fix(scanner): rebuild unreadable usage floor instead of stopping leader iteration

backlog#2918 retires the usage floor as a quota proof. After dual-corruption
recovery has been attempted, an unreadable floor is reported and rebuilt
through a CAS overwrite with a bootstrap marker rather than stopping the
leader iteration for a supervisor retry. Transient I/O errors that prevent
reading the floor revision fall through to the existing stop-and-retry path.

The identity-less floor regression from rustfs/rustfs#8670 now verifies
automatic rebuild and recovery instead of bounded backoff.

.agents/references/implementation.md

@@ -18,6 +18,7 @@ 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/e2e-distributed-selection.txt

@@ -1,2 +1,2 @@
-sha256-linux=eb33067d90ee66c0a97e8f3658e46c152e47f897d2fbfdc6cb5ad93cfa55414b
-sha256-darwin=eb33067d90ee66c0a97e8f3658e46c152e47f897d2fbfdc6cb5ad93cfa55414b
+sha256-linux=686dcc075e41a75dde3d37e5bd0393d016469f02f83aa3508f92bfc17f26a4d4
+sha256-darwin=686dcc075e41a75dde3d37e5bd0393d016469f02f83aa3508f92bfc17f26a4d4

.config/e2e-full-selection.txt

@@ -1,2 +1,2 @@
-sha256-darwin=4fb92e88763982eabafd74d05eb3d269387624a447e427a8c6f84914e5b03bfe
-sha256-linux=bd0db7e846ce24f056a097655db8fe2265201913260d0e16feb38d99dcb954a7
+sha256-darwin=7c705942d3a9e583ebaa85845daa21c4f81fdbf36def24db931aaef38636c53e
+sha256-linux=5c33dc395233671cb77452f8fb12900ecdbeb368632222b96835d310bce1aab8

.config/e2e-repl-nightly-selection.txt

@@ -1 +1 @@
-sha256=4eac269f9a59b2f9be4e7a87ea6aa38454f5ebe10ede35c9b8d4218137d2cd35
+sha256=e4ee3898b840a8374cb02c64342cc15f8d7ecd1becaf4b4a2a4657290f9e7ff1

.config/e2e-smoke-selection.txt

@@ -1 +1 @@
-sha256=879f421f1115d44f930e229510a2e533cfd5ebd4effe38730b82ef61f4fd7a86
+sha256=00f8a56b75990b487a594b97c36610b94476a6944ba00473e37187ea654d42bf

.config/make/lint-fmt.mak

@@ -70,11 +70,6 @@ s3s-footprint-check: ## Check the s3s dependency footprint ratchet stays frozen
 	@echo "📦 Checking s3s footprint ratchet..."
 	./scripts/check_s3s_footprint.sh
 
-.PHONY: test-count-ratchet-check
-test-count-ratchet-check: ## Check no workspace crate lost tests or gained #[ignore] against the committed baseline
-	@echo "🧪 Checking per-crate test-count ratchet..."
-	./scripts/check_test_count_ratchet.sh
-
 .PHONY: fips-wording-check
 fips-wording-check: ## Check docs and crates/kms do not over-claim crypto capabilities
 	@echo "📣 Checking cryptographic capability wording guard..."

.config/make/pre-commit.mak

@@ -20,11 +20,11 @@ planning-docs-check: ## Check that no planning-type documents are committed
 	./scripts/check_no_planning_docs.sh
 
 .PHONY: pre-commit
-pre-commit: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check error-other-ratchet-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check s3s-footprint-check test-count-ratchet-check fips-wording-check embedded-secrets-check test-wiring-check doc-paths-check planning-docs-check quick-check ## Run fast pre-commit checks without clippy/full tests
+pre-commit: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check error-other-ratchet-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check s3s-footprint-check fips-wording-check embedded-secrets-check test-wiring-check doc-paths-check planning-docs-check quick-check ## Run fast pre-commit checks without clippy/full tests
 	@echo "✅ All pre-commit checks passed!"
 
 .PHONY: pre-pr
-pre-pr: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check error-other-ratchet-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check s3s-footprint-check test-count-ratchet-check fips-wording-check embedded-secrets-check test-wiring-check doc-paths-check planning-docs-check log-analyzer-rules-check offline-enrollment-e2e-check clippy-check test ## Run full pre-PR checks with clippy and tests
+pre-pr: fmt-check unsafe-code-check architecture-migration-check logging-guardrails-check error-other-ratchet-check tokio-io-uring-check extension-schema-check body-cache-whitelist-check s3s-footprint-check fips-wording-check embedded-secrets-check test-wiring-check doc-paths-check planning-docs-check log-analyzer-rules-check offline-enrollment-e2e-check clippy-check test ## Run full pre-PR checks with clippy and tests
 	@echo "✅ All pre-PR checks passed!"
 
 .PHONY: dev-check

.config/make/tests.mak

@@ -51,9 +51,7 @@ script-tests: ## Run shell script tests
 	./scripts/test_python_bin.sh
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_check_doc_paths.py
 	./scripts/check_embedded_secrets.sh --self-test
-	./scripts/check_s3s_footprint.sh --self-test
 	$(RUSTFS_PYTHON_BIN) ./scripts/check_test_wiring.py --self-test
-	$(RUSTFS_PYTHON_BIN) ./scripts/codemods/s3_error_to_s3_types.py --self-test
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_e2e_binary.py
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_inspect_btf_prototypes.py
 	$(RUSTFS_PYTHON_BIN) ./scripts/test_release_build_workflow.py

.config/nextest.toml

@@ -356,12 +356,6 @@ threads-required = "num-test-threads"
 filter = 'package(rustfs-ecstore) & test(=store::init::tests::dispatch_manifest_rollback_bounded_concurrency_reaches_tail_behind_slow_member)'
 threads-required = "num-test-threads"
 
-# These short-deadline real-disk progress probes need the test run's capacity
-# for scanner and object-lock handoffs; keep their assertions and deadlines.
-[[profile.default.overrides]]
-filter = '(package(rustfs-scanner) & (test(=scanner::tests::cycle_persist_failure::later_cycle_post_commit_failure_reloads_durable_state) | test(=scanner::tests::running_main_loop_catches_up_pause_cleared_after_startup_observe))) | (package(rustfs-ecstore) & test(=store::init::tests::restored_transitioned_delete_causally_enqueues_free_version))'
-threads-required = "num-test-threads"
-
 # ---------------------------------------------------------------------------
 # ci profile — the strict CI gate (ci.yml `cargo nextest run --profile ci`)
 # ---------------------------------------------------------------------------
@@ -430,12 +424,6 @@ threads-required = "num-test-threads"
 filter = 'package(rustfs-scanner) & (test(/^scanner::backlog::tests::native_/) | test(=scanner_folder::tests::mrf_ownership::mrf_ownership_manager_completion_preserves_scanner_pending) | test(/^scanner_io::tests::service_cohort::/))'
 threads-required = "num-test-threads"
 
-# Keep short-deadline real-disk progress probes from competing with unrelated
-# tests for scanner and object-lock capacity. Assertions and deadlines stay on.
-[[profile.ci.overrides]]
-filter = '(package(rustfs-scanner) & (test(=scanner::tests::cycle_persist_failure::later_cycle_post_commit_failure_reloads_durable_state) | test(=scanner::tests::running_main_loop_catches_up_pause_cleared_after_startup_observe))) | (package(rustfs-ecstore) & test(=store::init::tests::restored_transitioned_delete_causally_enqueues_free_version))'
-threads-required = "num-test-threads"
-
 # Emit this expensive fixture's stage timings in CI and use tmpfs when safe.
 [[profile.ci.overrides]]
 filter = 'package(rustfs-ecstore) & test(=store::init::tests::decommission_durable_ilm_receipt_pagination_fails_closed_on_second_page)'
@@ -710,14 +698,6 @@ test-group = 'ecstore-serial-flaky'
 # the PR-lane e2e coverage for scanner usage snapshots consumed by quota and
 # admin surfaces. It uses the same single-node, random-port, isolated-temp-dir
 # fixture as the existing smoke modules.
-#
-# Dual-stack differential (rustfs/backlog#2740): `dual_stack_differential::`
-# starts two single-node servers from the same binary, one per
-# RUSTFS_S3_STACK value, on random ports with isolated temp dirs, and runs one
-# SDK script covering every operation of `impl S3 for FS` against both. Its
-# comparator unit tests need no server. It meets the admission criteria
-# unchanged; the module clause admits a new differential test without another
-# filter edit.
 [profile.e2e-smoke]
 default-filter = """
     package(e2e_test) & (
@@ -726,7 +706,6 @@ default-filter = """
         | test(/^reliant::lifecycle::/)
         | test(/^conditional_delete_objects_test::/)
         | test(/^reliant::tiering::/)
-        | test(/^dual_stack_differential::/)
         | test(/^upgrade_compatibility_test::upgrade_write_readiness_tests::/)
         | test(/^on_demand_migration::(get_basic_test::(get_miss_pulls_inline_and_serves_locally_afterwards|head_miss_answers_from_the_source_without_persisting)|interaction_test::test_odm_admin_config_is_redacted_and_status_counts_match_the_source)$/)
     )
@@ -981,6 +960,12 @@ test-group = 'e2e-inline-boundaries'
 filter = 'package(e2e_test) & test(/^heal_erasure_disk_rebuild_test::/)'
 test-group = 'e2e-cluster-nightly'
 
+# The multi-pool crash fixture seeds three nodes and 36 drives. Reserve this
+# nextest run's workers so other multi-node tests do not starve its deadline.
+[[profile.e2e-full.overrides]]
+filter = 'package(e2e_test) & test(=heal_erasure_disk_rebuild_test::tests::test_cluster_root_heal_recovers_ec84_shards_across_multi_pool_after_background_target_crash)'
+threads-required = "num-test-threads"
+
 [[profile.e2e-full.overrides]]
 filter = 'package(e2e_test) & (test(/^kms::kms_vault_test::/) | test(/^kms::kms_rekey_sweep_test::/) | test(/^kms::configured_roundtrip_test::test_configured_vault_kms_admin_and_versioned_cleanup$/))'
 test-group = 'e2e-vault'

.config/release-validation-plan.json

@@ -0,0 +1,77 @@
+{
+  "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."
+  }
+}

.config/s3s-edge-allowlist.txt

@@ -1,37 +0,0 @@
-# Files that may still reference s3s (`s3s::` or `s3s_sigv4`) when Phase 1 of
-# the gateway migration ends (rustfs/backlog#2734 task T0.6, rustfs/backlog#2741).
-# Consumed only by `scripts/check_s3s_footprint.sh --mode allowlist`.
-#
-# One entry per line: a repository-relative file path or a git `:(glob)`
-# pathspec. `**` matches across directories, `*` stays within one path
-# component, and a directory entry matches everything under it. Blank lines
-# and lines starting with `#` are ignored; an entry may not contain whitespace,
-# so a note belongs on its own comment line.
-#
-# Every Rust file listed by `git grep -l '\bs3s\(::\|_sigv4\)' -- '*.rs'` that
-# no entry matches fails the allowlist mode. Task T1.9 switches CI to that
-# mode; until then `--dry-run` prints the files still outside this list, which
-# is the Phase 1 tracking list.
-#
-# Never add crates/** other than crates/e2e_test: the engine crates leave s3s
-# entirely, and the script rejects such an entry. Only the s3s-facing edge of
-# the rustfs binary and the e2e oracle keep it.
-
-# rustfs binary: the s3s-facing edge that survives Phase 1
-rustfs/src/storage/ecfs.rs
-rustfs/src/storage/s3_compat/**
-rustfs/src/storage/access.rs
-rustfs/src/auth.rs
-rustfs/src/error.rs
-rustfs/src/storage_api.rs
-rustfs/src/app/storage_api.rs
-rustfs/src/admin/router.rs
-rustfs/src/app/metadata_route.rs
-rustfs/src/server/http.rs
-rustfs/src/server/layer.rs
-rustfs/src/server/hybrid.rs
-rustfs/src/protocols/client.rs
-
-# e2e oracle: the test target that verifies S3 behaviour against s3s
-crates/e2e_test/src/fake_s3_target/**
-crates/e2e_test/src/**

.config/s3s-footprint-baseline.txt

@@ -1,17 +0,0 @@
-# Exact baseline for the direct s3s footprint, consumed only by
-# scripts/check_s3s_footprint.sh (rustfs/backlog#1677; rustfs/backlog#2734 T0.4).
-#
-# Each value is the exact measurement of the tree, not a ceiling. CI fails when a
-# measured counter differs from its line here in either direction:
-#   - a larger measurement means new code widened the s3s surface: route it
-#     through the gateway abstractions instead; never raise a value here;
-#   - a smaller measurement means the PR shrank the surface: lower the matching
-#     value to the measured number in the same PR.
-#
-# files           Rust files referencing s3s paths, repo-wide minus crates/e2e_test
-# s3_error_lines  lines holding s3_error!, same scope, minus those the script
-#                 header's rule clears (rustfs_s3_types's macro); fails closed
-# ecstore_files   Rust files referencing s3s paths under crates/ecstore/src
-files=65
-s3_error_lines=289
-ecstore_files=0

.config/test-count-baseline.txt

@@ -1,64 +0,0 @@
-# Per-crate test-count baseline consumed by scripts/check_test_count_ratchet.sh
-# (rustfs/backlog#2734 section 1 rule 3; T0.3 in rustfs/backlog#2738).
-#
-# One row per workspace member: <package>, tests, ignored, tab-separated.
-# tests counts #[test], #[tokio::test], #[tokio::test(...)] and #[test_case(...)]
-# attribute lines under the package directory; ignored counts #[ignore] and
-# #[ignore = "..."]. Both columns are exact: CI fails when a crate's tests fall
-# below or rise above its row, or when its ignored count changes. Raise a row in
-# the PR that adds tests; lowering one is a reviewed statement that tests were
-# intentionally removed. Regenerate with:
-#   scripts/check_test_count_ratchet.sh --update
-e2e_test	993	20
-rustfs	6087	64
-rustfs-audit	70	0
-rustfs-checksums	26	0
-rustfs-common	36	0
-rustfs-concurrency	54	0
-rustfs-config	43	0
-rustfs-connect-symbol-catalog	6	0
-rustfs-credentials	24	0
-rustfs-crypto	67	0
-rustfs-data-usage	56	0
-rustfs-ecstore	7416	2
-rustfs-extension-schema	23	0
-rustfs-filemeta	353	0
-rustfs-heal	1033	3
-rustfs-heal-contracts	8	0
-rustfs-iam	401	0
-rustfs-io-core	49	0
-rustfs-io-metrics	154	0
-rustfs-keystone	29	0
-rustfs-kms	715	25
-rustfs-license	2	0
-rustfs-lifecycle	155	0
-rustfs-lock	143	0
-rustfs-log-analyzer	90	0
-rustfs-madmin	210	0
-rustfs-notify	140	0
-rustfs-object-capacity	92	0
-rustfs-object-data-cache	140	0
-rustfs-obs	385	0
-rustfs-policy	734	0
-rustfs-protocols	748	1
-rustfs-protos	73	0
-rustfs-replication	209	0
-rustfs-rio	206	0
-rustfs-rio-v2	34	6
-rustfs-s3-client	69	0
-rustfs-s3-ops	8	0
-rustfs-s3-types	105	0
-rustfs-s3select-api	207	0
-rustfs-s3select-query	189	2
-rustfs-scanner	1261	20
-rustfs-scanner-metrics	90	0
-rustfs-security-governance	20	0
-rustfs-signer	31	0
-rustfs-storage-api	34	0
-rustfs-targets	604	26
-rustfs-test-utils	1	0
-rustfs-tls-runtime	43	0
-rustfs-trusted-proxies	68	0
-rustfs-utils	247	0
-rustfs-zip	30	0
-zstd	11	0

.github/actions/quick-checks/action.yml

@@ -96,10 +96,6 @@ runs:
       shell: bash
       run: ./scripts/check_s3s_footprint.sh
 
-    - name: Check per-crate test-count ratchet
-      shell: bash
-      run: ./scripts/check_test_count_ratchet.sh
-
     - name: Check cryptographic capability wording
       shell: bash
       run: ./scripts/check_fips_wording.sh

.github/workflows/build.yml

@@ -814,13 +814,18 @@ jobs:
           export AWS_SECRET_ACCESS_KEY="$R2_SECRET_ACCESS_KEY"
           export AWS_DEFAULT_REGION="auto"
 
-          # Determine upload path based on build type
+          # 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.
           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://${R2_BUCKET}/artifacts/rustfs/release/"
-            echo "📤 Uploading release build to R2 release directory"
+            R2_PATH="s3://${R2_BUCKET}/artifacts/rustfs/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}/"
+            echo "📤 Staging release build for certification-gated promotion"
           fi
 
           # Upload all rustfs zip files to R2 using S3-compatible API
@@ -869,6 +874,221 @@ 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
@@ -1028,6 +1248,10 @@ 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
@@ -1068,6 +1292,45 @@ 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
           {
@@ -1084,16 +1347,59 @@ jobs:
 
           echo "✅ Updated latest.json for ${RELEASE_TYPE} release $VERSION"
 
-  # Publish release (remove draft status)
+  # Publish release (remove draft status). Requires the release-certification
+  # aggregate: without a complete legal success there is no public write.
   publish-release:
     name: Publish Release
-    needs: [ build-check, create-release, upload-release-assets ]
+    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
     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: test-and-lint (workspace and ILM), build-rustfs-debug-binary,
+  # Readers: workspace-lint-and-build, workspace-tests (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 test-and-lint's own run excludes. The second build adds
+      # e2e_test, which the workspace 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

@@ -16,9 +16,7 @@ name: Continuous Integration
 
 on:
   push:
-    # gateway/integration receives the daily merge of main as a direct push
-    # (rustfs/backlog#2734), so its pushes must prove the result like main's.
-    branches: [ main, gateway/integration ]
+    branches: [ main ]
     paths-ignore:
       - "**.md"
       - "docs/**"
@@ -115,7 +113,7 @@ 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 '^rehearse_shards=' "$GITHUB_OUTPUT"; then
+          if ! grep -q '^plan=' "$GITHUB_OUTPUT" || ! grep -q '^plan_contract=2$' "$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."
           fi
@@ -162,7 +160,7 @@ jobs:
       - name: Run shared quick checks
         uses: ./.github/actions/quick-checks
 
-  test-and-lint:
+  workspace-lint-and-build:
     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 ]
@@ -195,13 +193,13 @@ jobs:
 
       - name: Prepare test evidence
         run: |
-          mkdir -p artifacts/test-and-lint
+          mkdir -p artifacts/workspace
           {
             echo "run_id=${GITHUB_RUN_ID}"
             echo "job=${GITHUB_JOB}"
             echo "runner=${RUNNER_NAME}"
             echo "started_at=$(date --utc --iso-8601=seconds)"
-          } > artifacts/test-and-lint/run-metadata.txt
+          } > artifacts/workspace/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
@@ -235,11 +233,11 @@ jobs:
 
       - name: Run documentation tests
         run: |
-          mkdir -p artifacts/test-and-lint
+          mkdir -p artifacts/workspace
           set +e
           timeout --verbose --signal=TERM --kill-after=30s 15m \
             python3 scripts/ci_test_artifact.py cargo doc --configuration workspace \
-            2>&1 | tee artifacts/test-and-lint/doctest.log
+            2>&1 | tee artifacts/workspace/doctest.log
           status=${PIPESTATUS[0]}
           {
             echo "command=cargo test --all --exclude e2e_test --doc"
@@ -248,7 +246,7 @@ jobs:
             echo
             echo "Remaining test-related processes:"
             pgrep -af 'cargo|rustdoc|target/.*/deps/' || true
-          } > artifacts/test-and-lint/doctest-diagnostics.txt
+          } > artifacts/workspace/doctest-diagnostics.txt
           exit "${status}"
 
       - name: Upload test reports and diagnostics
@@ -257,7 +255,7 @@ jobs:
         with:
           name: junit-test-and-lint-${{ github.run_number }}-${{ github.run_attempt }}
           path: |
-            artifacts/test-and-lint
+            artifacts/workspace
           retention-days: 3
           if-no-files-found: error
 
@@ -270,7 +268,7 @@ jobs:
 
   workspace-tests:
     name: Workspace tests
-    needs: [ test-and-lint, classify-changes ]
+    needs: [ workspace-lint-and-build, 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
@@ -295,14 +293,14 @@ jobs:
 
       - name: Extract and list workspace tests
         run: |
-          mkdir -p artifacts/test-and-lint
+          mkdir -p artifacts/workspace
           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/test-and-lint/core-test-listing.json
-          python3 scripts/check_test_wiring.py --check-core artifacts/test-and-lint/core-test-listing.json
+            > artifacts/workspace/core-test-listing.json
+          python3 scripts/check_test_wiring.py --check-core artifacts/workspace/core-test-listing.json
 
       - name: Run nextest tests
         run: |
-          mkdir -p artifacts/test-and-lint
+          mkdir -p artifacts/workspace
           rm -f target/nextest/ci/junit.xml
           ./scripts/ci/resource_sampler.sh start nextest
           trap './scripts/ci/resource_sampler.sh stop' EXIT
@@ -311,7 +309,7 @@ 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/test-and-lint/nextest.log
+            2>&1 | tee artifacts/workspace/nextest.log
           status=${PIPESTATUS[0]}
           {
             echo "command=workspace archive execution"
@@ -323,13 +321,13 @@ jobs:
             echo
             echo "Kernel OOM / kill events:"
             dmesg -T 2>/dev/null | grep -iE 'oom|out of memory|killed process' | tail -20 || true
-          } > artifacts/test-and-lint/nextest-diagnostics.txt
+          } > artifacts/workspace/nextest-diagnostics.txt
           exit "${status}"
 
       - name: Verify workspace execution completeness
         run: |
-          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
+          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
 
       - name: Run ignored ILM integration tests serially
         if: needs.classify-changes.outputs.mode == 'full'
@@ -360,7 +358,7 @@ jobs:
           name: workspace-test-evidence-${{ github.run_attempt }}
           path: |
             target/nextest/ci/junit.xml
-            artifacts/test-and-lint
+            artifacts/workspace
             artifacts/ilm-integration
           retention-days: 3
           if-no-files-found: error
@@ -370,7 +368,7 @@ jobs:
         if: needs.classify-changes.outputs.rehearse_shards == 'true'
         run: |
           python3 scripts/ci_test_shards.py prepare \
-            --listing artifacts/test-and-lint/core-test-listing.json \
+            --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'
@@ -451,7 +449,7 @@ jobs:
 
   connect-feature-boundaries:
     name: Connect Feature Boundaries
-    if: needs.classify-changes.outputs.mode == 'full' && needs.classify-changes.outputs.connect != 'false' && (github.event_name != 'pull_request' || github.event.action != 'closed')
+    if: needs.classify-changes.outputs.mode == 'full' && needs.classify-changes.outputs.connect != 'false' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -501,11 +499,13 @@ jobs:
 
   test-and-lint-rio-v2:
     name: Test and Lint (rio-v2)
-    # 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)
+    # 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)
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -542,12 +542,12 @@ 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/test-and-lint
+          mkdir -p artifacts/workspace
           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/test-and-lint/nextest.log
+            2>&1 | tee artifacts/workspace/nextest.log
           cargo test -p rustfs --doc --features rio-v2
 
       - name: Upload rio-v2 test reports and diagnostics
@@ -557,14 +557,14 @@ jobs:
           name: junit-test-and-lint-rio-v2-${{ github.run_number }}-${{ github.run_attempt }}
           path: |
             target/nextest/ci/junit.xml
-            artifacts/test-and-lint
+            artifacts/workspace
           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('["merge_group", "schedule", "workflow_dispatch"]'), github.event_name)
+    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
     needs: [ quick-checks, classify-changes ]
     runs-on: sm-standard-4
     timeout-minutes: 90
@@ -633,7 +633,7 @@ jobs:
           path: |
             target/nextest/ci/junit.xml
             artifacts/protocol-tests
-            artifacts/test-and-lint
+            artifacts/workspace
           retention-days: 3
           if-no-files-found: warn
 
@@ -785,7 +785,7 @@ 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' && (github.event_name != 'pull_request' || github.event.action != 'closed')
+    if: needs.classify-changes.outputs.mode == 'full' && contains(fromJSON('["schedule", "workflow_dispatch"]'), github.event_name)
     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
@@ -899,8 +899,6 @@ jobs:
     # Retain the producer image and fixture paths until the runtime pilot passes.
     runs-on: sm-standard-4
     timeout-minutes: 30
-    env:
-      RUSTFS_S3_STACK: legacy
     steps:
       - name: Checkout repository
         uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
@@ -982,7 +980,7 @@ jobs:
           path: |
             ${{ runner.temp }}/rustfs-e2e-smoke-logs/
             ${{ runner.temp }}/rustfs-e2e-smoke-list.json
-            artifacts/test-and-lint
+            artifacts/workspace
           if-no-files-found: warn
 
       - name: Upload e2e smoke JUnit report
@@ -1021,122 +1019,18 @@ jobs:
           path: ${{ runner.temp }}/rustfs-e2e-*/rustfs.log
           retention-days: 3
 
-  # The same e2e-smoke suite against the same debug binary with the gateway
-  # S3 stack selected (rustfs/backlog#2734). Report-only: it is outside the
-  # Test and Lint aggregate and becomes required at T2.10. The test-binary
-  # download, identity, membership, run and completeness steps must stay
-  # identical to e2e-tests; scripts/ci_gate.py enforces that.
-  e2e-tests-gateway:
-    name: e2e-smoke (gateway, report-only until T2.10)
-    needs: [ build-rustfs-debug-binary ]
-    runs-on: sm-standard-2
-    timeout-minutes: 30
-    continue-on-error: true
-    env:
-      RUSTFS_S3_STACK: gateway
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
-        with:
-          persist-credentials: false
-
-      - name: Install verification runtime
-        uses: ./.github/actions/test-runtime
-
-      - name: Download E2E test binaries
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: e2e-test-binaries
-          path: ${{ runner.temp }}
-
-      - name: Verify E2E archive identity
-        run: python3 scripts/ci_test_artifact.py verify --configuration e2e --archive "$RUNNER_TEMP/e2e-tests.tar.zst"
-
-      - name: Set up Python
-        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
-        with:
-          python-version: "3.12"
-
-      - name: Install awscurl
-        run: |
-          python3 -m pip install --user --upgrade pip "awscurl==0.44"
-          echo "AWSCURL_PATH=$HOME/.local/bin/awscurl" >> "$GITHUB_ENV"
-
-      - name: Verify awscurl
-        run: test -x "$AWSCURL_PATH"
-
-      # Download after the cache restore so the freshly built binary from the
-      # build job always wins over anything restored into target/debug.
-      - name: Download debug binary
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-        with:
-          name: rustfs-debug-binary
-          path: target/debug
-
-      - name: Make binary executable
-        run: chmod +x ./target/debug/rustfs
-
-      # Build the e2e test graph once. The archive is reused by the smoke
-      # selection guard, security exact-count check, and run below, avoiding a
-      # second compile of the same e2e_test target on cold runners (backlog#1645).
-      - name: Verify e2e smoke test membership
-        env:
-          NEXTEST_ARCHIVE: ${{ runner.temp }}/e2e-tests.tar.zst
-          NEXTEST_LISTING: ${{ runner.temp }}/rustfs-e2e-smoke-list.json
-        run: |
-          cargo nextest list --profile e2e-smoke --archive-file "${NEXTEST_ARCHIVE}" --workspace-remap "$GITHUB_WORKSPACE" --extract-to "$GITHUB_WORKSPACE" --extract-overwrite --message-format json > "${NEXTEST_LISTING}"
-          python3 ./scripts/check_test_wiring.py --check-profile e2e-smoke "${NEXTEST_LISTING}"
-          ./scripts/check_security_smoke_count.sh check "${NEXTEST_LISTING}"
-
-      # PR smoke subset of the in-repo e2e suite (backlog#1149 ci-4). The
-      # profile.e2e-smoke default-filter in .config/nextest.toml is the single
-      # wiring mechanism for e2e tests in CI — extend that filter instead of
-      # adding new e2e jobs here. Each test spawns its own rustfs server on a
-      # random port and reuses the downloaded debug binary above.
-      - name: Run e2e smoke suite
-        env:
-          NEXTEST_ARCHIVE: ${{ runner.temp }}/e2e-tests.tar.zst
-          RUSTFS_E2E_LOG_DIR: ${{ runner.temp }}/rustfs-e2e-smoke-logs
-          SAMPLER_INTERVAL_SECS: "15"
-        run: |
-          ./scripts/ci/resource_sampler.sh start e2e-smoke
-          trap './scripts/ci/resource_sampler.sh stop' EXIT
-          python3 scripts/e2e_binary.py run --features e2e-test-hooks -- cargo nextest run --profile e2e-smoke --cargo-metadata target/nextest/cargo-metadata.json --binaries-metadata target/nextest/binaries-metadata.json --workspace-remap "$GITHUB_WORKSPACE" --target-dir-remap "$GITHUB_WORKSPACE/target" \
-            --status-level all --final-status-level all --failure-output final
-
-      - name: Verify e2e smoke execution completeness
-        run: python3 scripts/ci_test_artifact.py evidence "$RUNNER_TEMP/rustfs-e2e-smoke-list.json" target/nextest/e2e-smoke/junit.xml
-
-      - name: Upload e2e smoke diagnostics
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: e2e-smoke-gateway-diagnostics-${{ github.run_number }}-${{ github.run_attempt }}
-          path: |
-            ${{ runner.temp }}/rustfs-e2e-smoke-logs/
-            ${{ runner.temp }}/rustfs-e2e-smoke-list.json
-          if-no-files-found: warn
-
-      - name: Upload e2e smoke JUnit report
-        if: always()
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: e2e-smoke-gateway-junit-${{ github.run_number }}-${{ github.run_attempt }}
-          path: target/nextest/e2e-smoke/junit.xml
-          if-no-files-found: warn
-
   e2e-full:
     name: End-to-End Tests (full merge gate)
     # Merge gate only (backlog#1149 ci-5): the never-automated user-visible
     # suites — KMS, object_lock, multipart_auth, quota, checksum, encryption,
     # security-boundary, ... — via the e2e-full nextest profile. Too heavy for
-    # every PR, so it is gated to main and gateway/integration pushes, the merge
-    # queue, and manual dispatch. protocols / the 7 cluster suites / replication
-    # / #[ignore] are owned by other lanes (see .config/nextest.toml profile.e2e-full).
+    # every PR, so it is gated to main pushes, the merge queue, and manual
+    # dispatch. protocols / the 7 cluster suites / replication / #[ignore] are
+    # owned by other lanes (see .config/nextest.toml profile.e2e-full).
     if: >-
       github.event_name == 'workflow_dispatch' ||
       github.event_name == 'merge_group' ||
-      (github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/gateway/integration'))
+      (github.event_name == 'push' && github.ref == 'refs/heads/main')
     needs: [ build-rustfs-debug-binary ]
     # Retain the producer image and fixture paths until the runtime pilot passes.
     runs-on: sm-standard-4
@@ -1497,7 +1391,7 @@ jobs:
       - classify-changes
       - typos
       - quick-checks
-      - test-and-lint
+      - workspace-lint-and-build
       - workspace-tests
       - workspace-shards
       - workspace-shard-evidence
@@ -1533,7 +1427,7 @@ jobs:
       - required-checks
       - typos
       - quick-checks
-      - test-and-lint
+      - workspace-lint-and-build
       - workspace-tests
       - core-contract
       - test-and-lint-rio-v2

.github/workflows/docker.yml

@@ -329,13 +329,75 @@ 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 ${name} does not match its recorded digest" >&2
+              exit 1
+            fi
+          done < <(jq -r '.deliverables[] | select(.name | contains("linux")) | [.name, .location, .sha256] | @tsv' certification/candidate.json)
+
   # Build multi-arch Docker images
   # Strategy: Build images using pre-built binaries from dl.rustfs.com
   # Supports both release and dev channel binaries based on build context
   # Only runs when should_build is true (which includes workflow success check)
   build-docker:
     name: Build Docker Images
-    needs: build-check
+    needs: [ build-check, release-certification ]
     if: needs.build-check.outputs.should_build == 'true'
     runs-on: ubuntu-latest
     timeout-minutes: 60
@@ -443,6 +505,14 @@ jobs:
           # Output tags
           echo "tags=$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"
@@ -467,7 +537,9 @@ jobs:
           file: ${{ matrix.file }}
           platforms: ${{ env.DOCKER_PLATFORMS }}
           push: ${{ needs.build-check.outputs.should_push == 'true' }}
-          tags: ${{ steps.meta.outputs.tags }}
+          # 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 }}
           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
@@ -493,6 +565,114 @@ 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/helm-package.yml

@@ -30,9 +30,102 @@ 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/package.yml

@@ -225,10 +225,57 @@ 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 }}-${{ matrix.libc }})
-    needs: resolve
+    needs: [ resolve, release-certification ]
     runs-on: ubuntu-latest # gh CLI required; the sm-standard-2 fleet does not ship it
     timeout-minutes: 30
     strategy:
@@ -494,6 +541,55 @@ jobs:
           echo "rpm_file=$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 "$RUNNER_TEMP/wrapped-rustfs" \
+              --artifact-role binary
+          done
+
       - name: Upload packages to artifacts
         uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
         with:
@@ -531,10 +627,14 @@ jobs:
           export AWS_SECRET_ACCESS_KEY="$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 [[ "$BUILD_TYPE" == "development" ]]; then
             R2_PREFIX="artifacts/rustfs/packages/dev"
           else
-            R2_PREFIX="artifacts/rustfs/packages/release"
+            R2_PREFIX="artifacts/rustfs/packages/staging/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}"
           fi
           R2_PATH="s3://${R2_BUCKET}/${R2_PREFIX}/"
 
@@ -549,18 +649,6 @@ 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:
@@ -614,6 +702,114 @@ 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

ARCHITECTURE.md

@@ -155,7 +155,7 @@ default build (lifecycle:
    - ⚠️ PARTIALLY VIOLATED: serving-side `s3s` references remain in ecstore
      (bucket metadata/replication/lifecycle DTOs and error mapping). The
      count is ratcheted shrink-only by `scripts/check_s3s_footprint.sh`
-     (the `ecstore_files` line of `.config/s3s-footprint-baseline.txt`; the `object_lock` module was converted to
+     (`S3S_ECSTORE_FILES_BASELINE`; the `object_lock` module was converted to
      storage-level types as the first ratchet step). Target state: the
      baseline reaches zero and ecstore's `Cargo.toml` drops `s3s`.
 

Cargo.lock

@@ -1321,9 +1321,9 @@ dependencies = [
 
 [[package]]
 name = "aws-smithy-schema"
-version = "1.1.0"
+version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bec8dae1015a6d959a5faf86fbdf77486cfe19e4ccb6ee009d8a46efc45028a4"
+checksum = "9543fc722ed4865ab29fb66bd7ed0bef7b029d265ba8c587144511e30006d431"
 dependencies = [
  "aws-smithy-runtime-api",
  "aws-smithy-types",
@@ -4198,9 +4198,9 @@ checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
 
 [[package]]
 name = "encoding_rs"
-version = "0.8.42"
+version = "0.8.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e985e0451871ad22fb8d2b6b076e2028a502a0d3950998c2c5c0a4f9b5d9679"
+checksum = "89253175e704ab869b04f9db224d38630e0211a53841a79181deae0889e169f5"
 dependencies = [
  "cfg-if",
  "core_detect",
@@ -5277,9 +5277,9 @@ dependencies = [
 
 [[package]]
 name = "hotpath"
-version = "0.30.1"
+version = "0.30.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "502dc37a7c218b9b1d3a0ccfb904da81d10d6dda0e899c722c503092d55576ea"
+checksum = "b39e941010d86063ff233bf8325269bf68097fb24ba67000fbddc0a410e8056e"
 dependencies = [
  "arc-swap",
  "async-channel",
@@ -5312,15 +5312,15 @@ dependencies = [
 
 [[package]]
 name = "hotpath-drain"
-version = "0.30.1"
+version = "0.30.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ea17d04c231b90b1f68a91f6f80fb0762c5dea07c611dce9ae157b56a50ff4c"
+checksum = "d0faae1a9e1fd8ce5debaaaf452dcbe833fc8a8a4f3779d2ec8828b116c3c16a"
 
 [[package]]
 name = "hotpath-macros"
-version = "0.30.1"
+version = "0.30.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a76e0af911930fc97abc766b393b48cdca77fea9f5f6b388cf2123a6d9c30deb"
+checksum = "a24f5179ff680132003306354efd0ac8cde12e87b1a788719c836e91af35cb58"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5899,9 +5899,9 @@ dependencies = [
 
 [[package]]
 name = "js-sys"
-version = "0.3.106"
+version = "0.3.107"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7883d941dae510fb2d978fc3fe018c71c9e2892fd38854de3e8b92c2e5ad9cc5"
+checksum = "8dc09d2154098bbf4ef54eab6b117a3c24cbbffe94046b16ee6d6d4510584d3a"
 dependencies = [
  "cfg-if",
  "futures-util",
@@ -6094,9 +6094,9 @@ dependencies = [
 
 [[package]]
 name = "libbz2-rs-sys"
-version = "0.2.5"
+version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "34b357333733e8260735ba5894eb928c02ecc69c78715f01a8019e7fa7f2db4c"
+checksum = "32f454fd6831a29c0e827ed075bca2a15be201bd57f4168f0fd1041124eab17e"
 
 [[package]]
 name = "libc"
@@ -8305,9 +8305,9 @@ dependencies = [
 
 [[package]]
 name = "pulldown-cmark"
-version = "0.13.5"
+version = "0.13.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "278e9268c93b9e498a2da46c34d90ba93a3255eb99009646398f34bc73ab36eb"
+checksum = "3db2be46835f013dd3f4fa7f5f7402c537787b54ebb6fe2b94bbdd7e2669bb7b"
 dependencies = [
  "bitflags 2.13.2",
  "memchr",
@@ -8520,15 +8520,6 @@ version = "1.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
 
-[[package]]
-name = "quick-xml"
-version = "0.41.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e660451e55124f798a69a5af3f49ccfbefbd41910eefd25caf2393e1f3473ec1"
-dependencies = [
- "memchr",
-]
-
 [[package]]
 name = "quick-xml"
 version = "0.42.0"
@@ -8832,9 +8823,9 @@ dependencies = [
 
 [[package]]
 name = "redis"
-version = "1.8.0"
+version = "1.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7acd809e80afa754c63f586955699d8990efe1c4b6613183ee5f027a11fbc8b5"
+checksum = "db7f3d75b5a3301746bff39a767bf4c5c42506b08513527308b3875bfb64a031"
 dependencies = [
  "arc-swap",
  "arcstr",
@@ -9393,7 +9384,7 @@ dependencies = [
  "proptest",
  "prost 0.14.4",
  "pyroscope",
- "quick-xml 0.42.0",
+ "quick-xml",
  "quinn",
  "rand 0.10.3",
  "rcgen",
@@ -9412,7 +9403,6 @@ dependencies = [
  "rustfs-ecstore",
  "rustfs-extension-schema",
  "rustfs-filemeta",
- "rustfs-gateway-types",
  "rustfs-heal",
  "rustfs-heal-contracts",
  "rustfs-iam",
@@ -9691,7 +9681,6 @@ dependencies = [
  "rustfs-data-usage",
  "rustfs-erasure-codec",
  "rustfs-filemeta",
- "rustfs-gateway-types",
  "rustfs-heal-contracts",
  "rustfs-io-metrics",
  "rustfs-lifecycle",
@@ -9797,48 +9786,6 @@ dependencies = [
  "xxhash-rust",
 ]
 
-[[package]]
-name = "rustfs-gateway-stream"
-version = "0.2.0"
-source = "git+https://github.com/rustfs/gateway.git?rev=21283e874c2381bab611e9347acbc5b92e9e2b3c#21283e874c2381bab611e9347acbc5b92e9e2b3c"
-dependencies = [
- "bitflags 2.13.2",
- "bytes",
- "http 1.5.0",
- "http-body",
-]
-
-[[package]]
-name = "rustfs-gateway-types"
-version = "0.32.0+aws.2026-10-02"
-source = "git+https://github.com/rustfs/gateway.git?rev=21283e874c2381bab611e9347acbc5b92e9e2b3c#21283e874c2381bab611e9347acbc5b92e9e2b3c"
-dependencies = [
- "bytes",
- "crc-fast",
- "futures-core",
- "hex",
- "http 1.5.0",
- "md-5 0.11.0",
- "percent-encoding",
- "rustfs-gateway-stream",
- "rustfs-gateway-xml",
- "s3s",
- "sha1 0.11.0",
- "sha2 0.11.1",
- "time",
- "twox-hash",
- "unicode-normalization",
- "zeroize",
-]
-
-[[package]]
-name = "rustfs-gateway-xml"
-version = "0.4.0"
-source = "git+https://github.com/rustfs/gateway.git?rev=21283e874c2381bab611e9347acbc5b92e9e2b3c#21283e874c2381bab611e9347acbc5b92e9e2b3c"
-dependencies = [
- "quick-xml 0.41.0",
-]
-
 [[package]]
 name = "rustfs-heal"
 version = "1.0.2"
@@ -10109,10 +10056,10 @@ dependencies = [
  "metrics-util",
  "proptest",
  "rustfs-config",
- "rustfs-gateway-types",
  "rustfs-replication",
  "rustfs-scanner-metrics",
  "rustfs-storage-api",
+ "s3s",
  "serial_test",
  "temp-env",
  "time",
@@ -10175,6 +10122,7 @@ dependencies = [
  "reqwest",
  "rmp-serde",
  "rustfs-signer",
+ "s3s",
  "serde",
  "serde_json",
  "sysinfo",
@@ -10214,7 +10162,7 @@ dependencies = [
  "jiff",
  "metrics",
  "percent-encoding",
- "quick-xml 0.42.0",
+ "quick-xml",
  "rayon",
  "rustc-hash",
  "rustfs-config",
@@ -10395,13 +10343,10 @@ dependencies = [
  "rustfs-config",
  "rustfs-credentials",
  "rustfs-ecstore",
- "rustfs-gateway-stream",
- "rustfs-gateway-types",
  "rustfs-iam",
  "rustfs-keystone",
  "rustfs-policy",
  "rustfs-rio",
- "rustfs-s3-types",
  "rustfs-storage-api",
  "rustfs-test-utils",
  "rustfs-tls-runtime",
@@ -10409,13 +10354,13 @@ dependencies = [
  "rustfs-trusted-proxies",
  "rustfs-utils",
  "rustls",
+ "s3s",
  "serde",
  "serde_json",
  "sha1 0.11.0",
  "sha2 0.11.1",
  "socket2",
  "subtle",
- "sync_wrapper",
  "tempfile",
  "thiserror 2.0.21",
  "time",
@@ -10465,7 +10410,7 @@ dependencies = [
  "regex",
  "rmp",
  "rmp-serde",
- "rustfs-gateway-types",
+ "s3s",
  "serde",
  "time",
  "tokio",
@@ -10560,13 +10505,11 @@ dependencies = [
  "hyper-util",
  "lazy_static",
  "md-5 0.11.0",
- "quick-xml 0.42.0",
+ "quick-xml",
  "rand 0.10.3",
  "rustfs-checksums",
  "rustfs-config",
- "rustfs-gateway-types",
  "rustfs-rio",
- "rustfs-s3-types",
  "rustfs-signer",
  "rustfs-storage-api",
  "rustfs-tls-runtime",
@@ -10600,19 +10543,9 @@ dependencies = [
 name = "rustfs-s3-types"
 version = "1.0.2"
 dependencies = [
- "bytes",
- "futures-core",
  "hotpath",
- "http 1.5.0",
- "http-body",
- "http-body-util",
- "hyper",
- "hyper-util",
- "pin-project-lite",
- "s3s",
  "serde",
  "serde_json",
- "tokio",
 ]
 
 [[package]]
@@ -10636,10 +10569,9 @@ dependencies = [
  "parking_lot 0.13.0",
  "rustfs-common",
  "rustfs-ecstore",
- "rustfs-gateway-types",
- "rustfs-s3-types",
  "rustfs-storage-api",
  "rustfs-test-utils",
+ "s3s",
  "serde_json",
  "serial_test",
  "thiserror 2.0.21",
@@ -10665,6 +10597,7 @@ dependencies = [
  "parking_lot 0.13.0",
  "rustfs-s3select-api",
  "rustfs-test-utils",
+ "s3s",
  "serde",
  "serde_json",
  "tokio",
@@ -10684,6 +10617,9 @@ dependencies = [
  "hotpath",
  "http 1.5.0",
  "metrics",
+ "opentelemetry-proto",
+ "opentelemetry_sdk",
+ "prost 0.14.4",
  "rand 0.10.3",
  "rmp-serde",
  "rustfs-common",
@@ -10693,11 +10629,11 @@ dependencies = [
  "rustfs-data-usage",
  "rustfs-ecstore",
  "rustfs-filemeta",
- "rustfs-gateway-types",
  "rustfs-heal",
  "rustfs-heal-contracts",
  "rustfs-lifecycle",
  "rustfs-lock",
+ "rustfs-obs",
  "rustfs-s3-types",
  "rustfs-scanner-metrics",
  "rustfs-storage-api",
@@ -10750,10 +10686,9 @@ dependencies = [
  "bytes",
  "hotpath",
  "http 1.5.0",
- "http-body",
  "hyper",
- "rustfs-s3-types",
  "rustfs-utils",
+ "s3s",
  "serde_urlencoded",
  "thiserror 2.0.21",
  "time",
@@ -10811,6 +10746,7 @@ dependencies = [
  "rustfs-utils",
  "rustls",
  "rustls-native-certs",
+ "s3s",
  "serde",
  "serde_json",
  "sha2 0.11.1",
@@ -10912,8 +10848,7 @@ dependencies = [
 [[package]]
 name = "rustfs-uring"
 version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7deda770b7981ee3bfaa202ecd18625fc794c962b8d58cd4f436952b7e66dcf"
+source = "git+https://github.com/rustfs/uring.git?rev=eb8fc160e71d804427de1e905f5c226d580f71bf#eb8fc160e71d804427de1e905f5c226d580f71bf"
 dependencies = [
  "io-uring",
  "libc",
@@ -11202,7 +11137,7 @@ dependencies = [
  "numeric_cast",
  "phf 0.14.0",
  "pin-project-lite",
- "quick-xml 0.42.0",
+ "quick-xml",
  "regex",
  "s3s-multipart",
  "s3s-rfc2047",
@@ -12282,9 +12217,9 @@ dependencies = [
 
 [[package]]
 name = "sysinfo"
-version = "0.40.0"
+version = "0.40.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "110e37d98880fd804cd47509b90a8444f7aaaab655ae625e83cd442a8bc2ebf2"
+checksum = "0e8a3edbe0394ce115f3917a00349dd242be09eb5a091ed509eaf67b55cfb8a8"
 dependencies = [
  "libc",
  "memchr",
@@ -12775,9 +12710,9 @@ checksum = "06bdbd8cfc056b8d2e2e85f29b56a3bdbecb527cef81eb39e3e7b98af4652770"
 
 [[package]]
 name = "tonic"
-version = "0.14.8"
+version = "0.14.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd1fa9b1a51188f3266a823208078315811269d06d272c3a61be0b9a194194ff"
+checksum = "e2cdfc673aabd30fe8fee92e65837b644c37c5d47f0f97ae6d5e0f1237d15e1b"
 dependencies = [
  "async-trait",
  "axum",
@@ -12808,9 +12743,9 @@ dependencies = [
 
 [[package]]
 name = "tonic-build"
-version = "0.14.8"
+version = "0.14.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2c07bd4e9f99e2a3ed8bebad596ae02a94e53745b68acc6900e22c3475c8bc44"
+checksum = "ac6d916d206ed7bdda1778ddff9bda43303789c258877e7bc22fb44ee5c984b4"
 dependencies = [
  "prettyplease 0.2.37",
  "proc-macro2",
@@ -12820,9 +12755,9 @@ dependencies = [
 
 [[package]]
 name = "tonic-prost"
-version = "0.14.8"
+version = "0.14.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f63c616ffaa648f7c5dd5657e97d9a285fcb44ff3b70da761d436f5a13ff7be6"
+checksum = "eba464054e2226f182a34489b8b079bf4c6e3e7ab5fd7fc30e024f24aa92a484"
 dependencies = [
  "bytes",
  "prost 0.14.4",
@@ -12831,9 +12766,9 @@ dependencies = [
 
 [[package]]
 name = "tonic-prost-build"
-version = "0.14.8"
+version = "0.14.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4a05d8957fac6b3542999796cb4449d45da790751962f974a457e5e00c43d78c"
+checksum = "2ea216ddc448e08e7839ab09e20e60b06b6a1c32745ccb212c0ebd161c199f1b"
 dependencies = [
  "prettyplease 0.2.37",
  "proc-macro2",
@@ -13226,9 +13161,12 @@ checksum = "daf8dba3b7eb870caf1ddeed7bc9d2a049f3cfdfae7cb521b087cc33ae4c49da"
 
 [[package]]
 name = "utf8_iter"
-version = "1.0.4"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
+checksum = "af3bd9d3e571c26fcce9d033b87ea5ab061b8d2ffe9b7a5675d810d68f03edf0"
+dependencies = [
+ "utf_types",
+]
 
 [[package]]
 name = "utf8parse"
@@ -13236,6 +13174,12 @@ version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 
+[[package]]
+name = "utf_types"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a3b425286980a367278453f3b6d28cdcb134b574e5a35824a6ff5eebad50bb6"
+
 [[package]]
 name = "uuid"
 version = "1.29.0"
@@ -13350,12 +13294,11 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen"
-version = "0.2.129"
+version = "0.2.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9bb54f33acc68fd454578d9820b0bde1a1a3d17aa17bb7b6595806d02886d409"
+checksum = "a0181c14ddd6c7b8b0b0132a5f1ea2f32be0d893cd3ea97b6e3b28886b8a3d1c"
 dependencies = [
  "cfg-if",
- "once_cell",
  "rustversion",
  "wasm-bindgen-macro",
  "wasm-bindgen-shared",
@@ -13363,9 +13306,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-futures"
-version = "0.4.79"
+version = "0.4.80"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3cbab34de2d982e9b48e18d216d04c4a6f641066ff19ffb699980f591ee3610e"
+checksum = "5e14e0327cb5368ad60ccb22d04a9827a693c95a926d8d125e9fa39e0baec501"
 dependencies = [
  "js-sys",
  "tokio",
@@ -13374,9 +13317,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro"
-version = "0.2.129"
+version = "0.2.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e29d0c35b16e224a7eeb5cd2d25e3e1968fbd65604117b44d3b789d00ee8535"
+checksum = "6e931a02a39abdbf66966fc35902b5ed58344750a70885bed4ebb3d8eaf28ed9"
 dependencies = [
  "quote",
  "wasm-bindgen-macro-support",
@@ -13384,9 +13327,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-macro-support"
-version = "0.2.129"
+version = "0.2.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f501a8bc3719dba86ef8ae4728879c08001bea749eb1333ac5b91e040e2a6b7"
+checksum = "2ca4b54280e455bd831e33a6b8e734baf432fe63fbc35c42ac14ce67a043a53a"
 dependencies = [
  "bumpalo",
  "proc-macro2",
@@ -13397,9 +13340,9 @@ dependencies = [
 
 [[package]]
 name = "wasm-bindgen-shared"
-version = "0.2.129"
+version = "0.2.130"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23f0c9c52aa7cd7d77769a4cfe2a9adb1b331f489a41d912ce14513d5ab995c6"
+checksum = "3b1f9c3798725016c6ee5f2f57869ec0831e8bbc0ab0310a86e787e97f41389e"
 dependencies = [
  "unicode-ident",
 ]
@@ -13419,9 +13362,9 @@ dependencies = [
 
 [[package]]
 name = "web-sys"
-version = "0.3.106"
+version = "0.3.107"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88261b9deccee56594c11a3460c462c41f58d148598fe70ad77070126a68aba4"
+checksum = "d7d179596ff5ec0f6de4db64d54011bde6289cc49603d3a6e4ce3f329207ab88"
 dependencies = [
  "js-sys",
  "wasm-bindgen",

Cargo.toml

@@ -48,7 +48,7 @@ members = [
     "crates/replication", # Replication contracts and wire formats
     "crates/concurrency", # Concurrency management for RustFS - timeout, locking, backpressure, and I/O scheduling
     "crates/s3-client", # S3 client for engine-side consumption of remote S3 endpoints (tiering, transition targets)
-    "crates/s3-types", # S3 event and error type definitions
+    "crates/s3-types", # S3 event type definitions
     "crates/s3-ops", # S3 operation definitions and mapping
     "crates/s3select-api", # S3 Select API interface
     "crates/s3select-query", # S3 Select query engine
@@ -143,13 +143,6 @@ rustfs-tls-runtime = { path = "crates/tls-runtime", version = "1.0.2" }
 rustfs-utils = { path = "crates/utils", version = "1.0.2" }
 rustfs-zip = { path = "./crates/zip", version = "1.0.2" }
 
-# The gateway's S3 types: the DTOs and persisted bucket-configuration codecs the
-# engine crates move onto from s3s (rustfs/backlog#2745). The one pin of the
-# gateway in this workspace; no crate may enable a `compat-s3s*` feature except
-# the s3s-facing edge of the rustfs binary.
-rustfs-gateway-types = { git = "https://github.com/rustfs/gateway.git", rev = "21283e874c2381bab611e9347acbc5b92e9e2b3c", version = "0.32.0", default-features = false }
-rustfs-gateway-stream = { git = "https://github.com/rustfs/gateway.git", rev = "21283e874c2381bab611e9347acbc5b92e9e2b3c", version = "0.2.0", default-features = false }
-
 # Async Runtime and Networking
 async-channel = "2.5.0"
 async_zip = { default-features = false, version = "0.0.19" }
@@ -182,9 +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 = "0.14.8" }
-tonic-prost = { version = "0.14.8" }
-tonic-prost-build = { version = "0.14.8" }
+tonic = { version = "0.14.9" }
+tonic-prost = { version = "0.14.9" }
+tonic-prost-build = { version = "0.14.9" }
 tower = { version = "0.5.3" }
 tower-http = { version = "0.7.1" }
 h3 = "0.0.8"
@@ -326,17 +319,13 @@ 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 = "1.8.0" }
+redis = { version = "1.8.1" }
 rustify = { version = "0.7", default-features = false }
 rustix = { version = "1.1.6" }
 rust-embed = { version = "8.13.0" }
 rustc-hash = { version = "2.1.3" }
 s3s = { git = "https://github.com/s3s-project/s3s", rev = "5761ddfe4c509fcac87e3b99fd5bd9e176b442c0", features = ["minio"] }
 s3s-sigv4 = { git = "https://github.com/s3s-project/s3s", rev = "5761ddfe4c509fcac87e3b99fd5bd9e176b442c0" }
-# The same s3s pin under the name the legacy edge of the gateway migration uses
-# (crates/s3-types, feature `compat-s3s`). Keep `rev` identical to `s3s` above.
-# DELETE BY T4.2 (rustfs/backlog#2784).
-legacy-s3s = { package = "s3s", git = "https://github.com/s3s-project/s3s", rev = "5761ddfe4c509fcac87e3b99fd5bd9e176b442c0", features = ["minio"] }
 serial_test = "4.0.1"
 shadow-rs = { default-features = false, version = "2.0.0" }
 siphasher = "1.0.4"
@@ -345,8 +334,7 @@ compact_str = "0.10.0"
 snap = "1.1.2"
 starshard = { version = "2.4.0" }
 strum = { version = "0.28.0" }
-sync_wrapper = "1.0.2"
-sysinfo = "0.40.0"
+sysinfo = "0.40.1"
 temp-env = "0.3.6"
 tempfile = "3.27.0"
 test-case = "3.4.0"
@@ -398,7 +386,7 @@ dav-server = "0.11.0"
 # Performance Analysis and Memory Profiling
 rustfs-mimalloc = { version = "0.7.2" }
 # Preserve Unicode focus filters until rustfs/backlog#2302 is resolved.
-hotpath = { version = "0.30.1", default-features = false }
+hotpath = { version = "0.30.2", default-features = false }
 # Snapshot testing for output format regression detection
 insta = { version = "1.49" }
 

crates/concurrency/src/adaptive.rs

@@ -10,6 +10,10 @@ 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
@@ -36,6 +40,7 @@ pub struct AdaptiveAdmission {
     maximum: u32,
     slots: Box<[PermitSlots]>,
     next_chunk: AtomicUsize,
+    completed: AtomicU64,
 }
 
 struct PermitSlots {
@@ -61,10 +66,12 @@ pub struct AdaptivePermit {
 
 impl Clone for AdaptivePermit {
     fn clone(&self) -> Self {
-        // Every slot reference owns a strong owner reference. Clone the Arc
-        // first, so its overflow protection also bounds the slot refcount.
+        // Subset carriers can retain slot references through a shared owner,
+        // so the slot count needs its own bound in addition to Arc's guard.
         let owner = Arc::clone(&self.owner);
-        owner.slots[self.slot / 64].references[self.slot % 64].fetch_add(1, Ordering::Relaxed);
+        if owner.slots[self.slot / 64].references[self.slot % 64].fetch_add(1, Ordering::Relaxed) >= MAX_PERMIT_REFERENCES {
+            std::process::abort();
+        }
         Self { owner, slot: self.slot }
     }
 }
@@ -114,11 +121,22 @@ 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(&self.capacity, observation)
+        controller.update_with_probe(&self.capacity, observation, allow_probe)
     }
 
     /// Current leased scheduling cap and held async units.
@@ -249,16 +267,31 @@ 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(Instant::now(), observation);
+        let decision = self.decide_with_probe(Instant::now(), observation, allow_probe);
         gate.set_sampled_limit(decision.limit, Duration::from_secs(3));
         decision
     }
 
-    fn decide(&mut self, now: Instant, observation: Option<FeedbackObservation>) -> FeedbackDecision {
+    fn decide_with_probe(
+        &mut self,
+        now: Instant,
+        observation: Option<FeedbackObservation>,
+        allow_probe: bool,
+    ) -> FeedbackDecision {
         let Some(observation) = observation else {
             self.previous = None;
             self.stable_since = None;
@@ -303,7 +336,8 @@ impl FeedbackController {
             FeedbackReason::NewBaseline
         } else {
             let since = *self.stable_since.get_or_insert(now);
-            if advanced
+            if allow_probe
+                && 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
@@ -325,6 +359,13 @@ 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.
@@ -351,6 +392,7 @@ impl AdaptiveAdmission {
             maximum: maximum_u32,
             slots,
             next_chunk: AtomicUsize::new(0),
+            completed: AtomicU64::new(0),
         })
     }
 
@@ -466,6 +508,21 @@ 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.
@@ -493,13 +550,7 @@ impl AdaptiveAdmission {
 
 impl Drop for AdaptivePermit {
     fn drop(&mut self) {
-        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();
+        self.owner.release_reference(self.slot);
     }
 }
 
@@ -861,6 +912,24 @@ 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

@@ -30,6 +30,16 @@ 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).
@@ -328,5 +338,7 @@ 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

@@ -24,6 +24,14 @@ 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.
 ///
@@ -342,7 +350,7 @@ impl UnknownTierStats {
                     self.diagnostics_dropped = checked_saturating_add(1, self.diagnostics_dropped, &mut self.counter_overflowed);
                     continue;
                 }
-                self.diagnostics.push(diagnostic.clone());
+                self.diagnostics.push(clone_cache_value(diagnostic));
             }
         }
         if !self.diagnostics.is_empty() {
@@ -367,7 +375,7 @@ impl UnknownTierStats {
         if !self.fits_add(other) {
             return None;
         }
-        let mut merged = self.clone();
+        let mut merged = clone_cache_value(self);
         merged.merge(other);
         Some(merged)
     }
@@ -407,7 +415,7 @@ impl AllTierStats {
             if st.is_empty() {
                 continue;
             }
-            let entry = self.tiers.entry(tier.clone()).or_default();
+            let entry = self.tiers.entry(clone_cache_value(tier)).or_default();
             *entry = entry.add(st);
         }
     }
@@ -437,7 +445,7 @@ impl AllTierStats {
             .tiers
             .keys()
             .filter(|tier| tier.as_str() != "STANDARD" && tier.as_str() != "REDUCED_REDUNDANCY" && !known.contains(tier.as_str()))
-            .cloned()
+            .map(clone_cache_value)
             .collect();
         for tier in retired_tiers {
             if let Some(stats) = self.tiers.remove(&tier) {
@@ -1237,10 +1245,10 @@ impl DataUsageEntry {
     }
 
     pub fn add_child(&mut self, hash: &DataUsageHash) {
-        if self.children.contains(&hash.key()) {
+        if self.children.contains(&clone_cache_value(&hash.0)) {
             return;
         }
-        self.children.insert(hash.key());
+        self.children.insert(clone_cache_value(&hash.0));
     }
 
     pub fn merge(&mut self, other: &DataUsageEntry) {
@@ -1257,7 +1265,7 @@ 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(arn.clone()).or_default();
+                let st = s_rep.targets.entry(clone_cache_value(arn)).or_default();
                 st.pending_size += stat.pending_size;
                 st.replicated_size += stat.replicated_size;
                 st.failed_size += stat.failed_size;
@@ -1451,7 +1459,7 @@ pub fn prefix_usage_in_cache(
     } else {
         format!("{bucket}/{prefix}")
     };
-    let entry = cache.get(&hash_path(&root).key())?.clone();
+    let entry = clone_cache_value(cache.get(&clone_cache_value(&hash_path(&root).0))?);
 
     let usage = PrefixUsageSummary::from_entry(&flatten_entry(cache, &entry, 0)?);
 
@@ -1594,38 +1602,38 @@ pub struct DataUsageCache {
 impl DataUsageCache {
     pub fn replace(&mut self, path: &str, parent: &str, e: DataUsageEntry) {
         let hash = hash_path(path);
-        self.cache.insert(hash.key(), e);
+        self.cache.insert(clone_cache_value(&hash.0), e);
         if !parent.is_empty() {
             let phash = hash_path(parent);
             let p = {
-                let p = self.cache.entry(phash.key()).or_default();
+                let p = self.cache.entry(clone_cache_value(&phash.0)).or_default();
                 p.add_child(&hash);
-                p.clone()
+                clone_cache_value(p)
             };
-            self.cache.insert(phash.key(), p);
+            self.cache.insert(clone_cache_value(&phash.0), p);
         }
     }
 
     pub fn replace_hashed(&mut self, hash: &DataUsageHash, parent: &Option<DataUsageHash>, e: &DataUsageEntry) {
-        self.cache.insert(hash.key(), e.clone());
+        self.cache.insert(clone_cache_value(&hash.0), clone_cache_value(e));
         if let Some(parent) = parent {
-            self.cache.entry(parent.key()).or_default().add_child(hash);
+            self.cache.entry(clone_cache_value(&parent.0)).or_default().add_child(hash);
         }
     }
 
     pub fn find(&self, path: &str) -> Option<DataUsageEntry> {
-        self.cache.get(&hash_path(path).key()).cloned()
+        self.cache.get(&clone_cache_value(&hash_path(path).0)).map(clone_cache_value)
     }
 
     pub fn find_children_copy(&mut self, h: DataUsageHash) -> DataUsageHashMap {
-        self.cache.entry(h.string()).or_default().children.clone()
+        clone_cache_value(&self.cache.entry(clone_cache_value(&h.0)).or_default().children)
     }
 
     pub fn flatten(&self, root: &DataUsageEntry) -> DataUsageEntry {
-        let mut root = root.clone();
-        for id in root.children.clone().iter() {
+        let mut root = clone_cache_value(root);
+        for id in clone_cache_value(&root.children).iter() {
             if let Some(e) = self.cache.get(id) {
-                let mut e = e.clone();
+                let mut e = clone_cache_value(e);
                 if !e.children.is_empty() {
                     e = self.flatten(&e);
                 }
@@ -1637,16 +1645,16 @@ impl DataUsageCache {
     }
 
     pub fn copy_with_children(&mut self, src: &DataUsageCache, hash: &DataUsageHash, parent: &Option<DataUsageHash>) {
-        if let Some(e) = src.cache.get(&hash.string()) {
-            self.cache.insert(hash.key(), e.clone());
+        if let Some(e) = src.cache.get(&clone_cache_value(&hash.0)) {
+            self.cache.insert(clone_cache_value(&hash.0), clone_cache_value(e));
             for ch in e.children.iter() {
-                if *ch == hash.key() {
+                if *ch == clone_cache_value(&hash.0) {
                     return;
                 }
-                self.copy_with_children(src, &DataUsageHash(ch.to_string()), &Some(hash.clone()));
+                self.copy_with_children(src, &DataUsageHash(clone_cache_value(ch)), &Some(clone_cache_value(hash)));
             }
             if let Some(parent) = parent {
-                let p = self.cache.entry(parent.key()).or_default();
+                let p = self.cache.entry(clone_cache_value(&parent.0)).or_default();
                 p.add_child(hash);
             }
         }
@@ -1654,14 +1662,14 @@ impl DataUsageCache {
 
     pub fn delete_recursive(&mut self, hash: &DataUsageHash) {
         let mut need_remove = Vec::new();
-        if let Some(v) = self.cache.get(&hash.string()) {
+        if let Some(v) = self.cache.get(&clone_cache_value(&hash.0)) {
             for child in v.children.iter() {
-                need_remove.push(child.clone());
+                need_remove.push(clone_cache_value(child));
             }
         }
-        self.cache.remove(&hash.string());
+        self.cache.remove(&clone_cache_value(&hash.0));
         need_remove.iter().for_each(|child| {
-            self.delete_recursive(&DataUsageHash(child.to_string()));
+            self.delete_recursive(&DataUsageHash(clone_cache_value(child)));
         });
     }
 
@@ -1682,7 +1690,7 @@ impl DataUsageCache {
     }
 
     pub fn search_parent(&self, hash: &DataUsageHash) -> Option<DataUsageHash> {
-        let want = hash.key();
+        let want = clone_cache_value(&hash.0);
         if let Some(last_index) = want.rfind('/')
             && let Some(v) = self.find(&want[0..last_index])
             && v.children.contains(&want)
@@ -1693,7 +1701,7 @@ impl DataUsageCache {
 
         for (k, v) in self.cache.iter() {
             if v.children.contains(&want) {
-                let found = DataUsageHash(k.clone());
+                let found = DataUsageHash(clone_cache_value(k));
                 return Some(found);
             }
         }
@@ -1701,7 +1709,7 @@ impl DataUsageCache {
     }
 
     pub fn is_compacted(&self, hash: &DataUsageHash) -> bool {
-        match self.cache.get(&hash.key()) {
+        match self.cache.get(&clone_cache_value(&hash.0)) {
             Some(due) => due.compacted,
             None => false,
         }
@@ -1726,7 +1734,7 @@ impl DataUsageCache {
         if self.cache.len() < limit {
             return;
         }
-        let top = hash_path(&self.info.name).key();
+        let top = clone_cache_value(&hash_path(&self.info.name).0);
         let top_e = match self.find(&top) {
             Some(e) => e,
             None => return,
@@ -1753,7 +1761,7 @@ impl DataUsageCache {
     }
 
     pub fn reduce_children_of(&mut self, path: &DataUsageHash, limit: usize, compact_self: bool) {
-        let e = match self.cache.get(&path.key()) {
+        let e = match self.cache.get(&clone_cache_value(&path.0)) {
             Some(e) => e,
             None => return,
         };
@@ -1763,13 +1771,13 @@ impl DataUsageCache {
         }
 
         if e.children.len() > limit && compact_self {
-            let mut flat = self.size_recursive(&path.key()).unwrap_or_default();
+            let mut flat = self.size_recursive(&clone_cache_value(&path.0)).unwrap_or_default();
             flat.compacted = true;
             self.delete_recursive(path);
             self.replace_hashed(path, &None, &flat);
             return;
         }
-        let total = self.total_children_rec(&path.key());
+        let total = self.total_children_rec(&clone_cache_value(&path.0));
         if total < limit {
             return;
         }
@@ -1782,12 +1790,12 @@ impl DataUsageCache {
         let mut candidate_index = 0;
         while remove > 0 && candidate_index < candidates.len() {
             let e = &candidates[candidate_index];
-            let candidate = e.path.clone();
+            let candidate = clone_cache_value(&e.path);
             if candidate == *path && !compact_self {
                 break;
             }
-            let removing = self.total_children_rec(&candidate.key());
-            let mut flat = match self.size_recursive(&candidate.key()) {
+            let removing = self.total_children_rec(&clone_cache_value(&candidate.0));
+            let mut flat = match self.size_recursive(&clone_cache_value(&candidate.0)) {
                 Some(flat) => flat,
                 None => {
                     candidate_index += 1;
@@ -1824,7 +1832,7 @@ impl DataUsageCache {
             if o.root().is_none() {
                 return;
             }
-            *self = o.clone();
+            *self = clone_cache_value(o);
             return;
         };
 
@@ -1837,7 +1845,8 @@ impl DataUsageCache {
         }
 
         existing_root.merge(&other_root);
-        self.cache.insert(hash_path(&self.info.name).key(), existing_root);
+        self.cache
+            .insert(clone_cache_value(&hash_path(&self.info.name).0), existing_root);
 
         let root_hash = self.root_hash();
         for key in other_root.children.iter() {
@@ -1848,7 +1857,7 @@ impl DataUsageCache {
             if let Some(existing) = self.cache.get_mut(key) {
                 existing.merge(&flat);
             } else {
-                self.replace_hashed(&DataUsageHash(key.clone()), &Some(root_hash.clone()), &flat);
+                self.replace_hashed(&DataUsageHash(clone_cache_value(key)), &Some(clone_cache_value(&root_hash)), &flat);
             }
         }
     }
@@ -1892,7 +1901,7 @@ impl DataUsageCache {
 
                 for (arn, stat) in rs.targets.iter() {
                     bui.replication_info.insert(
-                        arn.clone(),
+                        clone_cache_value(arn),
                         BucketTargetUsageInfo {
                             replication_pending_size: stat.pending_size,
                             replicated_size: stat.replicated_size,
@@ -1905,7 +1914,7 @@ impl DataUsageCache {
                     );
                 }
             }
-            buckets_usage.insert(bucket_name.clone(), bui);
+            buckets_usage.insert(clone_cache_value(bucket_name), bui);
         }
 
         DataUsageInfo {
@@ -1937,20 +1946,20 @@ struct Inner {
 }
 
 fn add(data_usage_cache: &DataUsageCache, path: &DataUsageHash, candidates: &mut Vec<Inner>) -> usize {
-    let e = match data_usage_cache.cache.get(&path.key()) {
+    let e = match data_usage_cache.cache.get(&clone_cache_value(&path.0)) {
         Some(e) => e,
         None => return 0,
     };
     let mut objects = e.objects;
     for ch in e.children.iter() {
-        objects += add(data_usage_cache, &DataUsageHash(ch.clone()), candidates);
+        objects += add(data_usage_cache, &DataUsageHash(clone_cache_value(ch)), 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: path.clone(),
+            path: clone_cache_value(path),
         });
     }
     objects
@@ -1958,7 +1967,7 @@ 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(k.to_string());
+        found.insert(clone_cache_value(k));
         if let Some(ch) = duc.cache.get(k) {
             mark(duc, ch, found);
         }
@@ -2408,11 +2417,11 @@ impl SizeSummary {
         }
 
         for entry in &other.size_reconciliation {
-            self.record_size_reconciliation(entry.clone());
+            self.record_size_reconciliation(clone_cache_value(entry));
         }
         self.size_reconciliation_truncated |= other.size_reconciliation_truncated;
         for scope in &other.reconciliation_scopes {
-            self.record_reconciliation_scope(&scope.bucket, &scope.object);
+            self.record_reconciliation_scope_with(&scope.bucket, &scope.object, || clone_cache_value(scope));
         }
     }
 
@@ -2437,6 +2446,13 @@ 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()
@@ -2446,10 +2462,7 @@ impl SizeSummary {
                 self.size_reconciliation_truncated = true;
                 return;
             }
-            self.reconciliation_scopes.push(SizeReconciliationScope {
-                bucket: bucket.to_string(),
-                object: object.to_string(),
-            });
+            self.reconciliation_scopes.push(build());
         }
     }
 }
@@ -3404,6 +3417,42 @@ 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

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

crates/e2e_test/README.md

@@ -64,6 +64,25 @@ 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

crates/e2e_test/src/anonymous_access_test.rs

@@ -17,8 +17,7 @@
 //! when PublicAccessBlock configuration is missing or explicitly set.
 
 use crate::common::{RustFSTestEnvironment, init_logging, local_http_client};
-use crate::sts_query_compat_test::{OPA_AUTH_TOKEN, OpaMock};
-use aws_sdk_s3::types::{PublicAccessBlockConfiguration, Tag, Tagging};
+use aws_sdk_s3::types::PublicAccessBlockConfiguration;
 use tracing::info;
 
 async fn setup_public_bucket(
@@ -70,98 +69,6 @@ async fn anonymous_get_object(
     local_http_client().get(&url).send().await
 }
 
-#[tokio::test]
-async fn test_plain_http_matches_secure_transport_false_bucket_policy() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
-    init_logging();
-
-    let mut env = RustFSTestEnvironment::new().await?;
-    env.start_rustfs_server(vec![]).await?;
-    assert!(env.url.starts_with("http://"), "fixture must exercise plaintext HTTP: {}", env.url);
-
-    let bucket = "secure-transport-policy";
-    let key = "plain-http.txt";
-    let admin = env.create_s3_client();
-    admin.create_bucket().bucket(bucket).send().await?;
-    admin
-        .put_object()
-        .bucket(bucket)
-        .key(key)
-        .body(aws_sdk_s3::primitives::ByteStream::from_static(b"plain http"))
-        .send()
-        .await?;
-    admin
-        .put_bucket_policy()
-        .bucket(bucket)
-        .policy(
-            serde_json::json!({
-                "Version": "2012-10-17",
-                "Statement": [{
-                    "Effect": "Allow",
-                    "Principal": "*",
-                    "Action": "s3:GetObject",
-                    "Resource": format!("arn:aws:s3:::{bucket}/*"),
-                    "Condition": {"Bool": {"aws:SecureTransport": "false"}}
-                }]
-            })
-            .to_string(),
-        )
-        .send()
-        .await?;
-
-    let response = anonymous_get_object(&env, bucket, key).await?;
-    assert_eq!(response.status().as_u16(), 200);
-    assert_eq!(response.bytes().await?.as_ref(), b"plain http");
-    Ok(())
-}
-
-/// Root credentials have no attached IAM policy, so these requests depend on
-/// the owner flag reaching policy evaluation unchanged.
-#[tokio::test]
-async fn test_root_requests_keep_policy_owner_flag() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
-    init_logging();
-
-    let opa = OpaMock::start().await?;
-    let mut env = RustFSTestEnvironment::new().await?;
-    env.start_rustfs_server_with_env(
-        vec![],
-        &[
-            ("RUSTFS_POLICY_PLUGIN_URL", opa.url.as_str()),
-            ("RUSTFS_POLICY_PLUGIN_AUTH_TOKEN", OPA_AUTH_TOKEN),
-        ],
-    )
-    .await?;
-
-    let bucket = "root-owner-flag";
-    let key = "owner.txt";
-    let client = env.create_s3_client();
-    client.create_bucket().bucket(bucket).send().await?;
-    client
-        .put_object()
-        .bucket(bucket)
-        .key(key)
-        .body(aws_sdk_s3::primitives::ByteStream::from_static(b"owner access"))
-        .send()
-        .await?;
-
-    // Duplicate stored tags are ambiguous. An owner request must not enter the
-    // OPA tag-loading path, which rejects this metadata before evaluation.
-    client
-        .put_bucket_tagging()
-        .bucket(bucket)
-        .tagging(
-            Tagging::builder()
-                .tag_set(Tag::builder().key("department").value("finance").build()?)
-                .tag_set(Tag::builder().key("department").value("engineering").build()?)
-                .build()?,
-        )
-        .send()
-        .await?;
-    let object = client.get_object().bucket(bucket).key(key).send().await?;
-
-    assert_eq!(object.body.collect().await?.into_bytes().as_ref(), b"owner access");
-    Ok(())
-}
-
 /// Issue #2036: Anonymous GetObject should succeed when bucket policy allows it
 /// and no PublicAccessBlock configuration exists (ConfigNotFound).
 #[tokio::test]

crates/e2e_test/src/delete_marker_migration_semantics_test.rs

@@ -16,8 +16,193 @@
 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, VersioningConfiguration};
+    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");
+        }
+    }
 
     async fn create_versioned_bucket(client: &Client, bucket: &str) {
         client

crates/e2e_test/src/distributed/mod.rs

@@ -39,6 +39,8 @@ 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::RUSTFS_META_MULTIPART_BUCKET;
+use crate::storage_api::multipart_fence_acceptance::{LOCK_DIAGNOSTICS_FILTER, RUSTFS_META_MULTIPART_BUCKET};
 use aws_sdk_s3::{
     Client,
     config::retry::RetryConfig,
@@ -38,14 +38,16 @@ 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).await
+    fixture_from_binary(drives_per_node, storage_class, None, lock_diagnostics).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?;
@@ -90,6 +92,10 @@ 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 {
@@ -363,26 +369,120 @@ fn upload_path_scope(bucket: &str, key: &str, upload_id: &str) -> TestResult<Str
     ))
 }
 
-async fn with_paused_peers<T: Send + 'static>(
+async fn with_paused_peers<T, E>(
     proxies: &[RpcFaultProxy],
     methods: &[&'static str],
     limits: &[usize],
     scope: &str,
-    request: impl std::future::Future<Output = T> + Send + 'static,
-) -> TestResult<T> {
+    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;
     let pauses: Vec<_> = proxies[1..=limits.len()]
         .iter()
         .zip(limits)
         .map(|(proxy, limit)| proxy.pause(methods, *limit, Some(scope)))
         .collect::<Result<_, _>>()?;
-    let task = tokio::spawn(request);
-    wait_for_faults(&pauses, methods).await?;
-    let result = tokio::time::timeout(DEADLINE, task).await??;
+    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();
     for pause in &pauses {
         pause.discard_pending();
     }
     drop(pauses);
-    Ok(result)
+    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)),
+    }
 }
 
 fn quorum_outcome<T: std::fmt::Debug, E: std::fmt::Debug + ProvideErrorMetadata>(
@@ -1318,7 +1418,7 @@ 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").await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", true).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
@@ -1326,13 +1426,13 @@ 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").await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).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").await?;
+    let (cluster, proxies, clients, bucket) = fixture(4, "EC:4", false).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())?;
@@ -1346,7 +1446,7 @@ 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)).await?;
+    let (mut cluster, mut proxies, clients, bucket) = fixture_from_binary(4, "EC:4", Some(&previous), false).await?;
     assert!(
         proxies.is_empty(),
         "the genuine previous fleet boots and seeds through its normal direct transport"
@@ -1549,7 +1649,7 @@ 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").await?;
+    let (mut cluster, proxies, clients, bucket) = fixture(4, "EC:4", false).await?;
     let key = "partial-abort";
     let committed = payload_for("committed-before-abort", 4096);
     clients[0]
@@ -1765,7 +1865,7 @@ 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").await?;
+        let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).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")?;
@@ -1892,7 +1992,7 @@ 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").await?;
+            let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
             let key = "late-part-transaction";
             let previous = payload_for("committed-before-late-part", 4096);
             clients[0]
@@ -2075,7 +2175,7 @@ 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").await?;
+    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
     let pauses: Vec<_> = proxies[1..]
         .iter()
         .map(|proxy| proxy.pause(&["WriteMetadata"], usize::MAX, Some(&bucket)))
@@ -2098,7 +2198,7 @@ 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").await?;
+    let (cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
     for cancel_waiter in [false, true] {
         for complete in [false, true] {
             let key = format!("resend-{cancel_waiter}-{complete}");
@@ -2586,7 +2686,7 @@ 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").await?;
+    let (_cluster, proxies, clients, bucket) = fixture(1, "EC:2", false).await?;
     for locks in [false, true] {
         let key = format!("phase-{locks}");
         let client = clients[0].clone();

crates/e2e_test/src/dual_stack_differential/compare.rs

@@ -1,512 +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.
-
-//! What one stack answered, and how two answers are compared.
-//!
-//! An [`Observation`] keeps only what a client acts on: the HTTP status, the S3 error code, the
-//! allowlisted response headers and a few typed fields decoded from the response. The error
-//! message is kept for diagnostics and never compared: message wording is judged by the wire
-//! corpus, not here. The comparator is pure so it can be tested without a server.
-
-use serde::Serialize;
-use std::collections::{BTreeMap, BTreeSet};
-use std::path::{Path, PathBuf};
-
-/// Response headers compared exactly (after [`normalized_header_value`]).
-const HEADER_ALLOWLIST: [&str; 7] = [
-    "content-type",
-    "x-amz-version-id",
-    "etag",
-    "x-amz-delete-marker",
-    "content-range",
-    "accept-ranges",
-    "x-amz-request-charged",
-];
-
-/// Every response header with this prefix is compared as well.
-const HEADER_ALLOWLIST_PREFIX: &str = "x-amz-server-side-encryption";
-
-/// Placeholder for a field one side did not send.
-const ABSENT: &str = "<absent>";
-
-/// The lowercase header name if the comparator looks at this header.
-pub(crate) fn compared_header(name: &str) -> Option<String> {
-    let name = name.to_ascii_lowercase();
-    (HEADER_ALLOWLIST.contains(&name.as_str()) || name.starts_with(HEADER_ALLOWLIST_PREFIX)).then_some(name)
-}
-
-/// A version ID is minted per process, so its value never matches across two servers; only
-/// whether it is the literal `null` (an unversioned write) carries meaning.
-fn normalized_header_value(name: &str, value: &str) -> String {
-    if name == "x-amz-version-id" && value != "null" {
-        "<version-id>".to_owned()
-    } else {
-        value.to_owned()
-    }
-}
-
-/// One request's outcome as a client sees it.
-#[derive(Clone, Debug, Serialize)]
-pub(crate) struct Observation {
-    /// The S3 operation, named as in the `s3s::S3` trait (`GetObject`).
-    pub op: &'static str,
-    /// Which request of the script this was (`normal`, `negative`, or a setup label).
-    pub case: &'static str,
-    /// HTTP status; 0 when no response arrived.
-    pub status: u16,
-    /// The S3 error code, or the SDK's error kind when there was no service error.
-    pub error_code: Option<String>,
-    /// Allowlisted headers only, lowercase names, normalized values.
-    pub headers: BTreeMap<String, String>,
-    /// Typed values decoded from the response body, never free text.
-    pub fields: BTreeMap<String, String>,
-    /// Diagnostic only; never compared.
-    #[serde(skip)]
-    pub message: Option<String>,
-}
-
-impl Observation {
-    /// Builds an observation, keeping only the allowlisted headers.
-    pub(crate) fn new<'h>(
-        op: &'static str,
-        case: &'static str,
-        status: u16,
-        error_code: Option<String>,
-        headers: impl IntoIterator<Item = (&'h str, &'h str)>,
-    ) -> Self {
-        let headers = headers
-            .into_iter()
-            .filter_map(|(name, value)| compared_header(name).map(|name| (name, value)))
-            .map(|(name, value)| {
-                let value = normalized_header_value(&name, value);
-                (name, value)
-            })
-            .collect();
-        Self {
-            op,
-            case,
-            status,
-            error_code,
-            headers,
-            fields: BTreeMap::new(),
-            message: None,
-        }
-    }
-
-    pub(crate) fn with_field(mut self, name: &str, value: impl Into<String>) -> Self {
-        self.fields.insert(name.to_owned(), value.into());
-        self
-    }
-
-    pub(crate) fn is_success(&self) -> bool {
-        (200..300).contains(&self.status)
-    }
-}
-
-/// One field on which the two stacks answered differently.
-#[derive(Clone, Debug, PartialEq, Eq, Serialize)]
-pub(crate) struct Difference {
-    pub op: String,
-    pub case: String,
-    pub field: String,
-    pub a: String,
-    pub b: String,
-}
-
-/// Every difference between two transcripts of the same script, matched by `(op, case)`.
-pub(crate) fn compare(a: &[Observation], b: &[Observation]) -> Vec<Difference> {
-    let mut differences = Vec::new();
-    let (index_a, duplicates_a) = index(a);
-    let (index_b, duplicates_b) = index(b);
-    for (op, case) in duplicates_a.union(&duplicates_b) {
-        let count = |side: &[Observation]| {
-            side.iter()
-                .filter(|observation| (observation.op, observation.case) == (*op, *case))
-                .count()
-                .to_string()
-        };
-        differences.push(difference(op, case, "duplicate_case", count(a), count(b)));
-    }
-    let keys: BTreeSet<_> = index_a.keys().chain(index_b.keys()).copied().collect();
-    for key @ (op, case) in keys {
-        match (index_a.get(&key), index_b.get(&key)) {
-            (Some(a), Some(b)) => compare_one(a, b, &mut differences),
-            (a, b) => {
-                let presence = |side: Option<&&Observation>| if side.is_some() { "present" } else { ABSENT }.to_owned();
-                differences.push(difference(op, case, "observation", presence(a), presence(b)));
-            }
-        }
-    }
-    differences
-}
-
-type Key = (&'static str, &'static str);
-
-fn index(side: &[Observation]) -> (BTreeMap<Key, &Observation>, BTreeSet<Key>) {
-    let mut index = BTreeMap::new();
-    let mut duplicates = BTreeSet::new();
-    for observation in side {
-        let key = (observation.op, observation.case);
-        if index.insert(key, observation).is_some() {
-            duplicates.insert(key);
-        }
-    }
-    (index, duplicates)
-}
-
-fn difference(op: &str, case: &str, field: &str, a: String, b: String) -> Difference {
-    Difference {
-        op: op.to_owned(),
-        case: case.to_owned(),
-        field: field.to_owned(),
-        a,
-        b,
-    }
-}
-
-fn compare_one(a: &Observation, b: &Observation, differences: &mut Vec<Difference>) {
-    let mut field = |name: String, value_a: Option<&str>, value_b: Option<&str>| {
-        if value_a != value_b {
-            let show = |value: Option<&str>| value.unwrap_or(ABSENT).to_owned();
-            differences.push(difference(a.op, a.case, &name, show(value_a), show(value_b)));
-        }
-    };
-    field(
-        "status".to_owned(),
-        Some(a.status.to_string().as_str()),
-        Some(b.status.to_string().as_str()),
-    );
-    field("error_code".to_owned(), a.error_code.as_deref(), b.error_code.as_deref());
-    let headers: BTreeSet<_> = a.headers.keys().chain(b.headers.keys()).collect();
-    for name in headers {
-        field(
-            format!("header.{name}"),
-            a.headers.get(name).map(String::as_str),
-            b.headers.get(name).map(String::as_str),
-        );
-    }
-    let fields: BTreeSet<_> = a.fields.keys().chain(b.fields.keys()).collect();
-    for name in fields {
-        field(
-            format!("body.{name}"),
-            a.fields.get(name).map(String::as_str),
-            b.fields.get(name).map(String::as_str),
-        );
-    }
-}
-
-/// Operations observed on both sides.
-pub(crate) fn compared_ops(a: &[Observation], b: &[Observation]) -> BTreeSet<&'static str> {
-    let ops_b: BTreeSet<_> = b.iter().map(|observation| observation.op).collect();
-    a.iter()
-        .map(|observation| observation.op)
-        .filter(|op| ops_b.contains(op))
-        .collect()
-}
-
-/// `(op, case)` pairs observed on both sides.
-pub(crate) fn compared_cases(a: &[Observation], b: &[Observation]) -> usize {
-    let cases_b: BTreeSet<_> = b.iter().map(|observation| (observation.op, observation.case)).collect();
-    a.iter()
-        .map(|observation| (observation.op, observation.case))
-        .collect::<BTreeSet<_>>()
-        .intersection(&cases_b)
-        .count()
-}
-
-/// The JSON report written for every run.
-#[derive(Debug, Serialize)]
-pub(crate) struct Report {
-    pub schema: u32,
-    pub run: String,
-    pub stack_a: String,
-    pub stack_b: String,
-    pub region_a: Option<String>,
-    pub region_b: Option<String>,
-    pub compared_ops: usize,
-    pub compared_cases: usize,
-    pub differences: Vec<Difference>,
-}
-
-impl Report {
-    /// Writes the report as `<directory>/<run>.json` and returns its path.
-    pub(crate) fn write_to(&self, directory: &Path) -> std::io::Result<PathBuf> {
-        std::fs::create_dir_all(directory)?;
-        let path = directory.join(format!("{}.json", self.run));
-        let json = serde_json::to_vec_pretty(self).map_err(std::io::Error::other)?;
-        std::fs::write(&path, json)?;
-        Ok(path)
-    }
-}
-
-/// One line per difference, for a failing assertion.
-pub(crate) fn render(differences: &[Difference]) -> String {
-    differences
-        .iter()
-        .map(|d| format!("({}, {}, {}, a={:?}, b={:?})", d.op, d.case, d.field, d.a, d.b))
-        .collect::<Vec<_>>()
-        .join("\n")
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    fn ok(op: &'static str) -> Observation {
-        Observation::new(op, "normal", 200, None, [("content-type", "application/xml")])
-    }
-
-    fn fields(differences: &[Difference]) -> Vec<&str> {
-        differences.iter().map(|d| d.field.as_str()).collect()
-    }
-
-    #[test]
-    fn identical_transcripts_have_no_difference() {
-        let a = vec![
-            ok("HeadBucket"),
-            ok("GetBucketLocation").with_field("location_constraint", "us-east-1"),
-        ];
-        let b = a.clone();
-        assert_eq!(compare(&a, &b), Vec::new());
-        assert_eq!(compared_ops(&a, &b).len(), 2);
-    }
-
-    #[test]
-    fn a_status_difference_is_reported() {
-        let a = vec![ok("PutBucketAcl")];
-        let b = vec![Observation::new(
-            "PutBucketAcl",
-            "normal",
-            403,
-            None,
-            [("content-type", "application/xml")],
-        )];
-        assert_eq!(
-            compare(&a, &b),
-            vec![Difference {
-                op: "PutBucketAcl".into(),
-                case: "normal".into(),
-                field: "status".into(),
-                a: "200".into(),
-                b: "403".into(),
-            }]
-        );
-    }
-
-    #[test]
-    fn an_error_code_difference_is_reported() {
-        let a = vec![Observation::new("GetObject", "negative", 404, Some("NoSuchKey".into()), [])];
-        let b = vec![Observation::new(
-            "GetObject",
-            "negative",
-            404,
-            Some("NoSuchBucket".into()),
-            [],
-        )];
-        let differences = compare(&a, &b);
-        assert_eq!(fields(&differences), ["error_code"]);
-        assert_eq!((differences[0].a.as_str(), differences[0].b.as_str()), ("NoSuchKey", "NoSuchBucket"));
-    }
-
-    #[test]
-    fn an_error_code_on_one_side_only_is_reported() {
-        let a = vec![Observation::new("HeadBucket", "negative", 404, Some("NotFound".into()), [])];
-        let b = vec![Observation::new("HeadBucket", "negative", 404, None, [])];
-        let differences = compare(&a, &b);
-        assert_eq!(fields(&differences), ["error_code"]);
-        assert_eq!(differences[0].b, ABSENT);
-    }
-
-    #[test]
-    fn an_allowlisted_header_difference_is_reported() {
-        let a = vec![Observation::new("HeadObject", "normal", 200, None, [("ETag", "\"aa\"")])];
-        let b = vec![Observation::new("HeadObject", "normal", 200, None, [("etag", "\"bb\"")])];
-        assert_eq!(fields(&compare(&a, &b)), ["header.etag"]);
-    }
-
-    #[test]
-    fn a_header_sent_by_one_side_only_is_reported() {
-        let a = vec![Observation::new(
-            "DeleteObject",
-            "normal",
-            204,
-            None,
-            [("x-amz-delete-marker", "true")],
-        )];
-        let b = vec![Observation::new("DeleteObject", "normal", 204, None, [])];
-        let differences = compare(&a, &b);
-        assert_eq!(fields(&differences), ["header.x-amz-delete-marker"]);
-        assert_eq!((differences[0].a.as_str(), differences[0].b.as_str()), ("true", ABSENT));
-    }
-
-    #[test]
-    fn every_server_side_encryption_header_is_compared() {
-        let header = "x-amz-server-side-encryption-customer-key-md5";
-        let a = vec![Observation::new("PutObject", "sse-c", 200, None, [(header, "one")])];
-        let b = vec![Observation::new("PutObject", "sse-c", 200, None, [(header, "two")])];
-        assert_eq!(fields(&compare(&a, &b)), [format!("header.{header}")]);
-    }
-
-    #[test]
-    fn headers_outside_the_allowlist_are_not_compared() {
-        let a = vec![Observation::new(
-            "ListBuckets",
-            "normal",
-            200,
-            None,
-            [
-                ("date", "Mon"),
-                ("x-amz-request-id", "1"),
-                ("server", "a"),
-                ("content-length", "10"),
-            ],
-        )];
-        let b = vec![Observation::new(
-            "ListBuckets",
-            "normal",
-            200,
-            None,
-            [
-                ("date", "Tue"),
-                ("x-amz-request-id", "2"),
-                ("server", "b"),
-                ("content-length", "11"),
-            ],
-        )];
-        assert_eq!(compare(&a, &b), Vec::new());
-        assert!(a[0].headers.is_empty(), "non-allowlisted headers were kept: {:?}", a[0].headers);
-    }
-
-    #[test]
-    fn distinct_version_ids_are_not_a_difference() {
-        let a = vec![Observation::new(
-            "PutObject",
-            "normal",
-            200,
-            None,
-            [("x-amz-version-id", "0b1c")],
-        )];
-        let b = vec![Observation::new(
-            "PutObject",
-            "normal",
-            200,
-            None,
-            [("x-amz-version-id", "9f8e")],
-        )];
-        assert_eq!(compare(&a, &b), Vec::new());
-    }
-
-    #[test]
-    fn a_null_version_id_against_a_real_one_is_reported() {
-        let a = vec![Observation::new(
-            "PutObject",
-            "normal",
-            200,
-            None,
-            [("x-amz-version-id", "null")],
-        )];
-        let b = vec![Observation::new(
-            "PutObject",
-            "normal",
-            200,
-            None,
-            [("x-amz-version-id", "9f8e")],
-        )];
-        assert_eq!(fields(&compare(&a, &b)), ["header.x-amz-version-id"]);
-    }
-
-    #[test]
-    fn a_body_field_difference_is_reported() {
-        let a = vec![ok("GetBucketLocation").with_field("location_constraint", "us-east-1")];
-        let b = vec![ok("GetBucketLocation").with_field("location_constraint", "eu-west-1")];
-        let differences = compare(&a, &b);
-        assert_eq!(fields(&differences), ["body.location_constraint"]);
-        assert_eq!((differences[0].a.as_str(), differences[0].b.as_str()), ("us-east-1", "eu-west-1"));
-    }
-
-    #[test]
-    fn a_body_field_on_one_side_only_is_reported() {
-        let a = vec![ok("ListObjectsV2").with_field("keys", "[]")];
-        let b = vec![ok("ListObjectsV2")];
-        assert_eq!(fields(&compare(&a, &b)), ["body.keys"]);
-    }
-
-    #[test]
-    fn error_messages_are_never_compared() {
-        let mut a = Observation::new("GetObject", "negative", 404, Some("NoSuchKey".into()), []);
-        let mut b = a.clone();
-        a.message = Some("The specified key does not exist.".into());
-        b.message = Some("Object not found".into());
-        assert_eq!(compare(&[a], &[b]), Vec::new());
-    }
-
-    #[test]
-    fn a_case_observed_on_one_side_only_is_reported() {
-        let a = vec![ok("HeadBucket"), ok("ListBuckets")];
-        let b = vec![ok("HeadBucket")];
-        let differences = compare(&a, &b);
-        assert_eq!(fields(&differences), ["observation"]);
-        assert_eq!(differences[0].op, "ListBuckets");
-        assert_eq!(compared_ops(&a, &b).into_iter().collect::<Vec<_>>(), ["HeadBucket"]);
-    }
-
-    #[test]
-    fn a_case_recorded_twice_is_reported() {
-        let a = vec![ok("HeadBucket"), ok("HeadBucket")];
-        let b = vec![ok("HeadBucket")];
-        assert_eq!(fields(&compare(&a, &b)), ["duplicate_case"]);
-    }
-
-    #[test]
-    fn compared_ops_counts_operations_not_cases() {
-        let negative = Observation::new("HeadBucket", "negative", 404, Some("NotFound".into()), []);
-        let a = vec![ok("HeadBucket"), negative, ok("ListBuckets")];
-        let b = a.clone();
-        assert_eq!(compared_ops(&a, &b).len(), 2);
-    }
-
-    #[test]
-    fn the_report_lists_each_difference_as_op_field_a_b() {
-        let directory = std::env::temp_dir().join(format!("dual-stack-report-{}", uuid::Uuid::new_v4()));
-        let report = Report {
-            schema: 1,
-            run: "unit".into(),
-            stack_a: "legacy".into(),
-            stack_b: "legacy".into(),
-            region_a: None,
-            region_b: Some("eu-west-1".into()),
-            compared_ops: 1,
-            compared_cases: 1,
-            differences: compare(
-                &[ok("GetBucketLocation").with_field("location_constraint", "us-east-1")],
-                &[ok("GetBucketLocation").with_field("location_constraint", "eu-west-1")],
-            ),
-        };
-        let path = report.write_to(&directory).expect("write the report");
-        let json: serde_json::Value = serde_json::from_slice(&std::fs::read(&path).expect("read the report")).expect("parse");
-        let _ = std::fs::remove_dir_all(&directory);
-        assert_eq!(path.file_name().and_then(|name| name.to_str()), Some("unit.json"));
-        assert_eq!(json["compared_ops"], 1);
-        assert_eq!(
-            json["differences"],
-            serde_json::json!([{
-                "op": "GetBucketLocation",
-                "case": "normal",
-                "field": "body.location_constraint",
-                "a": "us-east-1",
-                "b": "eu-west-1",
-            }])
-        );
-    }
-}

crates/e2e_test/src/dual_stack_differential/mod.rs

@@ -1,199 +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.
-
-//! Dual-stack differential: one `rustfs` binary, two processes, one SDK script (rustfs/backlog#2740).
-//!
-//! Stack A always runs `RUSTFS_S3_STACK=legacy`. Stack B runs the value of `RUSTFS_E2E_STACK_B`
-//! (default `legacy` until the gateway stack is assembled), and `RUSTFS_E2E_STACK_B_REGION`, when
-//! set, starts B in another region so that a difference can be injected by hand. Both servers
-//! answer the script in `scenarios`, which covers every operation of `impl S3 for FS`; `compare`
-//! reports each `(op, field, a, b)` on which the answers differ, and every run writes its report
-//! to `<target>/dual-stack/<run>.json`. Two processes, not two embedded servers: bucket metadata
-//! is process-global, so two stacks in one process would read each other's buckets.
-
-mod compare;
-mod scenarios;
-
-use crate::common::{RustFSTestEnvironment, init_logging, workspace_root};
-use compare::{Difference, Observation, Report, compare, compared_cases, compared_ops, render};
-use std::path::PathBuf;
-use std::time::{SystemTime, UNIX_EPOCH};
-
-type BoxError = Box<dyn std::error::Error + Send + Sync>;
-
-const STACK_A: &str = "legacy";
-const ENV_STACK_B: &str = "RUSTFS_E2E_STACK_B";
-const ENV_STACK_B_REGION: &str = "RUSTFS_E2E_STACK_B_REGION";
-/// Becomes `gateway` once rustfs/backlog#2734 T2.5 assembles the gateway stack.
-const DEFAULT_STACK_B: &str = "legacy";
-/// The region the negative control gives stack A explicitly, so an inherited `RUSTFS_REGION`
-/// cannot erase the injected difference. Not `us-east-1`: that region answers GetBucketLocation
-/// with an empty LocationConstraint and re-creating an owned bucket with 200, so it would not
-/// report its own name and would add CreateBucket differences to the control.
-const CONTROL_REGION_A: &str = "us-west-2";
-const CONTROL_REGION_B: &str = "eu-west-1";
-/// `normal` cases the legacy stack must answer with a 2xx. The comparison alone cannot tell a
-/// script that exercises real behavior from one in which both stacks fail the same way. Five of
-/// the 73 fail on legacy by design of this script: PutBucketReplication (no registered remote
-/// target), GetBucketReplication (so no configuration), PutBucketNotificationConfiguration (no
-/// notification target configured), RestoreObject (the object is not archived) and
-/// GetObjectTorrent (legacy answers `NoSuchKey`).
-const MIN_NORMAL_SUCCESSES: usize = 68;
-
-struct PairConfig {
-    stack_b: String,
-    region_a: Option<String>,
-    region_b: Option<String>,
-}
-
-impl PairConfig {
-    fn from_env() -> Self {
-        Self {
-            stack_b: std::env::var(ENV_STACK_B).unwrap_or_else(|_| DEFAULT_STACK_B.to_owned()),
-            region_a: None,
-            region_b: std::env::var(ENV_STACK_B_REGION).ok(),
-        }
-    }
-}
-
-/// Starts one server on `stack`, overriding its region only when asked.
-async fn start_stack(stack: &str, region: Option<&str>) -> Result<RustFSTestEnvironment, BoxError> {
-    let mut env = RustFSTestEnvironment::new().await?;
-    let mut vars = vec![("RUSTFS_S3_STACK", stack)];
-    if let Some(region) = region {
-        vars.push(("RUSTFS_REGION", region));
-    }
-    env.start_rustfs_server_without_cleanup_with_env(&vars).await?;
-    Ok(env)
-}
-
-/// Starts stack A and stack B side by side, each with its own port and data directory.
-async fn spawn_pair(config: &PairConfig) -> Result<(RustFSTestEnvironment, RustFSTestEnvironment), BoxError> {
-    tokio::try_join!(
-        start_stack(STACK_A, config.region_a.as_deref()),
-        start_stack(&config.stack_b, config.region_b.as_deref())
-    )
-}
-
-fn report_directory() -> PathBuf {
-    let target = std::env::var_os("CARGO_TARGET_DIR").map_or_else(|| PathBuf::from("target"), PathBuf::from);
-    let target = if target.is_absolute() {
-        target
-    } else {
-        workspace_root().join(target)
-    };
-    target.join("dual-stack")
-}
-
-struct Run {
-    report: Report,
-    path: PathBuf,
-    a: Vec<Observation>,
-}
-
-/// Runs the script against both stacks concurrently and writes the report.
-async fn run_differential(label: &str, config: &PairConfig) -> Run {
-    let (server_a, server_b) = spawn_pair(config).await.expect("start stack A and stack B");
-    let (a, b) = tokio::join!(Box::pin(scenarios::run(&server_a)), Box::pin(scenarios::run(&server_b)));
-    let millis = SystemTime::now()
-        .duration_since(UNIX_EPOCH)
-        .map_or(0, |elapsed| elapsed.as_millis());
-    let report = Report {
-        schema: 1,
-        run: format!("{label}-{millis}-{}", std::process::id()),
-        stack_a: STACK_A.to_owned(),
-        stack_b: config.stack_b.clone(),
-        region_a: config.region_a.clone(),
-        region_b: config.region_b.clone(),
-        compared_ops: compared_ops(&a, &b).len(),
-        compared_cases: compared_cases(&a, &b),
-        differences: compare(&a, &b),
-    };
-    let path = report.write_to(&report_directory()).expect("write the dual-stack report");
-    Run { report, path, a }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[tokio::test]
-    async fn both_stacks_answer_every_operation_identically() {
-        init_logging();
-        let config = PairConfig::from_env();
-        let run = run_differential("self-comparison", &config).await;
-        let report = &run.report;
-
-        let mut observed: Vec<_> = run.a.iter().map(|observation| observation.op).collect();
-        observed.sort_unstable();
-        observed.dedup();
-        assert_eq!(
-            observed,
-            scenarios::OPERATIONS,
-            "the script must drive exactly the operations of impl S3 for FS"
-        );
-        assert_eq!(report.compared_ops, scenarios::OPERATIONS.len(), "report: {}", run.path.display());
-        assert!(
-            report.differences.is_empty(),
-            "stack {} and stack {} differ on {} of {} cases (report: {}):\n{}",
-            report.stack_a,
-            report.stack_b,
-            report.differences.len(),
-            report.compared_cases,
-            run.path.display(),
-            render(&report.differences)
-        );
-
-        let not_4xx: Vec<_> = run
-            .a
-            .iter()
-            .filter(|observation| observation.case == "negative" && !(400..500).contains(&observation.status))
-            .collect();
-        assert!(not_4xx.is_empty(), "negative cases must fail with a 4xx on {STACK_A}: {not_4xx:#?}");
-        let successes = run
-            .a
-            .iter()
-            .filter(|observation| observation.case == "normal" && observation.is_success())
-            .count();
-        assert!(
-            successes >= MIN_NORMAL_SUCCESSES,
-            "only {successes} normal cases succeeded on {STACK_A}: {:#?}",
-            run.a
-        );
-    }
-
-    #[tokio::test]
-    async fn differential_detects_an_injected_difference() {
-        init_logging();
-        let config = PairConfig {
-            stack_b: STACK_A.to_owned(),
-            region_a: Some(CONTROL_REGION_A.to_owned()),
-            region_b: Some(CONTROL_REGION_B.to_owned()),
-        };
-        let run = run_differential("injected-region", &config).await;
-        let expected = Difference {
-            op: "GetBucketLocation".to_owned(),
-            case: "normal".to_owned(),
-            field: "body.location_constraint".to_owned(),
-            a: CONTROL_REGION_A.to_owned(),
-            b: CONTROL_REGION_B.to_owned(),
-        };
-        assert!(
-            run.report.differences.contains(&expected),
-            "B started in {CONTROL_REGION_B} but GetBucketLocation was not reported (report: {}):\n{}",
-            run.path.display(),
-            render(&run.report.differences)
-        );
-    }
-}

crates/e2e_test/src/heal_erasure_disk_rebuild_test.rs

@@ -1700,6 +1700,15 @@ mod tests {
         );
 
         let mut cluster = RustFSTestClusterEnvironment::with_topology(topology.cluster_topology()).await?;
+        let bucket = "heal-restart-during-rebuild";
+        let mrf_fallback_scope = if !background_enabled {
+            let path = PathBuf::from(&cluster.temp_dir).join("skip-outage-mrf-fallback");
+            std::fs::write(&path, format!("{bucket}/cluster/written-while-node-down-"))?;
+            cluster.set_env("RUSTFS_E2E_SKIP_MRF_FALLBACK_PATH", path.to_string_lossy().into_owned());
+            Some(path)
+        } else {
+            None
+        };
         cluster.set_env("RUSTFS_UNSAFE_BYPASS_DISK_CHECK", "true");
         cluster.set_env("RUSTFS_HEAL_ENABLED", "true");
         if let Some(storage_class) = evidence_case.and_then(|case| case.storage_class_standard) {
@@ -1952,6 +1961,21 @@ mod tests {
             }
         };
 
+        if let Some(path) = &mrf_fallback_scope {
+            let observed = path.with_extension("observed");
+            let expected = format!("{bucket}/{outage_key}");
+            let deadline = Instant::now() + Duration::from_secs(30);
+            loop {
+                if tokio::fs::read_to_string(&observed).await.ok().as_deref() == Some(expected.as_str()) {
+                    break;
+                }
+                if Instant::now() >= deadline {
+                    return Err("outage repair did not reach the isolated best-effort fallback before target rejoin".into());
+                }
+                sleep(Duration::from_millis(50)).await;
+            }
+        }
+
         assert!(
             !outage_target_manifest_required
                 || target_set_peer_drives
@@ -2045,7 +2069,12 @@ mod tests {
             } else {
                 cluster_heal_is_idle(&recovered)
             };
-            if ready {
+            let pool_ready = if ready && background_enabled && !outage_write_deferred_until_rejoin {
+                all_nodes_pool_metadata_readiness(&cluster, recovery_deadline).await.0
+            } else {
+                true
+            };
+            if ready && pool_ready {
                 break;
             }
             if Instant::now() >= recovery_deadline {
@@ -2542,6 +2571,10 @@ mod tests {
             );
         }
 
+        if let Some(path) = &mrf_fallback_scope {
+            std::fs::remove_file(path)?;
+        }
+
         if let Some(cycle_end) = scanner_cycle_floor {
             wait_for_scanner_cycle_after(&cluster, cycle_end).await?;
         }

crates/e2e_test/src/lib.rs

@@ -31,12 +31,6 @@ pub mod chaos;
 #[cfg(test)]
 pub mod fake_s3_target;
 
-// Dual-stack differential (rustfs/backlog#2740): one binary, two processes on
-// different RUSTFS_S3_STACK values, the same SDK script for every S3 operation,
-// compared on status, error code, allowlisted headers and typed body fields.
-#[cfg(test)]
-mod dual_stack_differential;
-
 // On-demand migration (backlog#2147): shared two-server environment, admin
 // wrappers, and the harness self-test (backlog#2151). Behavior scenarios are
 // added by later ODM tasks.

crates/e2e_test/src/protocols/webdav_core.rs

@@ -32,9 +32,7 @@
 //! Advisory: <https://github.com/rustfs/rustfs/security/advisories/GHSA-3p3x-734c-h5vx>
 
 use crate::common::rustfs_binary_path_with_features;
-use crate::common::{
-    AdminTransport, admin_add_canned_policy_via, admin_attach_user_policy_via, admin_create_user_via, signed_s3_request,
-};
+use crate::common::{AdminTransport, admin_add_canned_policy_via, admin_attach_user_policy_via, admin_create_user_via};
 use crate::common::{FAST_DATA_USAGE_SCANNER_ENV, admin_request};
 use crate::protocols::test_env::{DEFAULT_ACCESS_KEY, DEFAULT_SECRET_KEY, ProtocolTestEnvironment};
 use anyhow::Result;
@@ -776,81 +774,6 @@ async fn test_webdav_core_operations_direct() -> Result<()> {
     test_webdav_core_operations().await
 }
 
-#[tokio::test]
-async fn test_webdav_content_type_directory_marker() -> Result<()> {
-    let env = ProtocolTestEnvironment::new().map_err(|e| anyhow::anyhow!("{}", e))?;
-    let admin_base_url = format!("http://{}", S3_TEST_ADDRESS);
-    let binary_path = rustfs_binary_path_with_features(Some("webdav"));
-    let mut server_process = Command::new(&binary_path)
-        .arg("--address")
-        .arg(S3_TEST_ADDRESS)
-        .env("RUSTFS_CONSOLE_ENABLE", "false")
-        .env("RUSTFS_WEBDAV_ENABLE", "true")
-        .env("RUSTFS_WEBDAV_ADDRESS", WEBDAV_ADDRESS)
-        .env("RUSTFS_WEBDAV_TLS_ENABLED", "false")
-        .arg(&env.temp_dir)
-        .spawn()?;
-
-    let result = async {
-        ProtocolTestEnvironment::wait_for_port_ready(WEBDAV_PORT, 30)
-            .await
-            .map_err(|e| anyhow::anyhow!("{}", e))?;
-
-        let client = create_client();
-        let bucket_name = "webdav-content-type-bucket";
-        let directory_name = "content-type-directory";
-        let webdav_base_url = format!("http://{}", WEBDAV_ADDRESS);
-        let mkcol_bucket = client
-            .request(
-                reqwest::Method::from_bytes(b"MKCOL").expect("MKCOL is a valid HTTP method"),
-                format!("{}/{}", webdav_base_url, bucket_name),
-            )
-            .header("Authorization", basic_auth_header())
-            .send()
-            .await?;
-        anyhow::ensure!(
-            mkcol_bucket.status().is_success() || mkcol_bucket.status().as_u16() == 201,
-            "MKCOL bucket should succeed, got: {}",
-            mkcol_bucket.status()
-        );
-
-        let mkcol_directory = client
-            .request(
-                reqwest::Method::from_bytes(b"MKCOL").expect("MKCOL is a valid HTTP method"),
-                format!("{}/{}/{}", webdav_base_url, bucket_name, directory_name),
-            )
-            .header("Authorization", basic_auth_header())
-            .send()
-            .await?;
-        anyhow::ensure!(
-            mkcol_directory.status().is_success() || mkcol_directory.status().as_u16() == 201,
-            "MKCOL directory should succeed, got: {}",
-            mkcol_directory.status()
-        );
-
-        let head_url = format!("{}/{}/{}/", admin_base_url, bucket_name, directory_name);
-        let head = signed_s3_request(http::Method::HEAD, &head_url, None, None, DEFAULT_ACCESS_KEY, DEFAULT_SECRET_KEY)
-            .await
-            .map_err(|error| anyhow::anyhow!("{error}"))?;
-        anyhow::ensure!(head.status().is_success(), "HEAD directory marker should succeed, got: {}", head.status());
-        let content_type = head
-            .headers()
-            .get("content-type")
-            .and_then(|value| value.to_str().ok())
-            .unwrap_or_default();
-        anyhow::ensure!(
-            content_type == "application/x-directory",
-            "WebDAV directory marker must preserve its content type, got: {content_type}"
-        );
-        Ok(())
-    }
-    .await;
-
-    let _ = server_process.kill().await;
-    let _ = server_process.wait().await;
-    result
-}
-
 /// Extract the numeric value of the first occurrence of a DAV property in a
 /// PROPFIND multistatus body. Namespace-prefix agnostic; a self-closing
 /// (unreported) property yields None.

crates/e2e_test/src/rpc_fault_proxy.rs

@@ -28,7 +28,8 @@ use hyper_util::{
 use prost::Message as _;
 use rustfs_protos::proto_gen::node_service::{
     BatchGenerallyLockRequest, DeleteRequest, GenerallyLockRequest, PreparePartTransactionResponse, ReadVersionRequest,
-    RecoverMultipartSourceRequest, RenameDataResponse, SettlePartTransactionRequest, SettlePartTransactionResponse,
+    RecoverMultipartSourceRequest, RenameDataResponse, ScannerScopedDirtyUsageAckRequest, SettlePartTransactionRequest,
+    SettlePartTransactionResponse,
 };
 use std::{
     collections::HashSet,
@@ -49,6 +50,9 @@ 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,
@@ -121,7 +125,8 @@ impl RpcPause {
         self.state.blocked.load(Ordering::SeqCst)
     }
 
-    /// Selected RPCs with successful HTTP/gRPC headers, excluding discarded packets.
+    /// Selected RPCs with successful HTTP/gRPC response headers, excluding
+    /// discarded packets. This does not prove a successful gRPC trailer or ACK apply.
     pub(crate) fn forwarded(&self) -> usize {
         self.state.forwarded.load(Ordering::SeqCst)
     }
@@ -233,6 +238,7 @@ pub(crate) struct RpcFaultProxy {
     address: SocketAddr,
     slot: PauseSlot,
     lock_slot: PauseSlot,
+    scoped_ack: scoped_ack::QueueSlot,
     task: JoinHandle<()>,
     late_requests: LateRequests,
 }
@@ -245,6 +251,8 @@ 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 {
@@ -259,6 +267,7 @@ 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>| {
@@ -272,6 +281,7 @@ 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/")
@@ -280,11 +290,11 @@ impl RpcFaultProxy {
                                 let late = late.clone();
                                 async move {
                                     if !retain {
-                                        return forward_request(request, client, target, pause).await;
+                                        return forward_request(request, client, target, pause, ack).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));
+                                    let task = tokio::spawn(forward_request(request, client, target, pause, ack));
                                     {
                                         let mut requests = late.lock().expect("late RPC ownership");
                                         if let Some(requests) = requests.as_mut() {
@@ -309,6 +319,7 @@ impl RpcFaultProxy {
             address,
             slot,
             lock_slot,
+            scoped_ack,
             task,
             late_requests,
         })
@@ -318,6 +329,11 @@ 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> {
@@ -469,6 +485,9 @@ 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 {
@@ -525,7 +544,9 @@ 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))
@@ -540,18 +561,39 @@ 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 (mut parts, body) = request.into_parts();
-    let mut body = body.map_err(io::Error::other).boxed();
+    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 observed = None;
     let mut inspection = None;
     if let Some(pause) = pause {
-        let method = parts.uri.path().strip_prefix("/node_service.NodeService/");
+        let method = parts
+            .uri
+            .path()
+            .strip_prefix("/node_service.NodeService/")
+            .or_else(|| parts.uri.path().strip_prefix("/node_service.ScannerControlService/"));
         if let Some(method) = method.filter(|name| pause.methods.contains(name)) {
             let mut route = None;
             let mut lock_owners = Vec::new();
@@ -599,6 +641,16 @@ 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
             };
@@ -642,24 +694,7 @@ async fn forward_request(
             }
         }
     }
-    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)?;
+    let response = forward_to_backend(Request::from_parts(parts, body), client, target).await?;
     if let Some((pause, disk)) = inspection
         && response.status().is_success()
         && response.headers().get("grpc-status").is_some_and(|status| status == "12")
@@ -712,6 +747,32 @@ 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() {
@@ -731,6 +792,7 @@ mod tests {
 
     struct Backend {
         received: Arc<AtomicUsize>,
+        auth_headers: Arc<Mutex<Vec<(String, String)>>>,
         address: SocketAddr,
         task: JoinHandle<()>,
     }
@@ -754,6 +816,8 @@ 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 {
@@ -761,10 +825,12 @@ 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);
@@ -773,6 +839,10 @@ 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();
@@ -795,7 +865,12 @@ mod tests {
                 }
             }
         });
-        Ok(Backend { received, address, task })
+        Ok(Backend {
+            received,
+            auth_headers,
+            address,
+            task,
+        })
     }
 
     async fn call(client: &ProxyClient, address: SocketAddr, method: &str) -> io::Result<hyper::Response<Incoming>> {
@@ -809,9 +884,14 @@ 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.NodeService/{method}"))
+            .uri(format!("http://{address}/node_service.{service}/{method}"))
             .header(http::header::TE, "trailers")
             .body(body)
             .map_err(io::Error::other)?;
@@ -826,6 +906,353 @@ 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,
@@ -1719,3 +2146,4 @@ mod tests {
         );
     }
 }
+// event-drill: isolated harness-only change

crates/e2e_test/src/rpc_fault_proxy/scoped_ack.rs

@@ -0,0 +1,404 @@
+// 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

@@ -70,6 +70,9 @@ 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)]
@@ -80,3 +83,14 @@ 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

@@ -1112,8 +1112,9 @@ 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)
-                        || error.as_service_error().and_then(ProvideErrorMetadata::code) != Some("ServiceUnavailable")
+                        || !matches!(code, Some("ServiceUnavailable" | "SlowDown" | "SlowDownRead"))
                     {
                         return Err(format!("{phase}: node {node} {probe} failed: {error:?}").into());
                     }

crates/ecstore/Cargo.toml

@@ -139,7 +139,6 @@ rustfs-lifecycle.workspace = true
 rustfs-s3-client = { workspace = true }
 rustfs-s3-types = { workspace = true }
 rustfs-data-usage.workspace = true
-rustfs-gateway-types.workspace = true
 rustfs-object-capacity.workspace = true
 rustfs-object-data-cache = { workspace = true, features = ["runtime-memory"] }
 arc-swap.workspace = true
@@ -158,6 +157,7 @@ serde = { workspace = true, features = ["derive"] }
 time = { workspace = true, features = ["parsing", "formatting", "macros", "serde"] }
 bytesize.workspace = true
 serde_json = { workspace = true, features = ["raw_value"] }
+s3s = { workspace = true, features = ["minio"] }
 http.workspace = true
 opentelemetry.workspace = true
 http-body = { workspace = true }
@@ -225,9 +225,11 @@ 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]
-# 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"
+# 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"] }
 
 [target.'cfg(windows)'.dependencies]
 winapi-util.workspace = true
@@ -246,7 +248,6 @@ windows-sys = { workspace = true, features = [
 windows-sys = { workspace = true, features = ["Win32_System_Ioctl"] }
 
 [dev-dependencies]
-s3s = { workspace = true, features = ["minio"] }
 aws-smithy-async.workspace = true
 rustfs-s3-ops.workspace = true
 tokio = { workspace = true, features = ["rt-multi-thread", "macros", "test-util", "fs"] }

crates/ecstore/src/api/mod.rs

@@ -66,8 +66,6 @@ pub mod bucket {
         }
 
         pub mod bucket_lifecycle_ops {
-            pub use rustfs_lifecycle::{RestoreOutputLocation, RestoreRequest, RestoreS3Location, RestoreTag, RestoreTagging};
-
             pub use crate::bucket::lifecycle::bucket_lifecycle_ops::{
                 ExpiryState, LifecycleOps, ManualTransitionCancelCheck, ManualTransitionProgressSink,
                 ManualTransitionQueueSnapshot, ManualTransitionRunExecution, ManualTransitionRunOptions,
@@ -139,7 +137,7 @@ pub mod bucket {
             pub use crate::bucket::lifecycle::lifecycle::{
                 Event, ExpirationOptions, IlmAction, LIFECYCLE_MALFORMED_XML_ERROR_KIND, Lifecycle, LifecycleCalculate,
                 ObjectOpts, RuleValidate, TRANSITION_COMPLETE, TRANSITION_PENDING, TransitionOptions, expected_expiry_time,
-                format_lifecycle_date, object_opts_from_object_info, parse_lifecycle_date,
+                object_opts_from_object_info,
             };
         }
 
@@ -237,7 +235,7 @@ pub mod bucket {
     }
 
     pub mod object_lock {
-        pub use crate::bucket::object_lock::ObjectLockApi;
+        pub use crate::bucket::object_lock::{ObjectLockApi, ObjectLockStatusExt};
 
         pub mod types {
             pub use crate::bucket::object_lock::types::{
@@ -332,9 +330,9 @@ pub mod bucket {
 
     pub mod utils {
         pub use crate::bucket::utils::{
-            BucketConfigXml, BucketConfigXmlError, check_bucket_and_object_names, check_list_objs_args,
-            check_object_name_for_length_and_slash, check_valid_bucket_name_strict, deserialize, has_bad_path_component,
-            is_meta_bucketname, is_valid_object_prefix, serialize,
+            check_bucket_and_object_names, check_list_objs_args, check_object_name_for_length_and_slash,
+            check_valid_bucket_name_strict, deserialize, has_bad_path_component, is_meta_bucketname, is_valid_object_prefix,
+            serialize,
         };
     }
 
@@ -361,7 +359,7 @@ pub mod capacity {
 }
 
 pub mod object_api_utils {
-    pub use crate::object_api::object_api_utils::{ObjReaderFn, PutObjReader, get_raw_etag, new_getobjectreader};
+    pub use crate::object_api::object_api_utils::{ObjReaderFn, PutObjReader, get_raw_etag, new_getobjectreader, to_s3s_etag};
 }
 
 pub mod cluster {
@@ -449,6 +447,9 @@ 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")]
@@ -477,6 +478,10 @@ 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;
@@ -617,6 +622,7 @@ 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,
@@ -626,8 +632,8 @@ 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, 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, rpc_background_admission,
+        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,
@@ -677,8 +683,9 @@ 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, 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, 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,
     };
     pub use crate::store::{HealObjectAbsenceProof, HealObjectStorageResult};
 }

crates/ecstore/src/bucket/lifecycle/bucket_lifecycle_ops.rs

@@ -88,14 +88,12 @@ use rustfs_filemeta::{
     FileInfo, FileInfoOpts, NULL_VERSION_ID, RestoreStatus, RestoreStatusOps, TRANSITION_COMPLETE, get_file_info,
     is_restored_object_on_disk,
 };
-use rustfs_gateway_types::persistence::PersistedObjectLockConfiguration as ObjectLockConfiguration;
-use rustfs_gateway_types::persistence::{PersistedLifecycleConfiguration, PersistedLifecycleFilter};
-use rustfs_lifecycle::{RestoreRequest, RestoreS3Location};
 use rustfs_lock::{NamespaceLockGuard, error::LockError};
 use rustfs_scanner_metrics::metrics::{
     IlmAction, Metrics, ScannerLifecycleExpiryStateUpdate, ScannerLifecycleTransitionStateUpdate, global_metrics,
 };
 use rustfs_utils::{get_env_i64, get_env_usize, path::encode_dir_object, string::parse_bool};
+use s3s::dto::{BucketLifecycleConfiguration, ExpirationStatus, ObjectLockConfiguration, RestoreRequest, RestoreRequestType};
 use sha2::{Digest, Sha256};
 use std::any::Any;
 use std::collections::{BTreeMap, HashMap, HashSet};
@@ -302,7 +300,7 @@ impl LifecycleSys {
         Arc::new(Self)
     }
 
-    pub async fn get(&self, bucket: &str) -> Option<PersistedLifecycleConfiguration> {
+    pub async fn get(&self, bucket: &str) -> Option<BucketLifecycleConfiguration> {
         match metadata_boundary::get_lifecycle_config(bucket).await {
             Ok((lc, _)) => Some(lc),
             Err(Error::ConfigNotFound) => None,
@@ -3559,7 +3557,7 @@ async fn stale_upload_lifecycle_due(
         Err(_) => return None,
     };
 
-    let has_size_filter = |filter: &PersistedLifecycleFilter| {
+    let has_size_filter = |filter: &s3s::dto::LifecycleRuleFilter| {
         filter.object_size_greater_than.is_some()
             || filter.object_size_less_than.is_some()
             || filter
@@ -3568,7 +3566,7 @@ async fn stale_upload_lifecycle_due(
                 .is_some_and(|and| and.object_size_greater_than.is_some() || and.object_size_less_than.is_some())
     };
     let needs_size = lifecycle.rules.iter().any(|rule| {
-        rule.status.as_str() != "Disabled"
+        rule.status.as_str() != ExpirationStatus::DISABLED
             && rule.abort_incomplete_multipart_upload.is_some()
             && rule.filter.as_ref().is_some_and(has_size_filter)
     });
@@ -4002,7 +4000,7 @@ pub fn init_background_stale_multipart_upload_cleanup(api: Arc<ECStore>) {
     });
 }
 
-pub async fn validate_transition_tier(lc: &PersistedLifecycleConfiguration) -> Result<(), std::io::Error> {
+pub async fn validate_transition_tier(lc: &BucketLifecycleConfiguration) -> Result<(), std::io::Error> {
     for rule in &lc.rules {
         if let Some(transitions) = &rule.transitions {
             for transition in transitions {
@@ -4119,9 +4117,8 @@ pub(crate) async fn enqueue_immediate_expiry(api: Arc<ECStore>, oi: &ObjectInfo,
         .map(lifecycle::object_opts_from_object_info)
         .collect::<Vec<ObjectOpts>>();
     let lock_config = configs.object_lock;
-    let evaluator_lock_config = lock_config.clone();
     let events = match Evaluator::new(lifecycle)
-        .with_lock_retention(evaluator_lock_config)
+        .with_lock_retention(lock_config.clone())
         .eval(&object_opts)
         .await
     {
@@ -4601,26 +4598,19 @@ pub async fn enqueue_transition_for_existing_objects_scoped(
     }
 }
 
-fn lifecycle_rule_has_date_expiration(lc: &PersistedLifecycleConfiguration, rule_id: &str) -> bool {
+fn lifecycle_rule_has_date_expiration(lc: &BucketLifecycleConfiguration, rule_id: &str) -> bool {
     lc.rules.iter().any(|rule| {
-        rule.status == "Enabled"
+        rule.status == ExpirationStatus::from_static(ExpirationStatus::ENABLED)
             && rule.id.as_deref() == Some(rule_id)
             && rule.expiration.as_ref().is_some_and(|expiration| expiration.date.is_some())
     })
 }
 
-fn should_defer_date_expiry_for_recent_config_update(lc: &PersistedLifecycleConfiguration, now: OffsetDateTime) -> bool {
-    lc.expiry_updated_at
-        .as_ref()
-        .is_some_and(|updated_at| match rustfs_lifecycle::parse_lifecycle_date(updated_at) {
-            Ok(updated_at) => {
-                now.unix_timestamp().saturating_sub(updated_at.unix_timestamp()) < DATE_EXPIRY_EXISTING_OBJECTS_GRACE_SECS
-            }
-            Err(error) => {
-                warn!(error = %error, "Deferring date expiry with an unreadable update timestamp");
-                true
-            }
-        })
+fn should_defer_date_expiry_for_recent_config_update(lc: &BucketLifecycleConfiguration, now: OffsetDateTime) -> bool {
+    lc.expiry_updated_at.as_ref().is_some_and(|updated_at| {
+        let updated_at = OffsetDateTime::from(updated_at.clone());
+        now.unix_timestamp().saturating_sub(updated_at.unix_timestamp()) < DATE_EXPIRY_EXISTING_OBJECTS_GRACE_SECS
+    })
 }
 
 async fn apply_existing_object_expiry(
@@ -4640,7 +4630,7 @@ async fn apply_existing_object_expiry(
 struct ExistingObjectExpiryContext<'a> {
     api: Arc<ECStore>,
     bucket: &'a str,
-    lc: Arc<PersistedLifecycleConfiguration>,
+    lc: Arc<BucketLifecycleConfiguration>,
     lock_config: Option<Arc<ObjectLockConfiguration>>,
     bucket_incarnation_id: Uuid,
     src: &'a LcEventSrc,
@@ -4660,9 +4650,8 @@ async fn enqueue_expiry_for_existing_object_group(
         .iter()
         .map(lifecycle::object_opts_from_object_info)
         .collect::<Vec<ObjectOpts>>();
-    let evaluator_lock_config = context.lock_config.clone();
     let events = match Evaluator::new(context.lc.clone())
-        .with_lock_retention(evaluator_lock_config)
+        .with_lock_retention(context.lock_config.clone())
         .eval(&object_opts)
         .await
     {
@@ -4856,7 +4845,7 @@ fn manual_transition_version_marker(oi: &ObjectInfo) -> String {
 async fn enqueue_transition_with_lifecycle_report(
     api: Option<Arc<ECStore>>,
     oi: &ObjectInfo,
-    lc: &PersistedLifecycleConfiguration,
+    lc: &BucketLifecycleConfiguration,
     src: &LcEventSrc,
     options: &ManualTransitionRunOptions,
     report: &mut ManualTransitionRunReport,
@@ -4922,7 +4911,7 @@ async fn enqueue_transition_with_lifecycle_report(
     false
 }
 
-async fn enqueue_transition_with_lifecycle(oi: &ObjectInfo, lc: &PersistedLifecycleConfiguration, src: &LcEventSrc) -> bool {
+async fn enqueue_transition_with_lifecycle(oi: &ObjectInfo, lc: &BucketLifecycleConfiguration, src: &LcEventSrc) -> bool {
     let event = lc.eval(&oi.to_lifecycle_opts()).await;
     match event.action {
         IlmAction::TransitionAction | IlmAction::TransitionVersionAction => {
@@ -5436,8 +5425,12 @@ pub async fn post_restore_opts(version_id: &str, bucket: &str, object: &str) ->
     })
 }
 
-fn select_restore_s3_location(rreq: &RestoreRequest) -> Result<Option<&RestoreS3Location>, std::io::Error> {
-    if rreq.type_.as_ref().is_none_or(|type_| type_.as_str() != "SELECT") {
+fn select_restore_s3_location(rreq: &RestoreRequest) -> Result<Option<&s3s::dto::S3Location>, std::io::Error> {
+    if rreq
+        .type_
+        .as_ref()
+        .is_none_or(|type_| type_.as_str() != RestoreRequestType::SELECT)
+    {
         return Ok(None);
     }
     let output_location = rreq
@@ -5479,25 +5472,27 @@ pub async fn put_restore_opts(
     // the OutputLocation metadata instead of a write to `OutputLocation.S3`
     // (backlog#1341). RestoreObject rejects SELECT at the API boundary; this
     // is the fail-closed backstop for any other caller.
-    if rreq.type_.as_ref().is_some_and(|type_| type_.as_str() == "SELECT") {
+    if rreq
+        .type_
+        .as_ref()
+        .is_some_and(|type_| type_.as_str() == RestoreRequestType::SELECT)
+    {
         return Err(std::io::Error::other("SELECT restore requests are not supported"));
     }
     for (k, v) in oi.user_defined.iter() {
         meta.insert(k.to_string(), v.clone());
     }
-    // The fleet capability gate guarantees physical copy-back support. Keep
-    // the completed transition identity for orphan recovery and remote cleanup.
     rustfs_utils::http::metadata_compat::remove_str(&mut meta, rustfs_utils::http::metadata_compat::SUFFIX_RESTORE_OPERATION_ID);
+    rustfs_utils::http::metadata_compat::remove_str(&mut meta, rustfs_utils::http::metadata_compat::SUFFIX_RESTORE_WORKER_LOCK);
     if !oi.user_tags.is_empty() {
         meta.insert(AMZ_OBJECT_TAGGING.to_string(), (*oi.user_tags).clone());
     }
-    // Finalization publishes completion and its expiry under the object lock.
-    // The local copy-back commit must not make unfinished work eligible for expiry.
+    let restore_expiry = lifecycle::expected_expiry_time(OffsetDateTime::now_utc(), rreq.days.unwrap_or(1));
     meta.insert(
         metadata_keys::RESTORE.to_string(),
         RestoreStatus {
-            is_restore_in_progress: Some(true),
-            restore_expiry_date: None,
+            is_restore_in_progress: Some(false),
+            restore_expiry_date: Some(restore_expiry),
         }
         .to_string(),
     );
@@ -5511,7 +5506,6 @@ pub async fn put_restore_opts(
         // computed MD5 is not the object's public plaintext ETag.
         preserve_etag: oi.etag.clone(),
         shard_integrity_write_mode: Some(oi.shard_integrity_write_mode()),
-        restore_copyback: true,
         //expires:           oi.expires,
         ..Default::default()
     })
@@ -5531,18 +5525,6 @@ impl LifecycleOps for ObjectInfo {
         if self.transitioned_object.status != lifecycle::TRANSITION_COMPLETE {
             return false;
         }
-        if rustfs_utils::http::metadata_compat::get_consistent_str(
-            &self.user_defined,
-            rustfs_utils::http::metadata_compat::SUFFIX_RESTORE_COPYBACK,
-        ) == Some(rustfs_utils::http::metadata_compat::RESTORE_COPYBACK_PROTOCOL_V1)
-            && self
-                .user_defined
-                .get(metadata_keys::RESTORE)
-                .and_then(|value| rustfs_filemeta::parse_restore_obj_status(value).ok())
-                .is_some_and(|status| status.is_restore_in_progress == Some(true))
-        {
-            return false;
-        }
         !is_restored_object_on_disk(&self.user_defined)
     }
 }
@@ -5554,25 +5536,25 @@ pub trait RestoreRequestOps {
 impl RestoreRequestOps for RestoreRequest {
     fn validate(&self, _api: Arc<ECStore>) -> Result<(), std::io::Error> {
         // SELECT type requires select_parameters, and vice versa
-        if self.type_.as_ref().is_none_or(|t| t.as_str() != "SELECT") && self.select_parameters.is_some() {
+        if self.type_.as_ref().is_none_or(|t| t.as_str() != RestoreRequestType::SELECT) && self.select_parameters.is_some() {
             return Err(std::io::Error::other("Select parameters can only be specified with SELECT request type"));
         }
         if let Some(type_) = &self.type_
-            && type_.as_str() == "SELECT"
+            && type_.as_str() == RestoreRequestType::SELECT
             && self.select_parameters.is_none()
         {
             return Err(std::io::Error::other("SELECT restore request requires select parameters to be specified"));
         }
 
         // OutputLocation is only valid for SELECT requests
-        if self.type_.as_ref().is_none_or(|t| t.as_str() != "SELECT") && self.output_location.is_some() {
+        if self.type_.as_ref().is_none_or(|t| t.as_str() != RestoreRequestType::SELECT) && self.output_location.is_some() {
             return Err(std::io::Error::other("OutputLocation can only be specified with SELECT request type"));
         }
         select_restore_s3_location(self)?;
 
         // Days must not be specified with SELECT requests
         if let Some(type_) = &self.type_
-            && type_.as_str() == "SELECT"
+            && type_.as_str() == RestoreRequestType::SELECT
             && self.days.is_some_and(|d| d > 0)
         {
             return Err(std::io::Error::other("Days cannot be specified with SELECT restore request"));
@@ -5614,7 +5596,7 @@ pub fn lifecycle_version_delete_target(oi: &ObjectInfo) -> Option<ObjectToDelete
 }
 
 pub async fn eval_action_from_lifecycle(
-    lc: &PersistedLifecycleConfiguration,
+    lc: &BucketLifecycleConfiguration,
     lock_config: Option<&ObjectLockConfiguration>,
     oi: &ObjectInfo,
 ) -> lifecycle::Event {
@@ -6319,19 +6301,14 @@ mod tests {
     use rustfs_data_usage::TierStats;
     use rustfs_filemeta::metadata_keys;
     use rustfs_filemeta::{FileInfo, FileMeta};
-    use rustfs_gateway_types::dto::MetadataEntry;
-    use rustfs_gateway_types::persistence::{
-        PersistedDefaultRetention as DefaultRetention, PersistedObjectLockConfiguration as ObjectLockConfiguration,
-        PersistedObjectLockRule as ObjectLockRule,
-    };
-    use rustfs_gateway_types::persistence::{
-        PersistedLifecycleConfiguration, PersistedLifecycleExpiration, PersistedLifecycleRule,
-        PersistedNoncurrentVersionExpiration, PersistedTransition,
-    };
-    use rustfs_lifecycle::{RestoreOutputLocation as OutputLocation, RestoreRequest, RestoreS3Location as S3Location};
     #[cfg(feature = "test-util")]
     use rustfs_s3_client::transition_api::ReaderImpl;
     use rustfs_scanner_metrics::metrics::{IlmAction, global_metrics};
+    use s3s::dto::{
+        BucketLifecycleConfiguration, DefaultRetention, ExpirationStatus, LifecycleExpiration, LifecycleRule, MetadataEntry,
+        NoncurrentVersionExpiration, ObjectLockConfiguration, ObjectLockEnabled, ObjectLockRetentionMode, ObjectLockRule,
+        OutputLocation, RestoreRequest, RestoreRequestType, S3Location, Timestamp, Transition, TransitionStorageClass,
+    };
     use serial_test::serial;
     use sha2::{Digest, Sha256};
     use std::collections::HashMap;
@@ -9338,7 +9315,7 @@ mod tests {
             output_location,
             select_parameters: None,
             tier: None,
-            type_: Some("SELECT".to_owned()),
+            type_: Some(RestoreRequestType::from_static(RestoreRequestType::SELECT)),
         }
     }
 
@@ -9655,12 +9632,12 @@ mod tests {
 
     #[test]
     fn lifecycle_rule_has_date_expiration_detects_enabled_date_rule() {
-        let lc = PersistedLifecycleConfiguration {
+        let lc = BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
-                    date: Some(lifecycle::format_lifecycle_date(OffsetDateTime::now_utc()).unwrap()),
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
+                    date: Some(Timestamp::from(OffsetDateTime::now_utc())),
                     ..Default::default()
                 }),
                 id: Some("rule-date".to_string()),
@@ -10177,15 +10154,14 @@ mod tests {
     #[test]
     fn should_defer_date_expiry_for_recent_config_update_respects_grace_window() {
         let now = OffsetDateTime::now_utc();
-        let recent = PersistedLifecycleConfiguration {
-            expiry_updated_at: Some(lifecycle::format_lifecycle_date(now - time::Duration::seconds(1)).unwrap()),
+        let recent = BucketLifecycleConfiguration {
+            expiry_updated_at: Some(Timestamp::from(now - time::Duration::seconds(1))),
             rules: Vec::new(),
         };
-        let stale = PersistedLifecycleConfiguration {
-            expiry_updated_at: Some(
-                lifecycle::format_lifecycle_date(now - time::Duration::seconds(DATE_EXPIRY_EXISTING_OBJECTS_GRACE_SECS + 1))
-                    .unwrap(),
-            ),
+        let stale = BucketLifecycleConfiguration {
+            expiry_updated_at: Some(Timestamp::from(
+                now - time::Duration::seconds(DATE_EXPIRY_EXISTING_OBJECTS_GRACE_SECS + 1),
+            )),
             rules: Vec::new(),
         };
 
@@ -10313,12 +10289,12 @@ mod tests {
         assert_eq!(deleted.version_id, None);
     }
 
-    fn expired_delete_marker_lifecycle() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn expired_delete_marker_lifecycle() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
                     expired_object_delete_marker: Some(true),
                     ..Default::default()
                 }),
@@ -10334,12 +10310,12 @@ mod tests {
         }
     }
 
-    fn latest_expiration_lifecycle() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn latest_expiration_lifecycle() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
                     days: Some(1),
                     ..Default::default()
                 }),
@@ -10355,12 +10331,12 @@ mod tests {
         }
     }
 
-    fn current_and_noncurrent_expiration_lifecycle() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn current_and_noncurrent_expiration_lifecycle() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
                     days: Some(30),
                     ..Default::default()
                 }),
@@ -10368,7 +10344,7 @@ mod tests {
                 del_marker_expiration: None,
                 filter: None,
                 id: Some("expire-current-and-noncurrent".to_string()),
-                noncurrent_version_expiration: Some(PersistedNoncurrentVersionExpiration {
+                noncurrent_version_expiration: Some(NoncurrentVersionExpiration {
                     noncurrent_days: Some(1),
                     newer_noncurrent_versions: None,
                 }),
@@ -10379,12 +10355,12 @@ mod tests {
         }
     }
 
-    fn all_versions_expiration_lifecycle() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn all_versions_expiration_lifecycle() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
                     days: Some(1),
                     expired_object_all_versions: Some(true),
                     ..Default::default()
@@ -10403,29 +10379,29 @@ mod tests {
 
     fn lock_enabled_without_default_retention() -> ObjectLockConfiguration {
         ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: None,
         }
     }
 
     fn lock_enabled_with_default_retention() -> ObjectLockConfiguration {
         ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: Some(ObjectLockRule {
                 default_retention: Some(DefaultRetention {
                     days: Some(30),
-                    mode: Some("COMPLIANCE".to_owned()),
+                    mode: Some(ObjectLockRetentionMode::from_static(ObjectLockRetentionMode::COMPLIANCE)),
                     years: None,
                 }),
             }),
         }
     }
 
-    fn latest_transition_lifecycle() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn latest_transition_lifecycle() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
                 expiration: None,
                 abort_incomplete_multipart_upload: None,
                 del_marker_expiration: None,
@@ -10434,10 +10410,10 @@ mod tests {
                 noncurrent_version_expiration: None,
                 noncurrent_version_transitions: None,
                 prefix: None,
-                transitions: Some(vec![PersistedTransition {
+                transitions: Some(vec![Transition {
                     days: Some(1),
                     date: None,
-                    storage_class: Some("WARM".to_owned()),
+                    storage_class: Some(TransitionStorageClass::from_static("WARM")),
                 }]),
             }],
         }
@@ -12974,9 +12950,8 @@ mod tests {
 
         for (name, object, lock_config, expected) in cases {
             let object_opts = lifecycle::object_opts_from_object_info(&object);
-            let evaluator_lock_config = lock_config.clone().map(Arc::new);
             let batch_event = Evaluator::new(Arc::new(lifecycle.clone()))
-                .with_lock_retention(evaluator_lock_config)
+                .with_lock_retention(lock_config.clone().map(Arc::new))
                 .eval(&[object_opts])
                 .await
                 .expect("batch lifecycle evaluation should succeed")
@@ -14233,7 +14208,10 @@ mod tests {
         let object = current_object_with_metadata(
             ReplicationStatusType::Completed,
             HashMap::from([
-                (metadata_keys::OBJECT_LOCK_MODE.to_string(), "COMPLIANCE".to_string()),
+                (
+                    metadata_keys::OBJECT_LOCK_MODE.to_string(),
+                    s3s::dto::ObjectLockRetentionMode::COMPLIANCE.to_string(),
+                ),
                 (metadata_keys::OBJECT_LOCK_RETAIN_UNTIL_DATE.to_string(), retain_until),
             ]),
         );
@@ -14245,7 +14223,7 @@ mod tests {
 
     #[tokio::test]
     async fn restored_copy_expiry_is_not_blocked_by_retention() {
-        let lifecycle = PersistedLifecycleConfiguration {
+        let lifecycle = BucketLifecycleConfiguration {
             expiry_updated_at: None,
             rules: Vec::new(),
         };
@@ -14255,7 +14233,10 @@ mod tests {
         let mut object = current_object_with_metadata(
             ReplicationStatusType::Completed,
             HashMap::from([
-                (metadata_keys::OBJECT_LOCK_MODE.to_string(), "COMPLIANCE".to_string()),
+                (
+                    metadata_keys::OBJECT_LOCK_MODE.to_string(),
+                    ObjectLockRetentionMode::COMPLIANCE.to_string(),
+                ),
                 (metadata_keys::OBJECT_LOCK_RETAIN_UNTIL_DATE.to_string(), retain_until),
             ]),
         );
@@ -14472,7 +14453,7 @@ mod tests {
                 "removed" => {
                     metadata_sys::delete(&bucket, BUCKET_LIFECYCLE_CONFIG).await.unwrap();
                 }
-                "disabled" => changed.rules[0].status = "Disabled".to_owned(),
+                "disabled" => changed.rules[0].status = ExpirationStatus::from_static(ExpirationStatus::DISABLED),
                 "longer-days" => {
                     changed.rules[0]
                         .noncurrent_version_expiration
@@ -14588,7 +14569,7 @@ mod tests {
         );
     }
 
-    async fn install_test_expiry_policy(ecstore: &Arc<ECStore>, bucket: &str) -> Arc<PersistedLifecycleConfiguration> {
+    async fn install_test_expiry_policy(ecstore: &Arc<ECStore>, bucket: &str) -> Arc<BucketLifecycleConfiguration> {
         let xml = br#"<LifecycleConfiguration><Rule><ID>expire</ID><Status>Enabled</Status><Filter><Prefix></Prefix></Filter><Expiration><Days>0</Days></Expiration><NoncurrentVersionExpiration><NoncurrentDays>0</NoncurrentDays></NoncurrentVersionExpiration></Rule></LifecycleConfiguration>"#;
         metadata_sys::update_in(&ecstore.ctx, bucket, BUCKET_LIFECYCLE_CONFIG, xml.to_vec())
             .await
@@ -15281,11 +15262,7 @@ mod tests {
     #[tokio::test]
     #[serial]
     async fn tier_free_version_recovery_production_entrypoint_enqueues_seeded_item() {
-        let (disk_paths, ecstore) =
-            temp_env::async_with_vars([(super::ENV_TIER_FREE_VERSION_RECOVERY_ENABLED, Some("false"))], async {
-                setup_test_env().await
-            })
-            .await;
+        let (disk_paths, ecstore) = setup_test_env().await;
         let tier = format!("RECOVERY{}", Uuid::new_v4().simple()).to_uppercase();
         crate::services::tier::test_util::register_mock_tier(&ecstore.tier_config_mgr(), &tier).await;
         let runtime_state = install_unconsumed_runtime_expiry_worker(&ecstore, 1).await;

crates/ecstore/src/bucket/lifecycle/core.rs

@@ -17,7 +17,7 @@ use crate::object_api::ObjectInfo;
 pub use rustfs_lifecycle::{
     Event, ExpirationOptions, IlmAction, LIFECYCLE_MALFORMED_XML_ERROR_KIND, Lifecycle, LifecycleCalculate, ObjectOpts,
     RuleValidate, TRANSITION_COMPLETE, TRANSITION_PENDING, TransitionOptions, abort_incomplete_multipart_upload_due,
-    expected_expiry_time, expiration_action_has_valid_target, format_lifecycle_date, parse_lifecycle_date,
+    expected_expiry_time, expiration_action_has_valid_target,
 };
 
 pub fn object_opts_from_object_info(oi: &ObjectInfo) -> ObjectOpts {

crates/ecstore/src/bucket/lifecycle/metadata_boundary.rs

@@ -14,8 +14,7 @@
 
 use std::sync::Arc;
 
-use rustfs_gateway_types::persistence::PersistedLifecycleConfiguration;
-use rustfs_gateway_types::persistence::PersistedObjectLockConfiguration as ObjectLockConfiguration;
+use s3s::dto::{BucketLifecycleConfiguration, ObjectLockConfiguration};
 use time::OffsetDateTime;
 use uuid::Uuid;
 
@@ -25,7 +24,7 @@ use crate::error::{Error, Result};
 
 #[derive(Debug)]
 pub(crate) struct LifecycleExpiryConfigs {
-    pub(crate) lifecycle: Option<Arc<PersistedLifecycleConfiguration>>,
+    pub(crate) lifecycle: Option<Arc<BucketLifecycleConfiguration>>,
     pub(crate) object_lock: Option<Arc<ObjectLockConfiguration>>,
     pub(crate) bucket_incarnation_id: Uuid,
     pub(crate) table_bucket_enabled: bool,
@@ -101,7 +100,7 @@ pub(crate) async fn get_expiry_configs_for_options(
     })
 }
 
-pub(crate) async fn get_lifecycle_config(bucket: &str) -> Result<(PersistedLifecycleConfiguration, OffsetDateTime)> {
+pub(crate) async fn get_lifecycle_config(bucket: &str) -> Result<(BucketLifecycleConfiguration, OffsetDateTime)> {
     metadata_sys::get_lifecycle_config(bucket).await
 }
 
@@ -111,15 +110,15 @@ mod tests {
     use crate::bucket::metadata::BucketMetadata;
     use crate::bucket::metadata_sys::{self, test_support::isolated_store_over_temp_disks};
     use crate::storage_api_contracts::bucket::MakeBucketOptions;
-    use rustfs_gateway_types::persistence::{PersistedLifecycleExpiration, PersistedLifecycleRule};
+    use s3s::dto::{ExpirationStatus, LifecycleExpiration, LifecycleRule};
     use serial_test::serial;
 
-    fn lifecycle_config() -> PersistedLifecycleConfiguration {
-        PersistedLifecycleConfiguration {
+    fn lifecycle_config() -> BucketLifecycleConfiguration {
+        BucketLifecycleConfiguration {
             expiry_updated_at: None,
-            rules: vec![PersistedLifecycleRule {
-                status: "Enabled".to_owned(),
-                expiration: Some(PersistedLifecycleExpiration {
+            rules: vec![LifecycleRule {
+                status: ExpirationStatus::from_static(ExpirationStatus::ENABLED),
+                expiration: Some(LifecycleExpiration {
                     days: Some(1),
                     ..Default::default()
                 }),

crates/ecstore/src/bucket/lifecycle/object_lock_boundary.rs

@@ -22,7 +22,7 @@ pub(crate) fn is_object_locked_by_metadata(user_defined: &HashMap<String, String
 }
 
 pub(crate) fn check_object_lock_for_deletion_with_config(
-    config: Option<&rustfs_gateway_types::persistence::PersistedObjectLockConfiguration>,
+    config: Option<&s3s::dto::ObjectLockConfiguration>,
     obj_info: &ObjectInfo,
     bypass_governance: bool,
 ) -> crate::error::Result<Option<ObjectLockBlockReason>> {

crates/ecstore/src/bucket/lifecycle/replication_sink.rs

@@ -82,13 +82,12 @@ mod tests {
     use crate::bucket::replication::{DeleteReplicationConfigSnapshot, ReplicationObjectBridge};
     use crate::object_api::{ObjectInfo, ObjectOptions};
     use crate::storage_api_contracts::object::ObjectToDelete;
-    use rustfs_gateway_types::dto::Status;
-    use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
-    use rustfs_gateway_types::persistence::{
-        PersistedOptionalReplicationStatus, PersistedReplicationConfiguration, PersistedReplicationDestination,
-        PersistedReplicationRule, PersistedReplicationStatus,
-    };
     use rustfs_scanner_metrics::metrics::IlmAction;
+    use s3s::dto::{
+        BucketVersioningStatus, DeleteMarkerReplication, DeleteMarkerReplicationStatus, DeleteReplication,
+        DeleteReplicationStatus, Destination, ReplicationConfiguration, ReplicationRule, ReplicationRuleStatus,
+        VersioningConfiguration,
+    };
     use uuid::Uuid;
 
     use super::*;
@@ -161,27 +160,27 @@ mod tests {
             for purge_enabled in [false, true] {
                 let snapshot = DeleteReplicationConfigSnapshot::from_configs_for_test(
                     VersioningConfiguration {
-                        status: Some("Enabled".to_owned()),
+                        status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
                         ..Default::default()
                     },
-                    Some(PersistedReplicationConfiguration {
+                    Some(ReplicationConfiguration {
                         role: String::new(),
-                        rules: vec![PersistedReplicationRule {
-                            delete_marker_replication: Some(PersistedOptionalReplicationStatus {
+                        rules: vec![ReplicationRule {
+                            delete_marker_replication: Some(DeleteMarkerReplication {
                                 status: Some(if marker_enabled {
-                                    Status::ENABLED.to_string()
+                                    DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::ENABLED)
                                 } else {
-                                    Status::DISABLED.to_string()
+                                    DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::DISABLED)
                                 }),
                             }),
-                            delete_replication: Some(PersistedReplicationStatus {
+                            delete_replication: Some(DeleteReplication {
                                 status: if purge_enabled {
-                                    Status::ENABLED.to_string()
+                                    DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED)
                                 } else {
-                                    Status::DISABLED.to_string()
+                                    DeleteReplicationStatus::from_static(DeleteReplicationStatus::DISABLED)
                                 },
                             }),
-                            destination: PersistedReplicationDestination {
+                            destination: Destination {
                                 bucket: "arn:rustfs:replication:target".to_string(),
                                 ..Default::default()
                             },
@@ -191,7 +190,7 @@ mod tests {
                             prefix: Some(String::new()),
                             priority: Some(1),
                             source_selection_criteria: None,
-                            status: Status::ENABLED.to_string(),
+                            status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
                         }],
                     }),
                 );

crates/ecstore/src/bucket/lifecycle/runtime_boundary.rs

@@ -14,7 +14,7 @@
 
 use std::sync::Arc;
 
-use rustfs_gateway_types::persistence::PersistedLifecycleConfiguration;
+use s3s::dto::BucketLifecycleConfiguration;
 use tokio::sync::RwLock;
 use tokio_util::sync::CancellationToken;
 
@@ -52,7 +52,7 @@ pub(crate) fn deployment_id() -> Option<String> {
     sources::deployment_id()
 }
 
-pub(crate) async fn bucket_lifecycle_config(bucket: &str) -> Option<PersistedLifecycleConfiguration> {
+pub(crate) async fn bucket_lifecycle_config(bucket: &str) -> Option<BucketLifecycleConfiguration> {
     sources::bucket_lifecycle_config(bucket).await
 }
 

crates/ecstore/src/bucket/metadata.rs

@@ -13,7 +13,7 @@
 // limitations under the License.
 
 use super::msgp_decode::{read_msgp_ext8_time, skip_msgp_value, write_msgp_time};
-use super::object_lock::ObjectLockApi;
+use super::object_lock::{ObjectLockApi, ObjectLockStatusExt};
 use super::versioning::VersioningApi;
 use super::{quota::BucketQuota, target::BucketTargets};
 use crate::bucket::replication::invalid_replication_config_status_field;
@@ -25,17 +25,12 @@ use crate::object_api::WriteCompletion;
 use crate::runtime::sources as runtime_sources;
 use crate::store::ECStore;
 use byteorder::{BigEndian, ByteOrder, LittleEndian};
-use rustfs_gateway_types::cors_tagging::{PersistedCorsConfiguration as CORSConfiguration, PersistedTagging as Tagging};
-use rustfs_gateway_types::persistence::{
-    PersistedAccelerateConfiguration as AccelerateConfiguration,
-    PersistedBucketEncryptionConfiguration as ServerSideEncryptionConfiguration,
-    PersistedBucketLoggingStatus as BucketLoggingStatus, PersistedLifecycleConfiguration,
-    PersistedNotificationConfiguration as NotificationConfiguration, PersistedObjectLockConfiguration as ObjectLockConfiguration,
-    PersistedPublicAccessBlockConfiguration as PublicAccessBlockConfiguration, PersistedReplicationConfiguration,
-    PersistedRequestPaymentConfiguration as RequestPaymentConfiguration,
-    PersistedVersioningConfiguration as VersioningConfiguration, PersistedWebsiteConfiguration as WebsiteConfiguration,
-};
 use rustfs_policy::policy::BucketPolicy;
+use s3s::dto::{
+    AccelerateConfiguration, BucketLifecycleConfiguration, BucketLoggingStatus, BucketVersioningStatus, CORSConfiguration,
+    NotificationConfiguration, ObjectLockConfiguration, PublicAccessBlockConfiguration, ReplicationConfiguration,
+    RequestPaymentConfiguration, ServerSideEncryptionConfiguration, Tagging, VersioningConfiguration, WebsiteConfiguration,
+};
 use serde::Serializer;
 use sha2::{Digest, Sha256};
 use std::collections::HashMap;
@@ -45,11 +40,23 @@ use time::{Date, OffsetDateTime, PrimitiveDateTime, Time as CivilTime, UtcOffset
 use tracing::error;
 use uuid::Uuid;
 
-// The persisted Object Lock configuration answers the storage-level trait
-// here because this module owns the persisted `ObjectLockConfiguration`.
+// The serving-layer DTO impls for the storage-level Object Lock traits live
+// here because this module owns the persisted `ObjectLockConfiguration`
+// during the s3s ratchet migration (rustfs/backlog#1842).
 impl ObjectLockApi for ObjectLockConfiguration {
     fn enabled(&self) -> bool {
-        self.object_lock_enabled.as_deref() == Some("Enabled")
+        self.object_lock_enabled
+            .as_ref()
+            .is_some_and(|v| v.as_str() == s3s::dto::ObjectLockEnabled::ENABLED)
+    }
+}
+
+impl ObjectLockStatusExt for s3s::dto::ObjectLockLegalHoldStatus {
+    fn valid(&self) -> bool {
+        matches!(
+            self.as_str(),
+            s3s::dto::ObjectLockLegalHoldStatus::ON | s3s::dto::ObjectLockLegalHoldStatus::OFF
+        )
     }
 }
 
@@ -432,8 +439,6 @@ pub struct BucketMetadata {
     pub bucket_incarnation_id: Uuid,
     pub(crate) bucket_incarnation_sidecar: bool,
     pub(crate) bucket_creation_committed: bool,
-    // A legacy default is not proof of an interrupted creation.
-    pub(crate) bucket_creation_commit_record_present: bool,
     pub policy_config_json: Vec<u8>,
     pub notification_config_xml: Vec<u8>,
     pub lifecycle_config_xml: Vec<u8>,
@@ -482,13 +487,13 @@ pub struct BucketMetadata {
 
     pub policy_config: Option<BucketPolicy>,
     pub notification_config: Option<NotificationConfiguration>,
-    pub lifecycle_config: Option<PersistedLifecycleConfiguration>,
+    pub lifecycle_config: Option<BucketLifecycleConfiguration>,
     pub object_lock_config: Option<ObjectLockConfiguration>,
     pub versioning_config: Option<VersioningConfiguration>,
     pub sse_config: Option<ServerSideEncryptionConfiguration>,
     pub tagging_config: Option<Tagging>,
     pub quota_config: Option<BucketQuota>,
-    pub replication_config: Option<PersistedReplicationConfiguration>,
+    pub replication_config: Option<ReplicationConfiguration>,
     pub bucket_target_config: Option<BucketTargets>,
     pub bucket_target_config_meta: Option<HashMap<String, String>>,
     pub cors_config: Option<CORSConfiguration>,
@@ -509,7 +514,6 @@ impl Default for BucketMetadata {
             bucket_incarnation_id: Uuid::nil(),
             bucket_incarnation_sidecar: false,
             bucket_creation_committed: false,
-            bucket_creation_commit_record_present: false,
             policy_config_json: Default::default(),
             notification_config_xml: Default::default(),
             lifecycle_config_xml: Default::default(),
@@ -748,10 +752,7 @@ impl BucketMetadata {
                 "TableBucketConfigUpdatedAt" => self.table_bucket_config_updated_at = read_msgp_time_value(rd)?,
                 "DurabilityConfigUpdatedAt" => self.durability_config_updated_at = read_msgp_time_value(rd)?,
                 "OnDemandMigrationConfigUpdatedAt" => self.on_demand_migration_config_updated_at = read_msgp_time_value(rd)?,
-                "BucketCreationCommitted" => {
-                    self.bucket_creation_committed = read_msgp_bool(rd)?;
-                    self.bucket_creation_commit_record_present = true;
-                }
+                "BucketCreationCommitted" => self.bucket_creation_committed = read_msgp_bool(rd)?,
                 other => {
                     tracing::debug!(field = %other, "BucketMetadata decode_from: skipping unknown field");
                     skip_msgp_value(rd)?;
@@ -764,10 +765,8 @@ impl BucketMetadata {
 
     /// Encode to msgp bytes. Field order follows MinIO BucketMetadata for compatibility.
     pub fn encode_to<W: Write>(&self, wr: &mut W) -> Result<()> {
-        // Preserve the absence of a legacy commit record across config rewrites.
-        let commit_record_present = self.bucket_creation_commit_record_present || self.bucket_creation_committed;
-        // Map size: MinIO fields (25) + RustFS extensions (21) + optional commit record.
-        let map_len: u32 = 46 + u32::from(commit_record_present);
+        // Map size: MinIO fields (25) + RustFS extensions (22)
+        let map_len: u32 = 47;
         rmp::encode::write_map_len(wr, map_len)?;
 
         // MinIO field order (same as Go struct)
@@ -848,10 +847,8 @@ impl BucketMetadata {
         write_msgp_time(wr, self.durability_config_updated_at)?;
         rmp::encode::write_str(wr, "OnDemandMigrationConfigUpdatedAt")?;
         write_msgp_time(wr, self.on_demand_migration_config_updated_at)?;
-        if commit_record_present {
-            rmp::encode::write_str(wr, "BucketCreationCommitted")?;
-            rmp::encode::write_bool(wr, self.bucket_creation_committed)?;
-        }
+        rmp::encode::write_str(wr, "BucketCreationCommitted")?;
+        rmp::encode::write_bool(wr, self.bucket_creation_committed)?;
 
         Ok(())
     }
@@ -1021,11 +1018,9 @@ impl BucketMetadata {
                     None
                 } else {
                     let config = deserialize::<VersioningConfiguration>(&data)?;
-                    if config
-                        .status
-                        .as_ref()
-                        .is_some_and(|status| !matches!(status.as_str(), "Enabled" | "Suspended"))
-                    {
+                    if config.status.as_ref().is_some_and(|status| {
+                        !matches!(status.as_str(), BucketVersioningStatus::ENABLED | BucketVersioningStatus::SUSPENDED)
+                    }) {
                         return Err(Error::other("bucket versioning configuration has an invalid status"));
                     }
                     Some(config)
@@ -1038,7 +1033,7 @@ impl BucketMetadata {
                 let config = if data.is_empty() {
                     None
                 } else {
-                    let config = deserialize::<PersistedReplicationConfiguration>(&data)?;
+                    let config = deserialize::<ReplicationConfiguration>(&data)?;
                     if let Some(field) = invalid_replication_config_status_field(&config) {
                         return Err(Error::other(format!("replication field {field} has an invalid status")));
                     }
@@ -1232,8 +1227,8 @@ impl BucketMetadata {
         }
         self.lifecycle_config = None;
         if !self.lifecycle_config_xml.is_empty()
-            && let Err(e) = deserialize::<PersistedLifecycleConfiguration>(&self.lifecycle_config_xml)
-                .map(|c| self.lifecycle_config = Some(c))
+            && let Err(e) =
+                deserialize::<BucketLifecycleConfiguration>(&self.lifecycle_config_xml).map(|c| self.lifecycle_config = Some(c))
         {
             tracing::warn!(
                 event = "bucket_metadata_parse_failed",
@@ -1319,8 +1314,8 @@ impl BucketMetadata {
         }
         self.replication_config = None;
         if !self.replication_config_xml.is_empty()
-            && let Err(e) = deserialize::<PersistedReplicationConfiguration>(&self.replication_config_xml)
-                .map(|c| self.replication_config = Some(c))
+            && let Err(e) =
+                deserialize::<ReplicationConfiguration>(&self.replication_config_xml).map(|c| self.replication_config = Some(c))
         {
             tracing::warn!(
                 event = "bucket_metadata_parse_failed",
@@ -1508,7 +1503,11 @@ pub(crate) async fn load_bucket_metadata_parse_with_presence(
     bucket: &str,
     parse: bool,
 ) -> Result<(BucketMetadata, bool)> {
-    let (mut bm, persisted) = match read_bucket_metadata(api.clone(), bucket).await {
+    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 {
         Ok(res) => (res, true),
         Err(err) => {
             if err != Error::ConfigNotFound {
@@ -1519,7 +1518,7 @@ pub(crate) async fn load_bucket_metadata_parse_with_presence(
         }
     };
 
-    let incarnation = load_bucket_incarnation(api.clone(), bucket).await?;
+    let incarnation = incarnation_res?;
     if persisted {
         if bm.name.is_empty() {
             bm.name = bucket.to_string();
@@ -1696,13 +1695,6 @@ mod test {
         let mut bm = BucketMetadata::unmarshal(&body[4..]).expect("unmarshal recovered blob");
         assert_eq!(bm.name, "interop");
         assert!(!bm.bucket_creation_committed, "legacy metadata must default to uncommitted");
-        assert!(!bm.bucket_creation_commit_record_present, "legacy metadata has no creation-commit record");
-        let rewritten = BucketMetadata::unmarshal(&bm.marshal_msg().expect("rewrite legacy metadata"))
-            .expect("read rewritten legacy metadata");
-        assert!(
-            !rewritten.bucket_creation_commit_record_present,
-            "rewriting legacy metadata must not fabricate a creation intent"
-        );
         bm.parse_all_configs().expect("parse recovered configs");
         assert!(bm.lifecycle_config.is_some());
     }
@@ -1720,7 +1712,6 @@ mod test {
 
         assert_eq!(bm.name, new.name);
         assert!(new.bucket_creation_committed);
-        assert!(new.bucket_creation_commit_record_present);
         assert!(!bm.bucket_incarnation_id.is_nil());
         assert_eq!(bm.bucket_incarnation_id, new.bucket_incarnation_id);
     }
@@ -1825,15 +1816,17 @@ mod test {
 
     #[test]
     fn object_locking_requires_lock_metadata_not_plain_versioning() {
+        use s3s::dto::ObjectLockEnabled;
+
         let mut bm = BucketMetadata::new("test-bucket");
         bm.versioning_config = Some(VersioningConfiguration {
-            status: Some("Enabled".to_owned()),
+            status: Some(s3s::dto::BucketVersioningStatus::from_static("Enabled")),
             ..Default::default()
         });
         assert!(!bm.object_locking());
 
         bm.object_lock_config = Some(ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             ..Default::default()
         });
         assert!(bm.object_locking());

crates/ecstore/src/bucket/metadata_sys.rs

@@ -30,18 +30,14 @@ use crate::storage_api_contracts::heal::HealOperations as _;
 use crate::storage_api_contracts::namespace::NamespaceLocking as _;
 use crate::store::{ECStore, await_bucket_namespace_operation};
 use futures::future::join_all;
-use rustfs_gateway_types::cors_tagging::{PersistedCorsConfiguration as CORSConfiguration, PersistedTagging as Tagging};
-use rustfs_gateway_types::persistence::{
-    PersistedAccelerateConfiguration as AccelerateConfiguration,
-    PersistedBucketEncryptionConfiguration as ServerSideEncryptionConfiguration,
-    PersistedBucketLoggingStatus as BucketLoggingStatus, PersistedLifecycleConfiguration,
-    PersistedNotificationConfiguration as NotificationConfiguration, PersistedObjectLockConfiguration as ObjectLockConfiguration,
-    PersistedPublicAccessBlockConfiguration as PublicAccessBlockConfiguration, PersistedReplicationConfiguration,
-    PersistedRequestPaymentConfiguration as RequestPaymentConfiguration,
-    PersistedVersioningConfiguration as VersioningConfiguration, PersistedWebsiteConfiguration as WebsiteConfiguration,
-};
 use rustfs_heal_contracts::heal_channel::HealOpts;
 use rustfs_policy::policy::BucketPolicy;
+use s3s::dto::ReplicationConfiguration;
+use s3s::dto::{
+    AccelerateConfiguration, BucketLifecycleConfiguration, BucketLoggingStatus, CORSConfiguration, NotificationConfiguration,
+    ObjectLockConfiguration, ObjectLockEnabled, ObjectLockRetentionMode, PublicAccessBlockConfiguration,
+    RequestPaymentConfiguration, ServerSideEncryptionConfiguration, Tagging, VersioningConfiguration, WebsiteConfiguration,
+};
 use std::collections::HashSet;
 use std::time::Duration;
 use std::{
@@ -172,7 +168,7 @@ pub(crate) fn object_lock_config_state_from_authoritative_metadata(bm: &BucketMe
     if bm.lock_enabled {
         return Ok(ObjectLockConfigState::Configured {
             config: ObjectLockConfiguration {
-                object_lock_enabled: Some("Enabled".to_owned()),
+                object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
                 rule: None,
             },
             updated_at: bm.object_lock_config_updated_at,
@@ -216,10 +212,17 @@ pub(crate) fn configured_object_lock_state_for_tests(
 ) -> ObjectLockConfigState {
     ObjectLockConfigState::Configured {
         config: ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
-            rule: Some(rustfs_gateway_types::persistence::PersistedObjectLockRule {
-                default_retention: Some(rustfs_gateway_types::persistence::PersistedDefaultRetention {
-                    mode: Some(mode.as_str().to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
+            rule: Some(s3s::dto::ObjectLockRule {
+                default_retention: Some(s3s::dto::DefaultRetention {
+                    mode: Some(s3s::dto::ObjectLockRetentionMode::from_static(match mode {
+                        crate::bucket::object_lock::types::RetentionMode::Governance => {
+                            s3s::dto::ObjectLockRetentionMode::GOVERNANCE
+                        }
+                        crate::bucket::object_lock::types::RetentionMode::Compliance => {
+                            s3s::dto::ObjectLockRetentionMode::COMPLIANCE
+                        }
+                    })),
                     days: Some(days),
                     years: None,
                 }),
@@ -230,7 +233,7 @@ pub(crate) fn configured_object_lock_state_for_tests(
 }
 
 fn validate_authoritative_object_lock_config(config: &ObjectLockConfiguration) -> Result<()> {
-    if config.object_lock_enabled.as_deref() != Some("Enabled") {
+    if config.object_lock_enabled.as_ref().map(ObjectLockEnabled::as_str) != Some(ObjectLockEnabled::ENABLED) {
         return Err(Error::other("persisted bucket Object Lock enabled state is invalid"));
     }
 
@@ -243,7 +246,7 @@ fn validate_authoritative_object_lock_config(config: &ObjectLockConfiguration) -
     if !retention
         .mode
         .as_ref()
-        .is_some_and(|mode| matches!(mode.as_str(), "COMPLIANCE" | "GOVERNANCE"))
+        .is_some_and(|mode| matches!(mode.as_str(), ObjectLockRetentionMode::COMPLIANCE | ObjectLockRetentionMode::GOVERNANCE))
     {
         return Err(Error::other("persisted bucket Object Lock retention mode is invalid"));
     }
@@ -1392,7 +1395,7 @@ pub async fn get_public_access_block_config(bucket: &str) -> Result<(PublicAcces
     bucket_meta_sys.get_public_access_block_config(bucket).await
 }
 
-pub async fn get_lifecycle_config(bucket: &str) -> Result<(PersistedLifecycleConfiguration, OffsetDateTime)> {
+pub async fn get_lifecycle_config(bucket: &str) -> Result<(BucketLifecycleConfiguration, OffsetDateTime)> {
     let bucket_meta_sys_lock = get_bucket_metadata_sys()?;
     let bucket_meta_sys = bucket_meta_sys_lock.read().await;
 
@@ -1432,6 +1435,7 @@ 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,
@@ -1450,6 +1454,27 @@ 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.
@@ -1459,6 +1484,24 @@ 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();
 
@@ -1474,7 +1517,7 @@ pub(crate) async fn get_delete_config_from_disk_in(
                 .await?
         }
     };
-    match authority {
+    match &authority {
         BucketMetadataAuthority::Authoritative(metadata)
             if metadata.bucket_incarnation_sidecar && !metadata.bucket_incarnation_id.is_nil() =>
         {
@@ -1486,11 +1529,11 @@ pub(crate) async fn get_delete_config_from_disk_in(
                 }
             }
             let object_lock_config_updated_at = metadata.object_lock_config_updated_at;
-            Ok((
-                object_lock_config_state_from_authoritative_metadata(&metadata)?,
-                metadata.bucket_incarnation_id,
-                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))
         }
         BucketMetadataAuthority::Authoritative(_) => {
             Err(Error::other(format!("bucket incarnation metadata is not authoritative: {bucket}")))
@@ -1561,6 +1604,23 @@ 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.
@@ -1611,7 +1671,7 @@ pub(crate) async fn get_cached_quota_config_and_incarnation_in(
     bucket_meta_sys.cached_quota_config_and_incarnation(bucket).await
 }
 
-pub async fn get_replication_config(bucket: &str) -> Result<(PersistedReplicationConfiguration, OffsetDateTime)> {
+pub async fn get_replication_config(bucket: &str) -> Result<(ReplicationConfiguration, OffsetDateTime)> {
     let bucket_meta_sys_lock = get_bucket_metadata_sys()?;
     let bucket_meta_sys = bucket_meta_sys_lock.read().await;
 
@@ -1621,7 +1681,7 @@ pub async fn get_replication_config(bucket: &str) -> Result<(PersistedReplicatio
 pub(crate) async fn get_replication_config_in(
     ctx: &crate::runtime::instance::InstanceContext,
     bucket: &str,
-) -> Result<(PersistedReplicationConfiguration, OffsetDateTime)> {
+) -> Result<(ReplicationConfiguration, OffsetDateTime)> {
     let bucket_meta_sys_lock = bucket_metadata_sys_of(ctx)?;
     let bucket_meta_sys = bucket_meta_sys_lock.read().await;
 
@@ -1747,27 +1807,22 @@ struct MetadataPublishGuard {
     _guard: tokio::sync::OwnedMutexGuard<MetadataPublishLockState>,
 }
 
-#[derive(Debug, Clone)]
-pub(crate) struct PendingBucketCreationProof {
-    pub(crate) generation: Uuid,
-    pub(crate) intent: Vec<u8>,
-    pub(crate) versioning_requested: bool,
-    pub(crate) witnesses: Vec<crate::disk::os::NativeBucketCreationWitness>,
+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);
 }
 
-impl PendingBucketCreationProof {
-    pub(crate) fn matches_metadata(&self, metadata: &BucketMetadata) -> Result<bool> {
-        Ok(!metadata.bucket_creation_committed
-            && metadata.bucket_incarnation_sidecar
-            && metadata.bucket_incarnation_id == self.generation
-            && metadata.marshal_msg()? == self.intent)
-    }
+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>>>>,
-    pending_bucket_creations: Arc<RwLock<HashMap<String, PendingBucketCreationProof>>>,
+    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>,
@@ -1811,7 +1866,7 @@ impl BucketMetadataSys {
     pub fn new(api: Arc<ECStore>) -> Self {
         Self {
             metadata_map: Arc::new(RwLock::new(HashMap::new())),
-            pending_bucket_creations: 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()),
             }),
@@ -1842,85 +1897,19 @@ impl BucketMetadataSys {
             .expect("bucket metadata object store should still be live")
     }
 
-    pub(crate) async fn pending_bucket_creation(&self, bucket: &str) -> Option<PendingBucketCreationProof> {
-        self.pending_bucket_creations.read().await.get(bucket).cloned()
-    }
-
-    pub(crate) async fn grant_pending_bucket_creation(&self, bucket: &str, proof: PendingBucketCreationProof) {
-        self.pending_bucket_creations.write().await.insert(bucket.to_owned(), proof);
-    }
-
-    pub(crate) async fn revoke_pending_bucket_creation(&self, bucket: &str) {
-        self.pending_bucket_creations.write().await.remove(bucket);
-    }
-
-    pub(crate) async fn consume_pending_bucket_creation(
-        &self,
-        bucket: &str,
-        metadata: &BucketMetadata,
-        witnesses: &[crate::disk::os::NativeBucketCreationWitness],
-    ) -> Result<bool> {
-        let mut pending = self.pending_bucket_creations.write().await;
-        let Some(proof) = pending.get(bucket) else {
-            return Ok(false);
-        };
-        if !proof.matches_metadata(metadata)?
-            || proof.witnesses.len() != witnesses.len()
-            || !proof
-                .witnesses
-                .iter()
-                .zip(witnesses)
-                .all(|(old, current)| old.matches(current))
-            || !crate::disk::os::consume_native_creation_witnesses(witnesses)
-        {
-            return Ok(false);
-        }
-        pending.remove(bucket);
-        Ok(true)
-    }
-
-    #[cfg(test)]
-    pub(crate) async fn refresh_bucket_for_test(&self, bucket: &str) -> Result<()> {
-        let expected = self.metadata_map.read().await.get(bucket).cloned();
-        let lock = self.object_store().new_ns_lock(bucket, bucket).await?;
-        let guard = lock.get_read_lock(crate::set_disk::get_lock_acquire_timeout()).await?;
-        self.load_bucket_under_namespace(bucket, MetadataLoadMode::Refresh, expected.as_ref(), &guard)
-            .await
-    }
-
-    #[cfg(test)]
-    pub(crate) async fn publish_persisted_metadata_for_test(&self, bucket: &str) -> Result<()> {
-        let expected = self.metadata_map.read().await.get(bucket).cloned();
-        let lock = self.object_store().new_ns_lock(bucket, bucket).await?;
-        let guard = lock.get_read_lock(crate::set_disk::get_lock_acquire_timeout()).await?;
-        let (metadata, persisted) = await_bucket_namespace_operation(
-            Some(&guard),
-            bucket,
-            "test cached metadata load",
-            load_bucket_metadata_parse_with_presence(self.object_store(), bucket, true),
-        )
-        .await?;
-        self.publish_if_unchanged(bucket, expected.as_ref(), metadata, persisted, &guard)
-            .await
-    }
-
-    #[cfg(test)]
-    pub(crate) async fn migrate_bucket_creation_commit_for_test(&self, bucket: &str) -> Result<()> {
-        self.migrate_bucket_creation_commit(bucket).await.map(|_| ())
-    }
-
-    #[cfg(test)]
-    pub(crate) async fn legacy_migration_reports_missing_bucket_for_test(&self, bucket: &str) -> Result<bool> {
-        Ok(matches!(
-            self.migrate_legacy_metadata(bucket).await?,
-            BucketMetadataAuthority::MissingBucket
-        ))
-    }
-
     fn object_store_if_live(&self) -> Option<Arc<ECStore>> {
         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)
     }
@@ -2107,7 +2096,6 @@ impl BucketMetadataSys {
         expected: Option<&Arc<BucketMetadata>>,
         namespace_guard: &rustfs_lock::NamespaceLockGuard,
     ) -> Result<()> {
-        self.revoke_pending_bucket_creation(bucket).await;
         if !await_bucket_namespace_operation(
             Some(namespace_guard),
             bucket,
@@ -2191,7 +2179,6 @@ impl BucketMetadataSys {
         persisted: bool,
         namespace_guard: &rustfs_lock::NamespaceLockGuard,
     ) -> Result<()> {
-        self.revoke_pending_bucket_creation(bucket).await;
         if !persisted {
             let _publish_guard = self
                 .lock_metadata_publish(bucket, namespace_guard, "refreshed bucket metadata absence publish")
@@ -2253,7 +2240,7 @@ impl BucketMetadataSys {
     }
 
     pub async fn set(&self, bucket: String, bm: Arc<BucketMetadata>) {
-        self.revoke_pending_bucket_creation(&bucket).await;
+        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;
@@ -2272,10 +2259,10 @@ 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;
         }
-        self.revoke_pending_bucket_creation(bucket).await;
         let publish_lock = self.metadata_publish_lock(bucket);
         let _publish_guard = publish_lock.lock().await;
         let mut map = self.metadata_map.write().await;
@@ -2293,7 +2280,7 @@ impl BucketMetadataSys {
     }
 
     async fn _reset(&mut self) {
-        self.pending_bucket_creations.write().await.clear();
+        bump_local_meta_mutation_gen();
         let mut map = self.metadata_map.write().await;
         map.clear();
         drop(map);
@@ -2432,7 +2419,6 @@ impl BucketMetadataSys {
     /// server's metadata never leaks into the ambient (first) instance.
     pub(crate) async fn persist_and_set(&self, bm: BucketMetadata) -> Result<()> {
         let mut bm = bm;
-        self.revoke_pending_bucket_creation(&bm.name).await;
         bm.save_with_store(self.object_store()).await?;
 
         self.set(bm.name.clone(), Arc::new(bm)).await;
@@ -2441,7 +2427,6 @@ impl BucketMetadataSys {
     }
 
     async fn persist_new_and_set(&self, mut bm: BucketMetadata) -> Result<()> {
-        self.revoke_pending_bucket_creation(&bm.name).await;
         bm.bucket_creation_committed = true;
         bm.save_with_store_committed(self.object_store()).await?;
         save_bucket_incarnation(self.object_store(), &bm.name, bm.bucket_incarnation_id).await?;
@@ -2451,9 +2436,7 @@ impl BucketMetadataSys {
     }
 
     async fn persist_new_bucket_metadata_intent(&self, mut bm: BucketMetadata) -> Result<()> {
-        self.revoke_pending_bucket_creation(&bm.name).await;
         bm.bucket_creation_committed = false;
-        bm.bucket_creation_commit_record_present = true;
         bm.save_with_store(self.object_store()).await?;
         save_bucket_incarnation(self.object_store(), &bm.name, bm.bucket_incarnation_id).await?;
         bm.bucket_incarnation_sidecar = true;
@@ -2463,7 +2446,6 @@ impl BucketMetadataSys {
     }
 
     async fn commit_bucket_metadata(&self, mut bm: BucketMetadata) -> Result<()> {
-        self.revoke_pending_bucket_creation(&bm.name).await;
         bm.parse_all_configs()?;
         bm.bucket_incarnation_sidecar = true;
         // The caller holds the full bucket creation fence (lifecycle, metadata
@@ -2512,7 +2494,6 @@ impl BucketMetadataSys {
         bucket: &str,
         namespace_guard: &rustfs_lock::NamespaceLockGuard,
     ) -> Result<()> {
-        self.revoke_pending_bucket_creation(bucket).await;
         let expected = self.metadata_map.read().await.get(bucket).cloned();
         if !self
             .bucket_exists(bucket, namespace_guard, "peer bucket metadata existence check")
@@ -2569,7 +2550,6 @@ impl BucketMetadataSys {
             #[cfg(test)]
             self.lazy_disk_loads.fetch_add(1, std::sync::atomic::Ordering::Relaxed);
 
-            self.revoke_pending_bucket_creation(bucket).await;
             let lock = self.object_store().new_ns_lock(bucket, bucket).await?;
             let guard = lock.get_read_lock(crate::set_disk::get_lock_acquire_timeout()).await?;
             #[cfg(test)]
@@ -2895,7 +2875,6 @@ impl BucketMetadataSys {
     /// revalidated at write quorum, so a stale snapshot can neither revert an
     /// acknowledged configuration update nor outlive a delete/recreate.
     async fn migrate_bucket_creation_commit(&self, bucket: &str) -> Result<BucketMetadataAuthority> {
-        self.revoke_pending_bucket_creation(bucket).await;
         let transaction_lock = self
             .object_store()
             .new_ns_lock(RUSTFS_META_BUCKET, &bucket_metadata_transaction_lock_key(bucket))
@@ -2973,7 +2952,6 @@ impl BucketMetadataSys {
         &self,
         bucket: &str,
     ) -> Result<BucketMetadataAuthority> {
-        self.revoke_pending_bucket_creation(bucket).await;
         #[cfg(test)]
         if self.object_lock_disk_read_errors.write().await.remove(bucket) {
             return Err(Error::other(format!("injected Object Lock metadata disk read failure: {bucket}")));
@@ -3106,30 +3084,77 @@ impl BucketMetadataSys {
             return Err(Error::other(format!("injected Object Lock metadata disk read failure: {bucket}")));
         }
 
-        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
-        {
+        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 {
             Ok(_) => {}
             Err(Error::VolumeNotFound) => return Ok(BucketMetadataAuthority::MissingBucket),
             Err(err) => return Err(err),
         }
 
-        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?;
+        let (metadata, persisted) = metadata_res?;
         if persisted && metadata.lock_enabled && !metadata.bucket_creation_committed {
             return Err(Error::ErasureWriteQuorum);
         }
         if persisted {
-            Ok(BucketMetadataAuthority::Authoritative(Arc::new(metadata)))
+            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))
         } else {
             Ok(BucketMetadataAuthority::Fabricated)
         }
@@ -3149,7 +3174,7 @@ impl BucketMetadataSys {
         }
     }
 
-    pub async fn get_lifecycle_config(&self, bucket: &str) -> Result<(PersistedLifecycleConfiguration, OffsetDateTime)> {
+    pub async fn get_lifecycle_config(&self, bucket: &str) -> Result<(BucketLifecycleConfiguration, OffsetDateTime)> {
         let (bm, _) = self.get_config(bucket).await?;
 
         match ConfigState::of(&bm.lifecycle_config_xml, &bm.lifecycle_config).require(bucket, BUCKET_LIFECYCLE_CONFIG)? {
@@ -3272,7 +3297,7 @@ impl BucketMetadataSys {
         }))
     }
 
-    pub async fn get_replication_config(&self, bucket: &str) -> Result<(PersistedReplicationConfiguration, OffsetDateTime)> {
+    pub async fn get_replication_config(&self, bucket: &str) -> Result<(ReplicationConfiguration, OffsetDateTime)> {
         let (bm, _) = self.get_config(bucket).await?;
 
         if !bm.replication_config_xml.is_empty() && bm.replication_config.is_none() {
@@ -3374,7 +3399,6 @@ mod tests {
     };
     use crate::bucket::target::{BucketTarget, BucketTargetType, Credentials};
     use crate::config::com::read_config;
-    use crate::disk::{DiskAPI as _, RUSTFS_META_TMP_BUCKET};
     use crate::storage_api_contracts::bucket::{BucketOperations as _, DeleteBucketOptions, MakeBucketOptions};
     use byteorder::{ByteOrder as _, LittleEndian};
     use serial_test::serial;
@@ -3429,180 +3453,6 @@ mod tests {
         ),
     ];
 
-    #[tokio::test]
-    #[serial(storage_class_env)]
-    async fn persistence_entry_failures_revoke_pending_creation_before_cache_publish() {
-        let (dirs, store) = isolated_store_over_temp_disks().await;
-        init_bucket_metadata_sys(store.clone(), Vec::new()).await;
-        let sys = bucket_metadata_sys_of(&store.ctx).expect("instance metadata system");
-        let sys = sys.read().await.clone();
-        let options = MakeBucketOptions {
-            lock_enabled: true,
-            ..Default::default()
-        };
-        for entry in ["save", "persist", "persist-new", "commit"] {
-            let bucket = format!("revoke-{entry}-{}", Uuid::new_v4());
-            store.fail_next_bucket_creation_after_intent_for_test(&bucket);
-            store
-                .make_bucket(&bucket, &options)
-                .await
-                .expect_err("stop the real producer before physical publication");
-            sys.pending_bucket_creation(&bucket)
-                .await
-                .expect("the producer must leave a real live creation permission");
-            let (intent, persisted) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-                .await
-                .expect("read the original producer intent");
-            assert!(persisted, "{entry}: the complete original intent must be persisted");
-            let original_intent = intent.marshal_msg().expect("encode the original intent");
-
-            // Keep the creation fence order used by the real producer.
-            let lifecycle_guard = store
-                .acquire_bucket_lifecycle_write_lock(&bucket)
-                .await
-                .expect("hold the bucket lifecycle fence");
-            let transaction_guard = acquire_bucket_metadata_transaction_lock_in(&store.ctx, &bucket)
-                .await
-                .expect("hold the metadata transaction fence");
-            let namespace_lock = store
-                .new_ns_lock(&bucket, &bucket)
-                .await
-                .expect("create the exact bucket namespace lock");
-            let namespace_guard = namespace_lock
-                .get_write_lock(crate::set_disk::get_lock_acquire_timeout())
-                .await
-                .expect("hold the exact bucket namespace fence");
-
-            // A file at each native staging root causes actual IO to fail before
-            // metadata can reach the cache-publishing set call. Preserve the
-            // original staging directories so no fixture data is discarded.
-            for dir in &dirs {
-                let staging = dir.path().join(RUSTFS_META_TMP_BUCKET);
-                let saved = dir.path().join(".rustfs.sys/revocation-saved-tmp");
-                std::fs::rename(&staging, &saved).expect("preserve the native staging directory");
-                std::fs::write(&staging, b"block metadata staging with a non-directory")
-                    .expect("install an actual non-directory IO obstruction");
-            }
-            let result = match entry {
-                "save" => sys.save(intent).await,
-                "persist" => sys.persist_and_set(intent).await,
-                "persist-new" => sys.persist_new_and_set(intent).await,
-                "commit" => sys.commit_bucket_metadata(intent).await,
-                _ => unreachable!(),
-            };
-            for dir in &dirs {
-                let staging = dir.path().join(RUSTFS_META_TMP_BUCKET);
-                let saved = dir.path().join(".rustfs.sys/revocation-saved-tmp");
-                std::fs::remove_file(&staging).expect("remove only the fixture's staging obstruction");
-                std::fs::rename(&saved, &staging).expect("restore the complete original staging directory");
-            }
-            drop((namespace_guard, transaction_guard, lifecycle_guard));
-            result.expect_err("native persistence must fail before its downstream cache set");
-            assert!(
-                sys.pending_bucket_creation(&bucket).await.is_none(),
-                "{entry}: the entry revoker must retire live permission even when persistence fails"
-            );
-            let (after_failure, present) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-                .await
-                .expect("read the intent after the failed persistence entry");
-            assert!(present, "{entry}: a failed persistence entry must retain the original metadata");
-            assert_eq!(
-                after_failure
-                    .marshal_msg()
-                    .expect("encode the original intent after persistence failure"),
-                original_intent,
-                "{entry}: native IO failure must not change the original generation or complete intent"
-            );
-            let error = store
-                .make_bucket(&bucket, &options)
-                .await
-                .expect_err("a failed ordinary persistence entry cannot preserve creation permission");
-            assert!(error.to_string().contains("administrator recovery"), "{entry}: {error}");
-            let (after_retry, _) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-                .await
-                .expect("read the original intent after the rejected retry");
-            assert_eq!(
-                after_retry.marshal_msg().expect("encode the intent after the rejected retry"),
-                original_intent,
-                "{entry}: the rejected retry must preserve the complete original intent"
-            );
-            for disk in store.pools[0].disk_set[0].disks.read().await.iter() {
-                assert!(
-                    matches!(
-                        disk.as_ref().expect("native disk").stat_volume(&bucket).await,
-                        Err(crate::disk::error::DiskError::VolumeNotFound)
-                    ),
-                    "{entry}: failed persistence and the rejected retry must not publish a physical volume"
-                );
-            }
-        }
-    }
-
-    #[tokio::test]
-    #[serial(storage_class_env)]
-    async fn metadata_reset_revokes_real_pending_creation_without_changing_persisted_intent() {
-        let (_dirs, store) = isolated_store_over_temp_disks().await;
-        init_bucket_metadata_sys(store.clone(), Vec::new()).await;
-        let bucket = format!("revoke-reset-{}", Uuid::new_v4());
-        let options = MakeBucketOptions {
-            lock_enabled: true,
-            ..Default::default()
-        };
-        store.fail_next_bucket_creation_after_intent_for_test(&bucket);
-        store
-            .make_bucket(&bucket, &options)
-            .await
-            .expect_err("stop the real producer before physical publication");
-        let sys = bucket_metadata_sys_of(&store.ctx).expect("instance metadata system");
-        let mut sys = sys.read().await.clone();
-        sys.pending_bucket_creation(&bucket)
-            .await
-            .expect("the real producer must leave live creation permission before reset");
-        let (intent, persisted) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-            .await
-            .expect("read the original intent before cache reset");
-        assert!(persisted, "cache reset starts from a complete real persisted intent");
-        let original_intent = intent.marshal_msg().expect("encode the original reset intent");
-        sys._reset().await;
-        assert!(
-            sys.pending_bucket_creation(&bucket).await.is_none(),
-            "reset must revoke the producer-issued permission shared with the instance metadata system"
-        );
-        let (after_reset, present) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-            .await
-            .expect("read the original intent after cache reset");
-        assert!(present, "cache reset must retain the persisted intent");
-        assert_eq!(
-            after_reset.marshal_msg().expect("encode the intent after cache reset"),
-            original_intent,
-            "cache reset must leave the original generation and complete persisted intent unchanged"
-        );
-        let error = store
-            .make_bucket(&bucket, &options)
-            .await
-            .expect_err("reset cannot regrant the producer's old creation permission");
-        assert!(error.to_string().contains("administrator recovery"), "{error}");
-        let (after_retry, _) = get_config_from_disk_with_presence_in(&store.ctx, &bucket)
-            .await
-            .expect("read the intent after the reset-induced retry rejection");
-        assert_eq!(
-            after_retry
-                .marshal_msg()
-                .expect("encode the intent after the rejected reset retry"),
-            original_intent,
-            "the reset-induced rejection must preserve the original complete intent"
-        );
-        for disk in store.pools[0].disk_set[0].disks.read().await.iter() {
-            assert!(
-                matches!(
-                    disk.as_ref().expect("native disk").stat_volume(&bucket).await,
-                    Err(crate::disk::error::DiskError::VolumeNotFound)
-                ),
-                "cache reset and the rejected retry must not publish a physical volume"
-            );
-        }
-    }
-
     #[tokio::test]
     async fn g_d3_003_new_writer_replication_loads_without_fail_closed_state() {
         let (dirs, store) = isolated_store_over_temp_disks().await;
@@ -3791,7 +3641,7 @@ mod tests {
         let mut versioned = BucketMetadata::new("authoritative-versioned");
         versioned.versioning_config_xml = b"<VersioningConfiguration><Status>Enabled</Status></VersioningConfiguration>".to_vec();
         versioned.versioning_config = Some(VersioningConfiguration {
-            status: Some("Enabled".to_owned()),
+            status: Some(s3s::dto::BucketVersioningStatus::from_static(s3s::dto::BucketVersioningStatus::ENABLED)),
             ..Default::default()
         });
         sys.set("authoritative-versioned".to_string(), Arc::new(versioned)).await;
@@ -3914,24 +3764,25 @@ mod tests {
         else {
             panic!("legacy lock-enabled metadata must remain configured");
         };
-        assert_eq!(config.object_lock_enabled.as_deref(), Some("Enabled"));
+        assert_eq!(
+            config.object_lock_enabled.as_ref().map(|value| value.as_str()),
+            Some(ObjectLockEnabled::ENABLED)
+        );
         assert!(config.rule.is_none());
     }
 
     #[test]
     fn authoritative_object_lock_state_rejects_invalid_retention_periods() {
-        use rustfs_gateway_types::persistence::{
-            PersistedDefaultRetention as DefaultRetention, PersistedObjectLockRule as ObjectLockRule,
-        };
+        use s3s::dto::{DefaultRetention, ObjectLockRule};
 
         for (days, years) in [(Some(0), None), (Some(-1), None), (Some(1), Some(1)), (None, None)] {
             let mut metadata = BucketMetadata::new("invalid-object-lock");
             metadata.object_lock_config = Some(ObjectLockConfiguration {
-                object_lock_enabled: Some("Enabled".to_owned()),
+                object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
                 rule: Some(ObjectLockRule {
                     default_retention: Some(DefaultRetention {
                         days,
-                        mode: Some("COMPLIANCE".to_owned()),
+                        mode: Some(ObjectLockRetentionMode::from_static(ObjectLockRetentionMode::COMPLIANCE)),
                         years,
                     }),
                 }),
@@ -3946,11 +3797,9 @@ mod tests {
 
     #[test]
     fn authoritative_object_lock_state_rejects_invalid_enabled_mode_and_rule() {
-        use rustfs_gateway_types::persistence::{
-            PersistedDefaultRetention as DefaultRetention, PersistedObjectLockRule as ObjectLockRule,
-        };
+        use s3s::dto::{DefaultRetention, ObjectLockRule};
 
-        for enabled in [None, Some("Disabled".to_string())] {
+        for enabled in [None, Some(ObjectLockEnabled::from("Disabled".to_string()))] {
             let mut metadata = BucketMetadata::new("invalid-object-lock-enabled");
             metadata.lock_enabled = true;
             metadata.object_lock_config = Some(ObjectLockConfiguration {
@@ -3962,11 +3811,11 @@ mod tests {
 
         let mut invalid_mode = BucketMetadata::new("invalid-object-lock-mode");
         invalid_mode.object_lock_config = Some(ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: Some(ObjectLockRule {
                 default_retention: Some(DefaultRetention {
                     days: Some(1),
-                    mode: Some("invalid".to_string()),
+                    mode: Some(ObjectLockRetentionMode::from("invalid".to_string())),
                     years: None,
                 }),
             }),
@@ -3975,7 +3824,7 @@ mod tests {
 
         let mut missing_retention = BucketMetadata::new("missing-object-lock-retention");
         missing_retention.object_lock_config = Some(ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: Some(ObjectLockRule { default_retention: None }),
         });
         assert!(object_lock_config_state_from_authoritative_metadata(&missing_retention).is_err());
@@ -3985,7 +3834,7 @@ mod tests {
     fn object_lock_ever_enabled_marker_survives_config_removal() {
         let mut metadata = BucketMetadata::new("lock-config-removed");
         let config = ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: None,
         };
         metadata
@@ -4003,7 +3852,10 @@ mod tests {
         else {
             panic!("an ever-enabled bucket must remain Object Lock configured");
         };
-        assert_eq!(config.object_lock_enabled.as_deref(), Some("Enabled"));
+        assert_eq!(
+            config.object_lock_enabled.as_ref().map(ObjectLockEnabled::as_str),
+            Some(ObjectLockEnabled::ENABLED)
+        );
     }
 
     #[tokio::test]
@@ -4019,7 +3871,7 @@ mod tests {
 
         let node = Arc::new(RwLock::new(BucketMetadataSys::new(ecstore.clone())));
         let config = ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: None,
         };
         update_with_sys(
@@ -5000,7 +4852,7 @@ mod tests {
     #[tokio::test]
     async fn update_config_with_persists_tagging_rewrite_across_disk_reload() {
         use crate::bucket::metadata::BUCKET_TAGGING_CONFIG;
-        use rustfs_gateway_types::cors_tagging::PersistedTag as Tag;
+        use s3s::dto::Tag;
 
         let (dirs, ecstore) = isolated_store_over_temp_disks().await;
 
@@ -5164,7 +5016,7 @@ mod tests {
     #[tokio::test]
     async fn concurrent_update_config_with_calls_do_not_lose_writes() {
         use crate::bucket::metadata::BUCKET_TAGGING_CONFIG;
-        use rustfs_gateway_types::cors_tagging::PersistedTag as Tag;
+        use s3s::dto::Tag;
 
         let (dirs, ecstore) = isolated_store_over_temp_disks().await;
         let sys = Arc::new(RwLock::new(BucketMetadataSys::new(ecstore)));
@@ -5264,7 +5116,7 @@ mod tests {
         let mut persisted = BucketMetadata::new("reload-bucket");
         persisted.policy_config_json = b"persisted-marker".to_vec();
         let lock_config = ObjectLockConfiguration {
-            object_lock_enabled: Some("Enabled".to_owned()),
+            object_lock_enabled: Some(ObjectLockEnabled::from_static(ObjectLockEnabled::ENABLED)),
             rule: None,
         };
         persisted
@@ -5543,7 +5395,7 @@ mod tests {
     #[serial]
     async fn bucket_delete_waits_for_config_mutation_fence() {
         use crate::bucket::metadata::BUCKET_TAGGING_CONFIG;
-        use rustfs_gateway_types::cors_tagging::PersistedTag as Tag;
+        use s3s::dto::Tag;
 
         let (_dirs, store) = isolated_store_over_temp_disks().await;
         init_bucket_metadata_sys(store.clone(), Vec::new()).await;

crates/ecstore/src/bucket/object_lock/mod.rs

@@ -17,8 +17,15 @@ pub mod objectlock_sys;
 pub mod types;
 
 /// Whether a bucket Object Lock configuration has locking enabled. The
-/// persisted `ObjectLockConfiguration` implements this in the bucket-metadata
-/// module, which owns the persisted configuration type.
+/// serving-layer `ObjectLockConfiguration` DTO implements this in
+/// the bucket-metadata module, which owns the persisted configuration type
+/// during the s3s ratchet migration (rustfs/backlog#1842).
 pub trait ObjectLockApi {
     fn enabled(&self) -> bool;
 }
+
+/// Whether a legal-hold status value is one of the two valid wire values.
+/// Implemented for the serving-layer DTO in the bucket-metadata module.
+pub trait ObjectLockStatusExt {
+    fn valid(&self) -> bool;
+}

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

@@ -12,7 +12,6 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-pub use rustfs_replication::config_cache_serde;
 pub use rustfs_replication::{
     ObjectOpts, OperatorRuleContract, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_READ_ONLY_HISTORICAL_FIELDS,
     REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS, REPLICATION_CAPABILITY_CONTRACT_VERSION,

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

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use rustfs_gateway_types::persistence::PersistedReplicationConfiguration;
+use s3s::dto::ReplicationConfiguration;
 
 use super::replication_config_boundary::ReplicationConfigurationExt as _;
 use super::replication_filemeta_boundary::{
@@ -42,7 +42,7 @@ impl ReplicationLifecycleBridge {
         dead_code,
         reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
     )]
-    pub(crate) fn new_config(config: PersistedReplicationConfiguration) -> ReplicationLifecycleConfig {
+    pub(crate) fn new_config(config: ReplicationConfiguration) -> ReplicationLifecycleConfig {
         ReplicationConfig::new(Some(config), None)
     }
 
@@ -118,17 +118,16 @@ impl ReplicationLifecycleBridge {
 
 #[cfg(test)]
 mod tests {
-    use rustfs_gateway_types::dto::Status;
-    use rustfs_gateway_types::persistence::{PersistedReplicationDestination, PersistedReplicationRule};
+    use s3s::dto::{Destination, ReplicationRule, ReplicationRuleStatus};
 
     use super::super::replication_filemeta_boundary::{ReplicateTargetDecision, VersionPurgeStatusType};
     use super::*;
 
-    fn replication_rule() -> PersistedReplicationRule {
-        PersistedReplicationRule {
+    fn replication_rule() -> ReplicationRule {
+        ReplicationRule {
             delete_marker_replication: None,
             delete_replication: None,
-            destination: PersistedReplicationDestination {
+            destination: Destination {
                 bucket: "arn:aws:s3:::target-bucket".to_string(),
                 ..Default::default()
             },
@@ -138,13 +137,13 @@ mod tests {
             prefix: Some(String::new()),
             priority: Some(1),
             source_selection_criteria: None,
-            status: Status::ENABLED.to_string(),
+            status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
         }
     }
 
     #[test]
     fn has_pending_version_purge_preserves_replication_active_rule_behavior() {
-        let config = ReplicationLifecycleBridge::new_config(PersistedReplicationConfiguration {
+        let config = ReplicationLifecycleBridge::new_config(ReplicationConfiguration {
             role: String::new(),
             rules: vec![replication_rule()],
         });

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

@@ -17,8 +17,8 @@ use std::sync::Arc;
 use crate::bucket::{metadata::BucketMetadata, metadata_sys};
 use crate::disk::{BUCKET_META_PREFIX, RUSTFS_META_BUCKET};
 use crate::runtime::instance::InstanceContext;
-use rustfs_gateway_types::persistence::PersistedReplicationConfiguration;
 use rustfs_utils::path::path_join_buf;
+use s3s::dto::ReplicationConfiguration;
 use time::OffsetDateTime;
 
 use super::replication_error_boundary::{Error, Result};
@@ -36,11 +36,11 @@ impl ReplicationMetadataStore {
     pub(crate) const FORCE_DELETE_REPLICATION_FILE: &'static str = "config/replication/force-delete.bin";
     pub(crate) const FORCE_DELETE_REPLICATION_TRANSACTION_LOCK: &'static str = "config/replication/force-delete.bin.transaction";
 
-    pub(crate) async fn replication_config(bucket: &str) -> Result<(PersistedReplicationConfiguration, OffsetDateTime)> {
+    pub(crate) async fn replication_config(bucket: &str) -> Result<(ReplicationConfiguration, OffsetDateTime)> {
         metadata_sys::get_replication_config(bucket).await
     }
 
-    pub(crate) async fn optional_replication_config(bucket: &str) -> Result<Option<PersistedReplicationConfiguration>> {
+    pub(crate) async fn optional_replication_config(bucket: &str) -> Result<Option<ReplicationConfiguration>> {
         let config = match Self::replication_config(bucket).await {
             Ok((config, _)) => Some(config),
             Err(err) => {

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

@@ -16,9 +16,7 @@ use std::{collections::HashMap, fmt, sync::Arc};
 
 use super::replication_filemeta_boundary::metadata_keys;
 use crate::bucket::metadata::BucketMetadata;
-use rustfs_gateway_types::dto::Status;
-use rustfs_gateway_types::persistence::PersistedReplicationConfiguration;
-use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
+use s3s::dto::{BucketVersioningStatus, ReplicationConfiguration, ReplicationRuleStatus, VersioningConfiguration};
 use serde::{Deserialize, Serialize};
 use time::OffsetDateTime;
 use tracing::error;
@@ -41,7 +39,7 @@ use super::replication_target_boundary::{BucketTargets, ReplicationTargetStore};
 use super::replication_versioning_boundary::ReplicationVersioningStore;
 use super::runtime_boundary as runtime_sources;
 
-pub(crate) async fn get_replication_config(bucket: &str) -> Result<Option<PersistedReplicationConfiguration>> {
+pub(crate) async fn get_replication_config(bucket: &str) -> Result<Option<ReplicationConfiguration>> {
     let config = ReplicationMetadataStore::optional_replication_config(bucket).await?;
     validate_delete_replication_config(&VersioningConfiguration::default(), config.as_ref())?;
     Ok(config)
@@ -66,7 +64,7 @@ impl DeleteReplicationConfigSnapshot {
     #[cfg(test)]
     pub(crate) fn from_configs_for_test(
         versioning: VersioningConfiguration,
-        replication: Option<PersistedReplicationConfiguration>,
+        replication: Option<ReplicationConfiguration>,
     ) -> Self {
         let metadata = replication.map(|config| {
             let mut metadata = BucketMetadata::new("test-bucket");
@@ -80,7 +78,7 @@ impl DeleteReplicationConfigSnapshot {
         &self.versioning
     }
 
-    pub fn replication_config(&self) -> Option<&PersistedReplicationConfiguration> {
+    pub fn replication_config(&self) -> Option<&ReplicationConfiguration> {
         self.metadata
             .as_ref()
             .and_then(|metadata| metadata.replication_config.as_ref())
@@ -103,7 +101,7 @@ impl DeleteReplicationConfigSnapshot {
     pub(crate) fn active_delete_marker_rules_require_tags(&self, object: &str) -> bool {
         self.replication_config().is_some_and(|config| {
             config.rules.iter().any(|rule| {
-                if rule.status == Status::DISABLED.as_str() {
+                if rule.status == ReplicationRuleStatus::from_static(ReplicationRuleStatus::DISABLED) {
                     return false;
                 }
                 if !object.starts_with(rule.prefix()) {
@@ -124,12 +122,12 @@ impl DeleteReplicationConfigSnapshot {
 
 fn validate_delete_replication_config(
     versioning: &VersioningConfiguration,
-    config: Option<&PersistedReplicationConfiguration>,
+    config: Option<&ReplicationConfiguration>,
 ) -> Result<()> {
     if versioning
         .status
         .as_ref()
-        .is_some_and(|status| !matches!(status.as_str(), "Enabled" | "Suspended"))
+        .is_some_and(|status| !matches!(status.as_str(), BucketVersioningStatus::ENABLED | BucketVersioningStatus::SUSPENDED))
     {
         return Err(super::replication_error_boundary::Error::other(
             "bucket versioning configuration has an invalid status",
@@ -146,7 +144,7 @@ fn validate_delete_replication_config(
         let role = config.role.trim();
         let mut role_destination = None;
         for rule in &config.rules {
-            if rule.status.as_str() == Status::ENABLED.as_str() {
+            if rule.status.as_str() == ReplicationRuleStatus::ENABLED {
                 let destination = rule.destination.bucket.trim();
                 if role.is_empty() && destination.is_empty() {
                     return Err(super::replication_error_boundary::Error::other(
@@ -171,7 +169,7 @@ fn validate_delete_replication_config(
     Ok(())
 }
 
-fn replication_config_from_metadata(metadata: &BucketMetadata) -> Result<Option<&PersistedReplicationConfiguration>> {
+fn replication_config_from_metadata(metadata: &BucketMetadata) -> Result<Option<&ReplicationConfiguration>> {
     if !metadata.replication_config_xml.is_empty() && metadata.replication_config.is_none() {
         return Err(super::replication_error_boundary::Error::other(
             "persisted bucket replication configuration is invalid",
@@ -252,15 +250,12 @@ pub(crate) async fn load_delete_replication_config_in(
 
 #[derive(Debug, Clone, Default, Serialize, Deserialize)]
 pub struct ReplicationConfig {
-    /// Carried in the scanner's persisted data usage cache, so its serde form
-    /// is the one the s3s DTO wrote there (see `config_cache_serde` in the replication crate).
-    #[serde(with = "super::replication_config_boundary::config_cache_serde")]
-    pub config: Option<PersistedReplicationConfiguration>,
+    pub config: Option<ReplicationConfiguration>,
     pub remotes: Option<BucketTargets>,
 }
 
 impl ReplicationConfig {
-    pub fn new(config: Option<PersistedReplicationConfiguration>, remotes: Option<BucketTargets>) -> Self {
+    pub fn new(config: Option<ReplicationConfiguration>, remotes: Option<BucketTargets>) -> Self {
         Self { config, remotes }
     }
 
@@ -473,7 +468,7 @@ fn check_replicate_delete_with_config(
     oi: &ObjectInfo,
     del_opts: &ObjectOptions,
     source_error: bool,
-    config: Option<&PersistedReplicationConfiguration>,
+    config: Option<&ReplicationConfiguration>,
     existing_delete_marker: bool,
     trust_persisted_replica_status: bool,
 ) -> ReplicateDecision {
@@ -592,7 +587,7 @@ pub(crate) async fn must_replicate(bucket: &str, object: &str, mopts: MustReplic
 }
 
 fn metadata_target_should_replicate(
-    cfg: &PersistedReplicationConfiguration,
+    cfg: &ReplicationConfiguration,
     opts: &ObjectOpts,
     mopts: &MustReplicateOptions,
     arn: &str,
@@ -602,21 +597,20 @@ fn metadata_target_should_replicate(
 
 #[cfg(test)]
 mod tests {
-    use rustfs_gateway_types::dto::Status;
-    use rustfs_gateway_types::persistence::{
-        PersistedOptionalReplicationStatus, PersistedReplicationDestination, PersistedReplicationFilter,
-        PersistedReplicationRule, PersistedReplicationStatus, PersistedReplicationTag, PersistedSourceSelectionCriteria,
+    use s3s::dto::{
+        DeleteMarkerReplication, DeleteMarkerReplicationStatus, DeleteReplication, DeleteReplicationStatus, Destination,
+        ReplicaModifications, ReplicationRule, ReplicationRuleFilter, ReplicationRuleStatus, SourceSelectionCriteria, Tag,
     };
 
     use super::super::replication_filemeta_boundary::VersionPurgeStatusType;
     use super::super::replication_target_boundary::BucketTarget;
     use super::*;
 
-    fn replication_rule() -> PersistedReplicationRule {
-        PersistedReplicationRule {
+    fn replication_rule() -> ReplicationRule {
+        ReplicationRule {
             delete_marker_replication: None,
             delete_replication: None,
-            destination: PersistedReplicationDestination {
+            destination: Destination {
                 bucket: "arn:aws:s3:::target-bucket".to_string(),
                 ..Default::default()
             },
@@ -626,7 +620,7 @@ mod tests {
             prefix: Some(String::new()),
             priority: Some(1),
             source_selection_criteria: None,
-            status: Status::ENABLED.to_string(),
+            status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
         }
     }
 
@@ -635,11 +629,11 @@ mod tests {
         let arn = "arn:rustfs:replication:us-east-1:target:bucket";
         let mut rule = replication_rule();
         rule.destination.bucket = arn.to_string();
-        rule.filter = Some(PersistedReplicationFilter {
+        rule.filter = Some(ReplicationRuleFilter {
             prefix: Some("admitted/".to_string()),
             ..Default::default()
         });
-        let cfg = PersistedReplicationConfiguration {
+        let cfg = ReplicationConfiguration {
             role: String::new(),
             rules: vec![rule],
         };
@@ -677,7 +671,7 @@ mod tests {
         assert!(!empty.replicate(&ObjectOpts::default()));
 
         let config = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
                 rules: vec![replication_rule()],
             }),
@@ -731,7 +725,7 @@ mod tests {
     fn delete_snapshot_rejects_enabled_rules_without_a_destination() {
         let mut rule = replication_rule();
         rule.destination.bucket.clear();
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: String::new(),
             rules: vec![rule],
         };
@@ -747,7 +741,7 @@ mod tests {
         let first = replication_rule();
         let mut second = replication_rule();
         second.destination.bucket = "arn:aws:s3:::other-target".to_string();
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: "arn:aws:s3:::role-target".to_string(),
             rules: vec![first, second],
         };
@@ -758,47 +752,47 @@ mod tests {
     #[test]
     fn delete_snapshot_rejects_unknown_status_values() {
         let invalid_versioning = VersioningConfiguration {
-            status: Some("Enabld".to_string()),
+            status: Some("Enabld".to_string().into()),
             ..Default::default()
         };
         assert!(validate_delete_replication_config(&invalid_versioning, None).is_err());
 
         let mut invalid_rule = replication_rule();
-        invalid_rule.status = "Enabld".to_string();
-        let config = PersistedReplicationConfiguration {
+        invalid_rule.status = "Enabld".to_string().into();
+        let config = ReplicationConfiguration {
             role: String::new(),
             rules: vec![invalid_rule],
         };
         assert!(validate_delete_replication_config(&VersioningConfiguration::default(), Some(&config)).is_err());
 
         let mut invalid_delete = replication_rule();
-        invalid_delete.delete_replication = Some(PersistedReplicationStatus {
-            status: "Enabld".to_string(),
+        invalid_delete.delete_replication = Some(DeleteReplication {
+            status: "Enabld".to_string().into(),
         });
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: String::new(),
             rules: vec![invalid_delete],
         };
         assert!(validate_delete_replication_config(&VersioningConfiguration::default(), Some(&config)).is_err());
 
         let mut invalid_delete_marker = replication_rule();
-        invalid_delete_marker.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some("Enabld".to_string()),
+        invalid_delete_marker.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some("Enabld".to_string().into()),
         });
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: String::new(),
             rules: vec![invalid_delete_marker],
         };
         assert!(validate_delete_replication_config(&VersioningConfiguration::default(), Some(&config)).is_err());
 
         let mut invalid_replica_modifications = replication_rule();
-        invalid_replica_modifications.source_selection_criteria = Some(PersistedSourceSelectionCriteria {
-            replica_modifications: Some(PersistedReplicationStatus {
-                status: "Enabld".to_string(),
+        invalid_replica_modifications.source_selection_criteria = Some(SourceSelectionCriteria {
+            replica_modifications: Some(ReplicaModifications {
+                status: "Enabld".to_string().into(),
             }),
             sse_kms_encrypted_objects: None,
         });
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: String::new(),
             rules: vec![invalid_replica_modifications],
         };
@@ -810,11 +804,11 @@ mod tests {
         let mut metadata = BucketMetadata::new("bucket");
         metadata.versioning_config_xml = b"configured".to_vec();
         metadata.versioning_config = Some(VersioningConfiguration {
-            status: Some("Enabled".to_owned()),
+            status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
             ..Default::default()
         });
         metadata.replication_config_xml = b"configured".to_vec();
-        metadata.replication_config = Some(PersistedReplicationConfiguration {
+        metadata.replication_config = Some(ReplicationConfiguration {
             role: String::new(),
             rules: vec![replication_rule()],
         });
@@ -854,7 +848,7 @@ mod tests {
         );
 
         let mut inconsistent = BucketMetadata::new("bucket");
-        inconsistent.replication_config = Some(PersistedReplicationConfiguration {
+        inconsistent.replication_config = Some(ReplicationConfiguration {
             role: String::new(),
             rules: vec![replication_rule()],
         });
@@ -869,11 +863,11 @@ mod tests {
         let arn = "arn:rustfs:replication:us-east-1:target:bucket";
         let mut rule = replication_rule();
         rule.destination.bucket = arn.to_string();
-        rule.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some(Status::ENABLED.to_string()),
+        rule.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some(DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::ENABLED)),
         });
         let mut metadata = BucketMetadata::new("bucket");
-        metadata.replication_config = Some(PersistedReplicationConfiguration {
+        metadata.replication_config = Some(ReplicationConfiguration {
             role: String::new(),
             rules: vec![rule],
         });
@@ -904,27 +898,27 @@ mod tests {
     fn delete_marker_source_read_is_required_only_for_tag_filtered_rules() {
         let mut prefix_rule = replication_rule();
         prefix_rule.prefix = Some("logs/".to_string());
-        prefix_rule.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some(Status::ENABLED.to_string()),
+        prefix_rule.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some(DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::ENABLED)),
         });
 
         let prefix_snapshot = DeleteReplicationConfigSnapshot::from_configs_for_test(
             VersioningConfiguration {
-                status: Some("Enabled".to_owned()),
+                status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
                 ..Default::default()
             },
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
                 rules: vec![prefix_rule],
             }),
         );
 
         let mut tag_rule = replication_rule();
-        tag_rule.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some(Status::ENABLED.to_string()),
+        tag_rule.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some(DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::ENABLED)),
         });
-        tag_rule.filter = Some(PersistedReplicationFilter {
-            tag: Some(PersistedReplicationTag {
+        tag_rule.filter = Some(ReplicationRuleFilter {
+            tag: Some(Tag {
                 key: Some("class".to_string()),
                 value: Some("audit".to_string()),
             }),
@@ -932,10 +926,10 @@ mod tests {
         });
         let tag_snapshot = DeleteReplicationConfigSnapshot::from_configs_for_test(
             VersioningConfiguration {
-                status: Some("Enabled".to_owned()),
+                status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
                 ..Default::default()
             },
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
                 rules: vec![tag_rule],
             }),
@@ -950,14 +944,14 @@ mod tests {
         let arn = "arn:rustfs:replication:us-east-1:target:bucket";
         let mut rule = replication_rule();
         rule.destination.bucket = arn.to_string();
-        rule.delete_replication = Some(PersistedReplicationStatus {
-            status: Status::ENABLED.to_string(),
+        rule.delete_replication = Some(DeleteReplication {
+            status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED),
         });
-        rule.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some(Status::DISABLED.to_string()),
+        rule.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some(DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::DISABLED)),
         });
         let config = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
                 rules: vec![rule],
             }),
@@ -991,22 +985,22 @@ mod tests {
     #[test]
     fn live_delete_does_not_trust_persisted_replica_status() {
         let mut rule = replication_rule();
-        rule.delete_replication = Some(PersistedReplicationStatus {
-            status: Status::ENABLED.to_string(),
+        rule.delete_replication = Some(DeleteReplication {
+            status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED),
         });
-        rule.source_selection_criteria = Some(PersistedSourceSelectionCriteria {
-            replica_modifications: Some(PersistedReplicationStatus {
-                status: Status::DISABLED.to_string(),
+        rule.source_selection_criteria = Some(SourceSelectionCriteria {
+            replica_modifications: Some(ReplicaModifications {
+                status: s3s::dto::ReplicaModificationsStatus::from_static(s3s::dto::ReplicaModificationsStatus::DISABLED),
             }),
             sse_kms_encrypted_objects: None,
         });
-        let replication = PersistedReplicationConfiguration {
+        let replication = ReplicationConfiguration {
             role: String::new(),
             rules: vec![rule],
         };
         let snapshot = DeleteReplicationConfigSnapshot::from_configs_for_test(
             VersioningConfiguration {
-                status: Some("Enabled".to_owned()),
+                status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
                 ..Default::default()
             },
             Some(replication.clone()),
@@ -1042,14 +1036,14 @@ mod tests {
         let arn = "arn:rustfs:replication:us-east-1:target:bucket";
         let mut rule = replication_rule();
         rule.destination.bucket = arn.to_string();
-        rule.delete_replication = Some(PersistedReplicationStatus {
-            status: Status::ENABLED.to_string(),
+        rule.delete_replication = Some(DeleteReplication {
+            status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED),
         });
-        rule.delete_marker_replication = Some(PersistedOptionalReplicationStatus {
-            status: Some(Status::DISABLED.to_string()),
+        rule.delete_marker_replication = Some(DeleteMarkerReplication {
+            status: Some(DeleteMarkerReplicationStatus::from_static(DeleteMarkerReplicationStatus::DISABLED)),
         });
         let config = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
                 rules: vec![rule],
             }),

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

@@ -4794,10 +4794,9 @@ mod tests {
     #[tokio::test]
     async fn heal_queue_marks_missing_versioning_state_as_missed() {
         use super::super::replication_target_boundary::BucketTargets;
-        use rustfs_gateway_types::dto::Status;
-        use rustfs_gateway_types::persistence::{
-            PersistedReplicationConfiguration, PersistedReplicationDestination, PersistedReplicationRule,
-            PersistedReplicationStatus,
+        use s3s::dto::{
+            DeleteReplication, DeleteReplicationStatus, Destination, ReplicationConfiguration, ReplicationRule,
+            ReplicationRuleStatus,
         };
 
         let arn = "arn:rustfs:replication:us-east-1:target:bucket";
@@ -4812,14 +4811,14 @@ mod tests {
                 ..Default::default()
             },
             ReplicationConfig::new(
-                Some(PersistedReplicationConfiguration {
+                Some(ReplicationConfiguration {
                     role: String::new(),
-                    rules: vec![PersistedReplicationRule {
+                    rules: vec![ReplicationRule {
                         delete_marker_replication: None,
-                        delete_replication: Some(PersistedReplicationStatus {
-                            status: Status::ENABLED.to_string(),
+                        delete_replication: Some(DeleteReplication {
+                            status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED),
                         }),
-                        destination: PersistedReplicationDestination {
+                        destination: Destination {
                             bucket: arn.to_string(),
                             ..Default::default()
                         },
@@ -4829,7 +4828,7 @@ mod tests {
                         prefix: Some(String::new()),
                         priority: Some(1),
                         source_selection_criteria: None,
-                        status: Status::ENABLED.to_string(),
+                        status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
                     }],
                 }),
                 Some(BucketTargets::default()),

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

@@ -85,8 +85,6 @@ use http_body_util::StreamBody;
 use metrics::counter;
 #[cfg(test)]
 use rmp_serde;
-#[cfg(test)]
-use rustfs_gateway_types::persistence::PersistedReplicationConfiguration;
 use rustfs_s3_types::EventName;
 use rustfs_utils::http::{
     AMZ_OBJECT_LOCK_LEGAL_HOLD, AMZ_OBJECT_LOCK_MODE, AMZ_OBJECT_LOCK_RETAIN_UNTIL_DATE, AMZ_TAGGING_DIRECTIVE,
@@ -94,6 +92,8 @@ use rustfs_utils::http::{
     insert_str, replication_target_versions,
 };
 use rustfs_utils::{DEFAULT_SIP_HASH_KEY, get_env_usize, sip_hash};
+#[cfg(test)]
+use s3s::dto::ReplicationConfiguration;
 use std::collections::{HashMap, HashSet};
 use std::fmt::Display;
 use std::pin::Pin;
@@ -6574,10 +6574,9 @@ mod tests {
 
     use super::super::replication_target_boundary::{BucketTarget, BucketTargets};
     use super::*;
-    use rustfs_gateway_types::dto::Status;
-    use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
-    use rustfs_gateway_types::persistence::{
-        PersistedReplicationDestination, PersistedReplicationRule, PersistedReplicationStatus,
+    use s3s::dto::{
+        BucketVersioningStatus, DeleteReplication, DeleteReplicationStatus, Destination, ExcludedPrefix, ReplicationRule,
+        ReplicationRuleStatus, VersioningConfiguration,
     };
     use std::collections::HashMap;
     use time::OffsetDateTime;
@@ -8688,7 +8687,7 @@ mod tests {
             ..Default::default()
         };
         let rcfg = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: role.to_string(),
                 rules: vec![],
             }),
@@ -8714,7 +8713,7 @@ mod tests {
         ReplicationVersioningStore::install_prefix_state_test_config(
             &bucket,
             VersioningConfiguration {
-                status: Some("Enabled".to_owned()),
+                status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
                 ..Default::default()
             },
         );
@@ -8747,20 +8746,22 @@ mod tests {
         ReplicationVersioningStore::install_prefix_state_test_config(
             &bucket,
             VersioningConfiguration {
-                status: Some("Enabled".to_owned()),
-                excluded_prefixes: Some(vec![Some("archive/".to_string())]),
+                status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
+                excluded_prefixes: Some(vec![ExcludedPrefix {
+                    prefix: Some("archive/".to_string()),
+                }]),
                 ..Default::default()
             },
         );
         let rcfg = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
-                rules: vec![PersistedReplicationRule {
+                rules: vec![ReplicationRule {
                     delete_marker_replication: None,
-                    delete_replication: Some(PersistedReplicationStatus {
-                        status: Status::ENABLED.to_string(),
+                    delete_replication: Some(DeleteReplication {
+                        status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::ENABLED),
                     }),
-                    destination: PersistedReplicationDestination {
+                    destination: Destination {
                         bucket: arn.to_string(),
                         ..Default::default()
                     },
@@ -8770,7 +8771,7 @@ mod tests {
                     prefix: Some(String::new()),
                     priority: Some(1),
                     source_selection_criteria: None,
-                    status: Status::ENABLED.to_string(),
+                    status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
                 }],
             }),
             Some(BucketTargets {
@@ -8806,14 +8807,14 @@ mod tests {
         let admitted_arn = "arn:rustfs:replication:us-east-1:target:admitted";
         let current_role = "arn:rustfs:replication:us-east-1:target:current";
         let rcfg = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: current_role.to_string(),
-                rules: vec![PersistedReplicationRule {
+                rules: vec![ReplicationRule {
                     delete_marker_replication: None,
-                    delete_replication: Some(PersistedReplicationStatus {
-                        status: Status::DISABLED.to_string(),
+                    delete_replication: Some(DeleteReplication {
+                        status: DeleteReplicationStatus::from_static(DeleteReplicationStatus::DISABLED),
                     }),
-                    destination: PersistedReplicationDestination {
+                    destination: Destination {
                         bucket: current_role.to_string(),
                         ..Default::default()
                     },
@@ -8823,7 +8824,7 @@ mod tests {
                     prefix: Some(String::new()),
                     priority: Some(1),
                     source_selection_criteria: None,
-                    status: Status::ENABLED.to_string(),
+                    status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
                 }],
             }),
             Some(BucketTargets {
@@ -8871,12 +8872,12 @@ mod tests {
     #[tokio::test]
     async fn heal_rejects_semantically_invalid_replication_config() {
         let rcfg = ReplicationConfig::new(
-            Some(PersistedReplicationConfiguration {
+            Some(ReplicationConfiguration {
                 role: String::new(),
-                rules: vec![PersistedReplicationRule {
+                rules: vec![ReplicationRule {
                     delete_marker_replication: None,
                     delete_replication: None,
-                    destination: PersistedReplicationDestination {
+                    destination: Destination {
                         bucket: "arn:rustfs:replication:us-east-1:target:bucket".to_string(),
                         ..Default::default()
                     },
@@ -8886,7 +8887,7 @@ mod tests {
                     prefix: Some(String::new()),
                     priority: Some(1),
                     source_selection_criteria: None,
-                    status: "Enabld".to_owned(),
+                    status: ReplicationRuleStatus::from_static("Enabld"),
                 }],
             }),
             Some(BucketTargets::default()),

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

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use rustfs_gateway_types::persistence::PersistedReplicationConfiguration;
+use s3s::dto::ReplicationConfiguration;
 
 use super::replication_config_boundary::{ObjectOpts, ReplicationConfigurationExt};
 use super::replication_filemeta_boundary::ReplicationType;
@@ -20,7 +20,7 @@ use super::replication_filemeta_boundary::ReplicationType;
 pub(crate) struct ReplicationTargetConfigBridge;
 
 impl ReplicationTargetConfigBridge {
-    pub(crate) fn target_is_used_by_rules(config: &PersistedReplicationConfiguration, arn: &str) -> bool {
+    pub(crate) fn target_is_used_by_rules(config: &ReplicationConfiguration, arn: &str) -> bool {
         config
             .filter_target_arns(&ObjectOpts {
                 op_type: ReplicationType::All,
@@ -37,7 +37,7 @@ mod tests {
 
     #[test]
     fn target_config_bridge_matches_role_target() {
-        let config = PersistedReplicationConfiguration {
+        let config = ReplicationConfiguration {
             role: " arn:target ".to_string(),
             rules: Vec::new(),
         };

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

@@ -15,7 +15,7 @@
 use super::replication_error_boundary::Result;
 use crate::bucket::{versioning::VersioningApi as _, versioning_sys::BucketVersioningSys};
 #[cfg(test)]
-use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
+use s3s::dto::VersioningConfiguration;
 #[cfg(test)]
 use std::{collections::HashMap, sync::LazyLock, sync::Mutex};
 

crates/ecstore/src/bucket/tagging/mod.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use rustfs_gateway_types::cors_tagging::PersistedTag as Tag;
+use s3s::dto::Tag;
 use std::cmp::Ordering;
 use std::collections::HashMap;
 use url::form_urlencoded;

crates/ecstore/src/bucket/utils.rs

@@ -15,23 +15,9 @@
 use crate::disk::{MIGRATING_META_BUCKET, RUSTFS_META_BUCKET};
 use crate::error::{Error, Result, StorageError};
 use regex::Regex;
-use rustfs_gateway_types::cors_tagging::{
-    CorsTaggingCodecError, PersistedCorsConfiguration, PersistedTagging, parse_cors, parse_tagging, serialize_cors,
-    serialize_tagging,
-};
-use rustfs_gateway_types::persistence::{
-    PersistedAccelerateConfiguration, PersistedBucketEncryptionConfiguration, PersistedBucketLoggingStatus,
-    PersistedLifecycleConfiguration, PersistedNotificationConfiguration, PersistedObjectLockConfiguration,
-    PersistedPublicAccessBlockConfiguration, PersistedReplicationConfiguration, PersistedRequestPaymentConfiguration,
-    PersistedVersioningConfiguration, PersistedWebsiteConfiguration, PersistenceCodecError, parse_accelerate,
-    parse_bucket_encryption, parse_bucket_logging, parse_lifecycle_legacy_dates, parse_notification, parse_object_lock,
-    parse_public_access_block, parse_replication, parse_request_payment, parse_versioning, parse_website, serialize_accelerate,
-    serialize_bucket_encryption, serialize_bucket_logging, serialize_lifecycle_legacy_dates, serialize_notification,
-    serialize_object_lock, serialize_public_access_block, serialize_replication, serialize_request_payment, serialize_versioning,
-    serialize_website,
-};
 use rustfs_utils::WindowsFileNameError;
 use rustfs_utils::path::SLASH_SEPARATOR;
+use s3s::xml;
 use tracing::instrument;
 
 pub fn is_meta_bucketname(name: &str) -> bool {
@@ -88,173 +74,37 @@ pub fn check_valid_bucket_name_strict(bucket_name: &str) -> Result<()> {
     check_bucket_name_common(bucket_name, true)
 }
 
-/// A bucket configuration persisted as XML in the bucket metadata, together
-/// with the codec that reads and writes its stored bytes.
-///
-/// Every family reads and writes its stored bytes through the gateway
-/// persistence codecs (`rustfs_gateway_types::persistence` and
-/// `rustfs_gateway_types::cors_tagging`, rustfs/backlog#2745). The codecs keep
-/// the persisted bytes the `bucket_config_goldens` pin, so a document the old
-/// s3s codec wrote reads back and re-encodes unchanged.
-pub trait BucketConfigXml: Sized {
-    /// Decodes the stored bytes of one configuration document.
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError>;
-
-    /// Encodes the value as RustFS stores it.
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError>;
+// RUSTFS_COMPAT_TODO(s3gate-metadata-xml): the s3s codec reads persisted XML during migration. Remove after every supported writer uses the gateway codec and every retained metadata object and backup archive is verified or rewritten.
+pub fn deserialize<T>(input: &[u8]) -> xml::DeResult<T>
+where
+    T: for<'xml> xml::Deserialize<'xml>,
+{
+    let mut d = xml::Deserializer::new(input);
+    let ans = T::deserialize(&mut d)?;
+    d.expect_eof()?;
+    Ok(ans)
 }
 
-/// Why a persisted bucket configuration could not be decoded or encoded.
-#[derive(Debug, thiserror::Error)]
-pub enum BucketConfigXmlError {
-    /// A gateway persistence codec refused the bytes or the value.
-    #[error(transparent)]
-    Persisted(#[from] PersistenceCodecError),
-    /// The gateway CORS or Tagging codec refused the bytes or the value.
-    #[error(transparent)]
-    CorsTagging(#[from] CorsTaggingCodecError),
+#[allow(
+    dead_code,
+    reason = "xml serialize helper with no caller in this port; the live sibling is deserialize (backlog#1823)"
+)]
+pub fn serialize_content<T: xml::SerializeContent>(val: &T) -> xml::SerResult<String> {
+    let mut buf = Vec::with_capacity(256);
+    {
+        let mut ser = xml::Serializer::new(&mut buf);
+        val.serialize_content(&mut ser)?;
+    }
+    Ok(String::from_utf8(buf).unwrap())
 }
 
-/// Decodes one persisted bucket configuration document.
-pub fn deserialize<T: BucketConfigXml>(input: &[u8]) -> std::result::Result<T, BucketConfigXmlError> {
-    T::decode_config_xml(input)
-}
-
-/// Encodes one bucket configuration as RustFS persists it.
-pub fn serialize<T: BucketConfigXml>(val: &T) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-    val.encode_config_xml()
-}
-
-impl BucketConfigXml for PersistedReplicationConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_replication(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_replication(self)?)
-    }
-}
-
-impl BucketConfigXml for PersistedLifecycleConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_lifecycle_legacy_dates(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_lifecycle_legacy_dates(self)?)
-    }
-}
-
-// The gateway writers of these families are infallible: a value that exists is
-// always encodable, so only the readers can refuse bytes.
-impl BucketConfigXml for PersistedAccelerateConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_accelerate(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_accelerate(self))
-    }
-}
-
-impl BucketConfigXml for PersistedBucketLoggingStatus {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_bucket_logging(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_bucket_logging(self))
-    }
-}
-
-impl BucketConfigXml for PersistedCorsConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_cors(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_cors(self))
-    }
-}
-
-impl BucketConfigXml for PersistedNotificationConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_notification(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_notification(self))
-    }
-}
-
-impl BucketConfigXml for PersistedObjectLockConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_object_lock(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_object_lock(self))
-    }
-}
-
-impl BucketConfigXml for PersistedPublicAccessBlockConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_public_access_block(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_public_access_block(self))
-    }
-}
-
-impl BucketConfigXml for PersistedRequestPaymentConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_request_payment(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_request_payment(self))
-    }
-}
-
-impl BucketConfigXml for PersistedBucketEncryptionConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_bucket_encryption(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_bucket_encryption(self))
-    }
-}
-
-impl BucketConfigXml for PersistedTagging {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_tagging(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_tagging(self))
-    }
-}
-
-impl BucketConfigXml for PersistedVersioningConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_versioning(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_versioning(self))
-    }
-}
-
-impl BucketConfigXml for PersistedWebsiteConfiguration {
-    fn decode_config_xml(input: &[u8]) -> std::result::Result<Self, BucketConfigXmlError> {
-        Ok(parse_website(input)?)
-    }
-
-    fn encode_config_xml(&self) -> std::result::Result<Vec<u8>, BucketConfigXmlError> {
-        Ok(serialize_website(self))
+pub fn serialize<T: xml::Serialize>(val: &T) -> xml::SerResult<Vec<u8>> {
+    let mut buf = Vec::with_capacity(256);
+    {
+        let mut ser = xml::Serializer::new(&mut buf);
+        val.serialize(&mut ser)?;
     }
+    Ok(buf)
 }
 
 pub fn has_bad_path_component(path: &str) -> bool {
@@ -584,40 +434,6 @@ mod tests {
     use super::*;
     use proptest::prelude::*;
 
-    /// Every bucket-configuration family reads and writes through its own
-    /// gateway codec (rustfs/backlog#2745): the family's golden document
-    /// decodes and re-encodes to the same bytes, and a document of another
-    /// family is refused instead of decoding into an empty configuration.
-    #[test]
-    fn every_bucket_config_family_uses_its_own_gateway_codec() {
-        fn assert_family<T: BucketConfigXml>(family: &str, own: &[u8], foreign: &[u8]) {
-            let value = deserialize::<T>(own).unwrap_or_else(|err| panic!("{family}: own document must decode: {err}"));
-            let encoded = serialize(&value).unwrap_or_else(|err| panic!("{family}: value must encode: {err}"));
-            assert_eq!(encoded, own, "{family}: re-encoding must keep the persisted bytes");
-            assert!(deserialize::<T>(foreign).is_err(), "{family}: a foreign root element must be refused");
-        }
-
-        macro_rules! golden {
-            ($family:literal) => {
-                include_bytes!(concat!("../../tests/fixtures/bucket-config-goldens/", $family, "/minio.out.xml"))
-            };
-        }
-        let tagging = golden!("tagging");
-        let versioning = golden!("versioning");
-
-        assert_family::<PersistedAccelerateConfiguration>("accelerate", golden!("accelerate"), tagging);
-        assert_family::<PersistedBucketLoggingStatus>("logging", golden!("logging"), tagging);
-        assert_family::<PersistedCorsConfiguration>("cors", golden!("cors"), tagging);
-        assert_family::<PersistedNotificationConfiguration>("notification", golden!("notification"), tagging);
-        assert_family::<PersistedObjectLockConfiguration>("object_lock", golden!("object_lock"), tagging);
-        assert_family::<PersistedPublicAccessBlockConfiguration>("public_access_block", golden!("public_access_block"), tagging);
-        assert_family::<PersistedRequestPaymentConfiguration>("request_payment", golden!("request_payment"), tagging);
-        assert_family::<PersistedBucketEncryptionConfiguration>("encryption", golden!("encryption"), tagging);
-        assert_family::<PersistedTagging>("tagging", tagging, versioning);
-        assert_family::<PersistedVersioningConfiguration>("versioning", versioning, tagging);
-        assert_family::<PersistedWebsiteConfiguration>("website", golden!("website"), tagging);
-    }
-
     /// rustfs#5785: keys whose path segments exceed the on-disk NAME_MAX
     /// budget must be rejected up front as ObjectNameInvalid (4xx), not leak
     /// ENAMETOOLONG as InternalError 500 from the disk layer.

crates/ecstore/src/bucket/versioning/mod.rs

@@ -12,8 +12,8 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
 use rustfs_utils::string::match_simple;
+use s3s::dto::{BucketVersioningStatus, VersioningConfiguration};
 
 pub trait VersioningApi {
     fn enabled(&self) -> bool;
@@ -28,10 +28,10 @@ pub trait VersioningApi {
 
 impl VersioningApi for VersioningConfiguration {
     fn enabled(&self) -> bool {
-        self.status.as_deref() == Some("Enabled")
+        self.status == Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED))
     }
     fn prefix_enabled(&self, prefix: &str) -> bool {
-        if self.status.as_deref() != Some("Enabled") {
+        if self.status != Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)) {
             return false;
         }
 
@@ -44,10 +44,12 @@ impl VersioningApi for VersioningConfiguration {
         }
 
         if let Some(ref excluded_prefixes) = self.excluded_prefixes {
-            for sprefix in excluded_prefixes.iter().flatten() {
-                let pattern = format!("{sprefix}*");
-                if match_simple(&pattern, prefix) {
-                    return false;
+            for p in excluded_prefixes.iter() {
+                if let Some(ref sprefix) = p.prefix {
+                    let pattern = format!("{sprefix}*");
+                    if match_simple(&pattern, prefix) {
+                        return false;
+                    }
                 }
             }
         }
@@ -56,11 +58,11 @@ impl VersioningApi for VersioningConfiguration {
     }
 
     fn prefix_suspended(&self, prefix: &str) -> bool {
-        if self.status.as_deref() == Some("Suspended") {
+        if self.status == Some(BucketVersioningStatus::from_static(BucketVersioningStatus::SUSPENDED)) {
             return true;
         }
 
-        if self.status.as_deref() == Some("Enabled") {
+        if self.status == Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)) {
             if prefix.is_empty() {
                 return false;
             }
@@ -73,10 +75,12 @@ impl VersioningApi for VersioningConfiguration {
             }
 
             if let Some(ref excluded_prefixes) = self.excluded_prefixes {
-                for sprefix in excluded_prefixes.iter().flatten() {
-                    let pattern = format!("{sprefix}*");
-                    if match_simple(&pattern, prefix) {
-                        return true;
+                for p in excluded_prefixes.iter() {
+                    if let Some(ref sprefix) = p.prefix {
+                        let pattern = format!("{sprefix}*");
+                        if match_simple(&pattern, prefix) {
+                            return true;
+                        }
                     }
                 }
             }
@@ -88,12 +92,14 @@ impl VersioningApi for VersioningConfiguration {
         self.prefix_enabled(prefix) || self.prefix_suspended(prefix)
     }
     fn suspended(&self) -> bool {
-        self.status.as_deref() == Some("Suspended")
+        self.status == Some(BucketVersioningStatus::from_static(BucketVersioningStatus::SUSPENDED))
     }
 }
 
 #[cfg(test)]
 mod tests {
+    use s3s::dto::{BucketVersioningStatus, ExcludedPrefix};
+
     use super::*;
 
     struct LegacyVersioning;
@@ -128,8 +134,10 @@ mod tests {
     #[test]
     fn delete_state_treats_excluded_prefixes_as_unversioned() {
         let config = VersioningConfiguration {
-            status: Some("Enabled".to_owned()),
-            excluded_prefixes: Some(vec![Some("archive/".to_string())]),
+            status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::ENABLED)),
+            excluded_prefixes: Some(vec![ExcludedPrefix {
+                prefix: Some("archive/".to_string()),
+            }]),
             ..Default::default()
         };
 
@@ -138,7 +146,7 @@ mod tests {
         assert_eq!(config.delete_state("live/object"), (true, false));
 
         let suspended = VersioningConfiguration {
-            status: Some("Suspended".to_owned()),
+            status: Some(BucketVersioningStatus::from_static(BucketVersioningStatus::SUSPENDED)),
             ..Default::default()
         };
         assert_eq!(suspended.delete_state("archive/object"), (false, true));

crates/ecstore/src/bucket/versioning_sys.rs

@@ -17,7 +17,7 @@ use super::metadata::unreadable_config_refusal;
 use super::{metadata_sys::get_bucket_metadata_sys, versioning::VersioningApi};
 use crate::disk::RUSTFS_META_BUCKET;
 use crate::error::Result;
-use rustfs_gateway_types::persistence::PersistedVersioningConfiguration as VersioningConfiguration;
+use s3s::dto::VersioningConfiguration;
 use tracing::{error, warn};
 
 pub struct BucketVersioningSys {}
@@ -163,7 +163,7 @@ mod tests {
 
     fn enabled() -> VersioningConfiguration {
         VersioningConfiguration {
-            status: Some("Enabled".to_owned()),
+            status: Some(s3s::dto::BucketVersioningStatus::from_static(s3s::dto::BucketVersioningStatus::ENABLED)),
             ..Default::default()
         }
     }

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

@@ -0,0 +1,682 @@
+// 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

@@ -0,0 +1,586 @@
+// 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, internode_rpc_body_digest_strict,
-    verify_tonic_peer_replay_capabilities_response,
+    RollingMutationBodyDigest, TIMESTAMP_HEADER, gen_tonic_replay_scope_headers_with_admission, internode_rpc_body_digest_strict,
+    rpc_background_admission, verify_tonic_peer_replay_capabilities_response,
 };
-use crate::cluster::rpc::{gen_tonic_replay_scope_headers, gen_tonic_signature_headers, normalize_tonic_rpc_audience};
+use crate::cluster::rpc::{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};
@@ -415,7 +415,16 @@ where
                     .get(RPC_CONTENT_SHA256_HEADER)
                     .and_then(|value| value.to_str().ok()),
             ) {
-                match gen_tonic_replay_scope_headers(audience, request.uri().path(), timestamp, content_sha256, boot_epoch) {
+                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,
+                    )
+                }) {
                     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

@@ -61,6 +61,9 @@ 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";
@@ -77,6 +80,46 @@ 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";
@@ -519,21 +562,23 @@ 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) -> String {
+fn generate_signature(secret: &str, url: &str, method: &Method, timestamp: i64, background: bool) -> 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) -> bool {
+fn verify_signature(secret: &str, url: &str, method: &Method, timestamp: i64, signature: &str, background: bool) -> 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()
 }
@@ -771,6 +816,7 @@ 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,
@@ -780,6 +826,7 @@ 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(),
@@ -818,6 +865,7 @@ 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,
@@ -827,6 +875,7 @@ 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(),
@@ -970,6 +1019,24 @@ 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"));
@@ -983,6 +1050,7 @@ pub fn gen_tonic_replay_scope_headers(
     let signature = generate_replay_scope_signature(
         &get_shared_secret()?,
         ReplayScope {
+            background,
             audience,
             path,
             timestamp,
@@ -992,6 +1060,7 @@ pub fn gen_tonic_replay_scope_headers(
         },
     )?;
     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,
@@ -1226,10 +1295,12 @@ 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);
+    let signature = generate_signature(&secret, url, method, timestamp, background);
 
     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,
@@ -1264,10 +1335,12 @@ 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 legacy_signature = generate_signature(&secret, TONIC_RPC_PREFIX, &Method::GET, timestamp);
+    let background = current_rpc_background_request();
+    let legacy_signature = generate_signature(&secret, TONIC_RPC_PREFIX, &Method::GET, timestamp, background);
     let signature_v2 = generate_signature_v2(
         &secret,
         SignatureV2Scope {
+            background,
             audience,
             service,
             rpc_method,
@@ -1278,6 +1351,7 @@ 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));
@@ -1501,6 +1575,7 @@ 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,
@@ -1625,6 +1700,9 @@ 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 {
@@ -1696,6 +1774,7 @@ fn verify_tonic_rpc_signature_with_strictness(
     if !verify_signature_v2(
         &secret,
         SignatureV2Scope {
+            background: rpc_background_admission(headers)?,
             audience,
             service,
             rpc_method,
@@ -1736,7 +1815,7 @@ 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) {
+    if !verify_signature(&secret, url, method, timestamp, signature, rpc_background_admission(headers)?) {
         let rpc_path = redacted_rpc_path(url);
         error!(
             rpc_path = %rpc_path,
@@ -1828,6 +1907,98 @@ 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";
@@ -1965,8 +2136,8 @@ mod tests {
         let method = Method::GET;
         let timestamp = 1640995200; // Fixed timestamp
 
-        let signature1 = generate_signature(secret, url, &method, timestamp);
-        let signature2 = generate_signature(secret, url, &method, timestamp);
+        let signature1 = generate_signature(secret, url, &method, timestamp, false);
+        let signature2 = generate_signature(secret, url, &method, timestamp, false);
 
         assert_eq!(signature1, signature2, "Same inputs should produce same signature");
         assert!(!signature1.is_empty(), "Signature should not be empty");
@@ -1979,10 +2150,10 @@ mod tests {
         let method = Method::GET;
         let timestamp = 1640995200;
 
-        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);
+        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);
 
         assert_ne!(signature1, signature2, "Different URLs should produce different signatures");
         assert_ne!(signature1, signature3, "Different methods should produce different signatures");
@@ -2088,14 +2259,14 @@ mod tests {
         let url = "http://example.com/api/test";
         let method = Method::GET;
         let timestamp = 1640995200;
-        let signature = generate_signature(secret, url, &method, timestamp);
+        let signature = generate_signature(secret, url, &method, timestamp, false);
         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));
-        assert!(!verify_signature(secret, url, &method, timestamp, &tampered_signature));
-        assert!(!verify_signature(secret, url, &method, timestamp, "invalid-signature"));
+        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));
     }
 
     #[test]
@@ -2112,11 +2283,11 @@ mod tests {
         );
         let method = Method::GET;
         let timestamp = 1_640_995_200;
-        let signature = generate_signature(secret, signed_url, &method, timestamp);
+        let signature = generate_signature(secret, signed_url, &method, timestamp, 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));
+        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));
     }
 
     #[test]
@@ -2126,7 +2297,7 @@ 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);
+        let expected_signature = generate_signature(&secret, url, &method, timestamp, false);
         let invalid_signature = "invalid-signature";
         let logs = CapturedLogs::default();
         let subscriber = tracing_subscriber::fmt()
@@ -2164,7 +2335,7 @@ 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);
+        let signature = generate_signature(&secret, url, &method, expired_timestamp, false);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&expired_timestamp.to_string()).unwrap());
@@ -2186,7 +2357,7 @@ 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);
+        let signature = generate_signature(&secret, url, &method, future_timestamp, false);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&future_timestamp.to_string()).unwrap());
@@ -2300,7 +2471,7 @@ 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);
+        let signature = generate_signature(&secret, url, &method, valid_timestamp, false);
 
         headers.insert(SIGNATURE_HEADER, HeaderValue::from_str(&signature).unwrap());
         headers.insert(TIMESTAMP_HEADER, HeaderValue::from_str(&valid_timestamp.to_string()).unwrap());
@@ -2311,7 +2482,7 @@ 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);
+        let signature = generate_signature(&secret, url, &method, invalid_timestamp, false);
 
         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

@@ -33,7 +33,9 @@ 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};
+use rustfs_rio::{
+    ChunkReaderBox, HttpChunkReader, HttpReader, HttpWriter, HttpWriterMemoryReservation, HttpWriterMemoryReserver,
+};
 use sha2::{Digest, Sha256};
 use std::collections::HashMap;
 use std::future::Future;
@@ -66,6 +68,19 @@ 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: {}",
@@ -346,13 +361,17 @@ 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 = HttpWriter::new(url.clone(), Method::PUT, headers).await?;
+        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?,
+        };
         match auth_scope {
             Some((nonce, server_epoch)) => Ok(Box::new(PutFileAuthWriter::new(writer, url, nonce, endpoint, server_epoch))),
             None => Ok(Box::new(writer)),
@@ -948,6 +967,193 @@ 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

@@ -13,6 +13,8 @@
 // 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;
@@ -33,16 +35,17 @@ pub use client::{
 // Re-exported through `api::rpc`; not every item is consumed inside this crate.
 #[allow(unused_imports)]
 pub use http_auth::{
-    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,
+    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,
 };
 #[cfg(test)]
 pub(crate) use internode_data_transport::TcpHttpInternodeDataTransport;

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

@@ -1965,15 +1965,6 @@ impl PeerRestClient {
         Ok((self.topology_member.clone(), epoch))
     }
 
-    pub async fn probe_restore_copyback_capability(&self, topology_fingerprint: String) -> Result<(String, Uuid)> {
-        let probe = rustfs_protos::restore_copyback_capability_probe(Uuid::new_v4().as_bytes());
-        let result = self
-            .heal_control(rustfs_protos::HEAL_CONTROL_PROTOCOL_VERSION, topology_fingerprint, probe)
-            .await?;
-        let epoch = decode_remote_version_state_capability(&self.topology_member, &result)?;
-        Ok((self.topology_member.clone(), epoch))
-    }
-
     pub async fn probe_cross_pool_fence(&self, topology_fingerprint: String) -> Result<(String, u32, Uuid)> {
         let mut probe = rustfs_protos::CROSS_POOL_FENCE_CAPABILITY_PROBE_PREFIX.to_vec();
         probe.extend_from_slice(Uuid::new_v4().as_bytes());

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

@@ -17,6 +17,7 @@ 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,
@@ -570,6 +571,7 @@ struct RetryingRemoteReader {
     reader: Option<FileReader>,
     transport: Arc<dyn InternodeDataTransport>,
     request: ReadStreamRequest,
+    background: bool,
     emitted: usize,
     retried: bool,
     initial_read_timeout: Option<Duration>,
@@ -590,6 +592,7 @@ impl RetryingRemoteReader {
             reader: Some(reader),
             transport,
             request,
+            background: current_rpc_background_request(),
             emitted: 0,
             retried: false,
             initial_read_timeout,
@@ -607,9 +610,10 @@ 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(async move {
-            with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_fresh(request)).await
-        })));
+        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 },
+        ))));
         Ok(())
     }
 
@@ -717,6 +721,7 @@ struct RetryingRemoteChunkReader {
     reader: Option<rustfs_rio::ChunkReaderBox>,
     transport: Arc<dyn InternodeDataTransport>,
     request: ReadStreamRequest,
+    background: bool,
     emitted: usize,
     retried: bool,
     initial_read_timeout: Option<Duration>,
@@ -737,6 +742,7 @@ impl RetryingRemoteChunkReader {
             reader: Some(reader),
             transport,
             request,
+            background: current_rpc_background_request(),
             emitted: 0,
             retried: false,
             initial_read_timeout,
@@ -754,9 +760,10 @@ 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(async move {
-            with_remote_read_recovery_timeout(recovery_timeout, transport.open_read_chunks_fresh(request)).await
-        })));
+        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 },
+        ))));
         Ok(())
     }
 
@@ -7769,6 +7776,98 @@ 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/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(Bytes::from(writer.into_inline_data().expect("fixture writer should retain inline bytes")));
+        info.data = Some(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

@@ -84,13 +84,12 @@ use rand::RngExt as _;
 use rmp_serde::Deserializer;
 use rmp_serde::Serializer;
 use rustfs_filemeta::{FileInfo, FileInfoVersions, MetaCacheEntries, MetaCacheEntry, MetadataResolutionParams};
-use rustfs_gateway_types::persistence::PersistedObjectLockConfiguration as ObjectLockConfiguration;
-use rustfs_gateway_types::persistence::{PersistedLifecycleConfiguration, PersistedReplicationConfiguration};
 use rustfs_heal_contracts::heal_channel::HealOpts;
 use rustfs_utils::crypto::{hex_sha256, is_sha256_checksum};
 use rustfs_utils::path::{
     decode_dir_object, encode_dir_object, path_join, path_to_bucket_object, path_to_bucket_object_with_base_path,
 };
+use s3s::dto::{BucketLifecycleConfiguration, ObjectLockConfiguration, ReplicationConfiguration};
 use serde::{Deserialize, Serialize};
 use sha2::{Digest, Sha256};
 use std::collections::{HashMap, HashSet};
@@ -12884,7 +12883,7 @@ pub(crate) async fn should_skip_lifecycle_for_data_movement(
     store: Arc<ECStore>,
     bucket: &str,
     version: &rustfs_filemeta::FileInfo,
-    lifecycle_config: Option<&PersistedLifecycleConfiguration>,
+    lifecycle_config: Option<&BucketLifecycleConfiguration>,
     object_lock_config: Option<&ObjectLockConfiguration>,
     apply_actions: bool,
     event_source: &LcEventSrc,
@@ -16813,9 +16812,9 @@ impl ECStore {
         generation: OffsetDateTime,
         bucket: String,
         set: Arc<SetDisks>,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
         object_lock_config: Option<ObjectLockConfiguration>,
-        replication_config: Option<(PersistedReplicationConfiguration, OffsetDateTime)>,
+        replication_config: Option<(ReplicationConfiguration, OffsetDateTime)>,
         expected_bucket_incarnation_id: Option<uuid::Uuid>,
         source_changed_exhaustions: Arc<AtomicUsize>,
         entry_budget: Arc<Semaphore>,
@@ -16987,9 +16986,9 @@ impl ECStore {
         mut deferred_entry: DeferredDecommissionEntry,
         bucket: String,
         set: Arc<SetDisks>,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
         object_lock_config: Option<ObjectLockConfiguration>,
-        replication_config: Option<(PersistedReplicationConfiguration, OffsetDateTime)>,
+        replication_config: Option<(ReplicationConfiguration, OffsetDateTime)>,
         expected_bucket_incarnation_id: Option<uuid::Uuid>,
         source_changed_exhaustions: Arc<AtomicUsize>,
         entry_budget: Arc<Semaphore>,
@@ -17096,9 +17095,9 @@ impl ECStore {
         generation: OffsetDateTime,
         set: Arc<SetDisks>,
         bi: DecomBucketInfo,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
         object_lock_config: Option<ObjectLockConfiguration>,
-        replication_config: Option<(PersistedReplicationConfiguration, OffsetDateTime)>,
+        replication_config: Option<(ReplicationConfiguration, OffsetDateTime)>,
         expected_bucket_incarnation_id: Option<uuid::Uuid>,
         source_changed_exhaustions: Arc<AtomicUsize>,
         entry_budget: Arc<Semaphore>,
@@ -17773,9 +17772,9 @@ impl ECStore {
         entry: MetaCacheEntry,
         bucket: String,
         set: Arc<SetDisks>,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
         object_lock_config: Option<ObjectLockConfiguration>,
-        replication_config: Option<(PersistedReplicationConfiguration, OffsetDateTime)>,
+        replication_config: Option<(ReplicationConfiguration, OffsetDateTime)>,
         expected_bucket_incarnation_id: Option<uuid::Uuid>,
         source_changed_exhaustions: Arc<AtomicUsize>,
         attempts: &mut usize,
@@ -17959,9 +17958,9 @@ impl ECStore {
         entry: MetaCacheEntry,
         bucket: String,
         set: Arc<SetDisks>,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
         object_lock_config: Option<ObjectLockConfiguration>,
-        replication_config: Option<(PersistedReplicationConfiguration, OffsetDateTime)>,
+        replication_config: Option<(ReplicationConfiguration, OffsetDateTime)>,
         expected_bucket_incarnation_id: Option<uuid::Uuid>,
         entry_attempt: usize,
         scanner_backlog_handoff_attempt: usize,
@@ -19247,7 +19246,7 @@ impl ECStore {
         entry: MetaCacheEntry,
         bucket: String,
         set: Arc<SetDisks>,
-        lifecycle_config: Option<PersistedLifecycleConfiguration>,
+        lifecycle_config: Option<BucketLifecycleConfiguration>,
     ) -> Result<()> {
         let expected_bucket_incarnation_id = if is_meta_bucketname(&bucket) {
             None

crates/ecstore/src/core/sets.rs

@@ -65,38 +65,6 @@ use uuid::Uuid;
 
 const LIST_MULTIPART_SETS_CONCURRENCY: usize = 4;
 
-#[cfg(test)]
-type TestSetLockers = HashMap<usize, Vec<Arc<dyn rustfs_lock::LockClient>>>;
-
-#[cfg(test)]
-static TEST_SET_LOCKERS: std::sync::LazyLock<std::sync::Mutex<TestSetLockers>> =
-    std::sync::LazyLock::new(|| std::sync::Mutex::new(HashMap::new()));
-
-/// Keep a fixture's real locker domain scoped to its owning instance.
-#[cfg(test)]
-pub(crate) struct ScopedSetLockers(Arc<InstanceContext>);
-
-#[cfg(test)]
-impl ScopedSetLockers {
-    pub(crate) fn install(ctx: Arc<InstanceContext>, lockers: Vec<Arc<dyn rustfs_lock::LockClient>>) -> Self {
-        let key = Arc::as_ptr(&ctx) as usize;
-        let mut domains = TEST_SET_LOCKERS.lock().expect("test set lockers mutex");
-        assert!(!domains.contains_key(&key), "the instance already owns a test locker domain");
-        domains.insert(key, lockers);
-        Self(ctx)
-    }
-}
-
-#[cfg(test)]
-impl Drop for ScopedSetLockers {
-    fn drop(&mut self) {
-        TEST_SET_LOCKERS
-            .lock()
-            .expect("test set lockers mutex")
-            .remove(&(Arc::as_ptr(&self.0) as usize));
-    }
-}
-
 fn is_idempotent_delete_prefix_error(err: &Error) -> bool {
     is_err_object_not_found(err) || is_err_strict_volume_not_found(err)
 }
@@ -298,14 +266,6 @@ impl Sets {
                 }
             }
 
-            #[cfg(test)]
-            let pool_lockers = TEST_SET_LOCKERS
-                .lock()
-                .expect("test set lockers mutex")
-                .get(&(Arc::as_ptr(&instance_ctx) as usize))
-                .cloned()
-                .unwrap_or_else(|| pool_lockers.clone());
-
             let set_disks = SetDisks::new_with_instance_ctx(
                 runtime_sources::local_node_name().await,
                 Arc::new(RwLock::new(set_drive)),

crates/ecstore/src/crash_inject.rs

@@ -84,7 +84,7 @@ pub(crate) enum CrashPoint {
 }
 
 #[cfg(test)]
-pub(crate) use armed::{arm, disarm, should_crash_at};
+pub(crate) use armed::{arm, disarm, is_armed, 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.
@@ -94,6 +94,12 @@ 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;
@@ -132,6 +138,10 @@ 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/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, with_background_disk_io, with_background_resource_unit};
-        use rustfs_concurrency::adaptive::AdaptiveAdmission;
-        use std::num::NonZeroU16;
+        use crate::disk::io_admission::{current_disk_io_context, test_resource_units, with_background_disk_io};
         use tokio_util::sync::CancellationToken;
 
-        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;
+        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"),
                         }
-                        _ => spawn(None, work)
-                            .await
-                            .expect("unisolated worker")
-                            .expect("unisolated operation"),
+                    }),
+                ));
+                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;
                     }
-                }),
-            ));
-            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");
+                })
+                .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");
+            }
         }
     }
     fn config(pending: usize, workers: usize, blocking_threads: usize) -> Config {

crates/ecstore/src/disk/disk_store.rs

@@ -40,6 +40,7 @@ use std::sync::OnceLock;
 use std::sync::atomic::AtomicBool;
 use std::{
     collections::HashMap,
+    io,
     path::PathBuf,
     pin::Pin,
     sync::{
@@ -99,6 +100,16 @@ async fn observe_disk_operation<F: std::future::Future>(
     }
 }
 
+// The health, admission and timeout layers above a disk operation each embed its
+// future, and unoptimized builds copy it into every awaiting frame. Box it where
+// it is created so those layers carry only a pointer: one allocation per operation.
+fn boxed_disk_operation<F, Fut>(operation: F, io_permit: Option<crate::disk::io_admission::DiskIoPermit>) -> Pin<Box<Fut>>
+where
+    F: FnOnce(Option<crate::disk::io_admission::DiskIoPermit>) -> Fut,
+{
+    Box::pin(operation(io_permit))
+}
+
 struct SlowDiskWriter {
     inner: crate::disk::FileWriter,
     endpoint: Endpoint,
@@ -1574,6 +1585,8 @@ pub struct LocalDiskWrapper {
     metrics: Arc<DiskHealthMetricEpoch>,
     /// Per-drive foreground/background admission shared across wrapper reconnects.
     io_admission: Arc<DiskIoAdmission>,
+    /// Physical leaves are refreshed by the node sampler, never by object I/O.
+    physical_admission: Arc<crate::disk::io_admission::PhysicalDiskBinding>,
     /// Whether health checking is enabled
     health_check: bool,
     /// Cancellation token for monitoring tasks
@@ -1728,6 +1741,7 @@ impl LocalDiskWrapper {
             health,
             metrics,
             io_admission,
+            physical_admission: Arc::new(crate::disk::io_admission::PhysicalDiskBinding::default()),
             health_check: health_check && env_health_check,
             cancel_token: CancellationToken::new(),
             disk_id: Arc::new(RwLock::new(None)),
@@ -1745,6 +1759,10 @@ impl LocalDiskWrapper {
         }
     }
 
+    pub(crate) fn physical_admission(&self) -> Arc<crate::disk::io_admission::PhysicalDiskBinding> {
+        self.physical_admission.clone()
+    }
+
     pub fn get_disk(&self) -> Arc<LocalDisk> {
         self.disk.clone()
     }
@@ -1786,6 +1804,33 @@ impl LocalDiskWrapper {
         context
     }
 
+    // Projection cannot wait: callers may already hold namespace or cache locks.
+    // Enter before identity probes, disk permits, or owned native jobs are created.
+    async fn with_native_resources<F: std::future::Future>(&self, operation: F) -> Result<F::Output> {
+        let Some(resources) = current_resource_unit() else {
+            if super::remote_io_admission::active() {
+                return Err(DiskError::Io(io::Error::from(io::ErrorKind::WouldBlock)));
+            }
+            return Ok(operation.await);
+        };
+        let resources = if let Some(permits) = resources.as_set() {
+            let unavailable = || DiskError::Io(io::Error::from(io::ErrorKind::WouldBlock));
+            let plan = self.physical_admission.plan().ok_or_else(unavailable)?;
+            let native = plan
+                .capture_or_acquire_native(permits)
+                .map_err(|error| DiskError::Io(io::Error::new(io::ErrorKind::WouldBlock, error)))?;
+            if !plan.is_current() {
+                return Err(unavailable());
+            }
+            resources.with_permits(native)
+        } else {
+            resources
+        };
+        #[cfg(target_os = "linux")]
+        let resources = resources.with_mount_lease(self.disk.native_mount_lease());
+        Ok(with_optional_resource_unit(Some(resources), operation).await)
+    }
+
     async fn acquire_disk_io_permit(&self) -> Result<Option<crate::disk::io_admission::DiskIoPermit>> {
         if let Some(context) = current_disk_io_context() {
             if let Some(permit) = context.permit
@@ -2201,6 +2246,19 @@ impl LocalDiskWrapper {
         versions: Vec<FileInfoVersions>,
         opts: DeleteOptions,
         namespace_owner: Option<Arc<dyn Send + Sync>>,
+    ) -> Vec<Option<Error>> {
+        let count = versions.len();
+        self.with_native_resources(self.delete_versions_admitted(volume, versions, opts, namespace_owner))
+            .await
+            .unwrap_or_else(|error| vec![Some(error); count])
+    }
+
+    async fn delete_versions_admitted(
+        &self,
+        volume: &str,
+        versions: Vec<FileInfoVersions>,
+        opts: DeleteOptions,
+        namespace_owner: Option<Arc<dyn Send + Sync>>,
     ) -> Vec<Option<Error>> {
         let version_count = versions.len();
         self.metrics.record_operation_call("delete_versions");
@@ -2253,6 +2311,19 @@ impl LocalDiskWrapper {
         versions: Vec<GuardedFileInfoVersions>,
         opts: DeleteOptions,
         namespace_owner: Option<Arc<dyn Send + Sync>>,
+    ) -> Vec<Option<Error>> {
+        let count = versions.len();
+        self.with_native_resources(self.delete_versions_guarded_admitted(volume, versions, opts, namespace_owner))
+            .await
+            .unwrap_or_else(|error| vec![Some(error); count])
+    }
+
+    async fn delete_versions_guarded_admitted(
+        &self,
+        volume: &str,
+        versions: Vec<GuardedFileInfoVersions>,
+        opts: DeleteOptions,
+        namespace_owner: Option<Arc<dyn Send + Sync>>,
     ) -> Vec<Option<Error>> {
         let version_count = versions.len();
         self.metrics.record_operation_call("delete_versions");
@@ -2327,6 +2398,51 @@ impl LocalDiskWrapper {
         .await
     }
 
+    pub(crate) async fn try_publish_prepared_delete_local(
+        &self,
+        volume: &str,
+        object: &str,
+        transaction: uuid::Uuid,
+        namespace_owner: Option<Arc<dyn Send + Sync>>,
+    ) -> Result<Option<(crate::disk::DeleteRecoveryJournal, bool, bool)>> {
+        self.track_disk_health_mutation(
+            "settle_delete_transaction",
+            DiskMetricMutation::Delete,
+            || {
+                Box::pin(async {
+                    self.disk
+                        .try_publish_prepared_delete_local(volume, object, transaction, namespace_owner)
+                        .await
+                })
+            },
+            crate::disk::get_delete_recovery_timeout()?,
+        )
+        .await
+    }
+
+    pub(crate) async fn try_finish_and_finalize_prepared_delete_local(
+        &self,
+        volume: &str,
+        object: &str,
+        transaction: uuid::Uuid,
+        journal: &crate::disk::DeleteRecoveryJournal,
+        namespace_owner: Option<Arc<dyn Send + Sync>>,
+    ) -> Result<bool> {
+        self.track_disk_health_mutation(
+            "settle_delete_transaction",
+            DiskMetricMutation::Delete,
+            || {
+                Box::pin(async {
+                    self.disk
+                        .try_finish_and_finalize_prepared_delete_local(volume, object, transaction, journal, namespace_owner)
+                        .await
+                })
+            },
+            crate::disk::get_delete_recovery_timeout()?,
+        )
+        .await
+    }
+
     /// Track disk health for an operation.
     /// This method should wrap disk operations to ensure health checking.
     pub async fn track_disk_health<T, F, Fut>(&self, operation: F, timeout_duration: Duration) -> Result<T>
@@ -2451,6 +2567,28 @@ impl LocalDiskWrapper {
         timeout_health_action: TimeoutHealthAction,
         mutation: DiskMetricMutation,
     ) -> Result<T>
+    where
+        F: FnOnce(Option<crate::disk::io_admission::DiskIoPermit>) -> Fut,
+        Fut: std::future::Future<Output = Result<T>>,
+    {
+        self.with_native_resources(self.track_admitted_disk_operation(
+            op,
+            operation,
+            timeout_duration,
+            timeout_health_action,
+            mutation,
+        ))
+        .await?
+    }
+
+    async fn track_admitted_disk_operation<T, F, Fut>(
+        &self,
+        op: &'static str,
+        operation: F,
+        timeout_duration: Duration,
+        timeout_health_action: TimeoutHealthAction,
+        mutation: DiskMetricMutation,
+    ) -> Result<T>
     where
         F: FnOnce(Option<crate::disk::io_admission::DiskIoPermit>) -> Fut,
         Fut: std::future::Future<Output = Result<T>>,
@@ -2483,13 +2621,14 @@ impl LocalDiskWrapper {
         let _waiting_guard = self.health.waiting_guard();
         let _metric_waiting_guard = self.metrics.waiting_guard();
         let started = Instant::now();
-        let operation = observe_disk_operation(|| self.endpoint(), op, operation(io_permit));
+        let operation = observe_disk_operation(|| self.endpoint(), op, boxed_disk_operation(operation, io_permit));
 
         if timeout_duration == Duration::ZERO {
             let result = operation.await;
             self.metrics.record_operation_latency(op, started.elapsed());
             self.record_result_error_metrics(&result);
             if result.is_ok() {
+                super::remote_io_admission::record_progress();
                 self.health.record_operation_success(&self.endpoint(), "operation_success");
                 self.metrics.record_mutation_success(mutation);
             }
@@ -2504,6 +2643,7 @@ impl LocalDiskWrapper {
                 self.record_result_error_metrics(&operation_result);
                 // Log success; the waiting guard balances every exit path.
                 if operation_result.is_ok() {
+                    super::remote_io_admission::record_progress();
                     self.health.record_operation_success(&self.endpoint(), "operation_success");
                     self.metrics.record_mutation_success(mutation);
                 }
@@ -2675,7 +2815,7 @@ impl DiskAPI for LocalDiskWrapper {
         if self.health.is_faulty() {
             return false;
         }
-        let Ok(Some(disk_id)) = self.disk.get_disk_id().await else {
+        let Ok(Some(disk_id)) = self.get_disk_id().await else {
             return false;
         };
 
@@ -2708,7 +2848,7 @@ impl DiskAPI for LocalDiskWrapper {
     }
 
     async fn get_disk_id(&self) -> Result<Option<Uuid>> {
-        self.disk.get_disk_id().await
+        self.with_native_resources(self.disk.get_disk_id()).await?
     }
 
     async fn set_disk_id(&self, id: Option<Uuid>) -> Result<()> {
@@ -2776,15 +2916,6 @@ impl DiskAPI for LocalDiskWrapper {
         })
     }
 
-    async fn bucket_creation_witness(&self, volume: &str) -> Result<Option<super::os::NativeBucketCreationWitness>> {
-        self.track_disk_health_with_op(
-            "bucket_creation_witness",
-            || async { self.disk.bucket_creation_witness(volume).await },
-            Duration::ZERO,
-        )
-        .await
-    }
-
     async fn make_volume(&self, volume: &str) -> Result<()> {
         // Scoped heal must drain directory creation before releasing its lifecycle owner.
         let timeout = if crate::store::bucket_heal_scope(volume).is_some() {
@@ -3149,25 +3280,29 @@ impl DiskAPI for LocalDiskWrapper {
     }
 
     async fn read_file(&self, volume: &str, path: &str) -> Result<crate::disk::FileReader> {
-        let reader = self
-            .track_disk_health_with_op(
-                "read_file",
-                || async { self.disk.read_file(volume, path).await },
-                get_max_timeout_duration(),
-            )
-            .await?;
-        Ok(Box::new(AdmissionReader::new(reader, self.io_admission.clone(), self.disk_io_context())))
+        self.track_disk_health_with_op(
+            "read_file",
+            || async {
+                let reader = self.disk.read_file(volume, path).await?;
+                Ok(Box::new(AdmissionReader::new(reader, self.io_admission.clone(), self.disk_io_context()))
+                    as crate::disk::FileReader)
+            },
+            get_max_timeout_duration(),
+        )
+        .await
     }
 
     async fn read_file_stream(&self, volume: &str, path: &str, offset: usize, length: usize) -> Result<crate::disk::FileReader> {
-        let reader = self
-            .track_disk_health_with_op(
-                "read_file_stream",
-                || async { self.disk.read_file_stream(volume, path, offset, length).await },
-                get_max_timeout_duration(),
-            )
-            .await?;
-        Ok(Box::new(AdmissionReader::new(reader, self.io_admission.clone(), self.disk_io_context())))
+        self.track_disk_health_with_op(
+            "read_file_stream",
+            || async {
+                let reader = self.disk.read_file_stream(volume, path, offset, length).await?;
+                Ok(Box::new(AdmissionReader::new(reader, self.io_admission.clone(), self.disk_io_context()))
+                    as crate::disk::FileReader)
+            },
+            get_max_timeout_duration(),
+        )
+        .await
     }
 
     async fn read_file_stream_chunks(
@@ -3177,20 +3312,21 @@ impl DiskAPI for LocalDiskWrapper {
         offset: usize,
         length: usize,
     ) -> Result<Option<rustfs_rio::ChunkReaderBox>> {
-        let reader = self
-            .track_disk_health_with_op(
-                "read_file_stream_chunks",
-                || async { self.disk.read_file_stream_chunks(volume, path, offset, length).await },
-                get_max_timeout_duration(),
-            )
-            .await?;
-        Ok(reader.map(|reader| {
-            Box::new(AdmissionReader::new(
-                BoxedChunkReader(reader),
-                self.io_admission.clone(),
-                self.disk_io_context(),
-            )) as rustfs_rio::ChunkReaderBox
-        }))
+        self.track_disk_health_with_op(
+            "read_file_stream_chunks",
+            || async {
+                let reader = self.disk.read_file_stream_chunks(volume, path, offset, length).await?;
+                Ok(reader.map(|reader| {
+                    Box::new(AdmissionReader::new(
+                        BoxedChunkReader(reader),
+                        self.io_admission.clone(),
+                        self.disk_io_context(),
+                    )) as rustfs_rio::ChunkReaderBox
+                }))
+            },
+            get_max_timeout_duration(),
+        )
+        .await
     }
 
     async fn read_file_mmap_copy(&self, volume: &str, path: &str, offset: usize, length: usize) -> Result<bytes::Bytes> {
@@ -4155,6 +4291,573 @@ mod tests {
         );
     }
 
+    #[tokio::test]
+    async fn local_disk_resource_identity_probes_keep_only_their_native_device_after_cancel() {
+        assert_native_identity_probe_cancellation(false).await;
+    }
+
+    #[tokio::test]
+    async fn remote_background_native_identity_cancellation_keeps_receiver_device() {
+        assert_native_identity_probe_cancellation(true).await;
+    }
+
+    async fn assert_native_identity_probe_cancellation(remote: bool) {
+        use rustfs_concurrency::adaptive::{
+            AdaptiveAdmission, FeedbackController, FeedbackObservation, NodeAdmission, ResourcePressure,
+            permit_set::AdaptivePermitSetOwner,
+        };
+        use std::num::NonZeroU16;
+
+        for read in [false, true] {
+            for online in [false, true] {
+                let dir = tempfile::tempdir().expect("format probe fixture");
+                let mut endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+                endpoint.set_pool_index(0);
+                endpoint.set_set_index(0);
+                endpoint.set_disk_index(0);
+                let meta = dir.path().join(RUSTFS_META_BUCKET);
+                tokio::fs::create_dir_all(&meta).await.expect("metadata directory");
+                let mut format = FormatV3::new(1, 1);
+                format.erasure.this = format.erasure.sets[0][0];
+                tokio::fs::write(meta.join(FORMAT_CONFIG_FILE), format.to_json().expect("format bytes"))
+                    .await
+                    .expect("write format");
+                let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("formatted disk"));
+                {
+                    let mut cache = disk.format_info.write().await;
+                    cache.last_check = None;
+                    if read {
+                        cache.file_info = None;
+                    }
+                }
+                let (started_tx, started_rx) = tokio::sync::oneshot::channel();
+                let (release_tx, release_rx) = tokio::sync::oneshot::channel();
+                disk.install_format_probe_hook(read, move || {
+                    let _ = started_tx.send(());
+                    let _ = release_rx.blocking_recv();
+                });
+                let wrapper = Arc::new(LocalDiskWrapper::new(disk, false));
+                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("catalog");
+                wrapper
+                    .physical_admission
+                    .set_test_shared_capacity(shared.clone(), vec![a.clone()])
+                    .expect("native device A");
+                let node = NodeAdmission::new(NonZeroU16::MIN);
+                node.update(
+                    &mut FeedbackController::new(),
+                    Some(FeedbackObservation {
+                        generation: 1,
+                        max_concurrency: 1,
+                        pressure: ResourcePressure::Unknown,
+                        completed_units: None,
+                    }),
+                );
+                let parent = (!remote).then(|| shared.try_acquire_with_node(&node).expect("planned devices"));
+                let task = tokio::spawn({
+                    let wrapper = wrapper.clone();
+                    let node = node.clone();
+                    async move {
+                        let operation = async {
+                            if online {
+                                assert!(wrapper.is_online().await);
+                            } else {
+                                wrapper.get_disk_id().await.expect("disk identity");
+                            }
+                        };
+                        if remote {
+                            crate::disk::with_remote_background_io(Some(crate::disk::RemoteBackgroundIo::new(node)), async {
+                                crate::disk::remote_io_admission::admit(&wrapper.physical_admission).expect("RPC disk admission");
+                                operation.await;
+                            })
+                            .await;
+                        } else {
+                            let parent = parent.expect("local operation admission");
+                            crate::disk::with_background_resource_set(parent.resources().clone(), operation).await;
+                            parent.complete();
+                        }
+                    }
+                });
+                tokio::time::timeout(Duration::from_secs(5), started_rx)
+                    .await
+                    .expect("native probe starts")
+                    .expect("native signal");
+                task.abort();
+                assert!(task.await.expect_err("cancel waiter").is_cancelled());
+                let held = [node.snapshot().active, a.snapshot().active, b.snapshot().active];
+                let healthy_available = b.try_acquire().is_some();
+                release_tx.send(()).expect("release native probe before assertions");
+                tokio::time::timeout(Duration::from_secs(5), async {
+                    while a.snapshot().active != 0 || b.snapshot().active != 0 {
+                        tokio::task::yield_now().await;
+                    }
+                })
+                .await
+                .expect("native probe releases its device");
+                assert_eq!(held, [0, 1, 0], "read={read}, online={online}");
+                assert!(healthy_available);
+                assert_eq!([node.completed(), a.completed(), b.completed()], [Some(0), Some(0), Some(0)]);
+                assert_eq!(wrapper.get_disk_id().await.expect("format remains readable"), Some(format.erasure.this));
+                assert!(wrapper.is_online().await);
+            }
+        }
+    }
+
+    #[tokio::test]
+    async fn local_disk_resource_projection_releases_unrelated_devices_after_native_cancellation() {
+        use crate::disk::io_admission::spawn_blocking_with_disk_io_permit;
+        use rustfs_concurrency::adaptive::{
+            AdaptiveAdmission, FeedbackController, FeedbackObservation, NodeAdmission, ResourcePressure,
+            permit_set::AdaptivePermitSetOwner,
+        };
+        use std::num::NonZeroU16;
+
+        for auxiliary in [false, true] {
+            let dir = tempfile::tempdir().expect("local disk fixture");
+            let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+            let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+            let wrapper = LocalDiskWrapper::new(disk, false);
+            let first = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+            let second = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+            let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![first.clone(), second.clone()])
+                .expect("shared operation resources");
+            wrapper
+                .physical_admission
+                .set_test_shared_capacity(shared.clone(), vec![if auxiliary { second.clone() } else { first.clone() }])
+                .expect("only the first device backs this wrapper");
+            let node = NodeAdmission::new(NonZeroU16::MIN);
+            node.update(
+                &mut FeedbackController::new(),
+                Some(FeedbackObservation {
+                    generation: 1,
+                    max_concurrency: 1,
+                    pressure: ResourcePressure::Unknown,
+                    completed_units: None,
+                }),
+            );
+            let parent = if auxiliary {
+                shared
+                    .select(std::slice::from_ref(&first))
+                    .expect("initial object device")
+                    .try_acquire_with_node(&node)
+            } else {
+                shared.try_acquire_with_node(&node)
+            }
+            .expect("initial object admission");
+            let (started_tx, started_rx) = tokio::sync::oneshot::channel();
+            let (release_tx, release_rx) = tokio::sync::oneshot::channel();
+            let task = tokio::spawn(async move {
+                crate::disk::with_background_resource_set(parent.resources().clone(), async {
+                    wrapper
+                        .track_disk_health_with_op_timeout_action_and_mutation_with_io_permit(
+                            "read_all",
+                            move |permit| async move {
+                                spawn_blocking_with_disk_io_permit(permit, move || {
+                                    started_tx.send(()).expect("signal native start");
+                                    release_rx.blocking_recv().expect("release native I/O");
+                                })
+                                .await
+                                .expect("native I/O joined");
+                                Ok(())
+                            },
+                            Duration::ZERO,
+                            TimeoutHealthAction::MarkFailure,
+                            DiskMetricMutation::None,
+                        )
+                        .await
+                        .expect("wrapped I/O");
+                })
+                .await;
+                parent.complete();
+            });
+            tokio::time::timeout(Duration::from_secs(5), started_rx)
+                .await
+                .expect("native work starts")
+                .expect("start notification");
+            task.abort();
+            assert!(task.await.expect_err("cancel waiter").is_cancelled());
+            let held = [node.snapshot().active, first.snapshot().active, second.snapshot().active];
+            let healthy_available = if auxiliary {
+                first.try_acquire().is_some()
+            } else {
+                second.try_acquire().is_some()
+            };
+            release_tx.send(()).expect("finish native work before asserting");
+            tokio::time::timeout(Duration::from_secs(5), async {
+                while first.snapshot().active != 0 || second.snapshot().active != 0 {
+                    tokio::task::yield_now().await;
+                }
+            })
+            .await
+            .expect("native resource return");
+            assert_eq!(
+                held,
+                if auxiliary { [0, 0, 1] } else { [0, 1, 0] },
+                "only the actual native device remains charged"
+            );
+            assert!(healthy_available, "healthy work must resume before native I/O finishes");
+            assert_eq!(node.completed(), Some(0), "cancelled work is not progress");
+            assert_eq!([first.completed(), second.completed()], [Some(0), Some(0)]);
+        }
+    }
+
+    #[tokio::test]
+    async fn local_disk_resource_projection_escaped_readers_keep_only_their_device() {
+        use rustfs_concurrency::adaptive::{AdaptiveAdmission, permit_set::AdaptivePermitSetOwner};
+        use std::num::NonZeroU16;
+        use tokio::io::AsyncReadExt;
+
+        let dir = tempfile::tempdir().expect("reader fixture");
+        let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+        let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+        let wrapper = LocalDiskWrapper::new(disk, false);
+        tokio::fs::create_dir_all(dir.path().join("bucket"))
+            .await
+            .expect("bucket directory");
+        let bytes = b"physical disk reader payload";
+        tokio::fs::write(dir.path().join("bucket/object"), bytes)
+            .await
+            .expect("reader bytes");
+        let first = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let second = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![first.clone(), second.clone()]).expect("parent resources");
+        wrapper
+            .physical_admission
+            .set_test_shared_capacity(shared.clone(), vec![first.clone()])
+            .expect("reader device");
+
+        for stream in [false, true] {
+            let a = first.try_acquire().expect("first device");
+            let b = second.try_acquire().expect("second device");
+            let parent = shared.capture(&[&a, &b]).expect("admitted parent");
+            drop((a, b));
+            let mut reader = crate::disk::with_background_resource_set(parent, async {
+                if stream {
+                    wrapper.read_file_stream("bucket", "object", 0, bytes.len()).await
+                } else {
+                    wrapper.read_file("bucket", "object").await
+                }
+            })
+            .await
+            .expect("reader escapes the resource scope");
+            assert_eq!([first.snapshot().active, second.snapshot().active], [1, 0]);
+            assert!(second.try_acquire().is_some(), "unrelated work is available while the reader lives");
+            let mut actual = Vec::new();
+            reader.read_to_end(&mut actual).await.expect("consume escaped reader");
+            assert_eq!(actual, bytes);
+            drop(reader);
+            assert_eq!(first.snapshot().active, 0);
+        }
+    }
+
+    #[cfg(unix)]
+    #[test]
+    fn local_disk_resource_projection_cancelled_stream_read_retains_native_device() {
+        use rustfs_concurrency::adaptive::{AdaptiveAdmission, permit_set::AdaptivePermitSetOwner};
+        use std::num::NonZeroU16;
+        use tokio::io::{AsyncRead, ReadBuf};
+
+        let runtime = tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .max_blocking_threads(1)
+            .build()
+            .expect("one-thread native read pool");
+        runtime.block_on(async {
+            let dir = tempfile::tempdir().expect("native reader fixture");
+            let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+            let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+            let wrapper = LocalDiskWrapper::new(disk, false);
+            std::fs::create_dir(dir.path().join("bucket")).expect("bucket directory");
+            let bytes = b"physical disk native reader payload";
+            std::fs::write(dir.path().join("bucket/object"), bytes).expect("reader bytes");
+            let first = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+            let second = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+            let shared =
+                AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![first.clone(), second.clone()]).expect("parent resources");
+            wrapper
+                .physical_admission
+                .set_test_shared_capacity(shared.clone(), vec![first.clone()])
+                .expect("reader device");
+            let mut observations = Vec::new();
+            for stream in [false, true] {
+                let a = first.try_acquire().expect("first device");
+                let b = second.try_acquire().expect("second device");
+                let parent = shared.capture(&[&a, &b]).expect("admitted parent");
+                drop((a, b));
+                let mut reader = crate::disk::with_background_resource_set(
+                    parent,
+                    crate::disk::with_background_disk_io(CancellationToken::new(), async {
+                        if stream {
+                            wrapper.read_file_stream("bucket", "object", 3, bytes.len() - 3).await
+                        } else {
+                            wrapper.read_file("bucket", "object").await
+                        }
+                    }),
+                )
+                .await
+                .expect("background reader escapes its parent");
+                assert_eq!([first.snapshot().active, second.snapshot().active], [1, 0]);
+                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 pool occupied after open");
+                let (pending_tx, pending_rx) = tokio::sync::oneshot::channel();
+                let task = tokio::spawn(async move {
+                    let mut data = [0; 1];
+                    let mut pending_tx = Some(pending_tx);
+                    std::future::poll_fn(|cx| {
+                        let mut buffer = ReadBuf::new(&mut data);
+                        let result = Pin::new(&mut reader).poll_read(cx, &mut buffer);
+                        if result.is_pending()
+                            && let Some(signal) = pending_tx.take()
+                        {
+                            let _ = signal.send(());
+                        }
+                        result
+                    })
+                    .await
+                });
+                tokio::time::timeout(Duration::from_secs(5), pending_rx)
+                    .await
+                    .expect("read queues behind native worker")
+                    .expect("pending read signal");
+                let admitted = wrapper.background_io_active_for_tests();
+                task.abort();
+                assert!(task.await.expect_err("cancel pending read").is_cancelled());
+                let held = [first.snapshot().active, second.snapshot().active];
+                release_tx.send(()).expect("release native pool before asserting");
+                blocker.await.expect("blocking worker released");
+                tokio::task::spawn_blocking(|| ())
+                    .await
+                    .expect("drain the single native queue");
+                assert_eq!([first.snapshot().active, second.snapshot().active], [0, 0]);
+                observations.push((stream, admitted, held));
+            }
+            for (stream, admitted, held) in observations {
+                assert!(admitted, "stream={stream}: cancellation follows disk admission, not its wait");
+                assert_eq!(held, [1, 0], "stream={stream}: only the pending native read's device stays charged");
+            }
+        });
+    }
+
+    #[cfg(unix)]
+    #[tokio::test]
+    async fn projected_stream_memory_survives_scope_exit_and_hot_shrink() {
+        use crate::disk::io_admission::{BackgroundMemoryBudget, ResourceIoUnit, with_optional_resource_unit};
+        use rustfs_concurrency::adaptive::{AdaptiveAdmission, permit_set::AdaptivePermitSetOwner};
+        use std::num::NonZeroU16;
+        use tokio::io::AsyncReadExt;
+
+        let dir = tempfile::tempdir().expect("memory admission fixture");
+        let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+        let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+        let wrapper = LocalDiskWrapper::new(disk, false);
+        std::fs::create_dir(dir.path().join("bucket")).expect("bucket directory");
+        let bytes = b"0123456789abcdefghijklmnopqrstuv";
+        std::fs::write(dir.path().join("bucket/object"), bytes).expect("reader bytes");
+        let first = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let second = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![first.clone(), second.clone()]).expect("parent resources");
+        wrapper
+            .physical_admission
+            .set_test_shared_capacity(shared.clone(), vec![first.clone()])
+            .expect("selected device");
+        let memory = BackgroundMemoryBudget::new();
+
+        for stream in [false, true] {
+            memory.set_sampled_limit(4, Duration::from_secs(30));
+            let a = first.try_acquire().expect("first device");
+            let b = second.try_acquire().expect("second device");
+            let parent =
+                ResourceIoUnit::from(shared.capture(&[&a, &b]).expect("admitted parent")).with_memory_budget(memory.clone());
+            drop((a, b));
+            let mut reader = with_optional_resource_unit(Some(parent), async {
+                if stream {
+                    wrapper.read_file_stream("bucket", "object", 0, bytes.len()).await
+                } else {
+                    wrapper.read_file("bucket", "object").await
+                }
+            })
+            .await
+            .expect("reader escapes its resource scope");
+            assert_eq!(memory.snapshot().used, 0, "opening does not allocate a read buffer");
+            let mut prefix = [0; 4];
+            reader.read_exact(&mut prefix).await.expect("initial read");
+            assert_eq!(&prefix, &bytes[..4]);
+            assert_eq!(memory.snapshot().used, 4, "projection retains the same memory owner");
+            assert_eq!([first.snapshot().active, second.snapshot().active], [1, 0]);
+
+            memory.set_sampled_limit(0, Duration::ZERO);
+            let mut reused = [0; 2];
+            reader
+                .read_exact(&mut reused)
+                .await
+                .expect("already allocated storage remains usable");
+            assert_eq!(&reused, &bytes[4..6]);
+            let mut next = [99; 8];
+            let error = reader.read(&mut next).await.expect_err("new storage is blocked after shrink");
+            assert_eq!(error.kind(), std::io::ErrorKind::WouldBlock);
+            assert_eq!(next, [99; 8], "denied allocation exposes no stale bytes");
+            assert_eq!(memory.snapshot().used, 4);
+
+            memory.set_sampled_limit(12, Duration::from_secs(30));
+            reader
+                .read_exact(&mut next)
+                .await
+                .expect("growth includes old and replacement storage");
+            assert_eq!(&next, &bytes[6..14], "denial did not advance the file");
+            assert_eq!(memory.snapshot().used, 8);
+            drop(reader);
+            assert_eq!(memory.snapshot().used, 0);
+            assert_eq!([first.snapshot().active, second.snapshot().active], [0, 0]);
+        }
+    }
+
+    #[tokio::test]
+    async fn local_disk_resource_projection_auxiliary_metadata_retries_without_parking_or_false_progress() {
+        use rustfs_concurrency::adaptive::{
+            AdaptiveAdmission, FeedbackController, FeedbackObservation, NodeAdmission, ResourcePressure,
+            permit_set::AdaptivePermitSetOwner,
+        };
+        use std::num::NonZeroU16;
+
+        let dir = tempfile::tempdir().expect("metadata fixture");
+        let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+        let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+        let wrapper = LocalDiskWrapper::new(disk, false);
+        tokio::fs::create_dir_all(dir.path().join("bucket"))
+            .await
+            .expect("metadata bucket");
+        tokio::fs::write(dir.path().join("bucket/metadata"), b"auxiliary metadata")
+            .await
+            .expect("metadata bytes");
+        let a = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let b = AdaptiveAdmission::new(NonZeroU16::MIN, 0);
+        let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![a.clone(), b.clone()]).expect("topology");
+        wrapper
+            .physical_admission
+            .set_test_shared_capacity(shared.clone(), vec![b.clone()])
+            .expect("metadata on B");
+        let node = NodeAdmission::new(NonZeroU16::MIN);
+        node.update(
+            &mut FeedbackController::new(),
+            Some(FeedbackObservation {
+                generation: 1,
+                max_concurrency: 1,
+                pressure: ResourcePressure::Unknown,
+                completed_units: None,
+            }),
+        );
+        let parent = shared
+            .select(std::slice::from_ref(&a))
+            .expect("object on A")
+            .try_acquire_with_node(&node)
+            .expect("object admission");
+        crate::disk::with_background_resource_set(parent.resources().clone(), async {
+            let mut read = Box::pin(wrapper.read_all("bucket", "metadata"));
+            let rejected = std::future::poll_fn(|cx| Poll::Ready(read.as_mut().poll(cx))).await;
+            assert!(
+                matches!(rejected, Poll::Ready(Err(DiskError::Io(error))) if error.kind() == io::ErrorKind::WouldBlock),
+                "auxiliary admission must return immediately under storage locks"
+            );
+            drop(read);
+            assert!(
+                matches!(wrapper.get_disk_id().await, Err(DiskError::Io(error)) if error.kind() == io::ErrorKind::WouldBlock)
+            );
+            assert!(!wrapper.is_online().await, "identity checks cannot bypass closed physical capacity");
+            assert_eq!([a.snapshot().active, b.snapshot().active, node.snapshot().active], [1, 0, 1]);
+            assert_eq!([a.completed(), b.completed(), node.completed()], [Some(0), Some(0), Some(0)]);
+            b.set_limit(1);
+            for _ in 0..2 {
+                assert_eq!(
+                    wrapper.read_all("bucket", "metadata").await.expect("retry metadata read"),
+                    Bytes::from_static(b"auxiliary metadata")
+                );
+                assert_eq!(b.snapshot().active, 1, "repeated I/O reuses the parent's physical unit");
+            }
+        })
+        .await;
+        assert_eq!(wrapper.metrics_snapshot().total_errors_availability, 0);
+        assert_eq!([a.completed(), b.completed(), node.completed()], [Some(0), Some(0), Some(0)]);
+        parent.complete();
+        assert_eq!([a.completed(), b.completed(), node.completed()], [Some(1), Some(1), Some(1)]);
+        assert_eq!([a.snapshot().active, b.snapshot().active, node.snapshot().active], [0, 0, 0]);
+    }
+
+    #[tokio::test]
+    async fn local_disk_resource_projection_defers_missing_or_foreign_owners_before_io() {
+        use rustfs_concurrency::adaptive::{AdaptiveAdmission, permit_set::AdaptivePermitSetOwner};
+        use std::num::NonZeroU16;
+
+        let dir = tempfile::tempdir().expect("unavailable resource fixture");
+        let endpoint = Endpoint::try_from(dir.path().to_str().expect("fixture path")).expect("local endpoint");
+        let disk = Arc::new(LocalDisk::new(&endpoint, false).await.expect("local disk"));
+        let wrapper = LocalDiskWrapper::new(disk, false);
+        let gate = AdaptiveAdmission::new(NonZeroU16::MIN, 1);
+        let shared = AdaptivePermitSetOwner::new(NonZeroU16::MIN, vec![gate.clone()]).expect("parent");
+        let permit = gate.try_acquire().expect("parent device");
+        let parent = shared.capture(&[&permit]).expect("parent ownership");
+        drop(permit);
+        for foreign in [false, true] {
+            if foreign {
+                wrapper
+                    .physical_admission
+                    .set_test_capacity(vec![AdaptiveAdmission::new(NonZeroU16::MIN, 1)])
+                    .expect("replaced device");
+            }
+            crate::disk::with_background_resource_set(parent.clone(), async {
+                let polled = std::cell::Cell::new(false);
+                let result = wrapper
+                    .track_disk_health_with_op(
+                        "read_all",
+                        || async {
+                            polled.set(true);
+                            Ok(())
+                        },
+                        Duration::ZERO,
+                    )
+                    .await;
+                assert!(matches!(result, Err(DiskError::Io(error)) if error.kind() == io::ErrorKind::WouldBlock));
+                assert!(!polled.get(), "unavailable ownership cannot start native work");
+                let group = FileInfoVersions::default();
+                let plain = wrapper
+                    .delete_versions("bucket", vec![group.clone(); 2], DeleteOptions::default())
+                    .await;
+                let guarded = wrapper
+                    .delete_versions_guarded_with_namespace_owner(
+                        "bucket",
+                        vec![
+                            GuardedFileInfoVersions {
+                                group,
+                                expected_current: crate::disk::CurrentDeleteGeneration::Absent
+                            };
+                            2
+                        ],
+                        DeleteOptions::default(),
+                        None,
+                    )
+                    .await;
+                for errors in [plain, guarded] {
+                    assert_eq!(errors.len(), 2);
+                    assert!(errors.iter().all(|error| matches!(error,
+                        Some(DiskError::Io(error)) if error.kind() == io::ErrorKind::WouldBlock)));
+                }
+            })
+            .await;
+            assert_eq!(wrapper.health.waiting_count(), 0);
+            assert_eq!(
+                wrapper.metrics_snapshot().total_errors_availability,
+                0,
+                "resource deferral is not a failed drive"
+            );
+            assert_eq!(gate.snapshot().active, 1, "rejection does not refund parent ownership");
+        }
+    }
+
     async fn assert_multipart_recovery_waiter_preserves_physical_owner(wait_timeout: Duration) {
         use crate::disk::multipart_source::{
             MULTIPART_SOURCE_PROTOCOL_VERSION, MultipartRecoveryRound, MultipartSourceOperation, MultipartSourcePhase,

crates/ecstore/src/disk/fs.rs

@@ -16,40 +16,15 @@ use std::{
     collections::HashMap,
     fs::Metadata,
     path::{Path, PathBuf},
-    sync::{Arc, Mutex, OnceLock},
+    sync::Mutex,
     time::{Duration, Instant},
 };
-use tokio::{
-    fs::{self, File},
-    io,
-};
+use tokio::{fs::File, io};
 
-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)
-    })
+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"))?
 }
 
 #[cfg(not(windows))]
@@ -117,36 +92,32 @@ pub const O_APPEND: FileMode = 0x00400;
 //     create_new: bool,
 
 pub async fn open_file(path: impl AsRef<Path>, mode: FileMode) -> io::Result<File> {
-    if mode & O_CREATE != 0 {
-        super::os::record_native_publication(path.as_ref());
-    }
-    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);
+    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),
         }
-        if mode & O_APPEND != 0 {
-            opts.append(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_TRUNC != 0 {
-            opts.truncate(true);
-        }
-        opts.open(path.as_ref()).await
-    } else {
-        base_opts.open(path.as_ref()).await
-    }
+        options.open(path).map(File::from_std)
+    })
+    .await
 }
 
 pub async fn access(path: impl AsRef<Path>) -> io::Result<()> {
-    fs::metadata(path).await?;
-    Ok(())
+    let path = path.as_ref().to_path_buf();
+    native_io(move || std::fs::metadata(path).map(|_| ())).await
 }
 
 pub fn access_std(path: impl AsRef<Path>) -> io::Result<()> {
@@ -155,7 +126,8 @@ pub fn access_std(path: impl AsRef<Path>) -> io::Result<()> {
 }
 
 pub async fn lstat(path: impl AsRef<Path>) -> io::Result<Metadata> {
-    fs::symlink_metadata(path).await
+    let path = path.as_ref().to_path_buf();
+    native_io(move || std::fs::symlink_metadata(path)).await
 }
 
 pub fn lstat_std(path: impl AsRef<Path>) -> io::Result<Metadata> {
@@ -172,9 +144,8 @@ pub fn create_dir_all_std(path: &Path) -> io::Result<()> {
 }
 
 pub async fn make_dir_all(path: impl AsRef<Path>) -> io::Result<()> {
-    super::os::record_native_publication(path.as_ref());
     let path = path.as_ref().to_path_buf();
-    tokio::task::spawn_blocking(move || create_dir_all_std(&path)).await?
+    native_io(move || create_dir_all_std(&path)).await
 }
 
 fn is_dir_error(e: &io::Error) -> bool {
@@ -187,9 +158,13 @@ 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
-    match fs::remove_file(path.as_ref()).await {
+    let file_path = path.as_ref().to_path_buf();
+    match native_io(move || std::fs::remove_file(file_path)).await {
         Ok(()) => Ok(()),
-        Err(e) if is_dir_error(&e) => fs::remove_dir(path.as_ref()).await,
+        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) => Err(e),
     }
 }
@@ -197,9 +172,13 @@ 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
-    match fs::remove_file(path.as_ref()).await {
+    let file_path = path.as_ref().to_path_buf();
+    match native_io(move || std::fs::remove_file(file_path)).await {
         Ok(()) => Ok(()),
-        Err(e) if is_dir_error(&e) => fs::remove_dir_all(path.as_ref()).await,
+        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) => Err(e),
     }
 }
@@ -226,18 +205,18 @@ pub fn remove_all_std(path: impl AsRef<Path>) -> io::Result<()> {
 
 #[cfg(test)]
 pub async fn mkdir(path: impl AsRef<Path>) -> io::Result<()> {
-    super::os::record_native_publication(path.as_ref());
-    fs::create_dir(path.as_ref()).await
+    let path = path.as_ref().to_path_buf();
+    native_io(move || std::fs::create_dir(path)).await
 }
 
 pub async fn rename(from: impl AsRef<Path>, to: impl AsRef<Path>) -> io::Result<()> {
-    super::os::record_native_publication(to.as_ref());
-    fs::rename(from, to).await
+    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
 }
 
 #[cfg(any(not(windows), test))]
 pub fn rename_std(from: impl AsRef<Path>, to: impl AsRef<Path>) -> io::Result<()> {
-    super::os::record_native_publication(to.as_ref());
     std::fs::rename(from, to)
 }
 
@@ -296,7 +275,7 @@ pub async fn cached_access(path: impl AsRef<Path>) -> io::Result<()> {
     }
 
     let path_buf = path.to_path_buf();
-    let result = fs::metadata(&path_buf).await;
+    let result = access(&path_buf).await;
 
     match &result {
         Ok(_) => BUCKET_EXISTENCE_CACHE.record(path_buf, true),
@@ -311,6 +290,7 @@ 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());
 }
 
@@ -320,6 +300,89 @@ 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

@@ -14,6 +14,18 @@
 
 //! 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;
@@ -25,18 +37,118 @@ 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: AdaptivePermit;
+    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)
 }
 
 #[derive(Clone, Copy, Debug, Eq, PartialEq)]
@@ -51,7 +163,7 @@ pub(crate) struct DiskIoContext {
     pub(crate) cancellation: CancellationToken,
     pub(crate) admission: Option<Arc<DiskIoAdmission>>,
     pub(crate) permit: Option<DiskIoPermit>,
-    pub(crate) resource_unit: Option<AdaptivePermit>,
+    pub(crate) resource_unit: Option<ResourceIoUnit>,
 }
 
 /// Mark disk I/O issued by `future` as background work for local-disk admission.
@@ -78,24 +190,46 @@ 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(unit, future).await
+    RESOURCE_IO_UNIT.scope(ResourceIoUnit::from(unit), future).await
 }
 
-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()
-    })
+/// 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()
 }
 
 /// 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<AdaptivePermit>, future: F) -> F::Output {
+pub(crate) async fn with_optional_resource_unit<F: Future>(unit: Option<ResourceIoUnit>, future: F) -> F::Output {
     match unit {
-        Some(unit) => with_background_resource_unit(unit, future).await,
+        Some(unit) => RESOURCE_IO_UNIT.scope(unit, future).await,
         None => future.await,
     }
 }
@@ -233,7 +367,7 @@ impl DiskIoAdmission {
         self.foreground_with_resource(current_resource_unit())
     }
 
-    fn foreground_with_resource(self: &Arc<Self>, resource_unit: Option<AdaptivePermit>) -> DiskIoPermit {
+    fn foreground_with_resource(self: &Arc<Self>, resource_unit: Option<ResourceIoUnit>) -> DiskIoPermit {
         self.foreground_active.fetch_add(1, Ordering::AcqRel);
         if self.background_waiters.load(Ordering::Acquire) > 0 {
             self.record_state();
@@ -254,7 +388,7 @@ impl DiskIoAdmission {
     async fn background_with_resource(
         self: &Arc<Self>,
         cancellation: &CancellationToken,
-        resource_unit: Option<AdaptivePermit>,
+        resource_unit: Option<ResourceIoUnit>,
     ) -> std::io::Result<DiskIoPermit> {
         let started_at = Instant::now();
         let ticket = {
@@ -429,7 +563,7 @@ impl DiskIoPermit {
 struct DiskIoPermitLease {
     admission: Arc<DiskIoAdmission>,
     class: DiskIoClass,
-    resource_unit: Option<AdaptivePermit>,
+    resource_unit: Option<ResourceIoUnit>,
 }
 
 pub(crate) fn spawn_blocking_with_disk_io_permit<T, F>(
@@ -450,6 +584,18 @@ 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 {
@@ -595,6 +741,63 @@ 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

@@ -0,0 +1,547 @@
+// 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

@@ -0,0 +1,443 @@
+// 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

@@ -0,0 +1,268 @@
+// 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

@@ -0,0 +1,309 @@
+// 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_write_before_open, run_rename_data_after_first_publication};
+use super::{run_inline_before_file_sync_admission, run_owned_file_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,
@@ -329,6 +329,38 @@ 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(RenameDataResp),
+    CommitErr(DiskError),
+    Fallback(os::RenameCommitGuard, Option<Bytes>, FileInfo),
+}
+
 async fn prepare_rename_commit_and_destination_metadata(
     create_source_parent: bool,
     source_parent: &Path,
@@ -571,6 +603,9 @@ 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;
         }
@@ -642,20 +677,8 @@ impl LocalDisk {
         };
         let dst_file_path = self.io_get_object_open_path(dst_volume, format!("{}/{}", dst_path, STORAGE_FORMAT_FILE).as_str())?;
 
-        // Multipart restore completion has validated staged local parts,
-        // while its public status stays pending until finalization.
-        let pending_multipart_restore = src_volume == crate::disk::RUSTFS_META_MULTIPART_BUCKET
-            && fi
-                .metadata
-                .get(rustfs_filemeta::metadata_keys::RESTORE)
-                .and_then(|value| rustfs_filemeta::parse_restore_obj_status(value).ok())
-                .is_some_and(|status| status.is_restore_in_progress == Some(true));
-        if pending_multipart_restore && fi.data_dir.is_none_or(|dir| dir.is_nil()) {
-            return Err(DiskError::FileCorrupt);
-        }
-
         // data_dir path (only used by the non-inline commit branch)
-        let has_data_dir_path = if no_inline && (!fi.is_remote() || pending_multipart_restore) {
+        let has_data_dir_path = if no_inline && !fi.is_remote() {
             if let Some(data_dir) = fi
                 .data_dir
                 .map(|dir| rustfs_utils::path::retain_slash(dir.to_string().as_str()))
@@ -710,6 +733,216 @@ 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()
+            && !super::has_rename_data_test_failpoints(dst_path)
+            && !crash_inject::is_armed(CrashPoint::RenameAfterDataRename, dst_path)
+            && !crash_inject::is_armed(CrashPoint::RenameAfterBackupBeforeMetaCommit, dst_path)
+            && !crash_inject::is_armed(CrashPoint::RenameAfterMetaCommit, dst_path)
+            && !super::has_delete_version_test_failpoints()
+        {
+            #[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 can share versions or require rollback
+                // restoration when a post-rename directory sync fails.
+                if is_cancelled() || (sync_commit_metadata && has_dst_buf.is_some()) {
+                    return Ok(FusedCommitAttempt::Fallback(guard, has_dst_buf, 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, 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();
+                }
+
+                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, sync_commit_metadata)?;
+
+                if no_inline {
+                    if sync_data_shards && let Some((src_data_path, _)) = has_data_dir_path_owned.as_ref() {
+                        let sync_result = if 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
+                        {
+                            return Err(err);
+                        }
+                    }
+                    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)
+                    {
+                        return Ok(FusedCommitAttempt::CommitErr(err));
+                    }
+                    #[cfg(test)]
+                    if has_data_dir_path_owned.is_some() {
+                        run_rename_data_after_first_publication(&root_owned, &dst_volume_str, &dst_path_str);
+                    }
+                }
+
+                if let Err(err) = os::rename_prepared_source_on_thread(
+                    prepared_metadata_source,
+                    &src_file_path_owned,
+                    &dst_file_path_owned,
+                    &skip_parent,
+                    &publication_root_owned,
+                    &guard,
+                ) {
+                    if no_inline && let Some((src_data_path, dst_data_path)) = has_data_dir_path_owned.as_ref() {
+                        let _ = std::fs::rename(dst_data_path, src_data_path);
+                    }
+                    return Ok(FusedCommitAttempt::CommitErr(err));
+                }
+
+                if sync_commit_metadata
+                    && let Err(err) =
+                        fsync_inline_commit_std(&dst_file_path_owned, &dst_volume_dir_owned, destination_was_absent, None, &guard)
+                {
+                    if no_inline && let Some((src_data_path, dst_data_path)) = has_data_dir_path_owned.as_ref() {
+                        let _ = std::fs::rename(dst_data_path, src_data_path);
+                    }
+                    return Err(err);
+                }
+
+                if let Some(parent) = src_file_path_owned.parent() {
+                    let _ = std::fs::remove_dir(parent);
+                }
+
+                Ok(FusedCommitAttempt::Committed(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::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);
+                }
+                Ok(FusedCommitAttempt::Fallback(guard, dst_buf, restored_fi)) => {
+                    fi = restored_fi;
+                    (guard, dst_buf)
+                }
+            }
+        } 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
@@ -852,7 +1085,7 @@ impl LocalDisk {
                 async move {
                     os::run_blocking_namespace_operation(owned_mutation_lease, move || {
                         #[cfg(test)]
-                        run_owned_file_write_before_open(&src_file_path);
+                        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,
@@ -1038,7 +1271,7 @@ impl LocalDisk {
                 // deterministic rollback backup.
                 let write_result = os::run_blocking_namespace_operation(commit.mutation_lease.clone(), move || {
                     #[cfg(test)]
-                    run_owned_file_write_before_open(&backup_path);
+                    run_owned_file_before_open(&backup_path);
                     backup_path_guard.write_file_for_path_access(
                         &backup_path,
                         backup_bytes.as_ref(),

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

@@ -1317,7 +1317,7 @@ impl LocalDisk {
                     continue;
                 };
                 #[cfg(test)]
-                run_owned_file_write_before_open(&record_destination.join(name));
+                run_owned_file_before_open(&record_destination.join(name));
                 let mut file = std::fs::File::create(staged.path().join(name))?;
                 std::io::Write::write_all(&mut file, bytes)?;
                 if sync && !bytes.is_empty() {
@@ -1795,7 +1795,7 @@ impl LocalDisk {
                         self.write_all_meta_with_namespace_owner(
                             volume,
                             &format!("{object}/{STORAGE_FORMAT_FILE}"),
-                            &target,
+                            target,
                             true,
                             owner.clone(),
                         )
@@ -2090,6 +2090,474 @@ impl LocalDisk {
     pub(super) async fn delete_recovery_barrier(&self, volume: &str, object: &str, transaction: Uuid, stage: &str) -> Result<()> {
         barrier(volume, object, transaction, stage, &self.root).await
     }
+
+    pub(super) async fn try_fused_recoverable_delete_version(
+        &self,
+        volume: &str,
+        object: &str,
+        fi: &FileInfo,
+        opts: &DeleteOptions,
+        transaction: Uuid,
+        owner: Option<Arc<dyn Send + Sync>>,
+    ) -> Result<Option<()>> {
+        if !opts.recoverable_delete
+            || opts.undo_write
+            || opts.expected_delete_marker.is_some()
+            || pool_meta_native::is_object(&self.root, volume, object)
+            || has_delete_version_test_failpoints()
+        {
+            return Ok(None);
+        }
+        self.reject_multipart_delete_recovery_mutation(volume, object)?;
+        self.wait_for_startup_cleanup().await;
+
+        let (_, file_path) = self.io_get_bucket_and_object_path(volume, object)?;
+        check_path_length(file_path.to_string_lossy().as_ref())?;
+        let xl_path = path_join(&[file_path.as_path(), Path::new(STORAGE_FORMAT_FILE)]);
+        let destination = file_path.join(transaction.to_string());
+        let staging_root = self.io_get_bucket_path(RUSTFS_META_TMP_BUCKET)?;
+        let sync = effective_durability(volume).syncs_commit_metadata();
+        let incarnation = opts.delete_recovery_bucket_incarnation;
+        let lease = os::acquire_namespace_mutation_lease_with_owner(&destination, owner).await;
+        let fi_clone = fi.clone();
+        let volume_str = volume.to_owned();
+        let object_str = object.to_owned();
+
+        let res = os::run_blocking_namespace_operation_with_sync(
+            lease,
+            sync,
+            move || -> std::io::Result<Result<Option<Option<Uuid>>>> {
+                let buf = match std::fs::read(&xl_path) {
+                    Ok(buf) => buf,
+                    Err(err) if err.kind() == ErrorKind::NotFound => return Ok(Ok(None)),
+                    Err(err) => return Err(err),
+                };
+                let (old_dir, journal_raw) = match (|| -> Result<Option<(Option<Uuid>, Vec<u8>)>> {
+                    let mut meta = FileMeta::load(&buf)?;
+                    let deleted_versions: Vec<_> = meta
+                        .versions
+                        .iter()
+                        .map(|v| v.header.version_id.unwrap_or_default())
+                        .collect();
+                    let original_versions: Vec<_> = meta
+                        .versions
+                        .iter()
+                        .map(|v| generation(v.into_fileinfo(&volume_str, &object_str, true)?))
+                        .collect::<Result<_>>()?;
+                    let old_dir = meta.delete_version(&fi_clone)?;
+                    if old_dir.is_some_and(|dir| dir == transaction || dir.is_nil()) {
+                        return Err(DiskError::FileCorrupt);
+                    }
+                    if let Some(uuid) = old_dir {
+                        meta.data.remove(vec![fi_clone.version_id.unwrap_or_default(), uuid])?;
+                        let old_path = path_join(&[file_path.as_path(), Path::new(uuid.to_string().as_str())]);
+                        check_path_length(old_path.to_string_lossy().as_ref())?;
+                        if old_path.join(STORAGE_FORMAT_FILE).exists() {
+                            return Ok(None);
+                        }
+                    }
+                    if !meta.versions.is_empty() {
+                        return Ok(None);
+                    }
+                    let mut predecessors = BTreeSet::new();
+                    if let Ok(entries) = std::fs::read_dir(&file_path) {
+                        for (visited, entry) in entries.enumerate() {
+                            if visited >= 65536 {
+                                return Err(DiskError::DiskOngoingReq);
+                            }
+                            let entry = entry.map_err(to_file_error)?;
+                            let Some(id) = entry
+                                .file_name()
+                                .to_str()
+                                .and_then(|name| Uuid::parse_str(name).ok())
+                                .filter(|id| !id.is_nil() && *id != transaction)
+                            else {
+                                continue;
+                            };
+                            if !entry.file_type().map_err(to_file_error)?.is_dir() {
+                                return Err(DiskError::InvalidPath);
+                            }
+                            let prepared = regular_bytes(&entry.path().join(PREPARED))?;
+                            let receipt = regular_bytes(&entry.path().join(DELETE_QUORUM_COMMITTED_FILE))?;
+                            let mut records = Vec::new();
+                            if let Some(bytes) = prepared {
+                                records.push(
+                                    serde_json::from_slice::<DeleteRecoveryJournal>(&bytes)
+                                        .map_err(|_| DiskError::FileCorrupt)?,
+                                );
+                            }
+                            if let Some(bytes) = receipt.filter(|bytes| !bytes.is_empty()) {
+                                records.push(
+                                    serde_json::from_slice::<CommitReceipt>(&bytes)
+                                        .map_err(|_| DiskError::FileCorrupt)?
+                                        .journal,
+                                );
+                            }
+                            for record in records {
+                                if record.protocol_version != DELETE_RECOVERY_PROTOCOL_VERSION
+                                    || record.volume != volume_str
+                                    || record.object != object_str
+                                    || record.transaction != id
+                                    || incarnation.zip(record.bucket_incarnation).is_some_and(|(a, b)| a != b)
+                                    || record.predecessors.iter().any(|before| before.is_nil() || *before == id)
+                                {
+                                    return Err(DiskError::FileCorrupt);
+                                }
+                                predecessors.insert(id);
+                            }
+                        }
+                    }
+                    let mut sparse = fi_clone;
+                    sparse.data = None;
+                    let journal = DeleteRecoveryJournal {
+                        protocol_version: DELETE_RECOVERY_PROTOCOL_VERSION,
+                        volume: volume_str,
+                        object: object_str,
+                        transaction,
+                        bucket_incarnation: incarnation,
+                        original_digest: Some(digest(&buf)),
+                        target_digest: None,
+                        data_dirs: old_dir.into_iter().collect(),
+                        deleted_versions,
+                        requests: vec![sparse],
+                        original_versions,
+                        predecessors: predecessors.into_iter().collect(),
+                    };
+                    Ok(Some((old_dir, journal_bytes(&journal)?)))
+                })() {
+                    Ok(Some(pair)) => pair,
+                    Ok(None) => return Ok(Ok(None)),
+                    Err(err) => return Ok(Err(err)),
+                };
+                std::fs::create_dir_all(&staging_root)?;
+                let staged = tempfile::Builder::new()
+                    .prefix("delete-preparation-")
+                    .tempdir_in(&staging_root)?;
+                for (name, bytes) in [
+                    (STORAGE_FORMAT_FILE_BACKUP, buf.as_slice()),
+                    (PREPARED, journal_raw.as_slice()),
+                ] {
+                    let mut file = std::fs::File::create(staged.path().join(name))?;
+                    std::io::Write::write_all(&mut file, bytes)?;
+                    if sync && !bytes.is_empty() {
+                        file.sync_data()?;
+                    }
+                }
+                if sync {
+                    os::fsync_dir_std(staged.path())?;
+                }
+                match std::fs::symlink_metadata(&destination) {
+                    Ok(metadata) if metadata.is_dir() => match std::fs::remove_dir(&destination) {
+                        Ok(()) => {}
+                        Err(err) if err.kind() == ErrorKind::NotFound => {}
+                        Err(err) if is_dir_not_empty_error(&err) => return Ok(Err(DiskError::OutdatedXLMeta)),
+                        Err(err) => return Err(err),
+                    },
+                    Ok(_) => return Ok(Err(DiskError::OutdatedXLMeta)),
+                    Err(err) if err.kind() == ErrorKind::NotFound => {}
+                    Err(err) => return Err(err),
+                }
+                if let Some(parent) = destination.parent() {
+                    std::fs::create_dir_all(parent)?;
+                }
+                std::fs::rename(staged.path(), &destination)?;
+                if sync {
+                    os::fsync_dir_std(&file_path)?;
+                }
+                let mut reserved_data_path = None;
+                if let Some(uuid) = old_dir {
+                    let old_path = file_path.join(uuid.to_string());
+                    if old_path.is_dir() {
+                        let reserved_marker = old_path.join(format!("{RESERVED_DELETE_DATA_DIR_MARKER_PREFIX}{transaction}"));
+                        let marker = std::fs::File::create(&reserved_marker)?;
+                        if sync {
+                            marker.sync_all()?;
+                            os::fsync_dir_std(&old_path)?;
+                        }
+                        reserved_data_path = Some((old_path, reserved_marker));
+                    }
+                }
+                if let Err(err) = std::fs::remove_file(&xl_path)
+                    && err.kind() != ErrorKind::NotFound
+                {
+                    if let Some((_, reserved_marker)) = &reserved_data_path {
+                        let _ = std::fs::remove_file(reserved_marker);
+                    }
+                    let _ = std::fs::remove_dir_all(&destination);
+                    return Err(err);
+                }
+                if sync {
+                    os::fsync_dir_std(&file_path)?;
+                }
+                if let Some((old_path, reserved_marker)) = reserved_data_path {
+                    let recovery_marker = old_path.join(format!("{RECOVERY_DELETE_DATA_DIR_MARKER_PREFIX}{transaction}"));
+                    match std::fs::rename(&reserved_marker, &recovery_marker) {
+                        Ok(()) if sync => os::fsync_dir_std(&old_path)?,
+                        Ok(()) => {}
+                        Err(err) if err.kind() == ErrorKind::NotFound => {}
+                        Err(err) => return Err(err),
+                    }
+                }
+                Ok(Ok(Some(old_dir)))
+            },
+        )
+        .await
+        .map_err(to_file_error)??;
+
+        let Some(old_dir) = res else {
+            return Ok(None);
+        };
+        if let Some(uuid) = old_dir {
+            self.io_backend
+                .invalidate_cached_fds_under(volume, &format!("{object}/{uuid}"));
+        }
+        Ok(Some(()))
+    }
+
+    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)>> {
+        self.reject_multipart_delete_recovery_mutation(volume, object)?;
+        if !safe_path(object, false) || transaction.is_nil() {
+            return Err(DiskError::InvalidPath);
+        }
+        let object_path = self.get_object_path(volume, object)?;
+        let metadata_owner = os::acquire_metadata_mutation_lease(&object_path, namespace_owner).await;
+        let volume_guard = os::disk_volume_mutation_lock(&self.root, volume).read_owned().await;
+        let owner: Option<Arc<dyn Send + Sync>> = Some(Arc::new((metadata_owner, volume_guard)));
+
+        let root = self.io_get_object_path(volume, object)?;
+        let rollback = root.join(transaction.to_string());
+        let receipt_path = rollback.join(DELETE_QUORUM_COMMITTED_FILE);
+        let staging_root = self.io_get_bucket_path(RUSTFS_META_TMP_BUCKET)?;
+        let sync = effective_durability(volume).syncs_commit_metadata();
+        let lease = os::acquire_namespace_mutation_lease_with_owner(&receipt_path, owner).await;
+        let volume_str = volume.to_owned();
+        let object_str = object.to_owned();
+
+        os::run_blocking_namespace_operation_with_sync(
+            lease,
+            sync,
+            move || -> std::io::Result<Result<Option<(DeleteRecoveryJournal, bool, bool)>>> {
+                let prepared = match regular_bytes(&rollback.join(PREPARED)) {
+                    Ok(Some(bytes)) => bytes,
+                    Ok(None) => return Ok(Ok(None)),
+                    Err(e) => return Ok(Err(e)),
+                };
+                let Ok(journal) = serde_json::from_slice::<DeleteRecoveryJournal>(&prepared) else {
+                    return Ok(Err(DiskError::FileCorrupt));
+                };
+                if journal.protocol_version != DELETE_RECOVERY_PROTOCOL_VERSION
+                    || journal.volume != volume_str
+                    || journal.object != object_str
+                    || journal.transaction != transaction
+                    || journal.transaction.is_nil()
+                    || journal.data_dirs.iter().any(|id| id.is_nil() || *id == transaction)
+                {
+                    return Ok(Err(DiskError::FileCorrupt));
+                }
+                let current_exists = match regular_file_exists(&root.join(STORAGE_FORMAT_FILE)) {
+                    Ok(exists) => exists,
+                    Err(e) => return Ok(Err(e)),
+                };
+                let unversioned_target_absent = journal.target_digest.is_none() && !current_exists;
+                if !unversioned_target_absent {
+                    return Ok(Ok(None));
+                }
+                let mut sole_transaction = journal.predecessors.is_empty();
+                if sole_transaction {
+                    match std::fs::read_dir(&root) {
+                        Ok(entries) => {
+                            for entry in entries {
+                                let entry = entry?;
+                                let Ok(name) = entry.file_name().into_string() else {
+                                    sole_transaction = false;
+                                    break;
+                                };
+                                if let Some(id) = canonical_uuid(&name).filter(|id| !id.is_nil())
+                                    && id != transaction
+                                    && !journal.data_dirs.contains(&id)
+                                {
+                                    sole_transaction = false;
+                                    break;
+                                }
+                            }
+                        }
+                        Err(err) if err.kind() == ErrorKind::NotFound => {}
+                        Err(err) => return Err(err),
+                    }
+                }
+                let receipt = CommitReceipt {
+                    journal: journal.clone(),
+                    finished: false,
+                };
+                let receipt_bytes = serde_json::to_vec(&receipt).map_err(std::io::Error::other)?;
+                std::fs::create_dir_all(&staging_root)?;
+                let mut staged = tempfile::NamedTempFile::new_in(&staging_root)?;
+                std::io::Write::write_all(staged.as_file_mut(), &receipt_bytes)?;
+                if sync && !receipt_bytes.is_empty() {
+                    staged.as_file().sync_data()?;
+                }
+                std::fs::rename(staged.path(), &receipt_path)?;
+                if sync {
+                    os::fsync_dir_std(&rollback)?;
+                }
+                Ok(Ok(Some((journal, sole_transaction, unversioned_target_absent))))
+            },
+        )
+        .await
+        .map_err(to_file_error)?
+    }
+
+    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> {
+        fn ignore_not_found(res: std::io::Result<()>) -> std::io::Result<()> {
+            match res {
+                Ok(()) => Ok(()),
+                Err(err) if err.kind() == ErrorKind::NotFound => Ok(()),
+                Err(err) => Err(err),
+            }
+        }
+        self.reject_multipart_delete_recovery_mutation(volume, object)?;
+        if !safe_path(object, false) || transaction.is_nil() {
+            return Err(DiskError::InvalidPath);
+        }
+        let object_path = self.get_object_path(volume, object)?;
+        let metadata_owner = os::acquire_metadata_mutation_lease(&object_path, namespace_owner).await;
+        let volume_guard = os::disk_volume_mutation_lock(&self.root, volume).read_owned().await;
+        let owner: Option<Arc<dyn Send + Sync>> = Some(Arc::new((metadata_owner, volume_guard)));
+
+        let mut claims: Vec<SnapshotLeaseDeleteClaim> = Vec::with_capacity(journal.data_dirs.len());
+        for data_dir in &journal.data_dirs {
+            let key = SnapshotLeaseKey {
+                volume: volume.to_owned(),
+                path: format!("{object}/{data_dir}"),
+            };
+            let opts = DeleteOptions {
+                recursive: true,
+                old_data_dir: Some(transaction),
+                ..Default::default()
+            };
+            let Some(claim) = self.claim_snapshot_delete(key, SnapshotPendingDelete::Ordinary(opts)) else {
+                for prior in claims {
+                    prior.finish(false);
+                }
+                return Ok(false);
+            };
+            claims.push(claim);
+        }
+
+        let bucket_path = self.io_get_bucket_path(volume)?;
+        let root = self.io_get_object_path(volume, object)?;
+        let rollback = root.join(transaction.to_string());
+        let receipt_path = rollback.join(DELETE_QUORUM_COMMITTED_FILE);
+        let sync = effective_durability(volume).syncs_commit_metadata();
+        let lease = os::acquire_namespace_mutation_lease_with_owner(&receipt_path, owner).await;
+        let data_dirs = journal.data_dirs.clone();
+        let prune_paths: Vec<_> = rollback
+            .ancestors()
+            .take_while(|dir| *dir != bucket_path.as_path() && dir.starts_with(&bucket_path))
+            .map(Path::to_path_buf)
+            .collect();
+
+        let res = os::run_blocking_namespace_operation_with_sync(lease, sync, move || -> std::io::Result<()> {
+            let committed = format!("{DELETE_DATA_DIR_MARKER_PREFIX}{transaction}");
+            let recovery_committed = format!("{RECOVERY_DELETE_DATA_DIR_MARKER_PREFIX}{transaction}");
+            let reserved = format!("{RESERVED_DELETE_DATA_DIR_MARKER_PREFIX}{transaction}");
+            for data_dir in &data_dirs {
+                for base in [&root, &rollback] {
+                    let dir_path = base.join(data_dir.to_string());
+                    match std::fs::read_dir(&dir_path) {
+                        Ok(entries) => {
+                            let mut removable = Vec::new();
+                            let mut preserve_dir = false;
+                            for entry in entries {
+                                let entry = entry?;
+                                let name = entry.file_name();
+                                let Some(name) = name.to_str() else {
+                                    preserve_dir = true;
+                                    continue;
+                                };
+                                if entry.file_type()?.is_file()
+                                    && (delete_recovery_part_file(name)
+                                        || name == committed
+                                        || name == recovery_committed
+                                        || name == reserved
+                                        || is_delete_transaction_marker(name, RESERVED_DELETE_DATA_DIR_MARKER_PREFIX))
+                                {
+                                    removable.push(entry.path());
+                                } else {
+                                    preserve_dir = true;
+                                }
+                            }
+                            for path in removable {
+                                ignore_not_found(std::fs::remove_file(path))?;
+                            }
+                            if sync {
+                                os::fsync_dir_std(&dir_path)?;
+                            }
+                            if !preserve_dir {
+                                match std::fs::remove_dir(&dir_path) {
+                                    Ok(()) => {}
+                                    Err(err) if err.kind() == ErrorKind::NotFound || is_dir_not_empty_error(&err) => {}
+                                    Err(err) => return Err(err),
+                                }
+                            }
+                        }
+                        Err(err) if err.kind() == ErrorKind::NotFound => {}
+                        Err(err) => return Err(err),
+                    }
+                }
+            }
+            if !data_dirs.is_empty() && sync && root.is_dir() {
+                os::fsync_dir_std(&root)?;
+            }
+            for name in [
+                STORAGE_FORMAT_FILE_BACKUP,
+                DELETE_MARKER_ROLLBACK_FILE,
+                TARGET,
+                PREPARED,
+                FINISHED,
+            ] {
+                ignore_not_found(std::fs::remove_file(rollback.join(name)))?;
+            }
+            if sync {
+                os::fsync_dir_std(&rollback)?;
+            }
+            ignore_not_found(std::fs::remove_file(&receipt_path))?;
+            for dir_path in &prune_paths {
+                if let Err(err) = std::fs::remove_dir(dir_path) {
+                    if is_dir_not_empty_error(&err) {
+                        break;
+                    }
+                    if !is_benign_object_rmdir_error(&err) {
+                        return Err(std::io::Error::other(FileAccessDeniedWithContext {
+                            path: dir_path.clone(),
+                            source: err,
+                        }));
+                    }
+                }
+            }
+            Ok(())
+        })
+        .await;
+
+        let ok = res.is_ok();
+        for claim in claims {
+            claim.finish(ok);
+        }
+        res.map(|()| true).map_err(|err| to_file_error(err).into())
+    }
 }
 
 #[cfg(not(feature = "e2e-test-hooks"))]
@@ -3038,12 +3506,12 @@ mod tests {
         let exit = native.exit_signal.as_ref().expect("fixture cleanup lifecycle");
         exit.send(()).expect("stop the existing idle cleanup task");
         tokio::time::timeout(Duration::from_secs(5), async {
-            while exit.receiver_count() != 0 || root_file.strong_count() != 2 {
+            while exit.receiver_count() != 0 || root_file.strong_count() != 3 {
                 tokio::task::yield_now().await;
             }
         })
         .await
-        .expect("only LocalDisk's publication and mount fields may retain the initial root FD");
+        .expect("only LocalDisk's publication, mount and I/O backend fields may retain the initial root FD");
         let transaction = Uuid::new_v4();
         let applied = apply(&native, transaction).await;
         let committed = native
@@ -3309,6 +3777,171 @@ mod tests {
         inspected
     }
 
+    #[tokio::test]
+    async fn fused_delete_recovery_survives_interrupted_prepare_and_publication() {
+        for published in [false, true] {
+            let (_temp, disk, _info, original) = fixture().await;
+            let transaction = Uuid::new_v4();
+            let prepared = disk
+                .try_fused_recoverable_delete_version(
+                    "recovery",
+                    "object",
+                    &request(),
+                    &DeleteOptions {
+                        recoverable_delete: true,
+                        old_data_dir: Some(transaction),
+                        ..Default::default()
+                    },
+                    transaction,
+                    None,
+                )
+                .await
+                .expect("prepare fused deletion");
+            assert_eq!(prepared, Some(()), "the test must exercise the fused path");
+
+            if published {
+                let (_, sole, target_absent) = disk
+                    .try_publish_prepared_delete_local("recovery", "object", transaction, None)
+                    .await
+                    .expect("publish fused receipt")
+                    .expect("fused publication must apply");
+                assert!(sole && target_absent);
+            }
+
+            let mut state = disk
+                .inspect_delete_transaction("recovery", "object", transaction)
+                .await
+                .expect("inspect persisted state after interruption");
+            if published {
+                assert_eq!(state.state, DeleteRecoveryState::QuorumCommitted);
+                for action in [DeleteRecoveryAction::FinishCommit, DeleteRecoveryAction::FinalizeCommit] {
+                    state = disk
+                        .settle_delete_transaction("recovery", "object", transaction, state.fingerprint, action)
+                        .await
+                        .expect("finish published deletion through recovery");
+                }
+                assert_eq!(state.state, DeleteRecoveryState::Absent);
+                assert!(disk.read_all("recovery", "object/xl.meta").await.is_err());
+            } else {
+                assert_eq!(state.state, DeleteRecoveryState::NewPrepared);
+                state = disk
+                    .settle_delete_transaction(
+                        "recovery",
+                        "object",
+                        transaction,
+                        state.fingerprint,
+                        DeleteRecoveryAction::Rollback,
+                    )
+                    .await
+                    .expect("roll back uncommitted fused deletion");
+                assert_eq!(state.state, DeleteRecoveryState::Absent);
+                assert_eq!(
+                    disk.read_all("recovery", "object/xl.meta")
+                        .await
+                        .expect("restore original metadata")
+                        .as_ref(),
+                    original
+                );
+            }
+        }
+    }
+
+    #[tokio::test]
+    async fn fused_delete_recovery_preserves_or_removes_shard_after_interruption() {
+        use crate::erasure::coding::BitrotWriter;
+
+        for mode in 0..3 {
+            let published = mode != 0;
+            let (_temp, disk, _info, _) = fixture().await;
+            let data_dir = Uuid::new_v4();
+            let payload = Bytes::from_static(b"original shard");
+            let mut info = test_file_info("object", Uuid::nil(), Some(data_dir), None);
+            info.size = i64::try_from(payload.len()).expect("payload size");
+            info.erasure.block_size = payload.len();
+            info.parts[0].size = payload.len();
+            info.parts[0].actual_size = info.size;
+            let original = test_meta(info.clone());
+            let mut writer = BitrotWriter::new(
+                std::io::Cursor::new(Vec::new()),
+                info.erasure.shard_size(),
+                HashAlgorithm::HighwayHash256S,
+            );
+            writer.write(&payload).await.expect("encode shard");
+            writer.shutdown().await.expect("finish shard encoding");
+            let encoded = writer.into_inner().into_inner();
+            let root = disk.io_get_object_path("recovery", "object").expect("object path");
+            fs::write(root.join(STORAGE_FORMAT_FILE), &original)
+                .await
+                .expect("write shard metadata");
+            let shard_dir = root.join(data_dir.to_string());
+            fs::create_dir_all(&shard_dir).await.expect("create shard directory");
+            fs::write(shard_dir.join("part.1"), &encoded)
+                .await
+                .expect("write original shard");
+            let transaction = Uuid::new_v4();
+            assert_eq!(
+                disk.try_fused_recoverable_delete_version(
+                    "recovery",
+                    "object",
+                    &request(),
+                    &DeleteOptions {
+                        recoverable_delete: true,
+                        old_data_dir: Some(transaction),
+                        ..Default::default()
+                    },
+                    transaction,
+                    None,
+                )
+                .await
+                .expect("prepare fused shard deletion"),
+                Some(()),
+                "the test must exercise the fused path"
+            );
+            if published {
+                let (journal, sole, target_absent) = disk
+                    .try_publish_prepared_delete_local("recovery", "object", transaction, None)
+                    .await
+                    .expect("publish fused receipt")
+                    .expect("fused publication must apply");
+                assert!(sole && target_absent);
+                if mode == 2 {
+                    assert!(
+                        disk.try_finish_and_finalize_prepared_delete_local("recovery", "object", transaction, &journal, None)
+                            .await
+                            .expect("finish fused deletion"),
+                        "the fused finalization must apply"
+                    );
+                    assert!(!shard_dir.exists(), "fused finalization must remove the shard");
+                    assert!(!root.join(STORAGE_FORMAT_FILE).exists());
+                    assert!(!root.join(transaction.to_string()).exists());
+                    continue;
+                }
+            }
+            let mut state = disk
+                .inspect_delete_transaction("recovery", "object", transaction)
+                .await
+                .expect("inspect persisted state");
+            let actions = if published {
+                vec![DeleteRecoveryAction::FinishCommit, DeleteRecoveryAction::FinalizeCommit]
+            } else {
+                vec![DeleteRecoveryAction::Rollback]
+            };
+            for action in actions {
+                state = disk
+                    .settle_delete_transaction("recovery", "object", transaction, state.fingerprint, action)
+                    .await
+                    .expect("recover shard deletion");
+            }
+            assert_eq!(state.state, DeleteRecoveryState::Absent);
+            if published {
+                assert!(!shard_dir.exists(), "committed deletion must remove the shard");
+            } else {
+                assert_eq!(fs::read(root.join(STORAGE_FORMAT_FILE)).await.expect("restore metadata"), original);
+                assert_eq!(fs::read(shard_dir.join("part.1")).await.expect("restore shard"), encoded);
+            }
+        }
+    }
+
     #[tokio::test]
     async fn delete_recovery_uncommitted_inline_rolls_back_exact_bytes() {
         let (_temp, disk, _info, original) = fixture().await;

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, InternalBuf::Ref(&replacement), SyncMode::FileOnly, &tmp_volume)
+                self.write_all_internal(&temporary, replacement, SyncMode::FileOnly, &tmp_volume)
                     .await?;
                 os::rename_metadata_and_sync_with_lease(
                     temporary,

crates/ecstore/src/disk/mod.rs

@@ -30,15 +30,21 @@ 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;
+pub(crate) use io_admission::{DiskIoClass, test_resource_units};
 pub(crate) use io_admission::{
-    acquire_context_disk_io_permit, current_disk_io_context, current_resource_unit, with_optional_disk_io_context,
-    with_optional_resource_unit,
+    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,
 };
-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";
@@ -305,6 +311,14 @@ 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 {
@@ -387,6 +401,39 @@ impl Disk {
         }
     }
 
+    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,
@@ -613,13 +660,6 @@ impl DiskAPI for Disk {
         }
     }
 
-    async fn bucket_creation_witness(&self, volume: &str) -> Result<Option<os::NativeBucketCreationWitness>> {
-        match self {
-            Disk::Local(local_disk) => local_disk.bucket_creation_witness(volume).await,
-            Disk::Remote(_) => Ok(None),
-        }
-    }
-
     #[tracing::instrument(level = "trace", skip_all)]
     async fn make_volume(&self, volume: &str) -> Result<()> {
         match self {
@@ -1477,11 +1517,6 @@ pub trait DiskAPI: Debug + Send + Sync + 'static {
     // NSScanner
 
     // Volume operations.
-    /// Unknown or remote backends cannot attest process-local publication history.
-    async fn bucket_creation_witness(&self, _volume: &str) -> Result<Option<os::NativeBucketCreationWitness>> {
-        Ok(None)
-    }
-
     async fn make_volume(&self, volume: &str) -> Result<()>;
     async fn make_volumes(&self, volume: Vec<&str>) -> Result<()>;
     async fn list_volumes(&self) -> Result<Vec<VolumeInfo>>;
@@ -2257,7 +2292,7 @@ impl DeleteRecoveryJournal {
             }
             let id = request.version_id.unwrap_or_default();
             let Some(original) = originals.get(&id) else {
-                return !id.is_nil() && !locals.contains_key(&id);
+                return false;
             };
             match locals.get(&id) {
                 Some(local) => local == original,
@@ -2307,10 +2342,7 @@ impl DeleteRecoveryJournal {
             };
             match (local, remote) {
                 (Some(local), Some(remote)) => local == remote,
-                (None, None) => {
-                    (!(request.deleted && request.mark_deleted) && request.version_id.is_some_and(|id| !id.is_nil()))
-                        || (self.original_digest.is_none() && authority.original_digest.is_none())
-                }
+                (None, None) => self.original_digest.is_none() && authority.original_digest.is_none(),
                 _ => false,
             }
         })
@@ -3635,46 +3667,6 @@ mod delete_recovery_adoption_tests {
         };
         assert!(journal.matches_adoption_source(&[]), "certified non-null removal can already be absent");
         assert!(journal.matches_adoption_source(std::slice::from_ref(&source)));
-        let missing = Uuid::new_v4();
-        journal.requests.push(FileInfo {
-            version_id: Some(missing),
-            ..Default::default()
-        });
-        journal.original_digest = Some([3; 32]);
-        assert!(
-            journal.matches_prepared_authority(&journal),
-            "an explicit UUID absent from both prepared sources remains a no-op with original metadata"
-        );
-        assert!(journal.matches_adoption_source(&[]), "both non-null versions can remain absent");
-        assert!(
-            journal.matches_adoption_source(std::slice::from_ref(&source)),
-            "a missing non-null version in the batch remains a no-op"
-        );
-        let mut unexpected = source.clone();
-        unexpected.version_id = Some(missing);
-        let mut foreign_preparation = journal.clone();
-        foreign_preparation.original_versions.push(unexpected.clone());
-        assert!(
-            !journal.matches_prepared_authority(&foreign_preparation)
-                && !foreign_preparation.matches_prepared_authority(&journal),
-            "absence from only one prepared source cannot establish a generation"
-        );
-        assert!(
-            !journal.matches_adoption_source(&[source.clone(), unexpected]),
-            "a version absent from the authority cannot be deleted locally"
-        );
-        for version_id in [None, Some(Uuid::nil())] {
-            journal.requests.last_mut().expect("missing-version request").version_id = version_id;
-            assert!(
-                !journal.matches_prepared_authority(&journal),
-                "a missing null version with original metadata cannot establish its generation"
-            );
-            assert!(
-                !journal.matches_adoption_source(std::slice::from_ref(&source)),
-                "a missing null version cannot establish its generation"
-            );
-        }
-        journal.requests.pop();
         let mut foreign = source.clone();
         foreign.metadata_digest = [2; 32];
         assert!(!journal.matches_adoption_source(std::slice::from_ref(&foreign)));
@@ -3690,25 +3682,6 @@ mod delete_recovery_adoption_tests {
         assert!(journal.matches_adoption_source(std::slice::from_ref(&journal.original_versions[0])));
         journal.requests.clear();
         assert!(!journal.matches_adoption_source(&journal.original_versions));
-
-        let mut marker = journal.clone();
-        marker.requests = vec![FileInfo {
-            version_id: Some(id),
-            deleted: true,
-            mark_deleted: true,
-            ..Default::default()
-        }];
-        marker.original_versions.clear();
-        marker.original_digest = Some([3; 32]);
-        assert!(
-            !marker.matches_prepared_authority(&marker),
-            "a marker with original metadata requires a source generation"
-        );
-        marker.original_digest = None;
-        assert!(
-            marker.matches_prepared_authority(&marker),
-            "marker preparation without original metadata retains the existing allowance"
-        );
     }
 }
 

crates/ecstore/src/disk/uring_read_budget.rs

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

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

@@ -98,6 +98,9 @@ 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>,
@@ -118,6 +121,8 @@ 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,
@@ -209,6 +214,7 @@ 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);
         }
@@ -229,6 +235,28 @@ 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!(
@@ -339,6 +367,8 @@ 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 {
@@ -381,7 +411,9 @@ where
 
                     if chunks.len() == MAX_RETAINED_CHUNKS_PER_BLOCK {
                         if tail_buf.is_empty() {
-                            tail_buf.reserve_exact(need - (received - chunk.len()));
+                            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.extend_from_slice(&chunk);
                     } else {
@@ -657,7 +689,12 @@ pub async fn bitrot_verify<R: AsyncRead + Unpin + Send>(
     algo: HashAlgorithm,
     mut shard_size: usize,
 ) -> std::io::Result<()> {
-    let mut hash_buf = vec![0; algo.size()];
+    // 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 left = want_size;
 
     if left != bitrot_shard_file_size(part_size, shard_size, algo.clone()) {
@@ -665,21 +702,30 @@ pub async fn bitrot_verify<R: AsyncRead + Unpin + Send>(
     }
 
     while left > 0 {
-        let n = r.read_exact(&mut hash_buf).await?;
+        let n = r.read_exact(hash_buf).await?;
         left -= n;
 
         if left < shard_size {
             shard_size = left;
         }
 
-        let mut buf = get_ec_buffer(shard_size);
-        buf.resize(shard_size, 0);
-        let read = r.read_exact(&mut buf).await?;
+        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 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
-        return_ec_buffer(buf);
+        if let Some(buf) = pooled {
+            return_ec_buffer(buf);
+        }
         if !hash_ok {
             return Err(std::io::Error::other("bitrot hash mismatch"));
         }
@@ -698,15 +744,74 @@ 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(Vec<u8>),
+    InlineBuffer(InlineBuffer),
     /// 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(Vec::new())
+        Self::InlineBuffer(InlineBuffer::new())
     }
 
     /// Create a new disk writer from any AsyncWrite implementation
@@ -720,15 +825,15 @@ 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),
+            Self::InlineBuffer(data) => Some(data.as_slice()),
             Self::Other(_) => None,
         }
     }
 
     /// Extract the inline buffer data, consuming the writer
-    pub fn into_inline_data(self) -> Option<Vec<u8>> {
+    pub fn into_inline_data(self) -> Option<bytes::Bytes> {
         match self {
-            Self::InlineBuffer(data) => Some(data),
+            Self::InlineBuffer(data) => Some(data.into_bytes()),
             Self::Other(_) => None,
         }
     }
@@ -741,10 +846,7 @@ impl AsyncWrite for CustomWriter {
         buf: &[u8],
     ) -> std::task::Poll<std::io::Result<usize>> {
         match self.get_mut() {
-            Self::InlineBuffer(data) => {
-                data.extend_from_slice(buf);
-                std::task::Poll::Ready(Ok(buf.len()))
-            }
+            Self::InlineBuffer(data) => std::task::Poll::Ready(data.append(&[IoSlice::new(buf)])),
             Self::Other(writer) => {
                 let pinned_writer = std::pin::Pin::new(writer.as_mut());
                 pinned_writer.poll_write(cx, buf)
@@ -778,13 +880,7 @@ impl AsyncWrite for CustomWriter {
         bufs: &[IoSlice<'_>],
     ) -> std::task::Poll<std::io::Result<usize>> {
         match self.get_mut() {
-            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::InlineBuffer(data) => std::task::Poll::Ready(data.append(bufs)),
             Self::Other(writer) => {
                 let pinned_writer = std::pin::Pin::new(writer.as_mut());
                 pinned_writer.poll_write_vectored(cx, bufs)
@@ -859,7 +955,7 @@ impl BitrotWriterWrapper {
     }
 
     /// Extract the inline buffer data, consuming the wrapper
-    pub fn into_inline_data(self) -> Option<Vec<u8>> {
+    pub fn into_inline_data(self) -> Option<bytes::Bytes> {
         match self.writer_type {
             WriterType::InlineBuffer => {
                 let writer = self.bitrot_writer.into_inner();
@@ -1506,6 +1602,184 @@ 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";
@@ -2403,4 +2677,128 @@ 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

@@ -175,8 +175,10 @@ 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 (current behavior: every live shard reader is read on every
-/// stripe).
+/// 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`.
 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;
 
@@ -189,6 +191,13 @@ 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(
@@ -832,6 +841,13 @@ 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
     }
@@ -2596,7 +2612,8 @@ 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 = reader.demand_bound_lockstep && matches!(decode_read_policy(), DecodeReadPolicy::Default);
+        let require_surplus_source =
+            get_lockstep_data_shards_only_enabled() && matches!(decode_read_policy(), DecodeReadPolicy::Default);
 
         let start = offset / self.block_size;
         let end = end_offset.saturating_sub(1) / self.block_size;
@@ -4367,9 +4384,9 @@ mod tests {
         .await;
     }
 
-    /// 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.
+    /// 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.
     #[tokio::test]
     #[serial_test::serial]
     async fn test_lockstep_default_reads_all_shards_per_stripe() {

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

@@ -16,6 +16,8 @@
 //! 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;
@@ -144,12 +146,54 @@ 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<reed_solomon_simd::ReedSolomonEncoder>>,
-    decoder_cache: RwLock<Option<reed_solomon_simd::ReedSolomonDecoder>>,
+    encoder_cache: RwLock<Option<LegacyWorkspace<reed_solomon_simd::ReedSolomonEncoder>>>,
+    decoder_cache: RwLock<Option<LegacyWorkspace<reed_solomon_simd::ReedSolomonDecoder>>>,
 }
 
 impl LegacyReedSolomonEncoder {
@@ -199,20 +243,29 @@ impl LegacyReedSolomonEncoder {
             .write()
             .map_err(|_| io::Error::other("Failed to acquire encoder cache lock"))?
             .take();
-        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:?}")))?,
-            }
-        };
+        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;
         for (i, shard) in shards.iter().enumerate().take(self.data_shards) {
             encoder
                 .add_original_shard(shard)
@@ -233,7 +286,7 @@ impl LegacyReedSolomonEncoder {
                 .write()
                 .map_err(|_| io::Error::other("Failed to return encoder to cache"))?;
             if cache.is_none() {
-                *cache = Some(encoder);
+                *cache = Some(workspace);
             }
         }
         Ok(())
@@ -254,21 +307,26 @@ impl LegacyReedSolomonEncoder {
             .write()
             .map_err(|_| io::Error::other("Failed to acquire decoder cache lock"))?
             .take();
-        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:?}")))?,
-            }
-        };
+        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;
 
         for (i, shard_opt) in shards.iter().enumerate() {
             if let Some(shard) = shard_opt {
@@ -308,7 +366,7 @@ impl LegacyReedSolomonEncoder {
                 .write()
                 .map_err(|_| io::Error::other("Failed to return decoder to cache"))?;
             if cache.is_none() {
-                *cache = Some(decoder);
+                *cache = Some(workspace);
             }
         }
 
@@ -333,6 +391,13 @@ 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)?;
 
@@ -431,8 +496,18 @@ impl ReedSolomonEncoder {
         }
 
         if let Some(ref rs) = self.encoder {
-            rs.verify(shards)
-                .map_err(|e| io::Error::other(format!("Reed-Solomon verify failed: {e:?}")))
+            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:?}")))
         } else {
             Ok(true)
         }
@@ -1200,6 +1275,105 @@ 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

@@ -12,8 +12,10 @@
 // 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;
@@ -22,6 +24,7 @@ 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};
@@ -30,21 +33,53 @@ 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,
-) -> (Vec<Option<Vec<u8>>>, Vec<Option<Error>>)
+) -> Result<(HealShards, Vec<Option<Error>>)>
 where
     R: AsyncRead + Unpin + Send + Sync,
 {
     let num_readers = readers.len();
-    let mut shards = vec![None; num_readers];
+    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 errs = vec![None; num_readers];
     let mut retire_readers = Vec::new();
 
     if shard_size == 0 {
-        return (shards, errs);
+        return Ok((shards, errs));
     }
 
     {
@@ -55,8 +90,17 @@ where
                 continue;
             };
 
+            let budget = shards.budget.clone();
             futures.push(Box::pin(async move {
-                let mut buf = vec![0; shard_size];
+                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 read_result = if read_timeout.is_zero() {
                     reader.read(&mut buf).await
                 } else {
@@ -75,7 +119,7 @@ where
                 match read_result {
                     Ok(n) => {
                         buf.truncate(n);
-                        (index, Ok(buf), false)
+                        (index, Ok((buf, memory)), false)
                     }
                     Err(err) => {
                         let should_retire = err.kind() == ErrorKind::TimedOut;
@@ -87,10 +131,14 @@ where
 
         while let Some((index, result, should_retire)) = futures.next().await {
             match result {
-                Ok(shard) => {
-                    shards[index] = Some(shard);
+                Ok((shard, memory)) => {
+                    shards.shards[index] = Some(shard);
+                    shards.memory[index] = memory;
                 }
                 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);
@@ -105,7 +153,7 @@ where
         warn!(shard_index = index, "retiring timed-out heal shard reader");
     }
 
-    (shards, errs)
+    Ok((shards, errs))
 }
 
 fn heal_writer_failure(writers: &mut MultiWriter<'_>, error: io::Error) -> Error {
@@ -164,7 +212,7 @@ 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 shards, errs) = read_heal_shards(&mut readers, shard_size, read_timeout).await;
+            let (mut owned_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
@@ -183,6 +231,24 @@ 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()
@@ -190,24 +256,23 @@ 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(&mut shards)?;
-                if !source_parity.is_empty() && !self.verify_data_and_parity(&shards)? {
+                self.decode_data_and_parity(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"));
                     }
                 }
             }
 
-            let shards = shards
-                .into_iter()
-                .map(|s| Bytes::from(s.unwrap_or_default()))
-                .collect::<Vec<_>>();
+            drop(source_parity);
+            drop(_source_memory);
+            let shards = owned_shards.into_bytes();
 
             if let Err(error) = writers.write(shards).await {
                 return Err(heal_writer_failure(&mut writers, error));
@@ -306,6 +371,90 @@ 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![
@@ -313,9 +462,11 @@ mod tests {
             None,
         ];
 
-        let (shards, errs) = read_heal_shards(&mut readers, 0, Duration::ZERO).await;
+        let (shards, errs) = read_heal_shards(&mut readers, 0, Duration::ZERO)
+            .await
+            .expect("empty read succeeds");
 
-        assert_eq!(shards, vec![None, None]);
+        assert_eq!(shards.shards, vec![None, None]);
         assert_eq!(errs, vec![None, None]);
     }
 
@@ -323,9 +474,11 @@ 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;
+        let (shards, errs) = read_heal_shards(&mut readers, 4, Duration::ZERO)
+            .await
+            .expect("ordinary failures remain per-shard");
 
-        assert!(shards[0].is_none());
+        assert!(shards.shards[0].is_none());
         assert!(
             errs[0]
                 .as_ref()
@@ -334,9 +487,11 @@ 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;
+        let (shards, errs) = read_heal_shards(&mut timeout_readers, 4, Duration::from_millis(1))
+            .await
+            .expect("timeouts remain per-shard");
 
-        assert_eq!(shards, vec![None]);
+        assert_eq!(shards.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");
     }