: &[u8]) -> String {
-    hex(Sha256::digest(bytes).as_ref())
-}
-
-fn hex(bytes: &[u8]) -> String {
-    hex_simd::encode_to_string(bytes, hex_simd::AsciiCase::Lower)
-}
-
-fn trailer_receipt(trailers: Option<&http::HeaderMap>) -> Value {
-    trailers.map_or(Value::Null, |headers| {
-        json!(
-            headers
-                .iter()
-                .map(|(name, value)| { json!({"name": name.as_str(), "value_hex": hex(value.as_bytes())}) })
-                .collect::<Vec<_>>()
-        )
-    })
-}
-
-fn header_hash(headers: &http::HeaderMap) -> String {
-    let mut hasher = Sha256::new();
-    for (name, value) in headers {
-        hasher.update(name.as_str().as_bytes());
-        hasher.update([0]);
-        hasher.update(value.as_bytes());
-        hasher.update([0]);
-    }
-    hex(hasher.finalize().as_ref())
-}
-
-fn millis(state: &QueueState) -> u64 {
-    u64::try_from(state.started.elapsed().as_millis()).unwrap_or(u64::MAX)
-}
-
-pub(super) async fn intercept(
-    request: Request<ProxyBody>,
-    client: ProxyClient,
-    target: SocketAddr,
-    state: Arc<QueueState>,
-) -> io::Result<Interception> {
-    if Instant::now() >= state.deadline || state.closed.load(Ordering::SeqCst) {
-        return Ok(Interception::Pass(request));
-    }
-    let (parts, body) = request.into_parts();
-    let collected = tokio::time::timeout_at(state.deadline, Limited::new(body, MAX_BYTES).collect())
-        .await
-        .map_err(|_| io::Error::new(io::ErrorKind::TimedOut, "scoped ACK frame collection expired"))?
-        .map_err(io::Error::other)?;
-    let trailers = collected.trailers().cloned();
-    let bytes = collected.to_bytes();
-    let decoded = ScannerScopedDirtyUsageAckRequest::decode(unary_payload(&bytes)?).map_err(io::Error::other)?;
-    let request = Request::from_parts(parts, restored_body(bytes.clone(), trailers.clone()));
-    if Instant::now() >= state.deadline || !state.scope.matches(&decoded) {
-        return Ok(Interception::Pass(request));
-    }
-    let header = |name| request.headers().get(name).and_then(|value| value.to_str().ok());
-    let (action, mut selected) = watch::channel(None);
-    let packet = {
-        let mut packets = state.packets.lock().expect("scoped ACK packets");
-        if packets.len() >= state.capacity || state.closed.load(Ordering::SeqCst) {
-            return Ok(Interception::Pass(request));
-        }
-        let id = packets.len();
-        let packet = Arc::new(Packet {
-            action,
-            task: Mutex::new(None),
-            receipt: Mutex::new(json!({
-                "id": id, "session_nonce": state.scope.nonce, "receiver": target.to_string(),
-                "authority": request.uri().authority().map(|value| value.as_str()),
-                "captured_at_ms": millis(&state), "completed": false, "forwarded": false,
-                "backend_complete": false, "outcome": "held", "request_bytes": bytes.len(),
-            "request_sha256": hash(&bytes), "request_frame_hex": hex(&bytes), "request_headers_sha256": header_hash(request.headers()),
-                "request_trailers_sha256": trailers.as_ref().map(header_hash),
-            "request_trailers": trailer_receipt(trailers.as_ref()),
-                "auth_nonce": header("x-rustfs-rpc-nonce"), "replay_nonce": header("x-rustfs-rpc-replay-nonce"),
-                "signature_sha256": header("x-rustfs-rpc-signature-v2").map(|value| hash(value.as_bytes())),
-                "replay_signature_sha256": header("x-rustfs-rpc-signature-v3").map(|value| hash(value.as_bytes())),
-                "request": {"owner_id": decoded.owner_id, "instance_id": decoded.instance_id,
-                    "probe_only": decoded.probe_only, "entries": decoded.entries.iter().map(|entry| json!({
-                        "bucket": entry.bucket, "bucket_incarnation": uuid::Uuid::from_slice(&entry.bucket_incarnation).ok().map(|value| value.to_string()),
-                        "generation": entry.generation })).collect::<Vec<_>>() }
-            })),
-        });
-        packets.push(packet.clone());
-        packet
-    };
-    let (reply, response) = oneshot::channel();
-    let worker_packet = packet.clone();
-    let worker_state = state.clone();
-    // This owner survives an HTTP/2 stream reset from the original 5 s caller.
-    // Every request is settled once and is discarded at the session deadline.
-    let task = tokio::spawn(async move {
-        let result = tokio::time::timeout_at(worker_state.deadline, async {
-            let fault = loop {
-                if let Some(fault) = *selected.borrow_and_update() {
-                    break fault;
-                }
-                selected
-                    .changed()
-                    .await
-                    .map_err(|_| io::Error::other("scoped ACK queue closed"))?;
-            };
-            if fault == ScopedAckFault::RequestLoss {
-                worker_packet.receipt.lock().expect("scoped ACK receipt")["outcome"] = json!("request_lost");
-                return Err(io::Error::new(io::ErrorKind::ConnectionAborted, "injected scoped ACK request loss"));
-            }
-            if worker_state.closed.load(Ordering::SeqCst) || Instant::now() >= worker_state.deadline {
-                return Err(io::Error::new(
-                    io::ErrorKind::ConnectionAborted,
-                    "scoped ACK session ended or expired before forwarding",
-                ));
-            }
-            {
-                let mut receipt = worker_packet.receipt.lock().expect("scoped ACK receipt");
-                receipt["forwarded"] = json!(true);
-                receipt["forwarded_at_ms"] = json!(millis(&worker_state));
-            }
-            let backend = forward_to_backend(request, client, target).await?;
-            let (parts, body) = backend.into_parts();
-            let collected = Limited::new(body, MAX_BYTES).collect().await.map_err(io::Error::other)?;
-            let trailers = collected.trailers().cloned();
-            let bytes = collected.to_bytes();
-            let grpc_status = trailers
-                .as_ref()
-                .and_then(|values| values.get("grpc-status"))
-                .or_else(|| parts.headers.get("grpc-status"))
-                .and_then(|value| value.to_str().ok());
-            let response = unary_payload(&bytes)
-                .ok()
-                .and_then(|payload| ScannerScopedDirtyUsageAckResponse::decode(payload).ok())
-                .map(|response| {
-                    json!({"owner_id": response.owner_id, "instance_id": response.instance_id,
-                    "supported": response.supported, "cleared": response.cleared,
-                    "response_proof_bytes": response.response_proof.len()})
-                });
-            {
-                let mut receipt = worker_packet.receipt.lock().expect("scoped ACK receipt");
-                receipt["backend_complete"] = json!(true);
-                receipt["backend_completed_at_ms"] = json!(millis(&worker_state));
-                receipt["response"] = json!({"status": parts.status.as_u16(), "grpc_status": grpc_status,
-                    "bytes": bytes.len(), "sha256": hash(&bytes), "frame_hex": hex(&bytes), "headers_sha256": header_hash(&parts.headers),
-                    "trailers": trailer_receipt(trailers.as_ref()),
-                    "trailers_sha256": trailers.as_ref().map(header_hash), "ack": response});
-                receipt["outcome"] = json!(if fault == ScopedAckFault::ResponseLoss {
-                    "response_lost"
-                } else {
-                    "forwarded"
-                });
-            }
-            if fault == ScopedAckFault::ResponseLoss {
-                return Err(io::Error::new(
-                    io::ErrorKind::ConnectionAborted,
-                    "injected scoped ACK response loss after backend trailers",
-                ));
-            }
-            Ok(Response::from_parts(parts, restored_body(bytes, trailers)))
-        })
-        .await
-        .unwrap_or_else(|_| Err(io::Error::new(io::ErrorKind::TimedOut, "scoped ACK retention expired")));
-        {
-            let mut receipt = worker_packet.receipt.lock().expect("scoped ACK receipt");
-            if result.is_err() && receipt["outcome"] == "held" {
-                receipt["outcome"] = json!("transport_failed_or_expired");
-            }
-            receipt["completed"] = json!(true);
-            receipt["completed_at_ms"] = json!(millis(&worker_state));
-        }
-        let _ = reply.send(result);
-        worker_state.changed.notify_one();
-    });
-    *packet.task.lock().expect("scoped ACK task") = Some(task.abort_handle());
-    if state.closed.load(Ordering::SeqCst) {
-        task.abort();
-    }
-    drop(task);
-    state.changed.notify_one();
-    response
-        .await
-        .map_err(|_| io::Error::new(io::ErrorKind::ConnectionAborted, "scoped ACK queue ended"))?
-        .map(Interception::Handled)
-}

crates/e2e_test/src/storage_api.rs

@@ -70,9 +70,6 @@ pub(crate) mod multipart_rpc_delay {
 #[cfg(test)]
 pub(crate) mod multipart_fence_acceptance {
     pub(crate) use super::RUSTFS_META_MULTIPART_BUCKET;
-
-    /// Targeted lock diagnostics for the metadata-delay quorum case.
-    pub(crate) const LOCK_DIAGNOSTICS_FILTER: &str = "warn,rustfs_lock::distributed_lock=debug,rustfs_ecstore::object_lock_diag=trace,rustfs_ecstore::cluster::rpc::remote_locker=info";
 }
 
 #[cfg(test)]
@@ -83,14 +80,3 @@ pub(crate) mod multipart_source_rpc {
         PublicationIdentity, SourceGeneration, SourceGeometry, SourceLineage,
     };
 }
-
-#[cfg(test)]
-pub(crate) mod scanner_peer_bucket {
-    use rustfs_ecstore::api::disk as ecstore_disk;
-    use rustfs_ecstore::api::erasure as ecstore_erasure;
-    use rustfs_ecstore::api::rpc as ecstore_rpc;
-
-    pub(crate) use ecstore_disk::{BUCKET_META_PREFIX, RUSTFS_META_BUCKET};
-    pub(crate) use ecstore_erasure::{ReedSolomonEncoder, calc_shard_size};
-    pub(crate) use ecstore_rpc::PeerRestClient;
-}

crates/e2e_test/src/upgrade_compatibility_test.rs

@@ -1112,9 +1112,8 @@ async fn wait_for_upgrade_writes(
             match response {
                 Ok(Ok(_)) => break,
                 Ok(Err(error)) => {
-                    let code = error.as_service_error().and_then(ProvideErrorMetadata::code);
                     if error.raw_response().map(|response| response.status().as_u16()) != Some(503)
-                        || !matches!(code, Some("ServiceUnavailable" | "SlowDown" | "SlowDownRead"))
+                        || error.as_service_error().and_then(ProvideErrorMetadata::code) != Some("ServiceUnavailable")
                     {
                         return Err(format!("{phase}: node {node} {probe} failed: {error:?}").into());
                     }

crates/ecstore/Cargo.toml

@@ -31,7 +31,6 @@ workspace = true
 
 [features]
 default = []
-fips = ["rustfs-s3-client/fips", "rustfs-utils/fips"]
 diagnostic-read-version-caller = ["rustfs-io-metrics/diagnostic-read-version-caller"]
 # Sampled wall/CPU diagnostics only; does not change the read backend.
 diagnostic-local-batch = ["rustix/time"]
@@ -226,11 +225,9 @@ metrics = { workspace = true }
 # The guard scripts/check_no_tokio_io_uring.sh allows an explicit
 # io-uring integration; only the tokio "io-uring" runtime feature is banned.
 [target.'cfg(target_os = "linux")'.dependencies]
-# Native completion owners keep physical I/O leases alive after cancellation.
-rustfs-uring = { git = "https://github.com/rustfs/uring.git", rev = "eb8fc160e71d804427de1e905f5c226d580f71bf" }
-
-[target.'cfg(target_os = "linux")'.dev-dependencies]
-rustfs-uring = { git = "https://github.com/rustfs/uring.git", rev = "eb8fc160e71d804427de1e905f5c226d580f71bf", features = ["fault-injection"] }
+# SharedReadBudget and the bounded read APIs are available in the 0.3.0
+# registry release; keep the application on the published contract.
+rustfs-uring = "0.3.0"
 
 [target.'cfg(windows)'.dependencies]
 winapi-util.workspace = true

crates/ecstore/src/api/mod.rs

@@ -447,9 +447,6 @@ pub mod data_usage {
 }
 
 pub mod disk {
-    pub use crate::cluster::rpc::background_pipe::{BackgroundPipeReader, BackgroundPipeWriter, background_pipe};
-    pub use crate::cluster::rpc::background_reader_stream::BackgroundReaderStream;
-    pub use crate::disk::background_memory::BackgroundEncodeBuffer;
     pub use crate::disk::disk_store::get_object_disk_read_timeout;
     pub use crate::disk::local::{ReplacementExecutionLease, ScanGuard};
     #[cfg(feature = "test-util")]
@@ -478,10 +475,6 @@ pub mod disk {
         UpdateMetadataOpts, VolumeInfo, WalkDirOptions, is_quota_mutation_fence_path, new_disk,
         validate_batch_read_version_item_count,
     };
-    pub use crate::disk::{
-        BackgroundMemoryBudget, PhysicalDiskBinding, PhysicalDiskPlan, PhysicalDiskSample, PhysicalDiskSampler,
-        PhysicalResourcePlan, RemoteBackgroundIo, with_background_resource_unit, with_remote_background_io,
-    };
     pub use bytes::Bytes;
     pub use endpoint::Endpoint;
     pub use error::DiskError;
@@ -622,7 +615,6 @@ pub mod rio {
 }
 
 pub mod rpc {
-    pub use crate::cluster::rpc::http_auth::with_rpc_background_request;
     pub use crate::cluster::rpc::{
         AuthenticatedChannel, KMS_SIGNAL_SUBSYSTEM, LocalPeerS3Client, MAX_NETWORK_PROBE_BYTES, MAX_NETWORK_PROBE_DURATION,
         NetworkPeerProbeClient, NetworkPeerProbeError, NetworkPeerProbeMeasurement, NetworkPeerTarget, PEER_RESTDRY_RUN,
@@ -632,8 +624,8 @@ pub mod rpc {
         TONIC_RPC_PREFIX, TonicInterceptor, build_put_file_auth_trailer, check_and_record_signed_rpc_nonce,
         decode_heal_bucket_rpc_options, encode_heal_bucket_rpc_options, gen_signature_headers, gen_tonic_replay_scope_headers,
         gen_tonic_signature_headers, gen_tonic_signature_interceptor, node_service_time_out_client,
-        node_service_time_out_client_no_auth, normalize_tonic_rpc_audience, rpc_background_admission,
-        set_tonic_canonical_body_digest, sign_ns_scanner_capability, sign_ns_scanner_capability_with_checkpoint_coverage,
+        node_service_time_out_client_no_auth, normalize_tonic_rpc_audience, set_tonic_canonical_body_digest,
+        sign_ns_scanner_capability, sign_ns_scanner_capability_with_checkpoint_coverage,
         sign_ns_scanner_capability_with_tier_registry_generation, sign_put_file_capability, sign_tonic_rpc_response_proof,
         tonic_boot_epoch_challenge, tonic_boot_epoch_response_headers, tonic_rpc_auth_failure_reason,
         verify_ns_scanner_capability, verify_ns_scanner_capability_with_checkpoint_coverage,
@@ -683,9 +675,8 @@ pub mod storage {
     pub use crate::store::HealWalkVersion;
     pub use crate::store::{
         BootstrapLocalTarget, ECStore, SCANNER_PUBLICATION_LEASE_TTL_MS, ScannerDataMovementPauseStatus, all_local_disk,
-        all_local_disk_path, find_local_disk_by_ref, find_local_disk_by_ref_for_rpc, init_local_disks,
-        init_local_disks_with_instance_ctx, init_lock_clients, prewarm_local_disk_id_map,
-        prewarm_local_disk_id_map_with_instance_ctx,
+        all_local_disk_path, find_local_disk_by_ref, init_local_disks, init_local_disks_with_instance_ctx, init_lock_clients,
+        prewarm_local_disk_id_map, prewarm_local_disk_id_map_with_instance_ctx,
     };
     pub use crate::store::{HealObjectAbsenceProof, HealObjectStorageResult};
 }

crates/ecstore/src/bucket/metadata.rs

@@ -1503,11 +1503,7 @@ pub(crate) async fn load_bucket_metadata_parse_with_presence(
     bucket: &str,
     parse: bool,
 ) -> Result<(BucketMetadata, bool)> {
-    let (metadata_res, incarnation_res) = tokio::join!(
-        Box::pin(read_bucket_metadata(api.clone(), bucket)),
-        Box::pin(load_bucket_incarnation(api.clone(), bucket)),
-    );
-    let (mut bm, persisted) = match metadata_res {
+    let (mut bm, persisted) = match read_bucket_metadata(api.clone(), bucket).await {
         Ok(res) => (res, true),
         Err(err) => {
             if err != Error::ConfigNotFound {
@@ -1518,7 +1514,7 @@ pub(crate) async fn load_bucket_metadata_parse_with_presence(
         }
     };
 
-    let incarnation = incarnation_res?;
+    let incarnation = load_bucket_incarnation(api.clone(), bucket).await?;
     if persisted {
         if bm.name.is_empty() {
             bm.name = bucket.to_string();

crates/ecstore/src/bucket/metadata_sys.rs

@@ -683,7 +683,6 @@ pub(crate) async fn update_validated_in<F>(
     bucket: &str,
     config_file: &str,
     data: Vec<u8>,
-    expected_incarnation_id: Option<Uuid>,
     validate: F,
 ) -> Result<OffsetDateTime>
 where
@@ -691,7 +690,7 @@ where
 {
     Box::pin(async {
         let sys = require_bucket_metadata_sys_in(ctx)?;
-        let guard = acquire_config_write_guard_for_incarnation(sys.clone(), bucket, expected_incarnation_id).await?;
+        let guard = acquire_config_write_guard(sys.clone(), bucket).await?;
         validate()?;
         update_under_config_write_guard(sys, &guard, config_file, data, None).await
     })
@@ -1436,7 +1435,6 @@ pub(crate) async fn get_object_lock_config_state_in(
 
 /// Re-read the Object Lock state and bucket incarnation from the same
 /// authoritative metadata blob while the caller holds the transaction lock.
-#[cfg(all(test, feature = "test-util"))]
 pub(crate) async fn get_object_lock_config_and_incarnation_from_disk_in(
     ctx: &crate::runtime::instance::InstanceContext,
     bucket: &str,
@@ -1455,27 +1453,6 @@ pub(crate) async fn get_object_lock_config_and_incarnation_from_disk_with_guard_
     get_delete_config_from_disk_in(ctx, bucket, guard, None).await
 }
 
-#[allow(clippy::type_complexity)]
-pub(crate) async fn get_object_lock_and_quota_config_from_disk_with_guard_in(
-    ctx: &crate::runtime::instance::InstanceContext,
-    bucket: &str,
-    guard: Option<&rustfs_lock::NamespaceLockGuard>,
-) -> Result<(
-    ObjectLockConfigState,
-    Uuid,
-    OffsetDateTime,
-    std::result::Result<(Option<BucketQuota>, Uuid, OffsetDateTime), String>,
-)> {
-    let (state, incarnation_id, updated_at, quota_res) =
-        get_delete_and_quota_config_from_disk_in(ctx, bucket, guard, None, true).await?;
-    Ok((
-        state,
-        incarnation_id,
-        updated_at,
-        quota_res.unwrap_or(Ok((None, incarnation_id, updated_at))),
-    ))
-}
-
 /// Validate queued expiration against the same fresh metadata used for Object
 /// Lock admission. The caller holds the transaction read lock through commit,
 /// so a successful lifecycle update cannot be followed by an old-policy delete.
@@ -1485,24 +1462,6 @@ pub(crate) async fn get_delete_config_from_disk_in(
     guard: Option<&rustfs_lock::NamespaceLockGuard>,
     expiry_policy: Option<&rustfs_lifecycle::ExpiryPolicySnapshot>,
 ) -> Result<(ObjectLockConfigState, Uuid, OffsetDateTime)> {
-    let (state, incarnation_id, updated_at, _) =
-        get_delete_and_quota_config_from_disk_in(ctx, bucket, guard, expiry_policy, false).await?;
-    Ok((state, incarnation_id, updated_at))
-}
-
-#[allow(clippy::type_complexity)]
-async fn get_delete_and_quota_config_from_disk_in(
-    ctx: &crate::runtime::instance::InstanceContext,
-    bucket: &str,
-    guard: Option<&rustfs_lock::NamespaceLockGuard>,
-    expiry_policy: Option<&rustfs_lifecycle::ExpiryPolicySnapshot>,
-    include_quota: bool,
-) -> Result<(
-    ObjectLockConfigState,
-    Uuid,
-    OffsetDateTime,
-    Option<std::result::Result<(Option<BucketQuota>, Uuid, OffsetDateTime), String>>,
-)> {
     let bucket_meta_sys_lock = bucket_metadata_sys_of(ctx)?;
     let bucket_meta_sys = bucket_meta_sys_lock.read().await.clone();
 
@@ -1518,7 +1477,7 @@ async fn get_delete_and_quota_config_from_disk_in(
                 .await?
         }
     };
-    match &authority {
+    match authority {
         BucketMetadataAuthority::Authoritative(metadata)
             if metadata.bucket_incarnation_sidecar && !metadata.bucket_incarnation_id.is_nil() =>
         {
@@ -1530,11 +1489,11 @@ async fn get_delete_and_quota_config_from_disk_in(
                 }
             }
             let object_lock_config_updated_at = metadata.object_lock_config_updated_at;
-            let state = object_lock_config_state_from_authoritative_metadata(metadata)?;
-            let incarnation_id = metadata.bucket_incarnation_id;
-            let quota_res = include_quota
-                .then(|| quota_config_and_incarnation_from_authority(bucket, authority).map_err(|err| err.to_string()));
-            Ok((state, incarnation_id, object_lock_config_updated_at, quota_res))
+            Ok((
+                object_lock_config_state_from_authoritative_metadata(&metadata)?,
+                metadata.bucket_incarnation_id,
+                object_lock_config_updated_at,
+            ))
         }
         BucketMetadataAuthority::Authoritative(_) => {
             Err(Error::other(format!("bucket incarnation metadata is not authoritative: {bucket}")))
@@ -1605,23 +1564,6 @@ pub(crate) async fn get_quota_config_and_incarnation_from_disk_for_options_in(
         return Err(Error::other("quota snapshot metadata transaction fence was released"));
     }
 
-    #[cfg(test)]
-    let has_injected_error = sys.object_lock_disk_read_errors.read().await.contains(bucket);
-    #[cfg(not(test))]
-    let has_injected_error = false;
-    if !ctx.lock_manager().is_disabled()
-        && !has_injected_error
-        && let Some(fresh_quota) = snapshot.take_fresh_put_quota()
-    {
-        if snapshot_guard.is_lock_lost()
-            || snapshot_guard.is_released()
-            || !snapshot.is_valid_for_destructive_put(store.id, bucket, opts.expected_bucket_incarnation_id.unwrap_or_default())
-        {
-            return Err(Error::other("quota snapshot fence or bucket incarnation changed during the disk read"));
-        }
-        return fresh_quota.map_err(Error::other);
-    }
-
     // The snapshot carries the caller's lifecycle fence, excluding deletion.
     // Its transaction guard excludes config writes, so a same-name object
     // owner need not recursively acquire the bucket namespace here.
@@ -1808,22 +1750,9 @@ struct MetadataPublishGuard {
     _guard: tokio::sync::OwnedMutexGuard<MetadataPublishLockState>,
 }
 
-static LOCAL_META_MUTATION_GEN: std::sync::atomic::AtomicU64 = std::sync::atomic::AtomicU64::new(1);
-
-pub(crate) fn bump_local_meta_mutation_gen() {
-    LOCAL_META_MUTATION_GEN.fetch_add(1, std::sync::atomic::Ordering::Release);
-}
-
-pub(crate) fn current_local_meta_mutation_gen() -> u64 {
-    LOCAL_META_MUTATION_GEN.load(std::sync::atomic::Ordering::Acquire)
-}
-
-type LocalAuthorityCache = Arc<StdMutex<HashMap<String, (u64, Arc<BucketMetadata>)>>>;
-
 #[derive(Debug, Clone)]
 pub struct BucketMetadataSys {
     metadata_map: Arc<RwLock<HashMap<String, Arc<BucketMetadata>>>>,
-    local_authority_cache: LocalAuthorityCache,
     /// Serializes metadata-map commits and their derived cache updates for one
     /// bucket. Namespace locks, when present, are acquired before this lock.
     metadata_publish_locks: Arc<MetadataPublishLockRegistry>,
@@ -1867,7 +1796,6 @@ impl BucketMetadataSys {
     pub fn new(api: Arc<ECStore>) -> Self {
         Self {
             metadata_map: Arc::new(RwLock::new(HashMap::new())),
-            local_authority_cache: Arc::new(StdMutex::new(HashMap::new())),
             metadata_publish_locks: Arc::new(MetadataPublishLockRegistry {
                 locks: StdMutex::new(HashMap::new()),
             }),
@@ -1902,15 +1830,6 @@ impl BucketMetadataSys {
         self.api.upgrade()
     }
 
-    /// Whether the backing `ECStore` has been dropped.
-    ///
-    /// Used by `InstanceContext::clear_bucket_metadata_sys_if_stale` during
-    /// `ECStore::drop` so a shared bootstrap context does not retain a
-    /// `BucketMetadataSys` whose weak handle is dangling.
-    pub(crate) fn is_store_stale(&self) -> bool {
-        self.api.upgrade().is_none()
-    }
-
     fn metadata_publish_lock(&self, bucket: &str) -> Arc<Mutex<MetadataPublishLockState>> {
         Self::bucket_lock_in(&self.metadata_publish_locks, bucket)
     }
@@ -2241,7 +2160,6 @@ impl BucketMetadataSys {
     }
 
     pub async fn set(&self, bucket: String, bm: Arc<BucketMetadata>) {
-        bump_local_meta_mutation_gen();
         if !is_meta_bucketname(&bucket) {
             let publish_lock = self.metadata_publish_lock(&bucket);
             let _publish_guard = publish_lock.lock().await;
@@ -2260,7 +2178,6 @@ impl BucketMetadataSys {
     ///
     /// Returns `true` if an entry was present. Reserved meta buckets are ignored.
     pub async fn remove(&self, bucket: &str) -> bool {
-        bump_local_meta_mutation_gen();
         if is_meta_bucketname(bucket) {
             return false;
         }
@@ -2281,7 +2198,6 @@ impl BucketMetadataSys {
     }
 
     async fn _reset(&mut self) {
-        bump_local_meta_mutation_gen();
         let mut map = self.metadata_map.write().await;
         map.clear();
         drop(map);
@@ -3085,77 +3001,30 @@ impl BucketMetadataSys {
             return Err(Error::other(format!("injected Object Lock metadata disk read failure: {bucket}")));
         }
 
-        let store = self.object_store();
-        let can_use_local_authority_cache = !store.ctx.lock_manager().is_disabled() && store.all_disks_local_and_online();
-        let gen_before = current_local_meta_mutation_gen();
-        let cached_authority = can_use_local_authority_cache
-            .then(|| {
-                self.local_authority_cache
-                    .lock()
-                    .unwrap_or_else(std::sync::PoisonError::into_inner)
-                    .get(bucket)
-                    .filter(|(cached_gen, _)| *cached_gen == gen_before)
-                    .map(|(_, bm)| Arc::clone(bm))
-            })
-            .flatten();
-        if let Some(cached) = cached_authority {
-            await_bucket_namespace_operation(
-                Some(guard),
-                bucket,
-                "bucket metadata authoritative snapshot",
-                std::future::ready(Ok::<_, Error>(())),
-            )
-            .await?;
-            if current_local_meta_mutation_gen() == gen_before && store.all_disks_local_and_online() {
-                return Ok(BucketMetadataAuthority::Authoritative(cached));
-            }
-        }
-
-        let (bucket_info_res, metadata_res) = tokio::join!(
-            Box::pin(await_bucket_namespace_operation(
-                Some(guard),
-                bucket,
-                "bucket metadata snapshot existence check",
-                async {
-                    store
-                        .get_bucket_info_from_sets_at_read_quorum(
-                            bucket,
-                            &crate::storage_api_contracts::bucket::BucketOptions::default(),
-                        )
-                        .await
-                },
-            )),
-            Box::pin(await_bucket_namespace_operation(
-                Some(guard),
-                bucket,
-                "bucket metadata authoritative snapshot",
-                load_bucket_metadata_parse_with_presence(Arc::clone(&store), bucket, true),
-            )),
-        );
-        match bucket_info_res {
+        match await_bucket_namespace_operation(Some(guard), bucket, "bucket metadata snapshot existence check", async {
+            self.object_store()
+                .get_bucket_info_from_sets_at_read_quorum(bucket, &crate::storage_api_contracts::bucket::BucketOptions::default())
+                .await
+        })
+        .await
+        {
             Ok(_) => {}
             Err(Error::VolumeNotFound) => return Ok(BucketMetadataAuthority::MissingBucket),
             Err(err) => return Err(err),
         }
 
-        let (metadata, persisted) = metadata_res?;
+        let (metadata, persisted) = await_bucket_namespace_operation(
+            Some(guard),
+            bucket,
+            "bucket metadata authoritative snapshot",
+            load_bucket_metadata_parse_with_presence(self.object_store(), bucket, true),
+        )
+        .await?;
         if persisted && metadata.lock_enabled && !metadata.bucket_creation_committed {
             return Err(Error::ErasureWriteQuorum);
         }
         if persisted {
-            let metadata = Arc::new(metadata);
-            if can_use_local_authority_cache
-                && metadata.bucket_incarnation_sidecar
-                && !metadata.bucket_incarnation_id.is_nil()
-                && current_local_meta_mutation_gen() == gen_before
-                && store.all_disks_local_and_online()
-            {
-                self.local_authority_cache
-                    .lock()
-                    .unwrap_or_else(std::sync::PoisonError::into_inner)
-                    .insert(bucket.to_string(), (gen_before, Arc::clone(&metadata)));
-            }
-            Ok(BucketMetadataAuthority::Authoritative(metadata))
+            Ok(BucketMetadataAuthority::Authoritative(Arc::new(metadata)))
         } else {
             Ok(BucketMetadataAuthority::Fabricated)
         }
@@ -5210,61 +5079,6 @@ mod tests {
         );
     }
 
-    #[tokio::test]
-    #[serial]
-    async fn validated_config_update_rejects_a_different_bucket_incarnation() {
-        let (_dirs, store) = isolated_store_over_temp_disks().await;
-        init_bucket_metadata_sys(store.clone(), Vec::new()).await;
-        let bucket = "catalog-cleanup-incarnation";
-        store
-            .make_bucket(bucket, &MakeBucketOptions::default())
-            .await
-            .expect("create bucket");
-        let incarnation = store
-            .bucket_incarnation_id_from_disk(bucket)
-            .await
-            .expect("read bucket incarnation");
-        let called = std::sync::atomic::AtomicBool::new(false);
-        let result = store
-            .update_bucket_metadata_config_for_incarnation_validated(
-                bucket,
-                "quota.json",
-                br#"{"quota":1}"#.to_vec(),
-                Uuid::new_v4(),
-                || {
-                    called.store(true, std::sync::atomic::Ordering::SeqCst);
-                    Ok(())
-                },
-            )
-            .await;
-        assert!(matches!(result, Err(Error::BucketNotFound(name)) if name == bucket));
-        assert!(
-            !called.load(std::sync::atomic::Ordering::SeqCst),
-            "incarnation must be checked before the external fence"
-        );
-        let (metadata, _) = get_config_from_disk_with_presence_in(&store.ctx, bucket)
-            .await
-            .expect("read unchanged bucket metadata");
-        assert!(
-            metadata.quota_config_json.is_empty(),
-            "a stale cleanup must not modify the replacement bucket"
-        );
-        store
-            .update_bucket_metadata_config_for_incarnation_validated(
-                bucket,
-                "quota.json",
-                br#"{"quota":1}"#.to_vec(),
-                incarnation,
-                || Ok(()),
-            )
-            .await
-            .expect("the current incarnation permits the validated update");
-        let (metadata, _) = get_config_from_disk_with_presence_in(&store.ctx, bucket)
-            .await
-            .expect("read updated bucket metadata");
-        assert_eq!(metadata.quota_config_json, br#"{"quota":1}"#);
-    }
-
     #[tokio::test]
     #[serial]
     async fn quota_admission_rejects_stale_cached_no_quota() {

crates/ecstore/src/bucket/replication/replication_pool.rs

@@ -3421,7 +3421,6 @@ mod tests {
         allow_first_read: Notify,
         read_count: AtomicUsize,
         delete_storage_calls: AtomicUsize,
-        delete_error: StdMutex<EcstoreError>,
         reported_size: StdMutex<Option<i64>>,
         stream_read_bytes: Arc<AtomicUsize>,
         write_count: AtomicUsize,
@@ -3673,12 +3672,7 @@ mod tests {
             _opts: Self::ObjectOptions,
         ) -> Result<Self::ObjectInfo, Self::Error> {
             self.shared.delete_storage_calls.fetch_add(1, Ordering::SeqCst);
-            Err(self
-                .shared
-                .delete_error
-                .lock()
-                .expect("delete error lock should not be poisoned")
-                .clone())
+            Err(EcstoreError::NotImplemented)
         }
 
         async fn delete_objects(
@@ -4177,7 +4171,6 @@ mod tests {
             allow_first_read: Notify::new(),
             read_count: AtomicUsize::new(0),
             delete_storage_calls: AtomicUsize::new(0),
-            delete_error: StdMutex::new(EcstoreError::NotImplemented),
             reported_size: StdMutex::new(None),
             stream_read_bytes: Arc::new(AtomicUsize::new(0)),
             write_count: AtomicUsize::new(0),
@@ -4228,103 +4221,6 @@ mod tests {
         }
     }
 
-    #[tokio::test]
-    async fn delete_worker_already_purged_source_completes_without_retry() {
-        let arn = "arn:test";
-        for delete_marker_version in [false, true] {
-            for version_id in [Uuid::new_v4(), Uuid::nil()] {
-                for error in [
-                    EcstoreError::VersionNotFound("source".to_string(), "purged".to_string(), version_id.to_string()),
-                    EcstoreError::ObjectNotFound("source".to_string(), "purged".to_string()),
-                    EcstoreError::FileVersionNotFound,
-                    EcstoreError::FileNotFound,
-                ] {
-                    let shared = empty_resync_shared_state();
-                    *shared.delete_error.lock().expect("delete error lock should not be poisoned") = error;
-                    let storage = Arc::new(LoadResyncNodeStore::new("purged-source", shared.clone()));
-                    let delete = DeletedObjectReplicationInfo {
-                        bucket: "source".to_string(),
-                        delete_object: ReplicationDeletedObject {
-                            object_name: "purged".to_string(),
-                            version_id: (!delete_marker_version).then_some(version_id),
-                            delete_marker_version_id: delete_marker_version.then_some(version_id),
-                            replication_state: Some(ReplicationState {
-                                replicate_decision_str: test_replicate_decision(&[arn]).to_string(),
-                                purge_targets: HashMap::from([(arn.to_string(), VersionPurgeStatusType::Complete)]),
-                                ..Default::default()
-                            }),
-                            ..Default::default()
-                        },
-                        op_type: ReplicationType::Delete,
-                        ..Default::default()
-                    };
-
-                    assert!(
-                        replicate_delete_with_outcome(delete, storage).await,
-                        "a confirmed target purge must complete when the source is already absent (marker={delete_marker_version}, version={version_id})"
-                    );
-                    assert_eq!(
-                        shared.delete_storage_calls.load(Ordering::SeqCst),
-                        2 + usize::from(!delete_marker_version && !version_id.is_nil()),
-                        "the worker must lock and attempt writeback, reading a non-null data version first"
-                    );
-                }
-            }
-        }
-    }
-
-    #[tokio::test]
-    async fn delete_worker_missing_source_does_not_hide_unfinished_replication() {
-        let arn = "arn:test";
-        for (version_purge, target_status, error) in [
-            (
-                true,
-                VersionPurgeStatusType::Pending,
-                EcstoreError::ObjectNotFound("source".to_string(), "purged".to_string()),
-            ),
-            (true, VersionPurgeStatusType::Complete, EcstoreError::ErasureWriteQuorum),
-            (
-                false,
-                VersionPurgeStatusType::Empty,
-                EcstoreError::ObjectNotFound("source".to_string(), "purged".to_string()),
-            ),
-        ] {
-            let shared = empty_resync_shared_state();
-            *shared.delete_error.lock().expect("delete error lock should not be poisoned") = error;
-            let storage = Arc::new(LoadResyncNodeStore::new("unfinished-delete", shared));
-            let delete = DeletedObjectReplicationInfo {
-                bucket: "source".to_string(),
-                delete_object: ReplicationDeletedObject {
-                    object_name: "purged".to_string(),
-                    version_id: version_purge.then(Uuid::new_v4),
-                    delete_marker: !version_purge,
-                    replication_state: Some(ReplicationState {
-                        replicate_decision_str: test_replicate_decision(&[arn]).to_string(),
-                        targets: if version_purge {
-                            HashMap::new()
-                        } else {
-                            HashMap::from([(arn.to_string(), ReplicationStatusType::Completed)])
-                        },
-                        purge_targets: if version_purge {
-                            HashMap::from([(arn.to_string(), target_status)])
-                        } else {
-                            HashMap::new()
-                        },
-                        ..Default::default()
-                    }),
-                    ..Default::default()
-                },
-                op_type: ReplicationType::Delete,
-                ..Default::default()
-            };
-
-            assert!(
-                !replicate_delete_with_outcome(delete, storage).await,
-                "unfinished target work, source I/O failures, and marker creation must remain retryable"
-            );
-        }
-    }
-
     #[tokio::test]
     async fn delete_worker_preserves_persisted_admission_without_live_config() {
         let arn = "arn:test";
@@ -5408,7 +5304,6 @@ mod tests {
                 allow_first_read: Notify::new(),
                 read_count: AtomicUsize::new(0),
                 delete_storage_calls: AtomicUsize::new(0),
-                delete_error: StdMutex::new(EcstoreError::NotImplemented),
                 reported_size: StdMutex::new(None),
                 stream_read_bytes: Arc::new(AtomicUsize::new(0)),
                 write_count: AtomicUsize::new(0),

crates/ecstore/src/bucket/replication/replication_resyncer.rs

@@ -2809,22 +2809,17 @@ pub(crate) async fn replicate_delete_with_outcome<S: ReplicationStorage>(
             true
         }
         Err(e) => {
-            // A batch purge or another worker may have removed this version
-            // already. Remote failures still control the final outcome below.
-            let source_already_purged = is_version_purge && (is_err_object_not_found(&e) || is_err_version_not_found(&e));
-            if !source_already_purged {
-                error!(
-                    event = EVENT_RESYNC_TARGET_OPERATION_FAILED,
-                    component = LOG_COMPONENT_ECSTORE,
-                    subsystem = LOG_SUBSYSTEM_REPLICATION_RESYNC,
-                    bucket = %bucket,
-                    arn = %dobj.target_arn,
-                    object = %dobj.delete_object.object_name,
-                    operation = "apply_replication_delete_state",
-                    error = %e,
-                    "Replication target operation failed"
-                );
-            }
+            error!(
+                event = EVENT_RESYNC_TARGET_OPERATION_FAILED,
+                component = LOG_COMPONENT_ECSTORE,
+                subsystem = LOG_SUBSYSTEM_REPLICATION_RESYNC,
+                bucket = %bucket,
+                arn = %dobj.target_arn,
+                object = %dobj.delete_object.object_name,
+                operation = "apply_replication_delete_state",
+                error = %e,
+                "Replication target operation failed"
+            );
             send_event(EventArgs {
                 event_name,
                 bucket_name: bucket.clone(),
@@ -2837,7 +2832,7 @@ pub(crate) async fn replicate_delete_with_outcome<S: ReplicationStorage>(
                 },
                 ..Default::default()
             });
-            source_already_purged
+            false
         }
     };
 
@@ -3287,18 +3282,10 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
 
     let mut join_set = JoinSet::new();
     let mut all_succeeded = true;
-    let mut target_infos = Vec::with_capacity(tgt_arns.len());
 
     for arn in tgt_arns {
         let Some(tgt_client) = ReplicationTargetStore::remote_target_client(bucket, &arn).await else {
             all_succeeded = false;
-            target_infos.push(force_delete_target_info(
-                dobj.op_type,
-                &arn,
-                "",
-                false,
-                Err(TARGET_CLIENT_UNAVAILABLE_ERROR.to_string()),
-            ));
             debug!(
                 event = EVENT_REPLICATION_FORCE_DELETE_SKIPPED,
                 component = LOG_COMPONENT_ECSTORE,
@@ -3324,7 +3311,6 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
 
         let bucket = bucket.clone();
         let object_name = object_name.clone();
-        let op_type = dobj.op_type;
 
         join_set.spawn(async move {
             if ReplicationTargetStore::target_is_offline(&tgt_client).await {
@@ -3349,16 +3335,9 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
                     user_agent: "Internal: [Replication]".to_string(),
                     ..Default::default()
                 });
-                return force_delete_target_info(
-                    op_type,
-                    &tgt_client.arn,
-                    &tgt_client.endpoint,
-                    tgt_client.secure,
-                    Err(FORCE_DELETE_TARGET_OFFLINE_ERROR.to_string()),
-                );
+                return false;
             }
 
-            let started = Instant::now();
             if let Err(e) = tgt_client
                 .remove_object(&tgt_client.bucket, &object_name, None, replication_force_delete_remove_options())
                 .await
@@ -3385,25 +3364,16 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
                     user_agent: "Internal: [Replication]".to_string(),
                     ..Default::default()
                 });
-                return force_delete_target_info(
-                    op_type,
-                    &tgt_client.arn,
-                    &tgt_client.endpoint,
-                    tgt_client.secure,
-                    Err(e.to_string()),
-                );
+                return false;
             }
 
-            force_delete_target_info(op_type, &tgt_client.arn, &tgt_client.endpoint, tgt_client.secure, Ok(started.elapsed()))
+            true
         });
     }
 
     while let Some(result) = join_set.join_next().await {
         match result {
-            Ok(info) => {
-                all_succeeded &= info.replication_status == ReplicationStatusType::Completed;
-                target_infos.push(info);
-            }
+            Ok(success) => all_succeeded &= success,
             Err(error) => {
                 all_succeeded = false;
                 error!(
@@ -3420,8 +3390,6 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
         }
     }
 
-    record_force_delete_target_stats(bucket, &target_infos).await;
-
     if all_succeeded
         && let Some(operation_id) = dobj.delete_object.force_delete_id
         && let Err(error) = super::replication_pool::complete_force_delete_intent(storage, operation_id).await
@@ -3441,53 +3409,6 @@ async fn replicate_force_delete_to_targets<S: ReplicationStorage>(dobj: &Deleted
     all_succeeded
 }
 
-const FORCE_DELETE_TARGET_OFFLINE_ERROR: &str = "replication target is offline";
-
-/// One target's outcome of a replicated force-delete in the shape the
-/// replication statistics consume. A force-delete carries no per-version
-/// replication state, so the previous status is always `Pending`: that is
-/// the transition `ReplicationStats::update` counts as a failure, whereas an
-/// `Empty` previous status would drop the outcome and leave `replication
-/// status` reporting zero failures while the peer still holds the objects.
-fn force_delete_target_info(
-    op_type: ReplicationType,
-    arn: &str,
-    endpoint: &str,
-    secure: bool,
-    outcome: std::result::Result<std::time::Duration, String>,
-) -> ReplicatedTargetInfo {
-    let mut rinfo = ReplicatedTargetInfo {
-        arn: arn.to_string(),
-        op_type,
-        endpoint: endpoint.to_string(),
-        secure,
-        prev_replication_status: ReplicationStatusType::Pending,
-        ..Default::default()
-    };
-    match outcome {
-        Ok(duration) => {
-            rinfo.replication_status = ReplicationStatusType::Completed;
-            rinfo.duration = duration;
-        }
-        Err(error) => {
-            rinfo.replication_status = ReplicationStatusType::Failed;
-            rinfo.error = Some(error);
-        }
-    }
-    rinfo
-}
-
-async fn record_force_delete_target_stats(bucket: &str, targets: &[ReplicatedTargetInfo]) {
-    let Some(stats) = runtime_sources::replication_stats() else {
-        return;
-    };
-    for target in targets {
-        stats
-            .update(bucket, target, target.replication_status.clone(), target.prev_replication_status.clone())
-            .await;
-    }
-}
-
 fn unavailable_delete_target_info(dobj: &DeletedObjectReplicationInfo, arn: &str) -> ReplicatedTargetInfo {
     let mut rinfo = dobj
         .delete_object
@@ -7523,51 +7444,6 @@ mod tests {
         server.join().expect("test HTTP server should finish");
     }
 
-    /// A force-delete the peer rejects must reach the replication failure
-    /// counters. A replicated force-delete used to only log the rejection, so
-    /// `replication status` reported zero failures while the sites diverged.
-    #[tokio::test]
-    async fn force_delete_target_outcomes_reach_replication_stats() {
-        let stats = super::super::replication_state::ReplicationStats::new();
-        let denied = force_delete_target_info(
-            ReplicationType::Delete,
-            "arn:rustfs:replication::denied:bucket",
-            "http://peer-a:9000",
-            false,
-            Err("remove_object failed: AccessDenied".to_string()),
-        );
-        assert_eq!(denied.replication_status, ReplicationStatusType::Failed);
-        assert_eq!(denied.prev_replication_status, ReplicationStatusType::Pending);
-        assert_eq!(denied.error.as_deref(), Some("remove_object failed: AccessDenied"));
-
-        let accepted = force_delete_target_info(
-            ReplicationType::Heal,
-            "arn:rustfs:replication::accepted:bucket",
-            "https://peer-b:9000",
-            true,
-            Ok(std::time::Duration::from_millis(3)),
-        );
-        assert_eq!(accepted.replication_status, ReplicationStatusType::Completed);
-        assert!(accepted.error.is_none());
-
-        for target in [&denied, &accepted] {
-            stats
-                .update(
-                    "bucket",
-                    target,
-                    target.replication_status.clone(),
-                    target.prev_replication_status.clone(),
-                )
-                .await;
-        }
-
-        let bucket_stats = stats.get("bucket").await;
-        let denied_stat = bucket_stats.stats.get(&denied.arn).expect("denied target: stats entry");
-        assert_eq!((denied_stat.failed.count, denied_stat.replicated_count), (1, 0));
-        let accepted_stat = bucket_stats.stats.get(&accepted.arn).expect("accepted target: stats entry");
-        assert_eq!((accepted_stat.failed.count, accepted_stat.replicated_count), (0, 1));
-    }
-
     /// AWS answers `HEAD ?versionId=<source marker id>` with a bodiless 400.
     /// The marker is verified through the latest version instead: a
     /// versionless 404 with `x-amz-delete-marker: true` proves it propagated.

crates/ecstore/src/cache_value/metacache_set.rs

@@ -747,16 +747,6 @@ async fn list_path_raw_inner(
             // Start every missing head read in the same round so one stalled
             // disk cannot multiply the wait budget by the erasure-set width.
             // Outcomes are still consumed below in stable disk-index order.
-            if !revjob_rx.is_cancelled() {
-                for (i, reader) in readers.iter_mut().enumerate() {
-                    if errs[i].is_none()
-                        && pending_entries[i].is_none()
-                        && let Some(Ok(Some(entry))) = reader.try_peek_buffered()
-                    {
-                        pending_entries[i] = Some(entry);
-                    }
-                }
-            }
             let concurrent_peeks = readers.iter_mut().enumerate().filter_map(|(i, reader)| {
                 if errs[i].is_some() || pending_entries[i].is_some() {
                     return None;
@@ -888,7 +878,7 @@ async fn list_path_raw_inner(
                 }
                 if entry.name == current.name {
                     // If exact match, we agree.
-                    if current.matches_strict_borrowed(&entry) {
+                    if current.matches_strict(&entry) {
                         top_entries[i] = Some(entry);
                         agree += 1;
                     } else {
@@ -996,9 +986,7 @@ async fn list_path_raw_inner(
 
             if agree == readers.len() && !opts.preserve_replica_metadata {
                 for r in readers.iter_mut() {
-                    if !r.skip_current() {
-                        let _ = r.skip(1).await;
-                    }
+                    let _ = r.skip(1).await;
                 }
 
                 if let Some(agreed_fn) = opts.agreed.as_ref() {
@@ -1021,7 +1009,7 @@ async fn list_path_raw_inner(
             }
 
             for (i, r) in readers.iter_mut().enumerate() {
-                if top_entries[i].is_some() && !r.skip_current() {
+                if top_entries[i].is_some() {
                     let _ = r.skip(1).await;
                 }
             }

crates/ecstore/src/cluster/rpc/background_pipe.rs

@@ -1,682 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use crate::disk::background_memory::BackgroundBuffer;
-use std::io::{self, IoSlice};
-use std::pin::Pin;
-use std::sync::{Arc, Mutex};
-use std::task::{Context, Poll, Waker, ready};
-use tokio::io::{AsyncRead, AsyncWrite, DuplexStream, ReadBuf};
-
-pub struct BackgroundPipeReader {
-    inner: PipeEnd,
-}
-
-pub struct BackgroundPipeWriter {
-    inner: PipeEnd,
-}
-
-impl BackgroundPipeWriter {
-    /// Capture only the payload owner, without retaining node or physical units.
-    pub fn memory_budget(&self) -> Option<Arc<crate::disk::BackgroundMemoryBudget>> {
-        match &self.inner {
-            PipeEnd::Foreground(_) => None,
-            PipeEnd::Background(state) => state
-                .lock()
-                .unwrap_or_else(std::sync::PoisonError::into_inner)
-                .buffer
-                .memory_budget(),
-        }
-    }
-}
-
-enum PipeEnd {
-    Foreground(DuplexStream),
-    Background(Arc<Mutex<PipeState>>),
-}
-
-// The pipe lock may reserve memory. The memory budget never locks a pipe.
-struct PipeState {
-    buffer: BackgroundBuffer,
-    read_offset: usize,
-    readable: usize,
-    capacity: usize,
-    reader_closed: bool,
-    writer_closed: bool,
-    admission_failure: Option<io::ErrorKind>,
-    read_waker: Option<Waker>,
-    write_waker: Option<Waker>,
-}
-
-/// Capture only memory ownership while the request is admitted. Payload storage
-/// is reserved and initialized once, before the first nonempty background write.
-pub fn background_pipe(capacity: usize) -> (BackgroundPipeReader, BackgroundPipeWriter) {
-    let capacity = capacity.max(1);
-    let memory = crate::disk::current_resource_unit().and_then(|resources| resources.memory_budget());
-    match memory {
-        Some(memory) => {
-            let state = Arc::new(Mutex::new(PipeState {
-                buffer: BackgroundBuffer::new(Some(memory)),
-                read_offset: 0,
-                readable: 0,
-                capacity,
-                reader_closed: false,
-                writer_closed: false,
-                admission_failure: None,
-                read_waker: None,
-                write_waker: None,
-            }));
-            (
-                BackgroundPipeReader {
-                    inner: PipeEnd::Background(state.clone()),
-                },
-                BackgroundPipeWriter {
-                    inner: PipeEnd::Background(state),
-                },
-            )
-        }
-        None => {
-            let (reader, writer) = tokio::io::duplex(capacity);
-            (
-                BackgroundPipeReader {
-                    inner: PipeEnd::Foreground(reader),
-                },
-                BackgroundPipeWriter {
-                    inner: PipeEnd::Foreground(writer),
-                },
-            )
-        }
-    }
-}
-
-fn advance_ring(offset: usize, count: usize, capacity: usize) -> usize {
-    let to_end = capacity - offset;
-    if count < to_end { offset + count } else { count - to_end }
-}
-
-fn poll_background_read(state: &Mutex<PipeState>, cx: &mut Context<'_>, output: &mut ReadBuf<'_>) -> Poll<io::Result<()>> {
-    if output.remaining() == 0 {
-        return Poll::Ready(Ok(()));
-    }
-    let mut state = state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-    if state.readable == 0 {
-        if let Some(kind) = state.admission_failure.take() {
-            drop(state);
-            return Poll::Ready(Err(io::Error::new(kind, "background pipe storage admission failed")));
-        }
-        if state.writer_closed {
-            return Poll::Ready(Ok(()));
-        }
-        let replaced = state.read_waker.replace(cx.waker().clone());
-        drop(state);
-        drop(replaced);
-        return Poll::Pending;
-    }
-    let length = state.readable.min(output.remaining());
-    let first = length.min(state.capacity - state.read_offset);
-    output.put_slice(&state.buffer.as_slice()[state.read_offset..state.read_offset + first]);
-    output.put_slice(&state.buffer.as_slice()[..length - first]);
-    state.read_offset = advance_ring(state.read_offset, length, state.capacity);
-    state.readable -= length;
-    let wake = state.write_waker.take();
-    drop(state);
-    if let Some(wake) = wake {
-        wake.wake();
-    }
-    Poll::Ready(Ok(()))
-}
-
-fn poll_background_write(state: &Mutex<PipeState>, cx: &mut Context<'_>, input: &[IoSlice<'_>]) -> Poll<io::Result<usize>> {
-    let mut state = state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-    if state.reader_closed || state.writer_closed {
-        return Poll::Ready(Err(io::ErrorKind::BrokenPipe.into()));
-    }
-    if input.iter().all(|part| part.is_empty()) {
-        return Poll::Ready(Ok(0));
-    }
-    let available = state.capacity - state.readable;
-    if available == 0 {
-        let replaced = state.write_waker.replace(cx.waker().clone());
-        drop(state);
-        drop(replaced);
-        return Poll::Pending;
-    }
-    let capacity = state.capacity;
-    if let Err(error) = state.buffer.ensure_len(capacity) {
-        // Legacy walk completion may suppress ordinary producer errors. A new
-        // pipe admission failure must also reach the reader instead of EOF.
-        state.admission_failure = Some(error.kind());
-        state.writer_closed = true;
-        let wake = state.read_waker.take();
-        drop(state);
-        if let Some(wake) = wake {
-            wake.wake();
-        }
-        return Poll::Ready(Err(error));
-    }
-    let mut offset = advance_ring(state.read_offset, state.readable, capacity);
-    let mut written = 0;
-    for part in input {
-        let length = part.len().min(available - written);
-        let first = length.min(capacity - offset);
-        state.buffer.as_mut_slice()[offset..offset + first].copy_from_slice(&part[..first]);
-        state.buffer.as_mut_slice()[..length - first].copy_from_slice(&part[first..length]);
-        offset = advance_ring(offset, length, capacity);
-        written += length;
-        if written == available {
-            break;
-        }
-    }
-    state.readable += written;
-    let wake = state.read_waker.take();
-    drop(state);
-    if let Some(wake) = wake {
-        wake.wake();
-    }
-    Poll::Ready(Ok(written))
-}
-
-impl AsyncRead for BackgroundPipeReader {
-    fn poll_read(self: Pin<&mut Self>, cx: &mut Context<'_>, output: &mut ReadBuf<'_>) -> Poll<io::Result<()>> {
-        match &mut self.get_mut().inner {
-            PipeEnd::Foreground(reader) => Pin::new(reader).poll_read(cx, output),
-            PipeEnd::Background(state) => {
-                let coop = ready!(tokio::task::coop::poll_proceed(cx));
-                let result = poll_background_read(state, cx, output);
-                if result.is_ready() {
-                    coop.made_progress();
-                }
-                result
-            }
-        }
-    }
-}
-
-impl AsyncWrite for BackgroundPipeWriter {
-    fn poll_write(self: Pin<&mut Self>, cx: &mut Context<'_>, input: &[u8]) -> Poll<io::Result<usize>> {
-        match &mut self.get_mut().inner {
-            PipeEnd::Foreground(writer) => Pin::new(writer).poll_write(cx, input),
-            PipeEnd::Background(state) => {
-                let coop = ready!(tokio::task::coop::poll_proceed(cx));
-                let result = poll_background_write(state, cx, &[IoSlice::new(input)]);
-                if result.is_ready() {
-                    coop.made_progress();
-                }
-                result
-            }
-        }
-    }
-
-    fn poll_write_vectored(self: Pin<&mut Self>, cx: &mut Context<'_>, input: &[IoSlice<'_>]) -> Poll<io::Result<usize>> {
-        match &mut self.get_mut().inner {
-            PipeEnd::Foreground(writer) => Pin::new(writer).poll_write_vectored(cx, input),
-            PipeEnd::Background(state) => {
-                let coop = ready!(tokio::task::coop::poll_proceed(cx));
-                let result = poll_background_write(state, cx, input);
-                if result.is_ready() {
-                    coop.made_progress();
-                }
-                result
-            }
-        }
-    }
-
-    fn is_write_vectored(&self) -> bool {
-        match &self.inner {
-            PipeEnd::Foreground(writer) => writer.is_write_vectored(),
-            PipeEnd::Background(_) => true,
-        }
-    }
-
-    fn poll_flush(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
-        match &mut self.get_mut().inner {
-            PipeEnd::Foreground(writer) => Pin::new(writer).poll_flush(cx),
-            PipeEnd::Background(_) => Poll::Ready(Ok(())),
-        }
-    }
-
-    fn poll_shutdown(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
-        match &mut self.get_mut().inner {
-            PipeEnd::Foreground(writer) => Pin::new(writer).poll_shutdown(cx),
-            PipeEnd::Background(state) => {
-                let mut state = state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-                state.writer_closed = true;
-                let wake = state.read_waker.take();
-                drop(state);
-                if let Some(wake) = wake {
-                    wake.wake();
-                }
-                Poll::Ready(Ok(()))
-            }
-        }
-    }
-}
-
-impl Drop for BackgroundPipeReader {
-    fn drop(&mut self) {
-        if let PipeEnd::Background(state) = &self.inner {
-            let mut state = state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-            state.reader_closed = true;
-            let wake = state.write_waker.take();
-            let cancelled = state.read_waker.take();
-            drop(state);
-            drop(cancelled);
-            if let Some(wake) = wake {
-                wake.wake();
-            }
-        }
-    }
-}
-
-impl Drop for BackgroundPipeWriter {
-    fn drop(&mut self) {
-        if let PipeEnd::Background(state) = &self.inner {
-            let mut state = state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-            state.writer_closed = true;
-            let wake = state.read_waker.take();
-            let cancelled = state.write_waker.take();
-            drop(state);
-            drop(cancelled);
-            if let Some(wake) = wake {
-                wake.wake();
-            }
-        }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::disk::BackgroundMemoryBudget;
-    use std::sync::atomic::{AtomicUsize, Ordering};
-    use std::time::Duration;
-    use tokio::io::{AsyncReadExt, AsyncWriteExt};
-
-    pub(super) fn budget(capacity: usize) -> Arc<BackgroundMemoryBudget> {
-        let budget = BackgroundMemoryBudget::new();
-        budget.set_sampled_limit(u64::try_from(capacity).expect("test capacity fits u64"), Duration::from_secs(30));
-        budget
-    }
-
-    pub(super) fn local_pipe(
-        memory: &Arc<BackgroundMemoryBudget>,
-        capacity: usize,
-    ) -> (BackgroundPipeReader, BackgroundPipeWriter) {
-        let state = Arc::new(Mutex::new(PipeState {
-            buffer: BackgroundBuffer::new(Some(memory.clone())),
-            read_offset: 0,
-            readable: 0,
-            capacity,
-            reader_closed: false,
-            writer_closed: false,
-            admission_failure: None,
-            read_waker: None,
-            write_waker: None,
-        }));
-        (
-            BackgroundPipeReader {
-                inner: PipeEnd::Background(state.clone()),
-            },
-            BackgroundPipeWriter {
-                inner: PipeEnd::Background(state),
-            },
-        )
-    }
-
-    pub(super) fn write_now(writer: &mut (impl AsyncWrite + Unpin), bytes: &[u8]) -> Poll<io::Result<usize>> {
-        Pin::new(writer).poll_write(&mut Context::from_waker(Waker::noop()), bytes)
-    }
-
-    pub(super) fn read_now(reader: &mut (impl AsyncRead + Unpin), bytes: &mut [u8]) -> Poll<io::Result<usize>> {
-        let mut output = ReadBuf::new(bytes);
-        match Pin::new(reader).poll_read(&mut Context::from_waker(Waker::noop()), &mut output) {
-            Poll::Ready(Ok(())) => Poll::Ready(Ok(output.filled().len())),
-            Poll::Ready(Err(error)) => Poll::Ready(Err(error)),
-            Poll::Pending => Poll::Pending,
-        }
-    }
-    #[test]
-    fn fixed_ring_allocates_lazily_once_and_keeps_last_owner_charged() {
-        for capacity in [1, 7, 64 * 1024, 1024 * 1024] {
-            let memory = budget(capacity);
-            let (mut reader, mut writer) = local_pipe(&memory, capacity);
-            assert_eq!(memory.snapshot().used, 0);
-            assert!(matches!(write_now(&mut writer, &[]), Poll::Ready(Ok(0))));
-            assert_eq!(memory.snapshot().used, 0);
-            assert!(matches!(write_now(&mut writer, b"x"), Poll::Ready(Ok(1))));
-            assert_eq!(memory.snapshot().used, capacity as u64);
-            memory.set_sampled_limit(0, Duration::ZERO);
-            let mut output = [0];
-            assert!(matches!(read_now(&mut reader, &mut output), Poll::Ready(Ok(1))));
-            assert_eq!(output, *b"x");
-            assert!(matches!(write_now(&mut writer, b"y"), Poll::Ready(Ok(1))));
-            drop(writer);
-            assert_eq!(memory.snapshot().used, capacity as u64, "reader still owns the real ring");
-            assert!(matches!(read_now(&mut reader, &mut output), Poll::Ready(Ok(1))));
-            assert_eq!(output, *b"y");
-            assert!(matches!(read_now(&mut reader, &mut output), Poll::Ready(Ok(0))));
-            assert_eq!(memory.snapshot().used, capacity as u64, "draining does not destroy allocation ownership");
-            drop(reader);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[test]
-    fn admission_error_reaches_writer_and_reader_once_without_payload() {
-        for sample in [None, Some((6, Duration::from_secs(30))), Some((7, Duration::ZERO))] {
-            let memory = BackgroundMemoryBudget::new();
-            if let Some((limit, validity)) = sample {
-                memory.set_sampled_limit(limit, validity);
-            }
-            let (mut reader, mut writer) = local_pipe(&memory, 7);
-            let error = match write_now(&mut writer, b"x") {
-                Poll::Ready(Err(e)) => e,
-                _ => panic!("reject before copying first payload"),
-            };
-            assert!(
-                crate::disk::background_memory::is_memory_pressure(&error),
-                "writer retains the original budget marker"
-            );
-            assert_eq!(memory.snapshot().used, 0);
-            let error = match read_now(&mut reader, &mut [0]) {
-                Poll::Ready(Err(e)) => e,
-                _ => panic!("reader must see a pipe admission failure"),
-            };
-            assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-            assert!(matches!(read_now(&mut reader, &mut [0]), Poll::Ready(Ok(0))), "failure is delivered once");
-            assert!(matches!(write_now(&mut writer,b"x"),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::BrokenPipe));
-            drop((reader, writer));
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[test]
-    fn allocation_overflow_is_a_reader_failure_without_a_leaked_reservation() {
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(u64::MAX, Duration::from_secs(30));
-        let (mut reader, mut writer) = local_pipe(&memory, usize::MAX);
-        assert!(matches!(write_now(&mut writer,b"x"),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::OutOfMemory));
-        assert_eq!(memory.snapshot().used, 0);
-        assert!(matches!(read_now(&mut reader,&mut[0]),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::OutOfMemory));
-    }
-
-    #[test]
-    fn scalar_and_vectored_wrap_match_a_reference_queue() {
-        use std::collections::VecDeque;
-        for capacity in [1, 3, 7, 31] {
-            let memory = budget(capacity);
-            let (mut reader, mut writer) = local_pipe(&memory, capacity);
-            let mut expected = VecDeque::new();
-            let mut next = 0u8;
-            for turn in 0..300 {
-                let input: Vec<_> = (0..(turn % 11 + 1))
-                    .map(|_| {
-                        let byte = next;
-                        next = next.wrapping_add(1);
-                        byte
-                    })
-                    .collect();
-                let available = capacity - expected.len();
-                let written = if turn % 2 == 0 {
-                    write_now(&mut writer, &input)
-                } else {
-                    let split = input.len() / 2;
-                    Pin::new(&mut writer).poll_write_vectored(
-                        &mut Context::from_waker(Waker::noop()),
-                        &[
-                            io::IoSlice::new(&[]),
-                            io::IoSlice::new(&input[..split]),
-                            io::IoSlice::new(&input[split..]),
-                        ],
-                    )
-                };
-                if available == 0 {
-                    assert!(written.is_pending());
-                } else {
-                    let accepted = input.len().min(available);
-                    assert!(matches!(written,Poll::Ready(Ok(n)) if n==accepted));
-                    expected.extend(&input[..accepted]);
-                }
-                let mut output = vec![0; turn % 5 + 1];
-                let count = output.len().min(expected.len());
-                assert!(matches!(read_now(&mut reader,&mut output),Poll::Ready(Ok(n)) if n==count));
-                for byte in &output[..count] {
-                    assert_eq!(Some(*byte), expected.pop_front());
-                }
-                assert_eq!(memory.snapshot().used, capacity as u64);
-            }
-            drop(writer);
-            let mut output = vec![0; capacity];
-            let count = expected.len();
-            assert!(matches!(read_now(&mut reader,&mut output),Poll::Ready(Ok(n)) if n==count));
-            assert_eq!(&output[..count], expected.into_iter().collect::<Vec<_>>().as_slice());
-            assert!(matches!(read_now(&mut reader, &mut output), Poll::Ready(Ok(0))));
-            drop(reader);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn reader_drop_wakes_blocked_writer_and_writer_drop_wakes_empty_reader() {
-        let memory = budget(7);
-        let (reader, mut writer) = local_pipe(&memory, 7);
-        writer.write_all(b"1234567").await.expect("fill the ring");
-        let task = tokio::spawn(async move { writer.write_all(b"blocked").await });
-        tokio::task::yield_now().await;
-        assert!(!task.is_finished());
-        drop(reader);
-        let error = tokio::time::timeout(Duration::from_secs(1), task)
-            .await
-            .expect("reader drop wakes writer")
-            .expect("writer task joins")
-            .expect_err("closed reader is BrokenPipe");
-        assert_eq!(error.kind(), io::ErrorKind::BrokenPipe);
-        assert_eq!(memory.snapshot().used, 0);
-        let (mut reader, writer) = local_pipe(&memory, 7);
-        let task = tokio::spawn(async move { reader.read(&mut [0]).await });
-        tokio::task::yield_now().await;
-        assert!(!task.is_finished());
-        drop(writer);
-        assert_eq!(
-            tokio::time::timeout(Duration::from_secs(1), task)
-                .await
-                .expect("writer drop wakes reader")
-                .expect("reader task joins")
-                .expect("clean EOF"),
-            0
-        );
-    }
-
-    #[tokio::test]
-    async fn read_wakes_a_full_writer_without_changing_byte_limit() {
-        let memory = budget(7);
-        let (mut reader, mut writer) = local_pipe(&memory, 7);
-        writer.write_all(b"1234567").await.expect("fill initial byte limit");
-        let task = tokio::spawn(async move {
-            writer.write_all(b"x").await.expect("resume after one byte is read");
-            writer
-        });
-        tokio::task::yield_now().await;
-        assert!(!task.is_finished());
-        let mut first = [0];
-        reader.read_exact(&mut first).await.expect("read one byte");
-        let writer = tokio::time::timeout(Duration::from_secs(1), task)
-            .await
-            .expect("read wakes writer")
-            .expect("writer joins");
-        assert_eq!(&first, b"1");
-        drop(writer);
-        let mut all = Vec::new();
-        reader.read_to_end(&mut all).await.expect("drain wrapped bytes");
-        assert_eq!(all, b"234567x");
-        drop(reader);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn shutdown_drains_then_eof_and_cancelled_writes_accept_nothing() {
-        let memory = budget(7);
-        let (mut reader, mut writer) = local_pipe(&memory, 7);
-        writer
-            .write_all(b"1234567")
-            .await
-            .expect("fill before cancelling a blocked write");
-        {
-            let blocked = writer.write(b"lost");
-            tokio::pin!(blocked);
-            assert!(futures::poll!(&mut blocked).is_pending());
-        }
-        writer.shutdown().await.expect("shutdown does not discard buffered bytes");
-        assert!(matches!(write_now(&mut writer,b"x"),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::BrokenPipe));
-        let mut out = Vec::new();
-        reader.read_to_end(&mut out).await.expect("drain after shutdown");
-        assert_eq!(out, b"1234567");
-        drop(reader);
-        assert_eq!(memory.snapshot().used, 7, "writer still holds the allocation");
-        drop(writer);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[test]
-    fn foreground_keeps_native_duplex_semantics() {
-        let (reader, mut writer) = background_pipe(7);
-        assert!(matches!(write_now(&mut writer, b"12345678"), Poll::Ready(Ok(7))));
-        assert!(write_now(&mut writer, b"x").is_pending());
-        drop(reader);
-        assert!(matches!(write_now(&mut writer,b"x"),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::BrokenPipe));
-        let (mut reader, writer) = background_pipe(7);
-        drop(writer);
-        assert!(matches!(read_now(&mut reader, &mut [0]), Poll::Ready(Ok(0))));
-    }
-
-    #[test]
-    fn cancelled_reader_leaves_the_real_ring_charged_until_writer_drop() {
-        let memory = budget(7);
-        let (reader, mut writer) = local_pipe(&memory, 7);
-        assert!(matches!(write_now(&mut writer, b"x"), Poll::Ready(Ok(1))));
-        drop(reader);
-        assert_eq!(memory.snapshot().used, 7, "the surviving writer still owns the ring allocation");
-        assert!(matches!(write_now(&mut writer,b"y"),Poll::Ready(Err(e)) if e.kind()==io::ErrorKind::BrokenPipe));
-        drop(writer);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[test]
-    fn runtime_shutdown_releases_queued_writer_but_not_the_surviving_reader() {
-        let runtime = tokio::runtime::Builder::new_current_thread()
-            .enable_all()
-            .build()
-            .expect("build isolated runtime");
-        let memory = budget(7);
-        let (reader, mut writer) = local_pipe(&memory, 7);
-        runtime.block_on(async {
-            writer.write_all(b"x").await.expect("allocate ring before runtime shutdown");
-            tokio::spawn(async move {
-                let _writer = writer;
-                std::future::pending::<()>().await;
-            });
-            tokio::task::yield_now().await;
-        });
-        drop(runtime);
-        assert_eq!(memory.snapshot().used, 7, "reader holds the actual allocation after runtime cancellation");
-        drop(reader);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn ready_operations_keep_tokio_cooperative_yields() {
-        let memory = budget(7);
-        let (_reader, mut writer) = local_pipe(&memory, 7);
-        let observed = Arc::new(AtomicUsize::new(0));
-        let flag = observed.clone();
-        let task = tokio::spawn(async move {
-            flag.store(1, Ordering::SeqCst);
-        });
-        for _ in 0..1000 {
-            assert_eq!(writer.write(&[]).await.expect("empty operation remains successful"), 0);
-        }
-        assert_eq!(
-            observed.load(Ordering::SeqCst),
-            1,
-            "ready pipe operations must not starve other ready tasks"
-        );
-        task.await.expect("observer task joins");
-    }
-}
-
-#[cfg(test)]
-mod waker_tests {
-    use super::*;
-    use std::sync::{
-        Weak,
-        atomic::{AtomicUsize, Ordering},
-    };
-    use std::task::Wake;
-
-    struct LockCheck {
-        state: Weak<Mutex<PipeState>>,
-        wakes: Arc<AtomicUsize>,
-        drops: Arc<AtomicUsize>,
-    }
-    impl LockCheck {
-        fn unlocked(&self) {
-            if let Some(state) = self.state.upgrade() {
-                assert!(state.try_lock().is_ok(), "waker code must run outside the pipe lock");
-            }
-        }
-    }
-    impl Wake for LockCheck {
-        fn wake(self: Arc<Self>) {
-            self.unlocked();
-            self.wakes.fetch_add(1, Ordering::SeqCst);
-        }
-    }
-    impl Drop for LockCheck {
-        fn drop(&mut self) {
-            self.unlocked();
-            self.drops.fetch_add(1, Ordering::SeqCst);
-        }
-    }
-
-    #[test]
-    fn replaced_and_woken_reader_and_writer_wakers_run_outside_the_lock() {
-        for waiting_reader in [true, false] {
-            let memory = super::tests::budget(7);
-            let (mut reader, mut writer) = super::tests::local_pipe(&memory, 7);
-            let PipeEnd::Background(state) = &reader.inner else { panic!("background fixture") };
-            let weak = Arc::downgrade(state);
-            let wakes = Arc::new(AtomicUsize::new(0));
-            let drops = Arc::new(AtomicUsize::new(0));
-            if !waiting_reader {
-                assert!(matches!(super::tests::write_now(&mut writer, b"1234567"), Poll::Ready(Ok(7))));
-            }
-            for _ in 0..2 {
-                let waker = Waker::from(Arc::new(LockCheck {
-                    state: weak.clone(),
-                    wakes: wakes.clone(),
-                    drops: drops.clone(),
-                }));
-                let mut cx = Context::from_waker(&waker);
-                if waiting_reader {
-                    let mut bytes = [0];
-                    assert!(
-                        Pin::new(&mut reader)
-                            .poll_read(&mut cx, &mut ReadBuf::new(&mut bytes))
-                            .is_pending()
-                    );
-                } else {
-                    assert!(Pin::new(&mut writer).poll_write(&mut cx, b"x").is_pending());
-                }
-                drop(waker);
-            }
-            assert_eq!(drops.load(Ordering::SeqCst), 1, "the replaced waker has been dropped");
-            if waiting_reader {
-                assert!(matches!(super::tests::write_now(&mut writer, b"x"), Poll::Ready(Ok(1))));
-            } else {
-                assert!(matches!(super::tests::read_now(&mut reader, &mut [0]), Poll::Ready(Ok(1))));
-            }
-            assert_eq!(wakes.load(Ordering::SeqCst), 1);
-            assert_eq!(drops.load(Ordering::SeqCst), 2);
-        }
-    }
-}

crates/ecstore/src/cluster/rpc/background_reader_stream.rs

@@ -1,586 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use crate::disk::background_memory::{BackgroundMemoryBudget, Reservation};
-use bytes::{Bytes, BytesMut};
-use futures::Stream;
-use std::io;
-use std::pin::Pin;
-use std::sync::Arc;
-use std::task::{Context, Poll};
-use tokio::io::{AsyncRead, ReadBuf};
-use tokio_util::io::ReaderStream;
-
-struct ReservedReadBytes {
-    // Free each payload view before releasing its shared allocation receipt.
-    bytes: Bytes,
-    _reservation: Arc<Reservation>,
-}
-
-impl AsRef<[u8]> for ReservedReadBytes {
-    fn as_ref(&self) -> &[u8] {
-        &self.bytes
-    }
-}
-
-struct ReaderBuffer {
-    // These initialized bytes are spare storage, not unconsumed source data.
-    bytes: BytesMut,
-    reservation: Option<Arc<Reservation>>,
-    budget: Arc<BackgroundMemoryBudget>,
-    capacity: usize,
-}
-
-impl ReaderBuffer {
-    fn new(budget: Arc<BackgroundMemoryBudget>, capacity: usize) -> Self {
-        Self {
-            bytes: BytesMut::new(),
-            reservation: None,
-            budget,
-            capacity: capacity.max(1),
-        }
-    }
-
-    fn clear(&mut self) {
-        self.bytes = BytesMut::new();
-        self.reservation = None;
-    }
-
-    fn ensure_readable(&mut self) -> io::Result<()> {
-        if !self.bytes.is_empty() {
-            return Ok(());
-        }
-        if self.reservation.is_some() {
-            if self.bytes.try_reclaim(self.capacity) {
-                self.bytes.resize(self.capacity, 0);
-                return Ok(());
-            }
-            // A live output owns this allocation. Drop our empty view before
-            // its receipt, then reserve independent replacement storage.
-            self.clear();
-        }
-        let reservation = self.budget.reserve(self.capacity)?;
-        let mut bytes = Vec::new();
-        bytes
-            .try_reserve_exact(self.capacity)
-            .map_err(|_| io::ErrorKind::OutOfMemory)?;
-        bytes.resize(self.capacity, 0);
-        // Fresh ordinary Bytes is unique and spans the complete allocation.
-        // Unlike from_owner output, this conversion cannot require a copy.
-        let bytes = Bytes::from(bytes.into_boxed_slice())
-            .try_into_mut()
-            .map_err(|_| io::Error::other("fresh reader storage was not unique"))?;
-        self.bytes = bytes;
-        self.reservation = Some(Arc::new(reservation));
-        Ok(())
-    }
-
-    fn take_bytes(&mut self, length: usize) -> io::Result<Bytes> {
-        let reservation = self
-            .reservation
-            .as_ref()
-            .cloned()
-            .ok_or_else(|| io::Error::other("reader storage has no memory reservation"))?;
-        Ok(Bytes::from_owner(ReservedReadBytes {
-            bytes: self.bytes.split_to(length).freeze(),
-            _reservation: reservation,
-        }))
-    }
-}
-
-/// RPC response chunks retain their background memory reservation until the
-/// last clone or slice is dropped. Foreground readers use the existing stream.
-pub struct BackgroundReaderStream<R> {
-    inner: ReaderState<R>,
-}
-
-enum ReaderState<R> {
-    Foreground(ReaderStream<R>),
-    Background { reader: Option<R>, buffer: ReaderBuffer },
-}
-
-impl<R: AsyncRead> BackgroundReaderStream<R> {
-    /// Capture memory ownership inside the admitted scope, before moving the
-    /// response body out of it. This stream retains no node or device capacity.
-    pub fn with_capacity(reader: R, capacity: usize) -> Self {
-        let memory = crate::disk::current_resource_unit().and_then(|resources| resources.memory_budget());
-        let inner = match memory {
-            Some(memory) => ReaderState::Background {
-                reader: Some(reader),
-                buffer: ReaderBuffer::new(memory, capacity),
-            },
-            None => ReaderState::Foreground(ReaderStream::with_capacity(reader, capacity)),
-        };
-        Self { inner }
-    }
-}
-
-impl<R: AsyncRead + Unpin> Stream for BackgroundReaderStream<R> {
-    type Item = io::Result<Bytes>;
-
-    fn poll_next(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
-        let this = self.get_mut();
-        match &mut this.inner {
-            ReaderState::Foreground(reader) => Pin::new(reader).poll_next(cx),
-            ReaderState::Background { reader, buffer } => {
-                let Some(inner) = reader.as_mut() else {
-                    return Poll::Ready(None);
-                };
-                if let Err(error) = buffer.ensure_readable() {
-                    *reader = None;
-                    return Poll::Ready(Some(Err(error)));
-                }
-                let mut output = ReadBuf::new(&mut buffer.bytes);
-                match std::task::ready!(Pin::new(inner).poll_read(cx, &mut output)) {
-                    Ok(()) => {
-                        let length = output.filled().len();
-                        if length == 0 {
-                            buffer.clear();
-                            *reader = None;
-                            Poll::Ready(None)
-                        } else {
-                            let bytes = buffer.take_bytes(length);
-                            if bytes.is_err() {
-                                buffer.clear();
-                                *reader = None;
-                            }
-                            Poll::Ready(Some(bytes))
-                        }
-                    }
-                    Err(error) => {
-                        buffer.clear();
-                        *reader = None;
-                        Poll::Ready(Some(Err(error)))
-                    }
-                }
-            }
-        }
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-    use futures::StreamExt;
-    use std::sync::Arc;
-    use std::sync::atomic::{AtomicUsize, Ordering};
-    use std::time::Duration;
-    use tokio::io::AsyncWriteExt;
-
-    struct ObservedReader {
-        polls: Arc<AtomicUsize>,
-        fail: bool,
-    }
-
-    impl AsyncRead for ObservedReader {
-        fn poll_read(self: Pin<&mut Self>, _cx: &mut Context<'_>, output: &mut ReadBuf<'_>) -> Poll<io::Result<()>> {
-            self.polls.fetch_add(1, Ordering::SeqCst);
-            if self.fail {
-                Poll::Ready(Err(io::Error::from(io::ErrorKind::PermissionDenied)))
-            } else {
-                output.put_slice(b"data");
-                Poll::Ready(Ok(()))
-            }
-        }
-    }
-
-    #[tokio::test]
-    async fn background_frames_keep_capacity_until_the_last_slice() {
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(16, Duration::from_secs(30));
-        let (resources, gates) = test_resource_units(2);
-        let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            BackgroundReaderStream::with_capacity(io::Cursor::new(b"data"), 16)
-        })
-        .await;
-        assert!(
-            gates.iter().all(|gate| gate.snapshot().active == 0),
-            "the stream captures only memory ownership"
-        );
-        assert_eq!(memory.snapshot().used, 0, "construction does not allocate payload storage");
-        let bytes = stream.next().await.expect("first frame").expect("read frame");
-        assert_eq!(bytes.as_ref(), b"data");
-        assert_eq!(memory.snapshot().used, 16, "charge full capacity rather than visible length");
-        let slice = bytes.slice(1..3);
-        memory.set_sampled_limit(0, Duration::ZERO);
-        drop(bytes);
-        drop(stream);
-        assert_eq!(slice.as_ref(), b"at");
-        assert_eq!(memory.snapshot().used, 16);
-        drop(slice);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn background_denial_happens_before_reading_and_never_falls_back() {
-        for sample in [None, Some((7, Duration::from_secs(30))), Some((8, Duration::ZERO))] {
-            let memory = BackgroundMemoryBudget::new();
-            if let Some((limit, validity)) = sample {
-                memory.set_sampled_limit(limit, validity);
-            }
-            let polls = Arc::new(AtomicUsize::new(0));
-            let (resources, _) = test_resource_units(1);
-            let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                BackgroundReaderStream::with_capacity(
-                    ObservedReader {
-                        polls: polls.clone(),
-                        fail: false,
-                    },
-                    8,
-                )
-            })
-            .await;
-            let error = stream
-                .next()
-                .await
-                .expect("allocation failure")
-                .expect_err("background allocation denied");
-            assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-            assert_eq!(polls.load(Ordering::SeqCst), 0, "denial cannot consume source bytes");
-            assert!(stream.next().await.is_none());
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn background_pending_read_keeps_storage_through_shrink_or_cancellation() {
-        for cancelled in [false, true] {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(16, Duration::from_secs(30));
-            let (resources, _) = test_resource_units(1);
-            let (mut sender, reader) = tokio::io::duplex(4);
-            let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                BackgroundReaderStream::with_capacity(reader, 16)
-            })
-            .await;
-            assert!(futures::poll!(stream.next()).is_pending());
-            memory.set_sampled_limit(0, Duration::ZERO);
-            assert_eq!(memory.snapshot().used, 16);
-            let bytes = if cancelled {
-                None
-            } else {
-                sender.write_all(b"data").await.expect("release pending read");
-                Some(
-                    stream
-                        .next()
-                        .await
-                        .expect("pending frame")
-                        .expect("existing allocation survives shrink"),
-                )
-            };
-            drop(stream);
-            if let Some(bytes) = bytes {
-                assert_eq!(bytes.as_ref(), b"data");
-                assert_eq!(memory.snapshot().used, 16);
-                drop(bytes);
-            }
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn background_read_error_and_eof_release_storage() {
-        for fail in [false, true] {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(8, Duration::from_secs(30));
-            let (resources, _) = test_resource_units(1);
-            let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                let reader: Box<dyn AsyncRead + Unpin> = if fail {
-                    Box::new(ObservedReader {
-                        polls: Arc::new(AtomicUsize::new(0)),
-                        fail: true,
-                    })
-                } else {
-                    Box::new(tokio::io::empty())
-                };
-                BackgroundReaderStream::with_capacity(reader, 8)
-            })
-            .await;
-            if fail {
-                let error = stream.next().await.expect("read failure").expect_err("preserve reader error");
-                assert_eq!(error.kind(), io::ErrorKind::PermissionDenied);
-            }
-            assert!(stream.next().await.is_none());
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn retained_frame_blocks_new_storage_until_released() {
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(8, Duration::from_secs(30));
-        let (resources, _) = test_resource_units(1);
-        let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            BackgroundReaderStream::with_capacity(io::Cursor::new(b"firstonefollowup"), 8)
-        })
-        .await;
-        let first = stream.next().await.expect("first frame").expect("fits exact budget");
-        assert_eq!(first.as_ref(), b"firstone");
-        let error = stream
-            .next()
-            .await
-            .expect("next allocation")
-            .expect_err("held frame exhausts budget");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        assert_eq!(memory.snapshot().used, 8);
-        drop(stream);
-        drop(first);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn consumed_frames_keep_reusable_capacity_until_eof() {
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(8, Duration::from_secs(30));
-        let (resources, _) = test_resource_units(1);
-        let mut stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            BackgroundReaderStream::with_capacity(io::Cursor::new(b"firstonefollowup"), 8)
-        })
-        .await;
-        for expected in [b"firstone", b"followup"] {
-            let bytes = stream.next().await.expect("next frame").expect("released previous capacity");
-            assert_eq!(bytes.as_ref(), expected);
-            assert_eq!(memory.snapshot().used, 8);
-            drop(bytes);
-            assert_eq!(memory.snapshot().used, 8, "the reusable allocation remains owned by the stream");
-        }
-        assert!(stream.next().await.is_none());
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn foreground_stream_and_unpolled_cancellation_preserve_existing_behavior() {
-        let mut stream = BackgroundReaderStream::with_capacity(io::Cursor::new(b"foreground"), 4);
-        assert!(matches!(stream.inner, ReaderState::Foreground(_)));
-        let mut bytes = Vec::new();
-        while let Some(chunk) = stream.next().await {
-            bytes.extend_from_slice(&chunk.expect("foreground chunk"));
-        }
-        assert_eq!(bytes, b"foreground");
-
-        let memory = BackgroundMemoryBudget::new();
-        let (resources, _) = test_resource_units(1);
-        let stream = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            BackgroundReaderStream::with_capacity(tokio::io::empty(), 8)
-        })
-        .await;
-        drop(stream);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-}
-
-#[cfg(test)]
-mod reuse_tests {
-    use super::*;
-    use bytes::Bytes;
-    use futures::StreamExt;
-    use std::sync::Arc;
-    use std::time::Duration;
-    use std::{
-        io,
-        pin::Pin,
-        task::{Context, Poll},
-    };
-    use tokio::io::{AsyncRead, ReadBuf};
-
-    static DATA: [u8; 1024] = [0x37; 1024];
-    struct ShortReader {
-        offset: usize,
-        length: usize,
-        chunk: usize,
-        fail_at: Option<usize>,
-    }
-    impl AsyncRead for ShortReader {
-        fn poll_read(mut self: Pin<&mut Self>, _: &mut Context<'_>, out: &mut ReadBuf<'_>) -> Poll<io::Result<()>> {
-            if self.fail_at == Some(self.offset) {
-                return Poll::Ready(Err(io::ErrorKind::PermissionDenied.into()));
-            }
-            let n = (self.length - self.offset).min(self.chunk).min(out.remaining());
-            out.put_slice(&DATA[self.offset..self.offset + n]);
-            self.offset += n;
-            Poll::Ready(Ok(()))
-        }
-    }
-    fn budget(limit: u64) -> Arc<crate::disk::BackgroundMemoryBudget> {
-        let b = crate::disk::BackgroundMemoryBudget::new();
-        b.set_sampled_limit(limit, Duration::from_secs(30));
-        b
-    }
-    async fn stream<R: AsyncRead>(
-        budget: &Arc<crate::disk::BackgroundMemoryBudget>,
-        reader: R,
-        capacity: usize,
-    ) -> BackgroundReaderStream<R> {
-        let (resources, _) = crate::disk::test_resource_units(1);
-        crate::disk::with_optional_resource_unit(Some(resources.with_memory_budget(budget.clone())), async {
-            BackgroundReaderStream::with_capacity(reader, capacity)
-        })
-        .await
-    }
-    #[tokio::test]
-    async fn complete_consumed_frames_reclaim_the_same_storage_after_expiry() {
-        let b = budget(64);
-        let mut s = stream(&b, io::Cursor::new(&DATA[..]), 64).await;
-        let mut pointer = None;
-        for _ in 0..16 {
-            let frame = s.next().await.expect("next full frame").expect("reclaimed backing");
-            assert_eq!(frame.len(), 64);
-            assert_eq!(frame.as_ref(), &DATA[..64]);
-            if let Some(p) = pointer {
-                assert_eq!(frame.as_ptr(), p);
-            } else {
-                pointer = Some(frame.as_ptr());
-            }
-            b.set_sampled_limit(0, Duration::ZERO);
-            drop(frame);
-            assert_eq!(b.snapshot().used, 64);
-        }
-        assert!(s.next().await.is_none());
-        assert_eq!(b.snapshot().used, 0);
-    }
-    #[tokio::test]
-    async fn short_live_frames_use_disjoint_tail_then_reserve_separate_storage() {
-        let b = budget(32);
-        let mut s = stream(
-            &b,
-            ShortReader {
-                offset: 0,
-                length: 32,
-                chunk: 4,
-                fail_at: None,
-            },
-            16,
-        )
-        .await;
-        let mut frames: Vec<Bytes> = Vec::new();
-        for i in 0..4 {
-            let frame = s.next().await.expect("short frame").expect("remaining initialized tail");
-            if i != 0 {
-                assert_eq!(frame.as_ptr(), frames[0].as_ptr().wrapping_add(i * 4));
-            }
-            assert_eq!(frame.as_ref(), &DATA[..4]);
-            frames.push(frame);
-            assert_eq!(b.snapshot().used, 16);
-        }
-        let next = s.next().await.expect("independent frame").expect("second backing fits");
-        assert_ne!(next.as_ptr(), frames[0].as_ptr());
-        assert_eq!(b.snapshot().used, 32);
-        drop(frames);
-        assert_eq!(b.snapshot().used, 16);
-        drop(s);
-        assert_eq!(b.snapshot().used, 16);
-        drop(next);
-        assert_eq!(b.snapshot().used, 0);
-    }
-    #[tokio::test]
-    async fn final_slice_prevents_reclaim_and_keeps_old_plus_new_charged() {
-        let b = budget(32);
-        let mut s = stream(&b, io::Cursor::new(&DATA[..32]), 16).await;
-        let first = s.next().await.expect("old frame").expect("old backing");
-        let last = first.slice(15..);
-        drop(first);
-        let next = s.next().await.expect("new frame").expect("second backing fits");
-        assert_eq!(last.as_ref(), &DATA[..1]);
-        assert_ne!(next.as_ptr(), last.as_ptr());
-        assert_eq!(b.snapshot().used, 32);
-        drop(s);
-        assert_eq!(b.snapshot().used, 32);
-        drop(next);
-        assert_eq!(b.snapshot().used, 16);
-        drop(last);
-        assert_eq!(b.snapshot().used, 0);
-    }
-    #[tokio::test]
-    async fn expiry_uses_tail_but_rejects_new_storage_before_consuming_source() {
-        let b = budget(16);
-        let mut s = stream(
-            &b,
-            ShortReader {
-                offset: 0,
-                length: 32,
-                chunk: 4,
-                fail_at: None,
-            },
-            16,
-        )
-        .await;
-        let first = s.next().await.expect("first frame").expect("initial backing");
-        b.set_sampled_limit(0, Duration::ZERO);
-        for _ in 0..3 {
-            drop(s.next().await.expect("tail frame").expect("reuse charged storage"));
-        }
-        let error = s
-            .next()
-            .await
-            .expect("new backing denied")
-            .expect_err("live frame prevents reclaim");
-        assert!(crate::disk::background_memory::is_memory_pressure(&error));
-        assert!(s.next().await.is_none());
-        assert_eq!(b.snapshot().used, 16);
-        drop(first);
-        assert_eq!(b.snapshot().used, 0);
-    }
-    #[tokio::test]
-    async fn eof_and_error_release_spare_but_keep_live_output_charged() {
-        for fail_at in [None, Some(4)] {
-            let b = budget(16);
-            let mut s = stream(
-                &b,
-                ShortReader {
-                    offset: 0,
-                    length: 4,
-                    chunk: 4,
-                    fail_at,
-                },
-                16,
-            )
-            .await;
-            let frame = s.next().await.expect("first short frame").expect("payload");
-            match fail_at {
-                None => assert!(s.next().await.is_none()),
-                Some(_) => assert_eq!(
-                    s.next()
-                        .await
-                        .expect("read error")
-                        .expect_err("preserve source failure")
-                        .kind(),
-                    io::ErrorKind::PermissionDenied
-                ),
-            }
-            assert!(s.next().await.is_none());
-            assert_eq!(b.snapshot().used, 16);
-            assert_eq!(frame.as_ref(), &DATA[..4]);
-            drop(frame);
-            assert_eq!(b.snapshot().used, 0);
-        }
-    }
-    #[test]
-    fn runtime_shutdown_drops_a_pending_stream_without_refunding_early() {
-        for abort in [false, true] {
-            let b = budget(16);
-            let rt = tokio::runtime::Builder::new_current_thread()
-                .enable_all()
-                .build()
-                .expect("runtime");
-            let (_tx, reader) = tokio::io::duplex(4);
-            let (began, wait) = tokio::sync::oneshot::channel();
-            let memory = b.clone();
-            let handle = rt.spawn(async move {
-                let mut s = stream(&memory, reader, 16).await;
-                assert!(futures::poll!(s.next()).is_pending());
-                assert_eq!(memory.snapshot().used, 16);
-                began.send(()).expect("notify pending allocation");
-                let _ = s.next().await;
-            });
-            rt.block_on(wait).expect("stream pending");
-            assert_eq!(b.snapshot().used, 16);
-            if abort {
-                handle.abort();
-                let _ = rt.block_on(handle);
-            }
-            drop(rt);
-            assert_eq!(b.snapshot().used, 0);
-        }
-    }
-}

crates/ecstore/src/cluster/rpc/client.rs

@@ -17,10 +17,10 @@ use crate::cluster::rpc::http_auth::RPC_REPLAY_SCOPE_VERSION_HEADER;
 use crate::cluster::rpc::http_auth::{
     AuthenticatedPeerReplayCapabilities, RPC_AUTH_VERSION_HEADER, RPC_AUTH_VERSION_V2, RPC_BOOT_EPOCH_CHALLENGE_HEADER,
     RPC_CONTENT_SHA256_HEADER, RPC_REPLAY_CACHE_CAPABILITY_HEADER, RPC_REPLAY_CACHE_CAPABILITY_PROOF_HEADER,
-    RollingMutationBodyDigest, TIMESTAMP_HEADER, gen_tonic_replay_scope_headers_with_admission, internode_rpc_body_digest_strict,
-    rpc_background_admission, verify_tonic_peer_replay_capabilities_response,
+    RollingMutationBodyDigest, TIMESTAMP_HEADER, internode_rpc_body_digest_strict,
+    verify_tonic_peer_replay_capabilities_response,
 };
-use crate::cluster::rpc::{gen_tonic_signature_headers, normalize_tonic_rpc_audience};
+use crate::cluster::rpc::{gen_tonic_replay_scope_headers, gen_tonic_signature_headers, normalize_tonic_rpc_audience};
 #[cfg(test)]
 use crate::cluster::rpc::{tonic_boot_epoch_challenge, tonic_boot_epoch_response_headers};
 use crate::disk::error::{DiskError, Error as DiskErrorType, RpcStatusError};
@@ -415,16 +415,7 @@ where
                     .get(RPC_CONTENT_SHA256_HEADER)
                     .and_then(|value| value.to_str().ok()),
             ) {
-                match rpc_background_admission(request.headers()).and_then(|background| {
-                    gen_tonic_replay_scope_headers_with_admission(
-                        audience,
-                        request.uri().path(),
-                        timestamp,
-                        content_sha256,
-                        boot_epoch,
-                        background,
-                    )
-                }) {
+                match gen_tonic_replay_scope_headers(audience, request.uri().path(), timestamp, content_sha256, boot_epoch) {
                     Ok(headers) => request.headers_mut().extend(headers),
                     Err(error) => debug!(error = %error, "could not attach replay-scoped RPC signature"),
                 }

crates/ecstore/src/cluster/rpc/http_auth.rs

@@ -32,6 +32,7 @@ use crate::storage_api_contracts::internode::{
     PUT_FILE_AUTH_TRAILER_MAGIC, PUT_FILE_CAPABILITY_VERSION,
 };
 
+use hmac::{Hmac, KeyInit, Mac};
 use http::uri::Authority;
 use http::{HeaderMap, HeaderValue, Method, Uri};
 #[cfg(test)]
@@ -46,7 +47,6 @@ use rustfs_io_metrics::internode_metrics::{
     global_internode_metrics,
 };
 use rustfs_object_data_cache::{MemoryBasis, resolve_effective_memory};
-use rustfs_utils::crypto::{HmacSha256, KeyInit, Mac};
 use rustfs_utils::get_env_bool;
 use sha2::Digest as _;
 use sha2::Sha256;
@@ -58,10 +58,9 @@ use time::OffsetDateTime;
 use tracing::{error, info, warn};
 use uuid::Uuid;
 
+type HmacSha256 = Hmac<Sha256>;
+
 const SIGNATURE_HEADER: &str = "x-rustfs-signature";
-pub const RPC_BACKGROUND_ADMISSION_HEADER: &str = "x-rustfs-rpc-background-admission";
-const RPC_BACKGROUND_ADMISSION_V1: &str = "v1";
-const RPC_BACKGROUND_ADMISSION_DOMAIN: &[u8] = b"rustfs-rpc-background-admission-v1\0";
 pub(crate) const TIMESTAMP_HEADER: &str = "x-rustfs-timestamp";
 pub(crate) const RPC_AUTH_VERSION_HEADER: &str = "x-rustfs-rpc-auth-version";
 const RPC_SIGNATURE_V2_HEADER: &str = "x-rustfs-rpc-signature-v2";
@@ -78,46 +77,6 @@ pub(crate) const RPC_REPLAY_CACHE_CAPABILITY_HEADER: &str = "x-rustfs-rpc-replay
 pub(crate) const RPC_REPLAY_CACHE_CAPABILITY_PROOF_HEADER: &str = "x-rustfs-rpc-replay-cache-capability-proof";
 const RPC_REPLAY_SCOPE_VERSION_V3: &str = "3";
 const RPC_RESPONSE_PROOF_DOMAIN: &[u8] = b"rustfs-rpc-response-proof-v1\0";
-
-tokio::task_local! {
-    static RPC_BACKGROUND_REQUEST: bool;
-}
-
-pub(crate) fn current_rpc_background_request() -> bool {
-    RPC_BACKGROUND_REQUEST
-        .try_with(|background| *background)
-        .unwrap_or_else(|_| crate::disk::has_resource_io_scope())
-}
-
-/// Preserve the authenticated wire class while polling locally admitted work.
-/// This scope carries only the class, never node, disk, or memory ownership.
-pub async fn with_rpc_background_request<F: std::future::Future>(background: bool, operation: F) -> F::Output {
-    RPC_BACKGROUND_REQUEST.scope(background, operation).await
-}
-
-/// Parse the request class only; callers must verify the signature before using it.
-pub fn rpc_background_admission(headers: &HeaderMap) -> std::io::Result<bool> {
-    let mut values = headers.get_all(RPC_BACKGROUND_ADMISSION_HEADER).iter();
-    match (values.next(), values.next()) {
-        (None, None) => Ok(false),
-        (Some(value), None) if value == RPC_BACKGROUND_ADMISSION_V1 => Ok(true),
-        _ => Err(std::io::Error::other("Invalid RPC background admission version")),
-    }
-}
-
-fn bind_background_admission(mac: &mut HmacSha256, background: bool) {
-    if background {
-        // Every auth lane binds the class, so stripping the marker or falling
-        // back to an older signature cannot turn admitted work into foreground I/O.
-        mac.update(RPC_BACKGROUND_ADMISSION_DOMAIN);
-    }
-}
-
-fn insert_background_admission(headers: &mut HeaderMap, background: bool) {
-    if background {
-        headers.insert(RPC_BACKGROUND_ADMISSION_HEADER, HeaderValue::from_static(RPC_BACKGROUND_ADMISSION_V1));
-    }
-}
 const RPC_REPLAY_SCOPE_DOMAIN: &[u8] = b"rustfs-rpc-replay-scope-v3\0";
 const RPC_BOOT_EPOCH_PROOF_DOMAIN: &[u8] = b"rustfs-rpc-boot-epoch-proof-v1\0";
 const RPC_REPLAY_CACHE_CAPABILITY_PROOF_DOMAIN: &[u8] = b"rustfs-rpc-replay-cache-capability-proof-v1\0";
@@ -560,23 +519,21 @@ fn redacted_rpc_path(url: &str) -> String {
 }
 
 /// Generate HMAC-SHA256 signature for the given data
-fn generate_signature(secret: &str, url: &str, method: &Method, timestamp: i64, background: bool) -> String {
+fn generate_signature(secret: &str, url: &str, method: &Method, timestamp: i64) -> String {
     let data = signature_payload(url, method, timestamp);
     let mut mac = <HmacSha256 as KeyInit>::new_from_slice(secret.as_bytes()).expect("HMAC can take key of any size");
-    bind_background_admission(&mut mac, background);
     mac.update(data.as_bytes());
     let result = mac.finalize();
     base64_simd::STANDARD.encode_to_string(result.into_bytes())
 }
 
-fn verify_signature(secret: &str, url: &str, method: &Method, timestamp: i64, signature: &str, background: bool) -> bool {
+fn verify_signature(secret: &str, url: &str, method: &Method, timestamp: i64, signature: &str) -> bool {
     let Ok(signature) = base64_simd::STANDARD.decode_to_vec(signature) else {
         return false;
     };
 
     let data = signature_payload(url, method, timestamp);
     let mut mac = <HmacSha256 as KeyInit>::new_from_slice(secret.as_bytes()).expect("HMAC can take key of any size");
-    bind_background_admission(&mut mac, background);
     mac.update(data.as_bytes());
     mac.verify_slice(&signature).is_ok()
 }
@@ -814,7 +771,6 @@ pub fn verify_ns_scanner_capability_with_checkpoint_coverage(
 
 #[derive(Clone, Copy)]
 struct SignatureV2Scope<'a> {
-    background: bool,
     audience: &'a str,
     service: &'a str,
     rpc_method: &'a str,
@@ -824,7 +780,6 @@ struct SignatureV2Scope<'a> {
 }
 
 fn update_signature_v2(mac: &mut HmacSha256, scope: SignatureV2Scope<'_>) {
-    bind_background_admission(mac, scope.background);
     for part in [
         b"rustfs-rpc-auth-v2|".as_slice(),
         scope.audience.as_bytes(),
@@ -863,7 +818,6 @@ fn verify_signature_v2(secret: &str, scope: SignatureV2Scope<'_>, signature: &st
 
 #[derive(Clone, Copy)]
 struct ReplayScope<'a> {
-    background: bool,
     audience: &'a str,
     path: &'a str,
     timestamp: &'a str,
@@ -873,7 +827,6 @@ struct ReplayScope<'a> {
 }
 
 fn update_replay_scope(mac: &mut HmacSha256, scope: ReplayScope<'_>) {
-    bind_background_admission(mac, scope.background);
     mac.update(RPC_REPLAY_SCOPE_DOMAIN);
     for part in [
         scope.audience.as_bytes(),
@@ -1017,24 +970,6 @@ pub fn gen_tonic_replay_scope_headers(
     timestamp: &str,
     content_sha256: &str,
     boot_epoch: Uuid,
-) -> std::io::Result<HeaderMap> {
-    gen_tonic_replay_scope_headers_with_admission(
-        audience,
-        path,
-        timestamp,
-        content_sha256,
-        boot_epoch,
-        current_rpc_background_request(),
-    )
-}
-
-pub(crate) fn gen_tonic_replay_scope_headers_with_admission(
-    audience: &str,
-    path: &str,
-    timestamp: &str,
-    content_sha256: &str,
-    boot_epoch: Uuid,
-    background: bool,
 ) -> std::io::Result<HeaderMap> {
     if audience.is_empty() || !path.starts_with('/') || !valid_content_sha256(content_sha256) || boot_epoch.is_nil() {
         return Err(std::io::Error::other("Invalid replay-scoped RPC signing scope"));
@@ -1048,7 +983,6 @@ pub(crate) fn gen_tonic_replay_scope_headers_with_admission(
     let signature = generate_replay_scope_signature(
         &get_shared_secret()?,
         ReplayScope {
-            background,
             audience,
             path,
             timestamp,
@@ -1058,7 +992,6 @@ pub(crate) fn gen_tonic_replay_scope_headers_with_admission(
         },
     )?;
     let mut headers = HeaderMap::new();
-    insert_background_admission(&mut headers, background);
     headers.insert(RPC_REPLAY_SCOPE_VERSION_HEADER, HeaderValue::from_static(RPC_REPLAY_SCOPE_VERSION_V3));
     headers.insert(
         RPC_REPLAY_SCOPE_SIGNATURE_HEADER,
@@ -1293,12 +1226,10 @@ pub fn build_auth_headers(url: &str, method: &Method, headers: &mut HeaderMap) -
 pub fn gen_signature_headers(url: &str, method: &Method) -> std::io::Result<HeaderMap> {
     let secret = get_shared_secret()?;
     let timestamp = OffsetDateTime::now_utc().unix_timestamp();
-    let background = current_rpc_background_request();
 
-    let signature = generate_signature(&secret, url, method, timestamp, background);
+    let signature = generate_signature(&secret, url, method, timestamp);
 
     let mut headers = HeaderMap::new();
-    insert_background_admission(&mut headers, background);
     headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).expect("Invalid header value"));
     headers.insert(
         TIMESTAMP_HEADER,
@@ -1333,12 +1264,10 @@ pub fn gen_tonic_signature_headers(
     let timestamp_header = timestamp.to_string();
     let body_nonce = (content_sha256 != UNSIGNED_PAYLOAD).then(|| Uuid::new_v4().to_string());
     let nonce = body_nonce.as_deref().unwrap_or(UNSIGNED_PAYLOAD_NONCE);
-    let background = current_rpc_background_request();
-    let legacy_signature = generate_signature(&secret, TONIC_RPC_PREFIX, &Method::GET, timestamp, background);
+    let legacy_signature = generate_signature(&secret, TONIC_RPC_PREFIX, &Method::GET, timestamp);
     let signature_v2 = generate_signature_v2(
         &secret,
         SignatureV2Scope {
-            background,
             audience,
             service,
             rpc_method,
@@ -1349,7 +1278,6 @@ pub fn gen_tonic_signature_headers(
     )?;
 
     let mut headers = HeaderMap::new();
-    insert_background_admission(&mut headers, background);
     headers.insert(SIGNATURE_HEADER, header_value(&legacy_signature, SIGNATURE_HEADER)?);
     headers.insert(TIMESTAMP_HEADER, header_value(&timestamp_header, TIMESTAMP_HEADER)?);
     headers.insert(RPC_AUTH_VERSION_HEADER, HeaderValue::from_static(RPC_AUTH_VERSION_V2));
@@ -1573,7 +1501,6 @@ fn verify_tonic_replay_scope_signature(audience: &str, path: &str, headers: &Hea
     if !verify_replay_scope_signature(
         &secret,
         ReplayScope {
-            background: rpc_background_admission(headers)?,
             audience,
             path,
             timestamp,
@@ -1698,9 +1625,6 @@ fn verify_tonic_rpc_signature_with_strictness(
     strict: bool,
 ) -> std::io::Result<()> {
     if !has_v2_auth_headers(headers) {
-        if rpc_background_admission(headers)? {
-            return Err(std::io::Error::other("RPC background admission requires v2 authentication"));
-        }
         // RUSTFS_COMPAT_TODO(heal-rpc-auth-v2): accept old peers during rolling upgrades. Remove after the minimum
         // supported RustFS peer version sends v2 authentication on every internode gRPC request.
         if strict {
@@ -1772,7 +1696,6 @@ fn verify_tonic_rpc_signature_with_strictness(
     if !verify_signature_v2(
         &secret,
         SignatureV2Scope {
-            background: rpc_background_admission(headers)?,
             audience,
             service,
             rpc_method,
@@ -1813,7 +1736,7 @@ pub fn verify_rpc_signature(url: &str, method: &Method, headers: &HeaderMap) ->
     // Verify signature with constant-time HMAC comparison.
     let secret = get_shared_secret()?;
 
-    if !verify_signature(&secret, url, method, timestamp, signature, rpc_background_admission(headers)?) {
+    if !verify_signature(&secret, url, method, timestamp, signature) {
         let rpc_path = redacted_rpc_path(url);
         error!(
             rpc_path = %rpc_path,
@@ -1905,98 +1828,6 @@ mod tests {
         runtime_sources::ensure_test_rpc_secret();
     }
 
-    #[tokio::test]
-    async fn background_admission_is_bound_in_http_and_both_tonic_signature_lanes() {
-        ensure_test_rpc_secret();
-        let secret = get_shared_secret().expect("RPC secret");
-        let path = "/node_service.NodeService/ReadAll";
-        for background in [false, true] {
-            let (http, tonic) = with_rpc_background_request(background, async {
-                (
-                    gen_signature_headers("/rustfs/rpc/read?disk=a", &Method::GET).expect("HTTP signature"),
-                    gen_tonic_signature_headers("node-a:9000", "node_service.NodeService", "ReadAll", None)
-                        .expect("gRPC signature"),
-                )
-            })
-            .await;
-            assert_eq!(rpc_background_admission(&http).expect("HTTP class"), background);
-            assert_eq!(rpc_background_admission(&tonic).expect("gRPC class"), background);
-            verify_rpc_signature("/rustfs/rpc/read?disk=a", &Method::GET, &http).expect("HTTP authentication");
-            verify_tonic_rpc_signature_with_strictness("node-a:9000", path, &tonic, true).expect("v2 authentication");
-
-            let timestamp = tonic[TIMESTAMP_HEADER].to_str().expect("timestamp");
-            let content = tonic[RPC_CONTENT_SHA256_HEADER].to_str().expect("content digest");
-            assert_eq!(
-                verify_signature_v2(
-                    &secret,
-                    SignatureV2Scope {
-                        background: false,
-                        audience: "node-a:9000",
-                        service: "node_service.NodeService",
-                        rpc_method: "ReadAll",
-                        timestamp,
-                        nonce: tonic[RPC_NONCE_HEADER].to_str().expect("nonce"),
-                        content_sha256: content,
-                    },
-                    tonic[RPC_SIGNATURE_V2_HEADER].to_str().expect("signature"),
-                ),
-                !background,
-                "an old peer cannot authenticate a background request as foreground"
-            );
-
-            let mut replay = tonic.clone();
-            // The channel can run outside the caller's task-local scope.
-            replay.extend(
-                gen_tonic_replay_scope_headers_with_admission(
-                    "node-a:9000",
-                    path,
-                    timestamp,
-                    content,
-                    tonic_rpc_boot_epoch(),
-                    background,
-                )
-                .expect("v3 signature"),
-            );
-            for mutation in ["strip-or-add", "unknown", "duplicate"] {
-                let alter = |headers: &HeaderMap| {
-                    let mut changed = headers.clone();
-                    match mutation {
-                        "strip-or-add" if background => {
-                            changed.remove(RPC_BACKGROUND_ADMISSION_HEADER);
-                        }
-                        "strip-or-add" => insert_background_admission(&mut changed, true),
-                        "unknown" => {
-                            changed.insert(RPC_BACKGROUND_ADMISSION_HEADER, HeaderValue::from_static("v2"));
-                        }
-                        _ => {
-                            insert_background_admission(&mut changed, true);
-                            changed.append(RPC_BACKGROUND_ADMISSION_HEADER, HeaderValue::from_static("v1"));
-                        }
-                    }
-                    changed
-                };
-                assert!(verify_rpc_signature("/rustfs/rpc/read?disk=a", &Method::GET, &alter(&http)).is_err());
-                assert!(verify_tonic_rpc_signature_with_strictness("node-a:9000", path, &alter(&tonic), true).is_err());
-                assert!(verify_tonic_replay_scope_signature("node-a:9000", path, &alter(&replay)).is_err());
-            }
-            verify_tonic_replay_scope_signature("node-a:9000", path, &replay).expect("v3 authentication");
-            assert!(
-                verify_tonic_replay_scope_signature("node-a:9000", path, &replay).is_err(),
-                "replay rejected"
-            );
-
-            if background {
-                let mut downgraded = HeaderMap::new();
-                for name in [SIGNATURE_HEADER, TIMESTAMP_HEADER, RPC_BACKGROUND_ADMISSION_HEADER] {
-                    downgraded.insert(name, tonic[name].clone());
-                }
-                assert!(verify_tonic_rpc_signature_with_strictness("node-a:9000", path, &downgraded, false).is_err());
-                downgraded.remove(RPC_BACKGROUND_ADMISSION_HEADER);
-                assert!(verify_tonic_rpc_signature_with_strictness("node-a:9000", path, &downgraded, false).is_err());
-            }
-        }
-    }
-
     #[test]
     fn namespace_scanner_capability_proof_binds_challenge_and_server_epoch() {
         let secret = "test-scanner-capability-secret";
@@ -2134,8 +1965,8 @@ mod tests {
         let method = Method::GET;
         let timestamp = 1640995200; // Fixed timestamp
 
-        let signature1 = generate_signature(secret, url, &method, timestamp, false);
-        let signature2 = generate_signature(secret, url, &method, timestamp, false);
+        let signature1 = generate_signature(secret, url, &method, timestamp);
+        let signature2 = generate_signature(secret, url, &method, timestamp);
 
         assert_eq!(signature1, signature2, "Same inputs should produce same signature");
         assert!(!signature1.is_empty(), "Signature should not be empty");
@@ -2148,10 +1979,10 @@ mod tests {
         let method = Method::GET;
         let timestamp = 1640995200;
 
-        let signature1 = generate_signature(secret, url, &method, timestamp, false);
-        let signature2 = generate_signature(secret, "http://different.com/api/test2", &method, timestamp, false);
-        let signature3 = generate_signature(secret, url, &Method::POST, timestamp, false);
-        let signature4 = generate_signature(secret, url, &method, timestamp + 1, false);
+        let signature1 = generate_signature(secret, url, &method, timestamp);
+        let signature2 = generate_signature(secret, "http://different.com/api/test2", &method, timestamp);
+        let signature3 = generate_signature(secret, url, &Method::POST, timestamp);
+        let signature4 = generate_signature(secret, url, &method, timestamp + 1);
 
         assert_ne!(signature1, signature2, "Different URLs should produce different signatures");
         assert_ne!(signature1, signature3, "Different methods should produce different signatures");
@@ -2257,14 +2088,14 @@ mod tests {
         let url = "http://example.com/api/test";
         let method = Method::GET;
         let timestamp = 1640995200;
-        let signature = generate_signature(secret, url, &method, timestamp, false);
+        let signature = generate_signature(secret, url, &method, timestamp);
         let mut tampered = base64_simd::STANDARD.decode_to_vec(&signature).unwrap();
         tampered[0] ^= 1;
         let tampered_signature = base64_simd::STANDARD.encode_to_string(tampered);
 
-        assert!(verify_signature(secret, url, &method, timestamp, &signature, false));
-        assert!(!verify_signature(secret, url, &method, timestamp, &tampered_signature, false));
-        assert!(!verify_signature(secret, url, &method, timestamp, "invalid-signature", false));
+        assert!(verify_signature(secret, url, &method, timestamp, &signature));
+        assert!(!verify_signature(secret, url, &method, timestamp, &tampered_signature));
+        assert!(!verify_signature(secret, url, &method, timestamp, "invalid-signature"));
     }
 
     #[test]
@@ -2281,11 +2112,11 @@ mod tests {
         );
         let method = Method::GET;
         let timestamp = 1_640_995_200;
-        let signature = generate_signature(secret, signed_url, &method, timestamp, false);
+        let signature = generate_signature(secret, signed_url, &method, timestamp);
 
-        assert!(verify_signature(secret, signed_url, &method, timestamp, &signature, false));
-        assert!(!verify_signature(secret, downgraded_url, &method, timestamp, &signature, false));
-        assert!(!verify_signature(secret, tampered_body_digest, &method, timestamp, &signature, false));
+        assert!(verify_signature(secret, signed_url, &method, timestamp, &signature));
+        assert!(!verify_signature(secret, downgraded_url, &method, timestamp, &signature));
+        assert!(!verify_signature(secret, tampered_body_digest, &method, timestamp, &signature));
     }
 
     #[test]
@@ -2295,7 +2126,7 @@ mod tests {
         let method = Method::GET;
         let timestamp = OffsetDateTime::now_utc().unix_timestamp();
         let secret = get_shared_secret().expect("test RPC secret should resolve");
-        let expected_signature = generate_signature(&secret, url, &method, timestamp, false);
+        let expected_signature = generate_signature(&secret, url, &method, timestamp);
         let invalid_signature = "invalid-signature";
         let logs = CapturedLogs::default();
         let subscriber = tracing_subscriber::fmt()
@@ -2333,7 +2164,7 @@ mod tests {
         // Set expired timestamp (older than SIGNATURE_VALID_DURATION)
         let expired_timestamp = OffsetDateTime::now_utc().unix_timestamp() - SIGNATURE_VALID_DURATION - 10;
         let secret = get_shared_secret().expect("test RPC secret should resolve");
-        let signature = generate_signature(&secret, url, &method, expired_timestamp, false);
+        let signature = generate_signature(&secret, url, &method, expired_timestamp);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&expired_timestamp.to_string()).unwrap());
@@ -2355,7 +2186,7 @@ mod tests {
 
         let future_timestamp = OffsetDateTime::now_utc().unix_timestamp() + SIGNATURE_VALID_DURATION + 10;
         let secret = get_shared_secret().expect("test RPC secret should resolve");
-        let signature = generate_signature(&secret, url, &method, future_timestamp, false);
+        let signature = generate_signature(&secret, url, &method, future_timestamp);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&future_timestamp.to_string()).unwrap());
@@ -2469,7 +2300,7 @@ mod tests {
         // Test timestamp just within valid duration
         let valid_timestamp = current_time - SIGNATURE_VALID_DURATION + 1;
 
-        let signature = generate_signature(&secret, url, &method, valid_timestamp, false);
+        let signature = generate_signature(&secret, url, &method, valid_timestamp);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&valid_timestamp.to_string()).unwrap());
@@ -2480,7 +2311,7 @@ mod tests {
         // Test timestamp just outside valid duration
         let mut headers = HeaderMap::new();
         let invalid_timestamp = current_time - SIGNATURE_VALID_DURATION - 15;
-        let signature = generate_signature(&secret, url, &method, invalid_timestamp, false);
+        let signature = generate_signature(&secret, url, &method, invalid_timestamp);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&invalid_timestamp.to_string()).unwrap());

crates/ecstore/src/cluster/rpc/internode_data_transport.rs

@@ -33,9 +33,7 @@ use rustfs_config::{
     DEFAULT_INTERNODE_DATA_TRANSPORT, ENV_RUSTFS_INTERNODE_DATA_TRANSPORT, INTERNODE_DATA_TRANSPORT_TCP,
     KNOWN_INTERNODE_DATA_TRANSPORT_BACKENDS,
 };
-use rustfs_rio::{
-    ChunkReaderBox, HttpChunkReader, HttpReader, HttpWriter, HttpWriterMemoryReservation, HttpWriterMemoryReserver,
-};
+use rustfs_rio::{ChunkReaderBox, HttpChunkReader, HttpReader, HttpWriter};
 use sha2::{Digest, Sha256};
 use std::collections::HashMap;
 use std::future::Future;
@@ -68,19 +66,6 @@ const PUT_FILE_CAPABILITY_PROBE_TIMEOUT: Duration = Duration::from_secs(5);
 const CONTENT_TYPE_JSON: &str = "application/json";
 const CONTENT_TYPE_MSGPACK: &str = "application/msgpack";
 
-fn http_writer_memory_reserver() -> Option<HttpWriterMemoryReserver> {
-    crate::disk::current_resource_unit()
-        .and_then(|resources| resources.memory_budget())
-        .map(|budget| {
-            // Payloads can outlive the operation; never retain its node or disk units.
-            Arc::new(move |capacity| {
-                budget
-                    .reserve(capacity)
-                    .map(|reservation| Box::new(reservation) as HttpWriterMemoryReservation)
-            }) as HttpWriterMemoryReserver
-        })
-}
-
 fn unsupported_transport_message(transport: &str) -> String {
     format!(
         "invalid {ENV_RUSTFS_INTERNODE_DATA_TRANSPORT}={transport:?}; supported values: {}",
@@ -361,17 +346,13 @@ impl InternodeDataTransport for TcpHttpInternodeDataTransport {
     }
 
     async fn open_write(&self, request: WriteStreamRequest) -> Result<FileWriter> {
-        let memory_reserver = http_writer_memory_reserver();
         let server_epoch = self.put_file_auth_capability(&request.endpoint).await?;
         let auth_scope = server_epoch.map(|server_epoch| (Uuid::new_v4(), server_epoch));
         let url = build_put_file_stream_url(&request, auth_scope);
         let endpoint = request.endpoint;
         let mut headers = json_headers();
         build_auth_headers(&url, &Method::PUT, &mut headers)?;
-        let writer = match memory_reserver {
-            Some(reserve) => HttpWriter::new_with_memory_reserver(url.clone(), Method::PUT, headers, reserve).await?,
-            None => HttpWriter::new(url.clone(), Method::PUT, headers).await?,
-        };
+        let writer = HttpWriter::new(url.clone(), Method::PUT, headers).await?;
         match auth_scope {
             Some((nonce, server_epoch)) => Ok(Box::new(PutFileAuthWriter::new(writer, url, nonce, endpoint, server_epoch))),
             None => Ok(Box::new(writer)),
@@ -967,193 +948,6 @@ mod tests {
     use tokio::io::AsyncWriteExt;
     use tokio::sync::{Barrier, Notify};
 
-    fn memory_test_write_request(authenticated: bool) -> WriteStreamRequest {
-        crate::runtime::sources::ensure_test_rpc_secret();
-        let endpoint = format!("http://writer-memory-{}.invalid", Uuid::new_v4());
-        put_file_capability_cache_entry(&endpoint).write().cached = Some(if authenticated {
-            PutFileCapabilityState::V1 {
-                server_epoch: Uuid::new_v4(),
-                revalidate_after: Instant::now() + PUT_FILE_V1_CAPABILITY_TTL,
-            }
-        } else {
-            PutFileCapabilityState::LegacyUntil(Instant::now() + PUT_FILE_LEGACY_CAPABILITY_TTL)
-        });
-        WriteStreamRequest {
-            endpoint,
-            disk: "disk-a".to_owned(),
-            volume: "bucket".to_owned(),
-            path: "part.1".to_owned(),
-            append: false,
-            size: 4,
-        }
-    }
-
-    #[tokio::test]
-    async fn http_write_memory_reserver_outlives_only_the_memory_scope() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        assert!(http_writer_memory_reserver().is_none(), "foreground must use the existing writer");
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(2 * 1024 * 1024, Duration::from_secs(30));
-        let (resources, gates) = test_resource_units(2);
-        let request = memory_test_write_request(true);
-        let endpoint = request.endpoint.clone();
-        let writer = with_optional_resource_unit(
-            Some(resources.with_memory_budget(memory.clone())),
-            TcpHttpInternodeDataTransport.open_write(request),
-        )
-        .await;
-        PUT_FILE_CAPABILITY_CACHE.write().remove(&endpoint);
-        let mut writer = writer.expect("admitted transport writer");
-        assert!(
-            gates.iter().all(|gate| gate.snapshot().active == 0),
-            "the callback must not retain disk units"
-        );
-        assert_eq!(memory.snapshot().used, 1024 * 1024);
-        writer.write_all(b"data").await.expect("buffered bytes");
-        writer.flush().await.expect("transfer charged allocation to queue");
-        memory.set_sampled_limit(2 * 1024 * 1024, Duration::ZERO);
-        writer
-            .write_all(&vec![0x5a; 1024 * 1024 - 4])
-            .await
-            .expect("reuse the already charged tail after observation expiry");
-        assert_eq!(memory.snapshot().used, 1024 * 1024, "reuse must not allocate separate storage");
-        let error = writer
-            .write(b"rejected")
-            .await
-            .expect_err("expired observation must reject new storage");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        assert!(
-            crate::disk::background_memory::is_memory_pressure(&error),
-            "preserve the typed memory-pressure marker"
-        );
-        assert_eq!(memory.snapshot().used, 1024 * 1024, "queued storage remains charged after expiry");
-        drop(writer);
-        tokio::task::yield_now().await;
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn http_write_memory_denial_preserves_the_budget_error() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        for (authenticated, sample) in [false, true].into_iter().flat_map(|authenticated| {
-            [
-                None,
-                Some((1024 * 1024 - 1, Duration::from_secs(30))),
-                Some((1024 * 1024, Duration::ZERO)),
-            ]
-            .into_iter()
-            .map(move |sample| (authenticated, sample))
-        }) {
-            let memory = BackgroundMemoryBudget::new();
-            if let Some((limit, valid_for)) = sample {
-                memory.set_sampled_limit(limit, valid_for);
-            }
-            let (resources, _) = test_resource_units(1);
-            let request = memory_test_write_request(authenticated);
-            let endpoint = request.endpoint.clone();
-            let result = with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                TcpHttpInternodeDataTransport.open_write(request),
-            )
-            .await;
-            PUT_FILE_CAPABILITY_CACHE.write().remove(&endpoint);
-            let error = match result {
-                Err(Error::Io(error)) => error,
-                Err(error) => panic!("unexpected transport error: {error}"),
-                Ok(_) => panic!("unavailable memory must reject construction"),
-            };
-            assert!(crate::disk::background_memory::is_memory_pressure(&error));
-            assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn admitted_remote_reads_bind_receiver_admission_to_the_http_signature() {
-        use crate::disk::with_background_resource_unit;
-        use rustfs_concurrency::adaptive::AdaptiveAdmission;
-        use std::num::NonZeroU16;
-
-        crate::runtime::sources::ensure_test_rpc_secret();
-        let listener = tokio::net::TcpListener::bind("127.0.0.1:0")
-            .await
-            .expect("remote admission listener");
-        let address = listener.local_addr().expect("remote admission address");
-        let server = tokio::spawn(async move {
-            let (mut socket, _) = listener.accept().await.expect("remote read connection");
-            let mut bytes = Vec::new();
-            while !bytes.windows(4).any(|window| window == b"\r\n\r\n") {
-                let mut chunk = [0; 1024];
-                let read = socket.read(&mut chunk).await.expect("remote read headers");
-                assert!(read > 0 && bytes.len() < 16 * 1024, "bounded complete request headers");
-                bytes.extend_from_slice(&chunk[..read]);
-            }
-            let request = std::str::from_utf8(&bytes).expect("HTTP request");
-            let mut lines = request.split("\r\n");
-            let target = lines
-                .next()
-                .expect("request line")
-                .split_whitespace()
-                .nth(1)
-                .expect("request target")
-                .to_owned();
-            let mut headers = HeaderMap::new();
-            for line in lines.take_while(|line| !line.is_empty()) {
-                let (name, value) = line.split_once(':').expect("header field");
-                headers.append(
-                    http::header::HeaderName::from_bytes(name.as_bytes()).expect("header name"),
-                    HeaderValue::from_str(value.trim()).expect("header value"),
-                );
-            }
-            socket
-                .write_all(b"HTTP/1.1 200 OK\r\ncontent-length: 5\r\nconnection: close\r\n\r\nhello")
-                .await
-                .expect("remote read response");
-            (target, headers)
-        });
-        let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-        let resource = gate.try_acquire().expect("sender device admission");
-        let mut reader = tokio::time::timeout(
-            Duration::from_secs(5),
-            with_background_resource_unit(
-                resource,
-                TcpHttpInternodeDataTransport.open_read(ReadStreamRequest {
-                    endpoint: format!("http://{address}"),
-                    disk: "disk-a".to_owned(),
-                    volume: "bucket".to_owned(),
-                    path: "part.1".to_owned(),
-                    offset: 0,
-                    length: 5,
-                    stall_timeout: Some(Duration::from_secs(5)),
-                }),
-            ),
-        )
-        .await
-        .expect("bounded remote request")
-        .expect("remote reader");
-        let mut body = Vec::new();
-        reader.read_to_end(&mut body).await.expect("complete remote body");
-        assert_eq!(body, b"hello");
-        let (target, headers) = server.await.expect("remote request capture");
-        assert_eq!(gate.snapshot().active, 0, "remote body does not retain the sender's device");
-        assert_eq!(
-            headers
-                .get("x-rustfs-rpc-background-admission")
-                .and_then(|value| value.to_str().ok()),
-            Some("v1"),
-            "resource-controlled remote work must request receiver-side admission"
-        );
-        crate::cluster::rpc::verify_rpc_signature(&target, &Method::GET, &headers).expect("bound request signature");
-        let mut stripped = headers;
-        stripped.remove("x-rustfs-rpc-background-admission");
-        assert!(
-            crate::cluster::rpc::verify_rpc_signature(&target, &Method::GET, &stripped).is_err(),
-            "removing background admission must invalidate the signature"
-        );
-    }
-
     async fn wait_for_capability_flight_waiters(entry: &PutFileCapabilityCacheEntry, waiters: usize) {
         tokio::time::timeout(Duration::from_secs(5), async {
             loop {

crates/ecstore/src/cluster/rpc/mod.rs

@@ -13,8 +13,6 @@
 // limitations under the License.
 
 pub(crate) mod background_monitor;
-pub(crate) mod background_pipe;
-pub(crate) mod background_reader_stream;
 pub(crate) mod client;
 pub(crate) mod context_propagation;
 pub(crate) mod http_auth;
@@ -35,17 +33,16 @@ pub use client::{
 // Re-exported through `api::rpc`; not every item is consumed inside this crate.
 #[allow(unused_imports)]
 pub use http_auth::{
-    RPC_BACKGROUND_ADMISSION_HEADER, TONIC_RPC_PREFIX, build_auth_headers, build_put_file_auth_trailer,
-    check_and_record_signed_rpc_nonce, gen_signature_headers, gen_tonic_replay_scope_headers, gen_tonic_signature_headers,
-    normalize_tonic_rpc_audience, rpc_background_admission, set_tonic_canonical_body_digest, set_tonic_mutation_body_digest,
-    set_tonic_rolling_canonical_body_digest, set_tonic_rolling_mutation_body_digest, sign_ns_scanner_capability,
-    sign_ns_scanner_capability_with_checkpoint_coverage, sign_ns_scanner_capability_with_tier_registry_generation,
-    sign_put_file_capability, sign_tonic_rpc_response_proof, tonic_boot_epoch_challenge, tonic_boot_epoch_response_headers,
-    tonic_rpc_auth_failure_reason, verify_ns_scanner_capability, verify_ns_scanner_capability_with_checkpoint_coverage,
-    verify_ns_scanner_capability_with_tier_registry_generation, verify_put_file_auth_trailer, verify_put_file_capability,
-    verify_rpc_signature, verify_tonic_boot_epoch_response, verify_tonic_canonical_body_digest,
-    verify_tonic_mutation_body_digest, verify_tonic_mutation_body_digest_reject_unsigned, verify_tonic_rpc_response_proof,
-    verify_tonic_rpc_signature, verify_tonic_rpc_signature_with_bootstrap,
+    TONIC_RPC_PREFIX, build_auth_headers, build_put_file_auth_trailer, check_and_record_signed_rpc_nonce, gen_signature_headers,
+    gen_tonic_replay_scope_headers, gen_tonic_signature_headers, normalize_tonic_rpc_audience, set_tonic_canonical_body_digest,
+    set_tonic_mutation_body_digest, set_tonic_rolling_canonical_body_digest, set_tonic_rolling_mutation_body_digest,
+    sign_ns_scanner_capability, sign_ns_scanner_capability_with_checkpoint_coverage,
+    sign_ns_scanner_capability_with_tier_registry_generation, sign_put_file_capability, sign_tonic_rpc_response_proof,
+    tonic_boot_epoch_challenge, tonic_boot_epoch_response_headers, tonic_rpc_auth_failure_reason, verify_ns_scanner_capability,
+    verify_ns_scanner_capability_with_checkpoint_coverage, verify_ns_scanner_capability_with_tier_registry_generation,
+    verify_put_file_auth_trailer, verify_put_file_capability, verify_rpc_signature, verify_tonic_boot_epoch_response,
+    verify_tonic_canonical_body_digest, verify_tonic_mutation_body_digest, verify_tonic_mutation_body_digest_reject_unsigned,
+    verify_tonic_rpc_response_proof, verify_tonic_rpc_signature, verify_tonic_rpc_signature_with_bootstrap,
 };
 #[cfg(test)]
 pub(crate) use internode_data_transport::TcpHttpInternodeDataTransport;

crates/ecstore/src/cluster/rpc/remote_disk.rs

@@ -17,7 +17,6 @@ use crate::cluster::rpc::client::{
     node_service_delete_recovery_client, node_service_time_out_client, node_service_time_out_client_for_class,
     node_service_time_out_client_no_auth,
 };
-use crate::cluster::rpc::http_auth::{current_rpc_background_request, with_rpc_background_request};
 use crate::cluster::rpc::internode_data_transport::{
     InternodeDataTransport, NsScannerCapabilityRequest, NsScannerStreamRequest, ReadStreamRequest, WalkDirStreamRequest,
     WriteStreamRequest,
@@ -571,7 +570,6 @@ struct RetryingRemoteReader {
     reader: Option<FileReader>,
     transport: Arc<dyn InternodeDataTransport>,
     request: ReadStreamRequest,
-    background: bool,
     emitted: usize,
     retried: bool,
     initial_read_timeout: Option<Duration>,
@@ -592,7 +590,6 @@ impl RetryingRemoteReader {
             reader: Some(reader),
             transport,
             request,
-            background: current_rpc_background_request(),
             emitted: 0,
             retried: false,
             initial_read_timeout,
@@ -610,10 +607,9 @@ impl RetryingRemoteReader {
         let request = resumed_read_request(&self.request, self.emitted)?;
         let recovery_timeout = self.recovery_timeout;
         let transport = Arc::clone(&self.transport);
-        self.resume = Some(AbortOnDropTask::new(tokio::spawn(with_rpc_background_request(
-            self.background,
-            async move { with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_fresh(request)).await },
-        ))));
+        self.resume = Some(AbortOnDropTask::new(tokio::spawn(async move {
+            with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_fresh(request)).await
+        })));
         Ok(())
     }
 
@@ -721,7 +717,6 @@ struct RetryingRemoteChunkReader {
     reader: Option<rustfs_rio::ChunkReaderBox>,
     transport: Arc<dyn InternodeDataTransport>,
     request: ReadStreamRequest,
-    background: bool,
     emitted: usize,
     retried: bool,
     initial_read_timeout: Option<Duration>,
@@ -742,7 +737,6 @@ impl RetryingRemoteChunkReader {
             reader: Some(reader),
             transport,
             request,
-            background: current_rpc_background_request(),
             emitted: 0,
             retried: false,
             initial_read_timeout,
@@ -760,10 +754,9 @@ impl RetryingRemoteChunkReader {
         let request = resumed_read_request(&self.request, self.emitted)?;
         let recovery_timeout = self.recovery_timeout;
         let transport = Arc::clone(&self.transport);
-        self.resume = Some(AbortOnDropTask::new(tokio::spawn(with_rpc_background_request(
-            self.background,
-            async move { with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_chunks_fresh(request)).await },
-        ))));
+        self.resume = Some(AbortOnDropTask::new(tokio::spawn(async move {
+            with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_chunks_fresh(request)).await
+        })));
         Ok(())
     }
 
@@ -1637,7 +1630,6 @@ impl RemoteDisk {
         let initial_probe_ok = Self::perform_connectivity_check(&addr).await.is_ok();
         if initial_probe_ok {
             health.record_operation_success(&endpoint, "connectivity_probe_success");
-            rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&addr);
         } else if health.mark_failure(&endpoint, "connectivity_probe_failed") {
             warn!(
                 event = EVENT_REMOTE_DISK_HEALTH,
@@ -1709,7 +1701,6 @@ impl RemoteDisk {
                     // Perform basic connectivity check
                     if Self::perform_connectivity_check(&addr).await.is_ok() {
                         health.record_operation_success(&endpoint, "connectivity_probe_success");
-                        rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&addr);
                     } else if health.mark_failure(&endpoint, "connectivity_probe_failed") {
                         warn!(
                             event = EVENT_REMOTE_DISK_HEALTH,
@@ -1780,7 +1771,6 @@ impl RemoteDisk {
                 }
                 _ = interval.tick() => {
                     if Self::perform_recovery_probe(&addr, &endpoint).await.is_ok() {
-                        rustfs_io_metrics::internode_metrics::record_peer_reachable(&addr);
                         let became_online = health.mark_recovery_success(&endpoint, "disk_info_probe_success");
                         debug!(
                             event = EVENT_REMOTE_DISK_HEALTH,
@@ -2012,7 +2002,6 @@ impl RemoteDisk {
             let operation_result = operation().await;
             if operation_result.is_ok() {
                 self.health.record_operation_success(&self.endpoint, "operation_success");
-                rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&self.addr);
             }
             self.handle_network_like_error(op, timeout_duration, &operation_result, failure_health_action)
                 .await;
@@ -2027,7 +2016,6 @@ impl RemoteDisk {
                 // Log success; the waiting guard balances every exit path.
                 if operation_result.is_ok() {
                     self.health.record_operation_success(&self.endpoint, "operation_success");
-                    rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&self.addr);
                 }
                 self.handle_network_like_error(op, timeout_duration, &operation_result, failure_health_action)
                     .await;
@@ -7781,98 +7769,6 @@ mod tests {
         .await;
     }
 
-    #[tokio::test]
-    async fn remote_read_retries_preserve_signed_admission_after_sender_scope_ends() {
-        use crate::cluster::rpc::{rpc_background_admission, verify_rpc_signature};
-        use crate::disk::with_background_resource_unit;
-        use rustfs_concurrency::adaptive::AdaptiveAdmission;
-        use std::num::NonZeroU16;
-
-        crate::runtime::sources::ensure_test_rpc_secret();
-        for background in [false, true] {
-            for chunked in [false, true] {
-                let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.expect("retry listener");
-                let address = listener.local_addr().expect("retry address");
-                let server = tokio::spawn(async move {
-                    let (mut socket, _) = listener.accept().await.expect("fresh connection");
-                    let mut bytes = Vec::new();
-                    while !bytes.windows(4).any(|window| window == b"\r\n\r\n") {
-                        let mut chunk = [0; 1024];
-                        let read = socket.read(&mut chunk).await.expect("retry request");
-                        assert!(read > 0 && bytes.len() < 16 * 1024, "bounded complete headers");
-                        bytes.extend_from_slice(&chunk[..read]);
-                    }
-                    let request = std::str::from_utf8(&bytes).expect("HTTP request");
-                    let mut lines = request.split("\r\n");
-                    let target = lines
-                        .next()
-                        .expect("request line")
-                        .split_whitespace()
-                        .nth(1)
-                        .expect("target")
-                        .to_owned();
-                    let mut headers = http::HeaderMap::new();
-                    for line in lines.take_while(|line| !line.is_empty()) {
-                        let (name, value) = line.split_once(':').expect("header");
-                        headers.append(
-                            http::header::HeaderName::from_bytes(name.as_bytes()).expect("header name"),
-                            http::HeaderValue::from_str(value.trim()).expect("header value"),
-                        );
-                    }
-                    socket
-                        .write_all(b"HTTP/1.1 200 OK\r\ncontent-length: 6\r\nconnection: close\r\n\r\n456789")
-                        .await
-                        .expect("retry response");
-                    (target, headers)
-                });
-                let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-                let request = ReadStreamRequest {
-                    endpoint: format!("http://{address}"),
-                    ..resume_request(10)
-                };
-                let create = async {
-                    let transport = Arc::new(TcpHttpInternodeDataTransport);
-                    if chunked {
-                        Box::new(RetryingRemoteChunkReader::new_with_timeouts(
-                            resume_step_chunk_reader(ResumeReadStep::PartialThenReset(b"0123".to_vec())),
-                            transport,
-                            request,
-                            None,
-                            None,
-                        )) as FileReader
-                    } else {
-                        Box::new(RetryingRemoteReader::new_with_timeouts(
-                            resume_step_reader(ResumeReadStep::PartialThenReset(b"0123".to_vec())),
-                            transport,
-                            request,
-                            None,
-                            None,
-                        )) as FileReader
-                    }
-                };
-                let mut reader = if background {
-                    with_background_resource_unit(gate.try_acquire().expect("sender admission"), create).await
-                } else {
-                    create.await
-                };
-                assert_eq!(gate.snapshot().active, 0, "retry reader cannot retain sender disk capacity");
-                let mut output = Vec::new();
-                tokio::time::timeout(
-                    Duration::from_secs(5),
-                    with_rpc_background_request(!background, reader.read_to_end(&mut output)),
-                )
-                .await
-                .expect("bounded retry")
-                .expect("resumed body");
-                assert_eq!(output, b"0123456789", "chunked={chunked}, background={background}");
-                let (target, headers) = server.await.expect("captured retry");
-                assert!(target.contains("offset=11") && target.contains("length=6"), "{target}");
-                assert_eq!(rpc_background_admission(&headers).expect("admission marker"), background);
-                verify_rpc_signature(&target, &http::Method::GET, &headers).expect("signed retry class");
-            }
-        }
-    }
-
     #[tokio::test]
     async fn remote_reader_resumes_from_emitted_bytes_without_duplicates() {
         let transport = Arc::new(ResumeTransport::with_read_steps(vec![ResumeReadStep::Data(b"456789".to_vec())]));

crates/ecstore/src/cluster/rpc/remote_locker.rs

@@ -445,10 +445,6 @@ impl RemoteClient {
                 }
             }
         });
-        // A successful lock RPC over a cached or fresh channel proves the peer is
-        // reachable; reconcile the internode peer-health gauge so it does not stay
-        // stale when no fresh dial fires (issue #9119).
-        rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&self.addr);
     }
 
     fn admit_late_release(&self) -> bool {
@@ -676,7 +672,6 @@ impl RemoteClient {
                     with_lock_peer_health(&addr, |health| {
                         health.last_success = Some(Instant::now());
                     });
-                    rustfs_io_metrics::internode_metrics::record_peer_reachable_if_offline(&addr);
                     rustfs_io_metrics::lock_metrics::record_remote_lock_rpc_late_completion(op, "success");
                     if let Some(late) = late {
                         late(response).await;
@@ -1320,6 +1315,34 @@ impl LockClient for RemoteClient {
         Ok(resp.success)
     }
 
+    async fn downgrade_committed_tail(&self, lock_id: &LockId) -> Result<bool> {
+        let marker = rustfs_lock::client::COMMITTED_TAIL_CONVERSION_MARKER;
+        let mut request = Self::create_unlock_request(lock_id);
+        request.metadata.tags.insert(marker.to_owned(), marker.to_owned());
+        let mut client = self.get_client().await?;
+        let resource_summary = request.resource.to_string();
+        let mut req = Request::new(GenerallyLockRequest {
+            args: serde_json::to_string(&request)
+                .map_err(|error| LockError::internal(format!("Failed to serialize request: {error}")))?,
+        });
+        attach_lock_mutation_body_digest(&mut req)?;
+        let response = self
+            .execute_rpc(
+                "refresh",
+                &resource_summary,
+                Self::rpc_timeout(),
+                async move { client.refresh(req).await },
+                RpcCleanup::new(None, None, None),
+            )
+            .await?
+            .into_inner();
+        if let Some(error) = response.error_info {
+            return Err(LockError::internal(error));
+        }
+        // Older nodes refresh normally but return no conversion marker.
+        Ok(response.success && response.lock_info.as_deref() == Some(marker))
+    }
+
     async fn force_release(&self, lock_id: &LockId) -> Result<bool> {
         info!("remote force_release for {}", lock_id);
         let force_request = Self::create_unlock_request(lock_id);

crates/ecstore/src/config/com.rs

@@ -3506,7 +3506,6 @@ mod tests {
                 replication_decision: String::new(),
                 checksum: None,
                 multipart_completion_replayed: false,
-                backfilled_old_current_size: None,
             }
         }
     }

crates/ecstore/src/core/pool_meta_native_integration_tests.rs

@@ -18,7 +18,6 @@ use crate::storage_api_contracts::namespace::NamespaceLocking as _;
 use codec::{fixture_inline_pool_meta_replicas as replicas, fixture_split_inline_pool_meta_replicas as split};
 use std::path::PathBuf;
 use tokio::fs;
-use uuid::Uuid;
 
 struct PhysicalFixture {
     _directories: Vec<tempfile::TempDir>,
@@ -629,559 +628,3 @@ async fn pool_meta_native_physical_three_plus_one_checkpoint_converges_all_shard
         );
     }
 }
-
-async fn owner_repair_no_backups_fixture() -> PhysicalFixture {
-    let fixture = fixture(0).await;
-    for pool in disks(&fixture.store).await {
-        for disk in pool {
-            let object = object_path(&disk);
-            let mut entries = fs::read_dir(&object).await.expect("fixture metadata directory");
-            while let Some(entry) = entries.next_entry().await.expect("fixture directory entry") {
-                if entry.file_type().await.expect("fixture entry type").is_dir() {
-                    fs::remove_dir_all(entry.path())
-                        .await
-                        .expect("remove task-owned fixture rollback directory");
-                }
-            }
-        }
-    }
-    fixture
-}
-
-async fn owner_repair_identity_heads(store: &ECStore) -> Vec<Vec<(Uuid, Bytes)>> {
-    let mut all = Vec::new();
-    for pool in &store.pools {
-        let set = pool.get_disks_by_key(POOL_META_IDENTITY_NAME);
-        let members = set
-            .disks
-            .read()
-            .await
-            .iter()
-            .cloned()
-            .map(|disk| disk.expect("identity fixture disk must be online"))
-            .collect::<Vec<_>>();
-        let mut heads = Vec::new();
-        for disk in members {
-            match disk
-                .pool_meta_native_recovery(Request::InspectIdentity {})
-                .await
-                .expect("physical identity inspection")
-            {
-                Response::IdentityInspected { disk_id, raw } => heads.push((disk_id, raw)),
-                _ => panic!("identity inspection must return its physical head"),
-            }
-        }
-        all.push(heads);
-    }
-    all
-}
-
-async fn legacy_native_owner_fixture(version: u16, stale: bool) -> (PhysicalFixture, Vec<u8>) {
-    let fixture = owner_repair_no_backups_fixture().await;
-    let mut meta = match decode_pool_meta_replica(fixture.canonical.clone()) {
-        PoolMetaReplica::Valid {
-            meta, committed: true, ..
-        } => meta,
-        _ => panic!("fixture must provide valid committed pool metadata"),
-    };
-    meta.version = version;
-    let raw = meta
-        .encode_config_data_for_v2_gate(version == POOL_META_VERSION)
-        .expect("legacy fixture should encode in its original version");
-    assert_eq!(u16::from_le_bytes([raw[2], raw[3]]), version);
-    let all = disks(&fixture.store).await;
-    let now = OffsetDateTime::now_utc();
-    for pool in &all {
-        let heads = replicas(&raw, now).await;
-        for (index, disk) in pool.iter().enumerate() {
-            fs::write(object_path(disk).join("xl.meta"), &heads[index])
-                .await
-                .expect("install exact legacy head");
-        }
-    }
-    if stale {
-        let old = replicas(&raw, now - Duration::seconds(10)).await;
-        fs::write(object_path(&all[0][0]).join("xl.meta"), &old[0])
-            .await
-            .expect("install stale same-raw legacy head");
-    }
-    (fixture, raw)
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_v1_with_all_upgrade_gates_disabled_keeps_exact_raw() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            let (fixture, raw) = legacy_native_owner_fixture(POOL_META_V1_VERSION, false).await;
-            let guard = owner(&fixture.store).await;
-            let mut state = fixture.store.pool_meta_save_gate.lock().await;
-            let result = tokio::time::timeout(
-                std::time::Duration::from_secs(30),
-                fixture.store.heal_pool_meta_replica_under_fence(0, guard, &mut state),
-            )
-            .await
-            .expect("legacy native heal must terminate");
-            assert!(result.is_ok(), "fully online legacy native heal should succeed: {result:?}");
-            drop(state);
-            let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-            for read in &reads {
-                assert!(
-                    matches!(&read.replica, PoolMetaReplica::Valid { raw: bytes, revision, .. }
-                    if bytes == &raw && revision.version == POOL_META_V1_VERSION),
-                    "native heal must not upgrade a V1 raw payload when both upgrade gates are disabled"
-                );
-            }
-        },
-    )
-    .await;
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_rejects_legacy_source_with_trailing_bytes_without_writes() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            for version in [POOL_META_V1_VERSION, POOL_META_VERSION] {
-                let (fixture, raw) = legacy_native_owner_fixture(version, false).await;
-                let mut source_raw = raw.clone();
-                // A second MessagePack value is readable by legacy decoding but
-                // must not be copied as part of an unverified repair payload.
-                source_raw.push(0xc0);
-                assert!(
-                    matches!(decode_pool_meta_replica(source_raw.clone()), PoolMetaReplica::Valid { raw, .. } if raw == source_raw),
-                    "ordinary legacy reads must remain compatible with trailing bytes"
-                );
-                let all_disks = disks(&fixture.store).await;
-                let source_heads = replicas(&source_raw, OffsetDateTime::now_utc() + Duration::seconds(1)).await;
-                for (index, disk) in all_disks[0].iter().enumerate() {
-                    fs::write(object_path(disk).join("xl.meta"), &source_heads[index])
-                        .await
-                        .expect("install readable legacy source with trailing bytes");
-                }
-                let selection = load_pool_meta_replicas(fixture.store.pools.clone(), true)
-                    .await
-                    .expect("legacy semantic selection must remain readable");
-                assert_eq!(selection.legacy_raw.as_deref(), Some(source_raw.as_slice()));
-                let before = snapshots(&fixture.store).await;
-                let identities = owner_repair_identity_heads(&fixture.store).await;
-                let guard = owner(&fixture.store).await;
-                let mut state = fixture.store.pool_meta_save_gate.lock().await;
-                let result = tokio::time::timeout(
-                    std::time::Duration::from_secs(30),
-                    fixture.store.heal_pool_meta_replica_under_fence(1, guard, &mut state),
-                )
-                .await
-                .expect("legacy native heal must terminate");
-                drop(state);
-                assert!(result.is_err(), "version {version}: unparsed trailing source bytes must not be republished");
-                assert_eq!(snapshots(&fixture.store).await, before, "version {version}: no pool.bin head or backup may change");
-                assert_eq!(
-                    owner_repair_identity_heads(&fixture.store).await,
-                    identities,
-                    "version {version}: no identity shard may change"
-                );
-                let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-                assert!(matches!(&reads[0].replica, PoolMetaReplica::Valid { raw, .. } if raw == &source_raw));
-                assert!(matches!(&reads[1].replica, PoolMetaReplica::Valid { raw: target, .. } if target == &raw));
-            }
-        },
-    )
-    .await;
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_mixed_v1_v2_preserves_observed_format_floor() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            for first_version in [POOL_META_V1_VERSION, POOL_META_VERSION] {
-                for target_pool in [0, 1] {
-                    let (fixture, raw_v1) = legacy_native_owner_fixture(POOL_META_V1_VERSION, false).await;
-                    let mut meta = match decode_pool_meta_replica(raw_v1.clone()) {
-                        PoolMetaReplica::Valid { meta, committed: true, .. } => meta,
-                        _ => panic!("initial V1 metadata must decode"),
-                    };
-                    meta.version = POOL_META_VERSION;
-                    let raw_v2 = meta.encode_config_data_for_v2_gate(true).expect("equivalent V2 payload must encode");
-                    assert_eq!(u16::from_le_bytes([raw_v1[2], raw_v1[3]]), POOL_META_V1_VERSION);
-                    assert_eq!(u16::from_le_bytes([raw_v2[2], raw_v2[3]]), POOL_META_VERSION);
-                    let semantic_v1 = match decode_pool_meta_replica(raw_v1.clone()) {
-                        PoolMetaReplica::Valid { canonical, .. } => canonical,
-                        _ => panic!("V1 payload must remain valid"),
-                    };
-                    let semantic_v2 = match decode_pool_meta_replica(raw_v2.clone()) {
-                        PoolMetaReplica::Valid { canonical, .. } => canonical,
-                        _ => panic!("V2 payload must remain valid"),
-                    };
-                    assert_eq!(semantic_v1, semantic_v2, "the two formats must carry equivalent metadata");
-                    let other_version = if first_version == POOL_META_V1_VERSION { POOL_META_VERSION } else { POOL_META_V1_VERSION };
-                    // Pool two follows pool zero; pools zero and one cover both
-                    // orderings and both target formats in separate runs.
-                    let versions = [first_version, other_version, first_version];
-                    let physical = disks(&fixture.store).await;
-                    let timestamp = OffsetDateTime::now_utc();
-                    for (pool_index, pool) in physical.iter().enumerate() {
-                        let raw = if versions[pool_index] == POOL_META_V1_VERSION { &raw_v1 } else { &raw_v2 };
-                        let heads = replicas(raw, timestamp).await;
-                        for (index, disk) in pool.iter().enumerate() {
-                            fs::write(object_path(disk).join("xl.meta"), &heads[index]).await.expect("install mixed legacy pool head");
-                        }
-                    }
-                    let before = snapshots(&fixture.store).await;
-                    let selection = load_pool_meta_replicas(fixture.store.pools.clone(), true)
-                        .await.expect("equivalent legacy pools should be selectable");
-                    assert_eq!(selection.revision.version, POOL_META_VERSION, "the observed V2 format floor must be retained");
-                    assert_eq!(selection.canonical.as_deref(), Some(semantic_v2.as_slice()));
-                    let guard = owner(&fixture.store).await;
-                    let mut state = fixture.store.pool_meta_save_gate.lock().await;
-                    tokio::time::timeout(std::time::Duration::from_secs(30),
-                        fixture.store.heal_pool_meta_replica_under_fence(target_pool, guard, &mut state))
-                        .await.expect("mixed legacy heal must terminate")
-                        .expect("equivalent legacy metadata should heal without downgrading the format floor");
-                    drop(state);
-                    let after = snapshots(&fixture.store).await;
-                    let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-                    for (pool_index, read) in reads.iter().enumerate() {
-                        let expected_version = if pool_index == target_pool { POOL_META_VERSION } else { versions[pool_index] };
-                        let expected_raw = if expected_version == POOL_META_V1_VERSION { &raw_v1 } else { &raw_v2 };
-                        assert!(matches!(&read.replica,
-                            PoolMetaReplica::Valid { raw, canonical, revision, committed: true, .. }
-                                if raw == expected_raw && canonical == &semantic_v2 && revision.version == expected_version
-                        ), "pool {pool_index}, first={first_version}, target={target_pool}: preserve equivalent payload and expected legacy version");
-                        for (index, snapshot) in after[pool_index].iter().enumerate() {
-                            codec::validate_inline_pool_meta_shard(snapshot.current.as_ref().expect("physical head"), index, expected_raw)
-                                .await.expect("every physical shard must match its selected legacy payload");
-                        }
-                        if pool_index != target_pool {
-                            assert_eq!(after[pool_index], before[pool_index], "healing one pool must not modify other pools");
-                        }
-                    }
-                }
-            }
-        },
-    ).await;
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_rejects_v1_and_v3_prepare_in_either_pool_order() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            for prepare_pool in [0, 1] {
-                let (fixture, raw_v1) = legacy_native_owner_fixture(POOL_META_V1_VERSION, false).await;
-                let (legacy_meta, legacy_canonical) = match decode_pool_meta_replica(raw_v1.clone()) {
-                    PoolMetaReplica::Valid {
-                        meta,
-                        canonical,
-                        revision,
-                        committed: true,
-                        ..
-                    } if revision.version == POOL_META_V1_VERSION => (meta, canonical),
-                    _ => panic!("baseline V1 metadata must be committed and readable"),
-                };
-                let previous = PoolMetaCommittedCandidate {
-                    canonical: legacy_canonical,
-                    meta: legacy_meta.clone(),
-                    revision: PoolMetaRevision::legacy(POOL_META_V1_VERSION),
-                };
-                let mut next = legacy_meta;
-                next.version = POOL_META_GENERATION_VERSION;
-                next.pools[0].last_update += Duration::seconds(1);
-                let revision = PoolMetaRevision {
-                    version: POOL_META_GENERATION_VERSION,
-                    cluster_id: fixture.revision.cluster_id,
-                    epoch: fixture.revision.epoch,
-                    generation: 1,
-                    transaction_id: Some(Uuid::new_v4()),
-                };
-                let pending = encode_pool_meta_v3_envelope(&next, revision, false, Some(&previous))
-                    .expect("V3 PREPARE with V1 predecessor must encode");
-                assert!(matches!(decode_pool_meta_replica(pending.clone()),
-                    PoolMetaReplica::Valid { committed: false, revision: actual, .. } if actual == revision));
-                let heads = replicas(&pending, OffsetDateTime::now_utc() + Duration::seconds(1)).await;
-                let physical = disks(&fixture.store).await;
-                for (index, disk) in physical[prepare_pool].iter().enumerate() {
-                    fs::write(object_path(disk).join("xl.meta"), &heads[index])
-                        .await
-                        .expect("install task-owned V3 PREPARE evidence");
-                }
-                let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-                assert!(matches!(&reads[prepare_pool].replica,
-                    PoolMetaReplica::Valid { raw, committed: false, revision: actual, .. }
-                        if raw == &pending && *actual == revision));
-                let other_pool = 1 - prepare_pool;
-                assert!(matches!(&reads[other_pool].replica,
-                    PoolMetaReplica::Valid { raw, committed: true, revision: actual, .. }
-                        if raw == &raw_v1 && actual.version == POOL_META_V1_VERSION));
-                let before = snapshots(&fixture.store).await;
-                let identities = owner_repair_identity_heads(&fixture.store).await;
-                let guard = owner(&fixture.store).await;
-                let mut state = fixture.store.pool_meta_save_gate.lock().await;
-                let result = tokio::time::timeout(
-                    std::time::Duration::from_secs(30),
-                    fixture
-                        .store
-                        .heal_pool_meta_replica_under_fence(prepare_pool, guard, &mut state),
-                )
-                .await
-                .expect("mixed V1/V3 PREPARE heal must terminate");
-                drop(state);
-                assert!(
-                    result.is_err(),
-                    "pool {prepare_pool}: native heal must not overwrite a V3 PREPARE with legacy data"
-                );
-                assert_eq!(
-                    snapshots(&fixture.store).await,
-                    before,
-                    "pool {prepare_pool}: rejection must retain all physical head and backup evidence"
-                );
-                assert_eq!(
-                    owner_repair_identity_heads(&fixture.store).await,
-                    identities,
-                    "pool {prepare_pool}: rejection must not mutate identity evidence"
-                );
-            }
-        },
-    )
-    .await;
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_rejects_v1_legacy_dont_save_true_without_writes() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            let (fixture, safe_v1) = legacy_native_owner_fixture(POOL_META_V1_VERSION, false).await;
-            let meta = match decode_pool_meta_replica(safe_v1.clone()) {
-                PoolMetaReplica::Valid {
-                    meta, committed: true, ..
-                } => meta,
-                _ => panic!("baseline V1 metadata must decode"),
-            };
-            let statuses = meta
-                .pools
-                .iter()
-                .map(|pool| {
-                    assert!(pool.decommission.is_none(), "this regression fixture does not inject decommission state");
-                    LegacyPoolStatus {
-                        id: pool.id,
-                        cmd_line: pool.cmd_line.clone(),
-                        last_update: pool.last_update,
-                        decommission: None,
-                    }
-                })
-                .collect();
-            let legacy = LegacyPoolMeta {
-                version: POOL_META_V1_VERSION,
-                pools: statuses,
-                dont_save: true,
-            };
-            let mut dangerous_raw = Vec::new();
-            dangerous_raw.extend_from_slice(&POOL_META_FORMAT.to_le_bytes());
-            dangerous_raw.extend_from_slice(&POOL_META_V1_VERSION.to_le_bytes());
-            dangerous_raw.extend_from_slice(&rmp_serde::to_vec(&legacy).expect("legacy three-field tuple must serialize"));
-            let old_reader: LegacyPoolMeta =
-                rmp_serde::from_slice(&dangerous_raw[4..]).expect("legacy reader must decode source");
-            assert!(old_reader.dont_save, "the old reader would treat this source as permanently do-not-save");
-            assert_eq!(rmp::decode::read_array_len(&mut &dangerous_raw[4..]).expect("tuple length"), 3);
-            let source = match decode_pool_meta_replica(dangerous_raw.clone()) {
-                PoolMetaReplica::Valid {
-                    canonical,
-                    revision,
-                    committed: true,
-                    ..
-                } => {
-                    assert_eq!(revision.version, POOL_META_V1_VERSION);
-                    canonical
-                }
-                _ => panic!("current reader must recognize the legacy source"),
-            };
-            assert!(matches!(decode_pool_meta_replica(safe_v1.clone()),
-                PoolMetaReplica::Valid { canonical, revision, committed: true, .. }
-                    if canonical == source && revision.version == POOL_META_V1_VERSION));
-            let physical = disks(&fixture.store).await;
-            let source_heads = replicas(&dangerous_raw, OffsetDateTime::now_utc() + Duration::seconds(1)).await;
-            for (index, disk) in physical[0].iter().enumerate() {
-                fs::write(object_path(disk).join("xl.meta"), &source_heads[index])
-                    .await
-                    .expect("install legacy source on pool zero");
-            }
-            let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-            assert!(matches!(&reads[0].replica, PoolMetaReplica::Valid { raw, committed: true, .. } if raw == &dangerous_raw));
-            assert!(matches!(&reads[1].replica, PoolMetaReplica::Valid { raw, committed: true, .. } if raw == &safe_v1));
-            let before = snapshots(&fixture.store).await;
-            let identities = owner_repair_identity_heads(&fixture.store).await;
-            let guard = owner(&fixture.store).await;
-            let mut state = fixture.store.pool_meta_save_gate.lock().await;
-            let result = tokio::time::timeout(
-                std::time::Duration::from_secs(30),
-                fixture.store.heal_pool_meta_replica_under_fence(1, guard, &mut state),
-            )
-            .await
-            .expect("unsafe legacy heal must terminate");
-            drop(state);
-            let error = result.expect_err("native heal must reject a source whose old-reader dont_save is true");
-            assert!(
-                error.to_string().contains("dont_save"),
-                "rejection must identify the unsafe legacy field: {error}"
-            );
-            assert_eq!(
-                snapshots(&fixture.store).await,
-                before,
-                "rejection must preserve every original head and backup"
-            );
-            assert_eq!(
-                owner_repair_identity_heads(&fixture.store).await,
-                identities,
-                "rejection must not write identity shards"
-            );
-            let after = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-            assert!(matches!(&after[0].replica, PoolMetaReplica::Valid { raw, .. } if raw == &dangerous_raw));
-            assert!(
-                matches!(&after[1].replica, PoolMetaReplica::Valid { raw, .. } if raw == &safe_v1),
-                "the dangerous source bytes must not be copied into the target pool"
-            );
-        },
-    )
-    .await;
-}
-
-#[tokio::test]
-#[serial_test::serial(pool_meta_version_env)]
-async fn pool_meta_native_heal_rejects_target_v1_dont_save_true_without_writes() {
-    temp_env::async_with_vars(
-        [
-            (rustfs_config::ENV_POOL_META_V2_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V2_FLEET_CONFIRMED, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_WRITE, Some("false")),
-            (rustfs_config::ENV_POOL_META_V3_FLEET_CONFIRMED, Some("false")),
-        ],
-        async {
-            let (fixture, safe_v1) = legacy_native_owner_fixture(POOL_META_V1_VERSION, false).await;
-            let meta = match decode_pool_meta_replica(safe_v1.clone()) {
-                PoolMetaReplica::Valid {
-                    meta, committed: true, ..
-                } => meta,
-                _ => panic!("baseline V1 metadata must decode"),
-            };
-            let statuses = meta
-                .pools
-                .iter()
-                .map(|pool| {
-                    assert!(pool.decommission.is_none(), "this regression fixture does not inject decommission state");
-                    LegacyPoolStatus {
-                        id: pool.id,
-                        cmd_line: pool.cmd_line.clone(),
-                        last_update: pool.last_update,
-                        decommission: None,
-                    }
-                })
-                .collect();
-            let legacy = LegacyPoolMeta {
-                version: POOL_META_V1_VERSION,
-                pools: statuses,
-                dont_save: true,
-            };
-            let mut dangerous_raw = Vec::new();
-            dangerous_raw.extend_from_slice(&POOL_META_FORMAT.to_le_bytes());
-            dangerous_raw.extend_from_slice(&POOL_META_V1_VERSION.to_le_bytes());
-            dangerous_raw.extend_from_slice(&rmp_serde::to_vec(&legacy).expect("legacy three-field tuple must serialize"));
-            let old_reader: LegacyPoolMeta =
-                rmp_serde::from_slice(&dangerous_raw[4..]).expect("legacy reader must decode target");
-            assert!(old_reader.dont_save, "the old reader interprets the target as do-not-save");
-            assert_eq!(rmp::decode::read_array_len(&mut &dangerous_raw[4..]).expect("tuple length"), 3);
-            let source_canonical = match decode_pool_meta_replica(safe_v1.clone()) {
-                PoolMetaReplica::Valid {
-                    canonical,
-                    revision,
-                    committed: true,
-                    ..
-                } => {
-                    assert_eq!(revision.version, POOL_META_V1_VERSION);
-                    canonical
-                }
-                _ => panic!("safe pool-zero source must decode"),
-            };
-            assert!(
-                matches!(decode_pool_meta_replica(dangerous_raw.clone()),
-                PoolMetaReplica::Valid { canonical, revision, committed: true, .. }
-                    if canonical == source_canonical && revision.version == POOL_META_V1_VERSION),
-                "the dangerous target must remain semantically equivalent to the safe source"
-            );
-            let physical = disks(&fixture.store).await;
-            let target_heads = replicas(&dangerous_raw, OffsetDateTime::now_utc() + Duration::seconds(1)).await;
-            for (index, disk) in physical[1].iter().enumerate() {
-                fs::write(object_path(disk).join("xl.meta"), &target_heads[index])
-                    .await
-                    .expect("install legacy dangerous target head");
-            }
-            let reads = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-            assert!(matches!(&reads[0].replica, PoolMetaReplica::Valid { raw, committed: true, .. } if raw == &safe_v1));
-            assert!(matches!(&reads[1].replica, PoolMetaReplica::Valid { raw, committed: true, .. } if raw == &dangerous_raw));
-            let before = snapshots(&fixture.store).await;
-            let identities = owner_repair_identity_heads(&fixture.store).await;
-            let guard = owner(&fixture.store).await;
-            let mut state = fixture.store.pool_meta_save_gate.lock().await;
-            let result = tokio::time::timeout(
-                std::time::Duration::from_secs(30),
-                fixture.store.heal_pool_meta_replica_under_fence(1, guard, &mut state),
-            )
-            .await
-            .expect("unsafe legacy target heal must terminate");
-            drop(state);
-            let error = result.expect_err("native heal must reject a target whose old-reader dont_save is true");
-            assert!(
-                error.to_string().contains("dont_save"),
-                "rejection must identify the unsafe legacy field: {error}"
-            );
-            assert_eq!(
-                snapshots(&fixture.store).await,
-                before,
-                "rejection must preserve all physical heads and backups"
-            );
-            assert_eq!(
-                owner_repair_identity_heads(&fixture.store).await,
-                identities,
-                "rejection must not write identity shards"
-            );
-            let after = read_pool_meta_replicas(fixture.store.pools.clone(), true).await;
-            assert!(matches!(&after[0].replica, PoolMetaReplica::Valid { raw, .. } if raw == &safe_v1));
-            assert!(
-                matches!(&after[1].replica, PoolMetaReplica::Valid { raw, .. } if raw == &dangerous_raw),
-                "unsafe target evidence must not be overwritten by the safe source"
-            );
-        },
-    )
-    .await;
-}

crates/ecstore/src/core/pool_meta_recovery_codec.rs

@@ -391,7 +391,7 @@ pub(super) async fn fixture_inline_pool_meta_replicas(payload: &[u8], modified:
         writer.shutdown().await.expect("fixture bitrot writer should finish");
         let mut info = base.clone();
         info.erasure.index = *coding_index;
-        info.data = Some(writer.into_inline_data().expect("fixture writer should retain inline bytes"));
+        info.data = Some(Bytes::from(writer.into_inline_data().expect("fixture writer should retain inline bytes")));
         let mut meta = FileMeta::new();
         meta.add_version(info).expect("test inline FileInfo should serialize");
         raw.push(Bytes::from(meta.marshal_msg().expect("test xl.meta should serialize")));

crates/ecstore/src/core/pools.rs

@@ -94,6 +94,7 @@ use serde::{Deserialize, Serialize};
 use sha2::{Digest, Sha256};
 use std::collections::{HashMap, HashSet};
 use std::fmt::Display;
+#[cfg(test)]
 use std::io::Cursor;
 use std::io::Write;
 use std::path::PathBuf;
@@ -3719,45 +3720,33 @@ fn is_decommission_copy_quorum_deferral(err: &Error) -> bool {
     data_movement::data_movement_stage_source_as::<DecommissionCopyQuorumFailure>(err).is_some()
 }
 
-/// A copy whose object namespace lock remained unavailable through its
-/// in-place retries, retained as a typed deferral.
+/// The storage error of a version copy that kept timing out on a namespace
+/// lock through its in-place retries, kept typed so the entry failure policy
+/// defers it.
 #[derive(Debug, thiserror::Error)]
 #[error("{0}")]
-struct DecommissionCopyLockUnavailable(#[source] Error);
+struct DecommissionCopyLockTimeout(#[source] Error);
 
-fn is_decommission_copy_lock_unavailable_error(err: &Error, bucket: &str, object: &str) -> bool {
-    let source = data_movement::data_movement_stage_source(err).unwrap_or(err);
-    match source {
-        Error::Lock(rustfs_lock::LockError::Timeout { .. }) => true,
-        Error::NamespaceLockQuorumUnavailable {
-            mode: "read",
-            bucket: lock_bucket,
-            object: lock_object,
-            ..
-        } => {
-            data_movement::data_movement_error_is_stage(err, "prepare_put_object")
-                && lock_bucket == bucket
-                && lock_object == object
-        }
-        _ => false,
-    }
+fn is_decommission_copy_lock_timeout_error(err: &Error) -> bool {
+    let err = data_movement::data_movement_stage_source(err).unwrap_or(err);
+    matches!(err, Error::Lock(rustfs_lock::LockError::Timeout { .. }))
 }
 
-/// A version copy that could not acquire its namespace lock leaves the source
+/// A version copy that timed out acquiring a namespace lock leaves the source
 /// in place; the next attempt copies the version again or finds an equivalent
 /// committed target. The lock is held by another mutation of the key or, when
 /// this node restarted mid-copy, by its previous incarnation until that lock's
 /// lease expires on the peers. Either clears by waiting, so the entry is
 /// deferred instead of being counted as a permanent per-object failure.
-fn decommission_copy_lock_unavailable_deferral(stage: &str, bucket: &str, object: &str, err: Error) -> Error {
+fn decommission_copy_lock_timeout_deferral(stage: &str, bucket: &str, object: &str, err: Error) -> Error {
     data_movement::data_movement_context_error(
-        format!("decommission {stage} could not acquire a namespace lock for {bucket}/{object}: {err}"),
-        DecommissionCopyLockUnavailable(err),
+        format!("decommission {stage} timed out on a namespace lock for {bucket}/{object}: {err}"),
+        DecommissionCopyLockTimeout(err),
     )
 }
 
-fn is_decommission_copy_lock_unavailable_deferral(err: &Error) -> bool {
-    data_movement::data_movement_stage_source_as::<DecommissionCopyLockUnavailable>(err).is_some()
+fn is_decommission_copy_lock_timeout_deferral(err: &Error) -> bool {
+    data_movement::data_movement_stage_source_as::<DecommissionCopyLockTimeout>(err).is_some()
 }
 
 /// The deferral of a version copy whose in-place retries ended on `error`, if
@@ -3767,8 +3756,8 @@ fn take_decommission_copy_deferral(stage: &str, bucket: &str, object: &str, erro
         return Some(decommission_copy_quorum_deferral(stage, bucket, object, err));
     }
     error
-        .take_if(|err| is_decommission_copy_lock_unavailable_error(err, bucket, object))
-        .map(|err| decommission_copy_lock_unavailable_deferral(stage, bucket, object, err))
+        .take_if(|err| is_decommission_copy_lock_timeout_error(err))
+        .map(|err| decommission_copy_lock_timeout_deferral(stage, bucket, object, err))
 }
 
 fn resolve_decommission_entry_reload_result(result: Result<()>, bucket: &str, object_name: &str) -> Result<()> {
@@ -5833,13 +5822,13 @@ enum DecommissionEntryOutcome {
 /// entry is done and must not be counted as a failure or escalated. A quorum
 /// failure of the source cleanup is deferred too: the copied source is still
 /// in place and the next attempt cleans it up again. So is a version copy that
-/// lost drive quorum or could not acquire an object namespace lock through its in-place
+/// lost drive quorum or timed out on a namespace lock through its in-place
 /// retries: the source still holds the version and the next attempt copies it
 /// again. Every other failure stays terminal.
 fn resolve_decommission_entry_failure(err: Error) -> Result<DecommissionEntryOutcome> {
     if is_decommission_source_cleanup_retryable_error(&err)
         || is_decommission_copy_quorum_deferral(&err)
-        || is_decommission_copy_lock_unavailable_deferral(&err)
+        || is_decommission_copy_lock_timeout_deferral(&err)
     {
         return Ok(DecommissionEntryOutcome::Deferred(err));
     }
@@ -6838,47 +6827,11 @@ impl Drop for PoolMetaTransactionArm {
     }
 }
 
-fn ensure_legacy_pool_meta_republish_safe(data: &[u8]) -> Result<()> {
-    if data.len() >= 4
-        && LittleEndian::read_u16(&data[2..4]) == POOL_META_V1_VERSION
-        // The selection already validates the payload. The runtime-only
-        // flag can only appear in the legacy three-field sequence or map.
-        && rmp::decode::read_array_len(&mut &data[4..])
-            .or_else(|_| rmp::decode::read_map_len(&mut &data[4..]))
-            .ok()
-            == Some(3)
-        && let Ok(legacy) = rmp_serde::from_slice::<LegacyPoolMeta>(&data[4..])
-        && legacy.dont_save
-    {
-        return Err(Error::other("pool metadata legacy source contains dont_save=true"));
-    }
-    Ok(())
-}
-
-// Ordinary legacy reads retain their compatibility behavior, but bytes that
-// will be copied to another pool must not contain an unparsed extension.
-fn ensure_legacy_pool_meta_payload_complete(data: &[u8]) -> Result<()> {
-    let payload = data
-        .get(4..)
-        .ok_or_else(|| Error::other("pool metadata legacy source is too short"))?;
-    let mut decoder = rmp_serde::Deserializer::new(Cursor::new(payload));
-    serde::de::IgnoredAny::deserialize(&mut decoder).map_err(|_| Error::other("pool metadata legacy source is invalid"))?;
-    let payload_len = u64::try_from(payload.len()).map_err(|_| Error::other("pool metadata legacy source is too large"))?;
-    if decoder.get_ref().position() != payload_len {
-        return Err(Error::other("pool metadata legacy source has trailing bytes"));
-    }
-    Ok(())
-}
-
 #[derive(Debug)]
 struct PoolMetaSelection {
     meta: PoolMeta,
     revision: PoolMetaRevision,
     canonical: Option<Vec<u8>>,
-    // Legacy semantic comparison canonicalizes to V2; a heal must instead
-    // preserve verified raw bytes at the highest observed format floor.
-    legacy_raw: Option<Vec<u8>>,
-    legacy_has_unsafe_flag: bool,
     replica_state: PoolMetaReplicaState,
     cas_tokens: Vec<PoolMetaCasToken>,
     absent: bool,
@@ -7269,8 +7222,6 @@ fn select_pool_meta_replica_reads(reads: Vec<PoolMetaReplicaRead>) -> Result<Poo
             meta: PoolMeta::default(),
             revision: PoolMetaRevision::legacy(0),
             canonical: None,
-            legacy_raw: None,
-            legacy_has_unsafe_flag: false,
             replica_state: PoolMetaReplicaState {
                 needs_repair: false,
                 repair_write_safe: true,
@@ -7325,8 +7276,6 @@ fn select_pool_meta_replica_reads(reads: Vec<PoolMetaReplicaRead>) -> Result<Poo
             meta: selected.meta.clone(),
             revision: selected.revision,
             canonical: Some(selected.canonical.clone()),
-            legacy_raw: None,
-            legacy_has_unsafe_flag: false,
             replica_state: PoolMetaReplicaState {
                 needs_repair,
                 repair_write_safe,
@@ -7340,10 +7289,6 @@ fn select_pool_meta_replica_reads(reads: Vec<PoolMetaReplicaRead>) -> Result<Poo
 
     // Legacy V1/V2 has no durable generation. Pool zero remains the commit
     // record; divergent backups without it are ambiguous and fail closed.
-    let legacy_has_unsafe_flag = committed
-        .iter()
-        .any(|(_, raw, _)| ensure_legacy_pool_meta_republish_safe(raw).is_err());
-    let mut floor_raw = None;
     let mut selected: Option<(usize, Vec<u8>, PoolMetaCommittedCandidate)> = None;
     for (idx, raw, candidate) in committed {
         if let Some((selected_idx, selected_raw, selected_candidate)) = selected.as_ref() {
@@ -7357,36 +7302,19 @@ fn select_pool_meta_replica_reads(reads: Vec<PoolMetaReplicaRead>) -> Result<Poo
                 }
             } else {
                 needs_repair |= selected_raw != &raw;
-                if floor_raw.is_none()
-                    && candidate.revision.version == observed_version
-                    && raw
-                        .get(2..4)
-                        .is_some_and(|version| LittleEndian::read_u16(version) == observed_version)
-                {
-                    floor_raw = Some(raw);
-                }
             }
         } else {
             selected = Some((idx, raw, candidate));
         }
     }
-    let (_, selected_raw, mut selected) =
+    let (_, _, mut selected) =
         selected.ok_or_else(|| Error::other("pool metadata recovery required: no valid legacy replica is available"))?;
-    if selected.revision.version == observed_version
-        && selected_raw
-            .get(2..4)
-            .is_some_and(|version| LittleEndian::read_u16(version) == observed_version)
-    {
-        floor_raw = Some(selected_raw);
-    }
     selected.meta.version = observed_version;
     selected.revision.version = observed_version;
     Ok(PoolMetaSelection {
         meta: selected.meta,
         revision: selected.revision,
         canonical: Some(selected.canonical),
-        legacy_raw: floor_raw,
-        legacy_has_unsafe_flag,
         replica_state: PoolMetaReplicaState {
             needs_repair,
             repair_write_safe,
@@ -14606,23 +14534,6 @@ impl ECStore {
             .canonical
             .as_ref()
             .ok_or_else(|| Error::other("pool metadata heal has no committed source"))?;
-        if selection.generation_protocol_observed && !selection.revision.is_generation_protocol() {
-            return Err(Error::other("pool metadata heal requires recovery of the observed generation protocol"));
-        }
-        if selection.legacy_has_unsafe_flag {
-            return Err(Error::other("pool metadata legacy replica contains dont_save=true"));
-        }
-        let repair_data = if selection.revision.is_generation_protocol() {
-            canonical.clone()
-        } else {
-            let raw = selection
-                .legacy_raw
-                .clone()
-                .ok_or_else(|| Error::other("pool metadata heal cannot prove the legacy format floor"))?;
-            ensure_legacy_pool_meta_payload_complete(&raw)?;
-            raw
-        };
-        ensure_legacy_pool_meta_republish_safe(&repair_data)?;
         let pool = self
             .pools
             .get(pool_index)
@@ -14633,10 +14544,10 @@ impl ECStore {
             .get(pool_index)
             .ok_or_else(|| Error::other("pool metadata heal has no target revision"))?;
         let mut arm = state.arm_transaction();
-        save_pool_meta_object_cas(pool.clone(), POOL_META_NAME, repair_data.clone(), token, &fence, "native_heal", &mut arm)
+        save_pool_meta_object_cas(pool.clone(), POOL_META_NAME, canonical.clone(), token, &fence, "native_heal", &mut arm)
             .await?;
         let (confirmed, _) = read_config_no_lock_preserve_empty_with_metadata(pool, POOL_META_NAME).await?;
-        if confirmed != repair_data {
+        if confirmed != *canonical {
             return Err(Error::other("pool metadata native heal readback diverged"));
         }
         fence.ensure_held()?;
@@ -28442,7 +28353,7 @@ mod tests {
             "one version must commit before the next version times out"
         );
         assert!(
-            matches!(&outcome, DecommissionEntryOutcome::Deferred(err) if is_decommission_copy_lock_unavailable_deferral(err)),
+            matches!(&outcome, DecommissionEntryOutcome::Deferred(err) if is_decommission_copy_lock_timeout_deferral(err)),
             "{outcome:?}"
         );
         assert_eq!(
@@ -28476,88 +28387,6 @@ mod tests {
         assert_eq!(actual, b"written after versioning was enabled");
     }
 
-    /// A target lookup that loses its read-lock quorum must retain the source
-    /// and resume an entry after an earlier version has already committed.
-    #[tokio::test]
-    #[serial_test::serial]
-    async fn decommission_defers_target_lookup_read_lock_quorum_and_resumes() {
-        use tokio::io::AsyncReadExt as _;
-
-        let fixture = NullVersionDecommission::new(NullVersionTop::NewerVersion).await;
-        let object = fixture.object;
-        let attempted = Arc::new(AtomicUsize::new(0));
-        let fault = DecommissionTestFaultGuard::install_with_error(
-            Arc::new({
-                let attempted = Arc::clone(&attempted);
-                move |stage, _, faulted, _, success| {
-                    stage == "before_target_commit"
-                        && faulted == object
-                        && success
-                        && attempted.fetch_add(1, Ordering::SeqCst) > 0
-                }
-            }),
-            Some(Arc::new(|_, bucket, object| {
-                data_movement::data_movement_stage_error_for_test(
-                    "decommission_object",
-                    "prepare_put_object",
-                    bucket,
-                    object,
-                    Error::NamespaceLockQuorumUnavailable {
-                        mode: "read",
-                        bucket: bucket.to_owned(),
-                        object: object.to_owned(),
-                        required: 1,
-                        achieved: 0,
-                    },
-                )
-            })),
-        );
-        let (outcome, _) = fixture.run_entry().await;
-        assert!(
-            matches!(&outcome, DecommissionEntryOutcome::Deferred(err) if is_decommission_copy_lock_unavailable_deferral(err)),
-            "{outcome:?}"
-        );
-        fixture.assert_source_retained().await;
-        assert_eq!(
-            fixture
-                .target_versions()
-                .await
-                .expect("first version committed")
-                .versions
-                .len(),
-            1
-        );
-        assert_eq!(
-            fixture.store.pool_meta.read().await.pools[0]
-                .decommission
-                .as_ref()
-                .expect("active decommission")
-                .items_decommission_failed,
-            0
-        );
-
-        drop(fault);
-        let (outcome, _) = fixture.run_entry().await;
-        assert!(matches!(outcome, DecommissionEntryOutcome::Complete), "{outcome:?}");
-        fixture.assert_moved().await;
-        let mut reader = fixture.store.pools[1]
-            .get_object_reader(
-                fixture.bucket,
-                fixture.object,
-                None,
-                HeaderMap::new(),
-                &ObjectOptions {
-                    version_id: Some(fixture.seeded.versions[0].version_id.expect("newer version").to_string()),
-                    ..Default::default()
-                },
-            )
-            .await
-            .expect("the newer version must remain readable");
-        let mut actual = Vec::new();
-        reader.stream.read_to_end(&mut actual).await.expect("read the newer version");
-        assert_eq!(actual, b"written after versioning was enabled");
-    }
-
     /// A namespace lock still held on the target key, as by a copy whose node
     /// was killed mid-write, makes target selection fail with a typed
     /// object-lock timeout. A real held lock, not an injected error, must defer
@@ -28600,7 +28429,7 @@ mod tests {
 
             let (outcome, _) = fixture.run_entry().await;
             assert!(
-                matches!(&outcome, DecommissionEntryOutcome::Deferred(err) if is_decommission_copy_lock_unavailable_deferral(err)),
+                matches!(&outcome, DecommissionEntryOutcome::Deferred(err) if is_decommission_copy_lock_timeout_deferral(err)),
                 "{outcome:?}"
             );
             assert_eq!(
@@ -29009,17 +28838,17 @@ mod tests {
             timeout(),
         );
         for err in [timeout(), prepare] {
-            assert!(is_decommission_copy_lock_unavailable_error(&err, "bucket-a", "object-a"), "{err}");
+            assert!(is_decommission_copy_lock_timeout_error(&err), "{err}");
             assert!(!is_decommission_copy_quorum_error(&err), "{err}");
             let mut error = Some(err);
             let deferred = take_decommission_copy_deferral("migrate_object", "bucket-a", "object-a", &mut error)
                 .expect("a lock timeout copy must be deferred");
             assert!(error.is_none());
-            assert!(is_decommission_copy_lock_unavailable_deferral(&deferred));
+            assert!(is_decommission_copy_lock_timeout_deferral(&deferred));
             assert!(!is_decommission_copy_quorum_deferral(&deferred));
-            let failure = data_movement::data_movement_stage_source_as::<DecommissionCopyLockUnavailable>(&deferred)
+            let failure = data_movement::data_movement_stage_source_as::<DecommissionCopyLockTimeout>(&deferred)
                 .expect("the deferred error must keep its lock-timeout origin");
-            assert!(is_decommission_copy_lock_unavailable_error(&failure.0, "bucket-a", "object-a"));
+            assert!(is_decommission_copy_lock_timeout_error(&failure.0));
             assert!(matches!(
                 resolve_decommission_entry_failure(deferred),
                 Ok(DecommissionEntryOutcome::Deferred(_))
@@ -29044,43 +28873,6 @@ mod tests {
         }
     }
 
-    #[test]
-    fn decommission_copy_defers_only_the_matching_object_read_lock_quorum() {
-        let quorum = |mode, bucket: &str, object: &str| Error::NamespaceLockQuorumUnavailable {
-            mode,
-            bucket: bucket.to_owned(),
-            object: object.to_owned(),
-            required: 1,
-            achieved: 0,
-        };
-        let wrap = |stage, err| {
-            data_movement::data_movement_stage_error_for_test("decommission_object", stage, "bucket-a", "object-a", err)
-        };
-        let mut error = Some(wrap("prepare_put_object", quorum("read", "bucket-a", "object-a")));
-        let deferred = take_decommission_copy_deferral("migrate_object", "bucket-a", "object-a", &mut error)
-            .expect("matching read-lock quorum must defer");
-        assert!(error.is_none());
-        assert!(matches!(
-            resolve_decommission_entry_failure(deferred),
-            Ok(DecommissionEntryOutcome::Deferred(_))
-        ));
-        for err in [
-            quorum("read", "bucket-a", "object-a"),
-            wrap("source_recheck", quorum("read", "bucket-a", "object-a")),
-            wrap("prepare_put_object", quorum("write", "bucket-a", "object-a")),
-            wrap(
-                "prepare_put_object",
-                quorum("exact_delete_capacity_reconciliation", "bucket-a", "object-a"),
-            ),
-            wrap("prepare_put_object", quorum("read", "other-bucket", "object-a")),
-            wrap("prepare_put_object", quorum("read", "bucket-a", "other-object")),
-        ] {
-            let mut error = Some(err);
-            assert!(take_decommission_copy_deferral("migrate_object", "bucket-a", "object-a", &mut error).is_none());
-            assert!(error.is_some(), "unrelated lock failures must stay terminal");
-        }
-    }
-
     #[test]
     fn decommission_target_capacity_error_accepts_wrapped_capacity_errors() {
         let disk_full = Error::other(format!("decommission_object: put_object failed for bucket/object: {}", Error::DiskFull));
@@ -29559,53 +29351,6 @@ mod tests {
         );
     }
 
-    #[test]
-    fn legacy_republish_guard_checks_only_three_field_sequence_or_map() {
-        let frame = |payload: Vec<u8>| {
-            let mut data = Vec::new();
-            data.extend_from_slice(&POOL_META_FORMAT.to_le_bytes());
-            data.extend_from_slice(&POOL_META_V1_VERSION.to_le_bytes());
-            data.extend_from_slice(&payload);
-            data
-        };
-        let two_fields = PersistedPoolMetaV1 {
-            version: POOL_META_V1_VERSION,
-            pools: Vec::new(),
-        };
-        for payload in [rmp_serde::to_vec(&two_fields), rmp_serde::to_vec_named(&two_fields)] {
-            let data = frame(payload.expect("two-field V1 payload must serialize"));
-            assert!(matches!(decode_pool_meta_replica(data.clone()), PoolMetaReplica::Valid { .. }));
-            assert!(ensure_legacy_pool_meta_republish_safe(&data).is_ok());
-            assert!(ensure_legacy_pool_meta_payload_complete(&data).is_ok());
-            let mut trailing = data;
-            trailing.push(0xc0);
-            assert!(ensure_legacy_pool_meta_payload_complete(&trailing).is_err());
-        }
-        for dont_save in [false, true] {
-            let legacy = LegacyPoolMeta {
-                version: POOL_META_V1_VERSION,
-                pools: Vec::new(),
-                dont_save,
-            };
-            for payload in [rmp_serde::to_vec(&legacy), rmp_serde::to_vec_named(&legacy)] {
-                let data = frame(payload.expect("three-field V1 payload must serialize"));
-                assert!(matches!(decode_pool_meta_replica(data.clone()), PoolMetaReplica::Valid { .. }));
-                assert_eq!(ensure_legacy_pool_meta_republish_safe(&data).is_err(), dont_save);
-                assert!(ensure_legacy_pool_meta_payload_complete(&data).is_ok());
-                let mut trailing = data;
-                trailing.push(0xc0);
-                assert!(ensure_legacy_pool_meta_payload_complete(&trailing).is_err());
-            }
-        }
-        // This guard is only called for already-decoded replicas; malformed
-        // containers must fail selection rather than becoming repair sources.
-        let truncated = frame(vec![0x93, 0x01]);
-        assert!(matches!(
-            decode_pool_meta_replica(truncated),
-            PoolMetaReplica::Corrupt(_) | PoolMetaReplica::Incompatible(_)
-        ));
-    }
-
     #[test]
     fn pool_meta_decode_supports_legacy_payload() {
         let start_time = OffsetDateTime::now_utc();

crates/ecstore/src/crash_inject.rs

@@ -84,7 +84,7 @@ pub(crate) enum CrashPoint {
 }
 
 #[cfg(test)]
-pub(crate) use armed::{arm, disarm, is_armed, should_crash_at};
+pub(crate) use armed::{arm, disarm, should_crash_at};
 
 /// Production no-op: the compiler inlines this to `false`, so armed crash points
 /// exist only in `#[cfg(test)]` builds and never add a branch to real commits.
@@ -94,12 +94,6 @@ pub(crate) fn should_crash_at(_point: CrashPoint, _key: &str) -> bool {
     false
 }
 
-#[cfg(not(test))]
-#[inline(always)]
-pub(crate) fn is_armed(_point: CrashPoint, _key: &str) -> bool {
-    false
-}
-
 #[cfg(test)]
 mod armed {
     use super::CrashPoint;
@@ -138,10 +132,6 @@ mod armed {
         guard().retain(|(p, k)| !(*p == point && k == key));
     }
 
-    pub(crate) fn is_armed(point: CrashPoint, key: &str) -> bool {
-        guard().iter().any(|(p, k)| *p == point && k == key)
-    }
-
     /// Returns `true` (consuming the arm) iff a crash is armed for exactly this
     /// `point` and `key`.
     pub(crate) fn should_crash_at(point: CrashPoint, key: &str) -> bool {

crates/ecstore/src/data_movement/mod.rs

@@ -605,7 +605,6 @@ fn resolve_data_movement_abort_result(
 #[derive(Debug)]
 struct DataMovementStageError {
     rendered: String,
-    stage: Option<String>,
     source: Box<dyn std::error::Error + Send + Sync>,
 }
 
@@ -627,7 +626,6 @@ where
 {
     Error::other(DataMovementStageError {
         rendered,
-        stage: None,
         source: Box::new(err),
     })
 }
@@ -636,21 +634,7 @@ fn data_movement_stage_error<E>(op_label: &str, stage: &str, bucket: &str, objec
 where
     E: std::error::Error + Send + Sync + 'static,
 {
-    Error::other(DataMovementStageError {
-        rendered: format!("{op_label}: {stage} failed for {bucket}/{object}: {err}"),
-        stage: Some(stage.to_owned()),
-        source: Box::new(err),
-    })
-}
-
-pub(crate) fn data_movement_error_is_stage(err: &Error, stage: &str) -> bool {
-    let Error::Io(io_err) = err else {
-        return false;
-    };
-    io_err
-        .get_ref()
-        .and_then(|source| source.downcast_ref::<DataMovementStageError>())
-        .is_some_and(|source| source.stage.as_deref() == Some(stage))
+    data_movement_context_error(format!("{op_label}: {stage} failed for {bucket}/{object}: {err}"), err)
 }
 
 #[cfg(test)]

crates/ecstore/src/disk/cleanup_runtime.rs

@@ -624,58 +624,58 @@ mod tests {
 
     #[tokio::test]
     async fn cleanup_dispatch_retains_resource_units_without_inheriting_disk_policy() {
-        use crate::disk::io_admission::{current_disk_io_context, test_resource_units, with_background_disk_io};
+        use crate::disk::io_admission::{current_disk_io_context, with_background_disk_io, with_background_resource_unit};
+        use rustfs_concurrency::adaptive::AdaptiveAdmission;
+        use std::num::NonZeroU16;
         use tokio_util::sync::CancellationToken;
 
-        for physical_count in [1, 2] {
-            for mode in 0..4 {
-                let runtime = Arc::new(CleanupRuntime::new(config(1, 1, 1)).expect("cleanup runtime"));
-                let worker_runtime = runtime.clone();
-                let (unit, gates) = test_resource_units(physical_count);
-                let (started_tx, started_rx) = tokio::sync::oneshot::channel();
-                let (release_tx, release_rx) = tokio::sync::oneshot::channel();
-                let work = async move {
-                    started_tx
-                        .send((current_resource_unit().is_some(), current_disk_io_context().is_none()))
-                        .expect("report worker context");
-                    release_rx.await.expect("release owned worker");
-                    Ok::<_, super::super::error::DiskError>(())
-                };
-                let task = tokio::spawn(with_background_disk_io(
-                    CancellationToken::new(),
-                    with_optional_resource_unit(Some(unit), async move {
-                        match mode {
-                            0 => worker_runtime
-                                .disk_operation(work, DiskAdmission::Request)
-                                .await
-                                .expect("disk operation"),
-                            1 => worker_runtime.gc_operation(move |_| work).await.expect("GC operation"),
-                            2 => {
-                                let reservation = worker_runtime.reserve().expect("cleanup reservation");
-                                run(Some(reservation), async { work.await.expect("cleanup operation") }).await;
-                            }
-                            _ => spawn(None, work)
-                                .await
-                                .expect("unisolated worker")
-                                .expect("unisolated operation"),
+        for mode in 0..4 {
+            let runtime = Arc::new(CleanupRuntime::new(config(1, 1, 1)).expect("cleanup runtime"));
+            let worker_runtime = runtime.clone();
+            let gate = AdaptiveAdmission::new(NonZeroU16::new(1).expect("one unit"), 1);
+            let (started_tx, started_rx) = tokio::sync::oneshot::channel();
+            let (release_tx, release_rx) = tokio::sync::oneshot::channel();
+            let work = async move {
+                started_tx
+                    .send((current_resource_unit().is_some(), current_disk_io_context().is_none()))
+                    .expect("report worker context");
+                release_rx.await.expect("release owned worker");
+                Ok::<_, super::super::error::DiskError>(())
+            };
+            let task = tokio::spawn(with_background_disk_io(
+                CancellationToken::new(),
+                with_background_resource_unit(gate.acquire().await, async move {
+                    match mode {
+                        0 => worker_runtime
+                            .disk_operation(work, DiskAdmission::Request)
+                            .await
+                            .expect("disk operation"),
+                        1 => worker_runtime.gc_operation(move |_| work).await.expect("GC operation"),
+                        2 => {
+                            let reservation = worker_runtime.reserve().expect("cleanup reservation");
+                            run(Some(reservation), async { work.await.expect("cleanup operation") }).await;
                         }
-                    }),
-                ));
-                let (inherited, original_policy) = deadline(started_rx).await.expect("owned work starts");
-                task.abort();
-                assert!(task.await.expect_err("waiter cancelled").is_cancelled());
-                let held: Vec<_> = gates.iter().map(|gate| gate.snapshot().active).collect();
-                release_tx.send(()).expect("owned work survives cancellation");
-                deadline(async {
-                    while gates.iter().any(|gate| gate.snapshot().active != 0) {
-                        tokio::task::yield_now().await;
+                        _ => spawn(None, work)
+                            .await
+                            .expect("unisolated worker")
+                            .expect("unisolated operation"),
                     }
-                })
-                .await;
-                assert!(inherited, "mode {mode} lost resource ownership");
-                assert!(original_policy, "mode {mode} changed the detached worker's disk policy");
-                assert_eq!(held, vec![1; physical_count], "mode {mode} released a live worker's unit");
-            }
+                }),
+            ));
+            let (inherited, original_policy) = deadline(started_rx).await.expect("owned work starts");
+            task.abort();
+            assert!(task.await.expect_err("waiter cancelled").is_cancelled());
+            let held = gate.snapshot().active;
+            release_tx.send(()).expect("owned work survives cancellation");
+            deadline(async {
+                while gate.snapshot().active != 0 {
+                    tokio::task::yield_now().await;
+                }
+            })
+            .await;
+            assert!(inherited, "mode {mode} lost resource ownership");
+            assert!(original_policy, "mode {mode} changed the detached worker's disk policy");
+            assert_eq!(held, 1, "mode {mode} released a live worker's unit");
         }
     }
     fn config(pending: usize, workers: usize, blocking_threads: usize) -> Config {

crates/ecstore/src/disk/fd_cache_tests.rs

@@ -5,7 +5,6 @@ use super::{FdCache, FdCacheEntry, FdKey};
 use std::fs::File;
 use std::os::unix::fs::FileExt;
 use std::sync::Arc;
-use std::sync::atomic::AtomicBool;
 
 fn key(volume: &str, path: &str, direct: bool) -> FdKey {
     FdKey {
@@ -53,11 +52,7 @@ async fn uring_fd_cache_exact_invalidation_removes_both_modes_and_preserves_othe
 async fn uring_fd_cache_exact_invalidation_bumps_one_generation_and_rejects_old_epoch_inserts() {
     let (_directory, file) = fixture();
     let cache = FdCache::new();
-    let entry = Arc::new(FdCacheEntry {
-        file,
-        len: 3,
-        invalidated: AtomicBool::new(false),
-    });
+    let entry = Arc::new(FdCacheEntry { file, len: 3 });
     let old_generation = cache.generation();
     cache.invalidate_exact("v", "part").await;
     let current_generation = cache.generation();
@@ -130,7 +125,7 @@ async fn uring_fd_cache_volume_and_clear_invalidation_cover_both_modes() {
         cache.insert(key("v", "part", direct), Arc::clone(&file)).await;
         assert!(
             cache.get(&key("v", "part", direct)).await.is_some(),
-            "new entries must survive the earlier volume invalidation"
+            "new entries must survive the earlier volume predicate"
         );
     }
     cache.clear();
@@ -169,7 +164,6 @@ async fn uring_fd_cache_invalidation_keeps_borrowed_old_inode_alive_and_allows_r
     let replacement = Arc::new(FdCacheEntry {
         file: Arc::new(File::open(directory.path().join("part")).expect("open replacement inode")),
         len: 11,
-        invalidated: AtomicBool::new(false),
     });
     for direct in [false, true] {
         let key = key("v", "part", direct);

crates/ecstore/src/disk/fs.rs

@@ -16,15 +16,40 @@ use std::{
     collections::HashMap,
     fs::Metadata,
     path::{Path, PathBuf},
-    sync::Mutex,
+    sync::{Arc, Mutex, OnceLock},
     time::{Duration, Instant},
 };
-use tokio::{fs::File, io};
+use tokio::{
+    fs::{self, File},
+    io,
+};
 
-async fn native_io<T: Send + 'static>(operation: impl FnOnce() -> io::Result<T> + Send + 'static) -> io::Result<T> {
-    super::io_admission::spawn_blocking_with_resource_ownership(operation)
-        .await
-        .map_err(|_| io::Error::other("background task failed"))?
+static READONLY_OPTIONS: OnceLock<Arc<fs::OpenOptions>> = OnceLock::new();
+static WRITEONLY_OPTIONS: OnceLock<Arc<fs::OpenOptions>> = OnceLock::new();
+static READWRITE_OPTIONS: OnceLock<Arc<fs::OpenOptions>> = OnceLock::new();
+
+fn get_readonly_options() -> &'static Arc<fs::OpenOptions> {
+    READONLY_OPTIONS.get_or_init(|| {
+        let mut opts = fs::OpenOptions::new();
+        opts.read(true);
+        Arc::new(opts)
+    })
+}
+
+fn get_writeonly_options() -> &'static Arc<fs::OpenOptions> {
+    WRITEONLY_OPTIONS.get_or_init(|| {
+        let mut opts = fs::OpenOptions::new();
+        opts.write(true);
+        Arc::new(opts)
+    })
+}
+
+fn get_readwrite_options() -> &'static Arc<fs::OpenOptions> {
+    READWRITE_OPTIONS.get_or_init(|| {
+        let mut opts = fs::OpenOptions::new();
+        opts.read(true).write(true);
+        Arc::new(opts)
+    })
 }
 
 #[cfg(not(windows))]
@@ -92,32 +117,33 @@ pub const O_APPEND: FileMode = 0x00400;
 //     create_new: bool,
 
 pub async fn open_file(path: impl AsRef<Path>, mode: FileMode) -> io::Result<File> {
-    let path = path.as_ref().to_path_buf();
-    native_io(move || {
-        let mut options = std::fs::OpenOptions::new();
-        match mode & (O_RDONLY | O_WRONLY | O_RDWR) {
-            O_WRONLY => options.write(true),
-            O_RDWR => options.read(true).write(true),
-            _ => options.read(true),
+    let base_opts = match mode & (O_RDONLY | O_WRONLY | O_RDWR) {
+        O_RDONLY => get_readonly_options(),
+        O_WRONLY => get_writeonly_options(),
+        O_RDWR => get_readwrite_options(),
+        _ => get_readonly_options(),
+    };
+
+    if (mode & (O_CREATE | O_APPEND | O_TRUNC)) != 0 {
+        let mut opts = (**base_opts).clone();
+        if mode & O_CREATE != 0 {
+            opts.create(true);
         }
-        .create(mode & O_CREATE != 0)
-        .append(mode & O_APPEND != 0)
-        .truncate(mode & O_TRUNC != 0);
-        #[cfg(all(any(test, feature = "test-util"), not(windows)))]
-        if mode == O_RDONLY {
-            super::os::prepared_publication_test_hooks::run(
-                super::os::prepared_publication_test_hooks::Stage::NativeReadOpen,
-                &path,
-            );
+        if mode & O_APPEND != 0 {
+            opts.append(true);
         }
-        options.open(path).map(File::from_std)
-    })
-    .await
+        if mode & O_TRUNC != 0 {
+            opts.truncate(true);
+        }
+        opts.open(path.as_ref()).await
+    } else {
+        base_opts.open(path.as_ref()).await
+    }
 }
 
 pub async fn access(path: impl AsRef<Path>) -> io::Result<()> {
-    let path = path.as_ref().to_path_buf();
-    native_io(move || std::fs::metadata(path).map(|_| ())).await
+    fs::metadata(path).await?;
+    Ok(())
 }
 
 pub fn access_std(path: impl AsRef<Path>) -> io::Result<()> {
@@ -126,8 +152,7 @@ pub fn access_std(path: impl AsRef<Path>) -> io::Result<()> {
 }
 
 pub async fn lstat(path: impl AsRef<Path>) -> io::Result<Metadata> {
-    let path = path.as_ref().to_path_buf();
-    native_io(move || std::fs::symlink_metadata(path)).await
+    fs::symlink_metadata(path).await
 }
 
 pub fn lstat_std(path: impl AsRef<Path>) -> io::Result<Metadata> {
@@ -145,7 +170,7 @@ pub fn create_dir_all_std(path: &Path) -> io::Result<()> {
 
 pub async fn make_dir_all(path: impl AsRef<Path>) -> io::Result<()> {
     let path = path.as_ref().to_path_buf();
-    native_io(move || create_dir_all_std(&path)).await
+    tokio::task::spawn_blocking(move || create_dir_all_std(&path)).await?
 }
 
 fn is_dir_error(e: &io::Error) -> bool {
@@ -158,13 +183,9 @@ fn is_dir_error(e: &io::Error) -> bool {
 #[tracing::instrument(level = "debug", skip_all)]
 pub async fn remove(path: impl AsRef<Path>) -> io::Result<()> {
     // Try remove_file first; fall back to remove_dir if it's a directory
-    let file_path = path.as_ref().to_path_buf();
-    match native_io(move || std::fs::remove_file(file_path)).await {
+    match fs::remove_file(path.as_ref()).await {
         Ok(()) => Ok(()),
-        Err(e) if is_dir_error(&e) => {
-            let path = path.as_ref().to_path_buf();
-            native_io(move || std::fs::remove_dir(path)).await
-        }
+        Err(e) if is_dir_error(&e) => fs::remove_dir(path.as_ref()).await,
         Err(e) => Err(e),
     }
 }
@@ -172,13 +193,9 @@ pub async fn remove(path: impl AsRef<Path>) -> io::Result<()> {
 #[allow(dead_code, reason = "asserted by this file's tests (backlog#1823)")]
 pub async fn remove_all(path: impl AsRef<Path>) -> io::Result<()> {
     // Try remove_file first; fall back to remove_dir_all if it's a directory
-    let file_path = path.as_ref().to_path_buf();
-    match native_io(move || std::fs::remove_file(file_path)).await {
+    match fs::remove_file(path.as_ref()).await {
         Ok(()) => Ok(()),
-        Err(e) if is_dir_error(&e) => {
-            let path = path.as_ref().to_path_buf();
-            native_io(move || std::fs::remove_dir_all(path)).await
-        }
+        Err(e) if is_dir_error(&e) => fs::remove_dir_all(path.as_ref()).await,
         Err(e) => Err(e),
     }
 }
@@ -205,14 +222,11 @@ pub fn remove_all_std(path: impl AsRef<Path>) -> io::Result<()> {
 
 #[cfg(test)]
 pub async fn mkdir(path: impl AsRef<Path>) -> io::Result<()> {
-    let path = path.as_ref().to_path_buf();
-    native_io(move || std::fs::create_dir(path)).await
+    fs::create_dir(path.as_ref()).await
 }
 
 pub async fn rename(from: impl AsRef<Path>, to: impl AsRef<Path>) -> io::Result<()> {
-    let from = from.as_ref().to_path_buf();
-    let to = to.as_ref().to_path_buf();
-    native_io(move || std::fs::rename(from, to)).await
+    fs::rename(from, to).await
 }
 
 #[cfg(any(not(windows), test))]
@@ -275,7 +289,7 @@ pub async fn cached_access(path: impl AsRef<Path>) -> io::Result<()> {
     }
 
     let path_buf = path.to_path_buf();
-    let result = access(&path_buf).await;
+    let result = fs::metadata(&path_buf).await;
 
     match &result {
         Ok(_) => BUCKET_EXISTENCE_CACHE.record(path_buf, true),
@@ -290,7 +304,6 @@ pub async fn cached_access(path: impl AsRef<Path>) -> io::Result<()> {
 }
 
 pub fn invalidate_bucket_cache(path: impl AsRef<Path>) {
-    crate::bucket::metadata_sys::bump_local_meta_mutation_gen();
     BUCKET_EXISTENCE_CACHE.invalidate(path.as_ref());
 }
 
@@ -300,89 +313,6 @@ mod tests {
     use tempfile::TempDir;
     use tokio::io::AsyncWriteExt;
 
-    #[test]
-    fn cancelled_filesystem_jobs_retain_physical_resources() {
-        use crate::disk::io_admission::{test_resource_units, with_optional_resource_unit};
-
-        let runtime = tokio::runtime::Builder::new_current_thread()
-            .enable_all()
-            .max_blocking_threads(1)
-            .build()
-            .expect("single native worker");
-        runtime.block_on(async {
-            let mut observations = Vec::new();
-            for count in 1..=2 {
-                for operation in [
-                    "access",
-                    "cached_access",
-                    "lstat",
-                    "mkdir",
-                    "make_dir_all",
-                    "remove",
-                    "remove_all",
-                    "rename",
-                    "open",
-                ] {
-                    let dir = TempDir::new().expect("filesystem ownership fixture");
-                    let source = dir.path().join("source");
-                    let target = dir.path().join("target");
-                    match operation {
-                        "mkdir" | "make_dir_all" | "open" => {}
-                        "remove_all" => {
-                            std::fs::create_dir(&source).expect("recursive removal directory");
-                            std::fs::write(source.join("child"), b"payload").expect("recursive removal child");
-                        }
-                        _ => std::fs::write(&source, b"payload").expect("existing file"),
-                    }
-                    let (resources, gates) = test_resource_units(count);
-                    let (started_tx, started_rx) = tokio::sync::oneshot::channel();
-                    let (release_tx, release_rx) = std::sync::mpsc::channel();
-                    let blocker = tokio::task::spawn_blocking(move || {
-                        let _ = started_tx.send(());
-                        let _ = release_rx.recv();
-                    });
-                    started_rx.await.expect("native worker occupied");
-                    let mut future = Box::pin(with_optional_resource_unit(Some(resources), async {
-                        match operation {
-                            "access" => access(&source).await,
-                            "cached_access" => cached_access(&source).await,
-                            "lstat" => lstat(&source).await.map(|_| ()),
-                            "mkdir" => mkdir(&source).await,
-                            "make_dir_all" => make_dir_all(source.join("child")).await,
-                            "remove" => remove(&source).await,
-                            "remove_all" => remove_all(&source).await,
-                            "rename" => rename(&source, &target).await,
-                            "open" => open_file(&source, O_CREATE | O_WRONLY).await.map(|_| ()),
-                            _ => unreachable!("fixed operation list"),
-                        }
-                    }));
-                    assert!(futures::poll!(&mut future).is_pending(), "{operation}: native job queued");
-                    drop(future);
-                    let held: Vec<_> = gates.iter().map(|gate| gate.snapshot().active).collect();
-                    release_tx.send(()).expect("release native worker before assertions");
-                    blocker.await.expect("native blocker completed");
-                    tokio::task::spawn_blocking(|| ()).await.expect("native queue drained");
-                    assert!(gates.iter().all(|gate| gate.snapshot().active == 0));
-                    match operation {
-                        "mkdir" => assert!(source.is_dir()),
-                        "make_dir_all" => assert!(source.join("child").is_dir()),
-                        "open" => assert!(source.is_file()),
-                        "remove" => assert!(!source.exists()),
-                        "rename" => {
-                            assert!(!source.exists());
-                            assert_eq!(std::fs::read(&target).expect("renamed file"), b"payload");
-                        }
-                        _ => {}
-                    }
-                    observations.push((count, operation, held));
-                }
-            }
-            for (count, operation, held) in observations {
-                assert_eq!(held, vec![1; count], "{operation}: queued native job keeps its physical resources");
-            }
-        });
-    }
-
     #[tokio::test]
     async fn test_file_mode_constants() {
         assert_eq!(O_RDONLY, 0x00000);

crates/ecstore/src/disk/io_admission.rs

@@ -14,18 +14,6 @@
 
 //! Per-local-disk foreground-priority admission for scanner I/O.
 
-pub(crate) mod memory;
-mod physical_identity;
-mod physical_owners;
-mod physical_sampler;
-
-pub use memory::BackgroundMemoryBudget;
-
-pub(crate) use physical_sampler::PhysicalHealBinding;
-pub use physical_sampler::{
-    PhysicalDiskBinding, PhysicalDiskPlan, PhysicalDiskSample, PhysicalDiskSampler, PhysicalResourcePlan,
-};
-
 use std::collections::VecDeque;
 use std::future::Future;
 use std::io;
@@ -37,118 +25,18 @@ use std::time::Duration;
 
 use metrics::{counter, gauge, histogram};
 use rustfs_concurrency::adaptive::AdaptivePermit;
-use rustfs_concurrency::adaptive::permit_set::AdaptivePermitSet;
 use rustfs_rio::ChunkReader;
 use tokio::io::{AsyncRead, ReadBuf};
 use tokio::sync::Notify;
 use tokio::time::Instant;
 use tokio_util::sync::CancellationToken;
 
-pub(crate) mod remote;
-pub use remote::{RemoteBackgroundIo, with_remote_background_io};
-
 const BACKGROUND_FOREGROUND_BURST: u32 = 8;
 const BACKGROUND_MAX_WAIT: Duration = Duration::from_millis(100);
 
 tokio::task_local! {
     static DISK_IO_CONTEXT: DiskIoContext;
-    static RESOURCE_IO_UNIT: ResourceIoUnit;
-}
-
-/// Native I/O retains the physical subset selected before storage work. A
-/// layered disk may touch several leaves; unrelated devices stay outside it.
-#[derive(Clone, Debug)]
-pub(crate) struct ResourceIoUnit {
-    permits: ResourceIoPermits,
-    memory_budget: Option<Arc<BackgroundMemoryBudget>>,
-    #[cfg(target_os = "linux")]
-    _mount_lease: Option<Arc<std::fs::File>>,
-}
-
-#[derive(Debug)]
-enum ResourceIoPermits {
-    Single(AdaptivePermit),
-    Set(AdaptivePermitSet),
-}
-
-impl Clone for ResourceIoPermits {
-    fn clone(&self) -> Self {
-        match self {
-            Self::Single(permit) => Self::Single(permit.clone()),
-            Self::Set(permits) => Self::Set(permits.clone()),
-        }
-    }
-}
-
-impl From<AdaptivePermit> for ResourceIoUnit {
-    fn from(permit: AdaptivePermit) -> Self {
-        Self {
-            permits: ResourceIoPermits::Single(permit),
-            memory_budget: BackgroundMemoryBudget::current(),
-            #[cfg(target_os = "linux")]
-            _mount_lease: None,
-        }
-    }
-}
-
-impl From<AdaptivePermitSet> for ResourceIoUnit {
-    fn from(permits: AdaptivePermitSet) -> Self {
-        Self {
-            permits: ResourceIoPermits::Set(permits),
-            memory_budget: BackgroundMemoryBudget::current(),
-            #[cfg(target_os = "linux")]
-            _mount_lease: None,
-        }
-    }
-}
-
-impl ResourceIoUnit {
-    pub(crate) fn memory_budget(&self) -> Option<Arc<BackgroundMemoryBudget>> {
-        self.memory_budget.clone()
-    }
-
-    pub(crate) fn with_permits(mut self, permits: AdaptivePermitSet) -> Self {
-        self.permits = ResourceIoPermits::Set(permits);
-        self
-    }
-
-    #[cfg(test)]
-    pub(crate) fn with_memory_budget(mut self, budget: Arc<BackgroundMemoryBudget>) -> Self {
-        self.memory_budget = Some(budget);
-        self
-    }
-
-    pub(crate) fn as_set(&self) -> Option<&AdaptivePermitSet> {
-        match &self.permits {
-            ResourceIoPermits::Single(_) => None,
-            ResourceIoPermits::Set(permits) => Some(permits),
-        }
-    }
-
-    #[cfg(target_os = "linux")]
-    pub(crate) fn with_mount_lease(mut self, mount_lease: Arc<std::fs::File>) -> Self {
-        // The selected disk's proc-fd paths must survive native jobs after its
-        // async wrapper retires. Clones carry the same pinned mount generation.
-        self._mount_lease = Some(mount_lease);
-        self
-    }
-}
-
-#[cfg(test)]
-pub(crate) fn test_resource_units(count: usize) -> (ResourceIoUnit, Vec<Arc<rustfs_concurrency::adaptive::AdaptiveAdmission>>) {
-    use rustfs_concurrency::adaptive::{AdaptiveAdmission, permit_set::AdaptivePermitSetOwner};
-    use std::num::NonZeroU16;
-
-    assert!((1..=2).contains(&count), "test single and layered disks");
-    let gates: Vec<_> = (0..count).map(|_| AdaptiveAdmission::new(NonZeroU16::MIN, 1)).collect();
-    let mut admitted: Vec<_> = gates.iter().map(|gate| gate.try_acquire().expect("test resource")).collect();
-    let unit = if count == 1 {
-        ResourceIoUnit::from(admitted.pop().expect("single resource"))
-    } else {
-        let owner = AdaptivePermitSetOwner::new(NonZeroU16::MIN, gates.clone()).expect("layered resource");
-        ResourceIoUnit::from(owner.capture(&admitted.iter().collect::<Vec<_>>()).expect("admitted subset"))
-    };
-    (unit, gates)
+    static RESOURCE_IO_UNIT: AdaptivePermit;
 }
 
 #[derive(Clone, Copy, Debug, Eq, PartialEq)]
@@ -163,7 +51,7 @@ pub(crate) struct DiskIoContext {
     pub(crate) cancellation: CancellationToken,
     pub(crate) admission: Option<Arc<DiskIoAdmission>>,
     pub(crate) permit: Option<DiskIoPermit>,
-    pub(crate) resource_unit: Option<ResourceIoUnit>,
+    pub(crate) resource_unit: Option<AdaptivePermit>,
 }
 
 /// Mark disk I/O issued by `future` as background work for local-disk admission.
@@ -190,46 +78,24 @@ pub async fn with_background_disk_io<F: Future>(cancellation: CancellationToken,
 /// of a stalled native operation. Escaping buffers need their own memory leases.
 #[doc(hidden)]
 pub async fn with_background_resource_unit<F: Future>(unit: AdaptivePermit, future: F) -> F::Output {
-    RESOURCE_IO_UNIT.scope(ResourceIoUnit::from(unit), future).await
+    RESOURCE_IO_UNIT.scope(unit, future).await
 }
 
-/// Retain only the previously admitted physical leaves touched by this I/O.
-/// Projection of owned units never waits and may run under storage locks.
-/// Acquire the planned resources before locking; auxiliary leaves discovered
-/// later must use nonblocking admission. Do not pass unrelated parent resources
-/// to a native job that touches only some of its disks.
-#[doc(hidden)]
-pub async fn with_background_resource_set<F: Future>(units: AdaptivePermitSet, future: F) -> F::Output {
-    RESOURCE_IO_UNIT.scope(ResourceIoUnit::from(units), future).await
-}
-
-pub(crate) fn current_resource_unit() -> Option<ResourceIoUnit> {
-    RESOURCE_IO_UNIT
-        .try_with(Clone::clone)
-        .ok()
-        .or_else(|| {
-            DISK_IO_CONTEXT
-                .try_with(|context| context.resource_unit.clone())
-                .ok()
-                .flatten()
-        })
-        .or_else(remote::resources)
-}
-
-pub(crate) fn has_resource_io_scope() -> bool {
-    RESOURCE_IO_UNIT.try_with(|_| ()).is_ok()
-        || DISK_IO_CONTEXT
-            .try_with(|context| context.resource_unit.is_some())
-            .unwrap_or(false)
-        || remote::active()
+pub(crate) fn current_resource_unit() -> Option<AdaptivePermit> {
+    RESOURCE_IO_UNIT.try_with(Clone::clone).ok().or_else(|| {
+        DISK_IO_CONTEXT
+            .try_with(|context| context.resource_unit.clone())
+            .ok()
+            .flatten()
+    })
 }
 
 /// Transfer only resource ownership into an existing spawned task. Disk
 /// classification/permits are not inherited: changing those can introduce a
 /// wait behind a disk permit still held by the parent.
-pub(crate) async fn with_optional_resource_unit<F: Future>(unit: Option<ResourceIoUnit>, future: F) -> F::Output {
+pub(crate) async fn with_optional_resource_unit<F: Future>(unit: Option<AdaptivePermit>, future: F) -> F::Output {
     match unit {
-        Some(unit) => RESOURCE_IO_UNIT.scope(unit, future).await,
+        Some(unit) => with_background_resource_unit(unit, future).await,
         None => future.await,
     }
 }
@@ -367,7 +233,7 @@ impl DiskIoAdmission {
         self.foreground_with_resource(current_resource_unit())
     }
 
-    fn foreground_with_resource(self: &Arc<Self>, resource_unit: Option<ResourceIoUnit>) -> DiskIoPermit {
+    fn foreground_with_resource(self: &Arc<Self>, resource_unit: Option<AdaptivePermit>) -> DiskIoPermit {
         self.foreground_active.fetch_add(1, Ordering::AcqRel);
         if self.background_waiters.load(Ordering::Acquire) > 0 {
             self.record_state();
@@ -388,7 +254,7 @@ impl DiskIoAdmission {
     async fn background_with_resource(
         self: &Arc<Self>,
         cancellation: &CancellationToken,
-        resource_unit: Option<ResourceIoUnit>,
+        resource_unit: Option<AdaptivePermit>,
     ) -> std::io::Result<DiskIoPermit> {
         let started_at = Instant::now();
         let ticket = {
@@ -563,7 +429,7 @@ impl DiskIoPermit {
 struct DiskIoPermitLease {
     admission: Arc<DiskIoAdmission>,
     class: DiskIoClass,
-    resource_unit: Option<ResourceIoUnit>,
+    resource_unit: Option<AdaptivePermit>,
 }
 
 pub(crate) fn spawn_blocking_with_disk_io_permit<T, F>(
@@ -584,18 +450,6 @@ where
     })
 }
 
-/// Run native filesystem work with the current resource ownership. Cancelling
-/// the async waiter cannot refund a unit while the native operation still runs.
-/// This does not acquire capacity or change foreground/background policy.
-#[doc(hidden)]
-pub fn spawn_blocking_with_resource_ownership<T, F>(operation: F) -> tokio::task::JoinHandle<T>
-where
-    T: Send + 'static,
-    F: FnOnce() -> T + Send + 'static,
-{
-    spawn_blocking_with_disk_io_permit(None, operation)
-}
-
 type AdmissionWait = Pin<Box<dyn Future<Output = io::Result<DiskIoPermit>> + Send>>;
 
 impl Drop for DiskIoPermitLease {
@@ -741,63 +595,6 @@ mod tests {
     use std::num::NonZeroU16;
     use tokio::io::{AsyncReadExt, AsyncWriteExt};
 
-    #[tokio::test]
-    async fn physical_subset_survives_native_cancellation_without_retaining_unrelated_disks() {
-        use rustfs_concurrency::adaptive::permit_set::AdaptivePermitSetOwner;
-
-        for disk_permit in [false, true] {
-            let maximum = NonZeroU16::new(1).expect("one physical unit");
-            let first = AdaptiveAdmission::new(maximum, 1);
-            let second = AdaptiveAdmission::new(maximum, 1);
-            let unrelated = AdaptiveAdmission::new(maximum, 1);
-            let owner = AdaptivePermitSetOwner::new(maximum, vec![first.clone(), second.clone()]).expect("layered disk");
-            let a = first.try_acquire().expect("first backing device");
-            let b = second.try_acquire().expect("second backing device");
-            let healthy = unrelated.try_acquire().expect("another disk in the parent operation");
-            let subset = owner.capture(&[&a, &b]).expect("capture before storage work");
-            drop((a, b, owner));
-            let disk = DiskIoAdmission::new("physical-subset-native");
-            let (started_tx, started_rx) = tokio::sync::oneshot::channel();
-            let (release_tx, release_rx) = tokio::sync::oneshot::channel();
-            let task = tokio::spawn(async move {
-                let _healthy = healthy;
-                with_background_resource_set(subset, async {
-                    let permit = if disk_permit {
-                        Some(disk.background(&CancellationToken::new()).await.expect("logical disk permit"))
-                    } else {
-                        None
-                    };
-                    spawn_blocking_with_disk_io_permit(permit, move || {
-                        started_tx.send(()).expect("native I/O started");
-                        release_rx.blocking_recv().expect("release native I/O");
-                    })
-                    .await
-                    .expect("native I/O completed");
-                })
-                .await;
-            });
-            started_rx.await.expect("native worker retains subset");
-            task.abort();
-            assert!(task.await.expect_err("cancel async waiter").is_cancelled());
-            let active = [first.snapshot().active, second.snapshot().active, unrelated.snapshot().active];
-            let healthy_available = unrelated.try_acquire().is_some();
-            first.set_limit(0);
-            second.set_limit(0);
-            release_tx.send(()).expect("finish native work");
-            tokio::time::timeout(Duration::from_secs(5), async {
-                while first.snapshot().active != 0 || second.snapshot().active != 0 {
-                    tokio::task::yield_now().await;
-                }
-            })
-            .await
-            .expect("both backing devices are returned after native completion");
-            assert_eq!(active, [1, 1, 0], "only the native I/O's physical subset remains charged");
-            assert!(healthy_available, "cancellation frees the independent disk immediately");
-            assert!(first.try_acquire().is_none());
-            assert!(second.try_acquire().is_none(), "old completions cannot reopen shrunken owners");
-        }
-    }
-
     #[tokio::test]
     async fn resource_unit_outlives_cancelled_scope_until_native_io_finishes() {
         for permit_mode in 0..4 {

crates/ecstore/src/disk/io_admission/memory.rs

@@ -1,547 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use bytes::Bytes;
-use std::io;
-use std::sync::{Arc, Mutex, OnceLock};
-use std::time::Duration;
-use tokio::time::Instant;
-
-static BACKGROUND_MEMORY: OnceLock<Arc<BackgroundMemoryBudget>> = OnceLock::new();
-
-/// Process-wide payload storage retained by admitted background I/O. The
-/// existing resource sampler publishes limits; this owner starts no workers.
-#[derive(Debug)]
-pub struct BackgroundMemoryBudget {
-    // This short critical section only changes counters and a deadline. It
-    // never allocates, calls storage, or acquires another lock while held.
-    state: Mutex<State>,
-}
-
-#[derive(Debug)]
-struct State {
-    limit: u64,
-    used: u64,
-    valid_until: Instant,
-}
-
-/// A coherent view of the leased cap and retained payload storage.
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
-pub struct BackgroundMemorySnapshot {
-    /// Zero when the latest resource observation has expired.
-    pub limit: u64,
-    /// Existing storage remains charged even after the cap shrinks below it.
-    pub used: u64,
-}
-
-impl BackgroundMemoryBudget {
-    /// Start closed until the existing resource sampler publishes a limit.
-    pub fn new() -> Arc<Self> {
-        Arc::new(Self {
-            state: Mutex::new(State {
-                limit: 0,
-                used: 0,
-                valid_until: Instant::now(),
-            }),
-        })
-    }
-
-    /// Install the sole process owner before starting adaptive background work.
-    /// Returns false if an owner was already installed.
-    pub fn install(self: &Arc<Self>) -> bool {
-        BACKGROUND_MEMORY.set(self.clone()).is_ok()
-    }
-
-    /// Return only the installed process memory policy; no node or disk ownership.
-    /// No policy is installed in the default, non-adaptive startup path.
-    pub fn current() -> Option<Arc<Self>> {
-        BACKGROUND_MEMORY.get().cloned()
-    }
-
-    /// Update admission without revoking storage retained by native tasks or
-    /// readers. Missing observations must publish zero capacity.
-    pub fn set_sampled_limit(&self, limit: u64, valid_for: Duration) {
-        let mut state = self.state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-        state.limit = limit;
-        let now = Instant::now();
-        state.valid_until = now.checked_add(valid_for).unwrap_or(now);
-    }
-
-    /// Read the cap and retained byte count under the same short lock.
-    pub fn snapshot(&self) -> BackgroundMemorySnapshot {
-        let state = self.state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-        BackgroundMemorySnapshot {
-            limit: if Instant::now() < state.valid_until { state.limit } else { 0 },
-            used: state.used,
-        }
-    }
-
-    pub(crate) fn reserve(self: &Arc<Self>, bytes: usize) -> io::Result<Reservation> {
-        let bytes = u64::try_from(bytes).map_err(|_| io::Error::from(io::ErrorKind::OutOfMemory))?;
-        let mut state = self.state.lock().unwrap_or_else(std::sync::PoisonError::into_inner);
-        let used = state
-            .used
-            .checked_add(bytes)
-            .ok_or_else(|| io::Error::new(io::ErrorKind::WouldBlock, BackgroundMemoryExhausted))?;
-        if bytes != 0 && (Instant::now() >= state.valid_until || used > state.limit) {
-            return Err(io::Error::new(io::ErrorKind::WouldBlock, BackgroundMemoryExhausted));
-        }
-        state.used = used;
-        Ok(Reservation {
-            owner: self.clone(),
-            bytes,
-        })
-    }
-}
-
-#[derive(Debug)]
-struct BackgroundMemoryExhausted;
-
-impl std::fmt::Display for BackgroundMemoryExhausted {
-    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        formatter.write_str("background buffer memory budget exhausted")
-    }
-}
-
-impl std::error::Error for BackgroundMemoryExhausted {}
-
-pub(crate) fn is_memory_pressure(error: &io::Error) -> bool {
-    error.kind() == io::ErrorKind::OutOfMemory || error.get_ref().is_some_and(|inner| inner.is::<BackgroundMemoryExhausted>())
-}
-
-pub(crate) struct Reservation {
-    owner: Arc<BackgroundMemoryBudget>,
-    bytes: u64,
-}
-
-impl Reservation {
-    pub(crate) fn belongs_to(&self, budget: &Arc<BackgroundMemoryBudget>) -> bool {
-        Arc::ptr_eq(&self.owner, budget)
-    }
-
-    pub(crate) fn wrap(bytes: Bytes, reservation: Option<Self>) -> Bytes {
-        if bytes.is_empty() {
-            drop(bytes);
-            drop(reservation);
-            return Bytes::new();
-        }
-        match reservation {
-            Some(reservation) => Bytes::from_owner(BackgroundBytes {
-                bytes,
-                _reservation: reservation,
-            }),
-            None => bytes,
-        }
-    }
-}
-
-struct BackgroundBytes {
-    // Free the payload before refunding it, including after the last slice.
-    bytes: Bytes,
-    _reservation: Reservation,
-}
-
-impl AsRef<[u8]> for BackgroundBytes {
-    fn as_ref(&self) -> &[u8] {
-        &self.bytes
-    }
-}
-
-impl Drop for Reservation {
-    fn drop(&mut self) {
-        self.owner
-            .state
-            .lock()
-            .unwrap_or_else(std::sync::PoisonError::into_inner)
-            .used -= self.bytes;
-    }
-}
-
-/// Reusable initialized payload storage. The reservation is embedded in the
-/// existing native job state, with no per-read owner allocation or payload copy.
-pub(crate) struct BackgroundBuffer {
-    // Field order releases the allocation before refunding its reservation.
-    bytes: Box<[u8]>,
-    reservation: Option<Reservation>,
-    budget: Option<Arc<BackgroundMemoryBudget>>,
-}
-
-impl BackgroundBuffer {
-    pub(crate) fn new(budget: Option<Arc<BackgroundMemoryBudget>>) -> Self {
-        Self {
-            bytes: Box::default(),
-            reservation: None,
-            budget,
-        }
-    }
-
-    /// Call only after the previous contents have been consumed. Growth charges
-    /// both allocations until the old buffer is freed, including after shrink.
-    pub(crate) fn ensure_len(&mut self, length: usize) -> io::Result<()> {
-        self.grow(length, 0)
-    }
-
-    /// Preserve an initialized prefix when replacing storage. Callers keep
-    /// `preserve` within both the existing allocation and the requested length.
-    pub(crate) fn grow(&mut self, length: usize, preserve: usize) -> io::Result<()> {
-        if self.bytes.len() >= length {
-            return Ok(());
-        }
-        let reservation = self.budget.as_ref().map(|budget| budget.reserve(length)).transpose()?;
-        let mut bytes = Vec::new();
-        bytes
-            .try_reserve_exact(length)
-            .map_err(|_| io::Error::from(io::ErrorKind::OutOfMemory))?;
-        bytes.resize(length, 0);
-        bytes[..preserve].copy_from_slice(&self.bytes[..preserve]);
-        self.bytes = bytes.into_boxed_slice();
-        self.reservation = reservation;
-        Ok(())
-    }
-
-    /// Metadata is only a size hint: concurrent growth still reads through EOF.
-    /// Every replacement is charged before copying the retained prefix.
-    pub(crate) fn read_to_end(mut self, reader: &mut impl io::Read, hint: usize) -> io::Result<Bytes> {
-        self.ensure_len(hint)?;
-        let mut filled = 0;
-        loop {
-            if filled == self.bytes.len() {
-                // Probe EOF without forcing a larger allocation for an exact fit.
-                let mut probe = [0];
-                match reader.read(&mut probe) {
-                    Ok(0) => break,
-                    Ok(_) => {
-                        let length = self.bytes.len().checked_mul(2).ok_or(io::ErrorKind::OutOfMemory)?.max(32);
-                        self.grow(length, filled)?;
-                        self.bytes[filled] = probe[0];
-                        filled += 1;
-                    }
-                    Err(error) if error.kind() == io::ErrorKind::Interrupted => continue,
-                    Err(error) => return Err(error),
-                }
-            }
-            match reader.read(&mut self.bytes[filled..]) {
-                Ok(0) => break,
-                Ok(length) => filled += length,
-                Err(error) if error.kind() == io::ErrorKind::Interrupted => continue,
-                Err(error) => return Err(error),
-            }
-        }
-        Ok(self.take_bytes(filled))
-    }
-
-    pub(crate) fn take_bytes(&mut self, length: usize) -> Bytes {
-        let bytes = std::mem::take(&mut self.bytes);
-        let reservation = self.reservation.take();
-        let mut bytes = Bytes::from(bytes.into_vec());
-        bytes.truncate(length);
-        Reservation::wrap(bytes, reservation)
-    }
-
-    pub(crate) fn memory_budget(&self) -> Option<Arc<BackgroundMemoryBudget>> {
-        self.budget.clone()
-    }
-
-    pub(crate) fn as_mut_slice(&mut self) -> &mut [u8] {
-        &mut self.bytes
-    }
-
-    pub(crate) fn as_slice(&self) -> &[u8] {
-        &self.bytes
-    }
-}
-
-/// Bounded encoded-frame storage for serializer output and raw read staging.
-/// Both paths reserve the actual allocation before initializing its bytes.
-pub struct BackgroundEncodeBuffer {
-    buffer: BackgroundBuffer,
-    filled: usize,
-    maximum: usize,
-}
-
-impl BackgroundEncodeBuffer {
-    pub fn new(memory: Arc<BackgroundMemoryBudget>, maximum: usize) -> Self {
-        Self {
-            buffer: BackgroundBuffer::new(Some(memory)),
-            filled: 0,
-            maximum,
-        }
-    }
-
-    /// Borrow initialized raw-frame staging; decode only after a successful read.
-    /// Staging is not encoded output: `into_bytes` remains empty for this path.
-    pub fn prepare_read(&mut self, length: usize) -> io::Result<&mut [u8]> {
-        if length > self.maximum {
-            return Err(io::Error::new(
-                io::ErrorKind::InvalidData,
-                "background encoded frame exceeds its size limit",
-            ));
-        }
-        self.buffer.ensure_len(length)?;
-        self.filled = 0;
-        Ok(&mut self.buffer.as_mut_slice()[..length])
-    }
-
-    pub fn into_bytes(mut self) -> Bytes {
-        self.buffer.take_bytes(self.filled)
-    }
-}
-
-impl io::Write for BackgroundEncodeBuffer {
-    fn write(&mut self, bytes: &[u8]) -> io::Result<usize> {
-        let required = self.filled.checked_add(bytes.len()).ok_or(io::ErrorKind::OutOfMemory)?;
-        if required > self.maximum {
-            return Err(io::Error::new(
-                io::ErrorKind::InvalidData,
-                "background encoded frame exceeds its size limit",
-            ));
-        }
-        if required > self.buffer.as_slice().len() {
-            let capacity = self
-                .buffer
-                .as_slice()
-                .len()
-                .saturating_mul(2)
-                .max(32)
-                .max(required)
-                .min(self.maximum);
-            self.buffer.grow(capacity, self.filled)?;
-        }
-        self.buffer.as_mut_slice()[self.filled..required].copy_from_slice(bytes);
-        self.filled = required;
-        Ok(bytes.len())
-    }
-
-    fn flush(&mut self) -> io::Result<()> {
-        Ok(())
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn encoded_buffer_growth_retains_both_allocations_and_the_last_slice() {
-        use std::io::Write;
-
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(95, Duration::from_secs(30));
-        let mut buffer = BackgroundEncodeBuffer::new(owner.clone(), 64);
-        buffer.write_all(&[7; 32]).expect("initial allocation fits");
-        assert_eq!(owner.snapshot().used, 32);
-
-        let error = buffer.write_all(&[8]).expect_err("old 32 plus replacement 64 exceed 95");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        assert!(is_memory_pressure(&error));
-        assert_eq!(buffer.filled, 32);
-        assert_eq!(buffer.buffer.as_slice(), &[7; 32]);
-        assert_eq!(owner.snapshot().used, 32);
-
-        owner.set_sampled_limit(96, Duration::from_secs(30));
-        buffer.write_all(&[8]).expect("old 32 plus replacement 64 fit 96");
-        assert_eq!(owner.snapshot().used, 64);
-        let bytes = buffer.into_bytes();
-        assert_eq!(&bytes[..32], &[7; 32]);
-        assert_eq!(bytes[32], 8);
-        assert_eq!(bytes.len(), 33);
-        let slice = bytes.slice(32..);
-        drop(bytes);
-        assert_eq!(slice.as_ref(), &[8]);
-        assert_eq!(owner.snapshot().used, 64);
-        drop(slice);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[test]
-    fn encoded_buffer_checks_its_limit_before_reserving_storage() {
-        use std::io::Write;
-
-        let owner = BackgroundMemoryBudget::new();
-        for maximum in [0, 3] {
-            let mut buffer = BackgroundEncodeBuffer::new(owner.clone(), maximum);
-            buffer
-                .write_all(&[])
-                .expect("empty input needs no storage, including at limit zero");
-            let error = buffer
-                .write_all(&[7; 4])
-                .expect_err("oversized input must fail before memory admission");
-            assert_eq!(error.kind(), io::ErrorKind::InvalidData);
-            assert!(buffer.buffer.as_slice().is_empty());
-            assert!(buffer.into_bytes().is_empty());
-            assert_eq!(owner.snapshot().used, 0);
-        }
-    }
-
-    #[test]
-    fn returned_bytes_keep_the_allocation_charged_through_slices_and_shrink() {
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(8, Duration::from_secs(30));
-        let bytes = BackgroundBuffer::new(Some(owner.clone()))
-            .read_to_end(&mut &b"abcdefgh"[..], 8)
-            .expect("exact allocation fits without an EOF growth allocation");
-        assert_eq!(bytes.as_ref(), b"abcdefgh");
-        assert_eq!(owner.snapshot().used, 8);
-        let slice = bytes.slice(2..6);
-        owner.set_sampled_limit(0, Duration::ZERO);
-        drop(bytes);
-        assert_eq!(slice.as_ref(), b"cdef");
-        assert_eq!(owner.snapshot().used, 8, "the final slice still owns the complete allocation");
-        assert!(owner.reserve(1).is_err());
-        drop(slice);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[test]
-    fn whole_file_size_hint_never_truncates_growth_or_exposes_unused_bytes() {
-        for (hint, retained) in [(0, 32), (4, 32), (8, 8), (16, 16)] {
-            let owner = BackgroundMemoryBudget::new();
-            owner.set_sampled_limit(36, Duration::from_secs(30));
-            let bytes = BackgroundBuffer::new(Some(owner.clone()))
-                .read_to_end(&mut &b"abcdefgh"[..], hint)
-                .expect("read through EOF independently of the metadata hint");
-            assert_eq!(bytes.as_ref(), b"abcdefgh", "hint={hint}");
-            assert_eq!(owner.snapshot().used, retained, "charge allocated capacity, not visible length");
-            drop(bytes);
-            assert_eq!(owner.snapshot().used, 0);
-        }
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(16, Duration::from_secs(30));
-        let bytes = BackgroundBuffer::new(Some(owner.clone()))
-            .read_to_end(&mut std::io::empty(), 16)
-            .expect("file shrank to empty");
-        assert!(bytes.is_empty());
-        assert_eq!(owner.snapshot().used, 0, "empty results free unused storage before refund");
-    }
-
-    #[test]
-    fn preserving_growth_keeps_existing_payload_on_denial_and_reuse() {
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(11, Duration::from_secs(30));
-        let mut buffer = BackgroundBuffer::new(Some(owner.clone()));
-        buffer.ensure_len(4).expect("allocate initial payload");
-        buffer.as_mut_slice().copy_from_slice(b"data");
-
-        let error = buffer
-            .grow(8, 4)
-            .expect_err("old and replacement allocations need twelve bytes");
-        assert!(is_memory_pressure(&error));
-        assert_eq!(buffer.as_slice(), b"data");
-        assert_eq!(owner.snapshot().used, 4);
-
-        owner.set_sampled_limit(12, Duration::from_secs(30));
-        buffer.grow(8, 4).expect("preserve the payload after admission");
-        assert_eq!(buffer.as_slice(), b"data\0\0\0\0");
-        assert_eq!(owner.snapshot().used, 8);
-        owner.set_sampled_limit(0, Duration::ZERO);
-        buffer.grow(8, 4).expect("reuse retained storage after expiry");
-        assert_eq!(buffer.as_slice(), b"data\0\0\0\0");
-
-        let bytes = buffer.take_bytes(4);
-        drop(buffer);
-        assert_eq!(bytes.as_ref(), b"data");
-        assert_eq!(owner.snapshot().used, 8);
-        drop(bytes);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[test]
-    fn whole_file_growth_denial_and_source_failure_refund_storage() {
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(35, Duration::from_secs(30));
-        let error = BackgroundBuffer::new(Some(owner.clone()))
-            .read_to_end(&mut &b"abcdefgh"[..], 4)
-            .expect_err("old four plus new thirty-two bytes exceed capacity");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        assert_eq!(owner.snapshot().used, 0);
-
-        struct FailedRead(u8);
-        impl io::Read for FailedRead {
-            fn read(&mut self, bytes: &mut [u8]) -> io::Result<usize> {
-                self.0 += 1;
-                match self.0 {
-                    1 => Err(io::ErrorKind::Interrupted.into()),
-                    2 => {
-                        bytes[..2].copy_from_slice(b"ab");
-                        Ok(2)
-                    }
-                    _ => Err(io::ErrorKind::PermissionDenied.into()),
-                }
-            }
-        }
-        let error = BackgroundBuffer::new(Some(owner.clone()))
-            .read_to_end(&mut FailedRead(0), 8)
-            .expect_err("failure after partial output is not successful EOF");
-        assert_eq!(error.kind(), io::ErrorKind::PermissionDenied);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn shrink_and_expiry_keep_retained_storage_charged() {
-        let owner = BackgroundMemoryBudget::new();
-        assert!(owner.reserve(1).is_err());
-        owner.set_sampled_limit(16, Duration::from_secs(3));
-        let mut buffer = BackgroundBuffer::new(Some(owner.clone()));
-        buffer.ensure_len(8).expect("initial allocation");
-        let pointer = buffer.as_slice().as_ptr();
-        owner.set_sampled_limit(4, Duration::from_secs(3));
-        buffer.ensure_len(8).expect("existing storage can be reused after shrink");
-        assert_eq!(buffer.as_slice().as_ptr(), pointer);
-        assert_eq!(owner.snapshot(), BackgroundMemorySnapshot { limit: 4, used: 8 });
-        assert_eq!(buffer.ensure_len(9).expect_err("growth must be denied").kind(), io::ErrorKind::WouldBlock);
-        assert_eq!(owner.snapshot().used, 8, "failed growth preserves the existing reservation");
-        tokio::time::advance(Duration::from_secs(3)).await;
-        assert_eq!(owner.snapshot(), BackgroundMemorySnapshot { limit: 0, used: 8 });
-        assert!(owner.reserve(1).is_err(), "an expired sampler cannot grant memory");
-        drop(buffer);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[test]
-    fn growth_accounts_for_both_allocations_and_refunds_failed_attempts() {
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(12, Duration::from_secs(3));
-        let mut buffer = BackgroundBuffer::new(Some(owner.clone()));
-        buffer.ensure_len(4).expect("first allocation");
-        buffer.as_mut_slice().copy_from_slice(b"data");
-        assert!(buffer.ensure_len(9).is_err(), "four old plus nine new bytes exceed the cap");
-        assert_eq!(buffer.as_slice(), b"data");
-        buffer.ensure_len(8).expect("four old plus eight new bytes fit");
-        assert_eq!(owner.snapshot().used, 8);
-        assert_eq!(buffer.as_slice(), &[0; 8]);
-        drop(buffer);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-
-    #[test]
-    fn concurrent_reservations_share_one_cap() {
-        let owner = BackgroundMemoryBudget::new();
-        owner.set_sampled_limit(1024, Duration::from_secs(30));
-        let ready = Arc::new(std::sync::Barrier::new(17));
-        let release = Arc::new(std::sync::Barrier::new(17));
-        // Start every worker before the first barrier; lazy spawning would deadlock.
-        let mut workers = Vec::with_capacity(16);
-        for _ in 0..16 {
-            let owner = owner.clone();
-            let ready = ready.clone();
-            let release = release.clone();
-            workers.push(std::thread::spawn(move || {
-                let reservation = owner.reserve(128).ok();
-                ready.wait();
-                release.wait();
-                reservation.is_some()
-            }));
-        }
-        ready.wait();
-        let retained = owner.snapshot().used;
-        release.wait();
-        let granted = workers
-            .into_iter()
-            .map(|worker| worker.join().expect("reservation worker"))
-            .filter(|granted| *granted)
-            .count();
-        assert_eq!(retained, 1024);
-        assert_eq!(granted, 8);
-        assert_eq!(owner.snapshot().used, 0);
-    }
-}

crates/ecstore/src/disk/io_admission/physical_identity.rs

@@ -1,443 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use std::collections::{BTreeMap, BTreeSet};
-use std::fs::File;
-use std::io::{self, Read};
-use std::path::{Path, PathBuf};
-
-const MAX_TOPOLOGY_NODES: usize = 256;
-const MAX_TOPOLOGY_DEPTH: usize = 32;
-const MAX_ATTRIBUTE_BYTES: u64 = 128;
-
-/// Kernel device numbers can be reused after removal. `diskseq` distinguishes
-/// those incarnations; this identity does not authorize storage mutations.
-#[derive(Clone, Copy, Debug, Eq, Ord, PartialEq, PartialOrd)]
-pub(super) struct PhysicalDeviceIdentity {
-    pub(super) major: u32,
-    pub(super) minor: u32,
-    pub(super) generation: u64,
-}
-
-fn invalid(message: &'static str) -> io::Error {
-    io::Error::new(io::ErrorKind::InvalidData, message)
-}
-
-pub(super) fn attribute(path: &Path) -> io::Result<String> {
-    let mut value = String::new();
-    File::open(path)?.take(MAX_ATTRIBUTE_BYTES + 1).read_to_string(&mut value)?;
-    if value.len() > MAX_ATTRIBUTE_BYTES as usize {
-        return Err(invalid("physical device attribute exceeds its bound"));
-    }
-    Ok(value.trim().to_owned())
-}
-
-fn number(value: &str) -> io::Result<u64> {
-    if value.is_empty() || !value.bytes().all(|byte| byte.is_ascii_digit()) {
-        return Err(invalid("invalid physical device number"));
-    }
-    value.parse().map_err(|_| invalid("physical device number overflow"))
-}
-
-fn identity(path: &Path) -> io::Result<PhysicalDeviceIdentity> {
-    let generation = number(&attribute(&path.join("diskseq"))?)?;
-    if generation == 0 {
-        return Err(invalid("physical device generation is missing"));
-    }
-    let device = attribute(&path.join("dev"))?;
-    let (major, minor) = device
-        .split_once(':')
-        .ok_or_else(|| invalid("invalid physical device identity"))?;
-    let major = u32::try_from(number(major)?).map_err(|_| invalid("physical major number overflow"))?;
-    let minor = u32::try_from(number(minor)?).map_err(|_| invalid("physical minor number overflow"))?;
-    if number(&attribute(&path.join("diskseq"))?)? != generation {
-        return Err(invalid("physical device changed during discovery"));
-    }
-    Ok(PhysicalDeviceIdentity {
-        major,
-        minor,
-        generation,
-    })
-}
-
-#[derive(Debug, Eq, PartialEq)]
-enum NodeTopology {
-    Partition {
-        device: String,
-        number: u64,
-        parent: PathBuf,
-    },
-    Whole {
-        identity: PhysicalDeviceIdentity,
-        children: Vec<PathBuf>,
-    },
-}
-
-fn canonical_beneath(path: &Path, root: &Path) -> io::Result<PathBuf> {
-    let path = path.canonicalize()?;
-    if !path.starts_with(root) {
-        return Err(invalid("physical device topology escapes sysfs"));
-    }
-    Ok(path)
-}
-
-fn node_topology(path: &Path, root: &Path) -> io::Result<NodeTopology> {
-    if canonical_beneath(path, root)? != path {
-        return Err(invalid("physical device path changed during discovery"));
-    }
-    match attribute(&path.join("partition")) {
-        Ok(partition) => {
-            let number = number(&partition)?;
-            if number == 0 {
-                return Err(invalid("physical partition number is missing"));
-            }
-            let parent = path.parent().ok_or_else(|| invalid("physical partition has no parent"))?;
-            return Ok(NodeTopology::Partition {
-                device: attribute(&path.join("dev"))?,
-                number,
-                parent: canonical_beneath(parent, root)?,
-            });
-        }
-        Err(error) if error.kind() == io::ErrorKind::NotFound => {}
-        Err(error) => return Err(error),
-    }
-    let identity = identity(path)?;
-    let mut children = Vec::new();
-    for entry in std::fs::read_dir(path.join("slaves"))? {
-        if children.len() >= MAX_TOPOLOGY_NODES {
-            return Err(invalid("physical device topology fanout exceeds its bound"));
-        }
-        children.push(canonical_beneath(&entry?.path(), root)?);
-    }
-    children.sort_unstable();
-    children.dedup();
-    Ok(NodeTopology::Whole { identity, children })
-}
-
-struct TopologySnapshot {
-    root: PathBuf,
-    entry: PathBuf,
-    first: PathBuf,
-    nodes: BTreeMap<PathBuf, NodeTopology>,
-    leaves: BTreeSet<PhysicalDeviceIdentity>,
-}
-
-impl TopologySnapshot {
-    fn discover(sysfs_root: &Path, major: u64, minor: u64) -> io::Result<Self> {
-        let root = sysfs_root.canonicalize()?;
-        let entry = root.join(format!("dev/block/{major}:{minor}"));
-        let first = canonical_beneath(&entry, &root)?;
-        if attribute(&first.join("dev"))? != format!("{major}:{minor}") {
-            return Err(invalid("physical device entry does not match its device number"));
-        }
-        let mut stack = vec![(first.clone(), 0, false)];
-        let mut active = BTreeSet::new();
-        let mut nodes = BTreeMap::new();
-        let mut leaves = BTreeMap::<PhysicalDeviceIdentity, PathBuf>::new();
-        while let Some((path, depth, exiting)) = stack.pop() {
-            if exiting {
-                active.remove(&path);
-                continue;
-            }
-            if depth > MAX_TOPOLOGY_DEPTH {
-                return Err(invalid("physical device topology is too deep"));
-            }
-            if active.contains(&path) {
-                return Err(invalid("physical device topology contains a cycle"));
-            }
-            if nodes.contains_key(&path) {
-                continue;
-            }
-            if nodes.len() >= MAX_TOPOLOGY_NODES {
-                return Err(invalid("physical device topology exceeds its node bound"));
-            }
-            let topology = node_topology(&path, &root)?;
-            active.insert(path.clone());
-            stack.push((path.clone(), depth, true));
-            match &topology {
-                NodeTopology::Partition { parent, .. } => stack.push((parent.clone(), depth + 1, false)),
-                NodeTopology::Whole { identity, children } => {
-                    if stack.len() + children.len() > MAX_TOPOLOGY_NODES * 2 {
-                        return Err(invalid("physical device topology fanout exceeds its bound"));
-                    }
-                    for child in children {
-                        stack.push((child.clone(), depth + 1, false));
-                    }
-                    if children.is_empty()
-                        && let Some(previous) = leaves.insert(*identity, path.clone())
-                        && previous != path
-                    {
-                        return Err(invalid("physical device identity is ambiguous"));
-                    }
-                }
-            }
-            nodes.insert(path, topology);
-        }
-        if leaves.is_empty() {
-            return Err(invalid("physical device topology has no leaves"));
-        }
-        Ok(Self {
-            root,
-            entry,
-            first,
-            nodes,
-            leaves: leaves.into_keys().collect(),
-        })
-    }
-
-    fn validate(&self) -> io::Result<()> {
-        if canonical_beneath(&self.entry, &self.root)? != self.first {
-            return Err(invalid("physical device entry changed during discovery"));
-        }
-        for (path, expected) in &self.nodes {
-            if &node_topology(path, &self.root)? != expected {
-                return Err(invalid("physical device topology changed during discovery"));
-            }
-        }
-        Ok(())
-    }
-}
-
-/// Resolve a bounded sysfs topology once, before installing an admission owner.
-/// Missing topology or generation evidence is unknown, never a name-based owner.
-/// Validate intermediate mappings too: stable leaves alone do not prove that a
-/// device-mapper table still points to those leaves. This is an observation, not
-/// a kernel topology lock; the admission owner must expire and refresh it.
-pub(super) fn resolve_physical_devices(sysfs_root: &Path, major: u64, minor: u64) -> io::Result<Vec<PhysicalDeviceIdentity>> {
-    let snapshot = TopologySnapshot::discover(sysfs_root, major, minor)?;
-    snapshot.validate()?;
-    Ok(snapshot.leaves.into_iter().collect())
-}
-
-#[cfg(all(test, unix))]
-mod tests {
-    use super::*;
-    use std::os::unix::fs::symlink;
-    use std::sync::atomic::{AtomicU64, Ordering};
-
-    struct Fixture(PathBuf);
-
-    impl Fixture {
-        fn new() -> Self {
-            static NEXT: AtomicU64 = AtomicU64::new(0);
-            let stamp = std::time::SystemTime::now()
-                .duration_since(std::time::UNIX_EPOCH)
-                .expect("clock")
-                .as_nanos();
-            let root = std::env::temp_dir().join(format!(
-                "physical-identity-{}-{stamp}-{}",
-                std::process::id(),
-                NEXT.fetch_add(1, Ordering::Relaxed)
-            ));
-            std::fs::create_dir(&root).expect("exclusive test root");
-            std::fs::create_dir_all(root.join("sys/dev/block")).expect("sysfs fixture");
-            Self(root)
-        }
-
-        fn root(&self) -> PathBuf {
-            self.0.join("sys")
-        }
-
-        fn device(&self, name: &str, major: u32, minor: u32, generation: u64) -> PathBuf {
-            let path = self.root().join("devices").join(name);
-            std::fs::create_dir_all(path.join("slaves")).expect("device fixture");
-            std::fs::write(path.join("dev"), format!("{major}:{minor}\n")).expect("device number");
-            std::fs::write(path.join("diskseq"), format!("{generation}\n")).expect("device generation");
-            symlink(&path, self.root().join(format!("dev/block/{major}:{minor}"))).expect("sysfs link");
-            path
-        }
-
-        fn link(&self, parent: &Path, child: &Path, name: &str) {
-            symlink(child, parent.join("slaves").join(name)).expect("slave link");
-        }
-    }
-
-    impl Drop for Fixture {
-        fn drop(&mut self) {
-            std::fs::remove_dir_all(&self.0).expect("remove owned fixture");
-        }
-    }
-
-    #[test]
-    fn partitions_share_the_leaf_generation_and_replacement_changes_identity() {
-        let fixture = Fixture::new();
-        let leaf = fixture.device("sda", 8, 0, 41);
-        let first = fixture.device("sda/sda1", 8, 1, 41);
-        let second = fixture.device("sda/sda2", 8, 2, 41);
-        std::fs::write(first.join("partition"), "1\n").expect("first partition");
-        std::fs::write(second.join("partition"), "2\n").expect("second partition");
-        let old = resolve_physical_devices(&fixture.root(), 8, 1).expect("first leaf");
-        assert_eq!(old, resolve_physical_devices(&fixture.root(), 8, 2).expect("alias leaf"));
-        assert_eq!(
-            old,
-            vec![PhysicalDeviceIdentity {
-                major: 8,
-                minor: 0,
-                generation: 41
-            }]
-        );
-        std::fs::write(leaf.join("diskseq"), "42\n").expect("replacement generation");
-        let new = resolve_physical_devices(&fixture.root(), 8, 1).expect("replacement leaf");
-        assert_ne!(old, new);
-        assert_eq!(new[0].generation, 42);
-    }
-
-    #[test]
-    fn overlapping_stacks_deduplicate_shared_physical_leaves() {
-        let fixture = Fixture::new();
-        let a = fixture.device("a", 8, 0, 1);
-        let b = fixture.device("b", 8, 16, 2);
-        let inner = fixture.device("dm-0", 253, 0, 3);
-        let outer = fixture.device("dm-1", 253, 1, 4);
-        fixture.link(&inner, &a, "a");
-        fixture.link(&inner, &b, "b");
-        fixture.link(&outer, &inner, "dm-0");
-        fixture.link(&outer, &a, "a-again");
-        assert_eq!(
-            resolve_physical_devices(&fixture.root(), 253, 0).expect("inner"),
-            resolve_physical_devices(&fixture.root(), 253, 1).expect("outer")
-        );
-        assert_eq!(resolve_physical_devices(&fixture.root(), 253, 1).expect("leaves").len(), 2);
-    }
-
-    #[test]
-    fn missing_or_invalid_generation_never_falls_back_to_a_device_name() {
-        let fixture = Fixture::new();
-        let leaf = fixture.device("a", 8, 0, 1);
-        for value in ["0", "-1", "18446744073709551616", "+1"] {
-            std::fs::write(leaf.join("diskseq"), value).expect("bad generation");
-            assert!(resolve_physical_devices(&fixture.root(), 8, 0).is_err(), "accepted {value}");
-        }
-        std::fs::remove_file(leaf.join("diskseq")).expect("missing generation");
-        assert_eq!(
-            resolve_physical_devices(&fixture.root(), 8, 0)
-                .expect_err("unknown generation")
-                .kind(),
-            io::ErrorKind::NotFound
-        );
-        assert!(resolve_physical_devices(&fixture.root(), 99, 99).is_err());
-    }
-
-    #[test]
-    fn topology_cycles_and_escaping_links_are_rejected() {
-        let fixture = Fixture::new();
-        let a = fixture.device("a", 8, 0, 1);
-        let b = fixture.device("b", 8, 16, 2);
-        fixture.link(&a, &b, "b");
-        fixture.link(&b, &a, "a");
-        assert!(
-            resolve_physical_devices(&fixture.root(), 8, 0)
-                .expect_err("cycle")
-                .to_string()
-                .contains("cycle")
-        );
-        std::fs::remove_file(b.join("slaves/a")).expect("remove cycle edge");
-        fixture.link(&b, &fixture.0, "outside");
-        assert!(
-            resolve_physical_devices(&fixture.root(), 8, 0)
-                .expect_err("escape")
-                .to_string()
-                .contains("escapes")
-        );
-    }
-
-    #[test]
-    fn intermediate_mapping_changes_are_rejected_even_when_old_leaves_survive() {
-        let fixture = Fixture::new();
-        let a = fixture.device("a", 8, 0, 1);
-        let b = fixture.device("b", 8, 16, 2);
-        let mapper = fixture.device("dm-0", 253, 0, 3);
-        fixture.link(&mapper, &a, "backing");
-        let snapshot = TopologySnapshot::discover(&fixture.root(), 253, 0).expect("initial mapping");
-        snapshot.validate().expect("unchanged topology");
-        std::fs::remove_file(mapper.join("slaves/backing")).expect("replace mapping");
-        fixture.link(&mapper, &b, "backing");
-        assert_eq!(identity(&a).expect("old leaf still exists").generation, 1);
-        assert!(snapshot.validate().is_err(), "stable old leaves cannot certify a changed mapper");
-        let current = resolve_physical_devices(&fixture.root(), 253, 0).expect("new complete mapping");
-        assert_eq!(current, vec![identity(&b).expect("new leaf")]);
-        let snapshot = TopologySnapshot::discover(&fixture.root(), 253, 0).expect("new mapping");
-        std::fs::write(mapper.join("diskseq"), "4\n").expect("replace mapper incarnation");
-        assert!(
-            snapshot.validate().is_err(),
-            "an intermediate generation change also invalidates discovery"
-        );
-    }
-
-    #[test]
-    fn entry_and_partition_changes_are_not_hidden_by_an_unchanged_parent() {
-        let fixture = Fixture::new();
-        fixture.device("a", 8, 0, 1);
-        let partition = fixture.device("a/p1", 8, 1, 1);
-        std::fs::write(partition.join("partition"), "1\n").expect("partition index");
-        let snapshot = TopologySnapshot::discover(&fixture.root(), 8, 1).expect("partition topology");
-        std::fs::write(partition.join("partition"), "2\n").expect("changed partition");
-        assert!(snapshot.validate().is_err());
-        let b = fixture.device("b", 8, 16, 2);
-        let snapshot = TopologySnapshot::discover(&fixture.root(), 8, 0).expect("first entry");
-        let entry = fixture.root().join("dev/block/8:0");
-        std::fs::remove_file(&entry).expect("replace entry");
-        symlink(&b, &entry).expect("changed entry target");
-        assert!(snapshot.validate().is_err());
-        assert!(
-            resolve_physical_devices(&fixture.root(), 8, 0).is_err(),
-            "entry device numbers must match"
-        );
-    }
-
-    #[test]
-    fn missing_slave_directory_is_unknown_not_a_physical_leaf() {
-        let fixture = Fixture::new();
-        let mapper = fixture.device("dm-0", 253, 0, 1);
-        std::fs::remove_dir(mapper.join("slaves")).expect("missing topology evidence");
-        assert!(resolve_physical_devices(&fixture.root(), 253, 0).is_err());
-    }
-
-    #[test]
-    fn topology_depth_and_attribute_sizes_are_bounded() {
-        let fixture = Fixture::new();
-        let first = fixture.device("d0", 253, 0, 1);
-        let mut previous = first.clone();
-        for index in 1..=MAX_TOPOLOGY_DEPTH + 1 {
-            let child = fixture.device(&format!("d{index}"), 253, u32::try_from(index).expect("bounded index"), 1);
-            fixture.link(&previous, &child, "next");
-            previous = child;
-        }
-        assert!(
-            resolve_physical_devices(&fixture.root(), 253, 0)
-                .expect_err("depth bound")
-                .to_string()
-                .contains("deep")
-        );
-        std::fs::remove_file(first.join("slaves/next")).expect("make first node a leaf");
-        std::fs::write(first.join("diskseq"), "1".repeat(129)).expect("oversized attribute");
-        assert!(
-            resolve_physical_devices(&fixture.root(), 253, 0)
-                .expect_err("attribute bound")
-                .to_string()
-                .contains("attribute")
-        );
-    }
-
-    #[test]
-    fn exact_node_bound_passes_and_one_more_node_is_rejected() {
-        let fixture = Fixture::new();
-        let root = fixture.device("root", 253, 0, 1);
-        for index in 0..MAX_TOPOLOGY_NODES - 1 {
-            let leaf = fixture.device(&format!("leaf-{index}"), 8, u32::try_from(index).expect("bounded index"), 2);
-            fixture.link(&root, &leaf, &format!("leaf-{index}"));
-        }
-        assert_eq!(
-            resolve_physical_devices(&fixture.root(), 253, 0)
-                .expect("exact node bound")
-                .len(),
-            MAX_TOPOLOGY_NODES - 1
-        );
-        let extra = fixture.device("extra", 9, 0, 3);
-        fixture.link(&root, &extra, "extra");
-        assert!(
-            resolve_physical_devices(&fixture.root(), 253, 0).is_err(),
-            "reject a graph above the node bound"
-        );
-    }
-}

crates/ecstore/src/disk/io_admission/physical_owners.rs

@@ -1,268 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use std::collections::{BTreeMap, BTreeSet};
-use std::io;
-use std::num::NonZeroU16;
-use std::sync::{Arc, Weak};
-use std::time::Duration;
-
-use rustfs_concurrency::adaptive::AdaptiveAdmission;
-#[cfg(test)]
-use rustfs_concurrency::adaptive::{AdaptiveAdmissionSnapshot, AdaptivePermit};
-
-use super::physical_identity::PhysicalDeviceIdentity;
-
-const MAX_PHYSICAL_OWNERS: usize = 256;
-
-/// Resolve aliases outside object work. The sampling owner serializes changes;
-/// attached handles and native permits never consult this registry.
-pub(super) struct PhysicalOwnerRegistry {
-    maximum: NonZeroU16,
-    owners: BTreeMap<PhysicalDeviceIdentity, Weak<AdaptiveAdmission>>,
-}
-
-/// One attachment to an existing physical capacity owner, not a reservation.
-/// The gate itself owns permit slots, so native permit clones keep a registry
-/// entry alive even after the last logical disk attachment disappears.
-pub(super) struct PhysicalDeviceAdmission {
-    #[cfg(test)]
-    identity: PhysicalDeviceIdentity,
-    gate: Arc<AdaptiveAdmission>,
-}
-
-impl PhysicalOwnerRegistry {
-    pub(super) fn new(maximum: NonZeroU16) -> Self {
-        Self {
-            maximum,
-            owners: BTreeMap::new(),
-        }
-    }
-
-    /// Old topology descriptors may still reference an unused gate. Close it
-    /// before reclaiming its registry slot; only admitted I/O keeps an absent
-    /// incarnation alive, and its final release still reaches the same owner.
-    pub(super) fn retire_absent(&mut self, current: &BTreeSet<PhysicalDeviceIdentity>) {
-        self.owners.retain(|identity, owner| {
-            let Some(gate) = owner.upgrade() else {
-                return false;
-            };
-            if current.contains(identity) {
-                return true;
-            }
-            gate.set_sampled_limit(0, Duration::ZERO);
-            gate.snapshot().active != 0
-        });
-    }
-
-    pub(super) fn bind(&mut self, identities: &[PhysicalDeviceIdentity]) -> io::Result<Vec<PhysicalDeviceAdmission>> {
-        if identities.is_empty() || identities.len() > MAX_PHYSICAL_OWNERS || identities.iter().any(|id| id.generation == 0) {
-            return Err(io::Error::new(io::ErrorKind::InvalidData, "invalid physical capacity identities"));
-        }
-        let identities = identities.iter().copied().collect::<BTreeSet<_>>();
-        self.owners.retain(|_, owner| owner.strong_count() != 0);
-        let new_owners = identities
-            .iter()
-            .filter(|identity| !self.owners.contains_key(identity))
-            .count();
-        if new_owners > MAX_PHYSICAL_OWNERS - self.owners.len() {
-            return Err(io::Error::new(io::ErrorKind::WouldBlock, "physical capacity registry is full"));
-        }
-        Ok(identities
-            .into_iter()
-            .map(|identity| {
-                let gate = self.owners.get(&identity).and_then(Weak::upgrade).unwrap_or_else(|| {
-                    let gate = AdaptiveAdmission::new(self.maximum, 0);
-                    self.owners.insert(identity, Arc::downgrade(&gate));
-                    gate
-                });
-                PhysicalDeviceAdmission {
-                    #[cfg(test)]
-                    identity,
-                    gate,
-                }
-            })
-            .collect())
-    }
-
-    /// Only the sampling owner publishes capacity. New or expired identities
-    /// remain closed until a fresh observation establishes a bounded limit.
-    #[cfg(test)]
-    pub(super) fn publish(&mut self, identity: PhysicalDeviceIdentity, limit: u32, valid_for: Duration) -> bool {
-        let Some(gate) = self.owners.get(&identity).and_then(Weak::upgrade) else {
-            return false;
-        };
-        gate.set_sampled_limit(limit, valid_for);
-        true
-    }
-}
-
-impl PhysicalDeviceAdmission {
-    pub(super) fn gate(&self) -> &Arc<AdaptiveAdmission> {
-        &self.gate
-    }
-
-    #[cfg(test)]
-    pub(super) fn identity(&self) -> PhysicalDeviceIdentity {
-        self.identity
-    }
-
-    #[cfg(test)]
-    pub(super) fn snapshot(&self) -> AdaptiveAdmissionSnapshot {
-        self.gate.snapshot()
-    }
-
-    #[cfg(test)]
-    pub(super) fn try_acquire(&self) -> Option<AdaptivePermit> {
-        self.gate.try_acquire()
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    fn device(minor: u32, generation: u64) -> PhysicalDeviceIdentity {
-        PhysicalDeviceIdentity {
-            major: 259,
-            minor,
-            generation,
-        }
-    }
-
-    fn registry() -> PhysicalOwnerRegistry {
-        PhysicalOwnerRegistry::new(NonZeroU16::new(2).expect("two units"))
-    }
-
-    #[test]
-    fn aliases_and_overlapping_stacks_share_one_physical_capacity() {
-        let mut registry = registry();
-        let a = device(1, 11);
-        let b = device(2, 12);
-        let single = registry.bind(&[a]).expect("single device");
-        let stack = registry.bind(&[b, a, a]).expect("overlapping stack");
-        assert_eq!(stack.len(), 2, "duplicates cannot reserve additional units");
-        assert_eq!(stack[0].identity(), a);
-        assert!(single[0].try_acquire().is_none(), "unobserved capacity is closed");
-        assert!(registry.publish(a, 1, Duration::from_secs(60)));
-        let held = single[0].try_acquire().expect("physical unit");
-        assert!(stack[0].try_acquire().is_none(), "the alias cannot double the capacity");
-        assert_eq!(stack[0].snapshot().active, 1);
-        drop(held);
-        assert!(stack[0].try_acquire().is_some());
-    }
-
-    #[test]
-    fn native_tail_keeps_the_owner_alive_after_all_attachments_are_gone() {
-        let mut registry = registry();
-        let id = device(1, 11);
-        let attachment = registry.bind(&[id]).expect("logical disk");
-        assert!(registry.publish(id, 1, Duration::from_secs(60)));
-        let waiter = attachment[0].try_acquire().expect("admitted work");
-        let native = waiter.clone();
-        drop(waiter);
-        drop(attachment);
-        let reconnected = registry.bind(&[id]).expect("reconnect during native I/O");
-        assert_eq!(reconnected[0].snapshot().active, 1);
-        assert!(reconnected[0].try_acquire().is_none());
-        drop(native);
-        assert!(reconnected[0].try_acquire().is_some(), "only the final native release returns capacity");
-    }
-
-    #[test]
-    fn replacement_generation_does_not_receive_old_native_refunds() {
-        let mut registry = registry();
-        let old_id = device(1, 11);
-        let new_id = device(1, 12);
-        let old = registry.bind(&[old_id]).expect("old incarnation");
-        assert!(registry.publish(old_id, 1, Duration::from_secs(60)));
-        let native = old[0].try_acquire().expect("old native I/O");
-        drop(old);
-        let new = registry.bind(&[new_id]).expect("replacement incarnation");
-        assert_eq!(new[0].snapshot().active, 0);
-        assert!(new[0].try_acquire().is_none());
-        assert!(registry.publish(new_id, 1, Duration::from_secs(60)));
-        let current = new[0].try_acquire().expect("new work");
-        drop(native);
-        assert_eq!(new[0].snapshot().active, 1, "old completion cannot refund the replacement");
-        assert!(new[0].try_acquire().is_none());
-        drop(current);
-        assert_eq!(new[0].snapshot().active, 0);
-    }
-
-    #[test]
-    fn shrink_and_expiry_preserve_active_units_and_leave_other_disks_available() {
-        let mut registry = registry();
-        let a = device(1, 11);
-        let b = device(2, 12);
-        let disks = registry.bind(&[a, b]).expect("two physical disks");
-        assert!(registry.publish(a, 2, Duration::from_secs(60)));
-        assert!(registry.publish(b, 1, Duration::from_secs(60)));
-        let first = disks[0].try_acquire().expect("first unit");
-        let second = disks[0].try_acquire().expect("second unit");
-        assert!(registry.publish(a, 1, Duration::from_secs(60)));
-        assert_eq!(disks[0].snapshot().active, 2);
-        assert!(disks[0].try_acquire().is_none());
-        assert!(disks[1].try_acquire().is_some(), "a stalled disk cannot consume another disk's capacity");
-        assert!(registry.publish(a, 2, Duration::ZERO));
-        assert_eq!(disks[0].snapshot().limit, 0);
-        assert_eq!(disks[0].snapshot().active, 2);
-        drop((first, second));
-        assert!(disks[0].try_acquire().is_none(), "expired observations do not reopen after completion");
-    }
-
-    #[test]
-    fn registry_bound_preserves_live_native_owners_and_reclaims_only_dead_entries() {
-        let mut registry = registry();
-        let ids = (0..MAX_PHYSICAL_OWNERS)
-            .map(|minor| device(u32::try_from(minor).expect("bounded minor"), 1))
-            .collect::<Vec<_>>();
-        let attachments = registry.bind(&ids).expect("exact registry bound");
-        let extra = device(999, 1);
-        assert!(matches!(registry.bind(&[extra]), Err(error) if error.kind() == io::ErrorKind::WouldBlock));
-        assert_eq!(registry.owners.len(), MAX_PHYSICAL_OWNERS, "failed binding must not add partial owners");
-        assert!(registry.publish(ids[0], 1, Duration::from_secs(60)));
-        let native = attachments[0].try_acquire().expect("native tail");
-        drop(attachments);
-        let replacement = registry.bind(&[extra]).expect("dead owners reclaimed");
-        assert_eq!(registry.owners.len(), 2, "the native tail still owns its original entry");
-        let original = registry.bind(&[ids[0]]).expect("original native owner");
-        assert_eq!(original[0].snapshot().active, 1);
-        drop((native, original, replacement));
-        assert!(!registry.publish(extra, 1, Duration::from_secs(60)), "a dead owner cannot be refreshed");
-        assert!(registry.bind(&[]).is_err());
-        assert!(registry.bind(&[device(1, 0)]).is_err());
-    }
-
-    #[test]
-    fn retirement_reclaims_idle_descriptors_but_keeps_active_native_incarnations() {
-        let mut registry = registry();
-        let ids = (0..MAX_PHYSICAL_OWNERS)
-            .map(|minor| device(u32::try_from(minor).expect("bounded minor"), 1))
-            .collect::<Vec<_>>();
-        let descriptors = registry.bind(&ids).expect("full registry");
-        assert!(registry.publish(ids[0], 1, Duration::from_secs(60)));
-        let native = descriptors[0].try_acquire().expect("active old incarnation");
-        let mut current = ids[2..].iter().copied().collect::<BTreeSet<_>>();
-        registry.retire_absent(&current);
-        assert_eq!(registry.owners.len(), MAX_PHYSICAL_OWNERS - 1);
-        assert_eq!(descriptors[0].snapshot().active, 1);
-        assert!(descriptors[0].try_acquire().is_none());
-        assert!(descriptors[1].try_acquire().is_none());
-        let first = device(0, 2);
-        let second = device(1, 2);
-        let replacement = registry.bind(&[first]).expect("idle descriptor was reclaimed");
-        current.insert(first);
-        assert!(matches!(registry.bind(&[second]), Err(error) if error.kind() == io::ErrorKind::WouldBlock));
-        drop(native);
-        registry.retire_absent(&current);
-        let next = registry.bind(&[second]).expect("final native release permits reclamation");
-        assert_eq!(replacement[0].snapshot().active, 0);
-        assert_eq!(next[0].snapshot().active, 0);
-        assert_eq!(descriptors[0].snapshot().active, 0);
-        assert!(
-            !registry.publish(ids[0], 1, Duration::from_secs(60)),
-            "retired identity cannot be refreshed"
-        );
-    }
-}

crates/ecstore/src/disk/io_admission/remote.rs

@@ -1,309 +0,0 @@
-// Copyright 2026 RustFS Team
-// Licensed under the Apache License, Version 2.0.
-
-use super::{PhysicalDiskBinding, ResourceIoUnit};
-use rustfs_concurrency::adaptive::{
-    NodeAdmission,
-    permit_set::{NodeResourceCompletion, NodeResourcePermit},
-};
-use std::cell::{Cell, RefCell};
-use std::future::Future;
-use std::io;
-use std::sync::Arc;
-
-tokio::task_local! {
-    static REMOTE_RESOURCES: RemoteBackgroundIo;
-}
-
-/// Receiver-owned admission for an authenticated background RPC. The owner must
-/// be the same node controller used by local Scanner and Heal work.
-pub struct RemoteBackgroundIo {
-    node: Arc<NodeAdmission>,
-    admitted: RefCell<Option<NodeResourcePermit>>,
-    progressed: Cell<bool>,
-    finished: Cell<bool>,
-}
-
-impl RemoteBackgroundIo {
-    pub fn new(node: Arc<NodeAdmission>) -> Self {
-        Self {
-            node,
-            admitted: RefCell::new(None),
-            progressed: Cell::new(false),
-            finished: Cell::new(false),
-        }
-    }
-
-    /// Move the request's reservations into its existing stream producer.
-    /// Only physical subsets may be cloned into native I/O; never its node unit.
-    pub fn take_current() -> Option<Self> {
-        REMOTE_RESOURCES
-            .try_with(|context| Self {
-                node: context.node.clone(),
-                admitted: RefCell::new(context.admitted.take()),
-                progressed: Cell::new(context.progressed.replace(false)),
-                finished: Cell::new(false),
-            })
-            .ok()
-    }
-
-    /// Defer a response's progress without keeping async admission alive while
-    /// its body streams. The reader retains its own native resource ownership.
-    pub fn take_current_completion() -> Option<NodeResourceCompletion> {
-        REMOTE_RESOURCES
-            .try_with(|context| {
-                let admitted = context.admitted.take();
-                if context.progressed.replace(false) {
-                    admitted.map(NodeResourcePermit::into_completion)
-                } else {
-                    None
-                }
-            })
-            .ok()
-            .flatten()
-    }
-
-    /// A failed response or cancelled producer must not credit earlier phases.
-    pub fn discard_current_progress() {
-        let _ = REMOTE_RESOURCES.try_with(|context| context.progressed.set(false));
-    }
-}
-
-impl Drop for RemoteBackgroundIo {
-    fn drop(&mut self) {
-        if self.finished.get()
-            && self.progressed.get()
-            && let Some(permit) = self.admitted.get_mut().take()
-        {
-            permit.complete();
-        }
-    }
-}
-
-/// Scope a verified request or its stream producer. An interrupted request
-/// returns node capacity while native jobs retain their selected physical units.
-pub async fn with_remote_background_io<F: Future>(context: Option<RemoteBackgroundIo>, operation: F) -> F::Output {
-    match context {
-        Some(context) => {
-            REMOTE_RESOURCES
-                .scope(context, async {
-                    let result = operation.await;
-                    REMOTE_RESOURCES.with(|context| context.finished.set(true));
-                    result
-                })
-                .await
-        }
-        None => operation.await,
-    }
-}
-
-pub(crate) fn active() -> bool {
-    REMOTE_RESOURCES.try_with(|_| ()).is_ok()
-}
-
-pub(crate) fn resources() -> Option<ResourceIoUnit> {
-    REMOTE_RESOURCES
-        .try_with(|context| {
-            context
-                .admitted
-                .borrow()
-                .as_ref()
-                .map(|permit| ResourceIoUnit::from(permit.resources().clone()))
-        })
-        .ok()
-        .flatten()
-}
-
-pub(crate) fn record_progress() {
-    let _ = REMOTE_RESOURCES.try_with(|context| context.progressed.set(true));
-}
-
-pub(crate) fn admit(binding: &PhysicalDiskBinding) -> io::Result<()> {
-    REMOTE_RESOURCES
-        .try_with(|context| {
-            let deferred = || io::Error::from(io::ErrorKind::WouldBlock);
-            let plan = binding.plan().ok_or_else(deferred)?;
-            let mut admitted = context.admitted.borrow_mut();
-            if let Some(permit) = admitted.as_ref() {
-                // Reuse the request's receipt for append/read/rename phases at
-                // capacity one. Additional attachments never wait under locks.
-                let native = plan.capture_or_acquire_native(permit.resources()).map_err(|_| deferred())?;
-                drop(native);
-                if !plan.is_current() {
-                    return Err(deferred());
-                }
-            } else {
-                *admitted = Some(plan.try_acquire(&context.node).ok_or_else(deferred)?);
-            }
-            Ok(())
-        })
-        .unwrap_or(Ok(()))
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use rustfs_concurrency::adaptive::{
-        AdaptiveAdmission, FeedbackController, FeedbackObservation, ResourcePressure, permit_set::AdaptivePermitSetOwner,
-    };
-    use std::num::NonZeroU16;
-
-    fn node() -> Arc<NodeAdmission> {
-        let node = NodeAdmission::new(NonZeroU16::MIN);
-        node.update(
-            &mut FeedbackController::new(),
-            Some(FeedbackObservation {
-                generation: 1,
-                max_concurrency: 1,
-                pressure: ResourcePressure::Unknown,
-                completed_units: None,
-            }),
-        );
-        node
-    }
-
-    #[tokio::test]
-    async fn receiver_reuses_one_receipt_across_phases_and_releases_only_native_subsets() {
-        let node = node();
-        let a = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-        let b = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-        let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![a.clone(), b.clone()]).expect("device catalog");
-        let first = PhysicalDiskBinding::default();
-        let second = PhysicalDiskBinding::default();
-        first
-            .set_test_shared_capacity(shared.clone(), vec![a.clone()])
-            .expect("device A");
-        second.set_test_shared_capacity(shared, vec![b.clone()]).expect("device B");
-
-        let native = with_remote_background_io(Some(RemoteBackgroundIo::new(node.clone())), async {
-            assert!(resources().is_none(), "no physical work before target selection");
-            admit(&first).expect("first phase");
-            let admitted = resources().expect("admitted resources");
-            let native = first
-                .plan()
-                .expect("current plan")
-                .capture_native(admitted.as_set().expect("resource set"))
-                .expect("escaped native read");
-            admit(&first).expect("second phase reuses capacity while the first reader lives");
-            admit(&second).expect("additional selected device");
-            assert_eq!([node.snapshot().active, a.snapshot().active, b.snapshot().active], [1, 1, 1]);
-            record_progress();
-            native
-        })
-        .await;
-        assert_eq!([node.snapshot().active, a.snapshot().active, b.snapshot().active], [0, 1, 0]);
-        assert_eq!([node.completed(), a.completed(), b.completed()], [Some(1), Some(1), Some(1)]);
-        drop(native);
-        assert_eq!(a.snapshot().active, 0);
-    }
-
-    #[tokio::test]
-    async fn receiver_cancellation_returns_node_but_not_escaped_native_capacity() {
-        let node = node();
-        let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-        let binding = PhysicalDiskBinding::default();
-        binding.set_test_capacity(vec![gate.clone()]).expect("device plan");
-        let (sender, receiver) = tokio::sync::oneshot::channel();
-        let task = tokio::spawn(with_remote_background_io(Some(RemoteBackgroundIo::new(node.clone())), async move {
-            admit(&binding).expect("receiver admission");
-            let admitted = resources().expect("receiver resources");
-            let native = binding
-                .plan()
-                .expect("plan")
-                .capture_native(admitted.as_set().expect("set"))
-                .expect("native subset");
-            sender.send(native).expect("native owner receiver");
-            record_progress();
-            std::future::pending::<()>().await;
-        }));
-        let native = receiver.await.expect("native read ownership");
-        task.abort();
-        assert!(task.await.expect_err("cancel request").is_cancelled());
-        assert_eq!([node.snapshot().active, gate.snapshot().active], [0, 1]);
-        assert_eq!([node.completed(), gate.completed()], [Some(0), Some(0)]);
-        drop(native);
-        assert_eq!(gate.snapshot().active, 0);
-    }
-
-    #[tokio::test]
-    async fn receiver_defers_stream_progress_without_retaining_node_capacity() {
-        for (progressed, succeeds) in [(false, true), (true, false), (true, true)] {
-            let node = node();
-            let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-            let binding = PhysicalDiskBinding::default();
-            binding.set_test_capacity(vec![gate.clone()]).expect("device plan");
-            let completion = with_remote_background_io(Some(RemoteBackgroundIo::new(node.clone())), async {
-                admit(&binding).expect("receiver admission");
-                if progressed {
-                    record_progress();
-                }
-                let completion = RemoteBackgroundIo::take_current_completion();
-                assert!(RemoteBackgroundIo::take_current_completion().is_none(), "single progress owner");
-                assert!(resources().is_none());
-                completion
-            })
-            .await;
-            assert_eq!([node.snapshot().active, gate.snapshot().active], [0, 0]);
-            assert_eq!([node.completed(), gate.completed()], [Some(0), Some(0)]);
-            assert_eq!(completion.is_some(), progressed);
-            if succeeds && let Some(completion) = completion {
-                completion.complete();
-            }
-            let expected = u64::from(progressed && succeeds);
-            assert_eq!([node.completed(), gate.completed()], [Some(expected), Some(expected)]);
-        }
-        assert!(
-            RemoteBackgroundIo::take_current_completion().is_none(),
-            "foreground has no progress owner"
-        );
-    }
-
-    #[tokio::test]
-    async fn receiver_failed_completion_does_not_credit_successful_preparation() {
-        let node = node();
-        let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
-        let binding = PhysicalDiskBinding::default();
-        binding.set_test_capacity(vec![gate.clone()]).expect("device plan");
-        with_remote_background_io(Some(RemoteBackgroundIo::new(node.clone())), async {
-            admit(&binding).expect("receiver admission");
-            record_progress();
-            RemoteBackgroundIo::discard_current_progress();
-        })
-        .await;
-        assert_eq!([node.snapshot().active, gate.snapshot().active], [0, 0]);
-        assert_eq!([node.completed(), gate.completed()], [Some(0), Some(0)]);
-    }
-
-    #[tokio::test]
-    async fn receiver_stream_transfer_moves_node_ownership_and_defers_unavailable_devices() {
-        let node = node();
-        let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 0);
-        let binding = PhysicalDiskBinding::default();
-        binding.set_test_capacity(vec![gate.clone()]).expect("device plan");
-        let context = with_remote_background_io(Some(RemoteBackgroundIo::new(node.clone())), async {
-            assert_eq!(admit(&binding).expect_err("closed device").kind(), io::ErrorKind::WouldBlock);
-            assert_eq!([node.snapshot().active, gate.snapshot().active], [0, 0]);
-            gate.set_limit(1);
-            admit(&binding).expect("opened device");
-            let context = RemoteBackgroundIo::take_current().expect("stream context");
-            assert!(resources().is_none(), "request cannot keep a second node owner");
-            context
-        })
-        .await;
-        assert_eq!([node.snapshot().active, gate.snapshot().active], [1, 1]);
-        assert_eq!(node.completed(), Some(0));
-        with_remote_background_io(Some(context), async {
-            admit(&binding).expect("stream reuses the request's receipt");
-            binding
-                .set_test_capacity(vec![AdaptiveAdmission::new(NonZeroU16::MIN, 1)])
-                .expect("replace physical device");
-            assert_eq!(
-                admit(&binding).expect_err("old receipt cannot cross topology").kind(),
-                io::ErrorKind::WouldBlock
-            );
-        })
-        .await;
-        assert_eq!([node.snapshot().active, gate.snapshot().active], [0, 0]);
-        assert_eq!(node.completed(), Some(0), "admission alone is not completed work");
-    }
-}

crates/ecstore/src/disk/local/commit.rs

@@ -28,7 +28,7 @@ use super::{
     should_remove_staged_meta_before_commit, skip_access_checks, tmp_staging_mutation_path,
 };
 #[cfg(test)]
-use super::{run_inline_before_file_sync_admission, run_owned_file_before_open, run_rename_data_after_first_publication};
+use super::{run_inline_before_file_sync_admission, run_owned_file_write_before_open, run_rename_data_after_first_publication};
 use crate::crash_inject::{self, CrashPoint};
 use crate::disk::{
     QUOTA_MUTATION_FENCE_METADATA_SUFFIX, RenameDataResp, STORAGE_FORMAT_FILE, STORAGE_FORMAT_FILE_BACKUP, SnapshotLeaseToken,
@@ -175,30 +175,17 @@ pub(super) fn create_local_inline_rollback_backup(
     dst_file_path: &Path,
     staging_file_path: &Path,
     old_metadata: &[u8],
-    sync: bool,
 ) -> std::io::Result<PathBuf> {
     let Some(staging_parent) = staging_file_path.parent() else {
         return Err(std::io::Error::new(ErrorKind::InvalidInput, "missing staging metadata parent"));
     };
     let backup_path = staging_parent.join(STORAGE_FORMAT_FILE_BACKUP);
     remove_file_if_exists(&backup_path)?;
-    if should_fail_local_inline_rollback_hardlink(dst_file_path) || std::fs::hard_link(dst_file_path, &backup_path).is_err() {
-        let write_res = (|| -> std::io::Result<()> {
-            #[cfg(test)]
-            run_owned_file_before_open(&backup_path);
-            let mut file = std::fs::File::create(&backup_path)?;
-            std::io::Write::write_all(&mut file, old_metadata)?;
-            if sync && !old_metadata.is_empty() {
-                file.sync_data()?;
-            }
-            Ok(())
-        })();
-        if let Err(err) = write_res {
-            let _ = remove_file_if_exists(&backup_path);
-            return Err(err);
-        }
-    } else if sync && !old_metadata.is_empty() {
-        std::fs::File::open(&backup_path)?.sync_data()?;
+    if (should_fail_local_inline_rollback_hardlink(dst_file_path) || std::fs::hard_link(dst_file_path, &backup_path).is_err())
+        && let Err(err) = std::fs::write(&backup_path, old_metadata)
+    {
+        let _ = remove_file_if_exists(&backup_path);
+        return Err(err);
     }
     Ok(backup_path)
 }
@@ -342,41 +329,6 @@ pub(super) async fn lock_rename_commit_directories(
     result.map_err(to_file_error).map_err(DiskError::from)
 }
 
-#[cfg(target_os = "linux")]
-fn prepare_rename_commit_and_destination_metadata_std(
-    create_source_parent: bool,
-    source_parent: &Path,
-    destination_parent: &Path,
-    destination_metadata: &Path,
-    base_dir: &Path,
-    publication_root: &os::PublicationRoot,
-) -> std::io::Result<(os::RenameCommitGuard, Option<Bytes>)> {
-    if create_source_parent {
-        std::fs::create_dir_all(source_parent)?;
-    }
-    let guard = match os::prepare_rename_commit_guard(source_parent, destination_parent, base_dir, publication_root) {
-        Ok(guard) => guard,
-        Err(err) => {
-            return Err(match std::fs::symlink_metadata(base_dir) {
-                Err(base_err) if base_err.kind() == ErrorKind::NotFound => base_err,
-                _ => err,
-            });
-        }
-    };
-    let data = os::read_destination_file_with_commit_guard(destination_metadata, &guard)?;
-    Ok((guard, data.map(Bytes::from)))
-}
-
-#[cfg(target_os = "linux")]
-enum FusedCommitAttempt {
-    Committed(Box<RenameDataResp>),
-    CommitErr(DiskError),
-    RestoreDataSource(os::RenameCommitGuard, DiskError),
-    Fallback(os::RenameCommitGuard, Option<Bytes>, Box<FileInfo>),
-    #[cfg(test)]
-    ResumePanic(Box<dyn std::any::Any + Send + 'static>),
-}
-
 async fn prepare_rename_commit_and_destination_metadata(
     create_source_parent: bool,
     source_parent: &Path,
@@ -556,9 +508,7 @@ impl LocalDisk {
             None
         };
         let multipart_publication = if let Some(staging) = multipart_staging.as_ref() {
-            Some(Arc::new(
-                pin_multipart_future(|| self.prepare_native_multipart_publication_deferred(src_path, &mut fi, staging)).await?,
-            ))
+            Some(pin_multipart_future(|| self.prepare_native_multipart_publication(src_path, &mut fi, staging)).await?)
         } else {
             None
         };
@@ -621,9 +571,6 @@ impl LocalDisk {
                 return Err(err);
             }
         }
-        if dst_volume == crate::disk::RUSTFS_META_BUCKET {
-            crate::bucket::metadata_sys::bump_local_meta_mutation_gen();
-        }
         if fi.is_legacy_indexed_delete_marker() {
             fi.erasure.index = 0;
         }
@@ -751,624 +698,6 @@ impl LocalDisk {
         let dst_file_parent = dst_file_path
             .parent()
             .ok_or_else(|| DiskError::other("missing object metadata parent"))?;
-
-        #[cfg(target_os = "linux")]
-        let (rename_commit_guard, has_dst_buf) = if !preserve_upload_metadata
-            && multipart_publication.is_none()
-            && pool_meta_condition.is_none()
-            && !fi_healing
-            && !os::dst_dir_fsync_group_commit_enabled()
-            && !os::file_fdatasync_group_commit_enabled()
-        {
-            #[cfg(test)]
-            if !no_inline {
-                run_inline_before_file_sync_admission(dst_path);
-            }
-            let sync_data_shards = no_inline && durability.syncs_data_shards();
-            let sync_commit_metadata = durability.syncs_commit_metadata();
-            let file_sync_admission = if sync_data_shards || sync_commit_metadata {
-                Some(
-                    os::acquire_file_sync_admission(self.file_sync_permits.clone())
-                        .await
-                        .map_err(to_file_error)
-                        .map_err(DiskError::from)?,
-                )
-            } else {
-                None
-            };
-            let src_parent_owned = src_file_parent.to_path_buf();
-            let dst_parent_owned = dst_file_parent.to_path_buf();
-            let src_file_path_owned = src_file_path.clone();
-            let dst_file_path_owned = dst_file_path.clone();
-            let dst_volume_dir_owned = dst_volume_dir.clone();
-            let publication_root_owned = self.publication_root.clone();
-            let has_data_dir_path_owned = has_data_dir_path.clone();
-            let dst_volume_str = dst_volume.to_string();
-            let dst_path_str = dst_path.to_string();
-            let fi_moved = fi;
-            #[cfg(test)]
-            let root_owned = self.root.clone();
-
-            let fused_attempt = move |is_cancelled: &dyn Fn() -> bool| -> std::io::Result<FusedCommitAttempt> {
-                let (guard, has_dst_buf) = prepare_rename_commit_and_destination_metadata_std(
-                    !no_inline,
-                    &src_parent_owned,
-                    &dst_parent_owned,
-                    &dst_file_path_owned,
-                    &dst_volume_dir_owned,
-                    &publication_root_owned,
-                )?;
-                // An existing xl.meta that replaces an existing version slot
-                // requires a rollback directory; appending a new version keeps
-                // an inline rollback backup for post-rename directory sync errors.
-                if is_cancelled() {
-                    return Ok(FusedCommitAttempt::Fallback(guard, has_dst_buf, Box::new(fi_moved)));
-                }
-                let mut xlmeta = FileMeta::new();
-                let mut dst_meta_unparsable = false;
-                if let Some(ref dst_buf) = has_dst_buf {
-                    if FileMeta::is_xl2_v1_format(dst_buf)
-                        && let Ok(nmeta) = FileMeta::load(dst_buf)
-                    {
-                        xlmeta = nmeta;
-                    } else {
-                        dst_meta_unparsable = true;
-                    }
-                }
-                let version_id = fi_moved.version_id.unwrap_or_default();
-                let has_old_data_dir = xlmeta.find_unshared_data_dir_for_version(Some(version_id));
-                let rollback_data_dir = has_old_data_dir.or_else(|| {
-                    if has_dst_buf.is_some() && xlmeta.find_version(Some(version_id)).is_ok() {
-                        Some(inline_metadata_rollback_dir(version_id, &xlmeta))
-                    } else {
-                        None
-                    }
-                });
-                if rollback_data_dir.is_some() {
-                    return Ok(FusedCommitAttempt::Fallback(guard, has_dst_buf, Box::new(fi_moved)));
-                }
-                #[cfg(test)]
-                let probe_active = os::file_sync_probe::is_active();
-                #[cfg(not(test))]
-                let probe_active = false;
-                if no_inline
-                    && sync_data_shards
-                    && let Some((src_data_path, _)) = has_data_dir_path_owned.as_ref()
-                    && (probe_active || !super::is_presynced_tmp_data_dir(src_data_path))
-                    && os::regular_files(src_data_path).is_ok_and(|files| files.len() >= os::PARALLEL_FILE_SYNC_THRESHOLD)
-                {
-                    return Ok(FusedCommitAttempt::Fallback(guard, has_dst_buf, Box::new(fi_moved)));
-                }
-                let (old_current_size, old_current_source_checked, old_current_source) = observe_old_current(
-                    has_dst_buf.is_some(),
-                    dst_meta_unparsable,
-                    &xlmeta,
-                    &dst_volume_str,
-                    &dst_path_str,
-                    version_id,
-                );
-                xlmeta.add_version(fi_moved)?;
-                let version_signature = rename_data_versions_signature(&xlmeta);
-                let new_dst_buf = xlmeta.marshal_msg().map_err(std::io::Error::other)?;
-                let destination_was_absent = has_dst_buf.is_none();
-                let mut skip_parent = dst_volume_dir_owned.clone();
-                if has_dst_buf.is_some() {
-                    skip_parent = dst_parent_owned.clone();
-                }
-
-                #[cfg(test)]
-                run_owned_file_before_open(&src_file_path_owned);
-                let mut prepared_metadata_source =
-                    os::create_prepared_rename_source_with_commit_guard(&src_file_path_owned, &dst_file_path_owned, &guard)?;
-                prepared_metadata_source.write_all(&new_dst_buf, false)?;
-                if !no_inline {
-                    run_inline_preparation_before_backup(&dst_path_str);
-                }
-
-                let mut staged_rollback_path = None;
-                if let Some(ref old_metadata) = has_dst_buf
-                    && (sync_commit_metadata || cfg!(test))
-                {
-                    let backup_path = create_local_inline_rollback_backup(
-                        &dst_file_path_owned,
-                        &src_file_path_owned,
-                        old_metadata,
-                        sync_commit_metadata,
-                    )?;
-                    staged_rollback_path = Some(StagedRollbackBackup(backup_path));
-                }
-
-                if no_inline {
-                    if sync_data_shards && let Some((src_data_path, _)) = has_data_dir_path_owned.as_ref() {
-                        let sync_result = if !probe_active && super::take_presynced_tmp_data_dir(src_data_path) {
-                            // The payload was synced, but its part.1 directory entry
-                            // must also be persisted before moving the data directory.
-                            os::fsync_dir_std(src_data_path)
-                        } else {
-                            os::sync_dir_files_std(src_data_path)
-                        };
-                        if let Err(err) = sync_result
-                            && err.kind() != ErrorKind::NotFound
-                        {
-                            if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                                let _ = remove_file_if_exists(backup_path);
-                            }
-                            return Err(err);
-                        }
-                    }
-                    if sync_commit_metadata && let Err(err) = prepared_metadata_source.sync_data() {
-                        if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                            let _ = remove_file_if_exists(backup_path);
-                        }
-                        return Err(err);
-                    }
-                } else if sync_commit_metadata && let Err(err) = prepared_metadata_source.sync_data() {
-                    if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                        let _ = remove_file_if_exists(backup_path);
-                    }
-                    return Err(err);
-                }
-
-                if is_cancelled() {
-                    drop(prepared_metadata_source);
-                    if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                        let _ = remove_file_if_exists(backup_path);
-                    }
-                    return Err(std::io::Error::new(ErrorKind::Interrupted, "commit cancelled"));
-                }
-
-                let guard = match super::remove_dst_base_before_commit_std(
-                    &dst_path_str,
-                    guard,
-                    &src_parent_owned,
-                    &dst_parent_owned,
-                    &dst_volume_dir_owned,
-                    &publication_root_owned,
-                ) {
-                    Ok(guard) => guard,
-                    Err(err) => {
-                        if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                            let _ = remove_file_if_exists(backup_path);
-                        }
-                        return Ok(FusedCommitAttempt::CommitErr(err));
-                    }
-                };
-                if should_remove_staged_meta_before_commit(&dst_path_str) {
-                    drop(prepared_metadata_source);
-                    if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                        let _ = remove_file_if_exists(backup_path);
-                    }
-                    std::fs::remove_file(&src_file_path_owned)?;
-                    return Ok(FusedCommitAttempt::CommitErr(DiskError::FileNotFound));
-                }
-
-                if no_inline {
-                    if let Some((src_data_path, dst_data_path)) = has_data_dir_path_owned.as_ref()
-                        && let Err(err) = os::rename_all_with_commit_guard_on_thread(src_data_path, dst_data_path, &guard)
-                    {
-                        if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                            let _ = remove_file_if_exists(backup_path);
-                        }
-                        return Ok(FusedCommitAttempt::RestoreDataSource(guard, err));
-                    }
-                    #[cfg(test)]
-                    if has_data_dir_path_owned.is_some()
-                        && let Err(panic_payload) = std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| {
-                            run_rename_data_after_first_publication(&root_owned, &dst_volume_str, &dst_path_str);
-                        }))
-                    {
-                        return Ok(FusedCommitAttempt::ResumePanic(panic_payload));
-                    }
-                    if crash_inject::should_crash_at(CrashPoint::RenameAfterDataRename, &dst_path_str) {
-                        return Ok(FusedCommitAttempt::CommitErr(DiskError::Unexpected));
-                    }
-                    if should_fail_before_old_metadata_backup(&dst_path_str) {
-                        if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                            let _ = remove_file_if_exists(backup_path);
-                        }
-                        return Ok(FusedCommitAttempt::RestoreDataSource(guard, DiskError::Unexpected));
-                    }
-                    if crash_inject::should_crash_at(CrashPoint::RenameAfterBackupBeforeMetaCommit, &dst_path_str) {
-                        return Ok(FusedCommitAttempt::CommitErr(DiskError::Unexpected));
-                    }
-                }
-
-                let rename_res = if should_fail_commit_rename(&dst_path_str) {
-                    drop(prepared_metadata_source);
-                    Err(DiskError::other("test fail during metadata commit rename"))
-                } else {
-                    os::rename_prepared_source_on_thread(
-                        prepared_metadata_source,
-                        &src_file_path_owned,
-                        &dst_file_path_owned,
-                        &skip_parent,
-                        &publication_root_owned,
-                        &guard,
-                    )
-                };
-                if let Err(err) = rename_res {
-                    if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                        let _ = remove_file_if_exists(backup_path);
-                    }
-                    if no_inline {
-                        return Ok(FusedCommitAttempt::RestoreDataSource(guard, err));
-                    }
-                    return Ok(FusedCommitAttempt::CommitErr(err));
-                }
-
-                if should_fail_after_metadata_commit(&dst_path_str) {
-                    if no_inline {
-                        rollback_inline_metadata_std(&dst_file_path_owned, None, staged_rollback_path.as_ref())?;
-                        if let Some((_, new_data_path)) = has_data_dir_path_owned.as_ref() {
-                            remove_dir_all_if_exists(new_data_path)?;
-                        }
-                        return Ok(FusedCommitAttempt::CommitErr(DiskError::Unexpected));
-                    }
-                    let err = rollback_inline_metadata_std(&dst_file_path_owned, None, staged_rollback_path.as_ref())
-                        .err()
-                        .unwrap_or_else(|| std::io::Error::other("test fail after metadata commit"));
-                    return Ok(FusedCommitAttempt::CommitErr(DiskError::from(err)));
-                }
-
-                if crash_inject::should_crash_at(CrashPoint::RenameAfterMetaCommit, &dst_path_str) {
-                    return Ok(FusedCommitAttempt::CommitErr(DiskError::Unexpected));
-                }
-
-                if sync_commit_metadata
-                    && let Err(err) = fsync_inline_commit_std(
-                        &dst_file_path_owned,
-                        &dst_volume_dir_owned,
-                        destination_was_absent,
-                        staged_rollback_path.as_ref(),
-                        &guard,
-                    )
-                {
-                    if no_inline {
-                        if let Some((_, new_data_path)) = has_data_dir_path_owned.as_ref() {
-                            remove_dir_all_if_exists(new_data_path)?;
-                        }
-                        return Ok(FusedCommitAttempt::CommitErr(to_file_error(err).into()));
-                    }
-                    return Ok(FusedCommitAttempt::CommitErr(DiskError::from(err)));
-                }
-
-                if let Some(backup_path) = staged_rollback_path.as_ref().map(StagedRollbackBackup::path) {
-                    let _ = remove_file_if_exists(backup_path);
-                }
-
-                if let Some(parent) = src_file_path_owned.parent() {
-                    let _ = std::fs::remove_dir(parent);
-                }
-
-                Ok(FusedCommitAttempt::Committed(Box::new(RenameDataResp {
-                    multipart_source: None,
-                    old_data_dir: None,
-                    rollback_data_dir: None,
-                    cleanup_data_dir: None,
-                    sign: version_signature,
-                    old_current_size,
-                    old_current_source_checked,
-                    old_current_source,
-                })))
-            };
-
-            let attempt_res = if let Some(admission) = file_sync_admission.as_ref() {
-                os::run_cancellable_blocking_namespace_file_sync_operation(mutation_lease.clone(), admission, fused_attempt).await
-            } else {
-                os::run_cancellable_blocking_namespace_operation(mutation_lease.clone(), fused_attempt).await
-            }
-            .map_err(to_file_error)
-            .map_err(DiskError::from);
-            drop(file_sync_admission);
-            match attempt_res {
-                Ok(FusedCommitAttempt::Committed(resp)) => {
-                    for part_path in &invalidate_part_paths {
-                        self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                    }
-                    #[cfg(unix)]
-                    if let Some(receipt_mutation) = receipt_mutation.as_mut() {
-                        receipt_mutation.complete();
-                    }
-                    return Ok(*resp);
-                }
-                Ok(FusedCommitAttempt::RestoreDataSource(directory_guard, err)) => {
-                    let commit = RenameCommitContext {
-                        directory_guard,
-                        publication_root: &self.publication_root,
-                        mutation_lease,
-                        source_metadata: &src_file_path,
-                        destination_metadata: &dst_file_path,
-                        source_volume_dir: &src_volume_dir,
-                        data_paths: has_data_dir_path.as_ref(),
-                    };
-                    commit.restore_published_data_source().await?;
-                    for part_path in &invalidate_part_paths {
-                        self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                    }
-                    return Err(err);
-                }
-                Ok(FusedCommitAttempt::CommitErr(err)) | Err(err) => {
-                    for part_path in &invalidate_part_paths {
-                        self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                    }
-                    return Err(err);
-                }
-                #[cfg(test)]
-                Ok(FusedCommitAttempt::ResumePanic(panic_payload)) => {
-                    std::panic::resume_unwind(panic_payload);
-                }
-                Ok(FusedCommitAttempt::Fallback(guard, dst_buf, restored_fi)) => {
-                    fi = *restored_fi;
-                    (guard, dst_buf)
-                }
-            }
-        } else if let Some(publication) = multipart_publication.as_ref()
-            && no_inline
-            && !preserve_upload_metadata
-            && !publication.legacy
-            && !fi_healing
-            && !os::dst_dir_fsync_group_commit_enabled()
-        {
-            enum MultipartFusedCommitOutcome {
-                Committed(Box<RenameDataResp>),
-                AbortBeforeDataRename(DiskError),
-                RestoreDataSource(os::RenameCommitGuard, DiskError),
-                RestoreTargetAfterError(DiskError, bool),
-            }
-            let publication_owned = Arc::clone(publication);
-            let src_parent_owned = src_file_parent.to_path_buf();
-            let dst_parent_owned = dst_file_parent.to_path_buf();
-            let dst_file_path_owned = dst_file_path.clone();
-            let src_file_path_owned = src_file_path.clone();
-            let dst_volume_dir_owned = dst_volume_dir.clone();
-            let publication_root_owned = self.publication_root.clone();
-            let has_data_dir_path_owned = has_data_dir_path.clone();
-            let sync_data_shards = durability.syncs_data_shards();
-            let sync_commit_metadata = durability.syncs_commit_metadata();
-            let staging_cleanup = multipart_staging.as_ref().map(|s| s.cleanup_handle());
-            let dst_volume_str = dst_volume.to_string();
-            let dst_path_str = dst_path.to_string();
-            let fi_moved = fi;
-            #[cfg(test)]
-            let root_owned = self.root.clone();
-
-            let outcome = os::run_blocking_namespace_operation_with_sync(
-                mutation_lease.clone(),
-                true,
-                move || -> std::io::Result<MultipartFusedCommitOutcome> {
-                    let (directory_guard_owned, has_dst_buf_owned) = match prepare_rename_commit_and_destination_metadata_std(
-                        false,
-                        &src_parent_owned,
-                        &dst_parent_owned,
-                        &dst_file_path_owned,
-                        &dst_volume_dir_owned,
-                        &publication_root_owned,
-                    ) {
-                        Ok(res) => res,
-                        Err(err) => return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(to_file_error(err).into())),
-                    };
-                    let mut xlmeta = FileMeta::new();
-                    let mut dst_meta_unparsable = false;
-                    if let Some(dst_buf) = has_dst_buf_owned.as_ref() {
-                        if FileMeta::is_xl2_v1_format(dst_buf)
-                            && let Ok(nmeta) = FileMeta::load(dst_buf)
-                        {
-                            xlmeta = nmeta;
-                        } else {
-                            dst_meta_unparsable = true;
-                        }
-                    }
-                    let skip_parent_owned = if has_dst_buf_owned.is_some() {
-                        dst_parent_owned.clone()
-                    } else {
-                        dst_volume_dir_owned.clone()
-                    };
-                    let version_id = fi_moved.version_id.unwrap_or_default();
-                    let (old_current_size, old_current_source_checked, old_current_source) = observe_old_current(
-                        has_dst_buf_owned.is_some(),
-                        dst_meta_unparsable,
-                        &xlmeta,
-                        &dst_volume_str,
-                        &dst_path_str,
-                        version_id,
-                    );
-                    let has_old_data_dir = xlmeta.find_unshared_data_dir_for_version(Some(version_id));
-                    if let Some(old_data_dir) = has_old_data_dir.as_ref() {
-                        let _ = xlmeta.data.remove_two(version_id, *old_data_dir);
-                    }
-                    if let Err(err) = xlmeta.add_version(fi_moved) {
-                        return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(err.into()));
-                    }
-                    let version_signature = rename_data_versions_signature(&xlmeta);
-                    let new_dst_buf_owned = match xlmeta.marshal_msg() {
-                        Ok(buf) => buf,
-                        Err(err) => return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(err.into())),
-                    };
-
-                    let prepared_metadata_source = match publication_owned.prepare_and_install_head_on_thread(
-                        &new_dst_buf_owned,
-                        has_dst_buf_owned.as_deref(),
-                        &dst_file_path_owned,
-                        &directory_guard_owned,
-                    ) {
-                        Ok(source) => source,
-                        Err(err) => return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(err)),
-                    };
-                    #[cfg(test)]
-                    let probe_active = os::file_sync_probe::is_active();
-                    #[cfg(not(test))]
-                    let probe_active = false;
-                    // When presynced, shard payloads were synced during UploadPart and
-                    // prepare_and_install_head_on_thread just fsynced src_data_path after
-                    // writing RETIREMENT_ANCHOR.
-                    if sync_data_shards
-                        && let Some((src_data_path, _)) = has_data_dir_path_owned.as_ref()
-                        && (probe_active || !super::take_presynced_tmp_data_dir(src_data_path))
-                        && let Err(err) = os::sync_dir_files_std(src_data_path)
-                        && err.kind() != ErrorKind::NotFound
-                    {
-                        return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(to_file_error(err).into()));
-                    }
-                    let directory_guard_owned = match super::remove_dst_base_before_commit_std(
-                        &dst_path_str,
-                        directory_guard_owned,
-                        &src_parent_owned,
-                        &dst_parent_owned,
-                        &dst_volume_dir_owned,
-                        &publication_root_owned,
-                    ) {
-                        Ok(guard) => guard,
-                        Err(err) => return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(err)),
-                    };
-                    if should_remove_staged_meta_before_commit(&dst_path_str) {
-                        drop(prepared_metadata_source);
-                        if let Err(err) = std::fs::remove_file(&src_file_path_owned) {
-                            return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(to_file_error(err).into()));
-                        }
-                        return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(DiskError::FileNotFound));
-                    }
-                    if let Some((src_data_path, dst_data_path)) = has_data_dir_path_owned.as_ref() {
-                        let Some(src_parent) = src_data_path.parent() else {
-                            return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(DiskError::InvalidPath));
-                        };
-                        let payload_guard = match os::multipart_payload_commit_guard_std(&directory_guard_owned, src_parent) {
-                            Ok(guard) => guard,
-                            Err(err) => return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(to_file_error(err).into())),
-                        };
-                        if let Err(err) = os::rename_all_with_commit_guard_on_thread(src_data_path, dst_data_path, &payload_guard)
-                        {
-                            return Ok(MultipartFusedCommitOutcome::RestoreDataSource(directory_guard_owned, err));
-                        }
-                        #[cfg(test)]
-                        run_rename_data_after_first_publication(&root_owned, &dst_volume_str, &dst_path_str);
-                        if crash_inject::should_crash_at(CrashPoint::RenameAfterDataRename, &dst_path_str) {
-                            return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(DiskError::Unexpected));
-                        }
-                        if should_fail_before_old_metadata_backup(&dst_path_str) {
-                            return Ok(MultipartFusedCommitOutcome::RestoreDataSource(
-                                directory_guard_owned,
-                                DiskError::Unexpected,
-                            ));
-                        }
-                        if crash_inject::should_crash_at(CrashPoint::RenameAfterBackupBeforeMetaCommit, &dst_path_str) {
-                            return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(DiskError::Unexpected));
-                        }
-                    }
-                    let rename_res = if should_fail_commit_rename(&dst_path_str) {
-                        drop(prepared_metadata_source);
-                        Err(DiskError::other("test fail during metadata commit rename"))
-                    } else {
-                        os::rename_prepared_source_on_thread(
-                            prepared_metadata_source,
-                            &src_file_path_owned,
-                            &dst_file_path_owned,
-                            &skip_parent_owned,
-                            &publication_root_owned,
-                            &directory_guard_owned,
-                        )
-                    };
-                    if let Err(err) = rename_res {
-                        return Ok(MultipartFusedCommitOutcome::RestoreDataSource(directory_guard_owned, err));
-                    }
-                    if should_fail_after_metadata_commit(&dst_path_str) {
-                        return Ok(MultipartFusedCommitOutcome::RestoreTargetAfterError(DiskError::Unexpected, false));
-                    }
-                    if crash_inject::should_crash_at(CrashPoint::RenameAfterMetaCommit, &dst_path_str) {
-                        return Ok(MultipartFusedCommitOutcome::AbortBeforeDataRename(DiskError::Unexpected));
-                    }
-                    if sync_commit_metadata {
-                        if let Some(parent) = dst_file_path_owned.parent()
-                            && let Err(err) = os::fsync_commit_directory_limited_std(parent, &directory_guard_owned)
-                        {
-                            return Ok(MultipartFusedCommitOutcome::RestoreTargetAfterError(to_file_error(err).into(), true));
-                        }
-                        if has_dst_buf_owned.is_none() {
-                            let mut ancestor = dst_file_path_owned.parent().and_then(|object_dir| object_dir.parent());
-                            while let Some(dir) = ancestor {
-                                if !dir.starts_with(&dst_volume_dir_owned) {
-                                    break;
-                                }
-                                if let Err(err) = os::fsync_dir_limited_std(dir) {
-                                    return Ok(MultipartFusedCommitOutcome::RestoreTargetAfterError(
-                                        to_file_error(err).into(),
-                                        true,
-                                    ));
-                                }
-                                if dir == dst_volume_dir_owned.as_path() {
-                                    break;
-                                }
-                                ancestor = dir.parent();
-                            }
-                        }
-                    }
-                    match publication_owned.finish_on_thread(sync_commit_metadata, staging_cleanup) {
-                        Ok(result) => Ok(MultipartFusedCommitOutcome::Committed(Box::new(RenameDataResp {
-                            multipart_source: Some(Box::new(result)),
-                            old_data_dir: has_old_data_dir,
-                            rollback_data_dir: None,
-                            cleanup_data_dir: has_old_data_dir,
-                            sign: version_signature,
-                            old_current_size,
-                            old_current_source_checked,
-                            old_current_source,
-                        }))),
-                        Err(err) => Ok(MultipartFusedCommitOutcome::RestoreTargetAfterError(err, false)),
-                    }
-                },
-            )
-            .await
-            .map_err(to_file_error)
-            .map_err(DiskError::from)?;
-
-            match outcome {
-                MultipartFusedCommitOutcome::Committed(resp) => {
-                    for part_path in &invalidate_part_paths {
-                        self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                    }
-                    return Ok(*resp);
-                }
-                MultipartFusedCommitOutcome::AbortBeforeDataRename(err) => return Err(err),
-                MultipartFusedCommitOutcome::RestoreDataSource(directory_guard, err) => {
-                    let commit = RenameCommitContext {
-                        directory_guard,
-                        publication_root: &self.publication_root,
-                        mutation_lease,
-                        source_metadata: &src_file_path,
-                        destination_metadata: &dst_file_path,
-                        source_volume_dir: &src_volume_dir,
-                        data_paths: has_data_dir_path.as_ref(),
-                    };
-                    commit.restore_published_data_source().await?;
-                    return Err(err);
-                }
-                MultipartFusedCommitOutcome::RestoreTargetAfterError(err, invalidate_before_return) => {
-                    if !invalidate_before_return {
-                        for part_path in &invalidate_part_paths {
-                            self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                        }
-                    }
-                    pin_multipart_future(|| publication.restore_target_after_error(mutation_lease.clone())).await?;
-                    if invalidate_before_return {
-                        for part_path in &invalidate_part_paths {
-                            self.io_backend.invalidate_cached_fd(dst_volume, part_path).await;
-                        }
-                    }
-                    return Err(err);
-                }
-            }
-        } else {
-            prepare_rename_commit_and_destination_metadata(
-                !no_inline && !preserve_upload_metadata,
-                src_file_parent,
-                dst_file_parent,
-                &dst_file_path,
-                &dst_volume_dir,
-                &self.publication_root,
-                mutation_lease.clone(),
-            )
-            .await?
-        };
-        #[cfg(not(target_os = "linux"))]
         // Acquire the common trees before reading destination metadata. On
         // Windows this pins the object directory identity across publication.
         // Multipart authority already created its source tree. Recreating it
@@ -1479,81 +808,71 @@ impl LocalDisk {
             // after the commit rename, and a crash before the rename means the
             // PUT was never acknowledged. A metadata commit: relaxed tiers
             // leave it to the page cache.
-            #[cfg(all(test, target_os = "linux"))]
-            let probe_active = os::file_sync_probe::is_active();
-            #[cfg(all(not(test), target_os = "linux"))]
-            let probe_active = false;
+            if let Some(publication) = multipart_publication.as_ref() {
+                pin_multipart_future(|| publication.prepare_metadata(&new_dst_buf, has_dst_buf.as_deref())).await?;
+            }
+            let tmp_meta_sync = if durability.syncs_commit_metadata() || multipart_publication.is_some() {
+                SyncMode::FileOnly
+            } else {
+                SyncMode::None
+            };
+            // The tmp xl.meta write and the shard-file fdatasync are independent
+            // (disjoint paths) and both only need to be durable before the commit
+            // renames below, so run them concurrently to drop a blocking
+            // round-trip from the PUT commit critical path (rustfs/backlog#922
+            // step 2). The "contents durable -> rename -> dst dir fsync" ordering
+            // is unchanged — both futures complete before any rename — which the
+            // rename_data crash-consistency harness (backlog#935) exercises.
+            //
+            // Shard durability: once rename_data succeeds the write is
+            // acknowledged, so data must not live only in the page cache.
+            // Multipart parts were already synced during rename_part, so their
+            // fdatasync here is a cheap no-op. A missing source dir is left for the
+            // rename below to report through the existing rollback path. Payload
+            // durability is kept by both strict and relaxed.
+            let tmp_meta_write = {
+                let src_file_path = multipart_publication
+                    .as_ref()
+                    .map_or_else(|| commit.source_metadata.to_path_buf(), |publication| publication.prepared_path.clone());
+                let dst_file_path = dst_file_path.clone();
+                let owned_directory_guard = commit.directory_guard.clone();
+                let owned_mutation_lease = commit.mutation_lease.clone();
+                async move {
+                    os::run_blocking_namespace_operation(owned_mutation_lease, move || {
+                        #[cfg(test)]
+                        run_owned_file_write_before_open(&src_file_path);
+                        let mut prepared_metadata_source = os::create_prepared_rename_source_with_commit_guard(
+                            &src_file_path,
+                            &dst_file_path,
+                            &owned_directory_guard,
+                        )?;
+                        prepared_metadata_source.write_all(&new_dst_buf, tmp_meta_sync != SyncMode::None)?;
+                        Ok(prepared_metadata_source)
+                    })
+                    .await
+                    .map_err(to_file_error)
+                    .map_err(DiskError::from)
+                }
+            };
             let shard_sync = async {
                 if durability.syncs_data_shards()
                     && let Some((src_data_path, _)) = has_data_dir_path.as_ref()
+                    && let Err(err) = os::sync_dir_files_with_limiter(src_data_path, self.file_sync_permits.clone()).await
+                    && err.kind() != ErrorKind::NotFound
                 {
-                    #[cfg(target_os = "linux")]
-                    if !probe_active && super::take_presynced_tmp_data_dir(src_data_path) {
-                        if multipart_publication.is_none()
-                            && let Err(err) = os::fsync_dir_with_owner(src_data_path, Some(commit.mutation_lease.clone())).await
-                            && err.kind() != ErrorKind::NotFound
-                        {
-                            return Err::<(), DiskError>(to_file_error(err).into());
-                        }
-                        return Ok(());
-                    }
-                    if let Err(err) = os::sync_dir_files_with_limiter(src_data_path, self.file_sync_permits.clone()).await
-                        && err.kind() != ErrorKind::NotFound
-                    {
-                        return Err::<(), DiskError>(to_file_error(err).into());
-                    }
+                    return Err::<(), DiskError>(to_file_error(err).into());
                 }
                 Ok(())
             };
-            let prepared_metadata_source = if let Some(publication) = multipart_publication.as_ref() {
-                let dst_file_path_ref = &dst_file_path;
-                let dir_guard_ref = &commit.directory_guard;
-                let lease_clone = commit.mutation_lease.clone();
-                let prepare_fut = pin_multipart_future(|| {
-                    publication.prepare_and_install_head(
-                        &new_dst_buf,
-                        has_dst_buf.as_deref(),
-                        dst_file_path_ref,
-                        dir_guard_ref,
-                        lease_clone,
-                    )
-                });
-                let (tmp_meta_res, shard_sync_res) = tokio::join!(prepare_fut, shard_sync);
-                let prepared_metadata_source = tmp_meta_res?;
-                shard_sync_res?;
-                prepared_metadata_source
-            } else {
-                let tmp_meta_sync = if durability.syncs_commit_metadata() {
-                    SyncMode::FileOnly
-                } else {
-                    SyncMode::None
-                };
-                let tmp_meta_write = {
-                    let src_file_path = commit.source_metadata.to_path_buf();
-                    let dst_file_path = dst_file_path.clone();
-                    let owned_directory_guard = commit.directory_guard.clone();
-                    let owned_mutation_lease = commit.mutation_lease.clone();
-                    async move {
-                        os::run_blocking_namespace_operation(owned_mutation_lease, move || {
-                            #[cfg(test)]
-                            run_owned_file_before_open(&src_file_path);
-                            let mut prepared_metadata_source = os::create_prepared_rename_source_with_commit_guard(
-                                &src_file_path,
-                                &dst_file_path,
-                                &owned_directory_guard,
-                            )?;
-                            prepared_metadata_source.write_all(&new_dst_buf, tmp_meta_sync != SyncMode::None)?;
-                            Ok(prepared_metadata_source)
-                        })
-                        .await
-                        .map_err(to_file_error)
-                        .map_err(DiskError::from)
-                    }
-                };
-                let (tmp_meta_res, shard_sync_res) = tokio::join!(tmp_meta_write, shard_sync);
-                let prepared_metadata_source = tmp_meta_res?;
-                shard_sync_res?;
-                prepared_metadata_source
+            let (tmp_meta_res, shard_sync_res) = tokio::join!(tmp_meta_write, shard_sync);
+            // Surface a tmp-meta failure first (its prior serial position), then a
+            // shard-sync failure; either aborts before any rename, exactly as the
+            // sequential version did.
+            let prepared_metadata_source = tmp_meta_res?;
+            shard_sync_res?;
+            let prepared_metadata_source = match multipart_publication.as_ref() {
+                Some(publication) => pin_multipart_future(|| publication.install_head(prepared_metadata_source)).await?,
+                None => prepared_metadata_source,
             };
             commit.directory_guard = remove_dst_base_before_commit(
                 dst_path,
@@ -1707,7 +1026,7 @@ impl LocalDisk {
                 // deterministic rollback backup.
                 let write_result = os::run_blocking_namespace_operation(commit.mutation_lease.clone(), move || {
                     #[cfg(test)]
-                    run_owned_file_before_open(&backup_path);
+                    run_owned_file_write_before_open(&backup_path);
                     backup_path_guard.write_file_for_path_access(
                         &backup_path,
                         backup_bytes.as_ref(),
@@ -1893,22 +1212,13 @@ impl LocalDisk {
             }
 
             let multipart_source = match multipart_publication.as_ref() {
-                Some(publication) => {
-                    let target_already_synced = durability.syncs_commit_metadata();
-                    let staging_cleanup = multipart_staging.as_ref().map(|s| s.cleanup_handle());
-                    match pin_multipart_future(|| {
-                        publication.finish(commit.mutation_lease.clone(), target_already_synced, staging_cleanup)
-                    })
-                    .await
-                    {
-                        Ok(result) => Some(Box::new(result)),
-                        Err(error) => {
-                            pin_multipart_future(|| publication.restore_target_after_error(commit.mutation_lease.clone()))
-                                .await?;
-                            return Err(error);
-                        }
+                Some(publication) => match pin_multipart_future(|| publication.finish(commit.mutation_lease.clone())).await {
+                    Ok(result) => Some(Box::new(result)),
+                    Err(error) => {
+                        pin_multipart_future(|| publication.restore_target_after_error(commit.mutation_lease.clone())).await?;
+                        return Err(error);
                     }
-                }
+                },
                 None => None,
             };
             Ok(RenameDataResp {
@@ -2108,8 +1418,13 @@ impl LocalDisk {
                     #[cfg(not(windows))]
                     let backup_path = {
                         let _backup = os::StageTimer::new(native_timing, "pool_meta_native_backup_create");
-                        create_local_inline_rollback_backup(&dst, &src, old_metadata, sync)?
+                        create_local_inline_rollback_backup(&dst, &src, old_metadata)?
                     };
+                    #[cfg(not(windows))]
+                    if sync {
+                        let _backup_sync = os::StageTimer::new(native_timing, "pool_meta_native_backup_file_sync");
+                        std::fs::File::open(&backup_path)?.sync_data()?;
+                    }
                     staged_rollback_path = Some(StagedRollbackBackup(backup_path));
                 }
 

crates/ecstore/src/disk/local/multipart_source_abort.rs

@@ -421,7 +421,6 @@ impl LocalDisk {
                     return Err(DiskError::ConditionalDeleteConflict);
                 }
                 let permit = AbortDeletePermit::new(&store, &expected, certificate.clone())?;
-                super::multipart_source_state::invalidate_active_multipart_source_head(&store.source);
                 let destination = self.io_get_object_path(RUSTFS_META_TMP_DELETED_BUCKET, &Uuid::new_v4().to_string())?;
                 let source = store.source.clone();
                 let base = store.base.clone();
@@ -619,9 +618,6 @@ pub(super) struct OrdinaryMultipartDeleteCheck {
     root: os::PublicationRoot,
 }
 impl OrdinaryMultipartDeleteCheck {
-    pub(super) fn source(&self) -> &Path {
-        &self.source
-    }
     pub(super) fn validate(&self) -> Result<()> {
         let pinned = match os::pin_multipart_source_directory(&self.source, &self.base, &self.root) {
             Ok(pinned) => pinned,

crates/ecstore/src/disk/local/multipart_source_state.rs

@@ -238,192 +238,9 @@ pub(super) fn read_optional_in_pinned(
         Err(error) => Err(error.into()),
     }
 }
-#[derive(Clone, Copy, PartialEq, Eq)]
-struct FileStamp {
-    len: u64,
-    modified: Option<std::time::SystemTime>,
-    #[cfg(unix)]
-    ino: u64,
-}
-
-impl FileStamp {
-    fn from_path(path: &Path) -> Option<Self> {
-        let meta = std::fs::symlink_metadata(path).ok()?;
-        Some(Self {
-            len: meta.len(),
-            modified: meta.modified().ok(),
-            #[cfg(unix)]
-            ino: {
-                use std::os::unix::fs::MetadataExt;
-                meta.ino()
-            },
-        })
-    }
-}
-
-#[derive(Clone)]
-struct ActiveMultipartSourceEntry {
-    raw: Bytes,
-    fi: FileInfo,
-    head_stamp: FileStamp,
-    unsettled_parts: std::collections::HashSet<usize>,
-    parts: std::collections::HashMap<usize, (FileStamp, rustfs_filemeta::ObjectPartInfo)>,
-}
-
-static ACTIVE_MULTIPART_SOURCE_HEADS: std::sync::LazyLock<
-    parking_lot::Mutex<std::collections::HashMap<PathBuf, ActiveMultipartSourceEntry>>,
-> = std::sync::LazyLock::new(|| parking_lot::Mutex::new(std::collections::HashMap::new()));
-
-pub(super) fn put_active_multipart_source_head(source: PathBuf, raw: Bytes, fi: FileInfo) {
-    let Some(head_stamp) = FileStamp::from_path(&source.join(STORAGE_FORMAT_FILE)) else {
-        return;
-    };
-    let mut map = ACTIVE_MULTIPART_SOURCE_HEADS.lock();
-    if map.len() >= 4096
-        && let Some(evict_key) = map.keys().next().cloned()
-    {
-        map.remove(&evict_key);
-    }
-    map.insert(
-        source,
-        ActiveMultipartSourceEntry {
-            raw,
-            fi,
-            head_stamp,
-            unsettled_parts: std::collections::HashSet::new(),
-            parts: std::collections::HashMap::new(),
-        },
-    );
-}
-
-fn stamp_matches_active_disk(source: &Path, expected_head_stamp: FileStamp) -> bool {
-    FileStamp::from_path(&source.join(STORAGE_FORMAT_FILE)) == Some(expected_head_stamp)
-        && !source.join(STATE).exists()
-        && !source.join(crate::disk::MULTIPART_RECOVERY_DIR).exists()
-        && !source.join(".mpu-completions").exists()
-}
-
-pub(super) fn get_active_multipart_source_head(source: &Path) -> Option<(Bytes, FileInfo)> {
-    let (raw, fi, head_stamp) = {
-        let map = ACTIVE_MULTIPART_SOURCE_HEADS.lock();
-        let entry = map.get(source)?;
-        (entry.raw.clone(), entry.fi.clone(), entry.head_stamp)
-    };
-    if !stamp_matches_active_disk(source, head_stamp) {
-        ACTIVE_MULTIPART_SOURCE_HEADS.lock().remove(source);
-        return None;
-    }
-    Some((raw, fi))
-}
-
-pub(super) fn has_active_multipart_source_head(source: &Path) -> bool {
-    let Some(head_stamp) = ACTIVE_MULTIPART_SOURCE_HEADS.lock().get(source).map(|entry| entry.head_stamp) else {
-        return false;
-    };
-    if !stamp_matches_active_disk(source, head_stamp) {
-        ACTIVE_MULTIPART_SOURCE_HEADS.lock().remove(source);
-        return false;
-    }
-    true
-}
-
-pub(super) fn has_clean_active_multipart_source(source: &Path) -> bool {
-    let Some((head_stamp, clean)) = ACTIVE_MULTIPART_SOURCE_HEADS
-        .lock()
-        .get(source)
-        .map(|entry| (entry.head_stamp, entry.unsettled_parts.is_empty()))
-    else {
-        return false;
-    };
-    if !stamp_matches_active_disk(source, head_stamp) {
-        ACTIVE_MULTIPART_SOURCE_HEADS.lock().remove(source);
-        return false;
-    }
-    clean
-}
-
-pub(super) fn begin_active_multipart_part_transaction(source: &Path, part_number: usize) {
-    if let Some(entry) = ACTIVE_MULTIPART_SOURCE_HEADS.lock().get_mut(source) {
-        entry.unsettled_parts.insert(part_number);
-        entry.parts.remove(&part_number);
-    }
-}
-
-pub(super) fn record_active_multipart_part_committed(source: &Path, part: rustfs_filemeta::ObjectPartInfo) {
-    let Some(data_dir) = ACTIVE_MULTIPART_SOURCE_HEADS
-        .lock()
-        .get(source)
-        .and_then(|entry| entry.fi.data_dir)
-        .filter(|dir| !dir.is_nil())
-    else {
-        return;
-    };
-    let part_meta_path = source.join(data_dir.to_string()).join(format!("part.{}.meta", part.number));
-    let Some(part_stamp) = FileStamp::from_path(&part_meta_path) else {
-        return;
-    };
-    if let Some(entry) = ACTIVE_MULTIPART_SOURCE_HEADS.lock().get_mut(source) {
-        entry.parts.insert(part.number, (part_stamp, part));
-    }
-}
-
-pub(super) fn finish_active_multipart_part_transaction(
-    source: &Path,
-    part_number: Option<usize>,
-    committed: bool,
-    retired_existing_txn: bool,
-) {
-    let mut map = ACTIVE_MULTIPART_SOURCE_HEADS.lock();
-    let Some(part_number) = part_number.filter(|_| committed) else {
-        map.remove(source);
-        return;
-    };
-    if !retired_existing_txn {
-        return;
-    }
-    if let Some(entry) = map.get_mut(source)
-        && !entry.unsettled_parts.remove(&part_number)
-    {
-        map.remove(source);
-    }
-}
-
-pub(super) fn get_active_multipart_source_part(source: &Path, part_number: usize) -> Option<rustfs_filemeta::ObjectPartInfo> {
-    let (head_stamp, data_dir, expected_stamp, part) = {
-        let map = ACTIVE_MULTIPART_SOURCE_HEADS.lock();
-        let entry = map.get(source)?;
-        if !entry.unsettled_parts.is_empty() {
-            return None;
-        }
-        let data_dir = entry.fi.data_dir.filter(|dir| !dir.is_nil())?;
-        let (expected_stamp, part) = entry.parts.get(&part_number)?;
-        (entry.head_stamp, data_dir, *expected_stamp, part.clone())
-    };
-    if !stamp_matches_active_disk(source, head_stamp) {
-        ACTIVE_MULTIPART_SOURCE_HEADS.lock().remove(source);
-        return None;
-    }
-    let part_meta_path = source.join(data_dir.to_string()).join(format!("part.{part_number}.meta"));
-    if FileStamp::from_path(&part_meta_path) != Some(expected_stamp) {
-        return None;
-    }
-    Some(part)
-}
-
-pub(super) fn invalidate_active_multipart_source_head(source: &Path) {
-    ACTIVE_MULTIPART_SOURCE_HEADS.lock().remove(source);
-}
-
-pub(super) fn invalidate_active_multipart_sources_under(prefix: &Path) {
-    ACTIVE_MULTIPART_SOURCE_HEADS.lock().retain(|key, _| !key.starts_with(prefix));
-}
-
 /// Canonical source mutations are admitted under SourceRW at the syscall,
 /// not on the earlier async caller that may have timed out.
 pub(super) fn validate_source_mutation(source: &Path, base: &Path, root: &os::PublicationRoot, initial: bool) -> Result<()> {
-    if !initial && has_active_multipart_source_head(source) {
-        return Ok(());
-    }
     let pinned = match os::pin_multipart_source_directory(source, base, root) {
         Ok(pinned) => pinned,
         Err(error) if error.kind() == std::io::ErrorKind::NotFound => {
@@ -623,7 +440,6 @@ impl SourceStore {
         terminal: Option<&Path>,
         sync_source_before: bool,
     ) -> std::io::Result<()> {
-        invalidate_active_multipart_source_head(source);
         #[cfg(unix)]
         let mut pinned = os::pin_multipart_source_directory(source, base, root)?;
         #[cfg(not(unix))]
@@ -654,7 +470,7 @@ impl SourceStore {
         let terminal = terminal_record_path(&source, state);
         let bytes = bytes.to_vec();
         os::run_blocking_namespace_operation_with_sync(self.lease.clone(), true, move || {
-            Self::write_owned_backup_std(&source, &base, &root, owner, target, &bytes, false)?;
+            Self::write_owned_backup_std(&source, &base, &root, owner, target, &bytes)?;
             Self::persist_state_std(&source, &base, &root, &raw, terminal.as_deref(), false)
         })
         .await
@@ -723,7 +539,7 @@ impl SourceStore {
         let root = self.publication_root.clone();
         let bytes = bytes.to_vec();
         os::run_blocking_namespace_operation(self.lease.clone(), move || {
-            Self::write_owned_backup_std(&source, &base, &root, owner, target, &bytes, true)
+            Self::write_owned_backup_std(&source, &base, &root, owner, target, &bytes)
         })
         .await
         .map_err(DiskError::from)
@@ -735,7 +551,6 @@ impl SourceStore {
         owner: Uuid,
         target: bool,
         bytes: &[u8],
-        sync_source_root: bool,
     ) -> std::io::Result<()> {
         let path = if target {
             target_backup_path(source, owner)
@@ -767,10 +582,9 @@ impl SourceStore {
         if !existed {
             os::replace_multipart_source_metadata(&path, bytes, base, root)?;
         }
-        os::sync_multipart_owned_record_parents_options(source, parent, existed, sync_source_root, base, root)
+        os::sync_multipart_owned_record_parents(source, parent, existed, base, root)
     }
     pub async fn replace_head(&self, bytes: &[u8]) -> Result<()> {
-        invalidate_active_multipart_source_head(&self.source);
         let path = self.source.join(STORAGE_FORMAT_FILE);
         let base = self.base.clone();
         let root = self.publication_root.clone();
@@ -1283,82 +1097,6 @@ pub(super) fn load_source(
     })
 }
 
-fn load_uninitialized_source(
-    raw: Bytes,
-    path: &str,
-    disk_id: Uuid,
-    physical_slot: usize,
-    disk_ids: &[Uuid],
-) -> Result<LoadedSource> {
-    let sha = raw_sha(&raw);
-    let length = raw.len() as u64;
-    let current = get_file_info(
-        &raw,
-        RUSTFS_META_MULTIPART_BUCKET,
-        path,
-        "",
-        FileInfoOpts {
-            data: false,
-            include_free_versions: false,
-            include_part_checksums: true,
-        },
-    )
-    .map_err(Error::other)?;
-    native_source_protocol(&current)?;
-    if source_status(&current)?.is_some()
-        || publication_identity(&current)?.is_some()
-        || SourceConditionV1::take(&mut current.clone())?.is_some()
-    {
-        return Err(DiskError::FileCorrupt);
-    }
-    let bucket = rustfs_utils::http::metadata_compat::get_consistent_str(&current.metadata, "multipart-bucket")
-        .ok_or(DiskError::FileCorrupt)?;
-    let object = rustfs_utils::http::metadata_compat::get_consistent_str(&current.metadata, "multipart-object")
-        .ok_or(DiskError::FileCorrupt)?;
-    let condition = capture_source_condition(bucket, object, path, &current, current.data_dir.ok_or(DiskError::FileCorrupt)?)?;
-    if condition.generation.epoch != 0 {
-        return Err(DiskError::FileCorrupt);
-    }
-    let slot = condition
-        .lineage
-        .geometry
-        .distribution
-        .iter()
-        .position(|index| *index == current.erasure.index)
-        .ok_or(DiskError::FileCorrupt)?;
-    if slot != physical_slot || condition.lineage.geometry.disks() != disk_ids.len() {
-        return Err(DiskError::ConditionalDeleteConflict);
-    }
-    let inventory = raw_sha(&encode(&(None::<[u8; 32]>, Some(sha), sha, None::<[u8; 32]>, None::<[u8; 32]>))?);
-    let snapshot = Some(MultipartSourceSnapshot {
-        disk_id,
-        physical_slot: slot,
-        lineage: condition.lineage,
-        generation: condition.generation,
-        revision: 0,
-        phase: MultipartSourcePhase::Active,
-        state_sha256: [0; 32],
-        head_sha256: Some(sha),
-        inventory_sha256: inventory,
-        capability_sha256: None,
-        publication: None,
-    });
-    Ok(LoadedSource {
-        root_missing: false,
-        state: None,
-        head: Some(SourceHead {
-            sha256: sha,
-            length,
-            raw: Some(raw.clone()),
-        }),
-        original: Some(raw),
-        info: Some(current),
-        snapshot,
-        head_matches_state: true,
-        head_matches_activation: false,
-    })
-}
-
 pub(super) const RETIREMENT_ANCHOR: &str = ".mpu-source-retirement";
 
 #[derive(Serialize, Deserialize)]
@@ -1585,6 +1323,41 @@ impl LocalDisk {
 }
 
 impl SourceStore {
+    /// Only native source validation may create provenance. Ordinary TMP/heal
+    /// publication can retain a valid old local anchor, never issue/rebind one.
+    pub async fn write_retirement_anchor(
+        &self,
+        state: &SourceState,
+        publication: &PublicationIdentity,
+        directory: &Path,
+        lease: Arc<os::NamespaceMutationLease>,
+    ) -> Result<()> {
+        if state.lineage != publication.lineage
+            || state.generation != publication.source_generation
+            || state.disk_id != self.disk_id
+            || state.physical_slot != self.physical_slot
+        {
+            return Err(DiskError::ConditionalDeleteConflict);
+        }
+        let record = NativeRetirementAnchor {
+            protocol_version: MULTIPART_SOURCE_PROTOCOL_VERSION,
+            disk_id: self.disk_id,
+            physical_slot: self.physical_slot,
+            publication: publication.clone(),
+            source_original_sha256: state.original_sha256,
+            source_validation_receipt_id: state.backup_owner,
+        };
+        let bytes = encode(&record)?;
+        let directory = directory.to_path_buf();
+        let base = self.base.clone();
+        let root = self.publication_root.clone();
+        os::run_blocking_namespace_operation(lease, move || {
+            let _parent = os::mkdir_all_below_existing_base_std(&directory, &base, &root)?;
+            os::replace_multipart_source_metadata(&directory.join(RETIREMENT_ANCHOR), &bytes, &base, &root)
+        })
+        .await
+        .map_err(DiskError::from)
+    }
     /// This caller already owns SourceRW and destination metadata ownership.
     /// An Aborting survivor can confirm a historical target only with its
     /// independent, same-disk publication anchor. Closure never creates one.
@@ -1683,8 +1456,6 @@ struct ValidatedPreparedPublication {
     length: u64,
 }
 
-type DeferredInitialPublication = (Vec<u8>, PathBuf, Vec<u8>);
-
 pub(super) struct NativeMultipartPublication {
     pub store: Arc<SourceStore>,
     pub publication: PublicationIdentity,
@@ -1692,49 +1463,22 @@ pub(super) struct NativeMultipartPublication {
     state: parking_lot::Mutex<SourceState>,
     capability: parking_lot::Mutex<Option<MultipartUndoCapability>>,
     validated_prepared: parking_lot::Mutex<Option<ValidatedPreparedPublication>>,
-    deferred_initial: parking_lot::Mutex<Option<DeferredInitialPublication>>,
     pub legacy: bool,
 }
 
 impl LocalDisk {
-    #[cfg(test)]
     pub(super) async fn prepare_native_multipart_publication(
         &self,
         path: &str,
         incoming: &mut FileInfo,
         staging: &MultipartCommitStaging,
-    ) -> Result<NativeMultipartPublication> {
-        self.prepare_native_multipart_publication_inner(path, incoming, staging, false)
-            .await
-    }
-
-    pub(super) async fn prepare_native_multipart_publication_deferred(
-        &self,
-        path: &str,
-        incoming: &mut FileInfo,
-        staging: &MultipartCommitStaging,
-    ) -> Result<NativeMultipartPublication> {
-        self.prepare_native_multipart_publication_inner(path, incoming, staging, true)
-            .await
-    }
-
-    async fn prepare_native_multipart_publication_inner(
-        &self,
-        path: &str,
-        incoming: &mut FileInfo,
-        staging: &MultipartCommitStaging,
-        defer_persist: bool,
     ) -> Result<NativeMultipartPublication> {
         // Real Complete is parts-backed, including a zero-byte last part.
         if incoming.data.is_some() || incoming.inline_data() {
             return Err(DiskError::UnsupportedDisk);
         }
         let store = Arc::new(self.multipart_store_from_staging(path, staging).await?);
-        let loaded = if defer_persist && let Some(raw) = staging.fresh_source_head() {
-            load_uninitialized_source(raw, &store.path, store.disk_id, store.physical_slot, &store.disk_ids)?
-        } else {
-            store.load().await?
-        };
+        let loaded = store.load().await?;
         let snapshot = loaded.snapshot.as_ref().ok_or(DiskError::ConditionalDeleteConflict)?;
         let original = loaded
             .head
@@ -1825,44 +1569,7 @@ impl LocalDisk {
         };
         // Copy the small source FI to an independent immutable inode. Its
         // canonical inode is never truncated to build the destination proxy.
-        let directory = staging.private_directory(publication.final_data_dir);
-        let anchor_record = NativeRetirementAnchor {
-            protocol_version: MULTIPART_SOURCE_PROTOCOL_VERSION,
-            disk_id: store.disk_id,
-            physical_slot: store.physical_slot,
-            publication: publication.clone(),
-            source_original_sha256: state.original_sha256,
-            source_validation_receipt_id: state.backup_owner,
-        };
-        let anchor_bytes = encode(&anchor_record)?;
-        state.validate(store.disk_id, &store.path)?;
-        let original_bytes = original.to_vec();
-        let deferred_initial = if defer_persist {
-            Some((original_bytes, directory, anchor_bytes))
-        } else {
-            let state_raw = encode(&state)?;
-            let source_dir = store.source.clone();
-            let base_dir = store.base.clone();
-            let pub_root = store.publication_root.clone();
-            let terminal = terminal_record_path(&source_dir, &state);
-            #[cfg(target_os = "linux")]
-            let can_mark_presynced = has_active_multipart_source_head(&source_dir)
-                && super::effective_durability(RUSTFS_META_MULTIPART_BUCKET).syncs_data_shards();
-            os::run_blocking_namespace_operation_with_sync(staging.lease.clone(), true, move || {
-                SourceStore::write_owned_backup_std(&source_dir, &base_dir, &pub_root, owner, false, &original_bytes, false)?;
-                SourceStore::persist_state_std(&source_dir, &base_dir, &pub_root, &state_raw, terminal.as_deref(), false)?;
-                let _parent = os::mkdir_all_below_existing_base_std(&directory, &base_dir, &pub_root)?;
-                os::replace_multipart_source_metadata(&directory.join(RETIREMENT_ANCHOR), &anchor_bytes, &base_dir, &pub_root)?;
-                #[cfg(target_os = "linux")]
-                if can_mark_presynced {
-                    super::mark_presynced_tmp_data_dir(directory);
-                }
-                Ok(())
-            })
-            .await
-            .map_err(DiskError::from)?;
-            None
-        };
+        store.write_owned_backup_and_persist(owner, false, original, &state).await?;
         let prepared_path = store.source.join(format!(".mpu-prepared-{owner}"));
         let context = NativeMultipartPublication {
             store,
@@ -1871,9 +1578,14 @@ impl LocalDisk {
             state: parking_lot::Mutex::new(state),
             capability: parking_lot::Mutex::new(Some(capability)),
             validated_prepared: parking_lot::Mutex::new(None),
-            deferred_initial: parking_lot::Mutex::new(deferred_initial),
             legacy,
         };
+        let directory = staging.private_directory(context.publication.final_data_dir);
+        let reserved = context.state.lock().clone();
+        context
+            .store
+            .write_retirement_anchor(&reserved, &context.publication, &directory, staging.lease.clone())
+            .await?;
         Ok(context)
     }
 }
@@ -1882,15 +1594,18 @@ impl NativeMultipartPublication {
     pub fn canonical_head(&self) -> PathBuf {
         self.store.source.join(STORAGE_FORMAT_FILE)
     }
-    #[cfg(test)]
     pub async fn prepare_metadata(&self, new_metadata: &[u8], old_metadata: Option<&[u8]>) -> Result<()> {
         let mut state = self.state.lock().clone();
+        let current = self.store.load().await?;
+        let current_state = current.state.as_ref().ok_or(DiskError::ConditionalDeleteConflict)?;
+        if encode(current_state)? != encode(&state)? || !current.head_matches_state {
+            return Err(DiskError::ConditionalDeleteConflict);
+        }
         // Validate the actual persisted representation once, after FileMeta's
         // canonicalization. No unvalidated input can install a source proxy.
         if !self.store.target_matches(&self.publication, new_metadata)? {
             return Err(DiskError::ConditionalDeleteConflict);
         }
-        let expected_state_raw = encode(&state)?;
         let validated = ValidatedPreparedPublication {
             publication: self.publication.clone(),
             sha256: raw_sha(new_metadata),
@@ -1903,298 +1618,17 @@ impl NativeMultipartPublication {
         state.prepared_sha256 = Some(validated.sha256);
         state.prepared_length = Some(validated.length);
         state.advance(MultipartSourcePhase::Prepared)?;
-        state.validate(self.store.disk_id, &self.store.path)?;
-        let next_state_raw = encode(&state)?;
-        let source = self.store.source.clone();
-        let base = self.store.base.clone();
-        let root = self.store.publication_root.clone();
-        let path = self.store.path.clone();
-        let disk_id = self.store.disk_id;
-        let physical_slot = self.store.physical_slot;
-        let disk_ids = self.store.disk_ids.clone();
-        let backup_owner = state.backup_owner;
-        let old_bytes = old_metadata.map(|b| b.to_vec());
-        let terminal = terminal_record_path(&source, &state);
-        os::run_blocking_namespace_operation_with_sync(self.store.lease.clone(), true, move || {
-            let current = load_source(&source, &base, &root, &path, disk_id, physical_slot, &disk_ids).map_err(IoError::other)?;
-            let current_state = current
-                .state
-                .as_ref()
-                .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-            let current_raw = encode(current_state).map_err(IoError::other)?;
-            if current_raw != expected_state_raw || !current.head_matches_state {
-                return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-            }
-            if let Some(previous) = old_bytes.as_deref() {
-                SourceStore::write_owned_backup_std(&source, &base, &root, backup_owner, true, previous, false)?;
-            }
-            SourceStore::persist_state_std(&source, &base, &root, &next_state_raw, terminal.as_deref(), false)
-        })
-        .await
-        .map_err(DiskError::from)?;
+        if let Some(previous) = old_metadata {
+            self.store
+                .write_owned_backup_and_persist(state.backup_owner, true, previous, &state)
+                .await?;
+        } else {
+            self.store.persist(&state).await?;
+        }
         *self.state.lock() = state;
         *self.validated_prepared.lock() = Some(validated);
         Ok(())
     }
-    #[cfg(target_os = "linux")]
-    pub(super) fn prepare_and_install_head_on_thread(
-        &self,
-        new_metadata: &[u8],
-        old_metadata: Option<&[u8]>,
-        dst_file_path: &Path,
-        directory_guard: &os::RenameCommitGuard,
-    ) -> Result<os::PreparedRenameSource> {
-        let mut state = self.state.lock().clone();
-        if !self.store.target_matches(&self.publication, new_metadata)? {
-            return Err(DiskError::ConditionalDeleteConflict);
-        }
-        let deferred_initial = self.deferred_initial.lock().take();
-        let expected_state_raw = encode(&state)?;
-        let expected_lineage = state.lineage.clone();
-        let expected_generation = state.generation;
-        let expected_revision = state.revision;
-        let validated = ValidatedPreparedPublication {
-            publication: self.publication.clone(),
-            sha256: raw_sha(new_metadata),
-            length: new_metadata.len() as u64,
-        };
-        if let Some(previous) = old_metadata {
-            state.previous_target_sha256 = Some(raw_sha(previous));
-            state.previous_target_length = Some(previous.len() as u64);
-        }
-        state.prepared_sha256 = Some(validated.sha256);
-        state.prepared_length = Some(validated.length);
-        state.advance(MultipartSourcePhase::Prepared)?;
-        state.validate(self.store.disk_id, &self.store.path)?;
-        let next_state_raw = encode(&state)?;
-        let source = &self.store.source;
-        let base = &self.store.base;
-        let root = &self.store.publication_root;
-        let path = &self.store.path;
-        let disk_id = self.store.disk_id;
-        let physical_slot = self.store.physical_slot;
-        let disk_ids = &self.store.disk_ids;
-        let backup_owner = state.backup_owner;
-        #[cfg(target_os = "linux")]
-        let can_mark_presynced = has_active_multipart_source_head(source)
-            && super::effective_durability(RUSTFS_META_MULTIPART_BUCKET).syncs_data_shards();
-        let terminal = terminal_record_path(source, &state);
-        let prepared_path = &self.prepared_path;
-        let canonical = self.canonical_head();
-        let prepared = (|| -> std::io::Result<os::PreparedRenameSource> {
-            if let Some((ref original_bytes, _, _)) = deferred_initial {
-                let current = load_source(source, base, root, path, disk_id, physical_slot, disk_ids).map_err(IoError::other)?;
-                let snapshot = current
-                    .snapshot
-                    .as_ref()
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                let current_head = current
-                    .head
-                    .as_ref()
-                    .and_then(SourceHead::raw)
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                if !current.head_matches_state
-                    || snapshot.phase != MultipartSourcePhase::Active
-                    || snapshot.capability_sha256.is_some()
-                    || snapshot.lineage != expected_lineage
-                    || snapshot.generation != expected_generation
-                    || snapshot.revision.checked_add(1) != Some(expected_revision)
-                    || current_head != original_bytes.as_slice()
-                {
-                    return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                }
-            } else {
-                let current = load_source(source, base, root, path, disk_id, physical_slot, disk_ids).map_err(IoError::other)?;
-                let current_state = current
-                    .state
-                    .as_ref()
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                let current_raw = encode(current_state).map_err(IoError::other)?;
-                if current_raw != expected_state_raw || !current.head_matches_state {
-                    return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                }
-            }
-            #[cfg(test)]
-            super::run_owned_file_before_open(prepared_path);
-            let mut prepared_metadata_source =
-                os::create_prepared_rename_source_with_commit_guard(prepared_path, dst_file_path, directory_guard)?;
-            if let Err(err) = prepared_metadata_source.write_all(new_metadata, false) {
-                drop(prepared_metadata_source);
-                let _ = std::fs::remove_file(prepared_path);
-                return Err(err);
-            }
-            let setup_res: std::io::Result<()> = (|| {
-                if let Some((original_bytes, directory, anchor_bytes)) = deferred_initial {
-                    SourceStore::write_owned_backup_std(source, base, root, backup_owner, false, &original_bytes, false)?;
-                    if let Some(previous) = old_metadata {
-                        SourceStore::write_owned_backup_std(source, base, root, backup_owner, true, previous, false)?;
-                    }
-                    SourceStore::persist_state_std(source, base, root, &next_state_raw, terminal.as_deref(), false)?;
-                    let _parent = os::mkdir_all_below_existing_base_std(&directory, base, root)?;
-                    os::replace_multipart_source_metadata(&directory.join(RETIREMENT_ANCHOR), &anchor_bytes, base, root)?;
-                    #[cfg(target_os = "linux")]
-                    if can_mark_presynced {
-                        super::mark_presynced_tmp_data_dir(directory);
-                    }
-                } else {
-                    if let Some(previous) = old_metadata {
-                        SourceStore::write_owned_backup_std(source, base, root, backup_owner, true, previous, false)?;
-                    }
-                    SourceStore::persist_state_std(source, base, root, &next_state_raw, terminal.as_deref(), false)?;
-                }
-                Ok(())
-            })();
-            if let Err(err) = setup_res {
-                drop(prepared_metadata_source);
-                let _ = std::fs::remove_file(prepared_path);
-                return Err(err);
-            }
-            if let Err(err) = prepared_metadata_source.sync_data() {
-                drop(prepared_metadata_source);
-                let _ = std::fs::remove_file(prepared_path);
-                return Err(err);
-            }
-            os::install_multipart_prepared_head(prepared_metadata_source, &canonical, base, root)
-        })()
-        .map_err(DiskError::from)?;
-        *self.state.lock() = state;
-        *self.validated_prepared.lock() = Some(validated);
-        Ok(prepared)
-    }
-
-    #[cfg(not(target_os = "linux"))]
-    pub async fn prepare_and_install_head(
-        &self,
-        new_metadata: &[u8],
-        old_metadata: Option<&[u8]>,
-        dst_file_path: &Path,
-        directory_guard: &os::RenameCommitGuard,
-        mutation_lease: Arc<os::NamespaceMutationLease>,
-    ) -> Result<os::PreparedRenameSource> {
-        let mut state = self.state.lock().clone();
-        if !self.store.target_matches(&self.publication, new_metadata)? {
-            return Err(DiskError::ConditionalDeleteConflict);
-        }
-        let deferred_initial = self.deferred_initial.lock().take();
-        let expected_state_raw = encode(&state)?;
-        let expected_lineage = state.lineage.clone();
-        let expected_generation = state.generation;
-        let expected_revision = state.revision;
-        let validated = ValidatedPreparedPublication {
-            publication: self.publication.clone(),
-            sha256: raw_sha(new_metadata),
-            length: new_metadata.len() as u64,
-        };
-        if let Some(previous) = old_metadata {
-            state.previous_target_sha256 = Some(raw_sha(previous));
-            state.previous_target_length = Some(previous.len() as u64);
-        }
-        state.prepared_sha256 = Some(validated.sha256);
-        state.prepared_length = Some(validated.length);
-        state.advance(MultipartSourcePhase::Prepared)?;
-        state.validate(self.store.disk_id, &self.store.path)?;
-        let next_state_raw = encode(&state)?;
-        let source = self.store.source.clone();
-        let base = self.store.base.clone();
-        let root = self.store.publication_root.clone();
-        let path = self.store.path.clone();
-        let disk_id = self.store.disk_id;
-        let physical_slot = self.store.physical_slot;
-        let disk_ids = self.store.disk_ids.clone();
-        let backup_owner = state.backup_owner;
-        #[cfg(target_os = "linux")]
-        let can_mark_presynced = has_active_multipart_source_head(&source)
-            && super::effective_durability(RUSTFS_META_MULTIPART_BUCKET).syncs_data_shards();
-        let old_bytes = old_metadata.map(|b| b.to_vec());
-        let new_bytes = new_metadata.to_vec();
-        let terminal = terminal_record_path(&source, &state);
-        let prepared_path = self.prepared_path.clone();
-        let canonical = self.canonical_head();
-        let dst_file_path = dst_file_path.to_path_buf();
-        let owned_directory_guard = directory_guard.clone();
-        let prepared = os::run_blocking_namespace_operation_with_sync(mutation_lease, true, move || {
-            let current = load_source(&source, &base, &root, &path, disk_id, physical_slot, &disk_ids).map_err(IoError::other)?;
-            if let Some((original_bytes, directory, anchor_bytes)) = deferred_initial {
-                let snapshot = current
-                    .snapshot
-                    .as_ref()
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                let current_head = current
-                    .head
-                    .as_ref()
-                    .and_then(SourceHead::raw)
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                if !current.head_matches_state
-                    || snapshot.phase != MultipartSourcePhase::Active
-                    || snapshot.capability_sha256.is_some()
-                    || snapshot.lineage != expected_lineage
-                    || snapshot.generation != expected_generation
-                    || snapshot.revision.checked_add(1) != Some(expected_revision)
-                    || current_head != original_bytes.as_slice()
-                {
-                    return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                }
-                SourceStore::write_owned_backup_std(&source, &base, &root, backup_owner, false, &original_bytes, false)?;
-                if let Some(previous) = old_bytes.as_deref() {
-                    SourceStore::write_owned_backup_std(&source, &base, &root, backup_owner, true, previous, false)?;
-                }
-                SourceStore::persist_state_std(&source, &base, &root, &next_state_raw, terminal.as_deref(), false)?;
-                let _parent = os::mkdir_all_below_existing_base_std(&directory, &base, &root)?;
-                os::replace_multipart_source_metadata(&directory.join(RETIREMENT_ANCHOR), &anchor_bytes, &base, &root)?;
-                #[cfg(target_os = "linux")]
-                if can_mark_presynced {
-                    super::mark_presynced_tmp_data_dir(directory);
-                }
-            } else {
-                let current_state = current
-                    .state
-                    .as_ref()
-                    .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-                let current_raw = encode(current_state).map_err(IoError::other)?;
-                if current_raw != expected_state_raw || !current.head_matches_state {
-                    return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                }
-                if let Some(previous) = old_bytes.as_deref() {
-                    SourceStore::write_owned_backup_std(&source, &base, &root, backup_owner, true, previous, false)?;
-                }
-                SourceStore::persist_state_std(&source, &base, &root, &next_state_raw, terminal.as_deref(), false)?;
-            }
-            #[cfg(test)]
-            super::run_owned_file_before_open(&prepared_path);
-            let mut prepared_metadata_source =
-                os::create_prepared_rename_source_with_commit_guard(&prepared_path, &dst_file_path, &owned_directory_guard)?;
-            prepared_metadata_source.write_all(&new_bytes, true)?;
-            os::install_multipart_prepared_head(prepared_metadata_source, &canonical, &base, &root)
-        })
-        .await
-        .map_err(DiskError::from)?;
-        *self.state.lock() = state;
-        *self.validated_prepared.lock() = Some(validated);
-        Ok(prepared)
-    }
-
-    #[cfg(target_os = "linux")]
-    pub async fn prepare_and_install_head(
-        self: &Arc<Self>,
-        new_metadata: &[u8],
-        old_metadata: Option<&[u8]>,
-        dst_file_path: &Path,
-        directory_guard: &os::RenameCommitGuard,
-        mutation_lease: Arc<os::NamespaceMutationLease>,
-    ) -> Result<os::PreparedRenameSource> {
-        let this = Arc::clone(self);
-        let new_bytes = new_metadata.to_vec();
-        let old_bytes = old_metadata.map(|b| b.to_vec());
-        let dst_file_path = dst_file_path.to_path_buf();
-        let owned_directory_guard = directory_guard.clone();
-        os::run_blocking_namespace_operation_with_sync(mutation_lease, true, move || {
-            this.prepare_and_install_head_on_thread(&new_bytes, old_bytes.as_deref(), &dst_file_path, &owned_directory_guard)
-                .map_err(IoError::other)
-        })
-        .await
-        .map_err(DiskError::from)
-    }
-    #[cfg(test)]
     pub async fn install_head(&self, prepared: os::PreparedRenameSource) -> Result<os::PreparedRenameSource> {
         {
             let guard = self.validated_prepared.lock();
@@ -2265,13 +1699,13 @@ impl NativeMultipartPublication {
         // return an error after consuming the last claimable source heads.
         self.store.restore_exact_target_with_lease(&state, lease).await
     }
-    pub(super) fn finish_on_thread(
-        &self,
-        target_already_synced: bool,
-        staging_cleanup: Option<(PathBuf, Arc<std::sync::atomic::AtomicBool>)>,
-    ) -> Result<MultipartPublicationResult> {
+    pub async fn finish(&self, target_lease: Arc<os::NamespaceMutationLease>) -> Result<MultipartPublicationResult> {
         let mut state = self.state.lock().clone();
-        let expected_state_raw = encode(&state)?;
+        let current = self.store.load().await?;
+        let current_state = current.state.as_ref().ok_or(DiskError::ConditionalDeleteConflict)?;
+        if current.head.is_some() || encode(current_state)? != encode(&state)? {
+            return Err(DiskError::ConditionalDeleteConflict);
+        }
         let (expected_sha256, expected_length) = {
             let guard = self.validated_prepared.lock();
             let validated = guard.as_ref().ok_or(DiskError::ConditionalDeleteConflict)?;
@@ -2283,88 +1717,16 @@ impl NativeMultipartPublication {
             }
             (validated.sha256, validated.length)
         };
-        let target_dir = self.store.target_path(&self.publication)?;
+        self.store
+            .read_and_sync_target_with_lease(&self.publication, target_lease, move |target| {
+                if target.len() as u64 != expected_length || raw_sha(target) != expected_sha256 {
+                    return Err(DiskError::ConditionalDeleteConflict);
+                }
+                Ok(())
+            })
+            .await?;
         state.advance(MultipartSourcePhase::ConsumedUnsealed)?;
-        state.validate(self.store.disk_id, &self.store.path)?;
-        let next_state_raw = encode(&state)?;
-        let snapshot = snapshot_for_state(self.store.disk_id, &state, &next_state_raw, None)?;
-        let source = &self.store.source;
-        let base = &self.store.base;
-        let root = &self.store.publication_root;
-        let path = &self.store.path;
-        let disk_id = self.store.disk_id;
-        let physical_slot = self.store.physical_slot;
-        let disk_ids = &self.store.disk_ids;
-        let terminal = terminal_record_path(source, &state);
-        (|| -> std::io::Result<()> {
-            let current = load_source(source, base, root, path, disk_id, physical_slot, disk_ids).map_err(IoError::other)?;
-            let current_state = current
-                .state
-                .as_ref()
-                .ok_or_else(|| IoError::other(DiskError::ConditionalDeleteConflict))?;
-            let current_raw = encode(current_state).map_err(IoError::other)?;
-            if current.head.is_some() || current_raw != expected_state_raw {
-                return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-            }
-            if target_already_synced {
-                let pinned = os::pin_multipart_source_directory(&target_dir, base, root).map_err(|error| {
-                    if error.kind() == std::io::ErrorKind::NotFound {
-                        IoError::other(DiskError::ConditionalDeleteConflict)
-                    } else {
-                        error
-                    }
-                })?;
-                let target = os::read_multipart_source_metadata_in_pinned(
-                    &pinned,
-                    &target_dir,
-                    std::ffi::OsStr::new(STORAGE_FORMAT_FILE),
-                    base,
-                    root,
-                )
-                .map_err(|error| {
-                    if error.kind() == std::io::ErrorKind::NotFound {
-                        IoError::other(DiskError::ConditionalDeleteConflict)
-                    } else {
-                        error
-                    }
-                })?;
-                if target.len() as u64 != expected_length || raw_sha(&target) != expected_sha256 {
-                    return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                }
-            } else {
-                os::read_and_sync_multipart_target_metadata(
-                    &target_dir,
-                    std::ffi::OsStr::new(STORAGE_FORMAT_FILE),
-                    base,
-                    root,
-                    |target| {
-                        if target.len() as u64 != expected_length || raw_sha(target) != expected_sha256 {
-                            return Err(IoError::other(DiskError::ConditionalDeleteConflict));
-                        }
-                        Ok(())
-                    },
-                )
-                .map_err(|error| {
-                    if error.kind() == std::io::ErrorKind::NotFound {
-                        IoError::other(DiskError::ConditionalDeleteConflict)
-                    } else {
-                        error
-                    }
-                })?;
-            }
-            SourceStore::persist_state_std(source, base, root, &next_state_raw, terminal.as_deref(), true)?;
-            if let Some((io_path, cleaned)) = staging_cleanup {
-                match std::fs::remove_dir(&io_path) {
-                    Ok(()) => cleaned.store(true, std::sync::atomic::Ordering::Release),
-                    Err(err) if err.kind() == std::io::ErrorKind::NotFound => {
-                        cleaned.store(true, std::sync::atomic::Ordering::Release);
-                    }
-                    Err(_) => {}
-                }
-            }
-            Ok(())
-        })()
-        .map_err(DiskError::from)?;
+        let snapshot = self.store.persist_with_source_sync(&state, true).await?;
         *self.state.lock() = state;
         let proof = self
             .store
@@ -2376,21 +1738,6 @@ impl NativeMultipartPublication {
             undo_capability: capability,
         })
     }
-
-    pub async fn finish(
-        self: &Arc<Self>,
-        target_lease: Arc<os::NamespaceMutationLease>,
-        target_already_synced: bool,
-        staging_cleanup: Option<(PathBuf, Arc<std::sync::atomic::AtomicBool>)>,
-    ) -> Result<MultipartPublicationResult> {
-        let this = Arc::clone(self);
-        os::run_blocking_namespace_operation_with_sync(target_lease, true, move || {
-            this.finish_on_thread(target_already_synced, staging_cleanup)
-                .map_err(IoError::other)
-        })
-        .await
-        .map_err(DiskError::from)
-    }
 }
 
 impl SourceStore {

crates/ecstore/src/disk/local/multipart_staging.rs

@@ -207,12 +207,6 @@ pub(super) struct MultipartSourceAdmission {
     initial: bool,
 }
 impl MultipartSourceAdmission {
-    pub(super) fn source(&self) -> &Path {
-        &self.source
-    }
-    pub(super) fn is_initial(&self) -> bool {
-        self.initial
-    }
     pub(super) fn precondition(&self) -> Arc<dyn Fn() -> std::io::Result<()> + Send + Sync> {
         let admission = self.clone();
         Arc::new(move || admission.validate())
@@ -256,8 +250,6 @@ pub(super) struct MultipartCommitStaging {
     logical_path: PathBuf,
     io_path: PathBuf,
     owner: Option<Arc<dyn Send + Sync>>,
-    cleaned: Arc<std::sync::atomic::AtomicBool>,
-    fresh_source_head: Option<bytes::Bytes>,
 }
 
 impl MultipartCommitStaging {
@@ -267,19 +259,10 @@ impl MultipartCommitStaging {
     pub(super) fn private_directory(&self, directory: Uuid) -> PathBuf {
         self.io_path.join(directory.to_string())
     }
-    pub(super) fn cleanup_handle(&self) -> (PathBuf, Arc<std::sync::atomic::AtomicBool>) {
-        (self.io_path.clone(), Arc::clone(&self.cleaned))
-    }
-    pub(super) fn fresh_source_head(&self) -> Option<bytes::Bytes> {
-        self.fresh_source_head.clone()
-    }
 }
 
 impl Drop for MultipartCommitStaging {
     fn drop(&mut self) {
-        if self.cleaned.load(std::sync::atomic::Ordering::Acquire) {
-            return;
-        }
         let logical_path = self.logical_path.clone();
         let io_path = self.io_path.clone();
         let owner = self.owner.clone();
@@ -302,14 +285,6 @@ impl Drop for MultipartCommitStaging {
 }
 
 impl LocalDisk {
-    pub(crate) fn has_clean_active_multipart_source(&self, upload_or_part_path: &str, part_path: bool) -> bool {
-        let root = upload_scope_root(upload_or_part_path, part_path);
-        let Ok(source) = self.io_get_object_path(RUSTFS_META_MULTIPART_BUCKET, root) else {
-            return false;
-        };
-        super::multipart_source_state::has_clean_active_multipart_source(&source)
-    }
-
     pub(super) fn multipart_source_admission(
         &self,
         volume: &str,
@@ -381,14 +356,12 @@ impl LocalDisk {
         let io_path = self.io_get_object_path(RUSTFS_META_TMP_BUCKET, &attempt)?;
         // The attempt root is exactly the namespace used by the tmp sweeper.
         let lease = os::acquire_namespace_mutation_lease_with_owner(&logical_path, owner.clone()).await;
-        let mut staging = MultipartCommitStaging {
+        let staging = MultipartCommitStaging {
             path: attempt,
             lease,
             logical_path,
             io_path,
             owner,
-            cleaned: Arc::new(std::sync::atomic::AtomicBool::new(false)),
-            fresh_source_head: None,
         };
         let canonical_metadata = self.io_get_object_path(RUSTFS_META_MULTIPART_BUCKET, &format!("{source_path}/xl.meta"))?;
         let source_object = self.io_get_object_path(RUSTFS_META_MULTIPART_BUCKET, source_path)?;
@@ -398,37 +371,31 @@ impl LocalDisk {
         let source_path = source_path.to_owned();
         let incoming = incoming.clone();
         let sync_directory = effective_durability(destination_volume).syncs_data_shards();
-        let fresh_head = os::run_cancellable_blocking_namespace_operation(Arc::clone(&staging.lease), move |cancelled| {
+        os::run_cancellable_blocking_namespace_operation(Arc::clone(&staging.lease), move |cancelled| {
             if cancelled() {
                 return Err(std::io::Error::new(std::io::ErrorKind::Interrupted, "multipart staging cancelled"));
             }
-            let cached_head = super::multipart_source_state::get_active_multipart_source_head(&source_object);
-            let (raw, source, from_active_cache) = if let Some((raw, source)) = cached_head {
-                (raw, source, true)
-            } else {
-                let raw = os::read_multipart_source_metadata(&canonical_metadata, &base, &publication_root).map_err(|error| {
-                    // A retired source has no authority for this delayed completion.
-                    // Preserve confinement and other I/O failures as their real errors.
-                    if error.kind() == std::io::ErrorKind::NotFound {
-                        DiskError::FileNotFound.into()
-                    } else {
-                        error
-                    }
-                })?;
-                let source = get_file_info(
-                    &raw,
-                    RUSTFS_META_MULTIPART_BUCKET,
-                    &source_path,
-                    "",
-                    FileInfoOpts {
-                        data: false,
-                        include_free_versions: false,
-                        include_part_checksums: true,
-                    },
-                )
-                .map_err(std::io::Error::other)?;
-                (bytes::Bytes::from(raw), source, false)
-            };
+            let raw = os::read_multipart_source_metadata(&canonical_metadata, &base, &publication_root).map_err(|error| {
+                // A retired source has no authority for this delayed completion.
+                // Preserve confinement and other I/O failures as their real errors.
+                if error.kind() == std::io::ErrorKind::NotFound {
+                    DiskError::FileNotFound.into()
+                } else {
+                    error
+                }
+            })?;
+            let source = get_file_info(
+                &raw,
+                RUSTFS_META_MULTIPART_BUCKET,
+                &source_path,
+                "",
+                FileInfoOpts {
+                    data: false,
+                    include_free_versions: false,
+                    include_part_checksums: true,
+                },
+            )
+            .map_err(std::io::Error::other)?;
             let source_dir = source
                 .data_dir
                 .filter(|dir| !dir.is_nil())
@@ -445,31 +412,23 @@ impl LocalDisk {
             let _attempt = os::mkdir_all_below_existing_base_std(&private_object, &base, &publication_root)?;
             if incoming.data.is_none() && !incoming.is_remote() {
                 let source_data_dir = source_object.join(source_dir.to_string());
-                let mut pinned_source_data = None;
+                let pinned_source_data = (!incoming.parts.is_empty())
+                    .then(|| os::pin_multipart_source_directory(&source_data_dir, &base, &publication_root))
+                    .transpose()?;
                 let mut names = Vec::with_capacity(incoming.parts.len().saturating_mul(3));
                 for part in &incoming.parts {
                     if cancelled() {
                         return Err(std::io::Error::new(std::io::ErrorKind::Interrupted, "multipart staging cancelled"));
                     }
                     let meta_name = format!("part.{}.meta", part.number);
-                    let actual = if let Some(cached_part) =
-                        super::multipart_source_state::get_active_multipart_source_part(&source_object, part.number)
-                    {
-                        cached_part
-                    } else {
-                        if pinned_source_data.is_none() {
-                            pinned_source_data =
-                                Some(os::pin_multipart_source_directory(&source_data_dir, &base, &publication_root)?);
-                        }
-                        let bytes = os::read_multipart_source_metadata_in_pinned(
-                            pinned_source_data.as_ref().expect("pinned source data directory"),
-                            &source_data_dir,
-                            std::ffi::OsStr::new(&meta_name),
-                            &base,
-                            &publication_root,
-                        )?;
-                        rustfs_filemeta::ObjectPartInfo::unmarshal(&bytes).map_err(std::io::Error::other)?
-                    };
+                    let bytes = os::read_multipart_source_metadata_in_pinned(
+                        pinned_source_data.as_ref().expect("pinned source data directory"),
+                        &source_data_dir,
+                        std::ffi::OsStr::new(&meta_name),
+                        &base,
+                        &publication_root,
+                    )?;
+                    let actual = rustfs_filemeta::ObjectPartInfo::unmarshal(&bytes).map_err(std::io::Error::other)?;
                     let normalized = i64::try_from(actual.size)
                         .map_err(std::io::Error::other)?
                         .max(actual.actual_size);
@@ -505,15 +464,10 @@ impl LocalDisk {
                     cancelled,
                 )?;
             }
-            let has_state = !from_active_cache
-                && (source_object.join(".mpu-source-state").exists()
-                    || source_object.join(".mpu-recovery").exists()
-                    || source_object.join(".mpu-completions").exists());
-            Ok((!has_state).then_some(raw))
+            Ok(())
         })
         .await
         .map_err(DiskError::from)?;
-        staging.fresh_source_head = fresh_head;
         Ok(staging)
     }
 }
@@ -1265,211 +1219,4 @@ mod tests {
             .expect("non-part empty hash cleanup must remain supported");
         assert!(!directory.exists(), "a per-upload safety guard must not strand empty hash directories");
     }
-
-    #[tokio::test]
-    async fn multipart_source_active_head_cache_populates_and_invalidates_across_part_and_delete_paths() {
-        use crate::disk::{DiskAPI as _, PartTransactionAction, ReadOptions};
-        let (_root, disk, completed, _) = fixture().await;
-        std::fs::create_dir_all(disk.io_get_bucket_path(RUSTFS_META_TMP_BUCKET).expect("TMP path")).expect("TMP bucket");
-        let upload = format!("{}/{}", "c".repeat(64), Uuid::new_v4());
-        let data_dir = Uuid::new_v4();
-        let mut init_fi = FileInfo::new(&upload, 2, 2);
-        init_fi.erasure.index = 1;
-        init_fi.data_dir = Some(data_dir);
-        init_fi.fresh = true;
-        init_fi.mod_time = Some(time::OffsetDateTime::now_utc());
-
-        disk.write_metadata("", RUSTFS_META_MULTIPART_BUCKET, &upload, init_fi.clone())
-            .await
-            .expect("fresh multipart upload metadata");
-        assert!(disk.has_clean_active_multipart_source(&upload, false));
-
-        let read_fi = disk
-            .read_version("", RUSTFS_META_MULTIPART_BUCKET, &upload, "", &ReadOptions::default())
-            .await
-            .expect("cached read_version");
-        assert_eq!(read_fi.data_dir, Some(data_dir));
-
-        let destination = format!("{upload}/{data_dir}/part.1");
-        let part_meta = bytes::Bytes::from(completed.parts[0].marshal_msg().expect("part meta"));
-        disk.write_all(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.1",
-            bytes::Bytes::from_static(b"immutable shard"),
-        )
-        .await
-        .expect("stage tmp part");
-        disk.prepare_part_transaction(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.1",
-            RUSTFS_META_MULTIPART_BUCKET,
-            &destination,
-            part_meta.clone(),
-        )
-        .await
-        .expect("prepare part transaction");
-        assert!(
-            !disk.has_clean_active_multipart_source(&upload, false),
-            "in-flight part transaction must mark active source as having unsettled part txn"
-        );
-        disk.rename_part(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.1",
-            RUSTFS_META_MULTIPART_BUCKET,
-            &destination,
-            part_meta,
-        )
-        .await
-        .expect("rename part");
-        disk.settle_part_transaction(RUSTFS_META_MULTIPART_BUCKET, &destination, PartTransactionAction::Commit)
-            .await
-            .expect("settle part transaction");
-        assert!(
-            disk.has_clean_active_multipart_source(&upload, false),
-            "settled commit must restore clean active multipart source status"
-        );
-        let read_parts = disk
-            .read_parts(RUSTFS_META_MULTIPART_BUCKET, &[format!("{destination}.meta")])
-            .await
-            .expect("cached read_parts");
-        assert_eq!(read_parts.len(), 1);
-        assert_eq!(read_parts[0].number, 1);
-
-        // Prepare part 2, then replay Commit for already-settled part 1: part 2's
-        // pending transaction must keep the upload marked as having unsettled part txns.
-        let destination2 = format!("{upload}/{data_dir}/part.2");
-        let mut part2_info = completed.parts[0].clone();
-        part2_info.number = 2;
-        let part2_meta = bytes::Bytes::from(part2_info.marshal_msg().expect("part 2 meta"));
-        disk.write_all(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.2",
-            bytes::Bytes::from_static(b"immutable shard"),
-        )
-        .await
-        .expect("stage tmp part 2");
-        disk.prepare_part_transaction(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.2",
-            RUSTFS_META_MULTIPART_BUCKET,
-            &destination2,
-            part2_meta.clone(),
-        )
-        .await
-        .expect("prepare part 2 transaction");
-        assert!(!disk.has_clean_active_multipart_source(&upload, false));
-        disk.settle_part_transaction(RUSTFS_META_MULTIPART_BUCKET, &destination, PartTransactionAction::Commit)
-            .await
-            .expect("replayed part 1 commit settlement");
-        assert!(
-            !disk.has_clean_active_multipart_source(&upload, false),
-            "replayed settlement for part 1 must not clear part 2's pending transaction"
-        );
-        disk.rename_part(
-            RUSTFS_META_TMP_BUCKET,
-            "cache-test-part/part.2",
-            RUSTFS_META_MULTIPART_BUCKET,
-            &destination2,
-            part2_meta,
-        )
-        .await
-        .expect("rename part 2");
-        disk.settle_part_transaction(RUSTFS_META_MULTIPART_BUCKET, &destination2, PartTransactionAction::Commit)
-            .await
-            .expect("settle part 2 transaction");
-        assert!(disk.has_clean_active_multipart_source(&upload, false));
-
-        // Deleting {upload}/xl.meta through delete_paths must invalidate the canonical {upload} cache key.
-        disk.delete_paths(RUSTFS_META_MULTIPART_BUCKET, &[format!("{upload}/xl.meta")])
-            .await
-            .expect("delete xl.meta via delete_paths");
-        assert!(
-            !disk.has_clean_active_multipart_source(&upload, false),
-            "per-file head deletion must invalidate the canonical upload cache key"
-        );
-        assert!(matches!(
-            disk.read_version("", RUSTFS_META_MULTIPART_BUCKET, &upload, "", &ReadOptions::default())
-                .await,
-            Err(DiskError::FileNotFound)
-        ));
-    }
-
-    #[cfg(not(windows))]
-    #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-    async fn multipart_source_cache_publication_holds_source_lock_against_concurrent_retirement() {
-        use crate::disk::{DiskAPI as _, disk_store::LocalDiskWrapper, os::prepared_publication_test_hooks as hooks};
-
-        let (_root, disk, _, _) = fixture().await;
-        std::fs::create_dir_all(disk.io_get_bucket_path(RUSTFS_META_TMP_BUCKET).expect("TMP path")).expect("TMP bucket");
-        let disk = Arc::new(disk);
-        let wrapper = LocalDiskWrapper::new(Arc::clone(&disk), false);
-        let upload = format!("{}/{}", "d".repeat(64), Uuid::new_v4());
-        let data_dir = Uuid::new_v4();
-        let mut init_fi = FileInfo::new(&upload, 2, 2);
-        init_fi.erasure.index = 1;
-        init_fi.data_dir = Some(data_dir);
-        init_fi.fresh = true;
-        init_fi.mod_time = Some(time::OffsetDateTime::now_utc());
-
-        let source_dir = disk
-            .io_get_object_path(RUSTFS_META_MULTIPART_BUCKET, &upload)
-            .expect("source dir");
-        let base_dir = disk
-            .io_get_bucket_path(RUSTFS_META_MULTIPART_BUCKET)
-            .expect("multipart bucket path");
-        let (entered_tx, entered_rx) = tokio::sync::oneshot::channel();
-        let (release_tx, release_rx) = std::sync::mpsc::channel();
-        let _hook = hooks::install_at(hooks::Stage::DirFsync, &source_dir, move || {
-            let _ = entered_tx.send(());
-            let _ = release_rx.recv();
-        });
-
-        let init_wrapper = wrapper.clone();
-        let init_upload = upload.clone();
-        let init_task = tokio::spawn(async move {
-            init_wrapper
-                .write_metadata("", RUSTFS_META_MULTIPART_BUCKET, &init_upload, init_fi)
-                .await
-        });
-
-        tokio::time::timeout(std::time::Duration::from_secs(5), entered_rx)
-            .await
-            .expect("initial write_metadata reaches parent dir fsync")
-            .expect("entered channel");
-
-        let retire_wrapper = wrapper.clone();
-        let retire_path = format!("{upload}/xl.meta");
-        let mut retire_fut = Box::pin(async move {
-            retire_wrapper
-                .delete_paths(RUSTFS_META_MULTIPART_BUCKET, &[retire_path])
-                .await
-        });
-        assert!(
-            futures::poll!(tokio::task::unconstrained(retire_fut.as_mut())).is_pending(),
-            "concurrent retirement must block on SourceRW while initial head publication is in flight"
-        );
-
-        let _ = release_tx.send(());
-        init_task.await.expect("init join").expect("initial write_metadata succeeds");
-        retire_fut
-            .await
-            .expect("concurrent retirement completes after SourceRW release");
-
-        assert!(
-            !super::super::multipart_source_state::has_active_multipart_source_head(&source_dir),
-            "retired source must not remain active in cache after interleaved initial publication"
-        );
-        assert!(
-            matches!(
-                super::super::multipart_source_state::validate_source_mutation(
-                    &source_dir,
-                    &base_dir,
-                    &disk.publication_root,
-                    false
-                ),
-                Err(DiskError::FileNotFound)
-            ),
-            "validate_source_mutation must reject non-initial mutation on retired source"
-        );
-    }
 }

crates/ecstore/src/disk/local/pool_meta_native.rs

@@ -604,7 +604,7 @@ impl LocalDisk {
                 let publication = os::acquire_namespace_mutation_lease_with_owner(&destination, Some(owner)).await;
                 let tmp_volume = self.io_get_bucket_path(RUSTFS_META_TMP_BUCKET)?;
                 let temporary = self.io_get_object_path(RUSTFS_META_TMP_BUCKET, &Uuid::new_v4().to_string())?;
-                self.write_all_internal(&temporary, replacement, SyncMode::FileOnly, &tmp_volume)
+                self.write_all_internal(&temporary, InternalBuf::Ref(&replacement), SyncMode::FileOnly, &tmp_volume)
                     .await?;
                 os::rename_metadata_and_sync_with_lease(
                     temporary,

crates/ecstore/src/disk/mod.rs

@@ -30,21 +30,15 @@ pub mod local;
 pub mod multipart_source;
 pub mod os;
 
-pub(crate) use io_admission::memory as background_memory;
-pub(crate) use io_admission::remote as remote_io_admission;
-pub use io_admission::{
-    BackgroundMemoryBudget, PhysicalDiskBinding, PhysicalDiskPlan, PhysicalDiskSample, PhysicalDiskSampler, PhysicalResourcePlan,
-    RemoteBackgroundIo, spawn_blocking_with_resource_ownership, with_background_disk_io, with_background_resource_set,
-    with_background_resource_unit, with_remote_background_io,
-};
 pub use local::pool_meta_native::{PoolMetaNativeCasCondition, PoolMetaNativeFileIdentity};
 
 #[cfg(test)]
-pub(crate) use io_admission::{DiskIoClass, test_resource_units};
+pub(crate) use io_admission::DiskIoClass;
 pub(crate) use io_admission::{
-    PhysicalHealBinding, acquire_context_disk_io_permit, current_disk_io_context, current_resource_unit, has_resource_io_scope,
-    with_optional_disk_io_context, with_optional_resource_unit,
+    acquire_context_disk_io_permit, current_disk_io_context, current_resource_unit, with_optional_disk_io_context,
+    with_optional_resource_unit,
 };
+pub use io_admission::{with_background_disk_io, with_background_resource_unit};
 
 pub const RUSTFS_META_BUCKET: &str = ".rustfs.sys";
 pub const MIGRATING_META_BUCKET: &str = ".minio.sys";
@@ -311,14 +305,6 @@ pub enum Disk {
 }
 
 impl Disk {
-    /// Physical ownership belongs to the node hosting the local attachment.
-    pub fn physical_admission(&self) -> Option<Arc<PhysicalDiskBinding>> {
-        match self {
-            Self::Local(disk) => Some(disk.physical_admission()),
-            Self::Remote(_) => None,
-        }
-    }
-
     /// A read-only probe; the physical delete repeats the same leaf checks.
     pub async fn is_plain_orphan_data_dir(&self, volume: &str, path: &str) -> Result<bool> {
         match self {
@@ -401,46 +387,6 @@ impl Disk {
         }
     }
 
-    pub(crate) fn has_clean_active_multipart_source(&self, upload_or_part_path: &str, part_path: bool) -> bool {
-        match self {
-            Self::Local(disk) => disk.has_clean_active_multipart_source(upload_or_part_path, part_path),
-            Self::Remote(_) => false,
-        }
-    }
-
-    pub(crate) async fn try_publish_prepared_delete_local(
-        &self,
-        volume: &str,
-        object: &str,
-        transaction: Uuid,
-        namespace_owner: Option<Arc<dyn Send + Sync>>,
-    ) -> Result<Option<(DeleteRecoveryJournal, bool, bool)>> {
-        match self {
-            Self::Local(disk) => {
-                disk.try_publish_prepared_delete_local(volume, object, transaction, namespace_owner)
-                    .await
-            }
-            Self::Remote(_) => Ok(None),
-        }
-    }
-
-    pub(crate) async fn try_finish_and_finalize_prepared_delete_local(
-        &self,
-        volume: &str,
-        object: &str,
-        transaction: Uuid,
-        journal: &DeleteRecoveryJournal,
-        namespace_owner: Option<Arc<dyn Send + Sync>>,
-    ) -> Result<bool> {
-        match self {
-            Self::Local(disk) => {
-                disk.try_finish_and_finalize_prepared_delete_local(volume, object, transaction, journal, namespace_owner)
-                    .await
-            }
-            Self::Remote(_) => Ok(false),
-        }
-    }
-
     pub(crate) async fn delete_version_recoverable_with_namespace_owner(
         &self,
         volume: &str,

crates/ecstore/src/disk/uring_read_budget.rs

@@ -76,14 +76,14 @@ impl DriverReadBudget {
         }
     }
 
-    pub(super) fn start_driver<O: Send + Unpin + 'static>(
+    pub(super) fn start_driver(
         &self,
         entries: u32,
         shards: usize,
-    ) -> Result<rustfs_uring::OwnedUringDriver<O>, rustfs_uring::ProbeFailure> {
+    ) -> Result<rustfs_uring::UringDriver, rustfs_uring::ProbeFailure> {
         match self {
-            Self::Disabled => rustfs_uring::OwnedUringDriver::probe_and_start_sharded(entries, shards),
-            Self::Limited { pool, per_driver } => rustfs_uring::OwnedUringDriver::probe_and_start_with_shared_budget(
+            Self::Disabled => rustfs_uring::UringDriver::probe_and_start_sharded(entries, shards),
+            Self::Limited { pool, per_driver } => rustfs_uring::UringDriver::probe_and_start_with_shared_budget(
                 entries,
                 shards,
                 rustfs_uring::ReadLimits {

crates/ecstore/src/erasure/coding/bitrot.rs

@@ -98,9 +98,6 @@ pin_project! {
         // contiguous on-disk `[hash][data]` block so both are pulled in a single
         // pass; grown lazily and never shrunk.
         buf: Vec<u8>,
-        // Free scratch storage before refunding its allocation.
-        buf_memory: Option<crate::disk::background_memory::Reservation>,
-        memory_budget: Option<std::sync::Arc<crate::disk::BackgroundMemoryBudget>>,
         // Reused owned chunk vector for the remote HTTP fast path. Keeping the
         // allocation with the reader avoids allocating once per bitrot block.
         chunks: Vec<bytes::Bytes>,
@@ -121,8 +118,6 @@ where
             hash_algo: algo,
             shard_size,
             buf: Vec::new(),
-            buf_memory: None,
-            memory_budget: crate::disk::current_resource_unit().and_then(|unit| unit.memory_budget()),
             chunks: Vec::new(),
             skip_verify,
             last_verify_duration: Duration::ZERO,
@@ -214,7 +209,6 @@ where
     /// On `Ok` the block is `self.buf[..need]`; the caller re-borrows it so the
     /// verification can also borrow `self` immutably.
     async fn read_scratch_block(&mut self, need: usize, want: usize) -> std::io::Result<()> {
-        reserve_bitrot_scratch(&mut self.buf, &mut self.buf_memory, self.memory_budget.as_ref(), need)?;
         if self.buf.len() < need {
             self.buf.resize(need, 0);
         }
@@ -235,28 +229,6 @@ where
     }
 }
 
-// Scratch growth happens only before a complete block or an empty chunk tail.
-// Old contents are consumed; keep both allocations charged until replacement.
-fn reserve_bitrot_scratch(
-    buf: &mut Vec<u8>,
-    reservation: &mut Option<crate::disk::background_memory::Reservation>,
-    budget: Option<&std::sync::Arc<crate::disk::BackgroundMemoryBudget>>,
-    capacity: usize,
-) -> std::io::Result<()> {
-    if let Some(budget) = budget
-        && buf.capacity() < capacity
-    {
-        let memory = budget.reserve(capacity)?;
-        let mut replacement = Vec::new();
-        replacement
-            .try_reserve_exact(capacity)
-            .map_err(|_| std::io::Error::from(std::io::ErrorKind::OutOfMemory))?;
-        *buf = replacement;
-        *reservation = Some(memory);
-    }
-    Ok(())
-}
-
 /// A truncated shard is `UnexpectedEof`, not a short success (backlog#799 B2).
 fn short_shard_read(got: usize, want: usize) -> std::io::Error {
     error!(
@@ -367,8 +339,6 @@ where
             let inner = &mut self.inner;
             let chunks = &mut self.chunks;
             let tail_buf = &mut self.buf;
-            let tail_memory = &mut self.buf_memory;
-            let memory_budget = self.memory_budget.as_ref();
             let mut received = 0usize;
             poll_fn(|cx| {
                 for _ in 0..MAX_CHUNK_POLLS_PER_YIELD {
@@ -411,9 +381,7 @@ where
 
                     if chunks.len() == MAX_RETAINED_CHUNKS_PER_BLOCK {
                         if tail_buf.is_empty() {
-                            let tail_capacity = need - (received - chunk.len());
-                            reserve_bitrot_scratch(tail_buf, tail_memory, memory_budget, tail_capacity)?;
-                            tail_buf.reserve_exact(tail_capacity);
+                            tail_buf.reserve_exact(need - (received - chunk.len()));
                         }
                         tail_buf.extend_from_slice(&chunk);
                     } else {
@@ -689,12 +657,7 @@ pub async fn bitrot_verify<R: AsyncRead + Unpin + Send>(
     algo: HashAlgorithm,
     mut shard_size: usize,
 ) -> std::io::Result<()> {
-    // Every supported digest fits on the stack; only shard payloads need leases.
-    let mut hash = [0; 64];
-    let hash_buf = &mut hash[..algo.size()];
-    let mut background_buffer = crate::disk::current_resource_unit()
-        .and_then(|unit| unit.memory_budget())
-        .map(|budget| crate::disk::background_memory::BackgroundBuffer::new(Some(budget)));
+    let mut hash_buf = vec![0; algo.size()];
     let mut left = want_size;
 
     if left != bitrot_shard_file_size(part_size, shard_size, algo.clone()) {
@@ -702,30 +665,21 @@ pub async fn bitrot_verify<R: AsyncRead + Unpin + Send>(
     }
 
     while left > 0 {
-        let n = r.read_exact(hash_buf).await?;
+        let n = r.read_exact(&mut hash_buf).await?;
         left -= n;
 
         if left < shard_size {
             shard_size = left;
         }
 
-        let mut pooled = None;
-        let buf = if let Some(buffer) = background_buffer.as_mut() {
-            buffer.ensure_len(shard_size)?;
-            &mut buffer.as_mut_slice()[..shard_size]
-        } else {
-            let buffer = pooled.insert(get_ec_buffer(shard_size));
-            buffer.resize(shard_size, 0);
-            buffer.as_mut_slice()
-        };
-        let read = r.read_exact(buf).await?;
+        let mut buf = get_ec_buffer(shard_size);
+        buf.resize(shard_size, 0);
+        let read = r.read_exact(&mut buf).await?;
 
-        let actual_hash = algo.hash_encode(buf);
+        let actual_hash = algo.hash_encode(&buf);
         let hash_ok = actual_hash.as_ref() == &hash_buf[0..n];
         drop(actual_hash); // 释放借用
-        if let Some(buf) = pooled {
-            return_ec_buffer(buf);
-        }
+        return_ec_buffer(buf);
         if !hash_ok {
             return Err(std::io::Error::other("bitrot hash mismatch"));
         }
@@ -744,74 +698,15 @@ pub async fn bitrot_verify<R: AsyncRead + Unpin + Send>(
 /// Custom writer enum that supports inline buffer storage
 pub enum CustomWriter {
     /// Inline buffer writer - stores data in memory
-    InlineBuffer(InlineBuffer),
+    InlineBuffer(Vec<u8>),
     /// Disk-based writer using tokio file
     Other(Box<dyn AsyncWrite + Unpin + Send + Sync>),
 }
 
-/// Inline payload storage retains its background allocation through export.
-pub struct InlineBuffer {
-    foreground: Vec<u8>,
-    background: Option<crate::disk::background_memory::BackgroundBuffer>,
-    filled: usize,
-}
-
-impl InlineBuffer {
-    fn new() -> Self {
-        let background = crate::disk::current_resource_unit()
-            .and_then(|unit| unit.memory_budget())
-            .map(|budget| crate::disk::background_memory::BackgroundBuffer::new(Some(budget)));
-        Self {
-            foreground: Vec::new(),
-            background,
-            filled: 0,
-        }
-    }
-
-    fn as_slice(&self) -> &[u8] {
-        match &self.background {
-            Some(buffer) => &buffer.as_slice()[..self.filled],
-            None => &self.foreground,
-        }
-    }
-
-    fn append(&mut self, bufs: &[IoSlice<'_>]) -> std::io::Result<usize> {
-        let total = bufs
-            .iter()
-            .try_fold(0usize, |length, buf| length.checked_add(buf.len()).ok_or(std::io::ErrorKind::OutOfMemory))?;
-        if let Some(buffer) = &mut self.background {
-            let length = self.filled.checked_add(total).ok_or(std::io::ErrorKind::OutOfMemory)?;
-            if length > buffer.as_slice().len() {
-                let capacity = buffer.as_slice().len().checked_mul(2).unwrap_or(length).max(length);
-                // Admission includes both allocations until the prefix has been copied.
-                buffer.grow(capacity, self.filled)?;
-            }
-            let mut offset = self.filled;
-            for buf in bufs {
-                buffer.as_mut_slice()[offset..offset + buf.len()].copy_from_slice(buf);
-                offset += buf.len();
-            }
-            self.filled = length;
-        } else {
-            for buf in bufs {
-                self.foreground.extend_from_slice(buf);
-            }
-        }
-        Ok(total)
-    }
-
-    fn into_bytes(self) -> bytes::Bytes {
-        match self.background {
-            Some(mut buffer) => buffer.take_bytes(self.filled),
-            None => bytes::Bytes::from(self.foreground),
-        }
-    }
-}
-
 impl CustomWriter {
     /// Create a new inline buffer writer
     pub fn new_inline_buffer() -> Self {
-        Self::InlineBuffer(InlineBuffer::new())
+        Self::InlineBuffer(Vec::new())
     }
 
     /// Create a new disk writer from any AsyncWrite implementation
@@ -825,15 +720,15 @@ impl CustomWriter {
     /// Get the inline buffer data if this is an inline buffer writer
     pub fn get_inline_data(&self) -> Option<&[u8]> {
         match self {
-            Self::InlineBuffer(data) => Some(data.as_slice()),
+            Self::InlineBuffer(data) => Some(data),
             Self::Other(_) => None,
         }
     }
 
     /// Extract the inline buffer data, consuming the writer
-    pub fn into_inline_data(self) -> Option<bytes::Bytes> {
+    pub fn into_inline_data(self) -> Option<Vec<u8>> {
         match self {
-            Self::InlineBuffer(data) => Some(data.into_bytes()),
+            Self::InlineBuffer(data) => Some(data),
             Self::Other(_) => None,
         }
     }
@@ -846,7 +741,10 @@ impl AsyncWrite for CustomWriter {
         buf: &[u8],
     ) -> std::task::Poll<std::io::Result<usize>> {
         match self.get_mut() {
-            Self::InlineBuffer(data) => std::task::Poll::Ready(data.append(&[IoSlice::new(buf)])),
+            Self::InlineBuffer(data) => {
+                data.extend_from_slice(buf);
+                std::task::Poll::Ready(Ok(buf.len()))
+            }
             Self::Other(writer) => {
                 let pinned_writer = std::pin::Pin::new(writer.as_mut());
                 pinned_writer.poll_write(cx, buf)
@@ -880,7 +778,13 @@ impl AsyncWrite for CustomWriter {
         bufs: &[IoSlice<'_>],
     ) -> std::task::Poll<std::io::Result<usize>> {
         match self.get_mut() {
-            Self::InlineBuffer(data) => std::task::Poll::Ready(data.append(bufs)),
+            Self::InlineBuffer(data) => {
+                let total = bufs.iter().map(|buf| buf.len()).sum::<usize>();
+                for buf in bufs {
+                    data.extend_from_slice(buf);
+                }
+                std::task::Poll::Ready(Ok(total))
+            }
             Self::Other(writer) => {
                 let pinned_writer = std::pin::Pin::new(writer.as_mut());
                 pinned_writer.poll_write_vectored(cx, bufs)
@@ -955,7 +859,7 @@ impl BitrotWriterWrapper {
     }
 
     /// Extract the inline buffer data, consuming the wrapper
-    pub fn into_inline_data(self) -> Option<bytes::Bytes> {
+    pub fn into_inline_data(self) -> Option<Vec<u8>> {
         match self.writer_type {
             WriterType::InlineBuffer => {
                 let writer = self.bitrot_writer.into_inner();
@@ -1602,184 +1506,6 @@ mod tests {
         assert_eq!(data, &out[..]);
     }
 
-    #[tokio::test]
-    async fn bitrot_reader_scratch_budget_preserves_growth_and_reuse() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        let algo = HashAlgorithm::HighwayHash256S;
-        let mut encoded = Vec::new();
-        for data in [&b"abcd"[..], &b"abcdefgh"[..], &b"ijklmnop"[..]] {
-            encoded.extend_from_slice(algo.hash_encode(data).as_ref());
-            encoded.extend_from_slice(data);
-        }
-        let memory = BackgroundMemoryBudget::new();
-        let (resources, _) = test_resource_units(1);
-        let mut reader = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            BitrotReader::new(Cursor::new(encoded), 8, algo, false)
-        })
-        .await;
-        let mut first = [0; 4];
-        assert_eq!(
-            reader.read(&mut first).await.expect_err("closed scratch budget").kind(),
-            io::ErrorKind::WouldBlock
-        );
-        assert_eq!(reader.inner.position(), 0, "allocation denial must not consume a frame");
-        memory.set_sampled_limit(36, Duration::from_secs(30));
-        reader.read(&mut first).await.expect("first scratch allocation fits");
-        assert_eq!(&first, b"abcd");
-        assert_eq!(memory.snapshot().used, 36);
-        memory.set_sampled_limit(75, Duration::from_secs(30));
-        let mut next = [0; 8];
-        assert_eq!(
-            reader
-                .read(&mut next)
-                .await
-                .expect_err("growth requires old36 plus new40")
-                .kind(),
-            io::ErrorKind::WouldBlock
-        );
-        assert_eq!(reader.inner.position(), 36);
-        assert_eq!(memory.snapshot().used, 36);
-        memory.set_sampled_limit(76, Duration::from_secs(30));
-        reader.read(&mut next).await.expect("growth now fits");
-        assert_eq!(&next, b"abcdefgh");
-        assert_eq!(memory.snapshot().used, 40);
-        memory.set_sampled_limit(0, Duration::ZERO);
-        reader.read(&mut next).await.expect("reuse after hot shrink");
-        assert_eq!(&next, b"ijklmnop");
-        assert_eq!(memory.snapshot().used, 40);
-        drop(reader);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn bitrot_chunk_tail_allocation_stays_charged_until_reader_drop() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        let algo = HashAlgorithm::HighwayHash256S;
-        let payload = vec![37; 256];
-        let encoded = encode_one_block(&payload, payload.len(), algo.clone()).await;
-        let tail_capacity = encoded.len() - MAX_RETAINED_CHUNKS_PER_BLOCK;
-        for fits in [false, true] {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(if fits { tail_capacity as u64 } else { 0 }, Duration::from_secs(30));
-            let (resources, _) = test_resource_units(1);
-            let mut reader = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                BitrotReader::new(GeneratedChunkSource::new(encoded.clone(), 1), payload.len(), algo.clone(), false)
-            })
-            .await;
-            let mut output = Vec::with_capacity(payload.len());
-            let result = reader.read_appending(&mut output, payload.len()).await;
-            if fits {
-                assert_eq!(result.expect("accounted tail fits"), payload.len());
-                assert_eq!(output, payload);
-                assert_eq!(memory.snapshot().used, tail_capacity as u64);
-                memory.set_sampled_limit(0, Duration::ZERO);
-                assert_eq!(memory.snapshot().used, tail_capacity as u64);
-            } else {
-                assert_eq!(result.expect_err("closed tail budget").kind(), io::ErrorKind::WouldBlock);
-                assert!(output.is_empty(), "an unverified fragment must not reach output");
-                assert_eq!(memory.snapshot().used, 0);
-            }
-            drop(reader);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn bitrot_verify_background_memory_is_bounded_and_reused() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        struct ShrinkingReader {
-            data: Cursor<Vec<u8>>,
-            memory: Arc<BackgroundMemoryBudget>,
-            first_block_end: u64,
-            peak: Arc<std::sync::atomic::AtomicU64>,
-        }
-        impl AsyncRead for ShrinkingReader {
-            fn poll_read(mut self: Pin<&mut Self>, cx: &mut Context<'_>, out: &mut ReadBuf<'_>) -> Poll<io::Result<()>> {
-                self.peak.fetch_max(self.memory.snapshot().used, Ordering::SeqCst);
-                let result = Pin::new(&mut self.data).poll_read(cx, out);
-                if self.data.position() >= self.first_block_end {
-                    self.memory.set_sampled_limit(0, Duration::ZERO);
-                }
-                result
-            }
-        }
-
-        for algo in [
-            HashAlgorithm::None,
-            HashAlgorithm::HighwayHash256S,
-            HashAlgorithm::HighwayHash256SLegacy,
-        ] {
-            let payload = [37; 17];
-            let mut writer = BitrotWriter::new(Cursor::new(Vec::new()), 8, algo.clone());
-            for chunk in payload.chunks(8) {
-                writer.write(chunk).await.expect("encoded bitrot block");
-            }
-            writer.shutdown().await.expect("complete fixture");
-            let encoded = writer.into_inner().into_inner();
-            let memory = BackgroundMemoryBudget::new();
-            let (resources, _) = test_resource_units(1);
-            let error = with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                bitrot_verify(Cursor::new(&encoded), encoded.len(), payload.len(), algo.clone(), 8),
-            )
-            .await
-            .expect_err("a closed background budget must reject bitrot payload allocation");
-            assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-            assert_eq!(memory.snapshot().used, 0);
-            memory.set_sampled_limit(8, Duration::from_secs(30));
-            let peak = Arc::new(std::sync::atomic::AtomicU64::new(0));
-            let reader = ShrinkingReader {
-                data: Cursor::new(encoded.clone()),
-                memory: memory.clone(),
-                first_block_end: (algo.size() + 8) as u64,
-                peak: peak.clone(),
-            };
-            let (resources, _) = test_resource_units(1);
-            with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                bitrot_verify(reader, encoded.len(), payload.len(), algo, 8),
-            )
-            .await
-            .expect("reuse the same allocation after shrink, including the short tail");
-            assert_eq!(peak.load(Ordering::SeqCst), 8);
-            assert_eq!(memory.snapshot().limit, 0);
-            assert_eq!(
-                memory.snapshot().used,
-                0,
-                "the verifier frees its payload instead of retaining it in an uncharged pool"
-            );
-        }
-    }
-
-    #[tokio::test]
-    async fn bitrot_verify_cancelled_payload_read_refunds_memory() {
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-
-        let algo = HashAlgorithm::HighwayHash256S;
-        let (mut sender, reader) = tokio::io::duplex(64);
-        sender
-            .write_all(algo.hash_encode(&[37; 8]).as_ref())
-            .await
-            .expect("send only hash");
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(8, Duration::from_secs(30));
-        let (resources, _) = test_resource_units(1);
-        let mut verify = Box::pin(with_optional_resource_unit(
-            Some(resources.with_memory_budget(memory.clone())),
-            bitrot_verify(reader, algo.size() + 8, 8, algo, 8),
-        ));
-        assert!(futures::poll!(&mut verify).is_pending(), "the payload read waits after the complete hash");
-        let retained = memory.snapshot().used;
-        memory.set_sampled_limit(0, Duration::ZERO);
-        drop(verify);
-        drop(sender);
-        assert_eq!(retained, 8, "pending verification owns its payload allocation");
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
     #[tokio::test]
     async fn bitrot_verify_accepts_valid_shard_file_and_rejects_size_or_hash_mismatch() {
         let data = b"bitrot verify covers every shard";
@@ -2677,128 +2403,4 @@ mod tests {
             assert_eq!(output, vec![9u8]);
         }
     }
-
-    mod inline_memory_regressions {
-        use super::*;
-        use crate::disk::background_memory::is_memory_pressure;
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-        use std::sync::Arc;
-        use std::time::Duration;
-        use tokio::io::AsyncWriteExt;
-
-        async fn writer_for(memory: Arc<BackgroundMemoryBudget>) -> CustomWriter {
-            let (resources, _) = test_resource_units(1);
-            with_optional_resource_unit(Some(resources.with_memory_budget(memory)), async { CustomWriter::new_inline_buffer() })
-                .await
-        }
-
-        #[tokio::test]
-        async fn inline_writer_rejects_closed_and_expired_owners_before_first_allocation() {
-            for expired in [false, true] {
-                let memory = BackgroundMemoryBudget::new();
-                if expired {
-                    memory.set_sampled_limit(128, Duration::ZERO);
-                }
-                let mut writer = writer_for(memory.clone()).await;
-                let error = writer.write_all(&[7; 64]).await.expect_err("no live grant");
-                assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-                assert!(is_memory_pressure(&error));
-                assert_eq!(writer.get_inline_data(), Some(&[][..]));
-                assert_eq!(memory.snapshot().used, 0);
-            }
-        }
-
-        #[tokio::test]
-        async fn inline_writer_growth_charges_old_plus_new_and_is_atomic_for_vectored_writes() {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(128, Duration::from_secs(30));
-            let mut writer = writer_for(memory.clone()).await;
-            writer.write_all(&[1; 64]).await.expect("first allocation");
-            assert_eq!(memory.snapshot().used, 64);
-            let second = [2; 32];
-            let third = [3; 32];
-            let chunks = [IoSlice::new(&second), IoSlice::new(&third)];
-            let error = writer.write_vectored(&chunks).await.expect_err("64 old + 128 new exceed 128");
-            assert!(is_memory_pressure(&error));
-            assert_eq!(writer.get_inline_data(), Some(&[1; 64][..]));
-            assert_eq!(memory.snapshot().used, 64);
-            memory.set_sampled_limit(192, Duration::from_secs(30));
-            assert_eq!(writer.write_vectored(&chunks).await.expect("old and new both fit"), 64);
-            assert_eq!(memory.snapshot().used, 128);
-            let data = writer.get_inline_data().expect("inline payload");
-            assert_eq!(&data[..64], &[1; 64]);
-            assert_eq!(&data[64..96], &second);
-            assert_eq!(&data[96..], &third);
-            drop(writer);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn inline_writer_expiry_preserves_charged_storage_but_blocks_growth() {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(192, Duration::from_secs(30));
-            let mut writer = writer_for(memory.clone()).await;
-            writer.write_all(&[5; 64]).await.expect("existing storage");
-            memory.set_sampled_limit(192, Duration::ZERO);
-            let error = writer
-                .write_all(&[9])
-                .await
-                .expect_err("expired sample cannot authorize replacement");
-            assert!(is_memory_pressure(&error));
-            assert_eq!(writer.get_inline_data(), Some(&[5; 64][..]));
-            assert_eq!(memory.snapshot().used, 64);
-            writer.write_all(&[]).await.expect("empty write needs no allocation");
-            writer.flush().await.expect("flush does not revoke storage");
-            writer.shutdown().await.expect("shutdown does not revoke storage");
-            let bytes = writer.into_inline_data().expect("export after expiry");
-            assert_eq!(bytes.as_ref(), &[5; 64]);
-            assert_eq!(memory.snapshot().used, 64);
-            drop(bytes);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn inline_writer_export_keeps_receipt_through_clones_and_the_last_slice() {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(64, Duration::from_secs(30));
-            let mut writer = writer_for(memory.clone()).await;
-            writer.write_all(&[11; 64]).await.expect("allocate payload");
-            let bytes = writer.into_inline_data().expect("export bytes");
-            let clone = bytes.clone();
-            let slice = bytes.slice(3..7);
-            memory.set_sampled_limit(0, Duration::ZERO);
-            drop(bytes);
-            drop(clone);
-            assert_eq!(slice.as_ref(), &[11; 4]);
-            assert_eq!(memory.snapshot().used, 64);
-            drop(slice);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn inline_writer_keeps_the_constructing_owner_after_leaving_its_scope() {
-            let first = BackgroundMemoryBudget::new();
-            first.set_sampled_limit(64, Duration::from_secs(30));
-            let mut writer = writer_for(first.clone()).await;
-            let second = BackgroundMemoryBudget::new();
-            let (resources, _) = test_resource_units(1);
-            with_optional_resource_unit(Some(resources.with_memory_budget(second.clone())), async {
-                writer.write_all(&[13; 64]).await.expect("writer still owns the first grant");
-            })
-            .await;
-            assert_eq!(first.snapshot().used, 64);
-            assert_eq!(second.snapshot().used, 0);
-            drop(writer);
-            assert_eq!(first.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn foreground_inline_writer_preserves_payload_and_empty_writes() {
-            let mut writer = CustomWriter::new_inline_buffer();
-            writer.write_all(&[]).await.expect("empty foreground write");
-            writer.write_all(b"inline body").await.expect("foreground write");
-            let bytes = writer.into_inline_data().expect("foreground export");
-            assert_eq!(bytes.as_ref(), b"inline body");
-        }
-    }
 }

crates/ecstore/src/erasure/coding/decode.rs

@@ -175,10 +175,8 @@ const DEFAULT_RUSTFS_GET_BITROT_DECODE_OVERLAP_ENABLE: bool = false;
 /// stripe via their stripe handle — only when a data shard is missing or dies.
 /// This halves per-GET read bytes, IOPS, and bitrot hashing on healthy
 /// objects with 2+2 layouts.
-/// Default: false for raw `Erasure::decode` calls without deferred parity
-/// handles; `DataBlocksFirst` reader setup attaches deferred parity handles and
-/// leaves those parity reserves unengaged by default unless this env var is set
-/// to `false`.
+/// Default: false (current behavior: every live shard reader is read on every
+/// stripe).
 const ENV_RUSTFS_GET_LOCKSTEP_DATA_SHARDS_ONLY_ENABLE: &str = "RUSTFS_GET_LOCKSTEP_DATA_SHARDS_ONLY_ENABLE";
 const DEFAULT_RUSTFS_GET_LOCKSTEP_DATA_SHARDS_ONLY_ENABLE: bool = false;
 
@@ -191,13 +189,6 @@ pub(crate) fn get_lockstep_data_shards_only_enabled() -> bool {
         )
 }
 
-/// Whether `DataBlocksFirst` reader setup and `with_deferred_parity_handles`
-/// should keep parity shards deferred until needed on healthy GETs.
-pub(crate) fn get_lockstep_data_shards_only_with_deferred_parity_enabled() -> bool {
-    matches!(decode_read_policy(), DecodeReadPolicy::DemandBound)
-        || rustfs_utils::get_env_bool(ENV_RUSTFS_GET_LOCKSTEP_DATA_SHARDS_ONLY_ENABLE, true)
-}
-
 /// Get whether bitrot-decode overlap is enabled.
 fn is_bitrot_decode_overlap_enabled() -> bool {
     rustfs_utils::get_env_bool(
@@ -841,13 +832,6 @@ where
     pub(crate) fn with_deferred_parity_handles(mut self, mut handles: Vec<Option<DeferredReaderStripeHandle>>) -> Self {
         handles.resize_with(self.readers.len(), || None);
         handles.truncate(self.readers.len());
-        if get_lockstep_data_shards_only_with_deferred_parity_enabled() {
-            for (index, handle) in handles.iter().enumerate().skip(self.data_shards) {
-                if handle.is_some() {
-                    self.engaged[index] = false;
-                }
-            }
-        }
         self.deferred_handles = handles;
         self
     }
@@ -2612,8 +2596,7 @@ impl Erasure {
         // the ordinary GET read quorum. Only the opt-in GET rollout requires a
         // surplus source; available surplus shards and integrity proofs are
         // still verified before any reconstructed copy bytes are emitted.
-        let require_surplus_source =
-            get_lockstep_data_shards_only_enabled() && matches!(decode_read_policy(), DecodeReadPolicy::Default);
+        let require_surplus_source = reader.demand_bound_lockstep && matches!(decode_read_policy(), DecodeReadPolicy::Default);
 
         let start = offset / self.block_size;
         let end = end_offset.saturating_sub(1) / self.block_size;
@@ -4384,9 +4367,9 @@ mod tests {
         .await;
     }
 
-    /// Compatibility lock: with the gate off (default), raw `Erasure::decode`
-    /// without deferred parity handles keeps the pre-backlog#923 behavior and
-    /// reads every live shard — including parity — on every stripe.
+    /// Compatibility lock: with the gate off (default), the lockstep path
+    /// keeps the pre-backlog#923 behavior and reads every live shard —
+    /// including parity — on every stripe.
     #[tokio::test]
     #[serial_test::serial]
     async fn test_lockstep_default_reads_all_shards_per_stripe() {

crates/ecstore/src/erasure/coding/erasure.rs

@@ -16,8 +16,6 @@
 //! Supports legacy (reed-solomon-simd) for reading/healing old-version files.
 //!
 
-use crate::disk::background_memory::{BackgroundBuffer, Reservation};
-use crate::disk::{BackgroundMemoryBudget, current_resource_unit};
 use bytes::{Bytes, BytesMut};
 use reed_solomon_simd;
 use rustfs_erasure_codec::galois_8::ReedSolomon;
@@ -146,54 +144,12 @@ pub fn calc_shard_size_legacy(block_size: usize, data_shards: usize) -> usize {
 
 /// Reed-Solomon encoder for legacy (main branch) format using reed-solomon-simd.
 /// Used when decoding/encoding files with uses_legacy_checksum == true.
-struct LegacyWorkspace<T> {
-    codec: T,
-    // The cached payload is freed before its reservation.
-    memory: Option<Reservation>,
-    payload_bound: usize,
-}
-
-impl<T> LegacyWorkspace<T> {
-    fn prepare(
-        cached: Option<Self>,
-        payload_bound: usize,
-        budget: Option<&Arc<BackgroundMemoryBudget>>,
-        create: impl FnOnce() -> io::Result<T>,
-        reset: impl FnOnce(&mut T) -> io::Result<()>,
-    ) -> io::Result<Self> {
-        if let Some(mut cached) = cached {
-            let reusable = match (&cached.memory, budget) {
-                (None, None) => true,
-                (Some(memory), budget) => {
-                    payload_bound <= cached.payload_bound && budget.is_none_or(|budget| memory.belongs_to(budget))
-                }
-                // Uncharged foreground caches can have larger retained Vec
-                // capacities after reset; start a measured background workspace.
-                (None, Some(_)) => false,
-            };
-            if reusable && reset(&mut cached.codec).is_ok() {
-                return Ok(cached);
-            }
-            // A fresh allocation avoids hidden geometric Vec growth. No payload
-            // references escape codec calls, so dropping this cache is safe.
-            drop(cached);
-        }
-        let memory = budget.map(|budget| budget.reserve(payload_bound)).transpose()?;
-        let codec = create()?;
-        Ok(Self {
-            codec,
-            memory,
-            payload_bound,
-        })
-    }
-}
-
 struct LegacyReedSolomonEncoder {
     data_shards: usize,
     parity_shards: usize,
     cache_workspaces: bool,
-    encoder_cache: RwLock<Option<LegacyWorkspace<reed_solomon_simd::ReedSolomonEncoder>>>,
-    decoder_cache: RwLock<Option<LegacyWorkspace<reed_solomon_simd::ReedSolomonDecoder>>>,
+    encoder_cache: RwLock<Option<reed_solomon_simd::ReedSolomonEncoder>>,
+    decoder_cache: RwLock<Option<reed_solomon_simd::ReedSolomonDecoder>>,
 }
 
 impl LegacyReedSolomonEncoder {
@@ -243,29 +199,20 @@ impl LegacyReedSolomonEncoder {
             .write()
             .map_err(|_| io::Error::other("Failed to acquire encoder cache lock"))?
             .take();
-        let budget = current_resource_unit().and_then(|resources| resources.memory_budget());
-        // reed-solomon-simd 3.1.0 Shards::resize allocates 64-byte units. A
-        // fresh Vec has at least four units; the decoder work-count bound also
-        // covers both encoder rate strategies.
-        let payload_bound = self
-            .logical_shard_bytes_upper_bound(shard_len)
-            .ok_or(io::ErrorKind::OutOfMemory)?
-            .max(256);
-        let mut workspace = LegacyWorkspace::prepare(
-            cached_encoder,
-            payload_bound,
-            budget.as_ref(),
-            || {
-                reed_solomon_simd::ReedSolomonEncoder::new(self.data_shards, self.parity_shards, shard_len)
-                    .map_err(|e| io::Error::other(format!("Failed to create SIMD encoder: {e:?}")))
-            },
-            |encoder| {
-                encoder
-                    .reset(self.data_shards, self.parity_shards, shard_len)
-                    .map_err(|e| io::Error::other(format!("Failed to reset SIMD encoder: {e:?}")))
-            },
-        )?;
-        let encoder = &mut workspace.codec;
+        let mut encoder = {
+            match cached_encoder {
+                Some(mut cached) => {
+                    if cached.reset(self.data_shards, self.parity_shards, shard_len).is_err() {
+                        reed_solomon_simd::ReedSolomonEncoder::new(self.data_shards, self.parity_shards, shard_len)
+                            .map_err(|e| io::Error::other(format!("Failed to create SIMD encoder: {e:?}")))?
+                    } else {
+                        cached
+                    }
+                }
+                None => reed_solomon_simd::ReedSolomonEncoder::new(self.data_shards, self.parity_shards, shard_len)
+                    .map_err(|e| io::Error::other(format!("Failed to create SIMD encoder: {e:?}")))?,
+            }
+        };
         for (i, shard) in shards.iter().enumerate().take(self.data_shards) {
             encoder
                 .add_original_shard(shard)
@@ -286,7 +233,7 @@ impl LegacyReedSolomonEncoder {
                 .write()
                 .map_err(|_| io::Error::other("Failed to return encoder to cache"))?;
             if cache.is_none() {
-                *cache = Some(workspace);
+                *cache = Some(encoder);
             }
         }
         Ok(())
@@ -307,26 +254,21 @@ impl LegacyReedSolomonEncoder {
             .write()
             .map_err(|_| io::Error::other("Failed to acquire decoder cache lock"))?
             .take();
-        let budget = current_resource_unit().and_then(|resources| resources.memory_budget());
-        let payload_bound = self
-            .logical_shard_bytes_upper_bound(shard_len)
-            .ok_or(io::ErrorKind::OutOfMemory)?
-            .max(256);
-        let mut workspace = LegacyWorkspace::prepare(
-            cached_decoder,
-            payload_bound,
-            budget.as_ref(),
-            || {
-                reed_solomon_simd::ReedSolomonDecoder::new(self.data_shards, self.parity_shards, shard_len)
-                    .map_err(|e| io::Error::other(format!("Failed to create SIMD decoder: {e:?}")))
-            },
-            |decoder| {
-                decoder
-                    .reset(self.data_shards, self.parity_shards, shard_len)
-                    .map_err(|e| io::Error::other(format!("Failed to reset SIMD decoder: {e:?}")))
-            },
-        )?;
-        let decoder = &mut workspace.codec;
+        let mut decoder = {
+            match cached_decoder {
+                Some(mut cached_decoder) => {
+                    if let Err(e) = cached_decoder.reset(self.data_shards, self.parity_shards, shard_len) {
+                        warn!("Failed to reset SIMD decoder: {:?}, creating new one", e);
+                        reed_solomon_simd::ReedSolomonDecoder::new(self.data_shards, self.parity_shards, shard_len)
+                            .map_err(|e| io::Error::other(format!("Failed to create SIMD decoder: {e:?}")))?
+                    } else {
+                        cached_decoder
+                    }
+                }
+                None => reed_solomon_simd::ReedSolomonDecoder::new(self.data_shards, self.parity_shards, shard_len)
+                    .map_err(|e| io::Error::other(format!("Failed to create SIMD decoder: {e:?}")))?,
+            }
+        };
 
         for (i, shard_opt) in shards.iter().enumerate() {
             if let Some(shard) = shard_opt {
@@ -366,7 +308,7 @@ impl LegacyReedSolomonEncoder {
                 .write()
                 .map_err(|_| io::Error::other("Failed to return decoder to cache"))?;
             if cache.is_none() {
-                *cache = Some(workspace);
+                *cache = Some(decoder);
             }
         }
 
@@ -391,13 +333,6 @@ impl LegacyReedSolomonEncoder {
             return Ok(true);
         }
 
-        let expected_bytes = shards.iter().try_fold(0usize, |total, shard| {
-            total
-                .checked_add(shard.len())
-                .ok_or_else(|| io::Error::from(io::ErrorKind::OutOfMemory))
-        })?;
-        let memory = current_resource_unit().and_then(|resources| resources.memory_budget());
-        let _expected_memory = memory.as_ref().map(|memory| memory.reserve(expected_bytes)).transpose()?;
         let mut expected = shards.iter().map(|shard| Some(shard.to_vec())).collect::<Vec<_>>();
         self.encode_parity(&mut expected)?;
 
@@ -496,18 +431,8 @@ impl ReedSolomonEncoder {
         }
 
         if let Some(ref rs) = self.encoder {
-            let result = if let Some(memory) = current_resource_unit().and_then(|resources| resources.memory_budget())
-                && let Some(shard_len) = shards.first().map(|shard| shard.len()).filter(|len| *len != 0)
-            {
-                let scratch_len = shard_len.checked_mul(self.parity_shards).ok_or(io::ErrorKind::OutOfMemory)?;
-                let mut scratch = BackgroundBuffer::new(Some(memory));
-                scratch.ensure_len(scratch_len)?;
-                let mut buffers: SmallVec<[&mut [u8]; 16]> = scratch.as_mut_slice().chunks_mut(shard_len).collect();
-                rs.verify_with_buffer(shards, &mut buffers)
-            } else {
-                rs.verify(shards)
-            };
-            result.map_err(|e| io::Error::other(format!("Reed-Solomon verify failed: {e:?}")))
+            rs.verify(shards)
+                .map_err(|e| io::Error::other(format!("Reed-Solomon verify failed: {e:?}")))
         } else {
             Ok(true)
         }
@@ -1275,105 +1200,6 @@ impl Erasure {
 #[cfg(test)]
 mod tests {
     use super::*;
-
-    #[tokio::test]
-    async fn background_legacy_workspaces_keep_their_memory_in_cache() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-        use std::time::Duration;
-
-        let codec = LegacyReedSolomonEncoder::with_workspace_cache(2, 1, true).expect("isolated cached codec");
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(512, Duration::from_secs(30));
-        let mut shards = [vec![7; 8], vec![9; 8], vec![0; 8]];
-        let (resources, _) = test_resource_units(1);
-        with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            codec
-                .encode(shards.iter_mut().map(Vec::as_mut_slice).collect())
-                .expect("accounted encoder");
-        })
-        .await;
-        assert_eq!(memory.snapshot().used, 256, "fresh SIMD work storage uses at most four 64-byte units");
-        memory.set_sampled_limit(0, Duration::ZERO);
-        let (resources, _) = test_resource_units(1);
-        with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            codec
-                .encode(shards.iter_mut().map(Vec::as_mut_slice).collect())
-                .expect("cached payload survives shrink");
-        })
-        .await;
-        assert_eq!(memory.snapshot().used, 256);
-
-        memory.set_sampled_limit(512, Duration::from_secs(30));
-        let mut decoded = vec![None, Some(shards[1].clone()), Some(shards[2].clone())];
-        let (resources, _) = test_resource_units(1);
-        with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            codec.reconstruct_data(&mut decoded).expect("accounted decoder");
-        })
-        .await;
-        assert_eq!(decoded[0].as_deref(), Some(shards[0].as_slice()));
-        assert_eq!(memory.snapshot().used, 512, "both cached codec payloads remain charged");
-        drop(codec);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn background_legacy_cache_cannot_reuse_a_different_memory_owner() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-        use std::time::Duration;
-
-        let codec = LegacyReedSolomonEncoder::with_workspace_cache(2, 1, true).expect("isolated cached codec");
-        let first = BackgroundMemoryBudget::new();
-        first.set_sampled_limit(256, Duration::from_secs(30));
-        let mut shards = [vec![7; 8], vec![9; 8], vec![0; 8]];
-        let (resources, _) = test_resource_units(1);
-        with_optional_resource_unit(Some(resources.with_memory_budget(first.clone())), async {
-            codec
-                .encode(shards.iter_mut().map(Vec::as_mut_slice).collect())
-                .expect("first owner");
-        })
-        .await;
-        let second = BackgroundMemoryBudget::new();
-        let (resources, _) = test_resource_units(1);
-        let error = with_optional_resource_unit(Some(resources.with_memory_budget(second.clone())), async {
-            codec.encode(shards.iter_mut().map(Vec::as_mut_slice).collect())
-        })
-        .await
-        .expect_err("a foreign cache must not bypass a closed owner");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        assert_eq!(first.snapshot().used, 0);
-        assert_eq!(second.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn background_modern_verification_charges_scratch_and_preserves_invalid_input_errors() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-        use std::time::Duration;
-
-        let codec = ReedSolomonEncoder::new(2, 1).expect("modern codec");
-        let mut shards = [vec![7; 8], vec![9; 8], vec![0; 8]];
-        codec
-            .encode(shards.iter_mut().map(Vec::as_mut_slice).collect())
-            .expect("valid parity");
-        let refs: Vec<_> = shards.iter().map(Vec::as_slice).collect();
-        let memory = BackgroundMemoryBudget::new();
-        let (resources, _) = test_resource_units(1);
-        let error =
-            with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async { codec.verify(&refs) })
-                .await
-                .expect_err("closed owner rejects verification scratch");
-        assert_eq!(error.kind(), io::ErrorKind::WouldBlock);
-        memory.set_sampled_limit(8, Duration::from_secs(30));
-        let (resources, _) = test_resource_units(1);
-        with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-            assert!(codec.verify(&refs).expect("exact parity scratch fits"));
-            assert!(
-                codec.verify(&[&[], &[9; 8], &[0; 8]]).is_err(),
-                "empty first shard remains an error instead of a panic"
-            );
-        })
-        .await;
-        assert_eq!(memory.snapshot().used, 0);
-    }
     use proptest::collection::{btree_set, vec};
     use proptest::prelude::*;
     use std::pin::Pin;

crates/ecstore/src/erasure/coding/heal.rs

@@ -12,10 +12,8 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::disk::background_memory::{Reservation, is_memory_pressure};
 use crate::disk::disk_store::get_object_disk_read_timeout;
 use crate::disk::error::{Error, Result};
-use crate::disk::{BackgroundMemoryBudget, current_resource_unit};
 use crate::erasure::coding::BitrotReader;
 use crate::erasure::coding::BitrotWriterWrapper;
 use crate::erasure::coding::encode::MultiWriter;
@@ -24,7 +22,6 @@ use futures::StreamExt;
 use futures::stream::FuturesUnordered;
 use std::io;
 use std::io::ErrorKind;
-use std::sync::Arc;
 use std::time::Duration;
 use tokio::io::AsyncRead;
 use tracing::{trace, warn};
@@ -33,53 +30,21 @@ const LOG_COMPONENT_ECSTORE: &str = "ecstore";
 const LOG_SUBSYSTEM_ERASURE: &str = "erasure";
 const EVENT_ERASURE_HEAL_STARTED: &str = "erasure_heal_started";
 
-struct HealShards {
-    // Drop payloads before refunding their reservations on every error path.
-    shards: Vec<Option<Vec<u8>>>,
-    memory: Vec<Option<Reservation>>,
-    budget: Option<Arc<BackgroundMemoryBudget>>,
-}
-
-impl HealShards {
-    fn reserve_missing(&mut self, shard_size: usize) -> io::Result<()> {
-        if let Some(budget) = &self.budget {
-            for (shard, memory) in self.shards.iter().zip(&mut self.memory) {
-                if shard.is_none() {
-                    *memory = Some(budget.reserve(shard_size)?);
-                }
-            }
-        }
-        Ok(())
-    }
-
-    fn into_bytes(self) -> Vec<Bytes> {
-        self.shards
-            .into_iter()
-            .zip(self.memory)
-            .map(|(shard, memory)| Reservation::wrap(Bytes::from(shard.unwrap_or_default()), memory))
-            .collect()
-    }
-}
-
 async fn read_heal_shards<R>(
     readers: &mut [Option<BitrotReader<R>>],
     shard_size: usize,
     read_timeout: Duration,
-) -> Result<(HealShards, Vec<Option<Error>>)>
+) -> (Vec<Option<Vec<u8>>>, Vec<Option<Error>>)
 where
     R: AsyncRead + Unpin + Send + Sync,
 {
     let num_readers = readers.len();
-    let mut shards = HealShards {
-        shards: vec![None; num_readers],
-        memory: std::iter::repeat_with(|| None).take(num_readers).collect(),
-        budget: current_resource_unit().and_then(|resources| resources.memory_budget()),
-    };
+    let mut shards = vec![None; num_readers];
     let mut errs = vec![None; num_readers];
     let mut retire_readers = Vec::new();
 
     if shard_size == 0 {
-        return Ok((shards, errs));
+        return (shards, errs);
     }
 
     {
@@ -90,17 +55,8 @@ where
                 continue;
             };
 
-            let budget = shards.budget.clone();
             futures.push(Box::pin(async move {
-                let memory = match budget.as_ref().map(|budget| budget.reserve(shard_size)).transpose() {
-                    Ok(memory) => memory,
-                    Err(error) => return (index, Err(Error::from(error)), false),
-                };
-                let mut buf = Vec::new();
-                if buf.try_reserve_exact(shard_size).is_err() {
-                    return (index, Err(Error::from(io::Error::from(ErrorKind::OutOfMemory))), false);
-                }
-                buf.resize(shard_size, 0);
+                let mut buf = vec![0; shard_size];
                 let read_result = if read_timeout.is_zero() {
                     reader.read(&mut buf).await
                 } else {
@@ -119,7 +75,7 @@ where
                 match read_result {
                     Ok(n) => {
                         buf.truncate(n);
-                        (index, Ok((buf, memory)), false)
+                        (index, Ok(buf), false)
                     }
                     Err(err) => {
                         let should_retire = err.kind() == ErrorKind::TimedOut;
@@ -131,14 +87,10 @@ where
 
         while let Some((index, result, should_retire)) = futures.next().await {
             match result {
-                Ok((shard, memory)) => {
-                    shards.shards[index] = Some(shard);
-                    shards.memory[index] = memory;
+                Ok(shard) => {
+                    shards[index] = Some(shard);
                 }
                 Err(err) => {
-                    if matches!(&err, Error::Io(error) if is_memory_pressure(error)) {
-                        return Err(err);
-                    }
                     errs[index] = Some(err);
                     if should_retire {
                         retire_readers.push(index);
@@ -153,7 +105,7 @@ where
         warn!(shard_index = index, "retiring timed-out heal shard reader");
     }
 
-    Ok((shards, errs))
+    (shards, errs)
 }
 
 fn heal_writer_failure(writers: &mut MultiWriter<'_>, error: io::Error) -> Error {
@@ -212,7 +164,7 @@ impl super::Erasure {
         for block_index in start_block..end_block {
             let shard_offset = block_index * self.shard_size();
             let shard_size = self.shard_size().min(shard_file_size.saturating_sub(shard_offset));
-            let (mut owned_shards, errs) = read_heal_shards(&mut readers, shard_size, read_timeout).await?;
+            let (mut shards, errs) = read_heal_shards(&mut readers, shard_size, read_timeout).await;
 
             // Every source shard is already bitrot-verified by its reader, so any
             // data_shards survivors are sufficient to reconstruct — requiring more
@@ -231,24 +183,6 @@ impl super::Erasure {
                 return Err(Error::ErasureReadQuorum);
             }
 
-            owned_shards.reserve_missing(shard_size)?;
-            let source_parity_bytes =
-                owned_shards
-                    .shards
-                    .iter()
-                    .skip(self.data_shards)
-                    .flatten()
-                    .try_fold(0usize, |total, shard| {
-                        total
-                            .checked_add(shard.len())
-                            .ok_or_else(|| io::Error::from(ErrorKind::OutOfMemory))
-                    })?;
-            let _source_memory = owned_shards
-                .budget
-                .as_ref()
-                .map(|budget| budget.reserve(source_parity_bytes))
-                .transpose()?;
-            let shards = &mut owned_shards.shards;
             let source_parity = shards
                 .iter()
                 .enumerate()
@@ -256,23 +190,24 @@ impl super::Erasure {
                 .filter_map(|(index, shard)| shard.as_ref().map(|shard| (index, shard.clone())))
                 .collect::<Vec<_>>();
             if self.parity_shards > 0 {
-                self.decode_data_and_parity(shards)?;
-                if !source_parity.is_empty() && !self.verify_data_and_parity(shards)? {
+                self.decode_data_and_parity(&mut shards)?;
+                if !source_parity.is_empty() && !self.verify_data_and_parity(&shards)? {
                     return Err(Error::other("can not reconstruct data: inconsistent heal source shards"));
                 }
-                for (index, source) in &source_parity {
-                    let Some(rebuilt) = shards[*index].as_ref() else {
+                for (index, source) in source_parity {
+                    let Some(rebuilt) = shards[index].as_ref() else {
                         return Err(Error::other("can not reconstruct data: missing rebuilt parity shard"));
                     };
-                    if rebuilt != source {
+                    if rebuilt != &source {
                         return Err(Error::other("can not reconstruct data: inconsistent heal source shards"));
                     }
                 }
             }
 
-            drop(source_parity);
-            drop(_source_memory);
-            let shards = owned_shards.into_bytes();
+            let shards = shards
+                .into_iter()
+                .map(|s| Bytes::from(s.unwrap_or_default()))
+                .collect::<Vec<_>>();
 
             if let Err(error) = writers.write(shards).await {
                 return Err(heal_writer_failure(&mut writers, error));
@@ -371,90 +306,6 @@ mod tests {
         BitrotWriterWrapper::new(CustomWriter::new_inline_buffer(), shard_size, HashAlgorithm::None)
     }
 
-    #[tokio::test]
-    async fn heal_shards_retain_memory_through_missing_outputs_and_last_slice() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(24, Duration::from_secs(30));
-        let mut readers = vec![
-            Some(BitrotReader::new(Cursor::new(vec![7; 8]), 8, HashAlgorithm::None, false)),
-            None,
-            Some(BitrotReader::new(Cursor::new(vec![9; 8]), 8, HashAlgorithm::None, false)),
-        ];
-        let (resources, _) = test_resource_units(1);
-        let (mut shards, _) = with_optional_resource_unit(
-            Some(resources.with_memory_budget(memory.clone())),
-            read_heal_shards(&mut readers, 8, Duration::ZERO),
-        )
-        .await
-        .expect("read two accounted shards");
-        assert_eq!(memory.snapshot().used, 16);
-        shards
-            .reserve_missing(8)
-            .expect("reserve the reconstructed output before allocation");
-        shards.shards[1] = Some(vec![11; 8]);
-        assert_eq!(memory.snapshot().used, 24);
-        let bytes = shards.into_bytes();
-        let slice = bytes[1].slice(1..3);
-        memory.set_sampled_limit(0, Duration::ZERO);
-        drop(bytes);
-        assert_eq!(slice.as_ref(), &[11; 2]);
-        assert_eq!(memory.snapshot().used, 8);
-        drop(slice);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
-    #[tokio::test]
-    async fn heal_memory_denial_is_not_replaced_with_read_quorum() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-
-        let erasure = Erasure::new(2, 1, 16);
-        let encoded = erasure.encode_data(&[37; 16]).expect("valid source shards");
-        for limit in [0, 23, 31, 39] {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(limit, Duration::from_secs(30));
-            let readers = encoded
-                .iter()
-                .map(|shard| Some(BitrotReader::new(Cursor::new(shard.clone()), 8, HashAlgorithm::None, false)))
-                .collect();
-            let mut writers = vec![Some(inline_writer(8)), None, None];
-            let (resources, _) = test_resource_units(1);
-            let result = with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                erasure.heal(&mut writers, readers, 16, &[]),
-            )
-            .await;
-            assert!(
-                matches!(result, Err(Error::Io(error)) if error.kind() == ErrorKind::WouldBlock),
-                "limit={limit}"
-            );
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
-
-    #[tokio::test]
-    async fn cancelled_heal_shard_reads_release_allocated_payloads() {
-        use crate::disk::{test_resource_units, with_optional_resource_unit};
-
-        let memory = BackgroundMemoryBudget::new();
-        memory.set_sampled_limit(16, Duration::from_secs(30));
-        let mut readers = vec![
-            Some(BitrotReader::new(PendingReader, 8, HashAlgorithm::None, false)),
-            Some(BitrotReader::new(PendingReader, 8, HashAlgorithm::None, false)),
-        ];
-        let (resources, _) = test_resource_units(1);
-        let mut read = Box::pin(with_optional_resource_unit(
-            Some(resources.with_memory_budget(memory.clone())),
-            read_heal_shards(&mut readers, 8, Duration::ZERO),
-        ));
-        assert!(futures::poll!(&mut read).is_pending());
-        assert_eq!(memory.snapshot().used, 16);
-        memory.set_sampled_limit(0, Duration::ZERO);
-        drop(read);
-        assert_eq!(memory.snapshot().used, 0);
-    }
-
     #[tokio::test]
     async fn read_heal_shards_returns_empty_slots_for_zero_sized_shards() {
         let mut readers = vec![
@@ -462,11 +313,9 @@ mod tests {
             None,
         ];
 
-        let (shards, errs) = read_heal_shards(&mut readers, 0, Duration::ZERO)
-            .await
-            .expect("empty read succeeds");
+        let (shards, errs) = read_heal_shards(&mut readers, 0, Duration::ZERO).await;
 
-        assert_eq!(shards.shards, vec![None, None]);
+        assert_eq!(shards, vec![None, None]);
         assert_eq!(errs, vec![None, None]);
     }
 
@@ -474,11 +323,9 @@ mod tests {
     async fn read_heal_shards_records_reader_errors_and_retiring_timeouts() {
         let mut readers = vec![Some(BitrotReader::new(FailingReader, 4, HashAlgorithm::None, false))];
 
-        let (shards, errs) = read_heal_shards(&mut readers, 4, Duration::ZERO)
-            .await
-            .expect("ordinary failures remain per-shard");
+        let (shards, errs) = read_heal_shards(&mut readers, 4, Duration::ZERO).await;
 
-        assert!(shards.shards[0].is_none());
+        assert!(shards[0].is_none());
         assert!(
             errs[0]
                 .as_ref()
@@ -487,11 +334,9 @@ mod tests {
         assert!(readers[0].is_some(), "ordinary read errors must not retire readers");
 
         let mut timeout_readers = vec![Some(BitrotReader::new(PendingReader, 4, HashAlgorithm::None, false))];
-        let (shards, errs) = read_heal_shards(&mut timeout_readers, 4, Duration::from_millis(1))
-            .await
-            .expect("timeouts remain per-shard");
+        let (shards, errs) = read_heal_shards(&mut timeout_readers, 4, Duration::from_millis(1)).await;
 
-        assert_eq!(shards.shards, vec![None]);
+        assert_eq!(shards, vec![None]);
         assert!(errs[0].as_ref().is_some_and(|err| err.to_string().contains("timed out")));
         assert!(timeout_readers[0].is_none(), "timed-out readers are retired");
     }

crates/ecstore/src/io_support/bitrot.rs

@@ -828,27 +828,13 @@ pub async fn create_bitrot_writer(
     length: i64,
     shard_size: usize,
     checksum_algo: HashAlgorithm,
-) -> disk::error::Result<BitrotWriterWrapper> {
-    create_bitrot_writer_with_orig_volume(is_inline_buffer, disk, "", volume, path, length, shard_size, checksum_algo).await
-}
-
-#[allow(clippy::too_many_arguments)]
-pub async fn create_bitrot_writer_with_orig_volume(
-    is_inline_buffer: bool,
-    disk: Option<&DiskStore>,
-    origvolume: &str,
-    volume: &str,
-    path: &str,
-    length: i64,
-    shard_size: usize,
-    checksum_algo: HashAlgorithm,
 ) -> disk::error::Result<BitrotWriterWrapper> {
     let writer = if is_inline_buffer {
         CustomWriter::new_inline_buffer()
     } else if let Some(disk) = disk {
         let length = bitrot_create_file_size(length, shard_size, &checksum_algo);
 
-        let file = disk.create_file(origvolume, volume, path, length).await?;
+        let file = disk.create_file("", volume, path, length).await?;
         #[cfg(feature = "hotpath")]
         let file = instrument_raw_shard_writer(file, disk.is_local());
         CustomWriter::new_tokio_writer(file)
@@ -1550,7 +1536,7 @@ mod tests {
             writer.write(chunk).await.expect("write chunk");
         }
 
-        let inline_data = writer.into_inline_data().expect("inline buffer");
+        let inline_data = Bytes::from(writer.into_inline_data().expect("inline buffer"));
         let mut reader = create_bitrot_reader_from_bytes(
             Some(inline_data),
             None,
@@ -1598,7 +1584,7 @@ mod tests {
 
         let inline_data = writer.into_inline_data().expect("inline buffer");
         let mut reader = create_deferred_bitrot_reader(
-            Some(inline_data),
+            Some(inline_data.into()),
             None,
             "test-bucket",
             "test-path",
@@ -1640,7 +1626,7 @@ mod tests {
 
             for stripe in 0..payload.len() / shard_size {
                 let (mut reader, handle) = create_deferred_bitrot_reader_with_stripe_handle(
-                    Some(inline_data.clone()),
+                    Some(inline_data.clone().into()),
                     None,
                     "test-bucket",
                     "test-path",
@@ -1685,7 +1671,7 @@ mod tests {
         for chunk in payload.chunks(shard_size) {
             writer.write(chunk).await.expect("write chunk");
         }
-        let mut inline_data = writer.into_inline_data().expect("inline buffer").to_vec();
+        let mut inline_data = writer.into_inline_data().expect("inline buffer");
 
         // Corrupt one payload byte of block 2 (blocks are hash + data).
         let block_len = algo.size() + shard_size;
@@ -1732,7 +1718,7 @@ mod tests {
         let inline_data = writer.into_inline_data().expect("inline buffer");
 
         let (mut reader, handle) = create_deferred_bitrot_reader_with_stripe_handle(
-            Some(inline_data),
+            Some(inline_data.into()),
             None,
             "test-bucket",
             "test-path",
@@ -1859,122 +1845,4 @@ mod tests {
 
         assert_eq!(output, data);
     }
-
-    mod inline_memory_regressions {
-        use super::*;
-        use crate::disk::background_memory::Reservation;
-        use crate::disk::{BackgroundMemoryBudget, test_resource_units, with_optional_resource_unit};
-        use std::time::Duration;
-
-        #[tokio::test]
-        async fn owned_inline_reader_retains_existing_receipt_without_a_new_grant() {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(64, Duration::from_secs(30));
-            let receipt = memory.reserve(64).expect("existing metadata payload grant");
-            let bytes = Reservation::wrap(Bytes::from(vec![7; 64]), Some(receipt));
-            memory.set_sampled_limit(0, Duration::ZERO);
-            let (resources, _) = test_resource_units(1);
-            let mut reader = with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                create_bitrot_reader_from_bytes(
-                    Some(bytes.clone()),
-                    None,
-                    "bucket",
-                    "inline",
-                    0,
-                    64,
-                    64,
-                    HashAlgorithm::None,
-                    false,
-                    false,
-                ),
-            )
-            .await
-            .expect("owned data requires no allocation")
-            .expect("inline reader");
-            drop(bytes);
-            assert_eq!(memory.snapshot().used, 64, "the source owner must remain attached to the reader");
-            let mut output = [0; 64];
-            assert_eq!(reader.read(&mut output).await.expect("read existing payload"), 64);
-            assert_eq!(output, [7; 64]);
-            assert_eq!(memory.snapshot().used, 64);
-            drop(reader);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn accounted_inline_writer_round_trips_bitrot_and_preserves_export_lifetime() {
-            let memory = BackgroundMemoryBudget::new();
-            memory.set_sampled_limit(192, Duration::from_secs(30));
-            let (resources, _) = test_resource_units(1);
-            let bytes = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                let mut writer = create_bitrot_writer(true, None, "bucket", "inline", 64, 64, HashAlgorithm::HighwayHash256S)
-                    .await
-                    .expect("inline writer");
-                assert_eq!(writer.write(&[19; 64]).await.expect("complete shard"), 64);
-                writer.shutdown().await.expect("shutdown");
-                writer.into_inline_data().expect("bitrot bytes")
-            })
-            .await;
-            assert_eq!(bytes.len(), 96);
-            assert_eq!(memory.snapshot().used, 96, "exported [hash][shard] remains charged");
-            let (resources, _) = test_resource_units(1);
-            let mut reader = with_optional_resource_unit(
-                Some(resources.with_memory_budget(memory.clone())),
-                create_bitrot_reader_from_bytes(
-                    Some(bytes.clone()),
-                    None,
-                    "bucket",
-                    "inline",
-                    0,
-                    64,
-                    64,
-                    HashAlgorithm::HighwayHash256S,
-                    false,
-                    false,
-                ),
-            )
-            .await
-            .expect("reader")
-            .expect("inline reader");
-            let mut output = [0; 64];
-            assert_eq!(reader.read(&mut output).await.expect("bitrot remains verified"), 64);
-            assert_eq!(output, [19; 64]);
-            assert_eq!(memory.snapshot().used, 192, "input owner and verification scratch are both live");
-            drop(reader);
-            assert_eq!(memory.snapshot().used, 96);
-            let slice = bytes.slice(32..36);
-            drop(bytes);
-            assert_eq!(memory.snapshot().used, 96);
-            drop(slice);
-            assert_eq!(memory.snapshot().used, 0);
-        }
-
-        #[tokio::test]
-        async fn inline_heal_writer_memory_denial_is_retryable_after_read_and_verify_fit() {
-            use crate::erasure::coding::Erasure;
-            let erasure = Erasure::new(2, 1, 16);
-            let encoded = erasure.encode_data(&[37; 16]).expect("foreground test fixture");
-            let readers = encoded
-                .into_iter()
-                .map(|shard| Some(BitrotReader::new(Cursor::new(shard), 8, HashAlgorithm::None, false)))
-                .collect();
-            let memory = BackgroundMemoryBudget::new();
-            // Read shards: 24 bytes; source parity: 8; verify scratch: 8.
-            // After verification, input shards still use 24. The target needs a
-            // new 40-byte [hash][shard] allocation and must fail before copying.
-            memory.set_sampled_limit(40, Duration::from_secs(30));
-            let (resources, _) = test_resource_units(1);
-            let result = with_optional_resource_unit(Some(resources.with_memory_budget(memory.clone())), async {
-                let writer = create_bitrot_writer(true, None, "bucket", "inline", 8, 8, HashAlgorithm::HighwayHash256S)
-                    .await
-                    .expect("writer setup does not allocate payload");
-                let mut writers = vec![Some(writer), None, None];
-                erasure.heal(&mut writers, readers, 16, &[]).await
-            })
-            .await;
-            assert!(matches!(result, Err(DiskError::Io(error)) if error.kind() == io::ErrorKind::WouldBlock));
-            assert_eq!(memory.snapshot().used, 0);
-        }
-    }
 }

crates/ecstore/src/io_support/rio.rs

@@ -429,7 +429,6 @@ impl WritePlan {
         let checksum = reader.content_hash().clone();
         let trailer = reader.get_trailer().cloned();
 
-        let delegate_inner_etag = self.compression.is_none() && reader.is_etag_reader();
         let encrypted = self.encryption.is_some();
         if let Some(algorithm) = self.compression {
             reader = HashReader::from_reader(
@@ -449,8 +448,7 @@ impl WritePlan {
                 }
                 WriteEncryptionMode::SinglepartObjectKey | WriteEncryptionMode::MultipartObjectKey { .. } => [0u8; 12],
             };
-            let protected_reader = rustfs_rio::EtagReader::new_encrypted(reader, encryption.key_bytes, etag_nonce)?
-                .with_inner_etag_delegation(delegate_inner_etag);
+            let protected_reader = rustfs_rio::EtagReader::new_encrypted(reader, encryption.key_bytes, etag_nonce)?;
             reader = match encryption.mode {
                 WriteEncryptionMode::SinglepartObjectKey => HashReader::from_reader(
                     #[cfg(feature = "rio-v2")]

crates/ecstore/src/io_support/shard_integrity.rs

@@ -333,34 +333,6 @@ struct ProofCache {
     preferred: usize,
 }
 
-type VerifiedStripeKey = (uuid::Uuid, [u8; 32], u32);
-
-static VERIFIED_STRIPE_RECORDS: std::sync::LazyLock<parking_lot::Mutex<std::collections::HashMap<VerifiedStripeKey, Bytes>>> =
-    std::sync::LazyLock::new(|| parking_lot::Mutex::new(std::collections::HashMap::new()));
-
-fn get_verified_stripe_record(part: &PartIntegrity, stripe: u32) -> Option<Bytes> {
-    VERIFIED_STRIPE_RECORDS
-        .lock()
-        .get(&(part.generation, part.root, stripe))
-        .cloned()
-}
-
-fn put_verified_stripe_record(part: &PartIntegrity, stripe: u32, record: Bytes) {
-    let mut map = VERIFIED_STRIPE_RECORDS.lock();
-    if map.len() >= 4096
-        && let Some(evict_key) = map.keys().next().copied()
-    {
-        map.remove(&evict_key);
-    }
-    map.insert((part.generation, part.root, stripe), record);
-}
-
-pub(crate) fn invalidate_verified_stripe_records(generation: uuid::Uuid) {
-    VERIFIED_STRIPE_RECORDS
-        .lock()
-        .retain(|(stored_gen, _, _), _| *stored_gen != generation);
-}
-
 impl PartProofReader {
     pub(crate) async fn reconstruction_proof(
         &self,
@@ -438,9 +410,6 @@ impl PartProofReader {
 
     pub(crate) async fn record(&self, stripe: u32) -> io::Result<Bytes> {
         let offset = self.part.record_offset(stripe).map_err(|_| corrupt())?;
-        if let Some(bytes) = get_verified_stripe_record(&self.part, stripe) {
-            return Ok(bytes);
-        }
         let mut cached = self.cached.lock().await;
         if let Some((_, bytes)) = cached.records.iter().find(|(number, _)| *number == stripe) {
             return Ok(bytes.clone());
@@ -496,9 +465,6 @@ impl PartProofReader {
             bytes
         };
         self.part.verify_record(stripe, &record).map_err(|_| corrupt())?;
-        if self.part.stripes <= 4 {
-            put_verified_stripe_record(&self.part, stripe, record.clone());
-        }
         if cached.records.len() == 2 {
             cached.records.pop_front();
         }
@@ -897,41 +863,4 @@ mod tests {
             prepared.part.verify_shard(stripe, 15, b"x", &record).expect("spilled proof");
         }
     }
-
-    #[tokio::test]
-    async fn verified_stripe_record_cache_serves_verified_record_and_still_verifies_payload() {
-        let layout = IntegrityLayout::new(2, 2, 8, false).expect("layout");
-        let mut builder = IntegrityBuilder::new(layout, 1).expect("builder");
-        let shards = [b"ABCD".as_slice(), b"EFGH", b"IJKL", b"MNOP"];
-        builder.push(shards.into_iter()).await.expect("stripe");
-        let prepared = builder.finish(8).await.expect("index");
-        let inline_bytes = prepared.inline_bytes().expect("inline bytes");
-        let part = prepared.part;
-
-        let warm_reader = PartProofReader {
-            part: part.clone(),
-            sources: Vec::new(),
-            volume: "bucket".to_owned(),
-            inline: Some(inline_bytes),
-            cached: Mutex::new(ProofCache::default()),
-        };
-        warm_reader.verify(0, 0, shards[0]).await.expect("warm verify");
-        assert!(
-            get_verified_stripe_record(&part, 0).is_some(),
-            "small verified stripe record should populate the verified stripe cache"
-        );
-
-        let cached_reader = Arc::new(PartProofReader {
-            part,
-            sources: Vec::new(),
-            volume: "bucket".to_owned(),
-            inline: None,
-            cached: Mutex::new(ProofCache::default()),
-        });
-        cached_reader.verify(0, 0, shards[0]).await.expect("cached verify");
-        assert!(
-            cached_reader.verify(0, 0, shards[1]).await.is_err(),
-            "cached record must still reject corrupt or mismatched shard payloads"
-        );
-    }
 }

crates/ecstore/src/lib.rs

@@ -55,9 +55,7 @@ mod set_disk;
 mod storage_api_contracts;
 mod store;
 
-pub use disk::{
-    spawn_blocking_with_resource_ownership, with_background_disk_io, with_background_resource_set, with_background_resource_unit,
-};
+pub use disk::{with_background_disk_io, with_background_resource_unit};
 pub use store::PoolMetaWriteGateStatus;
 
 // pub mod checksum;

crates/ecstore/src/object_api/types.rs

@@ -144,8 +144,6 @@ pub(crate) fn namespace_lock_signal_test_fence_is_lost(signal: &Arc<rustfs_lock:
         .is_some_and(|(_, fence)| fence.is_lock_lost())
 }
 
-type FreshPutQuota = std::result::Result<(Option<crate::bucket::quota::BucketQuota>, Uuid, OffsetDateTime), String>;
-
 #[derive(Debug)]
 pub struct ObjectLockConfigSnapshot {
     store_id: Option<Uuid>,
@@ -156,7 +154,6 @@ pub struct ObjectLockConfigSnapshot {
     lifecycle_fence: NamespaceLockFence,
     _lifecycle_guard: Option<rustfs_lock::NamespaceLockGuard>,
     metadata_transaction_guard: Option<Arc<rustfs_lock::NamespaceLockGuard>>,
-    fresh_put_quota: std::sync::Mutex<Option<FreshPutQuota>>,
 }
 
 impl ObjectLockConfigSnapshot {
@@ -170,7 +167,6 @@ impl ObjectLockConfigSnapshot {
             lifecycle_fence: NamespaceLockFence::new(),
             _lifecycle_guard: None,
             metadata_transaction_guard: None,
-            fresh_put_quota: std::sync::Mutex::new(None),
         }
     }
 
@@ -191,7 +187,6 @@ impl ObjectLockConfigSnapshot {
             lifecycle_fence: NamespaceLockFence::new(),
             _lifecycle_guard: None,
             metadata_transaction_guard: None,
-            fresh_put_quota: std::sync::Mutex::new(None),
         }
     }
 
@@ -217,7 +212,6 @@ impl ObjectLockConfigSnapshot {
             lifecycle_fence,
             _lifecycle_guard: Some(lifecycle_guard),
             metadata_transaction_guard: Some(Arc::new(metadata_transaction_guard)),
-            fresh_put_quota: std::sync::Mutex::new(None),
         }
     }
 
@@ -239,23 +233,9 @@ impl ObjectLockConfigSnapshot {
             lifecycle_fence,
             _lifecycle_guard: None,
             metadata_transaction_guard: Some(metadata_transaction_guard),
-            fresh_put_quota: std::sync::Mutex::new(None),
         }
     }
 
-    pub(crate) fn set_fresh_put_quota(&self, quota: FreshPutQuota) {
-        if self._lifecycle_guard.is_some() && self.metadata_transaction_guard.is_some() {
-            *self.fresh_put_quota.lock().unwrap_or_else(std::sync::PoisonError::into_inner) = Some(quota);
-        }
-    }
-
-    pub(crate) fn take_fresh_put_quota(&self) -> Option<FreshPutQuota> {
-        self.fresh_put_quota
-            .lock()
-            .unwrap_or_else(std::sync::PoisonError::into_inner)
-            .take()
-    }
-
     #[allow(dead_code, reason = "snapshot-scope predicate asserted by this file's tests (backlog#1823)")]
     pub(crate) fn is_for_store_bucket(
         &self,
@@ -1543,8 +1523,6 @@ pub struct ObjectInfo {
     /// published by the same upload. Callers must not repeat quota, replication,
     /// lifecycle, or object-created side effects for that response.
     pub multipart_completion_replayed: bool,
-    /// Previous current version's size observed during `rename_data` commit.
-    pub backfilled_old_current_size: Option<crate::disk::OldCurrentSize>,
 }
 
 impl Default for ObjectInfo {
@@ -1587,7 +1565,6 @@ impl Default for ObjectInfo {
             replication_decision: String::new(),
             checksum: None,
             multipart_completion_replayed: false,
-            backfilled_old_current_size: None,
         }
     }
 }
@@ -1631,7 +1608,6 @@ impl Clone for ObjectInfo {
             replication_decision: self.replication_decision.clone(),
             checksum: self.checksum.clone(),
             multipart_completion_replayed: self.multipart_completion_replayed,
-            backfilled_old_current_size: self.backfilled_old_current_size,
             expires: self.expires,
         }
     }

crates/ecstore/src/runtime/instance.rs

@@ -941,32 +941,6 @@ impl InstanceContext {
             .clone()
     }
 
-    /// Remove the `BucketMetadataSys` when its backing `ECStore` is gone.
-    ///
-    /// Called from `ECStore::drop`. When test fixtures share the bootstrap
-    /// context, the `BucketMetadataSys` stores a `Weak<ECStore>` to prevent a
-    /// reference cycle; once the store drops the weak is dangling and any
-    /// `object_store()` call panics. Clearing the slot here lets the next
-    /// fixture install a fresh `BucketMetadataSys` without hitting the stale one.
-    pub fn clear_bucket_metadata_sys_if_stale(&self) {
-        let mut guard = self.bucket_metadata_sys.lock().expect("bucket_metadata_sys lock poisoned");
-        if let Some(sys) = guard.as_ref() {
-            // `read()` may block briefly; the async RwLock is acceptable here
-            // because Drop is sync and the lock is held only long enough to
-            // check the weak reference.
-            let is_stale = {
-                let s = sys.try_read();
-                match s {
-                    Ok(s) => s.is_store_stale(),
-                    Err(_) => true, // contended: treat as stale-safe to clear
-                }
-            };
-            if is_stale {
-                *guard = None;
-            }
-        }
-    }
-
     /// Set this instance's background-services cancellation token (once).
     pub fn init_background_cancel_token(&self, token: CancellationToken) -> Result<(), CancellationToken> {
         self.background_cancel_token.set(token)

crates/ecstore/src/services/rebalance/worker.rs

@@ -318,21 +318,6 @@ fn is_rebalance_transient_lock_error(err: &rustfs_lock::LockError) -> bool {
     }
 }
 
-fn is_rebalance_metadata_admission_retryable(err: &Error) -> bool {
-    match rebalance_error_source(err) {
-        Error::Lock(err) => is_rebalance_transient_lock_error(err),
-        // No metadata was written when lock admission failed. Each attempt
-        // must acquire its quorum again before loading or saving this run.
-        Error::NamespaceLockQuorumUnavailable {
-            mode: "write",
-            bucket,
-            object,
-            ..
-        } => bucket == crate::disk::RUSTFS_META_BUCKET && object == REBAL_META_NAME,
-        _ => false,
-    }
-}
-
 fn is_rebalance_transient_io_error(err: &std::io::Error) -> bool {
     if err.kind() == std::io::ErrorKind::TimedOut {
         return true;
@@ -400,7 +385,9 @@ where
         match result {
             Ok(value) => return Ok(value),
             Err(err) => {
-                if attempt.saturating_add(1) >= max_attempts.max(1) || !is_rebalance_metadata_admission_retryable(&err) {
+                if attempt.saturating_add(1) >= max_attempts.max(1)
+                    || !matches!(rebalance_error_source(&err), Error::Lock(lock_err) if is_rebalance_transient_lock_error(lock_err))
+                {
                     return Err(err);
                 }
                 #[cfg(test)]
@@ -732,82 +719,6 @@ mod error_source_tests {
         }
     }
 
-    #[tokio::test(start_paused = true)]
-    async fn rebalance_metadata_retry_recovers_after_write_quorum_failure() {
-        let mut attempts = 0;
-        retry_rebalance_metadata_access(None, 3, || {
-            attempts += 1;
-            std::future::ready(if attempts == 1 {
-                resolve_rebalance_meta_save_result(
-                    Err(rebalance_meta_lock_error(
-                        rustfs_lock::LockError::QuorumNotReached {
-                            required: 1,
-                            achieved: 0,
-                        },
-                        "write",
-                    )),
-                    "stop_rebalance",
-                )
-            } else {
-                Ok(())
-            })
-        })
-        .await
-        .expect("a later quorum-protected admission must be allowed to succeed");
-        assert_eq!(attempts, 2);
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn rebalance_metadata_retry_retains_persistent_write_quorum_failure() {
-        for max_attempts in [0, 1, 3] {
-            let mut attempts = 0;
-            let result = retry_rebalance_metadata_access(None, max_attempts, || {
-                attempts += 1;
-                std::future::ready(Err::<(), _>(rebalance_meta_lock_error(
-                    rustfs_lock::LockError::QuorumNotReached {
-                        required: 1,
-                        achieved: 0,
-                    },
-                    "write",
-                )))
-            })
-            .await;
-            let error = result.expect_err("exhausted admission attempts must never acknowledge a write");
-            assert_eq!(attempts, max_attempts.max(1));
-            assert!(matches!(
-                rebalance_error_source(&error),
-                Error::NamespaceLockQuorumUnavailable {
-                    mode: "write",
-                    required: 1,
-                    achieved: 0,
-                    ..
-                }
-            ));
-        }
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn rebalance_metadata_retry_stops_after_admission_is_cancelled() {
-        let mut attempts = 0;
-        let result = retry_rebalance_metadata_access(None, 3, || {
-            attempts += 1;
-            std::future::ready(Err::<(), _>(if attempts == 1 {
-                rebalance_meta_lock_error(
-                    rustfs_lock::LockError::QuorumNotReached {
-                        required: 1,
-                        achieved: 0,
-                    },
-                    "write",
-                )
-            } else {
-                Error::OperationCanceled
-            }))
-        })
-        .await;
-        assert_eq!(attempts, 2, "a stale or cancelled run cannot enter another admission attempt");
-        assert!(matches!(result, Err(Error::OperationCanceled)));
-    }
-
     #[tokio::test]
     async fn rebalance_metadata_retry_does_not_retry_permanent_or_untyped_errors() {
         for err in [
@@ -820,20 +731,6 @@ mod error_source_tests {
                 required: 3,
                 achieved: 2,
             },
-            Error::NamespaceLockQuorumUnavailable {
-                mode: "write",
-                bucket: "data-bucket".to_string(),
-                object: REBAL_META_NAME.to_string(),
-                required: 1,
-                achieved: 0,
-            },
-            Error::NamespaceLockQuorumUnavailable {
-                mode: "write",
-                bucket: crate::disk::RUSTFS_META_BUCKET.to_string(),
-                object: "other-metadata.bin".to_string(),
-                required: 1,
-                achieved: 0,
-            },
             Error::other("stale rebalance run rejected: lock acquisition timed out"),
             Error::other("rebalance distributed run fence lost"),
             Error::Io(std::io::Error::from(std::io::ErrorKind::TimedOut)),

crates/ecstore/src/set_disk/core/io_primitives.rs

@@ -1288,7 +1288,7 @@ async fn try_create_bitrot_readers_via_batch_pread(
     // parity readers unopened; preading them here would discard their bytes
     // when fill_deferred_bitrot_readers installs stripe-aligned reserves.
     let data_first = strategy != BitrotReaderSetupStrategy::AllShards
-        && crate::erasure::coding::decode::get_lockstep_data_shards_only_with_deferred_parity_enabled();
+        && crate::erasure::coding::decode::get_lockstep_data_shards_only_enabled();
     let mut setup = BitrotReaderSetup::new(disks.len());
     for (idx, disk) in disks.iter().enumerate() {
         if disk.is_none() {
@@ -2549,8 +2549,6 @@ pub(in crate::set_disk) struct RenameTailCleanup {
 pub(in crate::set_disk) struct RenameTailOutcome {
     pub(in crate::set_disk) convergence: RenameConvergence,
     pub(in crate::set_disk) cleanup: Vec<RenameTailCleanup>,
-    pub(in crate::set_disk) old_current_source_all_successful_checked: bool,
-    pub(in crate::set_disk) all_online_local_succeeded: bool,
 }
 
 const RENAME_TAIL_CLEANUP_COUNTERFACTUAL_SKIP_ENV: &str = "RUSTFS_PUT_RENAME_TAIL_CLEANUP_COUNTERFACTUAL_SKIP";
@@ -3574,7 +3572,7 @@ pub(in crate::set_disk) async fn finish_rename_tail_heal<
     Guards: Send + 'static,
     Finalize: FnOnce() -> FinalizeFuture + Send,
     FinalizeFuture: Future<Output = ()> + Send,
-    Cleanup: FnOnce(Guards, Vec<RenameTailCleanup>, bool, bool) -> CleanupFuture + Send,
+    Cleanup: FnOnce(Guards, Vec<RenameTailCleanup>) -> CleanupFuture + Send,
     CleanupFuture: Future<Output = ()> + Send,
     Cleanup: 'static,
     CleanupFuture: 'static,
@@ -3582,41 +3580,34 @@ pub(in crate::set_disk) async fn finish_rename_tail_heal<
     SubmitFuture: Future<Output = ()> + Send,
 {
     let tail_async_started = rustfs_io_metrics::put_stage_timer();
-    let (needs_heal, tail_cleanup, tail_complete, old_current_source_all_successful_checked, all_online_local_succeeded) =
-        match tail_drain.await {
-            Ok(Some(outcome)) => (
-                outcome.convergence.needs_heal(),
-                outcome.cleanup,
-                true,
-                outcome.old_current_source_all_successful_checked,
-                outcome.all_online_local_succeeded,
-            ),
-            Ok(None) => {
-                warn!(
-                    event = EVENT_SET_DISK_RENAME_TAIL_DRAIN_FAILED,
-                    component = LOG_COMPONENT_ECSTORE,
-                    subsystem = LOG_SUBSYSTEM_SET_DISK,
-                    state = "missing_convergence",
-                    bucket = %request.bucket,
-                    object = request.object_prefix.as_deref().unwrap_or_default(),
-                    "committed rename tail drain completed without convergence"
-                );
-                (true, Vec::new(), false, false, false)
-            }
-            Err(err) => {
-                warn!(
-                    event = EVENT_SET_DISK_RENAME_TAIL_DRAIN_FAILED,
-                    component = LOG_COMPONENT_ECSTORE,
-                    subsystem = LOG_SUBSYSTEM_SET_DISK,
-                    state = "failed",
-                    bucket = %request.bucket,
-                    object = request.object_prefix.as_deref().unwrap_or_default(),
-                    error = %err,
-                    "rename tail drain failed"
-                );
-                (true, Vec::new(), false, false, false)
-            }
-        };
+    let (needs_heal, tail_cleanup, tail_complete) = match tail_drain.await {
+        Ok(Some(outcome)) => (outcome.convergence.needs_heal(), outcome.cleanup, true),
+        Ok(None) => {
+            warn!(
+                event = EVENT_SET_DISK_RENAME_TAIL_DRAIN_FAILED,
+                component = LOG_COMPONENT_ECSTORE,
+                subsystem = LOG_SUBSYSTEM_SET_DISK,
+                state = "missing_convergence",
+                bucket = %request.bucket,
+                object = request.object_prefix.as_deref().unwrap_or_default(),
+                "committed rename tail drain completed without convergence"
+            );
+            (true, Vec::new(), false)
+        }
+        Err(err) => {
+            warn!(
+                event = EVENT_SET_DISK_RENAME_TAIL_DRAIN_FAILED,
+                component = LOG_COMPONENT_ECSTORE,
+                subsystem = LOG_SUBSYSTEM_SET_DISK,
+                state = "failed",
+                bucket = %request.bucket,
+                object = request.object_prefix.as_deref().unwrap_or_default(),
+                error = %err,
+                "rename tail drain failed"
+            );
+            (true, Vec::new(), false)
+        }
+    };
     rustfs_io_metrics::record_put_object_stage_duration_from(
         rustfs_io_metrics::PUT_STAGE_SET_DISK_RENAME_TAIL_ASYNC_WAIT,
         tail_async_started,
@@ -3660,12 +3651,7 @@ pub(in crate::set_disk) async fn finish_rename_tail_heal<
             let job = RenameTailCleanupJob {
                 enqueued_at: Instant::now(),
                 targets,
-                future: Box::pin(cleanup(
-                    guards,
-                    tail_cleanup,
-                    old_current_source_all_successful_checked,
-                    all_online_local_succeeded,
-                )),
+                future: Box::pin(cleanup(guards, tail_cleanup)),
             };
             if let Err(job) = rename_tail_cleanup_queue().try_enqueue(job).await {
                 rustfs_io_metrics::record_put_object_stage_duration_from(
@@ -3690,13 +3676,7 @@ pub(in crate::set_disk) async fn finish_rename_tail_heal<
                 cleanup_submit_started,
             );
             let cleanup_started = rustfs_io_metrics::put_stage_timer();
-            cleanup(
-                guards,
-                tail_cleanup,
-                old_current_source_all_successful_checked,
-                all_online_local_succeeded,
-            )
-            .await;
+            cleanup(guards, tail_cleanup).await;
             rustfs_io_metrics::record_put_object_stage_duration_from(
                 rustfs_io_metrics::PUT_STAGE_SET_DISK_RENAME_TAIL_CLEANUP,
                 cleanup_started,
@@ -4175,14 +4155,7 @@ impl SetDisks {
                         }
                     }
 
-                    let pending_tasks = tasks.len();
-                    let checked_count = old_current_source_checked.iter().filter(|checked| **checked).count();
-                    let max_source_votes = Self::max_common_old_current_source_votes(&old_current_sources);
-                    let can_change_old_current_source = (checked_count < write_quorum
-                        && checked_count + pending_tasks >= write_quorum)
-                        || (max_source_votes < write_quorum && max_source_votes + pending_tasks >= write_quorum);
-
-                    if !sent_commit && success_count >= write_quorum && !can_change_old_current_source {
+                    if !sent_commit && success_count >= write_quorum {
                         let snapshot_commit = Self::rename_data_commit_from_observations(
                             RenameDataObservations {
                                 disks: &coordinator_disks,
@@ -4201,8 +4174,6 @@ impl SetDisks {
                             cleanup_at_snapshot = commit.cleanup_disks.iter().map(Option::is_some).collect();
                         }
                         if let Some(commit_tx) = commit_tx.take() {
-                            #[cfg(test)]
-                            rename_fanout_barrier::wait_for_armed_rename_before_early_ack(&fanout_dst_object).await;
                             let _ = commit_tx.send(snapshot_commit);
                         }
                         sent_commit = true;
@@ -4325,21 +4296,9 @@ impl SetDisks {
                     }
                 }
 
-                let old_current_source_all_successful_checked = errs
-                    .iter()
-                    .enumerate()
-                    .filter(|(_, err)| err.is_none())
-                    .all(|(idx, _)| old_current_source_checked.get(idx).copied().unwrap_or(false));
-                let all_online_local_succeeded = coordinator_disks.iter().zip(errs.iter()).all(|(disk, err)| match disk {
-                    Some(d) => d.is_local() && err.is_none(),
-                    None => true,
-                });
-
                 Some(RenameTailOutcome {
                     convergence: final_convergence,
                     cleanup: tail_cleanup,
-                    old_current_source_all_successful_checked,
-                    all_online_local_succeeded,
                 })
             }
         });
@@ -4904,14 +4863,6 @@ impl SetDisks {
         })
     }
 
-    pub(in crate::set_disk) fn max_common_old_current_source_votes(old_current_sources: &[Option<FileInfo>]) -> usize {
-        let mut counts: HashMap<[u8; 32], usize> = HashMap::new();
-        for source in old_current_sources.iter().flatten() {
-            *counts.entry(Self::file_info_quorum_hash(source)).or_insert(0) += 1;
-        }
-        counts.into_values().max().unwrap_or(0)
-    }
-
     pub(in crate::set_disk) fn reduce_common_old_current_source(
         old_current_sources: &[Option<FileInfo>],
         write_quorum: usize,
@@ -5340,14 +5291,6 @@ impl SetDisks {
         }
 
         let disks = self.get_disks_internal().await;
-        if disks.len() == self.set_drive_count
-            && disks.iter().all(|disk| {
-                disk.as_ref()
-                    .is_some_and(|disk| disk.has_clean_active_multipart_source(dst_object, true))
-            })
-        {
-            return Ok(false);
-        }
         let transaction_path = part_transaction_path(dst_object);
         let transaction_meta_path = format!("{transaction_path}/{PART_TRANSACTION_NEW_META}");
 
@@ -5547,14 +5490,6 @@ impl SetDisks {
         write_quorum: usize,
     ) -> disk::error::Result<()> {
         let disks = self.get_disks_internal().await;
-        if disks.len() == self.set_drive_count
-            && disks.iter().all(|disk| {
-                disk.as_ref()
-                    .is_some_and(|disk| disk.has_clean_active_multipart_source(part_path, false))
-            })
-        {
-            return Ok(());
-        }
         let listings = join_all(disks.iter().map(|disk| {
             let disk = disk.clone();
             async move {
@@ -5614,11 +5549,10 @@ impl SetDisks {
         write_quorum: usize,
         quorum_context: Option<MultipartWriteQuorumContext<'_>>,
     ) -> disk::error::Result<Vec<Option<DiskStore>>> {
+        self.recover_part_transaction(dst_object, write_quorum).await?;
         let part = ObjectPartInfo::unmarshal(&meta)?;
         let integrity = part.integrity.map(Arc::new);
 
-        self.recover_part_transaction(dst_object, write_quorum).await?;
-
         let src_bucket = Arc::new(src_bucket.to_string());
         let src_object = Arc::new(src_object.to_string());
         let dst_bucket = Arc::new(dst_bucket.to_string());
@@ -5640,9 +5574,7 @@ impl SetDisks {
                 if let Err(error) = prepared {
                     return Some(Err(error));
                 }
-                if let Some(integrity) = integrity
-                    && !disk.is_local()
-                {
+                if let Some(integrity) = integrity {
                     let Some((directory, _)) = dst_object.rsplit_once('/') else {
                         return Some(Err(DiskError::FileCorrupt));
                     };
@@ -5759,36 +5691,7 @@ impl SetDisks {
             return Err(err);
         }
 
-        let all_prepared_succeeded = errs
-            .iter()
-            .zip(prepared_disks.iter())
-            .all(|(err, disk)| err.is_none() && disk.as_ref().is_some_and(|d| d.is_local()));
-        let committed = if all_prepared_succeeded {
-            let settles = prepared_disks.iter().map(|disk| {
-                let disk = disk.clone();
-                let dst_object = dst_object.clone();
-                async move {
-                    let Some(disk) = disk else {
-                        return Err(DiskError::DiskNotFound);
-                    };
-                    disk.settle_part_transaction(RUSTFS_META_MULTIPART_BUCKET, &dst_object, PartTransactionAction::Commit)
-                        .await
-                }
-            });
-            let settle_results = join_all(settles).await;
-            if settle_results.iter().filter(|res| res.is_ok()).count() >= write_quorum
-                && settle_results
-                    .iter()
-                    .zip(prepared_disks.iter())
-                    .all(|(res, disk)| disk.is_none() || res.is_ok())
-            {
-                true
-            } else {
-                self.recover_part_transaction(&dst_object, write_quorum).await?
-            }
-        } else {
-            self.recover_part_transaction(&dst_object, write_quorum).await?
-        };
+        let committed = self.recover_part_transaction(&dst_object, write_quorum).await?;
         if !committed {
             let err = DiskError::ErasureWriteQuorum;
             if let Some(context) = quorum_context {
@@ -6785,7 +6688,9 @@ impl SetDisks {
                         object,
                     );
                 }
-                if should_prevent_write(&oi, http_preconditions.if_none_match_value(), http_preconditions.if_match_value())
+                let if_none_match = http_preconditions.if_none_match_value().map(str::to_owned);
+                let if_match = http_preconditions.if_match_value().map(str::to_owned);
+                if should_prevent_write(&oi, if_none_match, if_match)
                     && !crate::data_movement::can_replace_stale_data_movement_target(&oi, opts)
                 {
                     return Some(StorageError::PreconditionFailed);
@@ -7517,34 +7422,6 @@ pub(crate) mod rename_fanout_barrier {
         }
     }
 
-    pub(in crate::set_disk) async fn wait_for_armed_rename_before_early_ack(object: &str) {
-        loop {
-            let (any_armed, any_unpaused) = {
-                let reg = lock();
-                let mut any_armed = false;
-                let mut any_unpaused = false;
-                for ((obj, _, phase), armed) in &reg.armed {
-                    if obj == object && *phase == Phase::Rename {
-                        any_armed = true;
-                        if !armed.paused.load(Ordering::SeqCst) {
-                            any_unpaused = true;
-                            break;
-                        }
-                    }
-                }
-                (any_armed, any_unpaused)
-            };
-            if !any_armed {
-                return;
-            }
-            if !any_unpaused {
-                tokio::task::yield_now().await;
-                return;
-            }
-            tokio::task::yield_now().await;
-        }
-    }
-
     /// RAII scope that observes in-flight fan-out task counts for a single
     /// `object`. Counts accrue only while the scope is alive; it clears its own
     /// entry on drop.
@@ -8611,9 +8488,9 @@ mod tests {
         }
         assert_eq!(
             recorder.counter_value("rustfs_io_get_object_local_batch_shards_total", &[("outcome", "success")]),
-            2
+            4
         );
-        assert_eq!(recorder.counter_value("rustfs_io_get_object_local_batch_read_bytes_total", &[]), 7);
+        assert_eq!(recorder.counter_value("rustfs_io_get_object_local_batch_read_bytes_total", &[]), 14);
         assert_eq!(recorder.histogram_sample_count("rustfs_io_get_object_local_batch_prepare_seconds"), 8);
     }
 
@@ -9669,11 +9546,11 @@ mod tests {
             writer.shutdown().await.expect("inline writer should shutdown");
             let mut fi = base.clone();
             fi.erasure.index = index + 1;
-            fi.data = Some(
+            fi.data = Some(Bytes::from(
                 writer
                     .into_inline_data()
                     .expect("inline bitrot writer should retain encoded data"),
-            );
+            ));
             files.push(fi);
         }
         files
@@ -11038,7 +10915,7 @@ mod tests {
             move || async move {
                 *finalize_captured.lock().expect("finalize recorder should not poison") = true;
             },
-            move |(), _, _, _| async move {
+            move |(), _| async move {
                 *cleanup_captured.lock().expect("cleanup recorder should not poison") = true;
             },
             |request| async move {

crates/ecstore/src/set_disk/metadata.rs

@@ -161,7 +161,7 @@ impl SetDisks {
             )
         });
         let mut metadata = FileMeta::new();
-        for (version_id, parts) in versions {
+        for parts in versions.into_values() {
             let errors = parts
                 .iter()
                 .zip(&missing)
@@ -173,25 +173,15 @@ impl SetDisks {
                     }
                 })
                 .collect::<Vec<_>>();
-            let (read_quorum, write_quorum) = match Self::object_quorum_from_meta(&parts, &errors, default_parity) {
-                Ok((read, write)) => (
-                    usize::try_from(read).map_err(|_| DiskError::FileCorrupt)?,
-                    usize::try_from(write).map_err(|_| DiskError::FileCorrupt)?,
-                ),
+            let read_quorum = match Self::object_quorum_from_meta(&parts, &errors, default_parity) {
+                Ok((quorum, _)) => usize::try_from(quorum).map_err(|_| DiskError::FileCorrupt)?,
                 Err(DiskError::FileNotFound | DiskError::FileVersionNotFound) if complete => continue,
                 Err(DiskError::FileNotFound | DiskError::FileVersionNotFound) => return Err(DiskError::ErasureReadQuorum),
                 Err(DiskError::ErasureReadQuorum) if complete => continue,
                 Err(error) => return Err(error),
             };
-            let selected = if crate::bucket::utils::is_meta_bucketname(bucket) && version_id.is_none() {
-                // A null-version system record must carry the same commit proof
-                // as GET. Listing only needs the selected metadata, so no disk
-                // handles are retained from the shared read selector.
-                Self::select_committed_fileinfo(&vec![None; disk_count], &parts, &errors, "", read_quorum, write_quorum)?.1
-            } else {
-                let mod_time = Self::common_time(&Self::list_object_modtimes(&parts, &errors), read_quorum);
-                Self::pick_valid_fileinfo(&parts, mod_time, None, read_quorum)?
-            };
+            let mod_time = Self::common_time(&Self::list_object_modtimes(&parts, &errors), read_quorum);
+            let selected = Self::pick_valid_fileinfo(&parts, mod_time, None, read_quorum)?;
             metadata.add_version(selected)?;
         }
         if metadata.versions.is_empty() {

crates/ecstore/src/set_disk/mod.rs

@@ -80,7 +80,7 @@ use crate::erasure::codec::bridge::{
 use crate::erasure::coding;
 use crate::error::{Error, Result, is_err_version_not_found};
 use crate::error::{GenericError, ObjectApiError, is_err_object_not_found};
-use crate::io_support::bitrot::{create_bitrot_reader_from_bytes, create_bitrot_writer, create_bitrot_writer_with_orig_volume};
+use crate::io_support::bitrot::{create_bitrot_reader, create_bitrot_reader_from_bytes, create_bitrot_writer};
 use crate::object_api::ObjectOptions;
 use crate::object_api::get_object_body_cache_hook;
 use crate::object_api::object_api_utils::get_raw_etag;
@@ -120,6 +120,7 @@ use bytesize::ByteSize;
 use futures::future::join_all;
 use http::HeaderMap;
 use md5::{Digest as Md5Digest, Md5};
+use regex::Regex;
 use rustfs_config::MI_B;
 use rustfs_filemeta::metadata_keys;
 use rustfs_filemeta::{
@@ -410,6 +411,10 @@ impl ObjectLockDiagGuard {
         self
     }
 
+    async fn downgrade_committed_tail(&mut self) -> bool {
+        self.guard.downgrade_committed_tail().await
+    }
+
     /// Whether the underlying namespace lock's heartbeat has observed a
     /// refresh-quorum loss (backlog#899 Phase 2). Callers fence their commit
     /// point on this so a stale lock holder does not race a double-write.
@@ -4536,7 +4541,6 @@ fn resolve_tiered_decommission_write_quorum_result(
 pub struct SetDisks {
     pub locker_owner: String,
     pub disks: Arc<RwLock<Vec<Option<DiskStore>>>>,
-    pub(crate) physical_heal_admission: Arc<crate::disk::PhysicalHealBinding>,
     pub set_endpoints: Vec<Endpoint>,
     pub set_drive_count: usize,
     pub default_parity_count: usize,
@@ -4696,17 +4700,6 @@ pub(crate) fn same_distributed_lock_domain(left: &[Arc<dyn LockClient>], right:
             .all(|right_client| left.iter().any(|left_client| Arc::ptr_eq(left_client, right_client)))
 }
 
-// Reusing a held writer additionally requires the same quorum, so repeated
-// clients must not give different weight to an otherwise identical domain.
-fn same_distributed_lock_quorum(left: &[Arc<dyn LockClient>], right: &[Arc<dyn LockClient>]) -> bool {
-    !left.is_empty()
-        && left.len() == right.len()
-        && left.iter().all(|client| {
-            left.iter().filter(|other| Arc::ptr_eq(client, other)).count() == 1
-                && right.iter().filter(|other| Arc::ptr_eq(client, other)).count() == 1
-        })
-}
-
 const ERASURE_CACHE_MAX_ENTRIES: usize = 32;
 
 #[derive(Clone, Copy, Debug, Eq, Hash, PartialEq)]
@@ -5490,7 +5483,6 @@ impl SetDisks {
         Arc::new(SetDisks {
             locker_owner,
             disks,
-            physical_heal_admission: Arc::default(),
             set_drive_count,
             default_parity_count,
             set_index,
@@ -5656,9 +5648,9 @@ impl SetDisks {
     pub(crate) async fn shares_namespace_lock_domain(&self, other: &Self) -> bool {
         match (self.ctx.is_dist_erasure().await, other.ctx.is_dist_erasure().await) {
             (false, false) => Arc::ptr_eq(&self.local_lock_manager, &other.local_lock_manager),
-            // Distributed lock clients receive the raw ObjectKey; the pool
-            // namespace is not part of the key stored by their backends.
-            (true, true) => same_distributed_lock_quorum(&self.lockers, &other.lockers),
+            (true, true) => {
+                self.set_lock_namespace == other.set_lock_namespace && same_distributed_lock_domain(&self.lockers, &other.lockers)
+            }
             _ => false,
         }
     }
@@ -8046,29 +8038,16 @@ fn parts_after_marker(part_numbers: &[usize], part_number_marker: usize) -> Opti
     Some(&part_numbers[index..])
 }
 
-fn canonicalized_etag(etag: &str) -> Cow<'_, str> {
-    // Preserve the legacy suffix-matching behavior for embedded quotes.
-    let trimmed = etag.trim_end_matches('"');
-    let Some(last_quote) = trimmed.rfind('"') else {
-        return Cow::Borrowed(trimmed);
-    };
-    let prefix = trimmed[..last_quote].trim_end_matches('"');
-    let suffix = &trimmed[last_quote + 1..];
-    if prefix.is_empty() {
-        Cow::Borrowed(suffix)
-    } else {
-        let mut result = String::with_capacity(prefix.len() + suffix.len());
-        result.push_str(prefix);
-        result.push_str(suffix);
-        Cow::Owned(result)
-    }
+pub fn canonicalize_etag(etag: &str) -> String {
+    let re = Regex::new("\"*?([^\"]*?)\"*?$").unwrap();
+    re.replace_all(etag, "$1").to_string()
 }
 
 pub fn e_tag_matches(etag: &str, condition: &str) -> bool {
     if condition.trim() == "*" {
         return true;
     }
-    canonicalized_etag(etag) == canonicalized_etag(condition)
+    canonicalize_etag(etag) == canonicalize_etag(condition)
 }
 
 fn weak_etag_matches(etag: &str, condition: &str) -> bool {
@@ -8083,12 +8062,15 @@ fn weak_etag_matches(etag: &str, condition: &str) -> bool {
             .or_else(|| trimmed.strip_prefix("w/"))
             .unwrap_or(trimmed)
     }
-    canonicalized_etag(strip_weak(etag)) == canonicalized_etag(strip_weak(condition))
+    canonicalize_etag(strip_weak(etag)) == canonicalize_etag(strip_weak(condition))
 }
 
-pub fn should_prevent_write(oi: &ObjectInfo, if_none_match: Option<&str>, if_match: Option<&str>) -> bool {
-    let if_none_match = if_none_match.map(str::trim).filter(|condition| !condition.is_empty());
-    let if_match = if_match.map(str::trim).filter(|condition| !condition.is_empty());
+pub fn should_prevent_write(oi: &ObjectInfo, if_none_match: Option<String>, if_match: Option<String>) -> bool {
+    let if_none_match = if_none_match
+        .as_deref()
+        .map(str::trim)
+        .filter(|condition| !condition.is_empty());
+    let if_match = if_match.as_deref().map(str::trim).filter(|condition| !condition.is_empty());
 
     match &oi.etag {
         Some(etag) => {
@@ -9049,13 +9031,6 @@ mod tests {
             "constructing an object lock must not clone each client Arc"
         );
 
-        // Check shared ownership before acquisition can spawn pending cleanup.
-        let read_lock = set
-            .new_ns_lock("bucket", "read-object")
-            .await
-            .expect("second namespace lock should be created");
-        assert_eq!(Arc::strong_count(&set.shared_lockers), clients_before + 2);
-
         let write_error = write_lock
             .get_write_lock(Duration::from_millis(500))
             .await
@@ -9070,6 +9045,11 @@ mod tests {
             ),
             "the shared client representation must preserve the exact write quorum result: {write_error}"
         );
+        let read_lock = set
+            .new_ns_lock("bucket", "read-object")
+            .await
+            .expect("second namespace lock should be created");
+        assert_eq!(Arc::strong_count(&set.shared_lockers), clients_before + 2);
         let read_guard = read_lock
             .get_read_lock(Duration::from_millis(500))
             .await
@@ -9893,7 +9873,7 @@ mod tests {
 
     #[tokio::test(flavor = "multi_thread")]
     #[serial]
-    async fn distributed_namespace_lock_domain_follows_backend_not_pool_name() {
+    async fn namespace_lock_domain_includes_pool_namespace() {
         let _setup_type_guard = SetupTypeGuard::switch_to(SetupType::DistErasure).await;
 
         let first: Arc<dyn LockClient> = Arc::new(LocalClient::with_manager(Arc::new(rustfs_lock::GlobalLockManager::new())));
@@ -9932,25 +9912,11 @@ mod tests {
             "sets in the same pool share the object namespace lock domain"
         );
         assert!(
-            same_pool_first_set.shares_namespace_lock_domain(&other_pool_set).await,
-            "different pools using identical backends lock the same raw object key"
+            !same_pool_first_set.shares_namespace_lock_domain(&other_pool_set).await,
+            "different pool namespaces must not be deduplicated solely by identical clients"
         );
     }
 
-    #[test]
-    fn distributed_lock_domain_rejects_partial_or_duplicate_backends() {
-        let a: Arc<dyn LockClient> = Arc::new(LocalClient::with_manager(Arc::new(rustfs_lock::GlobalLockManager::new())));
-        let b: Arc<dyn LockClient> = Arc::new(LocalClient::with_manager(Arc::new(rustfs_lock::GlobalLockManager::new())));
-        let c: Arc<dyn LockClient> = Arc::new(LocalClient::with_manager(Arc::new(rustfs_lock::GlobalLockManager::new())));
-        assert!(same_distributed_lock_quorum(&[a.clone(), b.clone()], &[b.clone(), a.clone()]));
-        assert!(!same_distributed_lock_quorum(&[a.clone(), b.clone()], &[a.clone(), c]));
-        assert!(!same_distributed_lock_quorum(
-            &[a.clone(), a.clone(), b.clone()],
-            &[a.clone(), b.clone(), b]
-        ));
-        assert!(!same_distributed_lock_quorum(&[], &[]));
-    }
-
     #[tokio::test(flavor = "multi_thread")]
     #[serial]
     async fn streaming_reader_holds_read_lock_until_eof() {
@@ -13808,22 +13774,6 @@ mod tests {
         assert!(result2.iter().all(|d| d.is_none()));
     }
 
-    #[test]
-    fn canonicalized_etag_preserves_legacy_regex_semantics() {
-        let regex = regex::Regex::new("\"*?([^\"]*?)\"*?$").expect("valid legacy ETag pattern");
-        let alphabet = ['a', '"', '\n', 'é', '\0'];
-        for length in 0..=6_u32 {
-            for mut number in 0..alphabet.len().pow(length) {
-                let mut input = String::new();
-                for _ in 0..length {
-                    input.push(alphabet[number % alphabet.len()]);
-                    number /= alphabet.len();
-                }
-                assert_eq!(canonicalized_etag(&input), regex.replace_all(&input, "$1"), "input: {input:?}");
-            }
-        }
-    }
-
     #[test]
     fn test_etag_matches() {
         assert!(e_tag_matches("abc", "abc"));
@@ -14399,61 +14349,61 @@ mod tests {
             etag: Some("abc".to_string()),
             ..Default::default()
         };
-        let if_none_match = Some("abc");
+        let if_none_match = Some("abc".to_string());
         let if_match = None;
         assert!(should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("*");
+        let if_none_match = Some("*".to_string());
         let if_match = None;
         assert!(should_prevent_write(&oi, if_none_match, if_match));
 
         let if_none_match = None;
-        let if_match = Some("def");
+        let if_match = Some("def".to_string());
         assert!(should_prevent_write(&oi, if_none_match, if_match));
 
         let if_none_match = None;
-        let if_match = Some("*");
+        let if_match = Some("*".to_string());
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("def");
+        let if_none_match = Some("def".to_string());
         let if_match = None;
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("def");
-        let if_match = Some("*");
+        let if_none_match = Some("def".to_string());
+        let if_match = Some("*".to_string());
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("def");
-        let if_match = Some("\"abc\"");
+        let if_none_match = Some("def".to_string());
+        let if_match = Some("\"abc\"".to_string());
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("*");
-        let if_match = Some("\"abc\"");
+        let if_none_match = Some("*".to_string());
+        let if_match = Some("\"abc\"".to_string());
         assert!(should_prevent_write(&oi, if_none_match, if_match));
 
         let oi = ObjectInfo {
             etag: None,
             ..Default::default()
         };
-        let if_none_match = Some("*");
-        let if_match = Some("\"abc\"");
+        let if_none_match = Some("*".to_string());
+        let if_match = Some("\"abc\"".to_string());
         assert!(should_prevent_write(&oi, if_none_match, if_match));
 
         let if_none_match = None;
         let if_match = None;
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
-        let if_none_match = Some("");
-        let if_match = Some(" ");
+        let if_none_match = Some(String::new());
+        let if_match = Some(" ".to_string());
         assert!(!should_prevent_write(&oi, if_none_match, if_match));
 
         let oi = ObjectInfo {
             etag: Some("abc".to_string()),
             ..Default::default()
         };
-        assert!(should_prevent_write(&oi, Some("W/\"abc\""), None));
-        assert!(!should_prevent_write(&oi, Some("W/\"def\""), None));
-        assert!(should_prevent_write(&oi, None, Some("W/\"abc\"")));
+        assert!(should_prevent_write(&oi, Some("W/\"abc\"".to_string()), None));
+        assert!(!should_prevent_write(&oi, Some("W/\"def\"".to_string()), None));
+        assert!(should_prevent_write(&oi, None, Some("W/\"abc\"".to_string())));
     }
 
     #[test]
@@ -14861,7 +14811,7 @@ mod tests {
             file.erasure.index = files.len() + 1;
             file.erasure.block_size = erasure.block_size;
             file.uses_legacy_checksum = uses_legacy;
-            file.data = Some(data);
+            file.data = Some(Bytes::from(data));
             files.push(file);
         }
 
@@ -15322,7 +15272,7 @@ mod tests {
         }
 
         let encoded = bitrot_writer.into_inline_data().expect("bitrot encoded data should exist");
-        disk.write_all(bucket, &shard_path, encoded)
+        disk.write_all(bucket, &shard_path, Bytes::from(encoded))
             .await
             .expect("encoded shard should be stored");
 
@@ -15406,7 +15356,7 @@ mod tests {
         }
 
         let encoded = bitrot_writer.into_inline_data().expect("bitrot encoded data should exist");
-        disk.write_all(bucket, &shard_path, encoded)
+        disk.write_all(bucket, &shard_path, Bytes::from(encoded))
             .await
             .expect("encoded shard should be stored");
 
@@ -15519,7 +15469,7 @@ mod tests {
             }
 
             let encoded = bitrot_writer.into_inline_data().expect("bitrot encoded data should exist");
-            disk.write_all(bucket, &shard_path, encoded)
+            disk.write_all(bucket, &shard_path, Bytes::from(encoded))
                 .await
                 .expect("encoded shard should be stored");
         }

crates/ecstore/src/set_disk/ops/delete_recovery.rs

@@ -97,14 +97,6 @@ pub(crate) mod test_hooks {
             .push((bucket.to_owned(), object.to_owned(), hook));
     }
 
-    pub(super) fn has_before_gc_finalize(bucket: &str, object: &str) -> bool {
-        BEFORE_GC_FINALIZE
-            .lock()
-            .expect("GC finalize hooks")
-            .iter()
-            .any(|(hook_bucket, hook_object, _)| hook_bucket == bucket && hook_object == object)
-    }
-
     pub(super) async fn run_before_gc_finalize(bucket: &str, object: &str) {
         let hook = {
             let mut hooks = BEFORE_GC_FINALIZE.lock().expect("GC finalize hooks");
@@ -426,59 +418,6 @@ impl SetDisks {
             .unwrap_or_else(|| self.ctx.begin_namespace_commit());
         context.namespace_owner = Some(Arc::new((owner, Arc::clone(&transaction_guard))));
         let can_commit = context.can_commit;
-        let can_try_local_fast_path = disks.len() == self.set_drive_count
-            && disks.iter().all(|d| d.as_ref().is_some_and(|d| d.is_local()))
-            && !crate::disk::local::has_delete_version_test_failpoints()
-            && {
-                #[cfg(test)]
-                {
-                    !test_hooks::has_before_gc_finalize(bucket, object)
-                }
-                #[cfg(not(test))]
-                {
-                    true
-                }
-            };
-        if can_try_local_fast_path && can_commit() {
-            let fast_published = join_all(disks.iter().map(|disk| async {
-                if !can_commit() {
-                    return Err(DiskError::other("delete recovery namespace fence was lost"));
-                }
-                let disk = disk.as_ref().ok_or(DiskError::DiskNotFound)?;
-                disk.try_publish_prepared_delete_local(bucket, object, transaction, context.namespace_owner.clone())
-                    .await
-            }))
-            .await;
-            let all_fast_published = fast_published.len() == self.set_drive_count
-                && fast_published.iter().all(|res| matches!(res, Ok(Some((_, true, true)))));
-            if all_fast_published && can_commit() {
-                #[cfg(test)]
-                test_hooks::record_cleanup_attempt(bucket, object);
-                let finalized = join_all(disks.iter().zip(fast_published.iter()).map(|(disk, pub_res)| {
-                    let ns_owner = context.namespace_owner.clone();
-                    async move {
-                        if !can_commit() {
-                            return Ok(false);
-                        }
-                        let Some(disk) = disk.as_ref() else {
-                            return Ok(false);
-                        };
-                        let Ok(Some((journal, _, _))) = pub_res else {
-                            return Ok(false);
-                        };
-                        disk.try_finish_and_finalize_prepared_delete_local(bucket, object, transaction, journal, ns_owner)
-                            .await
-                    }
-                }))
-                .await;
-                if finalized.iter().all(|res| matches!(res, Ok(true))) {
-                    if let Some(ticket) = context.recovery_ticket.as_ref() {
-                        self.ctx.delete_recovery_hints().ack(ticket);
-                    }
-                    return Ok(());
-                }
-            }
-        }
         let states = inspect(disks, bucket, object, transaction).await;
         let untouched_absence = |state: &Result<DeleteRecoveryInspection>| matches!(state, Ok(state) if state.state == DeleteRecoveryState::Absent && state.current_digest.is_none());
         if states.iter().filter(|state| untouched_absence(state)).count() >= write_quorum

crates/ecstore/src/set_disk/ops/heal.rs

@@ -13,14 +13,14 @@
 // limitations under the License.
 
 use super::super::{
-    CHECK_PART_FILE_CORRUPT, CHECK_PART_SUCCESS, DeleteOptions, DiskError, DiskStore, DriveState, EVENT_SET_DISK_HEAL, Error,
-    FileInfo, HashAlgorithm, HashMap, HealDriveInfo, HealItemType, HealOpts, HealResultItem, HealScanMode, Infos,
+    Bytes, CHECK_PART_FILE_CORRUPT, CHECK_PART_SUCCESS, DeleteOptions, DiskError, DiskStore, DriveState, EVENT_SET_DISK_HEAL,
+    Error, FileInfo, HashAlgorithm, HashMap, HealDriveInfo, HealItemType, HealOpts, HealResultItem, HealScanMode, Infos,
     LOG_SUBSYSTEM_SET_DISK, ObjectInfo, ObjectOptions, ObjectPartInfo, Path, RUSTFS_META_TMP_BUCKET, ReadOptions, Result,
-    SLASH_SEPARATOR, SetDisks, StorageError, Uuid, coding, count_errs, count_part_not_success, create_bitrot_writer, debug, disk,
-    disks_with_all_parts, encode_dir_object, error, file_info_is_valid_for_metadata, formats_match_reference_slots,
-    get_format_erasure_in_quorum, get_lock_acquire_timeout, has_suffix, heal_bucket_local_on_disks, is_object_dir_dangling,
-    join_all, load_format_erasure_all, path_join_buf, save_format_file, should_heal_object_on_disk, stat_all_dirs, to_object_err,
-    warn,
+    SLASH_SEPARATOR, SetDisks, StorageError, Uuid, coding, count_errs, count_part_not_success, create_bitrot_reader,
+    create_bitrot_writer, debug, disk, disks_with_all_parts, encode_dir_object, error, file_info_is_valid_for_metadata,
+    formats_match_reference_slots, get_format_erasure_in_quorum, get_lock_acquire_timeout, has_suffix,
+    heal_bucket_local_on_disks, is_object_dir_dangling, join_all, load_format_erasure_all, path_join_buf, save_format_file,
+    should_heal_object_on_disk, stat_all_dirs, to_object_err, warn,
 };
 use crate::bucket::retirement::MarkerRetirementContext;
 use crate::diagnostics::object_lock::ObjectLockAttempt;
@@ -52,7 +52,7 @@ fn pin_object_heal_future<F: std::future::Future>(build: impl FnOnce() -> F) ->
 use crate::disk::DataDirDeleteStatus;
 use crate::disk::DiskAPI;
 use crate::disk::local::{DELETE_DATA_DIR_MARKER_PREFIX, metadata_less_part_file};
-use crate::io_support::bitrot::{create_bitrot_reader_from_bytes, object_mmap_read_enabled};
+use crate::io_support::bitrot::object_mmap_read_enabled;
 use crate::storage_api_contracts::namespace::NamespaceLocking as _;
 use rustfs_common::mrf_channel::MrfDeleteMarkerPurge;
 use rustfs_common::trace_bus::{TraceEvent, TraceFunc, TraceKind, trace_emit};
@@ -1236,7 +1236,6 @@ impl SetDisks {
                         result.object_size =
                             ObjectInfo::from_file_info(&latest_meta, bucket, object, true).get_actual_size()? as usize;
                         result.resolved_version_id = Some(*latest_meta.version_id.unwrap_or_default().as_bytes());
-                        result.quorum_selected_data_dir = selected_heal_data_dir(&latest_meta, opts);
                         // Loop to find number of disks with valid data, per-drive
                         // data state and a list of outdated disks on which data needs
                         // to be healed.
@@ -1424,9 +1423,13 @@ impl SetDisks {
                                 );
                             }
 
-                            // A no-remove request cannot turn surviving data into dangling
-                            // cleanup or its grace deferral.
-                            if read_repair_uses_shared_lock || preserve_unrepairable || !opts.remove {
+                            // A no-remove request cannot turn surviving same-version
+                            // data into dangling cleanup or its grace deferral.
+                            let preserve_surviving_data = !opts.remove
+                                && data_errs_by_disk
+                                    .values()
+                                    .any(|parts| !parts.is_empty() && parts.iter().all(|status| *status == CHECK_PART_SUCCESS));
+                            if read_repair_uses_shared_lock || preserve_unrepairable || preserve_surviving_data {
                                 return Ok((result, Some(cannot_heal_err)));
                             }
 
@@ -1812,8 +1815,8 @@ impl SetDisks {
                                                 checksum_info.algorithm
                                             };
 
-                                            match create_bitrot_reader_from_bytes(
-                                                metadata.data.clone(),
+                                            match create_bitrot_reader(
+                                                metadata.data.as_deref(),
                                                 Some(disk),
                                                 bucket,
                                                 &path_join_buf(&[object, &src_data_dir, &format!("part.{}", part.number)]),
@@ -1910,7 +1913,8 @@ impl SetDisks {
                                                 // if let Some(w) = writer.as_any().downcast_ref::<BitrotFileWriter>() {
                                                 //     parts_metadata[index].data = Some(w.inline_data().to_vec());
                                                 // }
-                                                parts_metadata[index].data = Some(writer.into_inline_data().unwrap_or_default());
+                                                parts_metadata[index].data =
+                                                    Some(writer.into_inline_data().map(Bytes::from).unwrap_or_default());
                                             }
                                             parts_metadata[index].set_inline_data();
                                         } else {
@@ -2198,13 +2202,6 @@ impl SetDisks {
                 }
             }
             Err(err) => {
-                // All replicas explicitly missing was handled before the
-                // quorum check. A partial read cannot prove object absence.
-                let err = if matches!(err, DiskError::FileNotFound | DiskError::FileVersionNotFound) {
-                    DiskError::ErasureReadQuorum
-                } else {
-                    err
-                };
                 if let Some(retirement) = retirement
                     && parts_metadata
                         .iter()
@@ -2244,8 +2241,7 @@ impl SetDisks {
                     }
                     return Ok((item, cleanup.err()));
                 }
-                if !opts.dry_run
-                    && allow_explicit_version_regen
+                if allow_explicit_version_regen
                     && !version_id.is_empty()
                     && self
                         .try_regenerate_explicit_version_meta(bucket, object, version_id, &parts_metadata, &errs, &disks)
@@ -2264,7 +2260,7 @@ impl SetDisks {
                     .await;
                 }
 
-                if opts.dry_run || preserve_unrepairable || !opts.remove {
+                if opts.dry_run || preserve_unrepairable {
                     return Ok((
                         self.default_heal_result(FileInfo::default(), &errs, bucket, object, version_id)
                             .await,
@@ -3265,13 +3261,6 @@ impl SetDisks {
     }
 }
 
-fn selected_heal_data_dir(metadata: &FileInfo, opts: &HealOpts) -> Option<[u8; 16]> {
-    if opts.read_repair || opts.dry_run || metadata.deleted || metadata.is_remote() {
-        return None;
-    }
-    metadata.data_dir.filter(|id| !id.is_nil()).map(|id| *id.as_bytes())
-}
-
 fn finalize_object_heal_result(
     mut result: HealResultItem,
     mut error: Option<Error>,
@@ -3295,9 +3284,6 @@ fn finalize_object_heal_result(
             achieved: 0,
         });
     }
-    if error.is_some() {
-        result.quorum_selected_data_dir = None;
-    }
     (result, error)
 }
 
@@ -4012,7 +3998,6 @@ mod heal_result_report_tests {
             metadata_verified: true,
             metadata_repair_verified: true,
             legacy_identity_unverified: true,
-            quorum_selected_data_dir: Some([1; 16]),
             ..Default::default()
         };
 
@@ -4023,7 +4008,6 @@ mod heal_result_report_tests {
         assert!(!result.metadata_verified);
         assert!(!result.metadata_repair_verified);
         assert!(!result.legacy_identity_unverified);
-        assert_eq!(result.quorum_selected_data_dir, None);
         assert!(absence.is_none());
         assert!(matches!(
             error,
@@ -4037,134 +4021,6 @@ mod heal_result_report_tests {
         ));
     }
 
-    #[test]
-    fn selected_data_dir_is_a_quorum_metadata_observation() {
-        let generation = Uuid::new_v4();
-        let mut metadata = FileInfo {
-            data_dir: Some(generation),
-            ..Default::default()
-        };
-        let opts = HealOpts::default();
-        assert_eq!(super::selected_heal_data_dir(&metadata, &opts), Some(*generation.as_bytes()));
-        assert_eq!(
-            super::selected_heal_data_dir(&metadata, &HealOpts { no_lock: true, ..opts }),
-            Some(*generation.as_bytes())
-        );
-        assert_eq!(super::selected_heal_data_dir(&metadata, &HealOpts { dry_run: true, ..opts }), None);
-        assert_eq!(
-            super::selected_heal_data_dir(
-                &metadata,
-                &HealOpts {
-                    read_repair: true,
-                    ..opts
-                }
-            ),
-            None
-        );
-        metadata.data_dir = Some(Uuid::nil());
-        assert_eq!(super::selected_heal_data_dir(&metadata, &opts), None);
-        metadata.data_dir = None;
-        assert_eq!(super::selected_heal_data_dir(&metadata, &opts), None);
-        metadata.data_dir = Some(generation);
-        metadata.deleted = true;
-        assert_eq!(super::selected_heal_data_dir(&metadata, &opts), None);
-        metadata.deleted = false;
-        metadata.transition_status = TRANSITION_COMPLETE.to_owned();
-        assert_eq!(super::selected_heal_data_dir(&metadata, &opts), None);
-    }
-
-    #[test]
-    fn failed_heal_does_not_publish_selected_generation() {
-        let result = rustfs_madmin::heal_commands::HealResultItem {
-            quorum_selected_data_dir: Some([1; 16]),
-            ..Default::default()
-        };
-        let mut absence = None;
-        let (result, error) =
-            super::finalize_object_heal_result(result, Some(Error::FileNotFound), &mut absence, false, "b", "o");
-        assert!(error.is_some());
-        assert_eq!(result.quorum_selected_data_dir, None);
-    }
-
-    #[tokio::test]
-    async fn heal_result_observes_current_generation_after_unversioned_overwrite() {
-        let (_temp_dirs, _disks, set) = hermetic_set_disks_isolated(4).await;
-        let bucket = "heal-result-generation";
-        let object = "object.bin";
-        set.make_bucket(bucket, &MakeBucketOptions::default())
-            .await
-            .expect("create test bucket");
-
-        let put_opts = ObjectOptions {
-            no_lock: true,
-            ..Default::default()
-        };
-        let mut first = PutObjReader::from_vec(vec![0x11; 1024 * 1024]);
-        let first_info = set
-            .put_object(bucket, object, &mut first, &put_opts)
-            .await
-            .expect("write first generation");
-        let first_generation = first_info.data_dir.expect("first object data directory");
-        let heal_opts = HealOpts {
-            scan_mode: HealScanMode::Deep,
-            ..Default::default()
-        };
-        let (first_result, first_error) =
-            crate::storage_api_contracts::heal::HealOperations::heal_object(set.as_ref(), bucket, object, "", &heal_opts)
-                .await
-                .expect("heal first generation");
-        assert!(first_error.is_none());
-        assert_eq!(first_result.quorum_selected_data_dir, Some(*first_generation.as_bytes()));
-
-        let mut second = PutObjReader::from_vec(vec![0x22; 1024 * 1024]);
-        let second_info = set
-            .put_object(bucket, object, &mut second, &put_opts)
-            .await
-            .expect("overwrite unversioned object");
-        let second_generation = second_info.data_dir.expect("second object data directory");
-        assert_ne!(first_generation, second_generation);
-        let (second_result, second_error) =
-            crate::storage_api_contracts::heal::HealOperations::heal_object(set.as_ref(), bucket, object, "", &heal_opts)
-                .await
-                .expect("heal second generation");
-        assert!(second_error.is_none());
-        assert_eq!(second_result.quorum_selected_data_dir, Some(*second_generation.as_bytes()));
-        assert_ne!(second_result.quorum_selected_data_dir, first_result.quorum_selected_data_dir);
-
-        let (unlocked_result, unlocked_error) = crate::storage_api_contracts::heal::HealOperations::heal_object(
-            set.as_ref(),
-            bucket,
-            object,
-            "",
-            &HealOpts {
-                no_lock: true,
-                ..heal_opts
-            },
-        )
-        .await
-        .expect("observe quorum selection without a namespace lock");
-        assert!(unlocked_error.is_none());
-        assert_eq!(unlocked_result.quorum_selected_data_dir, Some(*second_generation.as_bytes()));
-
-        for opts in [
-            HealOpts {
-                read_repair: true,
-                ..heal_opts
-            },
-            HealOpts {
-                dry_run: true,
-                ..heal_opts
-            },
-        ] {
-            let (result, error) =
-                crate::storage_api_contracts::heal::HealOperations::heal_object(set.as_ref(), bucket, object, "", &opts)
-                    .await
-                    .expect("observe heal without an eligible lock");
-            assert!(error.is_none());
-            assert_eq!(result.quorum_selected_data_dir, None);
-        }
-    }
-
     #[test]
     fn absent_and_nil_selected_versions_are_the_same_null_identity() {
         let requested_nil = Uuid::nil().to_string();
@@ -7669,13 +7525,12 @@ mod heal_result_report_tests {
                 "",
                 &HealOpts {
                     no_lock: true,
-                    remove: true,
                     ..Default::default()
                 },
             )
             .await
             .expect("unsafe dangling state should be reported without deletion");
-        assert_eq!(err, Some(DiskError::ErasureReadQuorum));
+        assert_eq!(err, Some(DiskError::FileNotFound));
         let surviving = disks[0]
             .as_ref()
             .expect("first test disk should be online")
@@ -7716,7 +7571,6 @@ mod heal_result_report_tests {
                 .expect("seed exact stale historical version");
             let opts = HealOpts {
                 no_lock: true,
-                remove: true,
                 scan_mode: HealScanMode::Deep,
                 ..Default::default()
             };
@@ -7792,443 +7646,6 @@ mod heal_result_report_tests {
         .await;
     }
 
-    #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
-    async fn heal_without_remove_preserves_unrecoverable_unversioned_shards() {
-        use crate::disk::{CHECK_PART_FILE_NOT_FOUND, CHECK_PART_SUCCESS};
-        use crate::object_api::WriteCompletion;
-        use futures::FutureExt as _;
-        use std::panic::AssertUnwindSafe;
-        use std::time::Duration;
-
-        // Exercise the same on-disk layout with explicit removal first, so
-        // an unrelated early failure cannot masquerade as preservation.
-        for remove in [true, false] {
-            let (dirs, disks, set) = hermetic_set_disks_isolated(4).await;
-            let outcome = AssertUnwindSafe(tokio::time::timeout(Duration::from_secs(45), async {
-                let bucket = if remove {
-                    "heal-remove-unversioned"
-                } else {
-                    "heal-preserve-unversioned"
-                };
-                let object = "object.bin";
-                let old_time = OffsetDateTime::from_unix_timestamp(1).expect("fixture modification time");
-                let elapsed = (OffsetDateTime::now_utc() - old_time).whole_seconds();
-                let grace = rustfs_utils::get_env_u64("RUSTFS_HEAL_DANGLING_DELETE_GRACE_SECS", 3600);
-                assert!(
-                    elapsed > i64::try_from(grace).unwrap_or(i64::MAX),
-                    "fixture must be outside the configured dangling-delete grace period"
-                );
-                set.make_bucket(bucket, &MakeBucketOptions::default())
-                    .await
-                    .expect("create fixture bucket");
-                let options = ObjectOptions {
-                    mod_time: Some(old_time),
-                    write_completion: WriteCompletion::TailDrained,
-                    ..Default::default()
-                };
-                set.put_object(bucket, object, &mut PutObjReader::from_vec(vec![0x5a; 1024 * 1024]), &options)
-                    .await
-                    .expect("write all four fixture shards");
-
-                let mut metadata = Vec::new();
-                let mut infos = Vec::new();
-                for (dir, disk) in dirs.iter().zip(&disks) {
-                    metadata.push(
-                        tokio::fs::read(dir.path().join(bucket).join(object).join(STORAGE_FORMAT_FILE))
-                            .await
-                            .expect("read each committed metadata file"),
-                    );
-                    infos.push(
-                        disk.read_version("", bucket, object, "", &ReadOptions::default())
-                            .await
-                            .expect("read each committed unversioned metadata replica"),
-                    );
-                }
-                let selected = &infos[0];
-                let data_dir = selected.data_dir.expect("fixture must be non-inline");
-                assert!(selected.version_id.is_none_or(|id| id.is_nil()));
-                assert_eq!(selected.mod_time, Some(old_time));
-                let missing_count = selected.erasure.parity_blocks + 1;
-                assert!(missing_count < disks.len(), "at least one physical shard must survive");
-                assert!(infos.iter().all(|info| {
-                    info.data_dir == Some(data_dir)
-                        && info.version_id.is_none_or(|id| id.is_nil())
-                        && info.erasure.parity_blocks == selected.erasure.parity_blocks
-                }));
-                let part_path = |dir: &TempDir| dir.path().join(bucket).join(object).join(data_dir.to_string()).join("part.1");
-                let surviving_shard = tokio::fs::read(part_path(&dirs[missing_count]))
-                    .await
-                    .expect("read the shard that must survive");
-                for dir in dirs.iter().take(missing_count) {
-                    tokio::fs::remove_file(part_path(dir)).await.expect("remove one exact shard");
-                }
-                for (index, (disk, info)) in disks.iter().zip(&infos).enumerate() {
-                    let checked = disk.check_parts(bucket, object, info).await.expect("check fixture shards");
-                    let expected = if index < missing_count {
-                        CHECK_PART_FILE_NOT_FOUND
-                    } else {
-                        CHECK_PART_SUCCESS
-                    };
-                    assert_eq!(checked.results, vec![expected], "disk {index} has the intended shard state");
-                }
-                let visible = set
-                    .get_object_info(
-                        bucket,
-                        object,
-                        &ObjectOptions {
-                            no_lock: true,
-                            ..Default::default()
-                        },
-                    )
-                    .await
-                    .expect("metadata quorum remains visible before heal");
-                assert_eq!(visible.data_dir, Some(data_dir));
-
-                let (result, error) = <SetDisks as crate::storage_api_contracts::heal::HealOperations>::heal_object(
-                    set.as_ref(),
-                    bucket,
-                    object,
-                    "",
-                    &HealOpts {
-                        remove,
-                        scan_mode: HealScanMode::Deep,
-                        ..Default::default()
-                    },
-                )
-                .await
-                .expect("heal returns an object result");
-                if remove {
-                    assert!(error.is_none(), "explicit dangling cleanup must succeed: {error:?}");
-                    for dir in &dirs {
-                        assert!(
-                            tokio::fs::metadata(dir.path().join(bucket))
-                                .await
-                                .expect("bucket remains readable")
-                                .is_dir()
-                        );
-                        assert!(
-                            matches!(
-                                tokio::fs::symlink_metadata(dir.path().join(bucket).join(object).join(STORAGE_FORMAT_FILE)).await,
-                                Err(error) if error.kind() == std::io::ErrorKind::NotFound
-                            ),
-                            "explicit removal must remove the metadata replica"
-                        );
-                    }
-                    assert!(
-                        matches!(tokio::fs::symlink_metadata(part_path(&dirs[missing_count])).await,
-                        Err(error) if error.kind() == std::io::ErrorKind::NotFound),
-                        "explicit removal must remove the surviving shard"
-                    );
-                    assert_eq!(result.after.drives.len(), disks.len());
-                    assert!(
-                        result
-                            .after
-                            .drives
-                            .iter()
-                            .all(|drive| drive.state == DriveState::Missing.to_string())
-                    );
-                } else {
-                    for (index, (dir, before)) in dirs.iter().zip(&metadata).enumerate() {
-                        let after = tokio::fs::read(dir.path().join(bucket).join(object).join(STORAGE_FORMAT_FILE))
-                            .await
-                            .expect("remove=false must keep each metadata replica");
-                        assert_eq!(&after, before, "remove=false changed metadata on disk {index}");
-                    }
-                    assert_eq!(
-                        tokio::fs::read(part_path(&dirs[missing_count]))
-                            .await
-                            .expect("remove=false must keep the surviving shard"),
-                        surviving_shard
-                    );
-                    assert!(matches!(&error, Some(Error::ErasureReadQuorum)), "unexpected heal result: {error:?}");
-                    assert_eq!(result.before.drives.len(), disks.len());
-                    assert_eq!(
-                        result
-                            .before
-                            .drives
-                            .iter()
-                            .filter(|drive| drive.state == DriveState::Missing.to_string())
-                            .count(),
-                        missing_count
-                    );
-                    let mut absence = None;
-                    let (_, proof_error) = set
-                        .heal_object_with_absence(
-                            bucket,
-                            object,
-                            "",
-                            &HealOpts {
-                                scan_mode: HealScanMode::Deep,
-                                ..Default::default()
-                            },
-                            &mut absence,
-                            AbsenceProofRequest {
-                                retirement: None,
-                                allow_unversioned: true,
-                            },
-                        )
-                        .await
-                        .expect("repeat through the absence-proof path");
-                    assert!(matches!(proof_error, Some(Error::ErasureReadQuorum)));
-                    assert!(absence.is_none(), "surviving shards cannot produce an absence proof");
-                }
-            }))
-            .catch_unwind()
-            .await;
-            drop(set);
-            drop(disks);
-            if !matches!(&outcome, Ok(Ok(()))) {
-                let retained: Vec<_> = dirs.into_iter().map(TempDir::keep).collect();
-                eprintln!("unrecoverable-shard fixture retained: {retained:?}");
-                match outcome {
-                    Ok(Err(_)) => panic!("unrecoverable-shard fixture timed out"),
-                    Err(panic) => std::panic::resume_unwind(panic),
-                    Ok(Ok(())) => unreachable!(),
-                }
-            }
-        }
-    }
-
-    #[tokio::test]
-    #[serial_test::serial]
-    async fn heal_without_remove_preserves_explicit_version_metadata_during_dry_run() {
-        use crate::object_api::{ShardIntegrityWriteMode, WriteCompletion};
-        use futures::FutureExt as _;
-        use std::panic::AssertUnwindSafe;
-        use std::time::Duration;
-
-        let (dirs, disks, set) = hermetic_set_disks_isolated(4).await;
-        let outcome = AssertUnwindSafe(tokio::time::timeout(Duration::from_secs(45), async {
-            let bucket = "heal-dry-run-versioned";
-            let object = "object.bin";
-            set.make_bucket(bucket, &MakeBucketOptions::default())
-                .await
-                .expect("create fixture bucket");
-            let original = set
-                .put_object(
-                    bucket,
-                    object,
-                    &mut PutObjReader::from_vec(vec![0x67; 1024 * 1024]),
-                    &ObjectOptions {
-                        versioned: true,
-                        shard_integrity_write_mode: Some(ShardIntegrityWriteMode::Legacy),
-                        write_completion: WriteCompletion::TailDrained,
-                        ..Default::default()
-                    },
-                )
-                .await
-                .expect("write a real version on all four disks");
-            let version = original.version_id.expect("explicit version");
-            assert!(!version.is_nil());
-            let generation = original.data_dir.expect("external data generation");
-            let version_string = version.to_string();
-            let metadata_path = |dir: &TempDir| dir.path().join(bucket).join(object).join(STORAGE_FORMAT_FILE);
-            let shard_path = |dir: &TempDir| {
-                dir.path()
-                    .join(bucket)
-                    .join(object)
-                    .join(generation.to_string())
-                    .join("part.1")
-            };
-            let mut shards = Vec::new();
-            for (dir, disk) in dirs.iter().zip(&disks) {
-                let info = disk
-                    .read_version("", bucket, object, &version_string, &ReadOptions::default())
-                    .await
-                    .expect("initial metadata on each disk");
-                assert_eq!(info.version_id, Some(version));
-                assert_eq!(info.data_dir, Some(generation));
-                assert!(info.parts.iter().all(|part| part.integrity.is_none()));
-                assert!(
-                    rustfs_filemeta::shard_integrity::descriptor_from_metadata(&info.metadata)
-                        .expect("metadata protection descriptor")
-                        .is_none()
-                );
-                shards.push(tokio::fs::read(shard_path(dir)).await.expect("save original shard"));
-            }
-            let surviving_metadata = tokio::fs::read(metadata_path(&dirs[0]))
-                .await
-                .expect("save surviving metadata");
-            for dir in dirs.iter().skip(1) {
-                tokio::fs::remove_file(metadata_path(dir))
-                    .await
-                    .expect("remove one metadata replica");
-            }
-            for disk in disks.iter().skip(1) {
-                assert!(matches!(
-                    disk.read_version("", bucket, object, &version_string, &ReadOptions::default())
-                        .await,
-                    Err(DiskError::FileNotFound | DiskError::FileVersionNotFound)
-                ));
-            }
-
-            let mut absence = None;
-            let (_, error) = set
-                .heal_object_with_absence(
-                    bucket,
-                    object,
-                    &version_string,
-                    &HealOpts {
-                        dry_run: true,
-                        ..Default::default()
-                    },
-                    &mut absence,
-                    AbsenceProofRequest {
-                        retirement: None,
-                        allow_unversioned: false,
-                    },
-                )
-                .await
-                .expect("dry-run reports the metadata quorum failure");
-            assert!(matches!(error, Some(Error::ErasureReadQuorum)), "partial metadata must not look absent");
-            assert!(absence.is_none());
-            assert_eq!(
-                tokio::fs::read(metadata_path(&dirs[0])).await.expect("surviving metadata"),
-                surviving_metadata
-            );
-            for (index, dir) in dirs.iter().enumerate() {
-                if index != 0 {
-                    assert!(matches!(
-                        tokio::fs::symlink_metadata(metadata_path(dir)).await,
-                        Err(error) if error.kind() == std::io::ErrorKind::NotFound
-                    ));
-                }
-                assert_eq!(tokio::fs::read(shard_path(dir)).await.expect("original shard"), shards[index]);
-            }
-
-            let (_, error) = set
-                .heal_object_with_absence(
-                    bucket,
-                    object,
-                    &version_string,
-                    &HealOpts::default(),
-                    &mut absence,
-                    AbsenceProofRequest {
-                        retirement: None,
-                        allow_unversioned: false,
-                    },
-                )
-                .await
-                .expect("normal heal attempts metadata regeneration");
-            assert!(error.is_none(), "normal heal must repair the same layout: {error:?}");
-            assert!(absence.is_none());
-            for (index, (dir, disk)) in dirs.iter().zip(&disks).enumerate() {
-                let info = disk
-                    .read_version("", bucket, object, &version_string, &ReadOptions::default())
-                    .await
-                    .expect("normal heal restored metadata");
-                assert_eq!(info.version_id, Some(version));
-                assert_eq!(info.data_dir, Some(generation));
-                assert_eq!(tokio::fs::read(shard_path(dir)).await.expect("original shard"), shards[index]);
-            }
-        }))
-        .catch_unwind()
-        .await;
-        drop(set);
-        drop(disks);
-        if !matches!(&outcome, Ok(Ok(()))) {
-            let retained: Vec<_> = dirs.into_iter().map(TempDir::keep).collect();
-            eprintln!("dry-run versioned fixture retained: {retained:?}");
-            match outcome {
-                Ok(Err(_)) => panic!("dry-run versioned fixture timed out"),
-                Err(panic) => std::panic::resume_unwind(panic),
-                Ok(Ok(())) => unreachable!(),
-            }
-        }
-    }
-
-    #[tokio::test]
-    #[serial_test::serial]
-    async fn heal_without_remove_preserves_dangling_inline_metadata_and_emits_no_absence_proof() {
-        use futures::FutureExt as _;
-        use std::panic::AssertUnwindSafe;
-        use std::time::Duration;
-
-        temp_env::async_with_vars([("RUSTFS_HEAL_DANGLING_DELETE_GRACE_SECS", Some("0"))], async {
-            for remove in [true, false] {
-                let bucket = if remove {
-                    "inline-dangling-remove"
-                } else {
-                    "inline-dangling-preserve"
-                };
-                let object = "stale.txt";
-                let (dirs, set, disks) =
-                    dangling_inline_test_fixture(bucket, object, OffsetDateTime::now_utc() - time::Duration::hours(2)).await;
-                let outcome = AssertUnwindSafe(tokio::time::timeout(Duration::from_secs(45), async {
-                    let metadata = dirs[0].path().join(bucket).join(object).join(STORAGE_FORMAT_FILE);
-                    let before = tokio::fs::read(&metadata).await.expect("read surviving inline metadata");
-                    let mut absence = None;
-                    let (_, error) = set
-                        .heal_object_with_absence(
-                            bucket,
-                            object,
-                            "",
-                            &HealOpts {
-                                no_lock: true,
-                                remove,
-                                ..Default::default()
-                            },
-                            &mut absence,
-                            AbsenceProofRequest {
-                                retirement: None,
-                                allow_unversioned: true,
-                            },
-                        )
-                        .await
-                        .expect("dangling inline heal returns an object result");
-                    if remove {
-                        assert!(error.is_none(), "explicit cleanup must succeed: {error:?}");
-                        assert!(
-                            absence.as_ref().is_some_and(|proof| proof.removed),
-                            "successful cleanup must prove removal"
-                        );
-                        assert!(matches!(
-                            tokio::fs::symlink_metadata(metadata).await,
-                            Err(error) if error.kind() == std::io::ErrorKind::NotFound
-                        ));
-                        let (_, missing_error) = set
-                            .heal_object_with_absence(
-                                bucket,
-                                object,
-                                "",
-                                &HealOpts {
-                                    no_lock: true,
-                                    ..Default::default()
-                                },
-                                &mut absence,
-                                AbsenceProofRequest {
-                                    retirement: None,
-                                    allow_unversioned: true,
-                                },
-                            )
-                            .await
-                            .expect("fully absent object returns a result");
-                        assert!(matches!(missing_error, Some(Error::FileNotFound)));
-                        assert!(absence.is_some_and(|proof| !proof.removed));
-                    } else {
-                        assert!(matches!(error, Some(Error::ErasureReadQuorum)), "partial metadata must not look absent");
-                        assert!(absence.is_none(), "a surviving candidate cannot prove authoritative absence");
-                        assert_eq!(tokio::fs::read(metadata).await.expect("metadata must remain"), before);
-                    }
-                }))
-                .catch_unwind()
-                .await;
-                drop(set);
-                drop(disks);
-                if !matches!(&outcome, Ok(Ok(()))) {
-                    let retained: Vec<_> = dirs.into_iter().map(TempDir::keep).collect();
-                    eprintln!("dangling-inline fixture retained: {retained:?}");
-                    match outcome {
-                        Ok(Err(_)) => panic!("dangling-inline fixture timed out"),
-                        Err(panic) => std::panic::resume_unwind(panic),
-                        Ok(Ok(())) => unreachable!(),
-                    }
-                }
-            }
-        })
-        .await;
-    }
-
     #[tokio::test]
     #[serial_test::serial]
     async fn heal_reports_success_after_dangling_inline_cleanup() {
@@ -8245,7 +7662,6 @@ mod heal_result_report_tests {
                     "",
                     &HealOpts {
                         no_lock: true,
-                        remove: true,
                         ..Default::default()
                     },
                 )
@@ -8276,7 +7692,6 @@ mod heal_result_report_tests {
                     "",
                     &HealOpts {
                         no_lock: true,
-                        remove: true,
                         ..Default::default()
                     },
                 )
@@ -8327,14 +7742,13 @@ mod heal_result_report_tests {
                     &HealOpts {
                         dry_run: true,
                         no_lock: true,
-                        remove: true,
                         ..Default::default()
                     },
                 )
                 .await
                 .expect("dry-run should report the dangling candidate without mutation");
 
-            assert_eq!(error, Some(DiskError::ErasureReadQuorum));
+            assert_eq!(error, Some(DiskError::FileNotFound));
             assert!(
                 temp_dirs[0]
                     .path()
@@ -8358,27 +7772,6 @@ mod heal_result_report_tests {
         seed_meta_regen_test_metadata(&disks, 0, bucket, object, &metadata).await;
         set.disks.write().await[1] = None;
 
-        let mut absence = None;
-        let (_, error) = set
-            .heal_object_with_absence(
-                bucket,
-                object,
-                "",
-                &HealOpts {
-                    no_lock: true,
-                    ..Default::default()
-                },
-                &mut absence,
-                AbsenceProofRequest {
-                    retirement: None,
-                    allow_unversioned: true,
-                },
-            )
-            .await
-            .expect("offline shard state should be reported without removal");
-        assert!(matches!(error, Some(Error::ErasureReadQuorum)));
-        assert!(absence.is_none(), "offline members cannot prove absence");
-
         let (_, err) = set
             .heal_object(
                 bucket,
@@ -8386,13 +7779,12 @@ mod heal_result_report_tests {
                 "",
                 &HealOpts {
                     no_lock: true,
-                    remove: true,
                     ..Default::default()
                 },
             )
             .await
             .expect("offline shard state should be reported without deletion");
-        assert_eq!(err, Some(DiskError::ErasureReadQuorum));
+        assert_eq!(err, Some(DiskError::FileNotFound));
         let surviving = disks[0]
             .as_ref()
             .expect("first test disk should be online")
@@ -8429,13 +7821,12 @@ mod heal_result_report_tests {
                 "",
                 &HealOpts {
                     no_lock: true,
-                    remove: true,
                     ..Default::default()
                 },
             )
             .await
             .expect("part probe timeout should be reported without deletion");
-        assert_eq!(err, Some(DiskError::ErasureReadQuorum));
+        assert_eq!(err, Some(DiskError::FileNotFound));
         let surviving = disks[0]
             .as_ref()
             .expect("first test disk should be online")

crates/ecstore/src/set_disk/ops/multipart.rs

@@ -41,8 +41,8 @@ use super::super::{
     SUFFIX_REPLICATION_SSEC_CRC, SUFFIX_RESTORE_OPERATION_ID, SUFFIX_RESTORE_WORKER_LOCK, SetDisks, SmallWritePath, StorageError,
     Uuid, WriteLayout, check_object_lock_for_deletion_with_state, classify_multipart_part_write_path, coding,
     complete_multipart_part_error, complete_multipart_part_error_result, complete_part_checksum, contains_key_str,
-    create_bitrot_writer_with_orig_volume, debug, disk, error, file_info_is_valid_for_metadata, get_complete_multipart_md5,
-    get_header_map, get_str, insert_str, is_err_object_not_found, is_err_version_not_found, is_min_allowed_part_size,
+    create_bitrot_writer, debug, disk, error, file_info_is_valid_for_metadata, get_complete_multipart_md5, get_header_map,
+    get_str, insert_str, is_err_object_not_found, is_err_version_not_found, is_min_allowed_part_size,
     log_multipart_write_quorum_failure, multipart_part_logical_size, parts_after_marker, path_join_buf,
     prepare_complete_multipart_parts, record_compression_total_memory, record_multipart_write_quorum_failure,
     reduce_read_quorum_errs, reduce_write_quorum_errs, remove_header_map, resolve_write_layout,
@@ -124,10 +124,9 @@ async fn create_part_writers(
         let Some(disk) = disk else {
             return (None, Some(DiskError::DiskNotFound));
         };
-        match create_bitrot_writer_with_orig_volume(
+        match create_bitrot_writer(
             false,
             Some(disk),
-            RUSTFS_META_MULTIPART_BUCKET,
             RUSTFS_META_TMP_BUCKET,
             path,
             length,
@@ -978,7 +977,7 @@ async fn multipart_upload_paths_on_disk(disk: DiskStore, bucket: &str, root_pref
         return Err(DiskError::DiskNotFound);
     }
 
-    if !root_prefix.is_empty() && root_prefix != DATA_MOVEMENT_MULTIPART_PREFIX {
+    if !root_prefix.is_empty() {
         let upload_dirs = match disk.list_dir(bucket, RUSTFS_META_MULTIPART_BUCKET, root_prefix, -1).await {
             Ok(entries) => entries,
             Err(DiskError::FileNotFound | DiskError::VolumeNotFound) => return Ok(Vec::new()),
@@ -1003,13 +1002,6 @@ async fn multipart_upload_paths_on_disk(disk: DiskStore, bucket: &str, root_pref
         .into_iter()
         .map(|sha_dir| sha_dir.trim_end_matches('/').to_owned())
         .filter(|sha_dir| sha_dir.len() == 64 && sha_dir.bytes().all(|byte| byte.is_ascii_hexdigit()))
-        .map(|sha_dir| {
-            if root_prefix.is_empty() {
-                sha_dir
-            } else {
-                format!("{root_prefix}/{sha_dir}")
-            }
-        })
         .collect::<Vec<_>>();
     let listed_upload_dirs = stream::iter(sha_dirs)
         .map(|sha_dir| {
@@ -1132,7 +1124,6 @@ impl SetDisks {
         orig_bucket: &str,
         error_path: &str,
         root_prefix: &str,
-        require_all_disks: bool,
     ) -> Result<(Vec<Option<DiskStore>>, Vec<String>, usize, bool)> {
         let disks = self.disks.read().await.clone();
         if disks.is_empty() {
@@ -1174,8 +1165,7 @@ impl SetDisks {
             }
         }
 
-        let required_discoveries = if require_all_disks { disks.len() } else { discovery_quorum };
-        if let Some(err) = reduce_read_quorum_errs(&discovery_errors, OBJECT_OP_IGNORED_ERRS, required_discoveries) {
+        if let Some(err) = reduce_read_quorum_errs(&discovery_errors, OBJECT_OP_IGNORED_ERRS, discovery_quorum) {
             return Err(to_object_err(err.into(), vec![orig_bucket, error_path]));
         }
 
@@ -1197,7 +1187,7 @@ impl SetDisks {
 
     pub(crate) async fn first_multipart_upload_path_for_decommission(&self, bucket: &str) -> Result<Option<String>> {
         let (_, paths, _, _) = self
-            .discover_multipart_upload_paths(bucket, RUSTFS_META_MULTIPART_BUCKET, "", false)
+            .discover_multipart_upload_paths(bucket, RUSTFS_META_MULTIPART_BUCKET, "")
             .await?;
         Ok(paths.into_iter().next())
     }
@@ -1210,9 +1200,8 @@ impl SetDisks {
         upload_identity: &str,
     ) -> Result<Vec<String>> {
         let expected_parent = format!("{DATA_MOVEMENT_MULTIPART_PREFIX}/{}", Self::get_multipart_sha_dir(bucket, object));
-        let (_, candidate_paths, _, has_minority_candidate) = self
-            .discover_multipart_upload_paths(bucket, object, &expected_parent, false)
-            .await?;
+        let (_, candidate_paths, _, has_minority_candidate) =
+            self.discover_multipart_upload_paths(bucket, object, &expected_parent).await?;
         if has_minority_candidate {
             return Err(Error::DecommissionCapacityBlocked {
                 message: "data movement multipart cleanup found an upload path on fewer than the discovery quorum of disks"
@@ -1761,54 +1750,6 @@ impl SetDisks {
         })
     }
 
-    pub(crate) async fn ensure_no_multipart_uploads(&self, bucket: &str) -> Result<()> {
-        // Every disk must confirm absence in both namespaces before cleanup can
-        // remove catalog protection from the bucket.
-        for root_prefix in ["", DATA_MOVEMENT_MULTIPART_PREFIX] {
-            let (disks, paths, _, has_minority_candidate) =
-                self.discover_multipart_upload_paths(bucket, "", root_prefix, true).await?;
-            if has_minority_candidate {
-                return Err(Error::ErasureReadQuorum);
-            }
-            for upload_path in paths {
-                let (sha_dir, _) = upload_path
-                    .rsplit_once('/')
-                    .filter(|(directory, upload_id)| !directory.is_empty() && !upload_id.is_empty())
-                    .ok_or(DiskError::CorruptedFormat)?;
-                let (metadata, errors) =
-                    Self::read_all_fileinfo(&disks, bucket, RUSTFS_META_MULTIPART_BUCKET, &upload_path, "", false, false, false)
-                        .await?;
-                let (read_quorum, _) = Self::object_quorum_from_meta(&metadata, &errors, self.default_parity_count)?;
-                let read_quorum = usize::try_from(read_quorum).map_err(|_| DiskError::ErasureReadQuorum)?;
-                if let Some(error) = reduce_read_quorum_errs(&errors, OBJECT_OP_IGNORED_ERRS, read_quorum) {
-                    return Err(to_object_err(error.into(), vec![bucket, &upload_path]));
-                }
-                let (_, modified, etag) = Self::list_online_disks(&disks, &metadata, &errors, read_quorum);
-                let file = Self::pick_valid_fileinfo(&metadata, modified, etag, read_quorum)?;
-                let (Some(owner_bucket), Some(owner_object)) = (
-                    file.metadata.get(RUSTFS_MULTIPART_BUCKET_KEY),
-                    file.metadata.get(RUSTFS_MULTIPART_OBJECT_KEY),
-                ) else {
-                    return Err(to_object_err(DiskError::CorruptedFormat.into(), vec![bucket, &upload_path]));
-                };
-                if owner_bucket.is_empty()
-                    || owner_object.is_empty()
-                    || Self::get_multipart_sha_dir(owner_bucket, owner_object)
-                        != sha_dir
-                            .strip_prefix(DATA_MOVEMENT_MULTIPART_PREFIX)
-                            .and_then(|suffix| suffix.strip_prefix('/'))
-                            .unwrap_or(sha_dir)
-                {
-                    return Err(to_object_err(DiskError::CorruptedFormat.into(), vec![bucket, &upload_path]));
-                }
-                if owner_bucket == bucket {
-                    return Err(Error::BucketNotEmpty(bucket.to_string()));
-                }
-            }
-        }
-        Ok(())
-    }
-
     #[allow(clippy::too_many_arguments)]
     pub(crate) async fn list_multipart_uploads_for_incarnation(
         &self,
@@ -1820,8 +1761,7 @@ impl SetDisks {
         max_uploads: usize,
         expected_incarnation_id: Option<Uuid>,
     ) -> Result<ListMultipartsInfo> {
-        let (disks, candidate_paths, discovery_quorum, _) =
-            self.discover_multipart_upload_paths(bucket, prefix, "", false).await?;
+        let (disks, candidate_paths, discovery_quorum, _) = self.discover_multipart_upload_paths(bucket, prefix, "").await?;
         let listed_uploads = stream::iter(candidate_paths)
             .map(|upload_path| {
                 let disks = &disks;
@@ -2432,7 +2372,7 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
             let multipart_part_size = data.size();
             let stream = mem::replace(
                 &mut data.stream,
-                HashReader::from_stream(Cursor::new(Vec::new()), 0, 0, None, None, true)?,
+                HashReader::from_stream(Cursor::new(Vec::new()), 0, 0, None, None, false)?,
             );
 
             let write_path = classify_multipart_part_write_path(multipart_part_size, fi.erasure.block_size);
@@ -2496,16 +2436,7 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
             }
 
             let part_integrity = if let Some(integrity) = integrity {
-                Some(
-                    integrity
-                        .write(
-                            &mut shuffle_disks,
-                            RUSTFS_META_MULTIPART_BUCKET,
-                            RUSTFS_META_TMP_BUCKET,
-                            &tmp_part,
-                        )
-                        .await?,
-                )
+                Some(integrity.write(&mut shuffle_disks, bucket, RUSTFS_META_TMP_BUCKET, &tmp_part).await?)
             } else { None };
             if shuffle_disks.iter().filter(|disk| disk.is_some()).count() < write_quorum {
                 return Err(Error::ErasureWriteQuorum);
@@ -3540,6 +3471,10 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
         bind_multipart_proof_snapshot(&disks, &self.multipart_proof_verification_context())?;
 
         let part_path = format!("{}/{}/", upload_id_path, fi.data_dir.unwrap_or(Uuid::nil()));
+        self.recover_part_transactions(&part_path, read_quorum, write_quorum)
+            .await
+            .map_err(|err| to_object_err(err.into(), vec![bucket, object]))?;
+
         let part_meta_paths = uploaded_parts
             .iter()
             .map(|v| format!("{part_path}part.{0}.meta", v.part_num))
@@ -3547,10 +3482,6 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
 
         let part_numbers = uploaded_parts.iter().map(|v| v.part_num).collect::<Vec<usize>>();
 
-        self.recover_part_transactions(&part_path, read_quorum, write_quorum)
-            .await
-            .map_err(|err| to_object_err(err.into(), vec![bucket, object]))?;
-
         let object_parts = Self::read_parts(&disks, RUSTFS_META_MULTIPART_BUCKET, &part_meta_paths, &part_numbers, read_quorum)
             .await
             .map_err(|err| to_object_err(err.into(), vec![bucket, object]))?;
@@ -4458,7 +4389,6 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
             let needs_immediate_heal = rename_commit.needs_immediate_heal();
             let op_old_dir = rename_commit.data_dir;
             let cleanup_disks = rename_commit.cleanup_disks;
-            let old_current_size = rename_commit.old_current_size;
             let committed_file_info = rename_commit.committed_file_info;
 
             if needs_immediate_heal {
@@ -4527,13 +4457,7 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
             // parts; deleting them before the commit would strand the upload
             // permanently. This mirrors the "clean up only after commit" pattern
             // already used for the old data-dir GC and the upload-dir delete_all below.
-            let can_skip_part_cleanup = !needs_upgrade
-                && commit_disks
-                    .iter()
-                    .all(|disk| disk.as_ref().is_some_and(|disk| disk.is_local()));
-            if !can_skip_part_cleanup {
-                commit_set.cleanup_multipart_path(&parts).await;
-            }
+            commit_set.cleanup_multipart_path(&parts).await;
 
             if let Some(old_dir) = op_old_dir {
                 // backlog#898: best-effort reclaim of the dereferenced old data dir.
@@ -4579,9 +4503,7 @@ impl crate::storage_api_contracts::multipart::MultipartOperations for SetDisks {
 
             drop(_upload_guard.take());
 
-            let mut obj_info = ObjectInfo::from_file_info(&fi, &commit_bucket, &commit_object, commit_is_versioned);
-            obj_info.backfilled_old_current_size = old_current_size;
-            Ok(obj_info)
+            Ok(ObjectInfo::from_file_info(&fi, &commit_bucket, &commit_object, commit_is_versioned))
         };
 
         let result = if detach_commit_owner {
@@ -10060,7 +9982,7 @@ mod tests {
 
         // Real disk callbacks and health probes must share wall-clock deadlines.
         // Advancing Tokio time can expire unrelated healthy-drive probes.
-        temp_env::async_with_vars([(rustfs_config::ENV_DRIVE_MAX_TIMEOUT_DURATION, None::<&str>)], async {
+        temp_env::async_with_vars([(rustfs_config::ENV_DRIVE_MAX_TIMEOUT_DURATION, Some("2"))], async {
             let (dirs, store) = crate::bucket::metadata_sys::test_support::isolated_store_over_temp_disks().await;
             crate::bucket::metadata_sys::init_bucket_metadata_sys(store.clone(), Vec::new()).await;
             let bucket = "mpu-quorum-success-physical";
@@ -10087,8 +10009,6 @@ mod tests {
                 local.observe_multipart_cleanup_for_test(&upload_path)
             }).collect::<Vec<_>>();
             let disk::Disk::Local(paused_local) = disks[3].as_ref() else { panic!("actual local physical tail") };
-            // Fault only the held leg; healthy disks keep their normal I/O budgets.
-            let _paused_timeout = paused_local.override_operation_timeout_for_test(Duration::from_secs(2));
             let io_target = paused_local.get_disk().get_object_path_for_io(bucket, object).expect("real IO target");
             let mutation_key = paused_local.get_disk().get_object_path(bucket, object).expect("logical native mutation key");
             let (entered_tx, entered_rx) = tokio::sync::oneshot::channel();
@@ -10245,15 +10165,7 @@ mod tests {
                 let size = copy_info.get_actual_size().expect("actual source size");
                 copy_info.put_object_reader = Some(PutObjReader::new(HashReader::from_stream(reader.stream, size, size, None, None, false).expect("actual Copy body stream")));
                 tokio::time::timeout(Duration::from_secs(5), store.copy_object(bucket, object, bucket, copy_object, &mut copy_info, &ObjectOptions::default(), &ObjectOptions::default()))
-                    .await.expect("cross-key Copy cannot wait on the old successful logical owner")
-                    .unwrap_or_else(|error| {
-                        let health = disks.iter().enumerate().map(|(slot, disk)| {
-                            let disk::Disk::Local(local) = disk.as_ref() else { panic!("actual local Copy backend") };
-                            let metrics = local.metrics_snapshot();
-                            (slot, disk.runtime_state(), metrics.total_errors_timeout, metrics.total_errors_availability, metrics.total_waiting, metrics.api_calls)
-                        }).collect::<Vec<_>>();
-                        panic!("actual CopyObject: {error:?}; drive health (slot, state, timeouts, unavailable, waiting, calls): {health:?}");
-                    });
+                    .await.expect("cross-key Copy cannot wait on the old successful logical owner").expect("actual CopyObject");
                 drop(copy_info);
                 let mut copied = store.get_object_reader(bucket, copy_object, None, HeaderMap::new(), &ObjectOptions::default()).await.expect("actual copied body");
                 let mut actual = Vec::new();
@@ -11282,163 +11194,6 @@ mod tests {
         assert_eq!(upload_uuid_suffix(&recovered[0]), upload_uuid_suffix(&upload.upload_id));
     }
 
-    #[tokio::test]
-    async fn multipart_absence_inspection_distinguishes_bucket_ownership() {
-        let (_temp_dirs, disk_stores, set_disks) = hermetic_set_disks(4).await;
-        let bucket = "multipart-cleanup-target";
-        let other = "multipart-cleanup-other";
-        for disk in &disk_stores {
-            disk.make_volume(bucket).await.expect("create target bucket");
-            disk.make_volume(other).await.expect("create other bucket");
-        }
-        set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect("an empty upload namespace permits cleanup");
-        set_disks
-            .new_multipart_upload(other, "object.bin", &ObjectOptions::default())
-            .await
-            .expect("create upload in other bucket");
-        set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect("an upload owned by another bucket permits cleanup");
-        set_disks
-            .new_multipart_upload(bucket, "object.bin", &ObjectOptions::default())
-            .await
-            .expect("create upload in target bucket");
-        assert!(
-            matches!(set_disks.ensure_no_multipart_uploads(bucket).await, Err(Error::BucketNotEmpty(name)) if name == bucket)
-        );
-    }
-
-    #[tokio::test]
-    async fn multipart_absence_inspection_requires_every_disk_online() {
-        let (_temp_dirs, disk_stores, set_disks) = hermetic_set_disks(4).await;
-        let bucket = "multipart-cleanup-offline";
-        for disk in &disk_stores {
-            disk.make_volume(bucket).await.expect("create bucket");
-        }
-        set_disks.disks.write().await[3] = None;
-        let listed = set_disks
-            .list_multipart_uploads_for_incarnation(bucket, "", None, None, None, 1000, None)
-            .await
-            .expect("ordinary listing preserves its discovery quorum");
-        assert!(listed.uploads.is_empty());
-        let error = set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect_err("an offline disk must prevent confirmation of an empty multipart namespace");
-        assert!(
-            matches!(&error, Error::InsufficientReadQuorum(error_bucket, error_path) if error_bucket == bucket && error_path.is_empty()),
-            "the offline disk must produce a bucket-scoped read quorum error: {error:?}"
-        );
-
-        set_disks.disks.write().await[3] = Some(disk_stores[3].clone());
-        set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect("all disks can confirm the empty namespace after recovery");
-    }
-
-    #[tokio::test]
-    async fn multipart_absence_inspection_rejects_a_failed_disk_enumeration() {
-        let (temp_dirs, disk_stores, set_disks) = hermetic_set_disks(4).await;
-        let bucket = "multipart-cleanup-list-error";
-        for disk in &disk_stores {
-            disk.make_volume(bucket).await.expect("create bucket");
-        }
-        let sha_dir = SetDisks::get_multipart_sha_dir(bucket, "object.bin");
-        let multipart_dir = temp_dirs[0].path().join(RUSTFS_META_MULTIPART_BUCKET);
-        tokio::fs::create_dir_all(&multipart_dir)
-            .await
-            .expect("create multipart staging directory");
-        tokio::fs::write(multipart_dir.join(&sha_dir), b"not a directory")
-            .await
-            .expect("replace one upload parent directory with a file");
-        multipart_upload_paths_on_disk(disk_stores[0].clone(), bucket, "")
-            .await
-            .expect_err("the affected disk must fail directory enumeration");
-        let listed = set_disks
-            .list_multipart_uploads_for_incarnation(bucket, "", None, None, None, 1000, None)
-            .await
-            .expect("ordinary listing still accepts the remaining discovery quorum");
-        assert!(listed.uploads.is_empty());
-        let error = set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect_err("a failed disk enumeration must prevent confirmation of an empty multipart namespace");
-        assert!(
-            matches!(&error, Error::InsufficientReadQuorum(error_bucket, error_path) if error_bucket == bucket && error_path.is_empty()),
-            "the failed enumeration must produce a bucket-scoped read quorum error: {error:?}"
-        );
-
-        tokio::fs::remove_file(temp_dirs[0].path().join(RUSTFS_META_MULTIPART_BUCKET).join(sha_dir))
-            .await
-            .expect("remove the invalid directory entry");
-        set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect("all disks can confirm the empty namespace after repair");
-    }
-
-    #[tokio::test]
-    async fn multipart_absence_inspection_rejects_data_movement_uploads() {
-        let (_temp_dirs, disk_stores, set_disks) = hermetic_set_disks(4).await;
-        let bucket = "multipart-cleanup-data-movement";
-        for disk in &disk_stores {
-            disk.make_volume(bucket).await.expect("create bucket");
-        }
-        let mut metadata = HashMap::new();
-        rustfs_utils::http::insert_str(
-            &mut metadata,
-            rustfs_utils::http::SUFFIX_DATA_MOVEMENT_UPLOAD,
-            format!("v1:{}:{}", Uuid::new_v4(), OffsetDateTime::now_utc().unix_timestamp_nanos()),
-        );
-        set_disks
-            .new_multipart_upload(
-                bucket,
-                "object.bin",
-                &ObjectOptions {
-                    data_movement: true,
-                    user_defined: metadata,
-                    ..Default::default()
-                },
-            )
-            .await
-            .expect("create data movement upload");
-        assert!(
-            matches!(set_disks.ensure_no_multipart_uploads(bucket).await, Err(Error::BucketNotEmpty(name)) if name == bucket)
-        );
-    }
-
-    #[tokio::test]
-    async fn multipart_absence_inspection_rejects_unreadable_ownership() {
-        let (temp_dirs, disk_stores, set_disks) = hermetic_set_disks(4).await;
-        let bucket = "multipart-cleanup-corrupt";
-        for disk in &disk_stores {
-            disk.make_volume(bucket).await.expect("create bucket");
-        }
-        set_disks
-            .new_multipart_upload(bucket, "object.bin", &ObjectOptions::default())
-            .await
-            .expect("create multipart upload");
-        let mut corrupted = 0;
-        for temp_dir in &temp_dirs {
-            for path in multipart_meta_files_on_disk(temp_dir, "xl.meta").await {
-                tokio::fs::write(path, b"invalid upload metadata")
-                    .await
-                    .expect("corrupt upload metadata");
-                corrupted += 1;
-            }
-        }
-        assert!(corrupted > 0, "upload metadata must exist before corruption");
-        set_disks
-            .ensure_no_multipart_uploads(bucket)
-            .await
-            .expect_err("unreadable upload ownership must block cleanup");
-    }
-
     /// Regression (issue #5716): a single upload directory whose `xl.meta` was
     /// destroyed (crash mid-write, torn disk state) must degrade to that upload
     /// alone. Failing the whole ListMultipartUploads turns one piece of stale