ci: stop running expensive jobs that cannot inform the result (#5528)

Three independent fixes that all avoid burning self-hosted runners on work
whose outcome is already determined. None of them changes what is tested.

- ci-docs-only: add a "Quick Checks" companion job. It is a prerequisite for
  gating ci.yml's expensive jobs behind quick-checks (rustfs/backlog#1599):
  once "Quick Checks" is a required check, a docs-only PR would otherwise wait
  on it forever. The steps are a byte-identical copy of ci.yml's quick-checks
  rather than an `echo`, so that on a mixed PR the two same-named check runs
  execute the same commands against the same merge ref and cannot disagree —
  GitHub has no written contract for how it picks between same-named required
  check runs, and the real job only takes 45-51s, leaving no timing margin to
  rely on.

- ci: guard uring-integration with the same `closed` check every other job
  already has. The pull_request trigger includes `closed` only so the
  concurrency group cancels in-flight runs; this job had no guard and no
  `needs`, so every closed or merged PR ran the full io_uring suite (4m17s,
  7m19s and 7m31s on runs 30678272341, 30678117601 and 30662728539).

- ci: gate s3-lifecycle-behavior-tests on e2e-tests, matching
  s3-implemented-tests. Both lanes only download the prebuilt debug binary, and
  s3-implemented-tests already finishes later, so a green PR's wall clock is
  unchanged; a red one stops holding a sm-standard-4 for up to 30 minutes.

Refs: rustfs/backlog#1598, rustfs/backlog#1599

.github/workflows/ci-docs-only.yml

@@ -12,18 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Companion to ci.yml for the required "Test and Lint" status check.
+# Companion to ci.yml for the required "Test and Lint" and "Quick Checks"
+# status checks.
 #
 # ci.yml skips docs-only pull requests via paths-ignore, but the branch
-# ruleset requires a check named "Test and Lint" — without this workflow a
-# docs-only PR would wait on that check forever. This workflow triggers on
-# exactly the paths ci.yml ignores and reports an instant success under the
-# same job name. Mixed PRs trigger both workflows and the real check still
-# gates: a required check with any failing run blocks the merge.
+# ruleset requires checks named "Test and Lint" and "Quick Checks" — without
+# this workflow a docs-only PR would wait on those checks forever. This
+# workflow triggers on exactly the paths ci.yml ignores and reports success
+# under the same job names. Mixed PRs trigger both workflows and the real
+# checks still gate: a required check with any failing run blocks the merge.
 # https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/defining-the-mergeability-of-pull-requests/troubleshooting-required-status-checks#handling-skipped-but-required-checks
 #
 # Keep the paths list below in sync with the pull_request paths-ignore list
-# in ci.yml.
+# in ci.yml, and keep the quick-checks steps below byte-identical to the
+# quick-checks job in ci.yml (see the comment on that job).
 
 name: Continuous Integration (docs only)
 
@@ -52,9 +54,63 @@ permissions:
   contents: read
 
 jobs:
+  # Deliberately NOT a bare `echo`. Once "Quick Checks" becomes a required
+  # check, ci.yml gates every expensive job behind it, so a mixed PR reports
+  # two check runs with this name: the real one (45-51s) and this companion.
+  # GitHub has no written contract for how it picks between same-named
+  # required check runs ("latest wins" vs "any failure blocks"), so instead of
+  # relying on ordering we make both runs execute the same commands against
+  # the same merge ref — their conclusions are then necessarily identical and
+  # the choice does not matter. Keep these steps byte-identical to the
+  # quick-checks job in ci.yml (a guard script that asserts this, and the paths
+  # sync below, is tracked in rustfs/backlog#1603).
+  #
+  # For a genuinely docs-only PR this adds no strictness (no code changed, so
+  # fmt and the guards always pass) and costs ~50s of ubuntu-latest.
+  quick-checks:
+    name: Quick Checks
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
+
+      - name: Install ripgrep
+        run: sudo apt-get update && sudo apt-get install -y ripgrep
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable
+        with:
+          components: rustfmt
+
+      - name: Check code formatting
+        run: cargo fmt --all --check
+
+      - name: Check unsafe code allowances
+        run: ./scripts/check_unsafe_code_allowances.sh
+
+      - name: Check layered dependencies
+        run: ./scripts/check_layer_dependencies.sh
+
+      - name: Check architecture migration rules
+        run: ./scripts/check_architecture_migration_rules.sh
+
+      - name: Check tokio io-uring feature guard
+        run: ./scripts/check_no_tokio_io_uring.sh
+
+      - name: Check extension schema boundaries
+        run: ./scripts/check_extension_schema_boundaries.sh
+
+      - name: Check body-cache whitelist guard
+        run: ./scripts/check_body_cache_whitelist.sh
+
+      - name: Check no planning docs committed
+        run: ./scripts/check_no_planning_docs.sh
+
   test-and-lint:
     name: Test and Lint
     runs-on: ubuntu-latest
+    timeout-minutes: 10
     steps:
       - name: Checkout repository
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7

.github/workflows/ci.yml

@@ -448,6 +448,13 @@ jobs:
 
   uring-integration:
     name: io_uring Integration (real)
+    # The pull_request trigger includes `closed` purely so the concurrency
+    # group cancels in-flight runs of a closed PR; every other job opts out of
+    # that run with this guard (or is skipped through its `needs` chain). This
+    # 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: github.event_name != 'pull_request' || github.event.action != 'closed'
     # 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
     # the probe succeeds and the tests exercise the real UringBackend/FdCache/
@@ -746,7 +753,13 @@ jobs:
   # evaluates ILM within ~2s of the due time, well inside the poll window.
   s3-lifecycle-behavior-tests:
     name: S3 Lifecycle Behavior Tests
-    needs: [ build-rustfs-debug-binary ]
+    # Also gated on e2e-tests, matching s3-implemented-tests: when the e2e smoke
+    # suite is already red this lane cannot tell us anything new, and it holds a
+    # sm-standard-4 for up to 30 minutes doing so. Both lanes only download the
+    # prebuilt debug binary (no cargo build), and s3-implemented-tests — which
+    # already waits on e2e-tests — finishes later anyway, so a green PR's total
+    # wall clock is unchanged.
+    needs: [ build-rustfs-debug-binary, e2e-tests ]
     runs-on: sm-standard-4
     timeout-minutes: 30
     steps:

crates/e2e_test/src/object_lock/object_lock_test.rs

@@ -26,6 +26,7 @@
 
 use super::common::*;
 use aws_sdk_s3::Client;
+use aws_sdk_s3::error::ProvideErrorMetadata;
 use aws_sdk_s3::primitives::{ByteStream, DateTimeFormat};
 use aws_sdk_s3::types::{
     CompletedMultipartUpload, CompletedPart, Delete, MetadataDirective, ObjectIdentifier, ObjectLockLegalHoldStatus,
@@ -2120,6 +2121,127 @@ async fn test_multipart_default_retention_fixed_at_create() {
 // Versioning Auto-Enable Tests
 // ============================================================================
 
+#[tokio::test]
+#[serial]
+async fn test_unretained_object_lock_object_delete_and_bucket_cleanup() {
+    init_logging();
+    info!("🧪 Test: Unretained Object Lock object delete and bucket cleanup (Issue #5339)");
+
+    let mut env = ObjectLockTestEnvironment::new()
+        .await
+        .expect("failed to create Object Lock test environment");
+    env.start_rustfs().await.expect("failed to start RustFS");
+
+    let bucket = "test-object-lock-delete-cleanup";
+    let key = "unretained-object";
+
+    env.create_object_lock_bucket(bucket)
+        .await
+        .expect("failed to create Object Lock bucket");
+    let client = env.s3_client();
+
+    let put_response = client
+        .put_object()
+        .bucket(bucket)
+        .key(key)
+        .body(ByteStream::from_static(b"unretained data"))
+        .send()
+        .await
+        .expect("failed to upload unretained object");
+    let object_version_id = put_response
+        .version_id()
+        .expect("Object Lock buckets must create versioned objects")
+        .to_string();
+
+    let delete_response = client
+        .delete_object()
+        .bucket(bucket)
+        .key(key)
+        .send()
+        .await
+        .expect("failed to create delete marker");
+    assert_eq!(delete_response.delete_marker(), Some(true));
+    let delete_marker_version_id = delete_response
+        .version_id()
+        .expect("Deleting without a version ID must create a delete marker")
+        .to_string();
+
+    let get_error = client
+        .get_object()
+        .bucket(bucket)
+        .key(key)
+        .send()
+        .await
+        .expect_err("GET must not return an object hidden by a delete marker");
+    assert_eq!(get_error.raw_response().map(|response| response.status().as_u16()), Some(404));
+    assert_eq!(get_error.as_service_error().and_then(|error| error.code()), Some("NoSuchKey"));
+
+    let listed_objects = client
+        .list_objects_v2()
+        .bucket(bucket)
+        .send()
+        .await
+        .expect("failed to list current objects");
+    assert!(
+        listed_objects.contents().iter().all(|object| object.key() != Some(key)),
+        "ListObjectsV2 must hide objects whose latest version is a delete marker"
+    );
+
+    let listed_versions = client
+        .list_object_versions()
+        .bucket(bucket)
+        .send()
+        .await
+        .expect("failed to list object versions");
+    assert!(
+        listed_versions
+            .versions()
+            .iter()
+            .any(|version| version.key() == Some(key) && version.version_id() == Some(object_version_id.as_str())),
+        "The data version must remain until it is explicitly deleted"
+    );
+    assert!(
+        listed_versions
+            .delete_markers()
+            .iter()
+            .any(|marker| marker.key() == Some(key) && marker.version_id() == Some(delete_marker_version_id.as_str())),
+        "ListObjectVersions must expose the delete marker"
+    );
+
+    client
+        .delete_object()
+        .bucket(bucket)
+        .key(key)
+        .version_id(object_version_id)
+        .send()
+        .await
+        .expect("failed to delete the data version");
+    client
+        .delete_object()
+        .bucket(bucket)
+        .key(key)
+        .version_id(delete_marker_version_id)
+        .send()
+        .await
+        .expect("failed to delete the delete marker");
+
+    let remaining_versions = client
+        .list_object_versions()
+        .bucket(bucket)
+        .send()
+        .await
+        .expect("failed to list versions after cleanup");
+    assert!(remaining_versions.versions().is_empty());
+    assert!(remaining_versions.delete_markers().is_empty());
+
+    client
+        .delete_bucket()
+        .bucket(bucket)
+        .send()
+        .await
+        .expect("Deleting every version must remove xl.meta so the bucket can be deleted normally");
+}
+
 #[tokio::test]
 #[serial]
 async fn test_versioning_auto_enabled_with_object_lock() {

rustfs/src/main.rs

@@ -12,9 +12,32 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+#[cfg(all(feature = "hotpath", feature = "hotpath-alloc"))]
+use std::alloc::{GlobalAlloc, Layout};
+
+#[cfg(all(feature = "hotpath", feature = "hotpath-alloc"))]
+#[derive(Default)]
+struct DefaultMiMalloc;
+
+#[cfg(all(feature = "hotpath", feature = "hotpath-alloc"))]
+// SAFETY: allocation and deallocation are forwarded unchanged to MiMalloc, so
+// MiMalloc's GlobalAlloc guarantees apply to every returned pointer and layout.
+#[allow(unsafe_code)]
+unsafe impl GlobalAlloc for DefaultMiMalloc {
+    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
+        // SAFETY: the caller upholds GlobalAlloc's contract for layout.
+        unsafe { mimalloc::MiMalloc.alloc(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) }
+    }
+}
+
 #[cfg(all(feature = "hotpath", feature = "hotpath-alloc"))]
 #[global_allocator]
-static GLOBAL: hotpath::CountingAllocator = hotpath::CountingAllocator::new();
+static GLOBAL: hotpath::CountingAllocator<DefaultMiMalloc> = hotpath::CountingAllocator::new();
 
 #[cfg(not(all(feature = "hotpath", feature = "hotpath-alloc")))]
 #[global_allocator]
@@ -25,3 +48,15 @@ fn main() {
 
     rustfs::startup_entrypoint::run_process();
 }
+
+#[cfg(all(test, feature = "hotpath", feature = "hotpath-alloc"))]
+mod tests {
+    #[test]
+    #[allow(unsafe_code)]
+    fn hotpath_allocator_uses_mimalloc() {
+        let allocation = Box::new([0_u8; 64]);
+
+        // SAFETY: the live Box pointer is valid to inspect for heap ownership.
+        assert!(unsafe { libmimalloc_sys::mi_is_in_heap_region(allocation.as_ptr().cast()) });
+    }
+}