Merge branch 'main' into overtrue/require-mc-e2e

* test(kms): bound Vault failover progress wait

* ci(nightly): honor manual dispatch ref

* test(kms): preserve Vault worker failures

* test(kms): validate Vault circuit recovery

.config/nextest.toml

@@ -325,8 +325,8 @@ slow-timeout = { period = "60s", terminate-after = 2, grace-period = "10s" }
 #
 # Wired by .github/workflows/e2e-replication-nightly.yml (schedule +
 # workflow_dispatch), which builds the rustfs binary once, installs awscurl so
-# the STS dual-node test actually exercises its path (it skips gracefully with
-# a visible log line when awscurl is absent), and routes scheduled failures
+# the STS dual-node test actually exercises its path (the test fails when
+# awscurl is absent), and routes scheduled failures
 # through .github/actions/schedule-failure-issue (ci-8). Explicit division of
 # labor with e2e-full: these tests run only in the consolidated nightly
 # workflow, not in the merge/main lane.

.github/workflows/ci.yml

@@ -681,6 +681,19 @@ jobs:
           cache-save-if: 'false'
           install-build-packaging-tools: 'false'
 
+      - name: Set up Python
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
+        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 "$AWSCURL_PATH"
+
       # Download after the cache restore so the freshly built binary from the
       # build job always wins over anything restored into target/debug.
       - name: Download debug binary
@@ -803,6 +816,20 @@ jobs:
       - name: Verify awscurl
         run: test -x "$AWSCURL_PATH"
 
+      - name: Install mc
+        env:
+          MC_VERSION: RELEASE.2025-08-13T08-35-41Z
+          MC_SHA256: 01f866e9c5f9b87c2b09116fa5d7c06695b106242d829a8bb32990c00312e891
+        run: |
+          MC_BINARY="mc.linux-amd64.${MC_VERSION}"
+          curl -fsSLo "$RUNNER_TEMP/mc" "https://github.com/minio/mc/releases/download/${MC_VERSION}/${MC_BINARY}"
+          echo "${MC_SHA256}  $RUNNER_TEMP/mc" | sha256sum --check --status
+          chmod +x "$RUNNER_TEMP/mc"
+          echo "$RUNNER_TEMP" >> "$GITHUB_PATH"
+
+      - name: Verify mc
+        run: mc --version
+
       - name: Install Vault
         run: |
           VAULT_VERSION="1.17.6"

.github/workflows/e2e-replication-nightly.yml

@@ -75,11 +75,7 @@ jobs:
           cache-save-if: ${{ github.ref == 'refs/heads/main' }}
           install-build-packaging-tools: 'false'
 
-      # awscurl lets the STS dual-node test actually exercise its path. Without
-      # it the test skips gracefully with a visible log line
-      # (`awscurl_available()` in crates/e2e_test/src/common.rs), so the lane
-      # still passes — installing it just upgrades that one test from skip to
-      # real coverage.
+      # The STS dual-node test requires awscurl and fails if it is unavailable.
       - name: Set up Python
         uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
         with:
@@ -87,7 +83,7 @@ jobs:
 
       - name: Install awscurl
         run: |
-          python3 -m pip install --user --upgrade pip awscurl
+          python3 -m pip install --user --upgrade pip "awscurl==0.44"
           echo "AWSCURL_PATH=$HOME/.local/bin/awscurl" >> "$GITHUB_ENV"
 
       - name: Verify awscurl

.github/workflows/nightly-gnu.yml

@@ -39,11 +39,10 @@ jobs:
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup
@@ -89,11 +88,10 @@ jobs:
       # either casing.
       NO_PROXY: 127.0.0.1,localhost
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup
@@ -178,11 +176,10 @@ jobs:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
       NO_PROXY: 127.0.0.1,localhost
     steps:
-      - name: Checkout main branch
+      - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
         with:
           persist-credentials: false
-          ref: main
 
       - name: Setup Rust environment
         uses: ./.github/actions/setup

CLAUDE.md

@@ -30,7 +30,8 @@ make build-docker BUILD_OS=ubuntu22.04
 - Crate membership: `Cargo.toml` `[workspace].members`
 - Architecture, layering, crate map: [ARCHITECTURE.md](ARCHITECTURE.md)
 - Migration guardrails & readiness contracts: [docs/architecture/](docs/architecture/README.md)
-- CI gates: `.github/workflows/ci.yml` (source of truth; never copy its steps into docs)
+- CI workflow steps: `.github/workflows/`; event, timeout, and required-status
+  matrix: [docs/testing/ci-gates.md](docs/testing/ci-gates.md)
 - Test-layer taxonomy, per-layer entry commands, serial/nextest rules, flake
   policy: [docs/testing/README.md](docs/testing/README.md)
 - Tier/ILM transition debugging (xl.meta inspection, versionId tracing):

CONTRIBUTING.md

@@ -70,6 +70,8 @@ make pre-pr
 
 > For the full test-layer taxonomy (unit / ecstore black-box / e2e / s3s-e2e / S3 compatibility / chaos / fuzz / bench), each layer's entry command, the naming conventions the migration gate depends on, and the serial/nextest rules, see [docs/testing/README.md](docs/testing/README.md).
 
+> For the event, timeout, required-status, and local reproduction matrix, see [docs/testing/ci-gates.md](docs/testing/ci-gates.md).
+
 ### 🔒 Automated Pre-commit Hooks
 #### What `make pre-commit` and `make pre-pr` actually run
 

Cargo.lock

@@ -1858,9 +1858,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.4.3"
+version = "1.4.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "509591b7bcd67f4ef775afad7662703b4935daaa6ec0e5605cfb1090b32a2b6d"
+checksum = "0ad534f4357a5264cce5019c989cf66a4f0dc4e0d1b1d15f8aacec0ff7360273"
 dependencies = [
  "find-msvc-tools",
  "jobserver",
@@ -2522,12 +2522,6 @@ dependencies = [
  "subtle",
 ]
 
-[[package]]
-name = "cty"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b365fabc795046672053e29c954733ec3b05e4be654ab130fe8f1f94d7051f35"
-
 [[package]]
 name = "curve25519-dalek"
 version = "4.1.3"
@@ -5988,15 +5982,6 @@ version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b6d2cec3eae94f9f509c767b45932f1ada8350c4bdb85af2fcab4a3c14807981"
 
-[[package]]
-name = "libmimalloc-sys"
-version = "0.1.49"
-source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
-dependencies = [
- "cc",
- "cty",
-]
-
 [[package]]
 name = "libredox"
 version = "0.1.20"
@@ -6397,14 +6382,6 @@ dependencies = [
  "synstructure 0.13.2",
 ]
 
-[[package]]
-name = "mimalloc"
-version = "0.1.52"
-source = "git+https://github.com/xonatius/mimalloc_rust.git?rev=6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11#6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11"
-dependencies = [
- "libmimalloc-sys",
-]
-
 [[package]]
 name = "mime"
 version = "0.3.17"
@@ -9162,13 +9139,11 @@ dependencies = [
  "insta",
  "jiff",
  "libc",
- "libmimalloc-sys",
  "libsystemd",
  "matchit 0.9.2",
  "md-5 0.11.0",
  "metrics",
  "metrics-util",
- "mimalloc",
  "mime_guess",
  "opentelemetry",
  "opentelemetry_sdk",
@@ -9204,6 +9179,8 @@ dependencies = [
  "rustfs-lock",
  "rustfs-log-analyzer",
  "rustfs-madmin",
+ "rustfs-mimalloc",
+ "rustfs-mimalloc-sys",
  "rustfs-notify",
  "rustfs-object-capacity",
  "rustfs-object-data-cache",
@@ -9875,6 +9852,24 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "rustfs-mimalloc"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a406f4aa07084301d485beec873af6dccc8e3f8762da244743df92038b1db1a6"
+dependencies = [
+ "rustfs-mimalloc-sys",
+]
+
+[[package]]
+name = "rustfs-mimalloc-sys"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3051b819175f58445d4c369a72f0ab88149f3885ba8bea2aff3be01f53fe7cd"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "rustfs-notify"
 version = "1.0.0-rc.3"

Cargo.toml

@@ -350,8 +350,8 @@ russh-sftp = "2.4.0"
 dav-server = "0.11.0"
 
 # Performance Analysis and Memory Profiling
-mimalloc = { version = "0.1.52", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11" }
-libmimalloc-sys = { version = "0.1.49", git = "https://github.com/xonatius/mimalloc_rust.git", rev = "6d4c41bb10c6d9da1d1b6f07b38c4cc051667f11", features = ["extended"] }
+rustfs-mimalloc = { version = "0.5.0" }
+rustfs-mimalloc-sys = { version = "0.5.0" }
 hotpath = { version = "0.23.3", default-features = false }
 # Snapshot testing for output format regression detection
 insta = { version = "1.48" }

crates/e2e_test/README.md

@@ -123,7 +123,7 @@ via `create_s3_client(idx)` / `create_all_clients()`. See
 | `find_available_port` | Random free port (isolation primitive) |
 | `rustfs_binary_path` / `_with_features` | Locate/build the binary; honors `RUSTFS_BUILD_FEATURES` |
 | `requested_rustfs_build_features` / `rustfs_build_feature_enabled` | Feature-gate a test to what the binary was built with |
-| `awscurl_available` + `execute_awscurl` / `awscurl_post` / `_get` / `_put` / `_delete` / `awscurl_post_sts_form_urlencoded` | Admin/STS API calls via `awscurl` (skip gracefully when absent) |
+| `execute_awscurl` / `awscurl_post` / `_get` / `_put` / `_delete` / `awscurl_post_sts_form_urlencoded` | Admin/STS API calls via `awscurl`; missing binaries are test failures |
 | `replication_fast_env` | Env vars that shrink replication timers (from repl-4); pass to `start_rustfs_server_with_env` |
 | `local_http_client` / `init_logging` | Loopback HTTP client; idempotent tracing init |
 | `RustFSTestClusterEnvironment` (`new`/`start`/`start_node`/`stop_node`/`create_all_clients`) | Multi-node harness |
@@ -189,7 +189,7 @@ cargo nextest run --profile e2e-smoke -p e2e_test
 cargo nextest run --profile e2e-full -p e2e_test
 # Cluster fault nightly lane
 cargo nextest run --profile e2e-nightly -p e2e_test
-# Replication nightly lane; install awscurl so STS paths do not skip
+# Replication nightly lane; awscurl is required for STS paths
 cargo nextest run --profile e2e-repl-nightly -p e2e_test
 # Fixed-port protocol nightly lane
 RUSTFS_BUILD_FEATURES=ftps,webdav,sftp \
@@ -221,9 +221,8 @@ The `s3s-e2e` CI job selects a random `RUSTFS_TEST_PORT` (see the `e2e-tests`
 job) to dodge this; local single-node tests already use random ports, so a
 lingering orphan is usually the cause of a spurious bind failure.
 
-**`awscurl` not found.** `awscurl`-dependent tests skip gracefully with a
-visible log line (`awscurl_available()`); install `awscurl` to actually run
-them.
+**`awscurl` not found.** `awscurl`-dependent tests fail closed with a process
+spawn error. Install the pinned CI version before running their profiles.
 
 ## Related
 
@@ -258,10 +257,9 @@ A test module may join the smoke filter only if every test in it is:
 2. **Single-node** — spawns its own server via
    `RustFSTestEnvironment`/`start_rustfs_server` on a random port with an
    isolated temp dir. No `RustFSTestClusterEnvironment`, no fixed ports.
-3. **Dependency-free** — no pre-started server at `localhost:9000`, no Vault,
-   no fixed protocol ports. Tools that may be absent on the runner (e.g.
-   `awscurl`) are acceptable only when the test skips gracefully with a
-   visible log line (see `bucket_policy_check_test.rs`).
+3. **Hermetic dependencies** — no pre-started server at `localhost:9000`, no
+   Vault, and no fixed protocol ports. Any required CLI must be pinned and
+   installed by the workflow; a missing CLI must fail the test.
 4. **Not `#[ignore]`** — ignored tests are activation work (backlog#1149
    ci-13 / backlog#1148 ilm-3), not smoke candidates.
 

crates/e2e_test/src/bucket_policy_check_test.rs

@@ -52,10 +52,6 @@ fn create_user_client(env: &RustFSTestEnvironment, access_key: &str, secret_key:
 #[tokio::test]
 async fn test_bucket_policy_authenticated_user() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !crate::common::awscurl_available() {
-        info!("Skipping test_bucket_policy_authenticated_user because awscurl is not available");
-        return Ok(());
-    }
     info!("Starting test_bucket_policy_authenticated_user...");
 
     let mut env = RustFSTestEnvironment::new().await?;

crates/e2e_test/src/common.rs

@@ -494,17 +494,6 @@ fn awscurl_binary_path() -> PathBuf {
         .unwrap_or_else(|| PathBuf::from("awscurl"))
 }
 
-pub fn awscurl_available() -> bool {
-    let path = awscurl_binary_path();
-    if path.components().count() > 1 || path.is_absolute() {
-        return path.is_file();
-    }
-
-    std::env::var_os("PATH")
-        .map(|paths| std::env::split_paths(&paths).any(|dir| dir.join(&path).is_file()))
-        .unwrap_or(false)
-}
-
 // Global initialization
 static INIT: Once = Once::new();
 

crates/e2e_test/src/existing_object_tag_policy_test.rs

@@ -16,9 +16,7 @@
 //! session policy** (`Policy` parameter) via `awscurl --service sts` with explicit
 //! `Content-Type: application/x-www-form-urlencoded` on `POST /`.
 
-use crate::common::{
-    RustFSTestEnvironment, awscurl_available, awscurl_delete, awscurl_post_sts_form_urlencoded, awscurl_put, init_logging,
-};
+use crate::common::{RustFSTestEnvironment, awscurl_delete, awscurl_post_sts_form_urlencoded, awscurl_put, init_logging};
 use aws_sdk_s3::config::{Credentials, Region};
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::{Delete, ObjectIdentifier, Tag, Tagging};
@@ -175,11 +173,6 @@ async fn cleanup_bucket_and_object(admin: &Client, bucket: &str, key: &str) {
 #[tokio::test]
 async fn test_e2e_iam_policy_existing_object_tag_get_object() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_iam_policy_existing_object_tag_get_object: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let user = format!("e2eiamtag-{suffix}");
     let user_secret = "longSecretKeyForTest123!";
@@ -233,11 +226,6 @@ async fn test_e2e_iam_policy_existing_object_tag_get_object() -> Result<(), Box<
 #[tokio::test]
 async fn test_e2e_bucket_policy_existing_object_tag_get_object() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_bucket_policy_existing_object_tag_get_object: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let user = format!("e2ebptag-{suffix}");
     let user_secret = "longSecretKeyForTest456!";
@@ -294,11 +282,6 @@ async fn test_e2e_bucket_policy_existing_object_tag_get_object() -> Result<(), B
 #[tokio::test]
 async fn test_e2e_sts_assume_role_session_policy_existing_object_tag() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_sts_assume_role_session_policy_existing_object_tag: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let parent = format!("e2e-sts-par-{suffix}");
     let parent_secret = "longSecretKeyForParentSts99!";
@@ -370,11 +353,6 @@ async fn test_e2e_sts_assume_role_session_policy_existing_object_tag() -> Result
 #[tokio::test]
 async fn test_e2e_sts_session_policy_delete_objects_object_prefix_only() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping test_e2e_sts_session_policy_delete_objects_object_prefix_only: awscurl not available");
-        return Ok(());
-    }
-
     let suffix = Uuid::new_v4();
     let parent = format!("e2e-sts-del-par-{suffix}");
     let parent_secret = "longSecretKeyForParentDelete99!";

crates/e2e_test/src/kms/common.rs

@@ -22,9 +22,7 @@
 //! - KMS backend configuration (Local and Vault)
 //! - SSE encryption testing utilities
 
-use crate::common::{
-    RustFSTestEnvironment, awscurl_available, awscurl_get, awscurl_post, init_logging as common_init_logging, local_http_client,
-};
+use crate::common::{RustFSTestEnvironment, awscurl_get, awscurl_post, init_logging as common_init_logging, local_http_client};
 use aws_sdk_s3::Client;
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::ServerSideEncryption;
@@ -59,15 +57,6 @@ pub fn init_logging() {
     // Additional KMS-specific logging configuration can be added here if needed
 }
 
-pub fn skip_if_kms_admin_tool_unavailable(test_name: &str) -> bool {
-    if awscurl_available() {
-        return false;
-    }
-
-    info!("Skipping {} because awscurl is not available in PATH", test_name);
-    true
-}
-
 pub fn sse_customer_key_md5_base64(key: &str) -> String {
     let mut hasher = Md5::new();
     hasher.update(key.as_bytes());
@@ -490,10 +479,6 @@ pub async fn test_kms_key_management(
     access_key: &str,
     secret_key: &str,
 ) -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
-    if skip_if_kms_admin_tool_unavailable("test_kms_key_management") {
-        return Ok(());
-    }
-
     info!("Testing KMS key management APIs");
 
     // Test CreateKey

crates/e2e_test/src/kms/kms_local_test.rs

@@ -20,8 +20,7 @@
 //! - Complete encryption/decryption lifecycle
 
 use super::common::{
-    LocalKMSTestEnvironment, get_kms_status, skip_if_kms_admin_tool_unavailable, sse_customer_key_md5_base64,
-    test_kms_key_management, test_sse_c_encryption,
+    LocalKMSTestEnvironment, get_kms_status, sse_customer_key_md5_base64, test_kms_key_management, test_sse_c_encryption,
 };
 use crate::common::{TEST_BUCKET, init_logging};
 use tracing::{error, info};
@@ -29,9 +28,6 @@ use tracing::{error, info};
 #[tokio::test]
 async fn test_local_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_local_kms_end_to_end") {
-        return Ok(());
-    }
     info!("Starting Local KMS End-to-End Test");
 
     // Create LocalKMS test environment

crates/e2e_test/src/kms/kms_vault_test.rs

@@ -22,8 +22,8 @@ use crate::common::{TEST_BUCKET, init_logging};
 use tracing::{error, info};
 
 use super::common::{
-    VAULT_KEY_NAME, VaultTestEnvironment, get_kms_status, skip_if_kms_admin_tool_unavailable, sse_customer_key_md5_base64,
-    start_kms, test_all_multipart_encryption_types, test_error_scenarios, test_kms_key_management, test_sse_c_encryption,
+    VAULT_KEY_NAME, VaultTestEnvironment, get_kms_status, sse_customer_key_md5_base64, start_kms,
+    test_all_multipart_encryption_types, test_error_scenarios, test_kms_key_management, test_sse_c_encryption,
     test_sse_kms_encryption, test_sse_s3_encryption,
 };
 
@@ -62,9 +62,6 @@ impl VaultKmsTestContext {
 #[tokio::test]
 async fn test_vault_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_end_to_end") {
-        return Ok(());
-    }
     info!("Starting Vault KMS End-to-End Test with default key {}", VAULT_KEY_NAME);
 
     let context = VaultKmsTestContext::new().await?;
@@ -117,9 +114,6 @@ async fn test_vault_kms_end_to_end() -> Result<(), Box<dyn std::error::Error + S
 #[tokio::test]
 async fn test_vault_kms_key_isolation() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_key_isolation") {
-        return Ok(());
-    }
     info!("Starting Vault KMS SSE-C key isolation test");
 
     let context = VaultKmsTestContext::new().await?;
@@ -203,9 +197,6 @@ async fn test_vault_kms_key_isolation() -> Result<(), Box<dyn std::error::Error
 #[tokio::test]
 async fn test_vault_kms_large_file() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_large_file") {
-        return Ok(());
-    }
     info!("Starting Vault KMS large file SSE-S3 test");
 
     let context = VaultKmsTestContext::new().await?;
@@ -267,9 +258,6 @@ async fn test_vault_kms_large_file() -> Result<(), Box<dyn std::error::Error + S
 #[tokio::test]
 async fn test_vault_kms_multipart_upload() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_multipart_upload") {
-        return Ok(());
-    }
     info!("Starting Vault KMS multipart upload encryption suite");
 
     let context = VaultKmsTestContext::new().await?;
@@ -297,9 +285,6 @@ async fn test_vault_kms_multipart_upload() -> Result<(), Box<dyn std::error::Err
 #[tokio::test]
 async fn test_vault_kms_key_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if skip_if_kms_admin_tool_unavailable("test_vault_kms_key_operations") {
-        return Ok(());
-    }
     info!("Starting Vault KMS key operations test (CRUD)");
 
     let context = VaultKmsTestContext::new().await?;

crates/e2e_test/src/mc_mirror_small_bucket_test.rs

@@ -41,13 +41,6 @@ async fn create_issue_3107_fixture(root: &Path) -> TestResult {
     Ok(())
 }
 
-fn mc_available() -> bool {
-    Command::new("mc")
-        .arg("--version")
-        .output()
-        .is_ok_and(|output| output.status.success())
-}
-
 fn run_mc(args: &[&str]) -> TestResult {
     let output = Command::new("mc").args(args).output()?;
     if !output.status.success() {
@@ -75,10 +68,7 @@ fn count_files(root: &Path) -> usize {
 async fn test_mc_mirror_small_bucket_completes_without_list_timeout() -> TestResult {
     crate::common::init_logging();
     info!("Starting issue #3107 mc mirror regression test");
-    if !mc_available() {
-        info!("Skipping issue #3107 mc mirror regression test because mc is not installed");
-        return Ok(());
-    }
+    run_mc(&["--version"])?;
 
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;

crates/e2e_test/src/multipart_auth_test.rs

@@ -4278,10 +4278,6 @@ async fn test_signed_put_object_extract_preserves_pax_metadata_and_version_id()
 async fn test_signed_put_object_extract_authorizes_each_pax_privilege_and_retention_conditions()
 -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
     init_logging();
-    if !crate::common::awscurl_available() {
-        return Ok(());
-    }
-
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;
 

crates/e2e_test/src/quota_test.rs

@@ -18,15 +18,6 @@ use http::{Method, StatusCode};
 use tokio::time::{Duration, sleep, timeout};
 use tracing::{debug, info};
 
-fn skip_without_awscurl() -> bool {
-    if crate::common::awscurl_available() {
-        return false;
-    }
-
-    info!("Skipping quota test because awscurl is not available");
-    true
-}
-
 /// Test environment setup for quota tests
 pub struct QuotaTestEnv {
     pub env: RustFSTestEnvironment,
@@ -276,9 +267,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_basic_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         // Create test bucket
@@ -320,9 +308,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_admission_aws_chunked_declared_encoding() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
         env.create_bucket().await?;
 
@@ -371,9 +356,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_update_and_clear() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -406,9 +388,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_delete_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -442,9 +421,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_usage_tracking() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -480,9 +456,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_statistics() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -513,9 +486,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_check_api() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -553,9 +523,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_multiple_buckets() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         // Create two buckets in the same environment
@@ -593,9 +560,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_error_handling() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -628,9 +592,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_http_endpoints() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -689,9 +650,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_normal_user_permissions() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
         env.create_bucket().await?;
 
@@ -744,9 +702,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_copy_operations() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -789,9 +744,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_batch_delete() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;
@@ -847,9 +799,6 @@ mod integration_tests {
     #[tokio::test]
     async fn test_quota_multipart_upload() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
         init_logging();
-        if skip_without_awscurl() {
-            return Ok(());
-        }
         let env = QuotaTestEnv::new().await?;
 
         env.create_bucket().await?;

crates/e2e_test/src/replication_extension_test.rs

@@ -13,9 +13,8 @@
 // limitations under the License.
 
 use crate::common::{
-    RustFSTestEnvironment, admin_create_user, awscurl_available, awscurl_post_sts_form_urlencoded, init_logging,
-    local_http_client, replication_fast_env, rustfs_binary_path, signed_request, signed_request_with_client,
-    signed_request_with_session_token,
+    RustFSTestEnvironment, admin_create_user, awscurl_post_sts_form_urlencoded, init_logging, local_http_client,
+    replication_fast_env, rustfs_binary_path, signed_request, signed_request_with_client, signed_request_with_session_token,
 };
 use crate::fake_s3_target::{
     FAKE_ACCESS_KEY, FAKE_SECRET_KEY, FakeS3Target, FaultAction as FakeTargetFault, Operation as FakeTargetOperation,
@@ -7281,11 +7280,6 @@ async fn test_site_replication_replicates_multiple_service_accounts_real_dual_no
 async fn test_site_replication_replicates_service_accounts_created_from_sts_session_real_dual_node() -> TestResult {
     init_logging();
 
-    if !awscurl_available() {
-        eprintln!("Skipping STS site replication service-account test because awscurl is unavailable");
-        return Ok(());
-    }
-
     let mut source_env = RustFSTestEnvironment::new().await?;
     source_env
         .start_rustfs_server_with_env(vec![], LOOPBACK_REPLICATION_TARGET_ENV)

crates/e2e_test/src/security_boundary_test.rs

@@ -21,7 +21,7 @@
 //! - SSRF prevention (internal/private endpoints rejected for tiering)
 //! - Race condition handling (concurrent writes converge without corruption)
 
-use crate::common::{RustFSTestEnvironment, awscurl_available, awscurl_put, init_logging};
+use crate::common::{RustFSTestEnvironment, awscurl_put, init_logging};
 use aws_sdk_s3::error::ProvideErrorMetadata;
 use aws_sdk_s3::primitives::ByteStream;
 use aws_sdk_s3::types::{CompletedMultipartUpload, CompletedPart, Tag, Tagging};
@@ -225,16 +225,11 @@ async fn test_concurrent_object_operations() -> Result<(), Box<dyn Error + Send
 /// outcome — the internal endpoint is not accepted — is asserted here.
 ///
 /// The admin API is exercised via signed `awscurl` requests, matching the
-/// pattern used by the other admin-API E2E tests in this crate; the test is
-/// skipped when `awscurl` is not installed.
+/// pattern used by the other admin-API E2E tests in this crate. The full E2E
+/// lane installs and verifies the pinned `awscurl` prerequisite.
 #[tokio::test]
 async fn test_tiering_url_validation() -> Result<(), Box<dyn Error + Send + Sync>> {
     init_logging();
-    if !awscurl_available() {
-        info!("Skipping tiering URL validation test because awscurl is not available");
-        return Ok(());
-    }
-
     let mut env = RustFSTestEnvironment::new().await?;
     env.start_rustfs_server(vec![]).await?;
 

crates/ecstore/src/io_support/bitrot.rs

@@ -784,6 +784,24 @@ pub(crate) fn create_deferred_bitrot_reader_with_stripe_handle(
 ///
 /// # Returns
 /// A Result containing the BitrotWriterWrapper or an error
+/// Size hint handed to `DiskAPI::create_file` for a bitrot-wrapped shard.
+///
+/// A known length is grown by one checksum per shard so the on-disk file size
+/// matches what the bitrot writer emits. A negative length is the
+/// unknown-size sentinel (`HashReader::SIZE_PRESERVE_LAYER`, used by SSE and
+/// compression) and must be preserved: `RemoteDisk::create_file` forwards it
+/// in the `put_file_stream` query, and the receiver only treats `size > 0` as
+/// a fixed body length when locating the authenticated trailer. Clamping it
+/// to `0` would claim an empty body and misframe the stream. `0` stays `0`
+/// because a genuinely empty object still means an empty body.
+fn bitrot_create_file_size(length: i64, shard_size: usize, checksum_algo: &HashAlgorithm) -> i64 {
+    if length <= 0 {
+        return length;
+    }
+    let length = length as usize;
+    (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
+}
+
 pub async fn create_bitrot_writer(
     is_inline_buffer: bool,
     disk: Option<&DiskStore>,
@@ -796,12 +814,7 @@ pub async fn create_bitrot_writer(
     let writer = if is_inline_buffer {
         CustomWriter::new_inline_buffer()
     } else if let Some(disk) = disk {
-        let length = if length > 0 {
-            let length = length as usize;
-            (length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
-        } else {
-            0
-        };
+        let length = bitrot_create_file_size(length, shard_size, &checksum_algo);
 
         let file = disk.create_file("", volume, path, length).await?;
         #[cfg(feature = "hotpath")]
@@ -820,6 +833,25 @@ mod tests {
     use rustfs_rio::ChunkReader;
     use std::collections::VecDeque;
 
+    #[test]
+    fn bitrot_create_file_size_grows_known_length_by_checksums() {
+        // 10 bytes over 4-byte shards = 3 shards, each followed by a 32-byte hash.
+        assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::HighwayHash256), 10 + 3 * 32);
+        assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::None), 10);
+    }
+
+    #[test]
+    fn bitrot_create_file_size_keeps_empty_and_unknown_distinct() {
+        assert_eq!(bitrot_create_file_size(0, 4, &HashAlgorithm::HighwayHash256), 0);
+        // SSE/compression streams advertise SIZE_PRESERVE_LAYER (-1); the remote
+        // put_file_stream receiver relies on a non-positive size to parse the auth
+        // trailer from the stream tail, so the sentinel must survive untouched.
+        assert_eq!(
+            bitrot_create_file_size(rustfs_rio::HashReader::SIZE_PRESERVE_LAYER, 4, &HashAlgorithm::HighwayHash256),
+            rustfs_rio::HashReader::SIZE_PRESERVE_LAYER
+        );
+    }
+
     struct TestChunkReader {
         chunks: VecDeque<Bytes>,
     }

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

@@ -2124,26 +2124,13 @@ impl SetDisks {
 
             let put_object_size = known_put_object_storage_size(data.size());
             let shard_file_size_raw = erasure.shard_file_size(put_object_size);
-            let is_inline_buffer =
-                storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
+            let is_inline_buffer = storage_class_config.should_inline(shard_file_size_raw, erasure.data_shards, opts.versioned);
 
             let collect_stage_timing = rustfs_io_metrics::put_stage_metrics_enabled() || issue3031_diag_enabled();
             let shard_file_size = shard_file_size_raw;
             let shard_size = erasure.shard_size();
             let write_path = classify_put_write_path(is_inline_buffer, put_object_size, fi.erasure.block_size);
             let direct_inline_commit = matches!(write_path, SmallWritePath::Inline);
-            {
-                use std::io::Write;
-                let msg = format!(
-                    "INLINE_DEBUG: bucket={} obj={} size={} shard_fs={} ds={} bs={} inline={} direct={} path={} iblock={} ver={}\n",
-                    bucket, object, put_object_size, shard_file_size_raw, erasure.data_shards, fi.erasure.block_size,
-                    is_inline_buffer, direct_inline_commit, write_path.metric_label(), storage_class_config.inline_block(), opts.versioned
-                );
-                if let Ok(mut f) = std::fs::OpenOptions::new().create(true).append(true).open("/tmp/rustfs_inline_debug.log") {
-                    let _ = f.write_all(msg.as_bytes());
-                }
-                let _ = std::io::stderr().write_all(msg.as_bytes());
-            }
             rustfs_io_metrics::record_put_object_path(write_path.metric_label());
             let writer_setup_stage_start = collect_stage_timing.then(Instant::now);
             let (mut writers, errors) = if direct_inline_commit {

crates/ecstore/src/store/object.rs

@@ -3194,7 +3194,7 @@ impl ECStore {
 
         // Default return value
         let mut del_objects = vec![DeletedObject::default(); objects.len()];
-        let mut accounting = vec![None; objects.len()];
+        let accounting = vec![None; objects.len()];
 
         let mut del_errs = Vec::with_capacity(objects.len());
         for _ in 0..objects.len() {

crates/ecstore/src/store/rebalance/support.rs

@@ -271,7 +271,7 @@ pub(super) fn resolve_latest_object_info_candidates(
             .filter(|candidate| latest_candidate_mod_time(candidate) == Some(latest_mod_time))
             .collect::<Vec<_>>();
 
-        latest_candidates.sort_by(|left, right| right.idx.cmp(&left.idx));
+        latest_candidates.sort_by_key(|candidate| std::cmp::Reverse(candidate.idx));
 
         let Some(winner) = latest_candidates.first() else {
             return Err(Error::ErasureReadQuorum);

crates/kms/tests/vault_ha_failover_live.rs

@@ -16,14 +16,14 @@
 //!
 //! `scripts/test/vault_ha_kms_live.sh` owns the official Vault containers and
 //! kills the active node while this test continuously decrypts through a
-//! surviving standby. KV2 and Transit requests must remain successful, use a
-//! bounded number of attempts, and leave the circuit and in-flight gauges at
-//! zero after a new leader is elected.
+//! surviving standby. KV2 and Transit must recover after the bounded circuit
+//! interval, use a bounded number of attempts, and leave the circuit and
+//! in-flight gauges at zero after a new leader is elected.
 
 use std::collections::HashMap;
 use std::path::{Path, PathBuf};
-use std::sync::Arc;
 use std::sync::atomic::{AtomicBool, AtomicU64, Ordering};
+use std::sync::{Arc, Mutex};
 use std::time::Duration;
 
 use metrics_util::MetricKind;
@@ -43,6 +43,11 @@ const OPERATION_ATTEMPTS: &str = "rustfs_kms_backend_operation_attempts";
 const IN_FLIGHT: &str = "rustfs_kms_backend_in_flight";
 const CIRCUIT_OPEN: &str = "rustfs_kms_backend_circuit_open";
 const MAX_ATTEMPTS: u32 = 10;
+const ATTEMPT_TIMEOUT: Duration = Duration::from_secs(2);
+const HEALTHY_PROGRESS_TIMEOUT: Duration = Duration::from_secs(20);
+// The circuit remains open for 30s after five failed attempts.
+const POST_FAILOVER_PROGRESS_TIMEOUT: Duration = Duration::from_secs(35);
+const FAILOVER_ERROR_POLL_INTERVAL: Duration = Duration::from_millis(100);
 
 type MetricEntry = (
     metrics_util::CompositeKey,
@@ -64,7 +69,7 @@ fn config(backend: KmsBackend, backend_config: BackendConfig) -> KmsConfig {
         backend,
         backend_config,
         allow_insecure_dev_defaults: true,
-        timeout: Duration::from_secs(2),
+        timeout: ATTEMPT_TIMEOUT,
         retry_attempts: MAX_ATTEMPTS,
         enable_cache: false,
         ..KmsConfig::default()
@@ -164,14 +169,31 @@ fn retryable_failures(snapshot: &[MetricEntry], operation: &str) -> u64 {
         .sum()
 }
 
-async fn wait_for_count(counter: &AtomicU64, minimum: u64, description: &str) {
-    tokio::time::timeout(Duration::from_secs(20), async {
+async fn wait_for_count(
+    counter: &AtomicU64,
+    failure: &Mutex<Option<String>>,
+    minimum: u64,
+    description: &str,
+    timeout: Duration,
+) {
+    tokio::time::timeout(timeout, async {
         while counter.load(Ordering::SeqCst) < minimum {
+            if let Some(error) = failure.lock().expect("decrypt failure lock poisoned").as_ref() {
+                panic!(
+                    "{description} worker failed after {} successful decrypts: {error}",
+                    counter.load(Ordering::SeqCst)
+                );
+            }
             tokio::time::sleep(Duration::from_millis(25)).await;
         }
     })
     .await
-    .unwrap_or_else(|_| panic!("timed out waiting for {description}"));
+    .unwrap_or_else(|_| {
+        panic!(
+            "timed out after {timeout:?} waiting for {description}: completed {}, expected {minimum}",
+            counter.load(Ordering::SeqCst)
+        )
+    });
 }
 
 async fn wait_for_file(path: &Path, description: &str) {
@@ -189,7 +211,8 @@ async fn decrypt_loop<B: KmsBackendTrait + Send + Sync + 'static>(
     request: DecryptRequest,
     expected: Vec<u8>,
     completed: Arc<AtomicU64>,
-    failed: Arc<AtomicBool>,
+    allow_failover_errors: Arc<AtomicBool>,
+    failure: Arc<Mutex<Option<String>>>,
     stop: CancellationToken,
 ) {
     while !stop.is_cancelled() {
@@ -197,8 +220,18 @@ async fn decrypt_loop<B: KmsBackendTrait + Send + Sync + 'static>(
             Ok(response) if response.plaintext == expected => {
                 completed.fetch_add(1, Ordering::SeqCst);
             }
-            Ok(_) | Err(_) => {
-                failed.store(true, Ordering::SeqCst);
+            Ok(_) => {
+                *failure.lock().expect("decrypt failure lock poisoned") =
+                    Some("decrypt returned unexpected plaintext".to_string());
+                return;
+            }
+            Err(rustfs_kms::KmsError::BackendError { .. } | rustfs_kms::KmsError::OperationTimedOut { .. })
+                if allow_failover_errors.load(Ordering::SeqCst) =>
+            {
+                tokio::time::sleep(FAILOVER_ERROR_POLL_INTERVAL).await;
+            }
+            Err(error) => {
+                *failure.lock().expect("decrypt failure lock poisoned") = Some(error.to_string());
                 return;
             }
         }
@@ -296,7 +329,9 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
     );
 
     let stop = CancellationToken::new();
-    let failed = Arc::new(AtomicBool::new(false));
+    let allow_failover_errors = Arc::new(AtomicBool::new(false));
+    let kv2_failure = Arc::new(Mutex::new(None));
+    let transit_failure = Arc::new(Mutex::new(None));
     let kv2_completed = Arc::new(AtomicU64::new(0));
     let transit_completed = Arc::new(AtomicU64::new(0));
     let kv2_worker = tokio::spawn(decrypt_loop(
@@ -304,7 +339,8 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
         kv2_request,
         kv2_data_key.plaintext_key,
         Arc::clone(&kv2_completed),
-        Arc::clone(&failed),
+        Arc::clone(&allow_failover_errors),
+        Arc::clone(&kv2_failure),
         stop.clone(),
     ));
     let transit_worker = tokio::spawn(decrypt_loop(
@@ -312,12 +348,21 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
         transit_request,
         transit_data_key.plaintext_key,
         Arc::clone(&transit_completed),
-        Arc::clone(&failed),
+        Arc::clone(&allow_failover_errors),
+        Arc::clone(&transit_failure),
         stop.clone(),
     ));
 
-    wait_for_count(&kv2_completed, 2, "two healthy KV2 decrypts").await;
-    wait_for_count(&transit_completed, 2, "two healthy Transit decrypts").await;
+    wait_for_count(&kv2_completed, &kv2_failure, 2, "two healthy KV2 decrypts", HEALTHY_PROGRESS_TIMEOUT).await;
+    wait_for_count(
+        &transit_completed,
+        &transit_failure,
+        2,
+        "two healthy Transit decrypts",
+        HEALTHY_PROGRESS_TIMEOUT,
+    )
+    .await;
+    allow_failover_errors.store(true, Ordering::SeqCst);
     std::fs::write(&marker, b"ready").expect("publish failover readiness marker");
 
     wait_for_file(&elected, "the replacement Vault leader").await;
@@ -326,18 +371,39 @@ async fn exercise_failover(snapshotter: &Snapshotter) {
 
     let kv2_after_election = kv2_completed.load(Ordering::SeqCst) + 2;
     let transit_after_election = transit_completed.load(Ordering::SeqCst) + 2;
-    wait_for_count(&kv2_completed, kv2_after_election, "post-failover KV2 decrypts").await;
-    wait_for_count(&transit_completed, transit_after_election, "post-failover Transit decrypts").await;
+    wait_for_count(
+        &kv2_completed,
+        &kv2_failure,
+        kv2_after_election,
+        "post-failover KV2 decrypts",
+        POST_FAILOVER_PROGRESS_TIMEOUT,
+    )
+    .await;
+    wait_for_count(
+        &transit_completed,
+        &transit_failure,
+        transit_after_election,
+        "post-failover Transit decrypts",
+        POST_FAILOVER_PROGRESS_TIMEOUT,
+    )
+    .await;
 
     stop.cancel();
     kv2_worker.await.expect("KV2 decrypt worker must join");
     transit_worker.await.expect("Transit decrypt worker must join");
-    assert!(!failed.load(Ordering::SeqCst), "no decrypt may fail or return different plaintext");
+    assert!(
+        kv2_failure.lock().expect("KV2 failure lock poisoned").is_none(),
+        "no KV2 decrypt may fail or return different plaintext"
+    );
+    assert!(
+        transit_failure.lock().expect("Transit failure lock poisoned").is_none(),
+        "no Transit decrypt may fail or return different plaintext"
+    );
 }
 
 #[test]
 #[ignore = "requires a real three-node Vault Raft cluster; run scripts/test/vault_ha_kms_live.sh"]
-fn vault_raft_leader_failure_preserves_kv2_and_transit_decrypts() {
+fn vault_raft_leader_failure_recovers_kv2_and_transit_decrypts() {
     let recorder = DebuggingRecorder::new();
     let snapshotter = recorder.snapshotter();
     metrics::with_local_recorder(&recorder, || {
@@ -349,11 +415,6 @@ fn vault_raft_leader_failure_preserves_kv2_and_transit_decrypts() {
     });
     let snapshot = snapshotter.snapshot().into_vec();
 
-    assert_eq!(
-        counter_value(&snapshot, OPERATIONS_TOTAL, &[("outcome", "circuit_open")]),
-        0,
-        "a bounded leader election must not open the circuit"
-    );
     assert_eq!(
         counter_value(&snapshot, OPERATIONS_TOTAL, &[("outcome", "budget_exhausted")]),
         0,

deny.toml

@@ -43,9 +43,6 @@ allow-git = [
     # RustFS fork carrying presigned expiry and constant-time authentication fixes.
     # owner: rustfs-maintainers  review: 2026-10
     "https://github.com/rustfs/s3s.git",
-    # MiMalloc fork pinned for hotpath allocation counting support.
-    # owner: houseme  review: 2026-10
-    "https://github.com/xonatius/mimalloc_rust.git",
 ]
 
 [bans]

docs/testing/ci-gates.md

@@ -0,0 +1,149 @@
+# CI gate matrix
+
+This file is the source of truth for which validation runs on each event, its
+configured wall-clock budget, and whether it can block a merge. Test taxonomy,
+naming, and nextest serialization rules remain in [README.md](README.md); e2e
+membership and counts remain in
+[e2e-suite-inventory.md](e2e-suite-inventory.md).
+
+The distinction between **required** and **report-only** is load-bearing:
+a failing job blocks a merge only when its exact check name is present in the
+live `main` ruleset. A workflow name, a `merge_group` trigger, or a red PR check
+does not make a job required by itself.
+
+## Required merge checks
+
+The live `main` ruleset (`6436880`) currently requires exactly these contexts:
+
+| Required context | Producer | Validation |
+|---|---|---|
+| `CLA Check` | `.github/workflows/cla.yml` | Contributor agreement |
+| `Quick Checks` | `.github/workflows/ci.yml` | Formatting and repository guard scripts |
+| `Test and Lint` | `.github/workflows/ci.yml` | Clippy, workspace nextest excluding `e2e_test`, doctests, and migration proofs |
+
+For pull requests limited to the paths excluded by the main CI workflow,
+`.github/workflows/ci-docs-only.yml` reports `Quick Checks` and
+`Test and Lint` under the same names. It runs the real quick checks and the
+planning-document guard; it does not claim that Rust compilation or runtime
+tests ran. Despite the workflow name, these paths also include selected deploy,
+workflow, and lock files.
+
+Verify the live rule rather than trusting this snapshot before changing merge
+policy:
+
+```bash
+gh api repos/rustfs/rustfs/rulesets/6436880 \
+  --jq '.rules[] | select(.type == "required_status_checks") | .parameters'
+```
+
+The ruleset currently has `strict_required_status_checks_policy=false`.
+`Continuous Integration` accepts `merge_group` events and runs `e2e-full` for
+them, but `End-to-End Tests (full merge gate)` is not currently a required
+context. Therefore the repository is prepared to test a merge-queue SHA, but
+the workflow alone does not prove that every merge passed that lane.
+
+## Pull request and merge matrix
+
+Budgets below are job `timeout-minutes`, not typical runtimes. “Report-only”
+means the result is visible and actionable but is not in the live required
+context list.
+
+| Event | Validation | Budget | Merge status | Reproduction |
+|---|---|---:|---|---|
+| PR, non-doc change | `Quick Checks` | 10 min | Required | `make pre-commit` (broader local umbrella) |
+| PR, non-doc change | `Test and Lint` | 90 min | Required | `cargo nextest run --profile ci --all --exclude e2e_test` |
+| PR, non-doc change | `Typos` | 10 min | Report-only | `typos` |
+| PR, non-doc change | `ILM Integration (serial)` | 90 min | Report-only | Use the exact command in `.github/workflows/ci.yml` |
+| PR, non-doc change | rio-v2 / swift / sftp test-and-lint variants | 90 min each | Report-only | `cargo nextest run` with the workflow's feature set |
+| PR, non-doc change | `Build RustFS Debug Binary` | 30 min | Report-only; prerequisite for black-box lanes | `cargo build -p rustfs --bins` |
+| PR, non-doc change | `io_uring Integration (real)` | 30 min | Report-only | `cargo test -p rustfs-ecstore --lib uring_ -- --test-threads=1 --nocapture` |
+| PR, non-doc change | `End-to-End Tests` (`e2e-smoke` plus `s3s-e2e`) | 30 min | Report-only | `cargo nextest run --profile e2e-smoke -p e2e_test`; then `./scripts/e2e-run.sh ./target/debug/rustfs <data-dir>` |
+| PR, non-doc change | `S3 Implemented Tests` | 60 min | Report-only | Build `rustfs`, then run `scripts/s3-tests/run.sh` with `DEPLOY_MODE=binary`, `TEST_MODE=single`, and `MAXFAIL=0` |
+| PR, non-doc change | `S3 Lifecycle Behavior Tests` | 30 min | Report-only | Use the accelerated scanner environment in `.github/workflows/ci.yml` with `scripts/s3-tests/run.sh` |
+| PR touching dependency or workflow inputs | Cargo Deny / Workflow Pin Report / Dependency Review | 20 / 5 / 30 min | Report-only | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
+| PR touching architecture rules or architecture docs | `Architecture Migration Rules` | 10 min | Report-only | `scripts/check_architecture_migration_rules.sh` |
+| PR touching Nix or workspace manifests | `Nix Build & Check` | 60 min | Report-only | `nix flake check` |
+| PR limited to main-CI-excluded paths | companion `Quick Checks` and `Test and Lint` | 10 min each | Required | `git diff --check`; `make doc-paths-check` when documentation paths changed |
+| `merge_group` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Standard required contexts only; `e2e-full` report-only | `cargo nextest run --profile e2e-full -p e2e_test` |
+| Push to `main` | Standard CI plus `e2e-full` | 55 min for `e2e-full` | Post-merge detection | Same as `merge_group` |
+| PR touching fuzz inputs or harness paths | Build plus five 60-second fuzz smoke targets | 60 min build; 30 min per target | Report-only | `MAX_TOTAL_TIME=60 ./scripts/fuzz/run.sh` |
+| PR touching selected ecstore disk/format paths | `Rename Safety` on Windows | 60 min | Report-only | Run the four `cargo test -p rustfs-ecstore --lib <filter>` commands in `windows-filesystem.yml` on Windows |
+
+The authoritative e2e filters live in `.config/nextest.toml`; extend a profile
+instead of adding a second ad-hoc selector. Before a profile runs,
+`scripts/check_test_wiring.py` compares its exact membership to the committed
+digest so a silent test drop fails closed.
+
+## Scheduled and manual validation
+
+Scheduled lanes are independent fault domains. They do not block a pull
+request, but their workflow-local gate can fail the run and scheduled failures
+are routed to the shared failure-issue action. The scheduled-validation
+watchdog and freshness workflow separately detect incomplete runs and missing
+schedules.
+
+| Cadence (UTC unless noted) | Workflow / validation | Budget | Verdict and artifacts | Reproduction |
+|---|---|---:|---|---|
+| Daily 02:17 | Fuzz: five nightly corpus targets | 60 min build; 60 min per target | Gate; corpus/crash artifacts, scheduled failure alert | `MAX_TOTAL_TIME=<seconds> ./scripts/fuzz/run.sh` |
+| Daily 03:17 | MinIO interop (EC + SSE read parity) | 40 min | Gate; scheduled failure alert | Dispatch `minio-interop.yml` or follow its pinned Docker fixture steps |
+| Daily 04:29 | Replication / cluster-fault / protocol e2e | 45 / 90 / 90 min | Three independent gates; JUnit, membership, and server logs | `cargo nextest run --profile e2e-repl-nightly -p e2e_test`; `--profile e2e-nightly`; `-j 1 --profile e2e-protocols` |
+| Daily 06:31 | Warp performance A/B | 180 min | Regression budget gate; A/B summaries and server logs | `bash scripts/run_hotpath_warp_abba.sh --help` |
+| Daily 00:07 Asia/Shanghai (16:07 UTC previous day) | Nightly GNU build and Vault lanes | 150 / 90 / 60 min | Build, live Vault, and HA failover gates | Use the commands and pinned Vault images in `nightly-gnu.yml` |
+| Daily 03:23 | Security Audit | 20 / 5 min, plus 30 min on PR dependency review | Cargo Deny and workflow-pin gates; scheduled failure alert | `cargo deny check`; `scripts/security/check_workflow_pins.sh` |
+| Daily 23:47 | Scheduled Validation Freshness | 10 min | Fails when a critical schedule was never created or is stale | Dispatch `scheduled-validation-freshness.yml` |
+| Sunday 00:11 | Full `Continuous Integration` matrix | Per-job budgets above | Weekly variant coverage, including dormant rio-v2 binary/e2e lanes | Dispatch `ci.yml` |
+| Sunday 01:13 | Seven-platform build matrix | 150 min per platform | Build/package integrity; scheduled failure alert | Dispatch `build.yml` with an exact platform set |
+| Sunday 02:19 | Ceph s3-tests full sweep: single and real four-node, four shards each | 180 min per shard | Compatibility gate; report, JUnit, exact node IDs, and server logs | `scripts/s3-tests/run.sh` against an existing single or distributed target |
+| Sunday 06:41 | Mint | 120 min | **Report-only by design**; per-suite PASS/FAIL/NA and raw `log.json` | Reproduce the pinned Docker sequence in `mint.yml` or dispatch it |
+| Sunday 07:43 | Workspace line coverage | 120 min | Report-only trend; lcov and JSON retained 90 days | `make coverage` |
+| Monthly, day 1 06:37 | Runner Hygiene | 15 min | Validates runner ephemerality; scheduled failure alert | Dispatch `runner-hygiene.yml` |
+
+Manual `workflow_dispatch` exists for the scheduled workflows above. Manual
+runs are debugging evidence and intentionally do not open scheduled-failure
+issues. A manual performance run may explicitly allow a known regression; that
+override must not be treated as an ordinary passing baseline.
+
+## Release validation
+
+Release validation is post-merge and tag-driven; it does not substitute for a
+pull-request gate.
+
+| Event | Validation | Budget | Result |
+|---|---|---:|---|
+| Push to `main` or weekly schedule | `Build and Release` platform matrix | 150 min per platform | Build artifacts for all selected targets; no release publication on a main push |
+| Valid release or preview tag | `Build and Release` plus asset checks | 150 min per platform | Draft release, checksummed assets, and publish step |
+| Successful non-preview release-tag build | Docker image build and image scan | 60 min build; 30 min scan | Multi-architecture images plus vulnerability report |
+| Successful release-tag build | DEB/RPM packaging | 30 min per architecture | Packages and checksum files uploaded to the release |
+| Successful non-preview release-tag build | Helm template test and package | 30 min build; 30 min publish | Versioned chart and repository index |
+
+Use an exact preview tag for end-to-end release rehearsal. Manual dispatches
+are backfill/debug paths and do not prove the automatic `workflow_run` chain.
+
+## Evidence requirements
+
+A green check is useful only when it proves the intended behavior ran:
+
+- Record the exact commit SHA and run URL.
+- Separate product failure from runner prerequisites, service readiness, and
+  cancellation. Repair the precondition, then rerun the exact workload.
+- Preserve membership manifests, JUnit, raw compatibility logs, seeds, and
+  server logs where the workflow provides them.
+- For a bug fix or a new fault checker, provide sensitivity evidence: the old
+  behavior or an intentional mutation must fail the new oracle, and the fixed
+  behavior must pass it.
+- Never promote a report-only lane to required from one green run. Require at
+  least 14 days and 30 representative pull requests with at least 99% complete
+  execution, then update the ruleset and this table together.
+
+## Change checklist
+
+Update this file in the same pull request when any of these change:
+
+- workflow triggers, job names, timeouts, or nextest profile ownership;
+- required status contexts or strict/merge-queue policy;
+- scheduled cadence, alert routing, artifact contract, or local reproduction;
+- report-only versus gating semantics.
+
+Do not copy per-module test counts here. Update
+[e2e-suite-inventory.md](e2e-suite-inventory.md) and its enforced membership
+digest instead.

rustfs/Cargo.toml

@@ -336,13 +336,13 @@ opentelemetry = { workspace = true }
 tracing-opentelemetry = { workspace = true }
 # Data structures
 hashbrown = { workspace = true, features = ["serde", "rayon"] }
-mimalloc = { workspace = true }
+rustfs-mimalloc = { workspace = true }
 
 [target.'cfg(target_os = "linux")'.dependencies]
 libsystemd.workspace = true
 
 [target.'cfg(not(target_os = "windows"))'.dependencies]
-libmimalloc-sys.workspace = true
+rustfs-mimalloc-sys.workspace = true
 
 [dev-dependencies]
 uuid = { workspace = true, features = ["v4", "v5", "fast-rng", "macro-diagnostics"] }

rustfs/src/allocator_reclaim.rs

@@ -369,14 +369,8 @@ pub fn allocator_reclaim_controller_snapshot(ctx: &CancellationToken) -> Allocat
 }
 
 #[cfg(not(target_os = "windows"))]
-#[allow(unsafe_code)]
 fn collect_allocator_memory(force: bool) -> Result<(), String> {
-    // SAFETY: `mi_collect` is provided by the active global allocator backend
-    // on this target family. It is explicitly intended to reclaim retained
-    // pages/segments and does not require additional invariants from the caller.
-    unsafe {
-        libmimalloc_sys::mi_collect(force);
-    }
+    rustfs_mimalloc::MiMalloc::collect(force);
     Ok(())
 }
 

rustfs/src/main.rs

@@ -26,22 +26,22 @@ struct MiMallocAllocator;
 unsafe impl GlobalAlloc for MiMallocAllocator {
     unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
         // SAFETY: the caller upholds GlobalAlloc's contract for layout.
-        unsafe { mimalloc::MiMalloc.alloc(layout) }
+        unsafe { rustfs_mimalloc::MiMalloc.alloc(layout) }
     }
 
     unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
         // SAFETY: the caller upholds GlobalAlloc's contract for layout.
-        unsafe { mimalloc::MiMalloc.alloc_zeroed(layout) }
+        unsafe { rustfs_mimalloc::MiMalloc.alloc_zeroed(layout) }
     }
 
     unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
         // SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
-        unsafe { mimalloc::MiMalloc.dealloc(ptr, layout) }
+        unsafe { rustfs_mimalloc::MiMalloc.dealloc(ptr, layout) }
     }
 
     unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
         // SAFETY: ptr and layout came from this allocator and are forwarded unchanged.
-        unsafe { mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
+        unsafe { rustfs_mimalloc::MiMalloc.realloc(ptr, layout, new_size) }
     }
 }
 
@@ -51,7 +51,7 @@ static GLOBAL: hotpath::CountingAllocator<MiMallocAllocator> = hotpath::Counting
 
 #[cfg(not(all(feature = "hotpath", feature = "hotpath-alloc")))]
 #[global_allocator]
-static GLOBAL: mimalloc::MiMalloc = mimalloc::MiMalloc;
+static GLOBAL: rustfs_mimalloc::MiMalloc = rustfs_mimalloc::MiMalloc;
 
 fn main() {
     let _hotpath_guard = hotpath::HotpathGuardBuilder::new("main").build();
@@ -71,8 +71,9 @@ mod tests {
         allocation.extend_from_slice(&[7_u8; 64]);
 
         assert_eq!(allocation.len(), 64);
+        let heap = rustfs_mimalloc::heap::Heap::main();
         // SAFETY: the live Vec pointer is valid to inspect for heap ownership.
-        assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(allocation.as_ptr().cast()) });
+        assert!(unsafe { heap.contains(allocation.as_ptr()) });
     }
 
     #[test]
@@ -85,12 +86,13 @@ mod tests {
         let layout = Layout::from_size_align(32, 8).expect("valid test allocation layout");
         let grown_layout = Layout::from_size_align(64, 8).expect("valid grown test allocation layout");
         let allocator = super::MiMallocAllocator;
+        let heap = rustfs_mimalloc::heap::Heap::main();
 
         // SAFETY: The pointer is checked for null before use and later released
         // through the same allocator with the corresponding layout.
         let ptr = unsafe { allocator.alloc_zeroed(layout) };
         assert!(!ptr.is_null());
-        assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(ptr.cast()) });
+        assert!(unsafe { heap.contains(ptr) });
         assert!(unsafe { std::slice::from_raw_parts(ptr, 32).iter().all(|byte| *byte == 0) });
 
         // SAFETY: `ptr` was allocated by `allocator` with `layout`; on failure
@@ -102,7 +104,7 @@ mod tests {
             panic!("mimalloc realloc failed in allocator smoke test");
         }
 
-        assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(grown_ptr.cast()) });
+        assert!(unsafe { heap.contains(grown_ptr) });
         // SAFETY: `grown_ptr` was reallocated by `allocator` and is released
         // with the matching grown layout.
         unsafe { allocator.dealloc(grown_ptr, grown_layout) };

rustfs/src/memory_observability.rs

@@ -17,10 +17,7 @@ use rustfs_io_metrics::{
     record_cpu_usage, record_memory_usage, record_process_memory_split,
 };
 use serde::Serialize;
-#[cfg(any(test, not(target_os = "windows")))]
 use serde_json::Value;
-#[cfg(not(target_os = "windows"))]
-use std::ffi::CStr;
 use std::path::Path;
 use std::sync::{Arc, Mutex, OnceLock};
 use std::time::Duration;
@@ -231,7 +228,18 @@ fn read_cgroup_memory_snapshot() -> Option<CgroupMemorySnapshot> {
     read_cgroup_v2().or_else(read_cgroup_v1)
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
+fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
+    let json = rustfs_mimalloc::MiMalloc::stats_json();
+    if json.is_empty() {
+        return None;
+    }
+    let observation = parse_mimalloc_stats_json(&json)?;
+    Some(AllocatorMemorySnapshot {
+        backend: crate::allocator_reclaim::allocator_backend(),
+        observation,
+    })
+}
+
 fn numeric_json_value(value: &Value) -> Option<u64> {
     match value {
         Value::Number(number) => number
@@ -242,7 +250,6 @@ fn numeric_json_value(value: &Value) -> Option<u64> {
     }
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
 fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
     match value {
         Value::Object(fields) => fields
@@ -254,7 +261,6 @@ fn numeric_json_field(value: &Value, field: &str) -> Option<u64> {
     }
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
 fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64> {
     match value {
         Value::Object(fields) => {
@@ -271,12 +277,10 @@ fn mimalloc_stat_field(value: &Value, metric: &str, field: &str) -> Option<u64>
     }
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
 fn mimalloc_stat_current(value: &Value, metric: &str) -> Option<u64> {
     mimalloc_stat_field(value, metric, "current")
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
 fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64> {
     metrics
         .iter()
@@ -285,7 +289,6 @@ fn mimalloc_stat_sum(value: &Value, metrics: &[&str], field: &str) -> Option<u64
         .filter(|value| *value > 0)
 }
 
-#[cfg(any(test, not(target_os = "windows")))]
 fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservation> {
     let value = serde_json::from_str::<Value>(stats_json).ok()?;
     let malloc_metrics = ["malloc_normal", "malloc_huge"];
@@ -312,33 +315,6 @@ fn parse_mimalloc_stats_json(stats_json: &str) -> Option<AllocatorMemoryObservat
     }
 }
 
-#[cfg(not(target_os = "windows"))]
-#[allow(unsafe_code)]
-fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
-    // SAFETY: `mi_stats_get_json` returns a null-terminated JSON buffer owned by
-    // mimalloc when called with a null input buffer. The mimalloc API requires
-    // freeing that buffer with `mi_free`; parsing finishes before the buffer is freed.
-    let observation = unsafe {
-        let stats_ptr = libmimalloc_sys::mi_stats_get_json(0, std::ptr::null_mut());
-        if stats_ptr.is_null() {
-            return None;
-        }
-
-        let observation = CStr::from_ptr(stats_ptr).to_str().ok().and_then(parse_mimalloc_stats_json);
-        libmimalloc_sys::mi_free(stats_ptr.cast());
-        observation?
-    };
-    Some(AllocatorMemorySnapshot {
-        backend: crate::allocator_reclaim::allocator_backend(),
-        observation,
-    })
-}
-
-#[cfg(target_os = "windows")]
-fn read_allocator_memory_snapshot() -> Option<AllocatorMemorySnapshot> {
-    None
-}
-
 fn configured_memory_observability_interval_secs() -> u64 {
     rustfs_utils::get_env_u64(ENV_MEMORY_OBSERVABILITY_INTERVAL_SECS, DEFAULT_MEMORY_OBSERVABILITY_INTERVAL_SECS).max(1)
 }
@@ -566,6 +542,13 @@ mod tests {
         assert_eq!(parse_mimalloc_stats_json(r#"{ "allocator": "unknown" }"#), None);
     }
 
+    #[test]
+    fn read_allocator_memory_snapshot_uses_mimalloc_stats_json() {
+        let snapshot = super::read_allocator_memory_snapshot();
+        #[cfg(not(target_os = "windows"))]
+        assert!(snapshot.is_some(), "allocator snapshot should be available on non-Windows");
+    }
+
     #[test]
     fn memory_observability_snapshot_reports_disabled_when_metrics_are_disabled() {
         let snapshot = build_memory_observability_status_snapshot(false, 15, false);

scripts/test/vault_ha_kms_live.sh

@@ -241,7 +241,7 @@ env \
   RUSTFS_TEST_VAULT_FAILOVER_MARKER="$MARKER" \
   RUSTFS_TEST_VAULT_OLD_LEADER="$OLD_LEADER" \
   cargo test -p rustfs-kms --test vault_ha_failover_live \
-    vault_raft_leader_failure_preserves_kv2_and_transit_decrypts -- \
+    vault_raft_leader_failure_recovers_kv2_and_transit_decrypts -- \
     --ignored --nocapture --test-threads=1 &
 TEST_PID=$!