fix(mount): add -posixDirNlink option for correct directory nlink

Add optional POSIX-compliant directory nlink counting
(nlink = 2 + number_of_subdirectories) behind the -posixDirNlink
flag. This requires listing cached directory entries on every stat,
which has a performance cost, so it's off by default.

When disabled (default), directories report nlink=2, which is the
POSIX-compliant baseline for empty directories and a common default
in distributed filesystems.

- Set nlink baseline to 2 for all directories (was 1)
- Add applyDirNlink() gated behind option.PosixDirNlink
- Add -posixDirNlink CLI flag

.claude/scheduled_tasks.lock

@@ -0,0 +1 @@
+{"sessionId":"d6574c47-eafc-4a94-9dce-f9ffea22b53c","pid":10111,"acquiredAt":1775248373916}

.github/workflows/binaries_dev.yml

@@ -18,6 +18,7 @@ jobs:
 
       - name: Delete old release assets
         uses: mknejp/delete-release-assets@v1
+        continue-on-error: true
         with:
           token: ${{ github.token }}
           tag: dev

.github/workflows/container_dev.yml

@@ -9,17 +9,96 @@ permissions:
 
 jobs:
 
+  # ── Pre-build Rust volume server binaries natively ──────────────────
+  build-rust-binaries:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-musl
+            arch: amd64
+          - target: aarch64-unknown-linux-musl
+            arch: arm64
+            cross: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install protobuf compiler
+        run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Install musl tools (amd64)
+        if: ${{ !matrix.cross }}
+        run: sudo apt-get install -y musl-tools
+
+      - name: Install cross-compilation tools (arm64)
+        if: matrix.cross
+        run: |
+          sudo apt-get install -y gcc-aarch64-linux-gnu
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
+          # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
+          echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
+
+      - name: Cache cargo registry and target
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            seaweed-volume/target
+          key: rust-docker-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+          restore-keys: |
+            rust-docker-dev-${{ matrix.target }}-
+
+      - name: Build normal variant
+        env:
+          SEAWEEDFS_COMMIT: ${{ github.sha }}
+        run: |
+          cd seaweed-volume
+          cargo build --release --target ${{ matrix.target }} --no-default-features
+          cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v7
+        with:
+          name: rust-volume-${{ matrix.arch }}
+          path: weed-volume-normal-${{ matrix.arch }}
+
   build-dev-containers:
+    needs: [build-rust-binaries]
     runs-on: [ubuntu-latest]
 
     steps:
-      -
-        name: Checkout
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
-      -
-        name: Docker meta
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Download pre-built Rust binaries
+        uses: actions/download-artifact@v8
+        with:
+          pattern: rust-volume-*
+          merge-multiple: true
+          path: ./rust-bins
+
+      - name: Place Rust binaries in Docker context
+        run: |
+          mkdir -p docker/weed-volume-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-volume-normal-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
+              echo "Placed pre-built Rust binary for ${arch}"
+            fi
+          done
+          ls -la docker/weed-volume-prebuilt/
+
+      - name: Docker meta
         id: docker_meta
-        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v3
+        uses: docker/metadata-action@v6
         with:
           images: |
             chrislusf/seaweedfs
@@ -30,40 +109,40 @@ jobs:
             org.opencontainers.image.title=seaweedfs
             org.opencontainers.image.description=SeaweedFS is a distributed storage system for blobs, objects, files, and data lake, to store and serve billions of files fast!
             org.opencontainers.image.vendor=Chris Lu
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v1
-      -
-        name: Create BuildKit config
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v4
+
+      - name: Create BuildKit config
         run: |
           cat > /tmp/buildkitd.toml <<EOF
           [registry."docker.io"]
             mirrors = ["https://mirror.gcr.io"]
           EOF
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v1
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v4
         with:
           buildkitd-flags: "--debug"
           buildkitd-config: /tmp/buildkitd.toml
-      -
-        name: Login to Docker Hub
+
+      - name: Login to Docker Hub
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      -
-        name: Login to GHCR
+
+      - name: Login to GHCR
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}
           password: ${{ secrets.GHCR_TOKEN }}
-      -
-        name: Build
-        uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v2
+
+      - name: Build
+        uses: docker/build-push-action@v7
         with:
           context: ./docker
           push: ${{ github.event_name != 'pull_request' }}

.github/workflows/container_foundationdb_version.yml

@@ -133,7 +133,7 @@ jobs:
 
       - name: Login to Docker Hub
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}

.github/workflows/container_latest.yml

@@ -58,8 +58,80 @@ jobs:
             echo "publish=true" >> "$GITHUB_OUTPUT"
           fi
 
+  # ── Pre-build Rust volume server binaries natively ──────────────────
+  build-rust-binaries:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-musl
+            arch: amd64
+          - target: aarch64-unknown-linux-musl
+            arch: arm64
+            cross: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
+
+      - name: Install protobuf compiler
+        run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Install musl tools (amd64)
+        if: ${{ !matrix.cross }}
+        run: sudo apt-get install -y musl-tools
+
+      - name: Install cross-compilation tools (arm64)
+        if: matrix.cross
+        run: |
+          sudo apt-get install -y gcc-aarch64-linux-gnu
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
+          # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
+          echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
+
+      - name: Cache cargo registry and target
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            seaweed-volume/target
+          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+          restore-keys: |
+            rust-docker-${{ matrix.target }}-
+
+      - name: Build large-disk variant
+        env:
+          SEAWEEDFS_COMMIT: ${{ github.sha }}
+        run: |
+          cd seaweed-volume
+          cargo build --release --target ${{ matrix.target }}
+          cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-large-disk-${{ matrix.arch }}
+
+      - name: Build normal variant
+        env:
+          SEAWEEDFS_COMMIT: ${{ github.sha }}
+        run: |
+          cd seaweed-volume
+          cargo build --release --target ${{ matrix.target }} --no-default-features
+          cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v7
+        with:
+          name: rust-volume-${{ matrix.arch }}
+          path: |
+            weed-volume-large-disk-${{ matrix.arch }}
+            weed-volume-normal-${{ matrix.arch }}
+
   build:
-    needs: [setup]
+    needs: [setup, build-rust-binaries]
     runs-on: ubuntu-latest
     strategy:
       matrix:
@@ -94,11 +166,32 @@ jobs:
           if [ "${{ matrix.variant }}" == "large_disk" ]; then
             echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
             echo "build_args=TAGS=5BytesOffset" >> $GITHUB_OUTPUT
+            echo "rust_variant=large-disk" >> $GITHUB_OUTPUT
           else
             echo "tag_suffix=" >> $GITHUB_OUTPUT
             echo "build_args=" >> $GITHUB_OUTPUT
+            echo "rust_variant=normal" >> $GITHUB_OUTPUT
           fi
 
+      - name: Download pre-built Rust binaries
+        uses: actions/download-artifact@v8
+        with:
+          pattern: rust-volume-*
+          merge-multiple: true
+          path: ./rust-bins
+
+      - name: Place Rust binaries in Docker context
+        run: |
+          mkdir -p docker/weed-volume-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-volume-${{ steps.config.outputs.rust_variant }}-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
+              echo "Placed pre-built Rust binary for ${arch}"
+            fi
+          done
+          ls -la docker/weed-volume-prebuilt/
+
       - name: Docker meta
         id: docker_meta
         uses: docker/metadata-action@v6
@@ -127,13 +220,13 @@ jobs:
           buildkitd-config: /tmp/buildkitd.toml
       - name: Login to Docker Hub
         if: needs.setup.outputs.publish == 'true'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
       - name: Login to GHCR
         if: needs.setup.outputs.publish == 'true'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}
@@ -166,7 +259,7 @@ jobs:
 
   trivy-scan:
     runs-on: ubuntu-latest
-    needs: [setup, build]
+    needs: [setup, build, build-rust-binaries]
     strategy:
       matrix:
         variant: ${{ fromJSON(needs.setup.outputs.variants) }}
@@ -181,7 +274,7 @@ jobs:
           fi
       - name: Login to GHCR
         if: needs.setup.outputs.publish == 'true'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}
@@ -191,6 +284,29 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
+      - name: Download pre-built Rust binaries for local scan
+        if: needs.setup.outputs.publish != 'true'
+        uses: actions/download-artifact@v8
+        with:
+          pattern: rust-volume-*
+          merge-multiple: true
+          path: ./rust-bins
+      - name: Place Rust binaries in Docker context for local scan
+        if: needs.setup.outputs.publish != 'true'
+        run: |
+          rust_variant="normal"
+          if [ "${{ matrix.variant }}" == "large_disk" ]; then
+            rust_variant="large-disk"
+          fi
+          mkdir -p docker/weed-volume-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-volume-${rust_variant}-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
+              echo "Placed pre-built Rust binary for ${arch}"
+            fi
+          done
+          ls -la docker/weed-volume-prebuilt/
       - name: Create BuildKit config for local scan build
         if: needs.setup.outputs.publish != 'true'
         run: |
@@ -313,12 +429,12 @@ jobs:
             ghcr.io/chrislusf/seaweedfs
           tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
       - name: Login to Docker Hub
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
       - name: Login to GHCR
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}

.github/workflows/container_release_foundationdb.yml

@@ -42,7 +42,7 @@ jobs:
       -
         name: Login to Docker Hub
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}

.github/workflows/container_release_unified.yml

@@ -39,7 +39,82 @@ concurrency:
   cancel-in-progress: false
 
 jobs:
+
+  # ── Pre-build Rust volume server binaries natively ──────────────────
+  # Cross-compiles for amd64 and arm64 without QEMU, turning a 5-hour
+  # emulated cargo build into ~15 minutes of native compilation.
+  build-rust-binaries:
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-musl
+            arch: amd64
+          - target: aarch64-unknown-linux-musl
+            arch: arm64
+            cross: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+
+      - name: Install protobuf compiler
+        run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Install musl tools (amd64)
+        if: ${{ !matrix.cross }}
+        run: sudo apt-get install -y musl-tools
+
+      - name: Install cross-compilation tools (arm64)
+        if: matrix.cross
+        run: |
+          sudo apt-get install -y gcc-aarch64-linux-gnu
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
+          # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
+          echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
+
+      - name: Cache cargo registry and target
+        uses: actions/cache@v5
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            seaweed-volume/target
+          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+          restore-keys: |
+            rust-docker-${{ matrix.target }}-
+
+      - name: Build large-disk variant
+        env:
+          SEAWEEDFS_COMMIT: ${{ github.sha }}
+        run: |
+          cd seaweed-volume
+          cargo build --release --target ${{ matrix.target }}
+          cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-large-disk-${{ matrix.arch }}
+
+      - name: Build normal variant
+        env:
+          SEAWEEDFS_COMMIT: ${{ github.sha }}
+        run: |
+          cd seaweed-volume
+          cargo build --release --target ${{ matrix.target }} --no-default-features
+          cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v7
+        with:
+          name: rust-volume-${{ matrix.arch }}
+          path: |
+            weed-volume-large-disk-${{ matrix.arch }}
+            weed-volume-normal-${{ matrix.arch }}
+
+  # ── Build Docker containers ─────────────────────────────────────────
   build:
+    needs: [build-rust-binaries]
     runs-on: ubuntu-latest
     strategy:
       # Build sequentially to avoid rate limits
@@ -52,20 +127,23 @@ jobs:
             dockerfile: ./docker/Dockerfile.go_build
             build_args: ""
             tag_suffix: ""
-            
-          # Large disk - multi-arch  
+            rust_variant: normal
+
+          # Large disk - multi-arch
           - variant: large_disk
             platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/386
             dockerfile: ./docker/Dockerfile.go_build
             build_args: TAGS=5BytesOffset
             tag_suffix: _large_disk
-            
+            rust_variant: large-disk
+
           # Full tags - multi-arch
           - variant: full
             platforms: linux/amd64,linux/arm64
             dockerfile: ./docker/Dockerfile.go_build
             build_args: TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
             tag_suffix: _full
+            rust_variant: normal
 
           # Large disk + full tags - multi-arch
           - variant: large_disk_full
@@ -73,19 +151,42 @@ jobs:
             dockerfile: ./docker/Dockerfile.go_build
             build_args: TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
             tag_suffix: _large_disk_full
-            
+            rust_variant: large-disk
+
           # RocksDB large disk - amd64 only
           - variant: rocksdb
             platforms: linux/amd64
             dockerfile: ./docker/Dockerfile.rocksdb_large
             build_args: ""
             tag_suffix: _large_disk_rocksdb
+            rust_variant: large-disk
             
     steps:
       - name: Checkout
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         uses: actions/checkout@v6
-        
+
+      - name: Download pre-built Rust binaries
+        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
+        uses: actions/download-artifact@v8
+        with:
+          pattern: rust-volume-*
+          merge-multiple: true
+          path: ./rust-bins
+
+      - name: Place Rust binaries in Docker context
+        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
+        run: |
+          mkdir -p docker/weed-volume-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-volume-${{ matrix.rust_variant }}-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
+              echo "Placed pre-built Rust binary for ${arch}"
+            fi
+          done
+          ls -la docker/weed-volume-prebuilt/
+
       - name: Free Disk Space
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         run: |
@@ -135,14 +236,14 @@ jobs:
           
       - name: Login to Docker Hub
         if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && github.event_name != 'pull_request'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
           
       - name: Login to GHCR
         if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && github.event_name != 'pull_request'
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}
@@ -198,14 +299,14 @@ jobs:
     steps:
       - name: Login to Docker Hub
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
           
       - name: Login to GHCR
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
-        uses: docker/login-action@v4
+        uses: docker/login-action@v4.1.0
         with:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}

.github/workflows/container_rocksdb_version.yml

@@ -88,7 +88,7 @@ jobs:
         uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v1
 
       - name: Login to Docker Hub
-        uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v1
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}

.github/workflows/fuse-dlm-integration.yml

@@ -0,0 +1,63 @@
+name: "FUSE DLM Integration Tests"
+
+on:
+  pull_request:
+    paths:
+      - 'weed/command/mount*.go'
+      - 'weed/mount/**'
+      - 'weed/cluster/**'
+      - 'test/fuse_dlm/**'
+      - '.github/workflows/fuse-dlm-integration.yml'
+  push:
+    branches: [master]
+    paths:
+      - 'weed/command/mount*.go'
+      - 'weed/mount/**'
+      - 'weed/cluster/**'
+      - 'test/fuse_dlm/**'
+
+concurrency:
+  group: ${{ github.head_ref || github.ref }}/fuse-dlm-integration
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  fuse-dlm-integration:
+    name: FUSE DLM Integration Tests
+    runs-on: ubuntu-22.04
+    timeout-minutes: 30
+
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v6
+
+      - name: Set up Go
+        uses: actions/setup-go@v6
+        with:
+          go-version-file: 'go.mod'
+
+      - name: Install FUSE dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libfuse3-dev
+          echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
+          sudo chmod 644 /etc/fuse.conf
+
+      - name: Build SeaweedFS
+        run: go build -o weed/weed -buildvcs=false ./weed
+
+      - name: Run DLM integration tests
+        timeout-minutes: 25
+        env:
+          WEED_BINARY: ${{ github.workspace }}/weed/weed
+        run: go test -v -count=1 -timeout=20m ./test/fuse_dlm/...
+
+      - name: Upload logs on failure
+        if: failure()
+        uses: actions/upload-artifact@v7
+        with:
+          name: fuse-dlm-test-logs
+          path: /tmp/seaweedfs-fuse-dlm-logs/
+          retention-days: 3

.github/workflows/pjdfstest.yml

@@ -0,0 +1,87 @@
+name: "pjdfstest POSIX Compliance"
+
+on:
+  push:
+    branches: [ master, main ]
+    paths:
+      - 'weed/mount/**'
+      - 'weed/filer/**'
+      - 'test/pjdfstest/**'
+      - '.github/workflows/pjdfstest.yml'
+  pull_request:
+    branches: [ master, main ]
+    paths:
+      - 'weed/mount/**'
+      - 'weed/filer/**'
+      - 'test/pjdfstest/**'
+      - '.github/workflows/pjdfstest.yml'
+  workflow_dispatch:
+
+concurrency:
+  group: pjdfstest/${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  pjdfstest:
+    name: pjdfstest
+    runs-on: ubuntu-22.04
+    timeout-minutes: 60
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v6
+
+    - name: Set up Go
+      uses: actions/setup-go@v6
+      with:
+        go-version-file: 'go.mod'
+
+    - name: Build SeaweedFS e2e image
+      run: |
+        cd docker
+        make build_e2e || {
+          echo "Retrying without buildx cache..."
+          make binary_race
+          docker build --no-cache -t chrislusf/seaweedfs:e2e -f Dockerfile.e2e .
+        }
+
+    - name: Build pjdfstest image
+      run: |
+        docker build -t chrislusf/seaweedfs:pjdfstest test/pjdfstest/
+
+    - name: Start SeaweedFS cluster
+      run: |
+        docker compose -f test/pjdfstest/docker-compose.yml up --wait
+
+    - name: Run pjdfstest
+      run: |
+        set -o pipefail
+        docker compose -f test/pjdfstest/docker-compose.yml exec -T mount \
+          /run.sh 2>&1 | tee /tmp/pjdfstest-output.log
+
+    - name: Collect logs
+      if: always()
+      run: |
+        mkdir -p /tmp/pjdfstest-docker-logs
+        for svc in master volume filer mount; do
+          docker compose -f test/pjdfstest/docker-compose.yml logs "$svc" \
+            > "/tmp/pjdfstest-docker-logs/${svc}.log" 2>&1 || true
+        done
+
+    - name: Tear down
+      if: always()
+      run: |
+        docker compose -f test/pjdfstest/docker-compose.yml down -v
+
+    - name: Upload logs
+      if: always()
+      uses: actions/upload-artifact@v7
+      with:
+        name: pjdfstest-results
+        path: |
+          /tmp/pjdfstest-output.log
+          /tmp/pjdfstest-docker-logs/
+        retention-days: 7

.github/workflows/rust-volume-server-tests.yml

@@ -93,7 +93,7 @@ jobs:
       - name: Build Go weed binary
         run: |
           cd weed
-          go build -o weed .
+          go build -tags 5BytesOffset -o weed .
           chmod +x weed
           ./weed version
 
@@ -169,7 +169,7 @@ jobs:
       - name: Build Go weed binary
         run: |
           cd weed
-          go build -o weed .
+          go build -tags 5BytesOffset -o weed .
           chmod +x weed
           ./weed version
 

.github/workflows/rust_binaries_dev.yml

@@ -19,6 +19,7 @@ jobs:
     steps:
       - name: Delete old Rust volume dev assets
         uses: mknejp/delete-release-assets@v1
+        continue-on-error: true
         with:
           token: ${{ github.token }}
           tag: dev

.github/workflows/rust_binaries_release.yml

@@ -99,7 +99,7 @@ jobs:
 
       - name: Upload artifacts
         if: ${{ !startsWith(github.ref, 'refs/tags/') }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: rust-volume-${{ matrix.asset_suffix }}
           path: |
@@ -176,7 +176,7 @@ jobs:
 
       - name: Upload artifacts
         if: ${{ !startsWith(github.ref, 'refs/tags/') }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: rust-volume-${{ matrix.asset_suffix }}
           path: |
@@ -245,7 +245,7 @@ jobs:
 
       - name: Upload artifacts
         if: ${{ !startsWith(github.ref, 'refs/tags/') }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: rust-volume-windows_amd64
           path: |

.superset/config.json

@@ -0,0 +1,5 @@
+{
+  "setup": [],
+  "teardown": [],
+  "run": []
+}

Makefile

@@ -42,8 +42,7 @@ test: admin-generate
 
 # Admin component targets
 admin-generate:
-	@echo "Generating admin component templates..."
-	@cd $(ADMIN_DIR) && templ generate ./view
+	@cd $(ADMIN_DIR) && $(MAKE) generate
 
 admin-build: admin-generate
 	@echo "Building admin component..."

docker/Dockerfile.go_build

@@ -16,15 +16,21 @@ RUN cd /go/src/github.com/seaweedfs/seaweedfs/weed \
   && export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=$(git rev-parse --short HEAD)" \
   && CGO_ENABLED=0 go install -tags "$TAGS" -ldflags "-extldflags -static ${LDFLAGS}"
 
-# Rust volume server builder. Alpine packages avoid depending on the
-# upstream rust:alpine manifest list, which no longer includes linux/386.
+# Rust volume server: use pre-built binary from CI when available (placed in
+# weed-volume-prebuilt/ by the build-rust-binaries job), otherwise compile
+# from source.  Pre-building avoids a multi-hour QEMU-emulated cargo build
+# for non-native architectures.
 FROM alpine:3.23 as rust_builder
 ARG TARGETARCH
+ARG TAGS
+COPY weed-volume-prebuilt/ /prebuilt/
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/seaweed-volume /build/seaweed-volume
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/weed /build/weed
 WORKDIR /build/seaweed-volume
-ARG TAGS
-RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
+RUN if [ -f "/prebuilt/weed-volume-${TARGETARCH}" ]; then \
+      echo "Using pre-built Rust binary for ${TARGETARCH}" && \
+      cp "/prebuilt/weed-volume-${TARGETARCH}" /weed-volume; \
+    elif [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
       apk add --no-cache musl-dev openssl-dev protobuf-dev git rust cargo; \
       if [ "$TAGS" = "5BytesOffset" ]; then \
         cargo build --release; \
@@ -51,7 +57,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh
 
 # Install dependencies and create non-root user
 RUN apk upgrade --no-cache zlib && \
-    apk add --no-cache fuse curl su-exec && \
+    apk add --no-cache fuse curl su-exec libgcc && \
     addgroup -g 1000 seaweed && \
     adduser -D -u 1000 -G seaweed seaweed
 

docker/compose/s3_static_users_example.json

@@ -0,0 +1,53 @@
+{
+  "identities": [
+    {
+      "name": "admin",
+      "credentials": [
+        {
+          "accessKey": "AKIAIOSFODNN7EXAMPLE",
+          "secretKey": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY"
+        }
+      ],
+      "actions": [
+        "Admin",
+        "Read",
+        "List",
+        "Tagging",
+        "Write"
+      ]
+    },
+    {
+      "name": "steward",
+      "credentials": [
+        {
+          "accessKey": "steward-key",
+          "secretKey": "steward-secret"
+        }
+      ],
+      "actions": [
+        "Read",
+        "List",
+        "Write"
+      ]
+    },
+    {
+      "name": "le001",
+      "credentials": [
+        {
+          "accessKey": "le001-key",
+          "secretKey": "le001-secret"
+        }
+      ],
+      "actions": [
+        "Read",
+        "List"
+      ]
+    },
+    {
+      "name": "anonymous",
+      "actions": [
+        "Read"
+      ]
+    }
+  ]
+}

go.mod

@@ -34,7 +34,7 @@ require (
 	github.com/google/btree v1.1.3
 	github.com/google/uuid v1.6.0
 	github.com/google/wire v0.7.0 // indirect
-	github.com/googleapis/gax-go/v2 v2.17.0 // indirect
+	github.com/googleapis/gax-go/v2 v2.19.0 // indirect
 	github.com/gorilla/mux v1.8.1
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-multierror v1.1.1 // indirect
@@ -86,7 +86,7 @@ require (
 	github.com/xdg-go/scram v1.2.0
 	github.com/xdg-go/stringprep v1.0.4 // indirect
 	github.com/youmark/pkcs8 v0.0.0-20240726163527-a2c0da244d78 // indirect
-	go.etcd.io/etcd/client/v3 v3.6.9
+	go.etcd.io/etcd/client/v3 v3.6.10
 	go.mongodb.org/mongo-driver v1.17.9
 	go.opencensus.io v0.24.0 // indirect
 	gocloud.dev v0.45.0
@@ -95,22 +95,21 @@ require (
 	golang.org/x/crypto v0.49.0
 	golang.org/x/exp v0.0.0-20260218203240-3dfff04db8fa
 	golang.org/x/image v0.38.0
-	golang.org/x/net v0.51.0
+	golang.org/x/net v0.52.0
 	golang.org/x/oauth2 v0.36.0
 	golang.org/x/sys v0.42.0
 	golang.org/x/text v0.35.0 // indirect
 	golang.org/x/tools v0.42.0 // indirect
 	golang.org/x/xerrors v0.0.0-20240903120638-7835f813f4da // indirect
-	google.golang.org/api v0.267.0
-	google.golang.org/genproto v0.0.0-20260128011058-8636f8732409 // indirect
+	google.golang.org/api v0.274.0
+	google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 // indirect
 	google.golang.org/grpc v1.79.3
 	google.golang.org/protobuf v1.36.11
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	modernc.org/b v1.0.0 // indirect
-	modernc.org/mathutil v1.7.1
+	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect
 	modernc.org/sqlite v1.46.1
-	modernc.org/strutil v1.2.1
 )
 
 require (
@@ -126,8 +125,8 @@ require (
 	github.com/armon/go-metrics v0.4.1
 	github.com/aws/aws-sdk-go-v2 v1.41.5
 	github.com/aws/aws-sdk-go-v2/config v1.32.13
-	github.com/aws/aws-sdk-go-v2/credentials v1.19.13
-	github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.14
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0
 	github.com/cognusion/imaging v1.0.2
 	github.com/fluent/fluent-logger-golang v1.10.1
 	github.com/getsentry/sentry-go v0.44.1
@@ -136,10 +135,9 @@ require (
 	github.com/google/flatbuffers/go v0.0.0-20230108230133-3b8644d32c50
 	github.com/hashicorp/raft v1.7.3
 	github.com/hashicorp/raft-boltdb/v2 v2.3.1
-	github.com/hashicorp/vault/api v1.22.0
+	github.com/hashicorp/vault/api v1.23.0
 	github.com/jhump/protoreflect v1.18.0
 	github.com/linkedin/goavro/v2 v2.15.0
-	github.com/mattn/go-sqlite3 v1.14.34
 	github.com/minio/crc64nvme v1.1.1
 	github.com/orcaman/concurrent-map/v2 v2.0.1
 	github.com/parquet-go/parquet-go v0.28.0
@@ -157,7 +155,7 @@ require (
 	github.com/xeipuuv/gojsonschema v1.2.0
 	github.com/ydb-platform/ydb-go-sdk-auth-environ v0.5.1
 	github.com/ydb-platform/ydb-go-sdk/v3 v3.125.3
-	go.etcd.io/etcd/client/pkg/v3 v3.6.9
+	go.etcd.io/etcd/client/pkg/v3 v3.6.10
 	go.uber.org/atomic v1.11.0
 	golang.org/x/sync v0.20.0
 	golang.org/x/tools/godoc v0.1.0-deprecated
@@ -291,7 +289,7 @@ require (
 
 require (
 	cel.dev/expr v0.25.1 // indirect
-	cloud.google.com/go/auth v0.18.1 // indirect
+	cloud.google.com/go/auth v0.18.2 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
 	cloud.google.com/go/iam v1.5.3 // indirect
@@ -323,21 +321,21 @@ require (
 	github.com/andybalholm/cascadia v1.3.3 // indirect
 	github.com/appscode/go-querystring v0.0.0-20170504095604-0126cfb3f1dc // indirect
 	github.com/arangodb/go-velocypack v0.0.0-20200318135517-5af53c29c67e // indirect
-	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 // indirect
 	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21 // indirect
 	github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.20.12 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sns v1.39.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sqs v1.42.17 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.30.14 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.18 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.15 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sts v1.41.10
 	github.com/aws/smithy-go v1.24.2
 	github.com/boltdb/bolt v1.3.1 // indirect
@@ -371,7 +369,7 @@ require (
 	github.com/geoffgarside/ber v1.2.0 // indirect
 	github.com/go-chi/chi/v5 v5.2.5 // indirect
 	github.com/go-darwin/apfs v0.0.0-20211011131704-f84b94dbf348 // indirect
-	github.com/go-jose/go-jose/v4 v4.1.3 // indirect
+	github.com/go-jose/go-jose/v4 v4.1.4 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-ole/go-ole v1.3.0 // indirect
@@ -387,7 +385,7 @@ require (
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang-jwt/jwt/v4 v4.5.2 // indirect
 	github.com/google/s2a-go v0.1.9 // indirect
-	github.com/googleapis/enterprise-certificate-proxy v0.3.11 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.3.14 // indirect
 	github.com/gorilla/schema v1.4.1 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
 	github.com/gorilla/sessions v1.4.0
@@ -486,22 +484,22 @@ require (
 	github.com/zeebo/blake3 v0.2.4 // indirect
 	github.com/zeebo/errs v1.4.0 // indirect
 	go.etcd.io/bbolt v1.4.3 // indirect
-	go.etcd.io/etcd/api/v3 v3.6.9 // indirect
+	go.etcd.io/etcd/api/v3 v3.6.10 // indirect
 	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
 	go.opentelemetry.io/contrib/detectors/gcp v1.39.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.63.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0 // indirect
-	go.opentelemetry.io/otel v1.40.0 // indirect
-	go.opentelemetry.io/otel/metric v1.40.0 // indirect
-	go.opentelemetry.io/otel/sdk v1.40.0 // indirect
-	go.opentelemetry.io/otel/sdk/metric v1.40.0 // indirect
-	go.opentelemetry.io/otel/trace v1.40.0 // indirect
+	go.opentelemetry.io/otel v1.43.0 // indirect
+	go.opentelemetry.io/otel/metric v1.43.0 // indirect
+	go.opentelemetry.io/otel/sdk v1.43.0 // indirect
+	go.opentelemetry.io/otel/sdk/metric v1.43.0 // indirect
+	go.opentelemetry.io/otel/trace v1.43.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.1 // indirect
-	golang.org/x/term v0.41.0 // indirect
-	golang.org/x/time v0.14.0 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 // indirect
+	golang.org/x/term v0.41.0
+	golang.org/x/time v0.15.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
 	gopkg.in/validator.v2 v2.0.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect

go.sum

@@ -94,8 +94,8 @@ cloud.google.com/go/assuredworkloads v1.7.0/go.mod h1:z/736/oNmtGAyU47reJgGN+KVo
 cloud.google.com/go/assuredworkloads v1.8.0/go.mod h1:AsX2cqyNCOvEQC8RMPnoc0yEarXQk6WEKkxYfL6kGIo=
 cloud.google.com/go/assuredworkloads v1.9.0/go.mod h1:kFuI1P78bplYtT77Tb1hi0FMxM0vVpRC7VVoJC3ZoT0=
 cloud.google.com/go/assuredworkloads v1.10.0/go.mod h1:kwdUQuXcedVdsIaKgKTp9t0UJkE5+PAVNhdQm4ZVq2E=
-cloud.google.com/go/auth v0.18.1 h1:IwTEx92GFUo2pJ6Qea0EU3zYvKnTAeRCODxfA/G5UWs=
-cloud.google.com/go/auth v0.18.1/go.mod h1:GfTYoS9G3CWpRA3Va9doKN9mjPGRS+v41jmZAhBzbrA=
+cloud.google.com/go/auth v0.18.2 h1:+Nbt5Ev0xEqxlNjd6c+yYUeosQ5TtEUaNcN/3FozlaM=
+cloud.google.com/go/auth v0.18.2/go.mod h1:xD+oY7gcahcu7G2SG2DsBerfFxgPAJz17zz2joOFF3M=
 cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=
 cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=
 cloud.google.com/go/automl v1.5.0/go.mod h1:34EjfoFGMZ5sgJ9EoLsRtdPSNZLcfflJR39VbVNS2M0=
@@ -310,8 +310,8 @@ cloud.google.com/go/lifesciences v0.6.0/go.mod h1:ddj6tSX/7BOnhxCSd3ZcETvtNr8NZ6
 cloud.google.com/go/lifesciences v0.8.0/go.mod h1:lFxiEOMqII6XggGbOnKiyZ7IBwoIqA84ClvoezaA/bo=
 cloud.google.com/go/logging v1.6.1/go.mod h1:5ZO0mHHbvm8gEmeEUHrmDlTDSu5imF6MUP9OfilNXBw=
 cloud.google.com/go/logging v1.7.0/go.mod h1:3xjP2CjkM3ZkO73aj4ASA5wRPGGCRrPIAeNqVNkzY8M=
-cloud.google.com/go/logging v1.13.1 h1:O7LvmO0kGLaHY/gq8cV7T0dyp6zJhYAOtZPX4TF3QtY=
-cloud.google.com/go/logging v1.13.1/go.mod h1:XAQkfkMBxQRjQek96WLPNze7vsOmay9H5PqfsNYDqvw=
+cloud.google.com/go/logging v1.13.2 h1:qqlHCBvieJT9Cdq4QqYx1KPadCQ2noD4FK02eNqHAjA=
+cloud.google.com/go/logging v1.13.2/go.mod h1:zaybliM3yun1J8mU2dVQ1/qDzjbOqEijZCn6hSBtKak=
 cloud.google.com/go/longrunning v0.1.1/go.mod h1:UUFxuDWkv22EuY93jjmDMFT5GPQKeFVJBIF6QlTqdsE=
 cloud.google.com/go/longrunning v0.3.0/go.mod h1:qth9Y41RRSUE69rDcOn6DdK3HfQfsUI0YSmW3iIlLJc=
 cloud.google.com/go/longrunning v0.4.1/go.mod h1:4iWDqhBZ70CvZ6BfETbvam3T8FMvLK+eFj0E6AaRQTo=
@@ -716,12 +716,12 @@ github.com/aws/aws-sdk-go v1.55.8 h1:JRmEUbU52aJQZ2AjX4q4Wu7t4uZjOu71uyNmaWlUkJQ
 github.com/aws/aws-sdk-go v1.55.8/go.mod h1:ZkViS9AqA6otK+JBBNH2++sx1sgxrPKcSzPPvQkUtXk=
 github.com/aws/aws-sdk-go-v2 v1.41.5 h1:dj5kopbwUsVUVFgO4Fi5BIT3t4WyqIDjGKCangnV/yY=
 github.com/aws/aws-sdk-go-v2 v1.41.5/go.mod h1:mwsPRE8ceUUpiTgF7QmQIJ7lgsKUPQOUl3o72QBrE1o=
-github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 h1:489krEF9xIGkOaaX3CE/Be2uWjiXrkCH6gUX+bZA/BU=
-github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4/go.mod h1:IOAPF6oT9KCsceNTvvYMNHy0+kMF8akOjeDvPENWxp4=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 h1:eBMB84YGghSocM7PsjmmPffTa+1FBUeNvGvFou6V/4o=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8/go.mod h1:lyw7GFp3qENLh7kwzf7iMzAxDn+NzjXEAGjKS2UOKqI=
 github.com/aws/aws-sdk-go-v2/config v1.32.13 h1:5KgbxMaS2coSWRrx9TX/QtWbqzgQkOdEa3sZPhBhCSg=
 github.com/aws/aws-sdk-go-v2/config v1.32.13/go.mod h1:8zz7wedqtCbw5e9Mi2doEwDyEgHcEE9YOJp6a8jdSMY=
-github.com/aws/aws-sdk-go-v2/credentials v1.19.13 h1:mA59E3fokBvyEGHKFdnpNNrvaR351cqiHgRg+JzOSRI=
-github.com/aws/aws-sdk-go-v2/credentials v1.19.13/go.mod h1:yoTXOQKea18nrM69wGF9jBdG4WocSZA1h38A+t/MAsk=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.14 h1:n+UcGWAIZHkXzYt87uMFBv/l8THYELoX6gVcUvgl6fI=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.14/go.mod h1:cJKuyWB59Mqi0jM3nFYQRmnHVQIcgoxjEMAbLkpr62w=
 github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21 h1:NUS3K4BTDArQqNu2ih7yeDLaS3bmHD0YndtA6UP884g=
 github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21/go.mod h1:YWNWJQNjKigKY1RHVJCuupeWDrrHjRqHm0N9rdrWzYI=
 github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.20.12 h1:Zy6Tme1AA13kX8x3CnkHx5cqdGWGaj/anwOiWGnA0Xo=
@@ -732,28 +732,28 @@ github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 h1:PEgGVtPoB6NTpPrBgq
 github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21/go.mod h1:p+hz+PRAYlY3zcpJhPwXlLC4C+kqn70WIHwnzAfs6ps=
 github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 h1:qYQ4pzQ2Oz6WpQ8T3HvGHnZydA72MnLuFK9tJwmrbHw=
 github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6/go.mod h1:O3h0IK87yXci+kg6flUKzJnWeziQUKciKrLjcatSNcY=
-github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17 h1:JqcdRG//czea7Ppjb+g/n4o8i/R50aTBHkA7vu0lK+k=
-github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17/go.mod h1:CO+WeGmIdj/MlPel2KwID9Gt7CNq4M65HUfBW97liM0=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 h1:rWyie/PxDRIdhNf4DzRk0lvjVOqFJuNnO8WwaIRVxzQ=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22/go.mod h1:zd/JsJ4P7oGfUhXn1VyLqaRZwPmZwg44Jf2dS84Dm3Y=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 h1:5EniKhLZe4xzL7a+fU3C2tfUN4nWIqlLesfrjkuPFTY=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7/go.mod h1:x0nZssQ3qZSnIcePWLvcoFisRXJzcTVvYpAAdYX8+GI=
-github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8 h1:Z5EiPIzXKewUQK0QTMkutjiaPVeVYXX7KIqhXu/0fXs=
-github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8/go.mod h1:FsTpJtvC4U1fyDXk7c71XoDv3HlRm8V3NiYLeYLh5YE=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 h1:JRaIgADQS/U6uXDqlPiefP32yXTda7Kqfx+LgspooZM=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13/go.mod h1:CEuVn5WqOMilYl+tbccq8+N2ieCy0gVn3OtRb0vBNNM=
 github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 h1:c31//R3xgIJMSC8S6hEVq+38DcvUlgFY0FM6mSI5oto=
 github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21/go.mod h1:r6+pf23ouCB718FUxaqzZdbpYFyDtehyZcmP5KL9FkA=
-github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17 h1:bGeHBsGZx0Dvu/eJC0Lh9adJa3M1xREcndxLNZlve2U=
-github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17/go.mod h1:dcW24lbU0CzHusTE8LLHhRLI42ejmINN8Lcr22bwh/g=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0 h1:oeu8VPlOre74lBA/PMhxa5vewaMIMmILM+RraSyB8KA=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0/go.mod h1:5jggDlZ2CLQhwJBiZJb4vfk4f0GxWdEDruWKEJ1xOdo=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 h1:ZlvrNcHSFFWURB8avufQq9gFsheUgjVD9536obIknfM=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21/go.mod h1:cv3TNhVrssKR0O/xxLJVRfd2oazSnZnkUeTf6ctUwfQ=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0 h1:foqo/ocQ7WqKwy3FojGtZQJo0FR4vto9qnz9VaumbCo=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0/go.mod h1:uoA43SdFwacedBfSgfFSjjCvYe8aYBS7EnU5GZ/YKMM=
 github.com/aws/aws-sdk-go-v2/service/signin v1.0.9 h1:QKZH0S178gCmFEgst8hN0mCX1KxLgHBKKY/CLqwP8lg=
 github.com/aws/aws-sdk-go-v2/service/signin v1.0.9/go.mod h1:7yuQJoT+OoH8aqIxw9vwF+8KpvLZ8AWmvmUWHsGQZvI=
 github.com/aws/aws-sdk-go-v2/service/sns v1.39.7 h1:fovS7qGMT+BBSuifkySdVaMWxXTyaYT6qaBx/1y6Ij4=
 github.com/aws/aws-sdk-go-v2/service/sns v1.39.7/go.mod h1:gFahrattA8ulEtiS4XL/fQiQ77l+Urc52Y96/r1e6ks=
 github.com/aws/aws-sdk-go-v2/service/sqs v1.42.17 h1:ZNMxVFPayuHe14u/vn+BwLi3wxQvxcNTw8WdPv2gqBc=
 github.com/aws/aws-sdk-go-v2/service/sqs v1.42.17/go.mod h1:ZxqweFQ2w6NNznWMUvWV9AvkAfM6J8F/MC250Mb4n1I=
-github.com/aws/aws-sdk-go-v2/service/sso v1.30.14 h1:GcLE9ba5ehAQma6wlopUesYg/hbcOhFNWTjELkiWkh4=
-github.com/aws/aws-sdk-go-v2/service/sso v1.30.14/go.mod h1:WSvS1NLr7JaPunCXqpJnWk1Bjo7IxzZXrZi1QQCkuqM=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.18 h1:mP49nTpfKtpXLt5SLn8Uv8z6W+03jYVoOSAl/c02nog=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.18/go.mod h1:YO8TrYtFdl5w/4vmjL8zaBSsiNp3w0L1FfKVKenZT7w=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.15 h1:lFd1+ZSEYJZYvv9d6kXzhkZu07si3f+GQ1AaYwa2LUM=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.15/go.mod h1:WSvS1NLr7JaPunCXqpJnWk1Bjo7IxzZXrZi1QQCkuqM=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19 h1:dzztQ1YmfPrxdrOiuZRMF6fuOwWlWpD2StNLTceKpys=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19/go.mod h1:YO8TrYtFdl5w/4vmjL8zaBSsiNp3w0L1FfKVKenZT7w=
 github.com/aws/aws-sdk-go-v2/service/sts v1.41.10 h1:p8ogvvLugcR/zLBXTXrTkj0RYBUdErbMnAFFp12Lm/U=
 github.com/aws/aws-sdk-go-v2/service/sts v1.41.10/go.mod h1:60dv0eZJfeVXfbT1tFJinbHrDfSJ2GZl4Q//OSSNAVw=
 github.com/aws/smithy-go v1.24.2 h1:FzA3bu/nt/vDvmnkg+R8Xl46gmzEDam6mZ1hzmwXFng=
@@ -1076,8 +1076,8 @@ github.com/go-git/go-billy/v5 v5.6.2/go.mod h1:rcFC2rAsp/erv7CMz9GczHcuD0D32fWzH
 github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
-github.com/go-jose/go-jose/v4 v4.1.3 h1:CVLmWDhDVRa6Mi/IgCgaopNosCaHz7zrMeF9MlZRkrs=
-github.com/go-jose/go-jose/v4 v4.1.3/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
+github.com/go-jose/go-jose/v4 v4.1.4 h1:moDMcTHmvE6Groj34emNPLs/qtYXRVcd6S7NHbHz3kA=
+github.com/go-jose/go-jose/v4 v4.1.4/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
 github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
 github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
 github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
@@ -1284,8 +1284,8 @@ github.com/googleapis/enterprise-certificate-proxy v0.1.0/go.mod h1:17drOmN3MwGY
 github.com/googleapis/enterprise-certificate-proxy v0.2.0/go.mod h1:8C0jb7/mgJe/9KK8Lm7X9ctZC2t60YyIpYEI16jx0Qg=
 github.com/googleapis/enterprise-certificate-proxy v0.2.1/go.mod h1:AwSRAtLfXpU5Nm3pW+v7rGDHp09LsPtGY9MduiEsR9k=
 github.com/googleapis/enterprise-certificate-proxy v0.2.3/go.mod h1:AwSRAtLfXpU5Nm3pW+v7rGDHp09LsPtGY9MduiEsR9k=
-github.com/googleapis/enterprise-certificate-proxy v0.3.11 h1:vAe81Msw+8tKUxi2Dqh/NZMz7475yUvmRIkXr4oN2ao=
-github.com/googleapis/enterprise-certificate-proxy v0.3.11/go.mod h1:RFV7MUdlb7AgEq2v7FmMCfeSMCllAzWxFgRdusoGks8=
+github.com/googleapis/enterprise-certificate-proxy v0.3.14 h1:yh8ncqsbUY4shRD5dA6RlzjJaT4hi3kII+zYw8wmLb8=
+github.com/googleapis/enterprise-certificate-proxy v0.3.14/go.mod h1:vqVt9yG9480NtzREnTlmGSBmFrA+bzb0yl0TxoBQXOg=
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
 github.com/googleapis/gax-go/v2 v2.1.0/go.mod h1:Q3nei7sK6ybPYH7twZdmQpAd1MKb7pfu6SK+H1/DsU0=
@@ -1296,8 +1296,8 @@ github.com/googleapis/gax-go/v2 v2.4.0/go.mod h1:XOTVJ59hdnfJLIP/dh8n5CGryZR2LxK
 github.com/googleapis/gax-go/v2 v2.5.1/go.mod h1:h6B0KMMFNtI2ddbGJn3T3ZbwkeT6yqEF02fYlzkUCyo=
 github.com/googleapis/gax-go/v2 v2.6.0/go.mod h1:1mjbznJAPHFpesgE5ucqfYEscaz5kMdcIDwU/6+DDoY=
 github.com/googleapis/gax-go/v2 v2.7.0/go.mod h1:TEop28CZZQ2y+c0VxMUmu1lV+fQx57QpBWsYpwqHJx8=
-github.com/googleapis/gax-go/v2 v2.17.0 h1:RksgfBpxqff0EZkDWYuz9q/uWsTVz+kf43LsZ1J6SMc=
-github.com/googleapis/gax-go/v2 v2.17.0/go.mod h1:mzaqghpQp4JDh3HvADwrat+6M3MOIDp5YKHhb9PAgDY=
+github.com/googleapis/gax-go/v2 v2.19.0 h1:fYQaUOiGwll0cGj7jmHT/0nPlcrZDFPrZRhTsoCr8hE=
+github.com/googleapis/gax-go/v2 v2.19.0/go.mod h1:w2ROXVdfGEVFXzmlciUU4EdjHgWvB5h2n6x/8XSTTJA=
 github.com/googleapis/go-type-adapters v1.0.0/go.mod h1:zHW75FOG2aur7gAO2B+MLby+cLsWGBF62rFAi7WjWO4=
 github.com/googleapis/google-cloud-go-testing v0.0.0-20200911160855-bcd43fbb19e8/go.mod h1:dvDLG8qkwmyD9a/MJJN3XJcT3xFxOKAvTZGvuZmac9g=
 github.com/gookit/color v1.4.2/go.mod h1:fqRyamkC1W8uxl+lxCQxOT09l/vYfZ+QeiX3rKQHCoQ=
@@ -1383,8 +1383,8 @@ github.com/hashicorp/raft-boltdb v0.0.0-20230125174641-2a8082862702 h1:RLKEcCuKc
 github.com/hashicorp/raft-boltdb v0.0.0-20230125174641-2a8082862702/go.mod h1:nTakvJ4XYq45UXtn0DbwR4aU9ZdjlnIenpbs6Cd+FM0=
 github.com/hashicorp/raft-boltdb/v2 v2.3.1 h1:ackhdCNPKblmOhjEU9+4lHSJYFkJd6Jqyvj6eW9pwkc=
 github.com/hashicorp/raft-boltdb/v2 v2.3.1/go.mod h1:n4S+g43dXF1tqDT+yzcXHhXM6y7MrlUd3TTwGRcUvQE=
-github.com/hashicorp/vault/api v1.22.0 h1:+HYFquE35/B74fHoIeXlZIP2YADVboaPjaSicHEZiH0=
-github.com/hashicorp/vault/api v1.22.0/go.mod h1:IUZA2cDvr4Ok3+NtK2Oq/r+lJeXkeCrHRmqdyWfpmGM=
+github.com/hashicorp/vault/api v1.23.0 h1:gXgluBsSECfRWTSW9niY2jwg2e9mMJc4WoHNv4g3h6A=
+github.com/hashicorp/vault/api v1.23.0/go.mod h1:zransKiB9ftp+kgY8ydjnvCU7Wk8i9L0DYWpXeMj9ko=
 github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
 github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
 github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU=
@@ -2101,12 +2101,12 @@ go.einride.tech/aip v0.73.0 h1:bPo4oqBo2ZQeBKo4ZzLb1kxYXTY1ysJhpvQyfuGzvps=
 go.einride.tech/aip v0.73.0/go.mod h1:Mj7rFbmXEgw0dq1dqJ7JGMvYCZZVxmGOR3S4ZcV5LvQ=
 go.etcd.io/bbolt v1.4.3 h1:dEadXpI6G79deX5prL3QRNP6JB8UxVkqo4UPnHaNXJo=
 go.etcd.io/bbolt v1.4.3/go.mod h1:tKQlpPaYCVFctUIgFKFnAlvbmB3tpy1vkTnDWohtc0E=
-go.etcd.io/etcd/api/v3 v3.6.9 h1:UA7iKfEW1AzgihcBSGXci2kDGQiokSq41F9HMCI/RTI=
-go.etcd.io/etcd/api/v3 v3.6.9/go.mod h1:csEk/qTfxKL36NqJdU15Tgtl65A8dyEY2BYo7PRsIwk=
-go.etcd.io/etcd/client/pkg/v3 v3.6.9 h1:T8nuk8Lz64C+Hzb0coBFLMSlVSQZBpAtFk46swdM1DA=
-go.etcd.io/etcd/client/pkg/v3 v3.6.9/go.mod h1:WEy3PpwbbEBVRdh1NVJYsuUe/8eyI21PNJRazeD8z/Y=
-go.etcd.io/etcd/client/v3 v3.6.9 h1:3X555hQXmhRr27O37wls53g68CpUiPOiHXrZfz2Al+o=
-go.etcd.io/etcd/client/v3 v3.6.9/go.mod h1:KO7H1HLYh1qaljuVZJQwBFk1lRce6pJzt+C81GEnrlM=
+go.etcd.io/etcd/api/v3 v3.6.10 h1:jlwjtELjA8yi2VWpOFH+0w0lGr3K6mVDyn0RDB9aaAY=
+go.etcd.io/etcd/api/v3 v3.6.10/go.mod h1:pdV4VeFmvhdNjB4LWRkC8ReLyRBAxUOze3GarMhE2sk=
+go.etcd.io/etcd/client/pkg/v3 v3.6.10 h1:tBT7podcPhuVbCVkAEzx8bC5I+aqxfLwBN8/As1arrA=
+go.etcd.io/etcd/client/pkg/v3 v3.6.10/go.mod h1:WEy3PpwbbEBVRdh1NVJYsuUe/8eyI21PNJRazeD8z/Y=
+go.etcd.io/etcd/client/v3 v3.6.10 h1:J598zJ+C/ZPvImypmq5waj84+bovePrlZERHklf34y0=
+go.etcd.io/etcd/client/v3 v3.6.10/go.mod h1:iHhUDUcEwaKs1YFq3MgmI9U4zhTVasp/vgdVbFf1RS8=
 go.mongodb.org/mongo-driver v1.17.9 h1:IexDdCuuNJ3BHrELgBlyaH9p60JXAvdzWR128q+U5tU=
 go.mongodb.org/mongo-driver v1.17.9/go.mod h1:LlOhpH5NUEfhxcAwG0UEkMqwYcc4JU18gtCdGudk/tQ=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
@@ -2128,8 +2128,8 @@ go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace v0.
 go.opentelemetry.io/contrib/instrumentation/net/http/httptrace/otelhttptrace v0.60.0/go.mod h1:CosX/aS4eHnG9D7nESYpV753l4j9q5j3SL/PUYd2lR8=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0 h1:RbKq8BG0FI8OiXhBfcRtqqHcZcka+gU3cskNuf05R18=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0/go.mod h1:h06DGIukJOevXaj/xrNjhi/2098RZzcLTbc0jDAUbsg=
-go.opentelemetry.io/otel v1.40.0 h1:oA5YeOcpRTXq6NN7frwmwFR0Cn3RhTVZvXsP4duvCms=
-go.opentelemetry.io/otel v1.40.0/go.mod h1:IMb+uXZUKkMXdPddhwAHm6UfOwJyh4ct1ybIlV14J0g=
+go.opentelemetry.io/otel v1.43.0 h1:mYIM03dnh5zfN7HautFE4ieIig9amkNANT+xcVxAj9I=
+go.opentelemetry.io/otel v1.43.0/go.mod h1:JuG+u74mvjvcm8vj8pI5XiHy1zDeoCS2LB1spIq7Ay0=
 go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.38.0 h1:vl9obrcoWVKp/lwl8tRE33853I8Xru9HFbw/skNeLs8=
 go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.38.0/go.mod h1:GAXRxmLJcVM3u22IjTg74zWBrRCKq8BnOqUVLodpcpw=
 go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp v1.35.0 h1:0NIXxOCFx+SKbhCVxwl3ETG8ClLPAa0KuKV6p3yhxP8=
@@ -2144,14 +2144,14 @@ go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.39.0 h1:5gn2urDL/FBnK8
 go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.39.0/go.mod h1:0fBG6ZJxhqByfFZDwSwpZGzJU671HkwpWaNe2t4VUPI=
 go.opentelemetry.io/otel/exporters/zipkin v1.36.0 h1:s0n95ya5tOG03exJ5JySOdJFtwGo4ZQ+KeY7Zro4CLI=
 go.opentelemetry.io/otel/exporters/zipkin v1.36.0/go.mod h1:m9wRxtKA2MZ1HcnNC4BKI+9aYe434qRZTCvI7QGUN7Y=
-go.opentelemetry.io/otel/metric v1.40.0 h1:rcZe317KPftE2rstWIBitCdVp89A2HqjkxR3c11+p9g=
-go.opentelemetry.io/otel/metric v1.40.0/go.mod h1:ib/crwQH7N3r5kfiBZQbwrTge743UDc7DTFVZrrXnqc=
-go.opentelemetry.io/otel/sdk v1.40.0 h1:KHW/jUzgo6wsPh9At46+h4upjtccTmuZCFAc9OJ71f8=
-go.opentelemetry.io/otel/sdk v1.40.0/go.mod h1:Ph7EFdYvxq72Y8Li9q8KebuYUr2KoeyHx0DRMKrYBUE=
-go.opentelemetry.io/otel/sdk/metric v1.40.0 h1:mtmdVqgQkeRxHgRv4qhyJduP3fYJRMX4AtAlbuWdCYw=
-go.opentelemetry.io/otel/sdk/metric v1.40.0/go.mod h1:4Z2bGMf0KSK3uRjlczMOeMhKU2rhUqdWNoKcYrtcBPg=
-go.opentelemetry.io/otel/trace v1.40.0 h1:WA4etStDttCSYuhwvEa8OP8I5EWu24lkOzp+ZYblVjw=
-go.opentelemetry.io/otel/trace v1.40.0/go.mod h1:zeAhriXecNGP/s2SEG3+Y8X9ujcJOTqQ5RgdEJcawiA=
+go.opentelemetry.io/otel/metric v1.43.0 h1:d7638QeInOnuwOONPp4JAOGfbCEpYb+K6DVWvdxGzgM=
+go.opentelemetry.io/otel/metric v1.43.0/go.mod h1:RDnPtIxvqlgO8GRW18W6Z/4P462ldprJtfxHxyKd2PY=
+go.opentelemetry.io/otel/sdk v1.43.0 h1:pi5mE86i5rTeLXqoF/hhiBtUNcrAGHLKQdhg4h4V9Dg=
+go.opentelemetry.io/otel/sdk v1.43.0/go.mod h1:P+IkVU3iWukmiit/Yf9AWvpyRDlUeBaRg6Y+C58QHzg=
+go.opentelemetry.io/otel/sdk/metric v1.43.0 h1:S88dyqXjJkuBNLeMcVPRFXpRw2fuwdvfCGLEo89fDkw=
+go.opentelemetry.io/otel/sdk/metric v1.43.0/go.mod h1:C/RJtwSEJ5hzTiUz5pXF1kILHStzb9zFlIEe85bhj6A=
+go.opentelemetry.io/otel/trace v1.43.0 h1:BkNrHpup+4k4w+ZZ86CZoHHEkohws8AY+WTX09nk+3A=
+go.opentelemetry.io/otel/trace v1.43.0/go.mod h1:/QJhyVBUUswCphDVxq+8mld+AvhXZLhe+8WVFxiFff0=
 go.opentelemetry.io/proto/otlp v0.7.0/go.mod h1:PqfVotwruBrMGOCsRd/89rSnXhoiJIqeYNgFYFoEGnI=
 go.opentelemetry.io/proto/otlp v0.15.0/go.mod h1:H7XAot3MsfNsj7EXtrA2q5xSNQ10UqI405h3+duxN4U=
 go.opentelemetry.io/proto/otlp v0.19.0/go.mod h1:H7XAot3MsfNsj7EXtrA2q5xSNQ10UqI405h3+duxN4U=
@@ -2344,8 +2344,8 @@ golang.org/x/net v0.16.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
 golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
 golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
 golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
-golang.org/x/net v0.51.0 h1:94R/GTO7mt3/4wIKpcR5gkGmRLOuE/2hNGeWq/GBIFo=
-golang.org/x/net v0.51.0/go.mod h1:aamm+2QF5ogm02fjy5Bb7CQ0WMt1/WVM7FtyaTLlA9Y=
+golang.org/x/net v0.52.0 h1:He/TN1l0e4mmR3QqHMT2Xab3Aj3L9qjbhRm78/6jrW0=
+golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -2552,8 +2552,8 @@ golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxb
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20220922220347-f3bd1da661af/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.1.0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
-golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
+golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
+golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
 golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -2703,8 +2703,8 @@ google.golang.org/api v0.106.0/go.mod h1:2Ts0XTHNVWxypznxWOYUeI4g3WdP9Pk2Qk58+a/
 google.golang.org/api v0.107.0/go.mod h1:2Ts0XTHNVWxypznxWOYUeI4g3WdP9Pk2Qk58+a/O9MY=
 google.golang.org/api v0.108.0/go.mod h1:2Ts0XTHNVWxypznxWOYUeI4g3WdP9Pk2Qk58+a/O9MY=
 google.golang.org/api v0.110.0/go.mod h1:7FC4Vvx1Mooxh8C5HWjzZHcavuS2f6pmJpZx60ca7iI=
-google.golang.org/api v0.267.0 h1:w+vfWPMPYeRs8qH1aYYsFX68jMls5acWl/jocfLomwE=
-google.golang.org/api v0.267.0/go.mod h1:Jzc0+ZfLnyvXma3UtaTl023TdhZu6OMBP9tJ+0EmFD0=
+google.golang.org/api v0.274.0 h1:aYhycS5QQCwxHLwfEHRRLf9yNsfvp1JadKKWBE54RFA=
+google.golang.org/api v0.274.0/go.mod h1:JbAt7mF+XVmWu6xNP8/+CTiGH30ofmCmk9nM8d8fHew=
 google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
 google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
 google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
@@ -2838,12 +2838,12 @@ google.golang.org/genproto v0.0.0-20230209215440-0dfe4f8abfcc/go.mod h1:RGgjbofJ
 google.golang.org/genproto v0.0.0-20230216225411-c8e22ba71e44/go.mod h1:8B0gmkoRebU8ukX6HP+4wrVQUY1+6PkQ44BSyIlflHA=
 google.golang.org/genproto v0.0.0-20230222225845-10f96fb3dbec/go.mod h1:3Dl5ZL0q0isWJt+FVcfpQyirqemEuLAK/iFvg1UP1Hw=
 google.golang.org/genproto v0.0.0-20230306155012-7f2fa6fef1f4/go.mod h1:NWraEVixdDnqcqQ30jipen1STv2r/n24Wb7twVTGR4s=
-google.golang.org/genproto v0.0.0-20260128011058-8636f8732409 h1:VQZ/yAbAtjkHgH80teYd2em3xtIkkHd7ZhqfH2N9CsM=
-google.golang.org/genproto v0.0.0-20260128011058-8636f8732409/go.mod h1:rxKD3IEILWEu3P44seeNOAwZN4SaoKaQ/2eTg4mM6EM=
-google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20 h1:7ei4lp52gK1uSejlA8AZl5AJjeLUOHBQscRQZUgAcu0=
-google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20/go.mod h1:ZdbssH/1SOVnjnDlXzxDHK2MCidiqXtbYccJNzNYPEE=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 h1:Jr5R2J6F6qWyzINc+4AM8t5pfUz6beZpHp678GNrMbE=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20/go.mod h1:j9x/tPzZkyxcgEFkiKEEGxfvyumM01BEtsW8xzOahRQ=
+google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 h1:JNfk58HZ8lfmXbYK2vx/UvsqIL59TzByCxPIX4TDmsE=
+google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:x5julN69+ED4PcFk/XWayw35O0lf/nGa4aNgODCmNmw=
+google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5 h1:CogIeEXn4qWYzzQU0QqvYBM8yDF9cFYzDq9ojSpv0Js=
+google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:EIQZ5bFCfRQDV4MhRle7+OgjNtZ6P1PiZBgAKuxXu/Y=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 h1:ndE4FoJqsIceKP2oYSnUZqhTdYufCYYkqwtFzfrhI7w=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.20.1/go.mod h1:10oTOabMzJvdu6/UiuZezV6QK5dSlG84ov/aaiqXj38=
 google.golang.org/grpc v1.21.1/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=

k8s/charts/seaweedfs/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v1
 description: SeaweedFS
 name: seaweedfs
-appVersion: "4.18"
+appVersion: "4.19"
 # Dev note: Trigger a helm chart release by `git tag -a helm-<version>`
-version: 4.18.0
+version: 4.19.0

k8s/charts/seaweedfs/values.yaml

@@ -1339,9 +1339,14 @@ worker:
   # Admin server to connect to
   adminServer: ""
 
-  # Worker job types - comma-separated list
-  # Available: vacuum, volume_balance, erasure_coding
-  jobType: "vacuum,volume_balance,erasure_coding"
+  # Worker job types - categories or comma-separated list of names/aliases
+  # Categories: all, default, heavy
+  #   default: vacuum, volume_balance, ec_balance, admin_script
+  #   heavy: erasure_coding, iceberg_maintenance
+  #   all: every registered job type
+  # Examples: "all", "default", "heavy", "default,iceberg" (default+iceberg), "vacuum,volume_balance"
+  # Refer: https://github.com/seaweedfs/seaweedfs/wiki/Worker
+  jobType: "all"
 
   # Maximum number of concurrent detection requests
   maxDetect: 1

seaweed-volume/Cargo.toml

@@ -20,7 +20,7 @@ default = ["5bytes"]
 [dependencies]
 # Async runtime
 tokio = { version = "1", features = ["full"] }
-tokio-stream = "0.1"
+tokio-stream = { version = "0.1", features = ["net"] }
 tokio-io-timeout = "1"
 
 # gRPC + protobuf
@@ -82,7 +82,7 @@ memmap2 = "0.9"
 uuid = { version = "1", features = ["v4"] }
 
 # HTTP client (for proxying, remote fetch)
-reqwest = { version = "0.12", features = ["rustls-tls", "stream", "multipart", "json"] }
+reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "stream", "multipart", "json"] }
 
 # Content hashing
 md-5 = "0.10"

seaweed-volume/src/main.rs

@@ -600,31 +600,35 @@ async fn run(
         })
     };
 
+    // Bind the gRPC listener before spawning to propagate bind errors at startup.
+    let grpc_listener = tokio::net::TcpListener::bind(&grpc_addr)
+        .await
+        .unwrap_or_else(|e| panic!("Failed to bind gRPC to {}: {}", grpc_addr, e));
+    let grpc_local_addr = grpc_listener
+        .local_addr()
+        .unwrap_or_else(|e| panic!("Failed to get gRPC local addr: {}", e));
+
     let grpc_handle = {
         let grpc_state = state.clone();
-        let grpc_addr = grpc_addr.clone();
         let grpc_tls_acceptor = grpc_tls_acceptor.clone();
         let mut shutdown_rx = shutdown_tx.subscribe();
+        let shutdown_tx_grpc = shutdown_tx.clone();
         tokio::spawn(async move {
-            let addr = grpc_addr.parse().expect("Invalid gRPC address");
             let grpc_service = VolumeGrpcService {
                 state: grpc_state.clone(),
             };
-            if let Some(tls_acceptor) = grpc_tls_acceptor {
-                let listener = tokio::net::TcpListener::bind(&grpc_addr)
-                    .await
-                    .unwrap_or_else(|e| panic!("Failed to bind gRPC to {}: {}", grpc_addr, e));
-                let incoming = grpc_tls_incoming(listener, tls_acceptor);
-                let reflection_v1 = tonic_reflection::server::Builder::configure()
-                    .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
-                    .build_v1()
-                    .expect("Failed to build gRPC reflection v1 service");
-                let reflection_v1alpha = tonic_reflection::server::Builder::configure()
-                    .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
-                    .build_v1alpha()
-                    .expect("Failed to build gRPC reflection v1alpha service");
-                info!("gRPC server listening on {} (TLS enabled)", addr);
-                if let Err(e) = build_grpc_server_builder()
+            let reflection_v1 = tonic_reflection::server::Builder::configure()
+                .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
+                .build_v1()
+                .expect("Failed to build gRPC reflection v1 service");
+            let reflection_v1alpha = tonic_reflection::server::Builder::configure()
+                .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
+                .build_v1alpha()
+                .expect("Failed to build gRPC reflection v1alpha service");
+            let result = if let Some(tls_acceptor) = grpc_tls_acceptor {
+                let incoming = grpc_tls_incoming(grpc_listener, tls_acceptor);
+                info!("gRPC server listening on {} (TLS enabled)", grpc_local_addr);
+                build_grpc_server_builder()
                     .layer(GrpcRequestIdLayer)
                     .add_service(reflection_v1)
                     .add_service(reflection_v1alpha)
@@ -633,32 +637,25 @@ async fn run(
                         let _ = shutdown_rx.recv().await;
                     })
                     .await
-                {
-                    error!("gRPC server error: {}", e);
-                }
             } else {
-                let reflection_v1 = tonic_reflection::server::Builder::configure()
-                    .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
-                    .build_v1()
-                    .expect("Failed to build gRPC reflection v1 service");
-                let reflection_v1alpha = tonic_reflection::server::Builder::configure()
-                    .register_encoded_file_descriptor_set(seaweed_volume::pb::FILE_DESCRIPTOR_SET)
-                    .build_v1alpha()
-                    .expect("Failed to build gRPC reflection v1alpha service");
-                info!("gRPC server listening on {}", addr);
-                if let Err(e) = build_grpc_server_builder()
+                let incoming =
+                    tokio_stream::wrappers::TcpListenerStream::new(grpc_listener);
+                info!("gRPC server listening on {}", grpc_local_addr);
+                build_grpc_server_builder()
                     .layer(GrpcRequestIdLayer)
                     .add_service(reflection_v1)
                     .add_service(reflection_v1alpha)
                     .add_service(build_volume_grpc_service(grpc_service))
-                    .serve_with_shutdown(addr, async move {
+                    .serve_with_incoming_shutdown(incoming, async move {
                         let _ = shutdown_rx.recv().await;
                     })
                     .await
-                {
-                    error!("gRPC server error: {}", e);
-                }
+            };
+            if let Err(ref e) = result {
+                error!("gRPC server error: {}", e);
+                let _ = shutdown_tx_grpc.send(());
             }
+            result
         })
     };
 
@@ -767,9 +764,40 @@ async fn run(
         }))
     };
 
-    // Wait for all servers
+    // Wait for servers. Use select! with &mut so the losing handle is not
+    // dropped, then await it explicitly afterward.
+    let mut server_err: Option<String> = None;
+    let mut http_handle = http_handle;
+    let mut grpc_handle = grpc_handle;
+    let grpc_finished_first = tokio::select! {
+        _ = &mut http_handle => false,
+        _ = &mut grpc_handle => true,
+    };
+    // Inspect the gRPC result (already resolved if it finished first,
+    // otherwise await it now).
+    let grpc_result = if grpc_finished_first {
+        grpc_handle.await
+    } else {
+        // HTTP finished first; gRPC is still running. Await it.
+        grpc_handle.await
+    };
+    match grpc_result {
+        Ok(Ok(())) => {}
+        Ok(Err(e)) => {
+            let msg = format!("gRPC server exited with error: {}", e);
+            error!("{}", msg);
+            server_err = Some(msg);
+            // serve error already sent shutdown inside the task
+        }
+        Err(e) => {
+            let msg = format!("gRPC task panicked: {}", e);
+            error!("{}", msg);
+            server_err = Some(msg);
+            let _ = shutdown_tx.send(());
+        }
+    }
+    // Ensure the HTTP handle completes too.
     let _ = http_handle.await;
-    let _ = grpc_handle.await;
     if let Some(h) = public_handle {
         let _ = h.await;
     }
@@ -794,6 +822,10 @@ async fn run(
         cpu_profile.finish().map_err(std::io::Error::other)?;
     }
 
+    if let Some(err_msg) = server_err {
+        return Err(std::io::Error::other(err_msg).into());
+    }
+
     info!("Volume server stopped.");
     Ok(())
 }

seaweed-volume/src/remote_storage/s3_tier.rs

@@ -486,6 +486,11 @@ impl S3TierRegistry {
         self.backends.keys().cloned().collect()
     }
 
+    /// Remove a backend by name.
+    pub fn remove(&mut self, name: &str) {
+        self.backends.remove(name);
+    }
+
     pub fn clear(&mut self) {
         self.backends.clear();
     }

seaweed-volume/src/server/grpc_server.rs

@@ -1867,6 +1867,7 @@ impl VolumeServer for VolumeGrpcService {
         {
             let needle_header = resp.needle_header;
             let mut needle_body = resp.needle_body;
+            let resp_version = resp.version;
 
             if needle_header.is_empty() {
                 continue;
@@ -1891,8 +1892,36 @@ impl VolumeServer for VolumeGrpcService {
             // Parse needle from header + body
             let mut n = Needle::default();
             n.read_header(&needle_header);
-            n.read_body_v2(&needle_body)
-                .map_err(|e| Status::internal(format!("parse needle body: {}", e)))?;
+
+            if n.size.0 < 0 {
+                return Err(Status::invalid_argument(format!(
+                    "unexpected negative needle size {} for needle {}",
+                    n.size.0, n.id.0
+                )));
+            } else if n.size.0 > 0 {
+                // Normal needle: parse the body fields (DataSize, Data, flags, etc.)
+                n.read_body_v2(&needle_body)
+                    .map_err(|e| Status::internal(format!("parse needle body: {}", e)))?;
+            } else {
+                // Delete tombstone (size == 0): body is checksum + timestamp
+                // (V3) or checksum only (V2) + padding. Validate minimum
+                // footer length for the protocol version.
+                use crate::storage::types::{
+                    NEEDLE_CHECKSUM_SIZE, TIMESTAMP_SIZE, VERSION_3, Version,
+                };
+                let version = Version(resp_version as u8);
+                let min_footer = if version >= VERSION_3 {
+                    NEEDLE_CHECKSUM_SIZE + TIMESTAMP_SIZE
+                } else {
+                    NEEDLE_CHECKSUM_SIZE
+                };
+                if needle_body.len() < min_footer {
+                    return Err(Status::invalid_argument(format!(
+                        "tombstone needle {} body too short: got {} bytes, need >= {} for version {}",
+                        n.id.0, needle_body.len(), min_footer, resp_version
+                    )));
+                }
+            }
 
             // Write needle to local volume
             let mut store = state.store.write().unwrap();
@@ -4047,11 +4076,12 @@ fn find_last_append_at_ns(idx_path: &str, dat_path: &str, version: u32) -> Optio
     let mut header = [0u8; 16];
     dat_file.read_exact(&mut header).ok()?;
     let needle_size = i32::from_be_bytes([header[12], header[13], header[14], header[15]]);
-    if needle_size <= 0 {
+    if needle_size < 0 {
         return None;
     }
 
     // Seek to tail: offset + 16 (header) + size -> checksum (4) + timestamp (8)
+    // For delete needles (size == 0), the tail is right after the header.
     let tail_offset = actual_offset as u64 + 16 + needle_size as u64;
     dat_file.seek(SeekFrom::Start(tail_offset)).ok()?;
 
@@ -4162,6 +4192,7 @@ mod tests {
         let addr = listener.local_addr().unwrap();
         listener.set_nonblocking(true).unwrap();
         let (shutdown_tx, shutdown_rx) = tokio::sync::oneshot::channel::<()>();
+        let (ready_tx, ready_rx) = std::sync::mpsc::channel::<()>();
 
         std::thread::spawn(move || {
             let runtime = tokio::runtime::Builder::new_current_thread()
@@ -4223,6 +4254,7 @@ mod tests {
                 }));
 
                 let listener = tokio::net::TcpListener::from_std(listener).unwrap();
+                let _ = ready_tx.send(());
                 axum::serve(listener, app)
                     .with_graceful_shutdown(async move {
                         let _ = shutdown_rx.await;
@@ -4232,6 +4264,8 @@ mod tests {
             });
         });
 
+        // Wait for the server thread to be ready before returning.
+        ready_rx.recv().unwrap();
         (format!("http://{}", addr), shutdown_tx)
     }
 
@@ -4277,7 +4311,9 @@ mod tests {
         std::fs::remove_file(&dat_path).unwrap();
 
         let (endpoint, shutdown_tx) = spawn_fake_s3_server(dat_bytes.clone());
-        global_s3_tier_registry().write().unwrap().clear();
+        // Use a test-specific backend_id to avoid racing with other tests
+        // that share the global registry.  Never call clear() — only
+        // register/remove our own entries.
         let tier_config = S3TierConfig {
             access_key: "access".to_string(),
             secret_key: "secret".to_string(),
@@ -4289,14 +4325,16 @@ mod tests {
         };
         {
             let mut registry = global_s3_tier_registry().write().unwrap();
-            registry.register("s3.default".to_string(), S3TierBackend::new(&tier_config));
-            registry.register("s3".to_string(), S3TierBackend::new(&tier_config));
+            registry.register(
+                "s3.incr_copy_test".to_string(),
+                S3TierBackend::new(&tier_config),
+            );
         }
 
         let vif = crate::storage::volume::VifVolumeInfo {
             files: vec![crate::storage::volume::VifRemoteFile {
                 backend_type: "s3".to_string(),
-                backend_id: "default".to_string(),
+                backend_id: "incr_copy_test".to_string(),
                 key: "remote-key".to_string(),
                 offset: 0,
                 file_size: dat_bytes.len() as u64,
@@ -4505,7 +4543,10 @@ mod tests {
         assert_eq!(copied, dat_bytes[super_block_size as usize..]);
 
         let _ = shutdown_tx.send(());
-        global_s3_tier_registry().write().unwrap().clear();
+        global_s3_tier_registry()
+            .write()
+            .unwrap()
+            .remove("s3.incr_copy_test");
     }
 
     #[tokio::test]

seaweed-volume/src/server/heartbeat.rs

@@ -1408,10 +1408,8 @@ mod tests {
     #[test]
     fn test_apply_storage_backends_registers_s3_default_aliases() {
         let state = test_state_with_store(Store::new(NeedleMapKind::InMemory));
-        crate::remote_storage::s3_tier::global_s3_tier_registry()
-            .write()
-            .unwrap()
-            .clear();
+        // Do not call clear() on the global registry — other tests may be
+        // running concurrently.  Just register our entries and verify them.
 
         apply_storage_backends(
             &state,
@@ -1443,10 +1441,8 @@ mod tests {
     #[test]
     fn test_apply_storage_backends_ignores_unsupported_types() {
         let state = test_state_with_store(Store::new(NeedleMapKind::InMemory));
-        crate::remote_storage::s3_tier::global_s3_tier_registry()
-            .write()
-            .unwrap()
-            .clear();
+        // Do not call clear() on the global registry — other tests may be
+        // running concurrently.
 
         apply_storage_backends(
             &state,
@@ -1457,12 +1453,17 @@ mod tests {
             }],
         );
 
+        // The per-state registry is freshly created and should have no entries
+        // since "rclone" is unsupported.
         let registry = state.s3_tier_registry.read().unwrap();
         assert!(registry.names().is_empty());
+        // Only check that the unsupported type was not added to the global
+        // registry.  Other tests may have their own entries present.
         let global_registry = crate::remote_storage::s3_tier::global_s3_tier_registry()
             .read()
             .unwrap();
-        assert!(global_registry.names().is_empty());
+        assert!(global_registry.get("rclone.default").is_none());
+        assert!(global_registry.get("rclone").is_none());
     }
 
     #[test]

seaweed-volume/src/storage/store.rs

@@ -1158,7 +1158,13 @@ mod tests {
                 Vec::new(),
             )
             .unwrap();
-        store.volume_size_limit.store(1024, Ordering::Relaxed);
+        // Use a large volume_size_limit so the unused-space difference between
+        // preallocate=true (0) and preallocate=false (~2 × limit) is big enough
+        // that integer-division rounding and disk-free fluctuations between the
+        // two get_disk_stats calls cannot make the quotients equal.
+        store
+            .volume_size_limit
+            .store(100 * 1024 * 1024, Ordering::Relaxed);
         store
             .add_volume(
                 VolumeId(61),

seaweed-volume/src/storage/volume.rs

@@ -3225,6 +3225,7 @@ mod tests {
         let addr = listener.local_addr().unwrap();
         listener.set_nonblocking(true).unwrap();
         let (shutdown_tx, shutdown_rx) = tokio::sync::oneshot::channel::<()>();
+        let (ready_tx, ready_rx) = std::sync::mpsc::channel::<()>();
 
         std::thread::spawn(move || {
             let runtime = tokio::runtime::Builder::new_current_thread()
@@ -3279,6 +3280,7 @@ mod tests {
                 }));
 
                 let listener = tokio::net::TcpListener::from_std(listener).unwrap();
+                let _ = ready_tx.send(());
                 axum::serve(listener, app)
                     .with_graceful_shutdown(async move {
                         let _ = shutdown_rx.await;
@@ -3288,6 +3290,8 @@ mod tests {
             });
         });
 
+        // Wait for the server thread to be ready before returning.
+        ready_rx.recv().unwrap();
         (format!("http://{}", addr), shutdown_tx)
     }
 
@@ -3833,7 +3837,7 @@ mod tests {
             let vif = VifVolumeInfo {
                 files: vec![VifRemoteFile {
                     backend_type: "s3".to_string(),
-                    backend_id: "default".to_string(),
+                    backend_id: "vif_rw_test".to_string(),
                     key: "remote-key".to_string(),
                     offset: 0,
                     file_size: v.dat_file_size().unwrap(),
@@ -3849,6 +3853,27 @@ mod tests {
             )
             .unwrap();
 
+            // Register a dummy S3 backend so load_remote_dat_file can look it
+            // up.  This test never reads remote data, so a dead endpoint is fine.
+            // Use a test-specific backend_id to avoid racing with other tests
+            // that share the global registry.
+            let tier_config = crate::remote_storage::s3_tier::S3TierConfig {
+                access_key: "access".to_string(),
+                secret_key: "secret".to_string(),
+                region: "us-east-1".to_string(),
+                bucket: "bucket-a".to_string(),
+                endpoint: "http://127.0.0.1:1".to_string(),
+                storage_class: "STANDARD".to_string(),
+                force_path_style: true,
+            };
+            crate::remote_storage::s3_tier::global_s3_tier_registry()
+                .write()
+                .unwrap()
+                .register(
+                    "s3.vif_rw_test".to_string(),
+                    crate::remote_storage::s3_tier::S3TierBackend::new(&tier_config),
+                );
+
             v.dat_file_size().unwrap()
         };
 
@@ -3892,6 +3917,11 @@ mod tests {
             .unwrap();
         assert!(deleted_size.0 > 0);
         assert_eq!(v.dat_file_size().unwrap(), dat_size_before_reload);
+
+        crate::remote_storage::s3_tier::global_s3_tier_registry()
+            .write()
+            .unwrap()
+            .remove("s3.vif_rw_test");
     }
 
     #[test]
@@ -4054,10 +4084,9 @@ mod tests {
         std::fs::remove_file(&dat_path).unwrap();
 
         let (endpoint, shutdown_tx) = spawn_fake_s3_server(dat_bytes.clone());
-        crate::remote_storage::s3_tier::global_s3_tier_registry()
-            .write()
-            .unwrap()
-            .clear();
+        // Use a test-specific backend_id to avoid racing with other tests
+        // that share the global registry.  Never call clear() — only
+        // register/remove our own entries.
         let tier_config = crate::remote_storage::s3_tier::S3TierConfig {
             access_key: "access".to_string(),
             secret_key: "secret".to_string(),
@@ -4072,11 +4101,7 @@ mod tests {
                 .write()
                 .unwrap();
             registry.register(
-                "s3.default".to_string(),
-                crate::remote_storage::s3_tier::S3TierBackend::new(&tier_config),
-            );
-            registry.register(
-                "s3".to_string(),
+                "s3.remote_only_rw".to_string(),
                 crate::remote_storage::s3_tier::S3TierBackend::new(&tier_config),
             );
         }
@@ -4084,7 +4109,7 @@ mod tests {
         let vif = VifVolumeInfo {
             files: vec![VifRemoteFile {
                 backend_type: "s3".to_string(),
-                backend_id: "default".to_string(),
+                backend_id: "remote_only_rw".to_string(),
                 key: "remote-key".to_string(),
                 offset: 0,
                 file_size: dat_bytes.len() as u64,
@@ -4141,6 +4166,10 @@ mod tests {
         assert_eq!(meta.data_size, 11);
 
         let _ = shutdown_tx.send(());
+        crate::remote_storage::s3_tier::global_s3_tier_registry()
+            .write()
+            .unwrap()
+            .remove("s3.remote_only_rw");
     }
 
     /// Volume destroy removes .vif alongside the primary data files.

seaweedfs-rdma-sidecar/go.mod

@@ -33,11 +33,11 @@ require (
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
-	golang.org/x/image v0.36.0 // indirect
-	golang.org/x/net v0.50.0 // indirect
+	golang.org/x/image v0.38.0 // indirect
+	golang.org/x/net v0.52.0 // indirect
 	golang.org/x/sys v0.42.0 // indirect
-	golang.org/x/text v0.34.0 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 // indirect
+	golang.org/x/text v0.35.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 // indirect
 	google.golang.org/grpc v1.79.3 // indirect
 	google.golang.org/protobuf v1.36.11 // indirect
 )

seaweedfs-rdma-sidecar/go.sum

@@ -27,8 +27,8 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
-github.com/klauspost/compress v1.18.4 h1:RPhnKRAQ4Fh8zU2FY/6ZFDwTVTxgJ/EMydqSTzE9a2c=
-github.com/klauspost/compress v1.18.4/go.mod h1:R0h/fSBs8DE4ENlcrlib3PsXS61voFxhIs2DeRhCvJ4=
+github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE=
+github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
@@ -84,35 +84,35 @@ github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAh
 github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
 go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=
 go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
-go.opentelemetry.io/otel v1.40.0 h1:oA5YeOcpRTXq6NN7frwmwFR0Cn3RhTVZvXsP4duvCms=
-go.opentelemetry.io/otel v1.40.0/go.mod h1:IMb+uXZUKkMXdPddhwAHm6UfOwJyh4ct1ybIlV14J0g=
-go.opentelemetry.io/otel/metric v1.40.0 h1:rcZe317KPftE2rstWIBitCdVp89A2HqjkxR3c11+p9g=
-go.opentelemetry.io/otel/metric v1.40.0/go.mod h1:ib/crwQH7N3r5kfiBZQbwrTge743UDc7DTFVZrrXnqc=
-go.opentelemetry.io/otel/sdk v1.40.0 h1:KHW/jUzgo6wsPh9At46+h4upjtccTmuZCFAc9OJ71f8=
-go.opentelemetry.io/otel/sdk v1.40.0/go.mod h1:Ph7EFdYvxq72Y8Li9q8KebuYUr2KoeyHx0DRMKrYBUE=
-go.opentelemetry.io/otel/sdk/metric v1.40.0 h1:mtmdVqgQkeRxHgRv4qhyJduP3fYJRMX4AtAlbuWdCYw=
-go.opentelemetry.io/otel/sdk/metric v1.40.0/go.mod h1:4Z2bGMf0KSK3uRjlczMOeMhKU2rhUqdWNoKcYrtcBPg=
-go.opentelemetry.io/otel/trace v1.40.0 h1:WA4etStDttCSYuhwvEa8OP8I5EWu24lkOzp+ZYblVjw=
-go.opentelemetry.io/otel/trace v1.40.0/go.mod h1:zeAhriXecNGP/s2SEG3+Y8X9ujcJOTqQ5RgdEJcawiA=
+go.opentelemetry.io/otel v1.42.0 h1:lSQGzTgVR3+sgJDAU/7/ZMjN9Z+vUip7leaqBKy4sho=
+go.opentelemetry.io/otel v1.42.0/go.mod h1:lJNsdRMxCUIWuMlVJWzecSMuNjE7dOYyWlqOXWkdqCc=
+go.opentelemetry.io/otel/metric v1.42.0 h1:2jXG+3oZLNXEPfNmnpxKDeZsFI5o4J+nz6xUlaFdF/4=
+go.opentelemetry.io/otel/metric v1.42.0/go.mod h1:RlUN/7vTU7Ao/diDkEpQpnz3/92J9ko05BIwxYa2SSI=
+go.opentelemetry.io/otel/sdk v1.42.0 h1:LyC8+jqk6UJwdrI/8VydAq/hvkFKNHZVIWuslJXYsDo=
+go.opentelemetry.io/otel/sdk v1.42.0/go.mod h1:rGHCAxd9DAph0joO4W6OPwxjNTYWghRWmkHuGbayMts=
+go.opentelemetry.io/otel/sdk/metric v1.42.0 h1:D/1QR46Clz6ajyZ3G8SgNlTJKBdGp84q9RKCAZ3YGuA=
+go.opentelemetry.io/otel/sdk/metric v1.42.0/go.mod h1:Ua6AAlDKdZ7tdvaQKfSmnFTdHx37+J4ba8MwVCYM5hc=
+go.opentelemetry.io/otel/trace v1.42.0 h1:OUCgIPt+mzOnaUTpOQcBiM/PLQ/Op7oq6g4LenLmOYY=
+go.opentelemetry.io/otel/trace v1.42.0/go.mod h1:f3K9S+IFqnumBkKhRJMeaZeNk9epyhnCmQh/EysQCdc=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0=
 go.yaml.in/yaml/v2 v2.4.3/go.mod h1:zSxWcmIDjOzPXpjlTTbAsKokqkDNAVtZO0WOMiT90s8=
 go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
 go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
-golang.org/x/image v0.36.0 h1:Iknbfm1afbgtwPTmHnS2gTM/6PPZfH+z2EFuOkSbqwc=
-golang.org/x/image v0.36.0/go.mod h1:YsWD2TyyGKiIX1kZlu9QfKIsQ4nAAK9bdgdrIsE7xy4=
-golang.org/x/net v0.50.0 h1:ucWh9eiCGyDR3vtzso0WMQinm2Dnt8cFMuQa9K33J60=
-golang.org/x/net v0.50.0/go.mod h1:UgoSli3F/pBgdJBHCTc+tp3gmrU4XswgGRgtnwWTfyM=
+golang.org/x/image v0.38.0 h1:5l+q+Y9JDC7mBOMjo4/aPhMDcxEptsX+Tt3GgRQRPuE=
+golang.org/x/image v0.38.0/go.mod h1:/3f6vaXC+6CEanU4KJxbcUZyEePbyKbaLoDOe4ehFYY=
+golang.org/x/net v0.52.0 h1:He/TN1l0e4mmR3QqHMT2Xab3Aj3L9qjbhRm78/6jrW0=
+golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo=
 golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
-golang.org/x/text v0.34.0 h1:oL/Qq0Kdaqxa1KbNeMKwQq0reLCCaFtqu2eNuSeNHbk=
-golang.org/x/text v0.34.0/go.mod h1:homfLqTYRFyVYemLBFl5GgL/DWEiH5wcsQ5gSh1yziA=
+golang.org/x/text v0.35.0 h1:JOVx6vVDFokkpaq1AEptVzLTpDe9KGpj5tR4/X+ybL8=
+golang.org/x/text v0.35.0/go.mod h1:khi/HExzZJ2pGnjenulevKNX1W67CUy0AsXcNubPGCA=
 gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
 gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 h1:Jr5R2J6F6qWyzINc+4AM8t5pfUz6beZpHp678GNrMbE=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20/go.mod h1:j9x/tPzZkyxcgEFkiKEEGxfvyumM01BEtsW8xzOahRQ=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 h1:ndE4FoJqsIceKP2oYSnUZqhTdYufCYYkqwtFzfrhI7w=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
 google.golang.org/grpc v1.79.3 h1:sybAEdRIEtvcD68Gx7dmnwjZKlyfuc61Dyo9pGXXkKE=
 google.golang.org/grpc v1.79.3/go.mod h1:KmT0Kjez+0dde/v2j9vzwoAScgEPx/Bw1CYChhHLrHQ=
 google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=

test/fuse_dlm/dlm_concurrent_write_test.go

@@ -0,0 +1,277 @@
+package fuse_dlm
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestDLMConcurrentWritersSameFile verifies that two mounts writing to the same
+// file concurrently produce valid (non-corrupted) data. With DLM enabled, the
+// writes are serialized — one blocks until the other completes.
+//
+// Note: cross-mount read consistency depends on FUSE kernel cache invalidation
+// and filer metadata subscription, which are asynchronous. This test verifies
+// write integrity, not instant read convergence.
+func TestDLMConcurrentWritersSameFile(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping DLM integration test in short mode")
+	}
+
+	cluster := startDLMTestCluster(t)
+	t.Cleanup(cluster.Stop)
+
+	const iterations = 5
+	for iter := 0; iter < iterations; iter++ {
+		fileName := fmt.Sprintf("concurrent_write_%d.txt", iter)
+		payloadA := []byte(fmt.Sprintf("mount0-iteration-%d-payload-AAAA", iter))
+		payloadB := []byte(fmt.Sprintf("mount1-iteration-%d-payload-BBBB", iter))
+
+		var wg sync.WaitGroup
+		wg.Add(2)
+
+		go func() {
+			defer wg.Done()
+			err := os.WriteFile(filepath.Join(cluster.mountPoints[0], fileName), payloadA, 0644)
+			assert.NoError(t, err, "mount0 write iteration %d", iter)
+		}()
+
+		go func() {
+			defer wg.Done()
+			err := os.WriteFile(filepath.Join(cluster.mountPoints[1], fileName), payloadB, 0644)
+			assert.NoError(t, err, "mount1 write iteration %d", iter)
+		}()
+
+		wg.Wait()
+
+		// Verify file is readable and contains one of the expected payloads
+		// (read from mount0 — its own view is authoritative for write success).
+		content, err := os.ReadFile(filepath.Join(cluster.mountPoints[0], fileName))
+		require.NoError(t, err, "read from mount0 iteration %d", iter)
+		validPayload := string(content) == string(payloadA) || string(content) == string(payloadB)
+		assert.True(t, validPayload,
+			"iteration %d: content must be one of the expected payloads, got: %q", iter, content)
+	}
+}
+
+// TestDLMRepeatedOpenWriteClose verifies that repeated open/write/close cycles
+// from both mounts all succeed without errors.
+func TestDLMRepeatedOpenWriteClose(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping DLM integration test in short mode")
+	}
+
+	cluster := startDLMTestCluster(t)
+	t.Cleanup(cluster.Stop)
+
+	const cycles = 20
+	fileName := "repeated_write.txt"
+
+	var wg sync.WaitGroup
+	wg.Add(2)
+
+	go func() {
+		defer wg.Done()
+		for i := 0; i < cycles; i++ {
+			data := []byte(fmt.Sprintf("mount0-cycle-%d", i))
+			err := os.WriteFile(filepath.Join(cluster.mountPoints[0], fileName), data, 0644)
+			assert.NoError(t, err, "mount0 cycle %d", i)
+		}
+	}()
+
+	go func() {
+		defer wg.Done()
+		for i := 0; i < cycles; i++ {
+			data := []byte(fmt.Sprintf("mount1-cycle-%d", i))
+			err := os.WriteFile(filepath.Join(cluster.mountPoints[1], fileName), data, 0644)
+			assert.NoError(t, err, "mount1 cycle %d", i)
+		}
+	}()
+
+	wg.Wait()
+
+	// File must be readable from at least one mount
+	content, err := os.ReadFile(filepath.Join(cluster.mountPoints[0], fileName))
+	require.NoError(t, err)
+	assert.NotEmpty(t, content, "file must not be empty")
+}
+
+// TestDLMWriteBlocksSecondWriter verifies the core DLM guarantee: while one
+// mount has a file open for writing, another mount's write-open blocks until
+// the first mount closes the file.
+func TestDLMWriteBlocksSecondWriter(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping DLM integration test in short mode")
+	}
+
+	cluster := startDLMTestCluster(t)
+	t.Cleanup(cluster.Stop)
+
+	fileName := "blocking_test.txt"
+	path0 := filepath.Join(cluster.mountPoints[0], fileName)
+	path1 := filepath.Join(cluster.mountPoints[1], fileName)
+
+	// Mount 0 opens the file for writing and holds it open
+	f, err := os.OpenFile(path0, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0644)
+	require.NoError(t, err, "mount0 open")
+	_, err = f.Write([]byte("mount0-holds-lock"))
+	require.NoError(t, err, "mount0 write")
+
+	// Mount 1 tries to write — should block (we use a goroutine with atomic flag)
+	var mount1Completed atomic.Bool
+	mount1Done := make(chan error, 1)
+	go func() {
+		err := os.WriteFile(path1, []byte("mount1-waited"), 0644)
+		mount1Completed.Store(true)
+		mount1Done <- err
+	}()
+
+	// Give mount 1 a moment — it should NOT complete while mount 0 holds the file open
+	time.Sleep(3 * time.Second)
+	require.False(t, mount1Completed.Load(),
+		"mount1 write must not complete while mount0 holds the file open")
+	t.Log("mount1 write is blocked as expected while mount0 holds the file")
+
+	// Mount 0 closes the file — this releases the DLM lock
+	require.NoError(t, f.Close(), "mount0 close")
+
+	// Mount 1 should now complete
+	select {
+	case err := <-mount1Done:
+		assert.NoError(t, err, "mount1 write after mount0 close")
+	case <-time.After(30 * time.Second):
+		t.Fatal("mount1 write did not complete within 30s after mount0 closed")
+	}
+}
+
+// TestDLMRenameWhileWriteOpen verifies that a rename is coordinated with DLM:
+// while mount0 has a file open for writing (re-opened after creation),
+// mount1 cannot rename it until mount0 closes the file.
+func TestDLMRenameWhileWriteOpen(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping DLM integration test in short mode")
+	}
+
+	cluster := startDLMTestCluster(t)
+	t.Cleanup(cluster.Stop)
+
+	origName := "rename_source.txt"
+	newName := "rename_dest.txt"
+
+	// Create and close the file first so it's flushed to the filer and
+	// visible on both mounts.
+	require.NoError(t, os.WriteFile(
+		filepath.Join(cluster.mountPoints[0], origName),
+		[]byte("initial-content"), 0644))
+	time.Sleep(2 * time.Second) // metadata propagation
+
+	// Verify mount1 can see the file
+	_, err := os.Stat(filepath.Join(cluster.mountPoints[1], origName))
+	require.NoError(t, err, "mount1 should see the file")
+
+	// Mount 0 re-opens the file for writing and holds it open
+	f, err := os.OpenFile(
+		filepath.Join(cluster.mountPoints[0], origName),
+		os.O_WRONLY|os.O_TRUNC, 0644)
+	require.NoError(t, err, "mount0 reopen")
+	_, err = f.Write([]byte("data-while-holding-lock"))
+	require.NoError(t, err, "mount0 write")
+
+	// Mount 1 tries to rename — should block because mount0 holds the
+	// DLM lock on the old path
+	var renameCompleted atomic.Bool
+	renameDone := make(chan error, 1)
+	go func() {
+		err := os.Rename(
+			filepath.Join(cluster.mountPoints[1], origName),
+			filepath.Join(cluster.mountPoints[1], newName))
+		renameCompleted.Store(true)
+		renameDone <- err
+	}()
+
+	// Rename must NOT complete while mount0 holds the file open
+	time.Sleep(3 * time.Second)
+	require.False(t, renameCompleted.Load(),
+		"rename must not complete while mount0 holds the file open")
+	t.Log("rename is blocked as expected while mount0 holds the file")
+
+	// Mount 0 closes → releases DLM lock → rename should proceed
+	require.NoError(t, f.Close(), "mount0 close")
+
+	select {
+	case err := <-renameDone:
+		assert.NoError(t, err, "rename after mount0 close")
+	case <-time.After(30 * time.Second):
+		t.Fatal("rename did not complete within 30s after mount0 closed")
+	}
+}
+
+// Note: Same-mount rename while a file is open for writing is not tested here
+// because macOS FUSE serializes operations on the same inode, causing a
+// kernel-level deadlock between the Rename handler's internal flush and the
+// pending Close. Same-mount coordination is already handled by the per-mount
+// fhLockTable and FUSE kernel serialization, so DLM is not needed for it.
+
+// TestDLMConcurrentRenames verifies that two concurrent renames of the same
+// file from different mounts don't corrupt metadata. DLM locks on both old
+// and new paths ensure renames are serialized.
+func TestDLMConcurrentRenames(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping DLM integration test in short mode")
+	}
+
+	cluster := startDLMTestCluster(t)
+	t.Cleanup(cluster.Stop)
+
+	// Create a file first
+	origPath := filepath.Join(cluster.mountPoints[0], "rename_race.txt")
+	require.NoError(t, os.WriteFile(origPath, []byte("original-content"), 0644))
+	time.Sleep(1 * time.Second) // propagation
+
+	// Both mounts try to rename the same file concurrently
+	var wg sync.WaitGroup
+	var errA, errB error
+	wg.Add(2)
+
+	go func() {
+		defer wg.Done()
+		errA = os.Rename(
+			filepath.Join(cluster.mountPoints[0], "rename_race.txt"),
+			filepath.Join(cluster.mountPoints[0], "renamed_by_mount0.txt"),
+		)
+	}()
+
+	go func() {
+		defer wg.Done()
+		errB = os.Rename(
+			filepath.Join(cluster.mountPoints[1], "rename_race.txt"),
+			filepath.Join(cluster.mountPoints[1], "renamed_by_mount1.txt"),
+		)
+	}()
+
+	wg.Wait()
+
+	// At least one rename should succeed; the other may fail with ENOENT
+	// since the source was already moved.
+	succeeded := 0
+	if errA == nil {
+		succeeded++
+		t.Logf("mount0 rename succeeded")
+	} else {
+		t.Logf("mount0 rename failed: %v", errA)
+	}
+	if errB == nil {
+		succeeded++
+		t.Logf("mount1 rename succeeded")
+	} else {
+		t.Logf("mount1 rename failed: %v", errB)
+	}
+	assert.GreaterOrEqual(t, succeeded, 1, "at least one rename must succeed")
+}

test/fuse_dlm/framework_test.go

@@ -0,0 +1,516 @@
+package fuse_dlm
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"sync"
+	"syscall"
+	"testing"
+	"time"
+
+	"github.com/seaweedfs/seaweedfs/weed/cluster/lock_manager"
+	"github.com/seaweedfs/seaweedfs/weed/pb"
+	"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
+	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+const filerGroup = "fuse-dlm-test"
+
+// dlmTestCluster manages a full SeaweedFS cluster with 2 filers and 2 FUSE
+// mounts for testing DLM-based cross-mount write coordination.
+type dlmTestCluster struct {
+	t          testing.TB
+	baseDir    string
+	weedBinary string
+
+	masterPort     int
+	masterGrpcPort int
+	volumePort     int
+	volumeGrpcPort int
+	filerPorts     [2]int
+	filerGrpcPorts [2]int
+	mountPoints    [2]string
+
+	masterCmd  *exec.Cmd
+	volumeCmd  *exec.Cmd
+	filerCmds  [2]*exec.Cmd
+	mountCmds  [2]*exec.Cmd
+	logFiles   []*os.File
+
+	cleanupOnce sync.Once
+}
+
+func startDLMTestCluster(t testing.TB) *dlmTestCluster {
+	binary := findWeedBinary()
+	if binary == "" {
+		t.Skip("weed binary not found; set WEED_BINARY or ensure it is on PATH")
+	}
+
+	baseDir, err := os.MkdirTemp("", "seaweedfs_fuse_dlm_test_")
+	require.NoError(t, err)
+
+	c := &dlmTestCluster{
+		t:          t,
+		baseDir:    baseDir,
+		weedBinary: binary,
+	}
+	// Register cleanup early so processes are stopped even if a require fails below.
+	t.Cleanup(c.Stop)
+
+	// Allocate ports: master(2) + volume(2) + filer0(2) + filer1(2) = 8
+	ports := allocatePorts(t, 8)
+	c.masterPort = ports[0]
+	c.masterGrpcPort = ports[1]
+	c.volumePort = ports[2]
+	c.volumeGrpcPort = ports[3]
+	c.filerPorts[0] = ports[4]
+	c.filerGrpcPorts[0] = ports[5]
+	c.filerPorts[1] = ports[6]
+	c.filerGrpcPorts[1] = ports[7]
+
+	// Write empty security.toml
+	configDir := filepath.Join(baseDir, "config")
+	require.NoError(t, os.MkdirAll(configDir, 0755))
+	require.NoError(t, os.WriteFile(filepath.Join(configDir, "security.toml"), []byte(""), 0644))
+
+	// Start master
+	require.NoError(t, c.startMaster(configDir))
+	require.NoError(t, c.waitForTCP(fmt.Sprintf("127.0.0.1:%d", c.masterPort), 30*time.Second),
+		"master not ready\n%s", c.tailLog("master"))
+
+	// Start volume
+	require.NoError(t, c.startVolume(configDir))
+	require.NoError(t, c.waitForTCP(fmt.Sprintf("127.0.0.1:%d", c.volumePort), 30*time.Second),
+		"volume not ready\n%s", c.tailLog("volume"))
+
+	// Start 2 filers
+	for i := 0; i < 2; i++ {
+		require.NoError(t, c.startFiler(i, configDir))
+		require.NoError(t, c.waitForTCP(fmt.Sprintf("127.0.0.1:%d", c.filerGrpcPorts[i]), 30*time.Second),
+			"filer %d not ready\n%s", i, c.tailLog(fmt.Sprintf("filer%d", i)))
+	}
+	require.NoError(t, c.waitForFilerCount(2, 30*time.Second), "filer group registration")
+	require.NoError(t, c.waitForLockRingConverged(30*time.Second), "lock ring convergence")
+
+	// Start 2 mounts, both pointing at filer0 for metadata consistency.
+	// (filer1 exists for the DLM lock ring but both mounts share filer0's
+	// metadata store since leveldb is per-filer.)
+	for i := 0; i < 2; i++ {
+		mp := filepath.Join(baseDir, fmt.Sprintf("mount%d", i))
+		require.NoError(t, os.MkdirAll(mp, 0755))
+		c.mountPoints[i] = mp
+		require.NoError(t, c.startMount(i, configDir))
+		require.NoError(t, c.waitForMount(mp, 30*time.Second),
+			"mount %d not ready\n%s", i, c.tailLog(fmt.Sprintf("mount%d", i)))
+	}
+
+	return c
+}
+
+func (c *dlmTestCluster) Stop() {
+	if c == nil {
+		return
+	}
+	c.cleanupOnce.Do(func() {
+		// Stop mounts first (triggers flush + DLM unlock).
+		// Use stopCmd for bounded wait to avoid hanging on wedged FUSE processes.
+		for i := 1; i >= 0; i-- {
+			stopCmd(c.mountCmds[i])
+			// Backup unmount in case FUSE teardown didn't clean up
+			exec.Command("fusermount3", "-u", c.mountPoints[i]).Run()
+			exec.Command("fusermount", "-u", c.mountPoints[i]).Run()
+		}
+		// Stop filers, volume, master
+		for i := 1; i >= 0; i-- {
+			stopCmd(c.filerCmds[i])
+		}
+		stopCmd(c.volumeCmd)
+		stopCmd(c.masterCmd)
+
+		for _, f := range c.logFiles {
+			f.Close()
+		}
+
+		// Copy logs for CI
+		c.copyLogsForCI()
+
+		if !c.t.Failed() {
+			os.RemoveAll(c.baseDir)
+		}
+
+		// Wait for ports to be fully released before the next test
+		// allocates new ports (avoids TIME_WAIT collisions).
+		time.Sleep(2 * time.Second)
+	})
+}
+
+// masterAddress returns the master address in the format that encodes both
+// HTTP and gRPC ports: "host:httpPort.grpcPort". This is the format that
+// SeaweedFS uses to communicate non-default gRPC ports between components.
+func (c *dlmTestCluster) masterAddress() string {
+	return string(pb.NewServerAddress("127.0.0.1", c.masterPort, c.masterGrpcPort))
+}
+
+func (c *dlmTestCluster) startMaster(configDir string) error {
+	c.masterCmd = exec.Command(c.weedBinary,
+		"-logdir="+filepath.Join(c.baseDir, "logs"),
+		"master",
+		"-ip=127.0.0.1",
+		"-ip.bind=127.0.0.1",
+		"-port="+strconv.Itoa(c.masterPort),
+		"-port.grpc="+strconv.Itoa(c.masterGrpcPort),
+		"-mdir="+filepath.Join(c.baseDir, "master"),
+	)
+	return c.startCmd(c.masterCmd, "master")
+}
+
+func (c *dlmTestCluster) startVolume(configDir string) error {
+	volDir := filepath.Join(c.baseDir, "volume")
+	if err := os.MkdirAll(volDir, 0755); err != nil {
+		return fmt.Errorf("create volume dir: %w", err)
+	}
+	c.volumeCmd = exec.Command(c.weedBinary,
+		"-logdir="+filepath.Join(c.baseDir, "logs"),
+		"volume",
+		"-ip=127.0.0.1",
+		"-ip.bind=127.0.0.1",
+		"-port="+strconv.Itoa(c.volumePort),
+		"-port.grpc="+strconv.Itoa(c.volumeGrpcPort),
+		"-master="+c.masterAddress(),
+		"-dir="+volDir,
+		"-max=10",
+	)
+	return c.startCmd(c.volumeCmd, "volume")
+}
+
+func (c *dlmTestCluster) startFiler(idx int, configDir string) error {
+	filerDir := filepath.Join(c.baseDir, fmt.Sprintf("filer%d", idx))
+	if err := os.MkdirAll(filerDir, 0755); err != nil {
+		return fmt.Errorf("create filer dir: %w", err)
+	}
+	c.filerCmds[idx] = exec.Command(c.weedBinary,
+		"-logdir="+filepath.Join(c.baseDir, "logs"),
+		"filer",
+		"-ip=127.0.0.1",
+		"-ip.bind=127.0.0.1",
+		"-port="+strconv.Itoa(c.filerPorts[idx]),
+		"-port.grpc="+strconv.Itoa(c.filerGrpcPorts[idx]),
+		"-master="+c.masterAddress(),
+		"-filerGroup="+filerGroup,
+		"-defaultStoreDir="+filerDir,
+	)
+	return c.startCmd(c.filerCmds[idx], fmt.Sprintf("filer%d", idx))
+}
+
+func (c *dlmTestCluster) filerAddress(idx int) string {
+	return string(pb.NewServerAddress("127.0.0.1", c.filerPorts[idx], c.filerGrpcPorts[idx]))
+}
+
+func (c *dlmTestCluster) startMount(idx int, configDir string) error {
+	cacheDir := filepath.Join(c.baseDir, fmt.Sprintf("cache%d", idx))
+	if err := os.MkdirAll(cacheDir, 0755); err != nil {
+		return fmt.Errorf("create cache dir: %w", err)
+	}
+	c.mountCmds[idx] = exec.Command(c.weedBinary,
+		"-logdir="+filepath.Join(c.baseDir, "logs"),
+		"mount",
+		"-filer="+c.filerAddress(0), // both mounts use filer0 for shared metadata
+		"-dir="+c.mountPoints[idx],
+		"-filer.path=/",
+		"-dirAutoCreate",
+		"-allowOthers=false",
+		"-cacheDir="+cacheDir,
+		"-dlm",
+	)
+	return c.startCmd(c.mountCmds[idx], fmt.Sprintf("mount%d", idx))
+}
+
+func (c *dlmTestCluster) startCmd(cmd *exec.Cmd, name string) error {
+	logPath := filepath.Join(c.baseDir, "logs")
+	if err := os.MkdirAll(logPath, 0755); err != nil {
+		return fmt.Errorf("create log dir: %w", err)
+	}
+	logFile, err := os.Create(filepath.Join(logPath, name+".log"))
+	if err != nil {
+		return err
+	}
+	c.logFiles = append(c.logFiles, logFile)
+	cmd.Stdout = logFile
+	cmd.Stderr = logFile
+	return cmd.Start()
+}
+
+func (c *dlmTestCluster) tailLog(name string) string {
+	data, err := os.ReadFile(filepath.Join(c.baseDir, "logs", name+".log"))
+	if err != nil {
+		return fmt.Sprintf("(log %s not available: %v)", name, err)
+	}
+	const maxTail = 8192
+	if len(data) > maxTail {
+		data = data[len(data)-maxTail:]
+	}
+	return string(data)
+}
+
+func (c *dlmTestCluster) copyLogsForCI() {
+	ciLogDir := "/tmp/seaweedfs-fuse-dlm-logs"
+	os.MkdirAll(ciLogDir, 0755)
+	logsDir := filepath.Join(c.baseDir, "logs")
+	entries, err := os.ReadDir(logsDir)
+	if err != nil {
+		return
+	}
+	for _, e := range entries {
+		data, err := os.ReadFile(filepath.Join(logsDir, e.Name()))
+		if err != nil {
+			continue
+		}
+		os.WriteFile(filepath.Join(ciLogDir, e.Name()), data, 0644)
+	}
+}
+
+func (c *dlmTestCluster) waitForTCP(addr string, timeout time.Duration) error {
+	deadline := time.Now().Add(timeout)
+	for time.Now().Before(deadline) {
+		conn, err := net.DialTimeout("tcp", addr, time.Second)
+		if err == nil {
+			conn.Close()
+			return nil
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+	return fmt.Errorf("service at %s not ready within timeout", addr)
+}
+
+// waitForMount waits for a FUSE filesystem to actually be mounted at
+// mountPoint by comparing the device ID of the mount point against its parent.
+// A plain directory (pre-created before mount) has the same device as its
+// parent; a mounted FUSE filesystem has a different device.
+func (c *dlmTestCluster) waitForMount(mountPoint string, timeout time.Duration) error {
+	parentDir := filepath.Dir(mountPoint)
+	deadline := time.Now().Add(timeout)
+	for time.Now().Before(deadline) {
+		parentStat, err := os.Stat(parentDir)
+		if err != nil {
+			time.Sleep(200 * time.Millisecond)
+			continue
+		}
+		mountStat, err := os.Stat(mountPoint)
+		if err != nil {
+			time.Sleep(200 * time.Millisecond)
+			continue
+		}
+		parentSys := parentStat.Sys().(*syscall.Stat_t)
+		mountSys := mountStat.Sys().(*syscall.Stat_t)
+		if parentSys.Dev != mountSys.Dev {
+			// Different device = FUSE mounted
+			return nil
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+	return fmt.Errorf("mount point %s not ready within timeout (FUSE not detected)", mountPoint)
+}
+
+func (c *dlmTestCluster) filerGRPCAddress(idx int) string {
+	return fmt.Sprintf("127.0.0.1:%d", c.filerGrpcPorts[idx])
+}
+
+func (c *dlmTestCluster) waitForFilerCount(expected int, timeout time.Duration) error {
+	addr := fmt.Sprintf("127.0.0.1:%d", c.masterGrpcPort)
+	conn, err := grpc.NewClient(addr, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return err
+	}
+	defer conn.Close()
+
+	client := master_pb.NewSeaweedClient(conn)
+	deadline := time.Now().Add(timeout)
+	for time.Now().Before(deadline) {
+		ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+		resp, err := client.ListClusterNodes(ctx, &master_pb.ListClusterNodesRequest{
+			ClientType: "filer",
+			FilerGroup: filerGroup,
+		})
+		cancel()
+		if err == nil && len(resp.ClusterNodes) >= expected {
+			return nil
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+	return fmt.Errorf("timed out waiting for %d filers in group %q", expected, filerGroup)
+}
+
+// waitForLockRingConverged verifies that both filers have a consistent view of
+// the lock ring by acquiring the same lock through each filer and checking
+// mutual exclusion. Adapted from test/s3/distributed_lock/.
+func (c *dlmTestCluster) waitForLockRingConverged(timeout time.Duration) error {
+	deadline := time.Now().Add(timeout)
+
+	owners := []pb.ServerAddress{
+		pb.ServerAddress(c.filerGRPCAddress(0)),
+		pb.ServerAddress(c.filerGRPCAddress(1)),
+	}
+	ring := lock_manager.NewHashRing(lock_manager.DefaultVnodeCount)
+	ring.SetServers(owners)
+
+	attempt := 0
+	for time.Now().Before(deadline) {
+		testKeys := convergenceKeysPerPrimary(ring, owners, attempt)
+		attempt++
+
+		allConverged := true
+		for _, key := range testKeys {
+			converged, _ := c.checkLockMutualExclusion(key)
+			if !converged {
+				allConverged = false
+				break
+			}
+		}
+		if allConverged {
+			return nil
+		}
+		time.Sleep(500 * time.Millisecond)
+	}
+	return fmt.Errorf("lock ring did not converge")
+}
+
+// convergenceKeysPerPrimary generates one test key per primary filer.
+func convergenceKeysPerPrimary(ring *lock_manager.HashRing, owners []pb.ServerAddress, attempt int) []string {
+	found := make(map[pb.ServerAddress]bool)
+	var keys []string
+	for i := 0; len(found) < len(owners) && i < 10000; i++ {
+		key := fmt.Sprintf("convergence-test-%d-%d", attempt, i)
+		primary, _ := ring.GetPrimaryAndBackup(key)
+		if !found[primary] {
+			found[primary] = true
+			keys = append(keys, key)
+		}
+	}
+	return keys
+}
+
+func (c *dlmTestCluster) checkLockMutualExclusion(key string) (bool, error) {
+	// Try to lock via filer0
+	conn0, err := grpc.NewClient(c.filerGRPCAddress(0), grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return false, err
+	}
+	defer conn0.Close()
+
+	client0 := filer_pb.NewSeaweedFilerClient(conn0)
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+	resp0, err := client0.DistributedLock(ctx, &filer_pb.LockRequest{
+		Name:          key,
+		SecondsToLock: 5,
+		Owner:         "convergence-test-0",
+	})
+	if err != nil {
+		return false, err
+	}
+	if resp0.Error != "" {
+		return false, fmt.Errorf("lock0: %s", resp0.Error)
+	}
+
+	// Try to lock via filer1 — should fail (already locked)
+	conn1, err := grpc.NewClient(c.filerGRPCAddress(1), grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return false, err
+	}
+	defer conn1.Close()
+
+	client1 := filer_pb.NewSeaweedFilerClient(conn1)
+	resp1, err := client1.DistributedLock(ctx, &filer_pb.LockRequest{
+		Name:          key,
+		SecondsToLock: 5,
+		Owner:         "convergence-test-1",
+	})
+
+	// Unlock via filer0
+	client0.DistributedUnlock(ctx, &filer_pb.UnlockRequest{
+		Name:       key,
+		RenewToken: resp0.RenewToken,
+	})
+
+	if err != nil {
+		return false, err
+	}
+	// If filer1 also got the lock, the ring hasn't converged
+	if resp1.Error == "" {
+		// Unlock the second one too
+		client1.DistributedUnlock(ctx, &filer_pb.UnlockRequest{
+			Name:       key,
+			RenewToken: resp1.RenewToken,
+		})
+		return false, nil
+	}
+
+	return true, nil
+}
+
+func stopCmd(cmd *exec.Cmd) {
+	if cmd == nil || cmd.Process == nil {
+		return
+	}
+	cmd.Process.Signal(syscall.SIGTERM)
+	done := make(chan struct{})
+	go func() {
+		cmd.Wait()
+		close(done)
+	}()
+	select {
+	case <-done:
+	case <-time.After(10 * time.Second):
+		cmd.Process.Kill()
+		<-done
+	}
+}
+
+func allocatePorts(t testing.TB, n int) []int {
+	t.Helper()
+	// Hold all listeners open until all ports are collected, then close
+	// them together. This prevents the OS from reassigning a just-freed
+	// port to the next Listen call within the same allocation batch.
+	listeners := make([]net.Listener, 0, n)
+	ports := make([]int, 0, n)
+	defer func() {
+		for _, l := range listeners {
+			l.Close()
+		}
+	}()
+	for i := 0; i < n; i++ {
+		l, err := net.Listen("tcp", "127.0.0.1:0")
+		require.NoError(t, err)
+		listeners = append(listeners, l)
+		ports = append(ports, l.Addr().(*net.TCPAddr).Port)
+	}
+	return ports
+}
+
+func findWeedBinary() string {
+	if p := os.Getenv("WEED_BINARY"); p != "" {
+		return p
+	}
+	if p, err := exec.LookPath("weed"); err == nil {
+		return p
+	}
+	candidates := []string{
+		"../../weed/weed",
+		"./weed",
+	}
+	for _, c := range candidates {
+		if info, err := os.Stat(c); err == nil && !info.IsDir() {
+			abs, _ := filepath.Abs(c)
+			return abs
+		}
+	}
+	return ""
+}

test/fuse_integration/concurrent_operations_test.go

@@ -249,11 +249,18 @@ func testConcurrentDirectoryOperations(t *testing.T, framework *FuseTestFramewor
 					return
 				}
 
-				// Create file in subdirectory
+				// Create file in subdirectory with retry for transient FUSE errors
 				testFile := filepath.Join(subDir, "test.txt")
 				content := []byte(fmt.Sprintf("Worker %d, Subdir %d", workerID, i))
-				if err := os.WriteFile(testFile, content, 0644); err != nil {
-					addError(fmt.Errorf("worker %d file %d: %v", workerID, i, err))
+				var writeErr error
+				for attempt := 0; attempt < 3; attempt++ {
+					if writeErr = os.WriteFile(testFile, content, 0644); writeErr == nil {
+						break
+					}
+					time.Sleep(100 * time.Millisecond)
+				}
+				if writeErr != nil {
+					addError(fmt.Errorf("worker %d file %d: %v", workerID, i, writeErr))
 					return
 				}
 			}

test/fuse_integration/framework_test.go

@@ -82,12 +82,13 @@ func NewFuseTestFramework(t *testing.T, config *TestConfig) *FuseTestFramework {
 	}
 }
 
-// freePort asks the OS for a free TCP port.
+// freePort asks the OS for a free TCP port in a range where the gRPC
+// offset (port + 10000) won't collide with well-known ports.
 func freePort(t *testing.T) int {
 	t.Helper()
 	const (
 		minServicePort = 20000
-		maxServicePort = 55535 // SeaweedFS gRPC service uses httpPort + 10000.
+		maxServicePort = 55535
 	)
 
 	portCount := maxServicePort - minServicePort + 1

test/fuse_integration/git_operations_test.go

@@ -85,9 +85,19 @@ func testGitCloneAndPull(t *testing.T, mountPoint, localDir string) {
 	branch := gitOutput(t, localClone, "rev-parse", "--abbrev-ref", "HEAD")
 	gitRun(t, localClone, "push", "origin", branch)
 
+	// The bare repo lives on the FUSE mount and can briefly disappear after
+	// the push completes, and pushed pack objects may not be immediately
+	// consistent on the FUSE layer. Give the mount a chance to settle, then
+	// recover from the local clone if the remote is still missing.
+	if !waitForBareRepoEventually(t, bareRepo, 10*time.Second) {
+		t.Logf("bare repo %s did not stabilise after push; forcing recovery before clone", bareRepo)
+	}
+	refreshDirEntry(t, bareRepo)
+	time.Sleep(1 * time.Second)
+
 	// ---- Phase 3: Clone from mount bare repo into on-mount working dir ----
 	t.Log("Phase 3: clone from mount bare repo to on-mount working dir")
-	gitRun(t, "", "clone", bareRepo, mountClone)
+	ensureMountCloneFromBareWithRecovery(t, bareRepo, localClone, mountClone)
 
 	assertFileContains(t, filepath.Join(mountClone, "README.md"), "# Updated")
 	assertFileContains(t, filepath.Join(mountClone, "src/main.go"), "v2")
@@ -290,7 +300,7 @@ func waitForBareRepoEventually(t *testing.T, bareRepo string, timeout time.Durat
 	t.Helper()
 	deadline := time.Now().Add(timeout)
 	for time.Now().Before(deadline) {
-		if isBareRepo(bareRepo) {
+		if isBareRepoAccessible(bareRepo) {
 			return true
 		}
 		refreshDirEntry(t, bareRepo)
@@ -312,6 +322,14 @@ func isBareRepo(bareRepo string) bool {
 	return true
 }
 
+func isBareRepoAccessible(bareRepo string) bool {
+	if !isBareRepo(bareRepo) {
+		return false
+	}
+	out, err := tryGitCommand("", "--git-dir="+bareRepo, "rev-parse", "--is-bare-repository")
+	return err == nil && out == "true"
+}
+
 func ensureMountClone(t *testing.T, bareRepo, mountClone string) {
 	t.Helper()
 	require.NoError(t, tryEnsureMountClone(bareRepo, mountClone))
@@ -320,7 +338,7 @@ func ensureMountClone(t *testing.T, bareRepo, mountClone string) {
 // tryEnsureBareRepo verifies the bare repo on the FUSE mount exists.
 // If it has vanished, it re-creates it from the local clone.
 func tryEnsureBareRepo(bareRepo, localClone string) error {
-	if _, err := os.Stat(filepath.Join(bareRepo, "HEAD")); err == nil {
+	if isBareRepoAccessible(bareRepo) {
 		return nil
 	}
 	branch, err := tryGitCommand(localClone, "rev-parse", "--abbrev-ref", "HEAD")
@@ -342,6 +360,36 @@ func tryEnsureBareRepo(bareRepo, localClone string) error {
 	return nil
 }
 
+func ensureMountCloneFromBareWithRecovery(t *testing.T, bareRepo, localClone, mountClone string) {
+	t.Helper()
+	const maxAttempts = 3
+	var lastErr error
+	for attempt := 1; attempt <= maxAttempts; attempt++ {
+		if lastErr = tryEnsureMountCloneFromBare(bareRepo, localClone, mountClone); lastErr == nil {
+			return
+		}
+		if attempt == maxAttempts {
+			require.NoError(t, lastErr, "git clone %s %s failed after %d recovery attempts", bareRepo, mountClone, maxAttempts)
+		}
+		t.Logf("clone recovery attempt %d: %v — removing clone for re-create", attempt, lastErr)
+		os.RemoveAll(mountClone)
+		time.Sleep(2 * time.Second)
+	}
+}
+
+func tryEnsureMountCloneFromBare(bareRepo, localClone, mountClone string) error {
+	if err := tryEnsureBareRepo(bareRepo, localClone); err != nil {
+		return fmt.Errorf("ensure bare repo: %w", err)
+	}
+	if err := tryEnsureMountClone(bareRepo, mountClone); err != nil {
+		return fmt.Errorf("ensure mount clone: %w", err)
+	}
+	if _, err := tryGitCommand(mountClone, "rev-parse", "HEAD"); err != nil {
+		return fmt.Errorf("verify mount clone: %w", err)
+	}
+	return nil
+}
+
 // tryEnsureMountClone is like ensureMountClone but returns an error instead
 // of failing the test, for use in recovery loops.
 func tryEnsureMountClone(bareRepo, mountClone string) error {
@@ -550,3 +598,33 @@ func TestTryEnsureBareRepoPreservesCurrentBranch(t *testing.T) {
 	assert.Equal(t, branch, restoredHead, "clone from recovered bare repo should check out the current branch")
 	assertFileContains(t, filepath.Join(restoredClone, "README.md"), "hello recovery")
 }
+
+func TestEnsureMountCloneFromBareWithRecoveryRecreatesMissingBareRepo(t *testing.T) {
+	tempDir, err := os.MkdirTemp("", "git_mount_clone_recovery_")
+	require.NoError(t, err)
+	defer os.RemoveAll(tempDir)
+
+	bareRepo := filepath.Join(tempDir, "repo.git")
+	localClone := filepath.Join(tempDir, "clone")
+	mountClone := filepath.Join(tempDir, "mount-clone")
+
+	gitRun(t, "", "init", "--bare", bareRepo)
+	gitRun(t, "", "clone", bareRepo, localClone)
+	gitRun(t, localClone, "config", "user.email", "test@seaweedfs.test")
+	gitRun(t, localClone, "config", "user.name", "Test")
+
+	writeFile(t, localClone, "README.md", "hello clone recovery\n")
+	gitRun(t, localClone, "add", "README.md")
+	gitRun(t, localClone, "commit", "-m", "initial commit")
+
+	branch := gitOutput(t, localClone, "rev-parse", "--abbrev-ref", "HEAD")
+	gitRun(t, localClone, "push", "origin", branch)
+
+	require.NoError(t, os.RemoveAll(bareRepo))
+
+	ensureMountCloneFromBareWithRecovery(t, bareRepo, localClone, mountClone)
+
+	head := gitOutput(t, mountClone, "rev-parse", "--abbrev-ref", "HEAD")
+	assert.Equal(t, branch, head, "recovered clone should stay on the pushed branch")
+	assertFileContains(t, filepath.Join(mountClone, "README.md"), "hello clone recovery")
+}

test/kafka/go.mod

@@ -14,7 +14,7 @@ require (
 replace github.com/seaweedfs/seaweedfs => ../../
 
 require (
-	cloud.google.com/go/auth v0.18.1 // indirect
+	cloud.google.com/go/auth v0.18.2 // indirect
 	cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 // indirect
@@ -43,25 +43,25 @@ require (
 	github.com/andybalholm/cascadia v1.3.3 // indirect
 	github.com/appscode/go-querystring v0.0.0-20170504095604-0126cfb3f1dc // indirect
 	github.com/aws/aws-sdk-go v1.55.8 // indirect
-	github.com/aws/aws-sdk-go-v2 v1.41.4 // indirect
-	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 // indirect
-	github.com/aws/aws-sdk-go-v2/config v1.32.9 // indirect
-	github.com/aws/aws-sdk-go-v2/credentials v1.19.12 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.20 // indirect
+	github.com/aws/aws-sdk-go-v2 v1.41.5 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 // indirect
+	github.com/aws/aws-sdk-go-v2/config v1.32.13 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.14 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21 // indirect
 	github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.20.12 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.20 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.20 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 // indirect
 	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.20 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17 // indirect
-	github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0 // indirect
-	github.com/aws/aws-sdk-go-v2/service/signin v1.0.8 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.30.13 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.17 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.41.9 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 // indirect
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0 // indirect
+	github.com/aws/aws-sdk-go-v2/service/signin v1.0.9 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.15 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.41.10 // indirect
 	github.com/aws/smithy-go v1.24.2 // indirect
 	github.com/bahlo/generic-list-go v0.2.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
@@ -104,7 +104,7 @@ require (
 	github.com/go-chi/chi/v5 v5.2.5 // indirect
 	github.com/go-darwin/apfs v0.0.0-20211011131704-f84b94dbf348 // indirect
 	github.com/go-git/go-billy/v5 v5.6.2 // indirect
-	github.com/go-jose/go-jose/v4 v4.1.3 // indirect
+	github.com/go-jose/go-jose/v4 v4.1.4 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-ole/go-ole v1.3.0 // indirect
@@ -124,8 +124,8 @@ require (
 	github.com/google/btree v1.1.3 // indirect
 	github.com/google/s2a-go v0.1.9 // indirect
 	github.com/google/uuid v1.6.0 // indirect
-	github.com/googleapis/enterprise-certificate-proxy v0.3.11 // indirect
-	github.com/googleapis/gax-go/v2 v2.17.0 // indirect
+	github.com/googleapis/enterprise-certificate-proxy v0.3.14 // indirect
+	github.com/googleapis/gax-go/v2 v2.19.0 // indirect
 	github.com/gorilla/mux v1.8.1 // indirect
 	github.com/gorilla/schema v1.4.1 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
@@ -197,7 +197,6 @@ require (
 	github.com/rcrowley/go-metrics v0.0.0-20250401214520-65e299d6c5c9 // indirect
 	github.com/rdleal/intervalst v1.5.0 // indirect
 	github.com/relvacode/iso8601 v1.7.0 // indirect
-	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/rfjakob/eme v1.1.2 // indirect
 	github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 // indirect
 	github.com/sagikazarmark/locafero v0.11.0 // indirect
@@ -242,30 +241,29 @@ require (
 	go.mongodb.org/mongo-driver v1.17.9 // indirect
 	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0 // indirect
-	go.opentelemetry.io/otel v1.40.0 // indirect
-	go.opentelemetry.io/otel/metric v1.40.0 // indirect
-	go.opentelemetry.io/otel/trace v1.40.0 // indirect
+	go.opentelemetry.io/otel v1.42.0 // indirect
+	go.opentelemetry.io/otel/metric v1.42.0 // indirect
+	go.opentelemetry.io/otel/trace v1.42.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/crypto v0.49.0 // indirect
 	golang.org/x/exp v0.0.0-20260218203240-3dfff04db8fa // indirect
 	golang.org/x/image v0.38.0 // indirect
-	golang.org/x/net v0.51.0 // indirect
+	golang.org/x/net v0.52.0 // indirect
 	golang.org/x/oauth2 v0.36.0 // indirect
 	golang.org/x/sync v0.20.0 // indirect
 	golang.org/x/sys v0.42.0 // indirect
 	golang.org/x/term v0.41.0 // indirect
 	golang.org/x/text v0.35.0 // indirect
-	golang.org/x/time v0.14.0 // indirect
-	google.golang.org/api v0.267.0 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 // indirect
+	golang.org/x/time v0.15.0 // indirect
+	google.golang.org/api v0.274.0 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 // indirect
 	google.golang.org/grpc/security/advancedtls v1.0.0 // indirect
 	google.golang.org/protobuf v1.36.11 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
 	gopkg.in/validator.v2 v2.0.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	modernc.org/mathutil v1.7.1 // indirect
 	moul.io/http2curl/v2 v2.3.0 // indirect
 	sigs.k8s.io/yaml v1.6.0 // indirect
 	storj.io/common v0.0.0-20251107171817-6221ae45072c // indirect

test/kafka/go.sum

@@ -13,8 +13,8 @@ cloud.google.com/go v0.56.0/go.mod h1:jr7tqZxxKOVYizybht9+26Z/gUq7tiRzu+ACVAMbKV
 cloud.google.com/go v0.57.0/go.mod h1:oXiQ6Rzq3RAkkY7N6t3TcE6jE+CIBBbA36lwQ1JyzZs=
 cloud.google.com/go v0.62.0/go.mod h1:jmCYTdRCQuc1PHIIJ/maLInMho30T/Y0M4hTdTShOYc=
 cloud.google.com/go v0.65.0/go.mod h1:O5N8zS7uWy9vkA9vayVHs65eM1ubvY4h553ofrNHObY=
-cloud.google.com/go/auth v0.18.1 h1:IwTEx92GFUo2pJ6Qea0EU3zYvKnTAeRCODxfA/G5UWs=
-cloud.google.com/go/auth v0.18.1/go.mod h1:GfTYoS9G3CWpRA3Va9doKN9mjPGRS+v41jmZAhBzbrA=
+cloud.google.com/go/auth v0.18.2 h1:+Nbt5Ev0xEqxlNjd6c+yYUeosQ5TtEUaNcN/3FozlaM=
+cloud.google.com/go/auth v0.18.2/go.mod h1:xD+oY7gcahcu7G2SG2DsBerfFxgPAJz17zz2joOFF3M=
 cloud.google.com/go/auth/oauth2adapt v0.2.8 h1:keo8NaayQZ6wimpNSmW5OPc283g65QNIiLpZnkHRbnc=
 cloud.google.com/go/auth/oauth2adapt v0.2.8/go.mod h1:XQ9y31RkqZCcwJWNSx2Xvric3RrU88hAYYbjDWYDL+c=
 cloud.google.com/go/bigquery v1.0.1/go.mod h1:i/xbL2UlR5RvWAURpBYZTtm/cXjCha9lbfbpx4poX+o=
@@ -112,44 +112,44 @@ github.com/appscode/go-querystring v0.0.0-20170504095604-0126cfb3f1dc h1:LoL75er
 github.com/appscode/go-querystring v0.0.0-20170504095604-0126cfb3f1dc/go.mod h1:w648aMHEgFYS6xb0KVMMtZ2uMeemhiKCuD2vj6gY52A=
 github.com/aws/aws-sdk-go v1.55.8 h1:JRmEUbU52aJQZ2AjX4q4Wu7t4uZjOu71uyNmaWlUkJQ=
 github.com/aws/aws-sdk-go v1.55.8/go.mod h1:ZkViS9AqA6otK+JBBNH2++sx1sgxrPKcSzPPvQkUtXk=
-github.com/aws/aws-sdk-go-v2 v1.41.4 h1:10f50G7WyU02T56ox1wWXq+zTX9I1zxG46HYuG1hH/k=
-github.com/aws/aws-sdk-go-v2 v1.41.4/go.mod h1:mwsPRE8ceUUpiTgF7QmQIJ7lgsKUPQOUl3o72QBrE1o=
-github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 h1:489krEF9xIGkOaaX3CE/Be2uWjiXrkCH6gUX+bZA/BU=
-github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4/go.mod h1:IOAPF6oT9KCsceNTvvYMNHy0+kMF8akOjeDvPENWxp4=
-github.com/aws/aws-sdk-go-v2/config v1.32.9 h1:ktda/mtAydeObvJXlHzyGpK1xcsLaP16zfUPDGoW90A=
-github.com/aws/aws-sdk-go-v2/config v1.32.9/go.mod h1:U+fCQ+9QKsLW786BCfEjYRj34VVTbPdsLP3CHSYXMOI=
-github.com/aws/aws-sdk-go-v2/credentials v1.19.12 h1:oqtA6v+y5fZg//tcTWahyN9PEn5eDU/Wpvc2+kJ4aY8=
-github.com/aws/aws-sdk-go-v2/credentials v1.19.12/go.mod h1:U3R1RtSHx6NB0DvEQFGyf/0sbrpJrluENHdPy1j/3TE=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.20 h1:zOgq3uezl5nznfoK3ODuqbhVg1JzAGDUhXOsU0IDCAo=
-github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.20/go.mod h1:z/MVwUARehy6GAg/yQ1GO2IMl0k++cu1ohP9zo887wE=
+github.com/aws/aws-sdk-go-v2 v1.41.5 h1:dj5kopbwUsVUVFgO4Fi5BIT3t4WyqIDjGKCangnV/yY=
+github.com/aws/aws-sdk-go-v2 v1.41.5/go.mod h1:mwsPRE8ceUUpiTgF7QmQIJ7lgsKUPQOUl3o72QBrE1o=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8 h1:eBMB84YGghSocM7PsjmmPffTa+1FBUeNvGvFou6V/4o=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.8/go.mod h1:lyw7GFp3qENLh7kwzf7iMzAxDn+NzjXEAGjKS2UOKqI=
+github.com/aws/aws-sdk-go-v2/config v1.32.13 h1:5KgbxMaS2coSWRrx9TX/QtWbqzgQkOdEa3sZPhBhCSg=
+github.com/aws/aws-sdk-go-v2/config v1.32.13/go.mod h1:8zz7wedqtCbw5e9Mi2doEwDyEgHcEE9YOJp6a8jdSMY=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.14 h1:n+UcGWAIZHkXzYt87uMFBv/l8THYELoX6gVcUvgl6fI=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.14/go.mod h1:cJKuyWB59Mqi0jM3nFYQRmnHVQIcgoxjEMAbLkpr62w=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21 h1:NUS3K4BTDArQqNu2ih7yeDLaS3bmHD0YndtA6UP884g=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.21/go.mod h1:YWNWJQNjKigKY1RHVJCuupeWDrrHjRqHm0N9rdrWzYI=
 github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.20.12 h1:Zy6Tme1AA13kX8x3CnkHx5cqdGWGaj/anwOiWGnA0Xo=
 github.com/aws/aws-sdk-go-v2/feature/s3/manager v1.20.12/go.mod h1:ql4uXYKoTM9WUAUSmthY4AtPVrlTBZOvnBJTiCUdPxI=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.20 h1:CNXO7mvgThFGqOFgbNAP2nol2qAWBOGfqR/7tQlvLmc=
-github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.20/go.mod h1:oydPDJKcfMhgfcgBUZaG+toBbwy8yPWubJXBVERtI4o=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.20 h1:tN6W/hg+pkM+tf9XDkWUbDEjGLb+raoBMFsTodcoYKw=
-github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.20/go.mod h1:YJ898MhD067hSHA6xYCx5ts/jEd8BSOLtQDL3iZsvbc=
-github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 h1:WKuaxf++XKWlHWu9ECbMlha8WOEGm0OUEZqm4K/Gcfk=
-github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4/go.mod h1:ZWy7j6v1vWGmPReu0iSGvRiise4YI5SkR3OHKTZ6Wuc=
-github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17 h1:JqcdRG//czea7Ppjb+g/n4o8i/R50aTBHkA7vu0lK+k=
-github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.17/go.mod h1:CO+WeGmIdj/MlPel2KwID9Gt7CNq4M65HUfBW97liM0=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21 h1:Rgg6wvjjtX8bNHcvi9OnXWwcE0a2vGpbwmtICOsvcf4=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.21/go.mod h1:A/kJFst/nm//cyqonihbdpQZwiUhhzpqTsdbhDdRF9c=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21 h1:PEgGVtPoB6NTpPrBgqSE5hE/o47Ij9qk/SEZFbUOe9A=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.21/go.mod h1:p+hz+PRAYlY3zcpJhPwXlLC4C+kqn70WIHwnzAfs6ps=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 h1:qYQ4pzQ2Oz6WpQ8T3HvGHnZydA72MnLuFK9tJwmrbHw=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6/go.mod h1:O3h0IK87yXci+kg6flUKzJnWeziQUKciKrLjcatSNcY=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22 h1:rWyie/PxDRIdhNf4DzRk0lvjVOqFJuNnO8WwaIRVxzQ=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.22/go.mod h1:zd/JsJ4P7oGfUhXn1VyLqaRZwPmZwg44Jf2dS84Dm3Y=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 h1:5EniKhLZe4xzL7a+fU3C2tfUN4nWIqlLesfrjkuPFTY=
 github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7/go.mod h1:x0nZssQ3qZSnIcePWLvcoFisRXJzcTVvYpAAdYX8+GI=
-github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8 h1:Z5EiPIzXKewUQK0QTMkutjiaPVeVYXX7KIqhXu/0fXs=
-github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.8/go.mod h1:FsTpJtvC4U1fyDXk7c71XoDv3HlRm8V3NiYLeYLh5YE=
-github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.20 h1:2HvVAIq+YqgGotK6EkMf+KIEqTISmTYh5zLpYyeTo1Y=
-github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.20/go.mod h1:V4X406Y666khGa8ghKmphma/7C0DAtEQYhkq9z4vpbk=
-github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17 h1:bGeHBsGZx0Dvu/eJC0Lh9adJa3M1xREcndxLNZlve2U=
-github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.17/go.mod h1:dcW24lbU0CzHusTE8LLHhRLI42ejmINN8Lcr22bwh/g=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0 h1:oeu8VPlOre74lBA/PMhxa5vewaMIMmILM+RraSyB8KA=
-github.com/aws/aws-sdk-go-v2/service/s3 v1.96.0/go.mod h1:5jggDlZ2CLQhwJBiZJb4vfk4f0GxWdEDruWKEJ1xOdo=
-github.com/aws/aws-sdk-go-v2/service/signin v1.0.8 h1:0GFOLzEbOyZABS3PhYfBIx2rNBACYcKty+XGkTgw1ow=
-github.com/aws/aws-sdk-go-v2/service/signin v1.0.8/go.mod h1:LXypKvk85AROkKhOG6/YEcHFPoX+prKTowKnVdcaIxE=
-github.com/aws/aws-sdk-go-v2/service/sso v1.30.13 h1:kiIDLZ005EcKomYYITtfsjn7dtOwHDOFy7IbPXKek2o=
-github.com/aws/aws-sdk-go-v2/service/sso v1.30.13/go.mod h1:2h/xGEowcW/g38g06g3KpRWDlT+OTfxxI0o1KqayAB8=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.17 h1:jzKAXIlhZhJbnYwHbvUQZEB8KfgAEuG0dc08Bkda7NU=
-github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.17/go.mod h1:Al9fFsXjv4KfbzQHGe6V4NZSZQXecFcvaIF4e70FoRA=
-github.com/aws/aws-sdk-go-v2/service/sts v1.41.9 h1:Cng+OOwCHmFljXIxpEVXAGMnBia8MSU6Ch5i9PgBkcU=
-github.com/aws/aws-sdk-go-v2/service/sts v1.41.9/go.mod h1:LrlIndBDdjA/EeXeyNBle+gyCwTlizzW5ycgWnvIxkk=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13 h1:JRaIgADQS/U6uXDqlPiefP32yXTda7Kqfx+LgspooZM=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.13/go.mod h1:CEuVn5WqOMilYl+tbccq8+N2ieCy0gVn3OtRb0vBNNM=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 h1:c31//R3xgIJMSC8S6hEVq+38DcvUlgFY0FM6mSI5oto=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21/go.mod h1:r6+pf23ouCB718FUxaqzZdbpYFyDtehyZcmP5KL9FkA=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21 h1:ZlvrNcHSFFWURB8avufQq9gFsheUgjVD9536obIknfM=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.21/go.mod h1:cv3TNhVrssKR0O/xxLJVRfd2oazSnZnkUeTf6ctUwfQ=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0 h1:foqo/ocQ7WqKwy3FojGtZQJo0FR4vto9qnz9VaumbCo=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.98.0/go.mod h1:uoA43SdFwacedBfSgfFSjjCvYe8aYBS7EnU5GZ/YKMM=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.9 h1:QKZH0S178gCmFEgst8hN0mCX1KxLgHBKKY/CLqwP8lg=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.9/go.mod h1:7yuQJoT+OoH8aqIxw9vwF+8KpvLZ8AWmvmUWHsGQZvI=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.15 h1:lFd1+ZSEYJZYvv9d6kXzhkZu07si3f+GQ1AaYwa2LUM=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.15/go.mod h1:WSvS1NLr7JaPunCXqpJnWk1Bjo7IxzZXrZi1QQCkuqM=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19 h1:dzztQ1YmfPrxdrOiuZRMF6fuOwWlWpD2StNLTceKpys=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.19/go.mod h1:YO8TrYtFdl5w/4vmjL8zaBSsiNp3w0L1FfKVKenZT7w=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.10 h1:p8ogvvLugcR/zLBXTXrTkj0RYBUdErbMnAFFp12Lm/U=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.10/go.mod h1:60dv0eZJfeVXfbT1tFJinbHrDfSJ2GZl4Q//OSSNAVw=
 github.com/aws/smithy-go v1.24.2 h1:FzA3bu/nt/vDvmnkg+R8Xl46gmzEDam6mZ1hzmwXFng=
 github.com/aws/smithy-go v1.24.2/go.mod h1:YE2RhdIuDbA5E5bTdciG9KrW3+TiEONeUWCqxX9i1Fc=
 github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=
@@ -284,8 +284,8 @@ github.com/go-git/go-billy/v5 v5.6.2/go.mod h1:rcFC2rAsp/erv7CMz9GczHcuD0D32fWzH
 github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
-github.com/go-jose/go-jose/v4 v4.1.3 h1:CVLmWDhDVRa6Mi/IgCgaopNosCaHz7zrMeF9MlZRkrs=
-github.com/go-jose/go-jose/v4 v4.1.3/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
+github.com/go-jose/go-jose/v4 v4.1.4 h1:moDMcTHmvE6Groj34emNPLs/qtYXRVcd6S7NHbHz3kA=
+github.com/go-jose/go-jose/v4 v4.1.4/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
 github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
 github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
@@ -385,12 +385,12 @@ github.com/google/s2a-go v0.1.9 h1:LGD7gtMgezd8a/Xak7mEWL0PjoTQFvpRudN895yqKW0=
 github.com/google/s2a-go v0.1.9/go.mod h1:YA0Ei2ZQL3acow2O62kdp9UlnvMmU7kA6Eutn0dXayM=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/googleapis/enterprise-certificate-proxy v0.3.11 h1:vAe81Msw+8tKUxi2Dqh/NZMz7475yUvmRIkXr4oN2ao=
-github.com/googleapis/enterprise-certificate-proxy v0.3.11/go.mod h1:RFV7MUdlb7AgEq2v7FmMCfeSMCllAzWxFgRdusoGks8=
+github.com/googleapis/enterprise-certificate-proxy v0.3.14 h1:yh8ncqsbUY4shRD5dA6RlzjJaT4hi3kII+zYw8wmLb8=
+github.com/googleapis/enterprise-certificate-proxy v0.3.14/go.mod h1:vqVt9yG9480NtzREnTlmGSBmFrA+bzb0yl0TxoBQXOg=
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
-github.com/googleapis/gax-go/v2 v2.17.0 h1:RksgfBpxqff0EZkDWYuz9q/uWsTVz+kf43LsZ1J6SMc=
-github.com/googleapis/gax-go/v2 v2.17.0/go.mod h1:mzaqghpQp4JDh3HvADwrat+6M3MOIDp5YKHhb9PAgDY=
+github.com/googleapis/gax-go/v2 v2.19.0 h1:fYQaUOiGwll0cGj7jmHT/0nPlcrZDFPrZRhTsoCr8hE=
+github.com/googleapis/gax-go/v2 v2.19.0/go.mod h1:w2ROXVdfGEVFXzmlciUU4EdjHgWvB5h2n6x/8XSTTJA=
 github.com/gopherjs/gopherjs v1.17.2 h1:fQnZVsXk8uxXIStYb0N4bGk7jeyTalG/wsZjQ25dO0g=
 github.com/gopherjs/gopherjs v1.17.2/go.mod h1:pRRIvn/QzFLrKfvEz3qUuEhtE/zLCWfreZ6J5gM2i+k=
 github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
@@ -600,8 +600,6 @@ github.com/rdleal/intervalst v1.5.0 h1:SEB9bCFz5IqD1yhfH1Wv8IBnY/JQxDplwkxHjT6ha
 github.com/rdleal/intervalst v1.5.0/go.mod h1:xO89Z6BC+LQDH+IPQQw/OESt5UADgFD41tYMUINGpxQ=
 github.com/relvacode/iso8601 v1.7.0 h1:BXy+V60stMP6cpswc+a93Mq3e65PfXCgDFfhvNNGrdo=
 github.com/relvacode/iso8601 v1.7.0/go.mod h1:FlNp+jz+TXpyRqgmM7tnzHHzBnz776kmAH2h3sZCn0I=
-github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
-github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/rfjakob/eme v1.1.2 h1:SxziR8msSOElPayZNFfQw4Tjx/Sbaeeh3eRvrHVMUs4=
 github.com/rfjakob/eme v1.1.2/go.mod h1:cVvpasglm/G3ngEfcfT/Wt0GwhkuO32pf/poW6Nyk1k=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
@@ -707,8 +705,8 @@ github.com/xanzy/ssh-agent v0.3.3 h1:+/15pJfg/RsTxqYcX6fHqOXZwwMP+2VyYWJeWM2qQFM
 github.com/xanzy/ssh-agent v0.3.3/go.mod h1:6dzNDKs0J9rVPHPhaGCukekBHKqfl+L3KghI1Bc68Uw=
 github.com/xdg-go/pbkdf2 v1.0.0 h1:Su7DPu48wXMwC3bs7MCNG+z4FhcyEuz5dlvchbq0B0c=
 github.com/xdg-go/pbkdf2 v1.0.0/go.mod h1:jrpuAogTd400dnrH08LKmI/xc1MbPOebTwRqcT5RDeI=
-github.com/xdg-go/scram v1.1.2 h1:FHX5I5B4i4hKRVRBCFRxq1iQRej7WO3hhBuJf+UUySY=
-github.com/xdg-go/scram v1.1.2/go.mod h1:RT/sEzTbU5y00aCK8UOx6R7YryM0iF1N2MOmC3kKLN4=
+github.com/xdg-go/scram v1.2.0 h1:bYKF2AEwG5rqd1BumT4gAnvwU/M9nBp2pTSxeZw7Wvs=
+github.com/xdg-go/scram v1.2.0/go.mod h1:3dlrS0iBaWKYVt2ZfA4cj48umJZ+cAEbR6/SjLA88I8=
 github.com/xdg-go/stringprep v1.0.4 h1:XLI/Ng3O1Atzq0oBs3TWm+5ZVgkq2aqdlvP9JtoZ6c8=
 github.com/xdg-go/stringprep v1.0.4/go.mod h1:mPGuuIYwz7CmR2bT9j4GbQqutWS1zV24gijq1dTyGkM=
 github.com/xeipuuv/gojsonpointer v0.0.0-20180127040702-4e3ac2762d5f/go.mod h1:N2zxlSyiKSe5eX1tZViRH5QA0qijqEDrYZiPEAiq3wU=
@@ -754,16 +752,16 @@ go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ
 go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0 h1:RbKq8BG0FI8OiXhBfcRtqqHcZcka+gU3cskNuf05R18=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.63.0/go.mod h1:h06DGIukJOevXaj/xrNjhi/2098RZzcLTbc0jDAUbsg=
-go.opentelemetry.io/otel v1.40.0 h1:oA5YeOcpRTXq6NN7frwmwFR0Cn3RhTVZvXsP4duvCms=
-go.opentelemetry.io/otel v1.40.0/go.mod h1:IMb+uXZUKkMXdPddhwAHm6UfOwJyh4ct1ybIlV14J0g=
-go.opentelemetry.io/otel/metric v1.40.0 h1:rcZe317KPftE2rstWIBitCdVp89A2HqjkxR3c11+p9g=
-go.opentelemetry.io/otel/metric v1.40.0/go.mod h1:ib/crwQH7N3r5kfiBZQbwrTge743UDc7DTFVZrrXnqc=
-go.opentelemetry.io/otel/sdk v1.40.0 h1:KHW/jUzgo6wsPh9At46+h4upjtccTmuZCFAc9OJ71f8=
-go.opentelemetry.io/otel/sdk v1.40.0/go.mod h1:Ph7EFdYvxq72Y8Li9q8KebuYUr2KoeyHx0DRMKrYBUE=
-go.opentelemetry.io/otel/sdk/metric v1.40.0 h1:mtmdVqgQkeRxHgRv4qhyJduP3fYJRMX4AtAlbuWdCYw=
-go.opentelemetry.io/otel/sdk/metric v1.40.0/go.mod h1:4Z2bGMf0KSK3uRjlczMOeMhKU2rhUqdWNoKcYrtcBPg=
-go.opentelemetry.io/otel/trace v1.40.0 h1:WA4etStDttCSYuhwvEa8OP8I5EWu24lkOzp+ZYblVjw=
-go.opentelemetry.io/otel/trace v1.40.0/go.mod h1:zeAhriXecNGP/s2SEG3+Y8X9ujcJOTqQ5RgdEJcawiA=
+go.opentelemetry.io/otel v1.42.0 h1:lSQGzTgVR3+sgJDAU/7/ZMjN9Z+vUip7leaqBKy4sho=
+go.opentelemetry.io/otel v1.42.0/go.mod h1:lJNsdRMxCUIWuMlVJWzecSMuNjE7dOYyWlqOXWkdqCc=
+go.opentelemetry.io/otel/metric v1.42.0 h1:2jXG+3oZLNXEPfNmnpxKDeZsFI5o4J+nz6xUlaFdF/4=
+go.opentelemetry.io/otel/metric v1.42.0/go.mod h1:RlUN/7vTU7Ao/diDkEpQpnz3/92J9ko05BIwxYa2SSI=
+go.opentelemetry.io/otel/sdk v1.42.0 h1:LyC8+jqk6UJwdrI/8VydAq/hvkFKNHZVIWuslJXYsDo=
+go.opentelemetry.io/otel/sdk v1.42.0/go.mod h1:rGHCAxd9DAph0joO4W6OPwxjNTYWghRWmkHuGbayMts=
+go.opentelemetry.io/otel/sdk/metric v1.42.0 h1:D/1QR46Clz6ajyZ3G8SgNlTJKBdGp84q9RKCAZ3YGuA=
+go.opentelemetry.io/otel/sdk/metric v1.42.0/go.mod h1:Ua6AAlDKdZ7tdvaQKfSmnFTdHx37+J4ba8MwVCYM5hc=
+go.opentelemetry.io/otel/trace v1.42.0 h1:OUCgIPt+mzOnaUTpOQcBiM/PLQ/Op7oq6g4LenLmOYY=
+go.opentelemetry.io/otel/trace v1.42.0/go.mod h1:f3K9S+IFqnumBkKhRJMeaZeNk9epyhnCmQh/EysQCdc=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0=
@@ -869,8 +867,8 @@ golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
 golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
 golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
 golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
-golang.org/x/net v0.51.0 h1:94R/GTO7mt3/4wIKpcR5gkGmRLOuE/2hNGeWq/GBIFo=
-golang.org/x/net v0.51.0/go.mod h1:aamm+2QF5ogm02fjy5Bb7CQ0WMt1/WVM7FtyaTLlA9Y=
+golang.org/x/net v0.52.0 h1:He/TN1l0e4mmR3QqHMT2Xab3Aj3L9qjbhRm78/6jrW0=
+golang.org/x/net v0.52.0/go.mod h1:R1MAz7uMZxVMualyPXb+VaqGSa3LIaUqk0eEt3w36Sw=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -981,8 +979,8 @@ golang.org/x/text v0.35.0/go.mod h1:khi/HExzZJ2pGnjenulevKNX1W67CUy0AsXcNubPGCA=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
-golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
+golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
+golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -1054,8 +1052,8 @@ google.golang.org/api v0.24.0/go.mod h1:lIXQywCXRcnZPGlsd8NbLnOjtAoL6em04bJ9+z0M
 google.golang.org/api v0.28.0/go.mod h1:lIXQywCXRcnZPGlsd8NbLnOjtAoL6em04bJ9+z0MncE=
 google.golang.org/api v0.29.0/go.mod h1:Lcubydp8VUV7KeIHD9z2Bys/sm/vGKnG1UHuDBSrHWM=
 google.golang.org/api v0.30.0/go.mod h1:QGmEvQ87FHZNiUVJkT14jQNYJ4ZJjdRF23ZXz5138Fc=
-google.golang.org/api v0.267.0 h1:w+vfWPMPYeRs8qH1aYYsFX68jMls5acWl/jocfLomwE=
-google.golang.org/api v0.267.0/go.mod h1:Jzc0+ZfLnyvXma3UtaTl023TdhZu6OMBP9tJ+0EmFD0=
+google.golang.org/api v0.274.0 h1:aYhycS5QQCwxHLwfEHRRLf9yNsfvp1JadKKWBE54RFA=
+google.golang.org/api v0.274.0/go.mod h1:JbAt7mF+XVmWu6xNP8/+CTiGH30ofmCmk9nM8d8fHew=
 google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
 google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
 google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
@@ -1091,12 +1089,12 @@ google.golang.org/genproto v0.0.0-20200618031413-b414f8b61790/go.mod h1:jDfRM7Fc
 google.golang.org/genproto v0.0.0-20200729003335-053ba62fc06f/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200804131852-c06518451d9c/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
 google.golang.org/genproto v0.0.0-20200825200019-8632dd797987/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
-google.golang.org/genproto v0.0.0-20260128011058-8636f8732409 h1:VQZ/yAbAtjkHgH80teYd2em3xtIkkHd7ZhqfH2N9CsM=
-google.golang.org/genproto v0.0.0-20260128011058-8636f8732409/go.mod h1:rxKD3IEILWEu3P44seeNOAwZN4SaoKaQ/2eTg4mM6EM=
-google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20 h1:7ei4lp52gK1uSejlA8AZl5AJjeLUOHBQscRQZUgAcu0=
-google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20/go.mod h1:ZdbssH/1SOVnjnDlXzxDHK2MCidiqXtbYccJNzNYPEE=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20 h1:Jr5R2J6F6qWyzINc+4AM8t5pfUz6beZpHp678GNrMbE=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20260203192932-546029d2fa20/go.mod h1:j9x/tPzZkyxcgEFkiKEEGxfvyumM01BEtsW8xzOahRQ=
+google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5 h1:JNfk58HZ8lfmXbYK2vx/UvsqIL59TzByCxPIX4TDmsE=
+google.golang.org/genproto v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:x5julN69+ED4PcFk/XWayw35O0lf/nGa4aNgODCmNmw=
+google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5 h1:CogIeEXn4qWYzzQU0QqvYBM8yDF9cFYzDq9ojSpv0Js=
+google.golang.org/genproto/googleapis/api v0.0.0-20260316180232-0b37fe3546d5/go.mod h1:EIQZ5bFCfRQDV4MhRle7+OgjNtZ6P1PiZBgAKuxXu/Y=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7 h1:ndE4FoJqsIceKP2oYSnUZqhTdYufCYYkqwtFzfrhI7w=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20260319201613-d00831a3d3e7/go.mod h1:4Hqkh8ycfw05ld/3BWL7rJOSfebL2Q+DVDeRgYgxUU8=
 google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
 google.golang.org/grpc v1.20.1/go.mod h1:10oTOabMzJvdu6/UiuZezV6QK5dSlG84ov/aaiqXj38=
 google.golang.org/grpc v1.21.1/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=
@@ -1154,8 +1152,6 @@ honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWh
 honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
 honnef.co/go/tools v0.0.1-2020.1.3/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
 honnef.co/go/tools v0.0.1-2020.1.4/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
-modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU=
-modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg=
 moul.io/http2curl/v2 v2.3.0 h1:9r3JfDzWPcbIklMOs2TnIFzDYvfAZvjeavG6EzP7jYs=
 moul.io/http2curl/v2 v2.3.0/go.mod h1:RW4hyBjTWSYDOxapodpNEtX0g5Eb16sxklBqmd2RHcE=
 rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=

test/multi_master/cluster.go

@@ -6,7 +6,6 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"os"
 	"os/exec"
@@ -17,6 +16,8 @@ import (
 	"sync"
 	"testing"
 	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 const (
@@ -73,23 +74,23 @@ func StartMasterCluster(t testing.TB) *MasterCluster {
 	logsDir := filepath.Join(baseDir, "logs")
 	os.MkdirAll(logsDir, 0o755)
 
-	// Allocate 3 port pairs (http, grpc) atomically to prevent reuse.
-	portPairs, err := allocateMultipleMasterPortPairs(3)
+	// Allocate 3 mini-safe ports (each guarantees port+10000 is also free).
+	httpPorts, err := testutil.AllocateMiniPorts(3)
 	if err != nil {
 		t.Fatalf("allocate ports: %v", err)
 	}
 	var nodes [3]*masterNode
 	var peerParts []string
-	for i, pp := range portPairs {
+	for i, hp := range httpPorts {
 		dataDir := filepath.Join(baseDir, fmt.Sprintf("m%d", i))
 		os.MkdirAll(dataDir, 0o755)
 		nodes[i] = &masterNode{
-			port:     pp[0],
-			grpcPort: pp[1],
+			port:     hp,
+			grpcPort: hp + testutil.GrpcPortOffset,
 			dataDir:  dataDir,
 			logFile:  filepath.Join(logsDir, fmt.Sprintf("master%d.log", i)),
 		}
-		peerParts = append(peerParts, fmt.Sprintf("127.0.0.1:%d", pp[0]))
+		peerParts = append(peerParts, fmt.Sprintf("127.0.0.1:%d", hp))
 	}
 
 	mc := &MasterCluster{
@@ -357,41 +358,6 @@ func (mc *MasterCluster) tailLog(i int) string {
 	return strings.Join(lines, "\n")
 }
 
-// --- port and binary helpers (adapted from test/volume_server/framework) ---
-
-// allocateMultipleMasterPortPairs finds n non-overlapping (http, grpc) port
-// pairs, holding all listeners until all are found, then releasing them
-// together to avoid races between consecutive allocations.
-func allocateMultipleMasterPortPairs(n int) ([][2]int, error) {
-	var listeners []net.Listener
-	var pairs [][2]int
-
-	defer func() {
-		for _, l := range listeners {
-			l.Close()
-		}
-	}()
-
-	for masterPort := 10000; masterPort <= 55535 && len(pairs) < n; masterPort++ {
-		grpcPort := masterPort + 10000
-		l1, err := net.Listen("tcp", net.JoinHostPort("127.0.0.1", strconv.Itoa(masterPort)))
-		if err != nil {
-			continue
-		}
-		l2, err := net.Listen("tcp", net.JoinHostPort("127.0.0.1", strconv.Itoa(grpcPort)))
-		if err != nil {
-			l1.Close()
-			continue
-		}
-		listeners = append(listeners, l1, l2)
-		pairs = append(pairs, [2]int{masterPort, grpcPort})
-	}
-
-	if len(pairs) < n {
-		return nil, fmt.Errorf("could only allocate %d of %d master port pairs", len(pairs), n)
-	}
-	return pairs, nil
-}
 
 func findOrBuildWeedBinary() (string, error) {
 	if fromEnv := os.Getenv("WEED_BINARY"); fromEnv != "" {

test/pjdfstest/Dockerfile

@@ -0,0 +1,28 @@
+FROM chrislusf/seaweedfs:e2e
+
+RUN apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -y \
+    --no-install-recommends \
+    --no-install-suggests \
+    autoconf \
+    automake \
+    build-essential \
+    git \
+    libtap-harness-archive-perl \
+    perl \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+ARG PJDFSTEST_REPO=https://github.com/pjd/pjdfstest.git
+ARG PJDFSTEST_REF=03eb25706d8dbf3611c3f820b45b7a5e09a36c06
+
+RUN git clone "${PJDFSTEST_REPO}" /opt/pjdfstest && \
+    cd /opt/pjdfstest && \
+    git checkout "${PJDFSTEST_REF}" && \
+    autoreconf -ifs && \
+    ./configure && \
+    make pjdfstest
+
+COPY run_inside_container.sh /run.sh
+COPY known_failures.txt /known_failures.txt
+RUN chmod +x /run.sh

test/pjdfstest/docker-compose.yml

@@ -0,0 +1,57 @@
+services:
+  master:
+    image: chrislusf/seaweedfs:e2e
+    command: "-v=4 master -ip=master -ip.bind=0.0.0.0 -raftBootstrap"
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "-I", "http://localhost:9333/cluster/healthz"]
+      interval: 2s
+      timeout: 10s
+      retries: 30
+      start_period: 10s
+
+  volume:
+    image: chrislusf/seaweedfs:e2e
+    command: "-v=4 volume -master=master:9333 -ip=volume -ip.bind=0.0.0.0 -preStopSeconds=1"
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "-I", "http://localhost:8080/healthz"]
+      interval: 2s
+      timeout: 10s
+      retries: 15
+      start_period: 5s
+    depends_on:
+      master:
+        condition: service_healthy
+
+  filer:
+    image: chrislusf/seaweedfs:e2e
+    command: "-v=4 filer -master=master:9333 -ip=filer -ip.bind=0.0.0.0"
+    healthcheck:
+      test: ["CMD", "curl", "--fail", "-I", "http://localhost:8888/healthz"]
+      interval: 2s
+      timeout: 10s
+      retries: 15
+      start_period: 5s
+    depends_on:
+      volume:
+        condition: service_healthy
+
+  mount:
+    image: chrislusf/seaweedfs:pjdfstest
+    build:
+      context: .
+    command: "-v=4 mount -filer=filer:8888 -filer.path=/ -dirAutoCreate -dir=/mnt/seaweedfs -allowOthers"
+    cap_add:
+      - SYS_ADMIN
+    devices:
+      - /dev/fuse
+    security_opt:
+      - apparmor:unconfined
+    healthcheck:
+      test: ["CMD", "mountpoint", "-q", "--", "/mnt/seaweedfs"]
+      interval: 2s
+      timeout: 10s
+      retries: 15
+      start_period: 10s
+    depends_on:
+      filer:
+        condition: service_healthy

test/pjdfstest/known_failures.txt

@@ -0,0 +1,60 @@
+# Known pjdfstest failures for SeaweedFS FUSE mount.
+#
+# Tests listed here are skipped during CI runs. Each entry must be a path
+# relative to the pjdfstest root (e.g. tests/chmod/02.t).
+#
+# A failure in any test NOT listed here will cause the CI job to fail,
+# catching regressions immediately.
+
+# ── Linux FUSE NAME_MAX=255 limitation ──────────────────────────────────
+# The Linux FUSE kernel module enforces NAME_MAX=255 at the VFS layer.
+# These tests create filenames >255 bytes which cannot be looked up via
+# normal syscalls (stat, chmod, etc.) after creation.
+tests/chmod/02.t
+tests/chmod/03.t
+tests/chown/02.t
+tests/chown/03.t
+tests/ftruncate/02.t
+tests/ftruncate/03.t
+tests/link/02.t
+tests/link/03.t
+tests/mkdir/02.t
+tests/mkdir/03.t
+tests/mkfifo/02.t
+tests/mkfifo/03.t
+tests/mknod/02.t
+tests/mknod/03.t
+tests/open/02.t
+tests/open/03.t
+tests/rename/01.t
+tests/rename/02.t
+tests/rmdir/02.t
+tests/rmdir/03.t
+tests/symlink/02.t
+tests/symlink/03.t
+tests/truncate/02.t
+tests/truncate/03.t
+tests/unlink/02.t
+tests/unlink/03.t
+
+# ── Hard link nlink/ctime tracking (requires filer changes) ────────────
+# nlink counts are not correctly maintained across rename operations.
+tests/rename/23.t
+tests/rename/24.t
+
+# ── Parent directory mtime/ctime on deferred file create ───────────────
+# When file creation is deferred (not flushed to filer immediately),
+# the parent directory mtime/ctime cannot be updated without invalidating
+# the just-cached child entry in the metadata cache.
+tests/open/00.t
+
+# ── Directory rename permission edge case ──────────────────────────────
+# Cross-directory rename of a subdirectory with restricted permissions
+# causes cascading test failures within the test file.
+tests/rename/21.t
+
+# ── rmdir after hard link unlink ───────────────────────────────────────
+# The filer may still report a directory as non-empty after all hard-linked
+# entries have been unlinked.
+tests/unlink/14.t
+

test/pjdfstest/run.sh

@@ -0,0 +1,173 @@
+#!/usr/bin/env bash
+#
+# Run the pjdfstest POSIX compliance suite against a SeaweedFS FUSE mount.
+#
+# This script:
+#   1. Starts a self-contained "weed mini" server (master+volume+filer in one)
+#   2. Mounts the filesystem with "weed mount"
+#   3. Builds pjdfstest from upstream and runs it under prove(1)
+#
+# Requirements: weed in $PATH, fusermount3, perl with TAP::Harness::Archive,
+# autoconf, make, sudo (pjdfstest exercises chown/chmod which need root).
+#
+# Usage:
+#   test/pjdfstest/run.sh                # runs full suite
+#   PJDFSTEST_TESTS=tests/chmod ./run.sh # runs a subset
+
+set -euo pipefail
+
+WEED_BIN="${WEED_BIN:-weed}"
+WORK_DIR="${WORK_DIR:-$(mktemp -d /tmp/seaweedfs-pjdfstest.XXXXXX)}"
+MOUNT_DIR="${MOUNT_DIR:-${WORK_DIR}/mnt}"
+DATA_DIR="${DATA_DIR:-${WORK_DIR}/data}"
+LOG_DIR="${LOG_DIR:-${WORK_DIR}/logs}"
+FILER_PORT="${FILER_PORT:-28888}"
+FILER_ADDR="127.0.0.1:${FILER_PORT}"
+
+# Pin to an immutable upstream commit so CI is reproducible. Override via env
+# if you want to test against a different ref or fork.
+PJDFSTEST_REPO="${PJDFSTEST_REPO:-https://github.com/pjd/pjdfstest.git}"
+PJDFSTEST_REF="${PJDFSTEST_REF:-03eb25706d8dbf3611c3f820b45b7a5e09a36c06}"
+PJDFSTEST_TESTS="${PJDFSTEST_TESTS:-tests/}"
+
+mini_pid=""
+mount_pid=""
+
+CI_LOG_DIR="/tmp/seaweedfs-pjdfstest-logs"
+
+cleanup() {
+  set +e
+  if [[ -n "${mount_pid}" ]] && kill -0 "${mount_pid}" 2>/dev/null; then
+    kill -TERM "${mount_pid}" 2>/dev/null || true
+    wait "${mount_pid}" 2>/dev/null || true
+  fi
+  if mountpoint -q "${MOUNT_DIR}" 2>/dev/null; then
+    fusermount3 -u "${MOUNT_DIR}" 2>/dev/null || \
+      fusermount -u "${MOUNT_DIR}" 2>/dev/null || \
+      sudo umount "${MOUNT_DIR}" 2>/dev/null || true
+  fi
+  if [[ -n "${mini_pid}" ]] && kill -0 "${mini_pid}" 2>/dev/null; then
+    kill -TERM "${mini_pid}" 2>/dev/null || true
+    wait "${mini_pid}" 2>/dev/null || true
+  fi
+  # Copy logs to a fixed path for CI artifact upload.
+  mkdir -p "${CI_LOG_DIR}"
+  cp "${LOG_DIR}"/*.log "${CI_LOG_DIR}/" 2>/dev/null || true
+}
+trap cleanup EXIT INT TERM
+
+mkdir -p "${MOUNT_DIR}" "${DATA_DIR}" "${LOG_DIR}"
+
+echo "==> Starting weed mini on ${FILER_ADDR}"
+"${WEED_BIN}" mini \
+  -dir="${DATA_DIR}" \
+  -ip=127.0.0.1 \
+  -filer.port="${FILER_PORT}" \
+  -s3=false \
+  -webdav=false \
+  -admin.ui=false \
+  >"${LOG_DIR}/mini.log" 2>&1 &
+mini_pid=$!
+
+# Wait for filer to accept connections.
+for i in $(seq 1 60); do
+  if (echo > "/dev/tcp/127.0.0.1/${FILER_PORT}") 2>/dev/null; then
+    break
+  fi
+  if ! kill -0 "${mini_pid}" 2>/dev/null; then
+    echo "weed mini exited early; log tail:" >&2
+    tail -n 100 "${LOG_DIR}/mini.log" >&2 || true
+    exit 1
+  fi
+  sleep 0.5
+done
+
+if ! (echo > "/dev/tcp/127.0.0.1/${FILER_PORT}") 2>/dev/null; then
+  echo "weed mini filer did not become reachable within 30s; log tail:" >&2
+  tail -n 100 "${LOG_DIR}/mini.log" >&2 || true
+  exit 1
+fi
+
+echo "==> Mounting SeaweedFS at ${MOUNT_DIR}"
+# allowOthers is required so that pjdfstest's setuid/setgid sub-tests (run via
+# sudo) can access files created as the invoking user.
+sudo "${WEED_BIN}" mount \
+  -filer="${FILER_ADDR}" \
+  -dir="${MOUNT_DIR}" \
+  -filer.path=/ \
+  -dirAutoCreate \
+  -allowOthers=true \
+  >"${LOG_DIR}/mount.log" 2>&1 &
+mount_pid=$!
+
+for i in $(seq 1 60); do
+  if mountpoint -q "${MOUNT_DIR}"; then
+    break
+  fi
+  if ! kill -0 "${mount_pid}" 2>/dev/null; then
+    echo "weed mount exited early; log tail:" >&2
+    tail -n 100 "${LOG_DIR}/mount.log" >&2 || true
+    exit 1
+  fi
+  sleep 0.5
+done
+
+if ! mountpoint -q "${MOUNT_DIR}"; then
+  echo "FUSE mount did not come up within 30s" >&2
+  tail -n 100 "${LOG_DIR}/mount.log" >&2 || true
+  exit 1
+fi
+
+echo "==> Cloning and building pjdfstest"
+PJDFSTEST_DIR="${WORK_DIR}/pjdfstest"
+if [[ ! -d "${PJDFSTEST_DIR}/.git" ]]; then
+  git clone "${PJDFSTEST_REPO}" "${PJDFSTEST_DIR}"
+fi
+git -C "${PJDFSTEST_DIR}" remote set-url origin "${PJDFSTEST_REPO}"
+git -C "${PJDFSTEST_DIR}" fetch --depth 1 origin "${PJDFSTEST_REF}"
+git -C "${PJDFSTEST_DIR}" checkout --detach FETCH_HEAD
+(
+  cd "${PJDFSTEST_DIR}"
+  autoreconf -ifs
+  ./configure
+  make pjdfstest
+)
+
+# pjdfstest must run inside the filesystem under test.
+TEST_ROOT="${MOUNT_DIR}/pjdfstest-root"
+sudo mkdir -p "${TEST_ROOT}"
+sudo cp -r "${PJDFSTEST_DIR}/." "${TEST_ROOT}/"
+
+cd "${TEST_ROOT}"
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+KNOWN_FAILURES="${SCRIPT_DIR}/known_failures.txt"
+
+# Build the list of tests to run, excluding known failures.
+if [[ -f "${KNOWN_FAILURES}" ]] && [[ "${PJDFSTEST_TESTS}" == "tests/" ]]; then
+  mapfile -t skip < <(grep -v '^#' "${KNOWN_FAILURES}" | grep -v '^$')
+  all_tests=()
+  while IFS= read -r -d '' t; do
+    all_tests+=("$t")
+  done < <(find tests/ -name '*.t' -print0 | sort -z)
+
+  run_tests=()
+  for t in "${all_tests[@]}"; do
+    is_skipped=false
+    for s in "${skip[@]}"; do
+      if [[ "$t" == "$s" ]]; then
+        is_skipped=true
+        break
+      fi
+    done
+    if ! $is_skipped; then
+      run_tests+=("$t")
+    fi
+  done
+
+  echo "==> Running pjdfstest (${#run_tests[@]} tests, ${#skip[@]} skipped)"
+  sudo prove -rv "${run_tests[@]}"
+else
+  echo "==> Running pjdfstest (${PJDFSTEST_TESTS})"
+  sudo prove -rv "${PJDFSTEST_TESTS}"
+fi

test/pjdfstest/run_inside_container.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+#
+# Runs pjdfstest inside the mount container against /mnt/seaweedfs.
+# Invoked via: docker compose exec mount /run.sh
+#
+# Uses known_failures.txt to skip tests with known issues. Any failure
+# in a test NOT in the skip list causes a non-zero exit (regression).
+set -euo pipefail
+
+MOUNT_DIR="/mnt/seaweedfs"
+PJDFSTEST_TESTS="${PJDFSTEST_TESTS:-tests/}"
+KNOWN_FAILURES="/known_failures.txt"
+
+# Copy pjdfstest into the mounted filesystem so tests exercise the FS under test.
+TEST_ROOT="${MOUNT_DIR}/pjdfstest-root"
+mkdir -p "${TEST_ROOT}"
+cp -r /opt/pjdfstest/. "${TEST_ROOT}/"
+
+cd "${TEST_ROOT}"
+
+# Build the list of tests to run, excluding known failures.
+if [[ -f "${KNOWN_FAILURES}" ]] && [[ "${PJDFSTEST_TESTS}" == "tests/" ]]; then
+  mapfile -t skip < <(grep -v '^#' "${KNOWN_FAILURES}" | grep -v '^$')
+  all_tests=()
+  while IFS= read -r -d '' t; do
+    all_tests+=("$t")
+  done < <(find tests/ -name '*.t' -print0 | sort -z)
+
+  run_tests=()
+  for t in "${all_tests[@]}"; do
+    is_skipped=false
+    for s in "${skip[@]}"; do
+      if [[ "$t" == "$s" ]]; then
+        is_skipped=true
+        break
+      fi
+    done
+    if ! $is_skipped; then
+      run_tests+=("$t")
+    fi
+  done
+
+  echo "==> Running pjdfstest (${#run_tests[@]} tests, ${#skip[@]} skipped)"
+  prove -rv "${run_tests[@]}"
+else
+  echo "==> Running pjdfstest (${PJDFSTEST_TESTS})"
+  prove -rv "${PJDFSTEST_TESTS}"
+fi

test/plugin_workers/volume_fixtures.go

@@ -7,6 +7,7 @@ import (
 	"path/filepath"
 	"testing"
 
+	"github.com/seaweedfs/seaweedfs/weed/storage/needle"
 	"github.com/seaweedfs/seaweedfs/weed/storage/types"
 )
 
@@ -21,7 +22,12 @@ func WriteTestVolumeFiles(t *testing.T, baseDir string, volumeID uint32, datSize
 	datPath := filepath.Join(baseDir, volumeFilename(volumeID, ".dat"))
 	idxPath := filepath.Join(baseDir, volumeFilename(volumeID, ".idx"))
 
-	data := make([]byte, datSize)
+	// The idx entry records the needle's data size. The actual on-disk size
+	// includes header + checksum + timestamp (GetActualSize). The .dat must
+	// be large enough to hold the full needle.
+	needleDataSize := types.Size(datSize)
+	actualSize := needle.GetActualSize(needleDataSize, needle.Version3)
+	data := make([]byte, actualSize)
 	rng := rand.New(rand.NewSource(99))
 	_, _ = rng.Read(data)
 	if err := os.WriteFile(datPath, data, 0644); err != nil {
@@ -35,7 +41,7 @@ func WriteTestVolumeFiles(t *testing.T, baseDir string, volumeID uint32, datSize
 
 	types.NeedleIdToBytes(entry[:idEnd], types.NeedleId(1))
 	types.OffsetToBytes(entry[idEnd:offsetEnd], types.ToOffset(0))
-	types.SizeToBytes(entry[offsetEnd:sizeEnd], types.Size(datSize))
+	types.SizeToBytes(entry[offsetEnd:sizeEnd], needleDataSize)
 
 	if err := os.WriteFile(idxPath, entry, 0644); err != nil {
 		t.Fatalf("write idx file: %v", err)

test/s3/catalog_trino/trino_catalog_test.go

@@ -5,7 +5,6 @@ import (
 	"crypto/rand"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"os"
 	"os/exec"
@@ -13,6 +12,8 @@ import (
 	"strings"
 	"testing"
 	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 type TestEnvironment struct {
@@ -96,29 +97,26 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 		t.Fatalf("Failed to create temp dir: %v", err)
 	}
 
-	bindIP := findBindIP()
+	bindIP := testutil.FindBindIP()
 
-	masterPort, masterGrpcPort := mustFreePortPair(t, "Master")
-	volumePort, volumeGrpcPort := mustFreePortPair(t, "Volume")
-	filerPort, filerGrpcPort := mustFreePortPair(t, "Filer")
-	s3Port, s3GrpcPort := mustFreePortPair(t, "S3")
-	icebergPort := mustFreePort(t, "Iceberg")
+	// 9 ports: master(2), volume(2), filer(2), s3(2), iceberg(1)
+	ports := testutil.MustAllocatePorts(t, 9)
 
 	return &TestEnvironment{
 		seaweedDir:      seaweedDir,
 		weedBinary:      weedBinary,
 		dataDir:         dataDir,
 		bindIP:          bindIP,
-		s3Port:          s3Port,
-		s3GrpcPort:      s3GrpcPort,
-		icebergPort:     icebergPort,
-		masterPort:      masterPort,
-		masterGrpcPort:  masterGrpcPort,
-		filerPort:       filerPort,
-		filerGrpcPort:   filerGrpcPort,
-		volumePort:      volumePort,
-		volumeGrpcPort:  volumeGrpcPort,
-		dockerAvailable: hasDocker(),
+		masterPort:      ports[0],
+		masterGrpcPort:  ports[1],
+		volumePort:      ports[2],
+		volumeGrpcPort:  ports[3],
+		filerPort:       ports[4],
+		filerGrpcPort:   ports[5],
+		s3Port:          ports[6],
+		s3GrpcPort:      ports[7],
+		icebergPort:     ports[8],
+		dockerAvailable: testutil.HasDocker(),
 	}
 }
 
@@ -333,73 +331,6 @@ func createObjectBucket(t *testing.T, env *TestEnvironment, bucketName string) {
 	}
 }
 
-func hasDocker() bool {
-	cmd := exec.Command("docker", "version")
-	return cmd.Run() == nil
-}
-
-func mustFreePort(t *testing.T, name string) int {
-	t.Helper()
-
-	port, err := getFreePort()
-	if err != nil {
-		t.Fatalf("Failed to get free port for %s: %v", name, err)
-	}
-	return port
-}
-
-func mustFreePortPair(t *testing.T, name string) (int, int) {
-	t.Helper()
-
-	httpPort, grpcPort, err := findAvailablePortPair()
-	if err != nil {
-		t.Fatalf("Failed to get free port pair for %s: %v", name, err)
-	}
-	return httpPort, grpcPort
-}
-
-func findAvailablePortPair() (int, int, error) {
-	httpPort, err := getFreePort()
-	if err != nil {
-		return 0, 0, err
-	}
-	grpcPort, err := getFreePort()
-	if err != nil {
-		return 0, 0, err
-	}
-	return httpPort, grpcPort, nil
-}
-
-func getFreePort() (int, error) {
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		return 0, err
-	}
-	defer listener.Close()
-
-	addr := listener.Addr().(*net.TCPAddr)
-	return addr.Port, nil
-}
-
-func findBindIP() string {
-	addrs, err := net.InterfaceAddrs()
-	if err != nil {
-		return "127.0.0.1"
-	}
-	for _, addr := range addrs {
-		ipNet, ok := addr.(*net.IPNet)
-		if !ok || ipNet.IP == nil {
-			continue
-		}
-		ip := ipNet.IP.To4()
-		if ip == nil || ip.IsLoopback() || ip.IsLinkLocalUnicast() {
-			continue
-		}
-		return ip.String()
-	}
-	return "127.0.0.1"
-}
-
 func randomString(length int) string {
 	const charset = "abcdefghijklmnopqrstuvwxyz0123456789"
 	b := make([]byte, length)

test/s3/distributed_lock/distributed_lock_cluster_test.go

@@ -20,8 +20,11 @@ import (
 	"github.com/aws/aws-sdk-go-v2/config"
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
+	"github.com/seaweedfs/seaweedfs/weed/cluster/lock_manager"
 	"github.com/seaweedfs/seaweedfs/weed/pb"
+	"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
 	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
 	"github.com/stretchr/testify/require"
 	"google.golang.org/grpc"
@@ -113,7 +116,7 @@ func startDistributedLockCluster(t *testing.T) *distributedLockCluster {
 		require.NoError(t, os.MkdirAll(dir, 0o755), "create %s", dir)
 	}
 
-	ports, err := allocatePorts(12)
+	ports, err := testutil.AllocatePorts(12)
 	require.NoError(t, err, "allocate ports")
 	cluster.masterPort = ports[0]
 	cluster.masterGrpcPort = ports[1]
@@ -139,6 +142,7 @@ func startDistributedLockCluster(t *testing.T) *distributedLockCluster {
 		require.NoError(t, cluster.waitForTCP(cluster.filerGRPCAddress(i), 30*time.Second), "wait for filer %d grpc\n%s", i, cluster.tailLog(fmt.Sprintf("filer%d.log", i)))
 	}
 	require.NoError(t, cluster.waitForFilerCount(2, 30*time.Second), "wait for filer group registration")
+	require.NoError(t, cluster.waitForLockRingConverged(30*time.Second), "wait for lock ring convergence")
 
 	for i := 0; i < 2; i++ {
 		require.NoError(t, cluster.startS3(i), "start s3 %d", i)
@@ -411,6 +415,130 @@ func (c *distributedLockCluster) waitForFilerCount(expected int, timeout time.Du
 	return fmt.Errorf("timed out waiting for %d filers in group %q", expected, c.filerGroup)
 }
 
+// waitForLockRingConverged verifies that both filers have a consistent view of the
+// lock ring by acquiring the same lock through each filer and checking mutual exclusion.
+// This guards against the window between master seeing both filers and the filers
+// actually receiving the LockRingUpdate broadcast (delayed by the stabilization timer).
+//
+// A single arbitrary key could false-pass: if the key's real primary is filer0 and
+// filer0 has a stale ring (only sees itself), it still grants correctly because it IS
+// the primary. To catch the stale ring we must also test a key whose real primary is
+// filer1. So we generate one test key per primary filer using the same consistent-hash
+// ring as production, and require mutual exclusion for all of them.
+func (c *distributedLockCluster) waitForLockRingConverged(timeout time.Duration) error {
+	deadline := time.Now().Add(timeout)
+
+	owners := make([]pb.ServerAddress, 0, len(c.filerPorts))
+	for i := range c.filerPorts {
+		owners = append(owners, c.filerServerAddress(i))
+	}
+	ring := lock_manager.NewHashRing(lock_manager.DefaultVnodeCount)
+	ring.SetServers(owners)
+
+	attempt := 0
+	for time.Now().Before(deadline) {
+		// Generate one unique test key per primary filer
+		testKeys := c.convergenceKeysPerPrimary(ring, owners, attempt)
+		attempt++
+
+		allConverged := true
+		for _, key := range testKeys {
+			converged, _ := c.checkLockMutualExclusion(key)
+			if !converged {
+				allConverged = false
+				break
+			}
+		}
+		if allConverged {
+			return nil
+		}
+		time.Sleep(500 * time.Millisecond)
+	}
+	return fmt.Errorf("lock ring did not converge: both filers independently grant the same lock")
+}
+
+// convergenceKeysPerPrimary returns one lock key per distinct primary filer,
+// using the same consistent-hash ring as production routing.
+func (c *distributedLockCluster) convergenceKeysPerPrimary(ring *lock_manager.HashRing, owners []pb.ServerAddress, attempt int) []string {
+	keysByOwner := make(map[pb.ServerAddress]string, len(owners))
+	for i := 0; len(keysByOwner) < len(owners) && i < 1024; i++ {
+		candidate := fmt.Sprintf("convergence-%d-%d", attempt, i)
+		primary := ring.GetPrimary(candidate)
+		if _, exists := keysByOwner[primary]; !exists {
+			keysByOwner[primary] = candidate
+		}
+	}
+	keys := make([]string, 0, len(keysByOwner))
+	for _, k := range keysByOwner {
+		keys = append(keys, k)
+	}
+	return keys
+}
+
+// checkLockMutualExclusion acquires a lock via filer0, then tries the same lock via filer1.
+// Returns true if mutual exclusion holds (second attempt is denied).
+func (c *distributedLockCluster) checkLockMutualExclusion(testKey string) (bool, error) {
+	conn0, err := grpc.NewClient(c.filerGRPCAddress(0), grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return false, err
+	}
+	defer conn0.Close()
+
+	conn1, err := grpc.NewClient(c.filerGRPCAddress(1), grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		return false, err
+	}
+	defer conn1.Close()
+
+	client0 := filer_pb.NewSeaweedFilerClient(conn0)
+	client1 := filer_pb.NewSeaweedFilerClient(conn1)
+
+	// Acquire lock via filer0
+	ctx0, cancel0 := context.WithTimeout(context.Background(), 2*time.Second)
+	defer cancel0()
+	resp0, err := client0.DistributedLock(ctx0, &filer_pb.LockRequest{
+		Name:          testKey,
+		SecondsToLock: 5,
+		Owner:         "convergence-filer0",
+	})
+	if err != nil || resp0.RenewToken == "" {
+		return false, fmt.Errorf("filer0 lock failed: err=%v resp=%v", err, resp0)
+	}
+	defer func() {
+		// Always release the lock we acquired
+		client0.DistributedUnlock(context.Background(), &filer_pb.UnlockRequest{
+			Name:       testKey,
+			RenewToken: resp0.RenewToken,
+		})
+	}()
+
+	// Try the same lock via filer1 - should be denied
+	ctx1, cancel1 := context.WithTimeout(context.Background(), 2*time.Second)
+	defer cancel1()
+	resp1, err := client1.DistributedLock(ctx1, &filer_pb.LockRequest{
+		Name:          testKey,
+		SecondsToLock: 5,
+		Owner:         "convergence-filer1",
+	})
+	if err != nil {
+		return false, err
+	}
+	if resp1.RenewToken != "" {
+		// Both filers granted the lock - ring not converged. Release the second lock.
+		client1.DistributedUnlock(context.Background(), &filer_pb.UnlockRequest{
+			Name:       testKey,
+			RenewToken: resp1.RenewToken,
+		})
+		return false, nil
+	}
+	// Verify the denial is specifically because the lock is already held,
+	// not due to a transient error that might give a false positive.
+	if !strings.Contains(resp1.Error, "lock already owned") {
+		return false, nil
+	}
+	return true, nil
+}
+
 func (c *distributedLockCluster) waitForHTTP(url string, timeout time.Duration) error {
 	client := &net.Dialer{Timeout: time.Second}
 	httpClient := &httpClientWithDialer{dialer: client}
@@ -464,25 +592,6 @@ func (c *distributedLockCluster) tailLog(name string) string {
 	return strings.Join(lines, "\n")
 }
 
-func allocatePorts(count int) ([]int, error) {
-	listeners := make([]net.Listener, 0, count)
-	ports := make([]int, 0, count)
-	for i := 0; i < count; i++ {
-		l, err := net.Listen("tcp", "127.0.0.1:0")
-		if err != nil {
-			for _, openListener := range listeners {
-				_ = openListener.Close()
-			}
-			return nil, err
-		}
-		listeners = append(listeners, l)
-		ports = append(ports, l.Addr().(*net.TCPAddr).Port)
-	}
-	for _, l := range listeners {
-		_ = l.Close()
-	}
-	return ports, nil
-}
 
 func stopProcess(cmd *exec.Cmd) {
 	if cmd == nil || cmd.Process == nil {

test/s3/distributed_lock/distributed_lock_test.go

@@ -6,7 +6,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"sort"
 	"strings"
 	"sync"
 	"testing"
@@ -15,9 +14,9 @@ import (
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
 	"github.com/aws/smithy-go"
+	"github.com/seaweedfs/seaweedfs/weed/cluster/lock_manager"
 	"github.com/seaweedfs/seaweedfs/weed/pb"
 	"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
-	"github.com/seaweedfs/seaweedfs/weed/util"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -149,14 +148,15 @@ func (c *distributedLockCluster) findLockOwnerKeys(bucket, prefix string) map[pb
 	for i := range c.filerPorts {
 		owners = append(owners, c.filerServerAddress(i))
 	}
-	sort.Slice(owners, func(i, j int) bool {
-		return owners[i] < owners[j]
-	})
+
+	ring := lock_manager.NewHashRing(lock_manager.DefaultVnodeCount)
+	ring.SetServers(owners)
 
 	keysByOwner := make(map[pb.ServerAddress]string, len(owners))
 	for i := 0; i < 1024 && len(keysByOwner) < len(owners); i++ {
 		key := fmt.Sprintf("%s-%03d.txt", prefix, i)
-		lockOwner := ownerForObjectLock(bucket, key, owners)
+		lockKey := fmt.Sprintf("s3.object.write:/buckets/%s/%s", bucket, s3_constants.NormalizeObjectKey(key))
+		lockOwner := ring.GetPrimary(lockKey)
 		if _, exists := keysByOwner[lockOwner]; !exists {
 			keysByOwner[lockOwner] = key
 		}
@@ -164,15 +164,6 @@ func (c *distributedLockCluster) findLockOwnerKeys(bucket, prefix string) map[pb
 	return keysByOwner
 }
 
-func ownerForObjectLock(bucket, object string, owners []pb.ServerAddress) pb.ServerAddress {
-	lockKey := fmt.Sprintf("s3.object.write:/buckets/%s/%s", bucket, s3_constants.NormalizeObjectKey(object))
-	hash := util.HashStringToLong(lockKey)
-	if hash < 0 {
-		hash = -hash
-	}
-	return owners[hash%int64(len(owners))]
-}
-
 func lockOwnerLabel(owner pb.ServerAddress) string {
 	replacer := strings.NewReplacer(":", "_", ".", "_")
 	return "owner_" + replacer.Replace(string(owner))

test/s3/iam/s3_iam_admin_test.go

@@ -321,6 +321,13 @@ func TestIAMPolicyManagement(t *testing.T) {
 		require.NoError(t, err)
 		defer iamClient.DeleteUser(&iam.DeleteUserInput{UserName: aws.String(userName)})
 
+		// List user policies before any inline policy is attached
+		listResp, err := iamClient.ListUserPolicies(&iam.ListUserPoliciesInput{
+			UserName: aws.String(userName),
+		})
+		require.NoError(t, err)
+		assert.Empty(t, listResp.PolicyNames, "New user should have no inline policies")
+
 		policyName := "test-inline-policy"
 		policyDoc := `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":"s3:GetObject","Resource":"arn:aws:s3:::*"}]}`
 
@@ -332,6 +339,14 @@ func TestIAMPolicyManagement(t *testing.T) {
 		})
 		require.NoError(t, err)
 
+		// List user policies after attaching inline policy
+		listResp, err = iamClient.ListUserPolicies(&iam.ListUserPoliciesInput{
+			UserName: aws.String(userName),
+		})
+		require.NoError(t, err)
+		assert.NotEmpty(t, listResp.PolicyNames, "User should have inline policies after PutUserPolicy")
+		assert.False(t, *listResp.IsTruncated)
+
 		// Get user policy
 		getResp, err := iamClient.GetUserPolicy(&iam.GetUserPolicyInput{
 			UserName:   aws.String(userName),
@@ -348,5 +363,22 @@ func TestIAMPolicyManagement(t *testing.T) {
 			PolicyName: aws.String(policyName),
 		})
 		require.NoError(t, err)
+
+		// List user policies after deletion
+		listResp, err = iamClient.ListUserPolicies(&iam.ListUserPoliciesInput{
+			UserName: aws.String(userName),
+		})
+		require.NoError(t, err)
+		assert.Empty(t, listResp.PolicyNames, "User should have no inline policies after DeleteUserPolicy")
+	})
+
+	t.Run("list_user_policies_nonexistent_user", func(t *testing.T) {
+		_, err := iamClient.ListUserPolicies(&iam.ListUserPoliciesInput{
+			UserName: aws.String("nonexistent-user-for-list-policies"),
+		})
+		require.Error(t, err)
+		awsErr, ok := err.(awserr.Error)
+		require.True(t, ok, "Expected AWS error type")
+		assert.Equal(t, iam.ErrCodeNoSuchEntityException, awsErr.Code())
 	})
 }

test/s3/iam/s3_iam_group_test.go

@@ -778,6 +778,105 @@ func TestIAMGroupRawAPI(t *testing.T) {
 	})
 }
 
+// TestIAMGroupInlinePolicy tests group inline policy operations:
+// PutGroupPolicy, GetGroupPolicy, ListGroupPolicies, DeleteGroupPolicy
+func TestIAMGroupInlinePolicy(t *testing.T) {
+	framework := NewS3IAMTestFramework(t)
+	defer framework.Cleanup()
+
+	iamClient, err := framework.CreateIAMClientWithJWT("admin-user", "TestAdminRole")
+	require.NoError(t, err)
+
+	// Skip if running against embedded IAM (which returns NotImplemented for group inline policies)
+	_, probeErr := iamClient.ListGroupPolicies(&iam.ListGroupPoliciesInput{GroupName: aws.String("probe-group-inline-support")})
+	if probeErr != nil {
+		if awsErr, ok := probeErr.(awserr.Error); ok && awsErr.Code() == "NotImplemented" {
+			t.Skip("Skipping: group inline policies not supported in embedded IAM mode")
+		}
+	}
+	require.NoError(t, err)
+
+	groupName := "test-group-inline-policy"
+	policyName := "TestInlinePolicy"
+	_, err = iamClient.CreateGroup(&iam.CreateGroupInput{
+		GroupName: aws.String(groupName),
+	})
+	require.NoError(t, err)
+	defer func() {
+		// Clean up inline policies before deleting the group
+		iamClient.DeleteGroupPolicy(&iam.DeleteGroupPolicyInput{
+			GroupName:  aws.String(groupName),
+			PolicyName: aws.String(policyName),
+		})
+		iamClient.DeleteGroup(&iam.DeleteGroupInput{GroupName: aws.String(groupName)})
+	}()
+
+	t.Run("list_empty", func(t *testing.T) {
+		resp, err := iamClient.ListGroupPolicies(&iam.ListGroupPoliciesInput{
+			GroupName: aws.String(groupName),
+		})
+		require.NoError(t, err)
+		assert.Empty(t, resp.PolicyNames)
+		assert.False(t, *resp.IsTruncated)
+	})
+
+	policyDoc := `{"Version":"2012-10-17","Statement":[{"Effect":"Allow","Action":"s3:GetObject","Resource":"arn:aws:s3:::test-bucket/*"}]}`
+
+	t.Run("put_group_policy", func(t *testing.T) {
+		_, err := iamClient.PutGroupPolicy(&iam.PutGroupPolicyInput{
+			GroupName:      aws.String(groupName),
+			PolicyName:     aws.String(policyName),
+			PolicyDocument: aws.String(policyDoc),
+		})
+		require.NoError(t, err)
+	})
+
+	t.Run("list_after_put", func(t *testing.T) {
+		resp, err := iamClient.ListGroupPolicies(&iam.ListGroupPoliciesInput{
+			GroupName: aws.String(groupName),
+		})
+		require.NoError(t, err)
+		assert.NotEmpty(t, resp.PolicyNames)
+	})
+
+	t.Run("get_group_policy", func(t *testing.T) {
+		resp, err := iamClient.GetGroupPolicy(&iam.GetGroupPolicyInput{
+			GroupName:  aws.String(groupName),
+			PolicyName: aws.String(policyName),
+		})
+		require.NoError(t, err)
+		assert.Equal(t, groupName, *resp.GroupName)
+		assert.Equal(t, policyName, *resp.PolicyName)
+		assert.Contains(t, *resp.PolicyDocument, "s3:GetObject")
+	})
+
+	t.Run("delete_group_policy", func(t *testing.T) {
+		_, err := iamClient.DeleteGroupPolicy(&iam.DeleteGroupPolicyInput{
+			GroupName:  aws.String(groupName),
+			PolicyName: aws.String(policyName),
+		})
+		require.NoError(t, err)
+	})
+
+	t.Run("list_after_delete", func(t *testing.T) {
+		resp, err := iamClient.ListGroupPolicies(&iam.ListGroupPoliciesInput{
+			GroupName: aws.String(groupName),
+		})
+		require.NoError(t, err)
+		assert.Empty(t, resp.PolicyNames)
+	})
+
+	t.Run("nonexistent_group", func(t *testing.T) {
+		_, err := iamClient.ListGroupPolicies(&iam.ListGroupPoliciesInput{
+			GroupName: aws.String("nonexistent-group-for-policies"),
+		})
+		require.Error(t, err)
+		awsErr, ok := err.(awserr.Error)
+		require.True(t, ok, "Expected AWS error type")
+		assert.Equal(t, iam.ErrCodeNoSuchEntityException, awsErr.Code())
+	})
+}
+
 // createS3Client creates an S3 client with static credentials
 func createS3Client(t *testing.T, accessKey, secretKey string) *s3.S3 {
 	sess, err := session.NewSession(&aws.Config{

test/s3/iam/s3_sts_get_federation_token_test.go

@@ -0,0 +1,511 @@
+package iam
+
+import (
+	"encoding/xml"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/aws/aws-sdk-go/aws"
+	"github.com/aws/aws-sdk-go/aws/credentials"
+	"github.com/aws/aws-sdk-go/aws/session"
+	"github.com/aws/aws-sdk-go/service/s3"
+	v4 "github.com/aws/aws-sdk-go/aws/signer/v4"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// GetFederationTokenTestResponse represents the STS GetFederationToken response
+type GetFederationTokenTestResponse struct {
+	XMLName xml.Name `xml:"GetFederationTokenResponse"`
+	Result  struct {
+		Credentials struct {
+			AccessKeyId     string `xml:"AccessKeyId"`
+			SecretAccessKey string `xml:"SecretAccessKey"`
+			SessionToken    string `xml:"SessionToken"`
+			Expiration      string `xml:"Expiration"`
+		} `xml:"Credentials"`
+		FederatedUser struct {
+			FederatedUserId string `xml:"FederatedUserId"`
+			Arn             string `xml:"Arn"`
+		} `xml:"FederatedUser"`
+	} `xml:"GetFederationTokenResult"`
+}
+
+func getTestCredentials() (string, string) {
+	accessKey := os.Getenv("STS_TEST_ACCESS_KEY")
+	if accessKey == "" {
+		accessKey = "admin"
+	}
+	secretKey := os.Getenv("STS_TEST_SECRET_KEY")
+	if secretKey == "" {
+		secretKey = "admin"
+	}
+	return accessKey, secretKey
+}
+
+// isGetFederationTokenImplemented checks if the running server supports GetFederationToken
+func isGetFederationTokenImplemented(t *testing.T) bool {
+	accessKey, secretKey := getTestCredentials()
+	resp, err := callSTSAPIWithSigV4(t, url.Values{
+		"Action":  {"GetFederationToken"},
+		"Version": {"2011-06-15"},
+		"Name":    {"probe"},
+	}, accessKey, secretKey)
+	if err != nil {
+		return false
+	}
+	defer resp.Body.Close()
+
+	body, _ := io.ReadAll(resp.Body)
+	var errResp STSErrorTestResponse
+	if xml.Unmarshal(body, &errResp) == nil {
+		if errResp.Error.Code == "InvalidAction" || errResp.Error.Code == "NotImplemented" {
+			return false
+		}
+	}
+	return true
+}
+
+// TestSTSGetFederationTokenValidation tests input validation for the GetFederationToken endpoint
+func TestSTSGetFederationTokenValidation(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	if !isSTSEndpointRunning(t) {
+		t.Fatal("SeaweedFS STS endpoint is not running at", TestSTSEndpoint, "- please run 'make setup-all-tests' first")
+	}
+
+	if !isGetFederationTokenImplemented(t) {
+		t.Fatal("GetFederationToken action is not implemented in the running server")
+	}
+
+	accessKey, secretKey := getTestCredentials()
+
+	t.Run("missing_name", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			// Name is missing
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "MissingParameter", errResp.Error.Code)
+	})
+
+	t.Run("name_too_short", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {"A"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "InvalidParameterValue", errResp.Error.Code)
+	})
+
+	t.Run("name_too_long", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {strings.Repeat("A", 33)},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "InvalidParameterValue", errResp.Error.Code)
+	})
+
+	t.Run("name_invalid_characters", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {"bad name"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "InvalidParameterValue", errResp.Error.Code)
+	})
+
+	t.Run("duration_too_short", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":          {"GetFederationToken"},
+			"Version":         {"2011-06-15"},
+			"Name":            {"TestApp"},
+			"DurationSeconds": {"100"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "InvalidParameterValue", errResp.Error.Code)
+	})
+
+	t.Run("duration_too_long", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":          {"GetFederationToken"},
+			"Version":         {"2011-06-15"},
+			"Name":            {"TestApp"},
+			"DurationSeconds": {"200000"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "InvalidParameterValue", errResp.Error.Code)
+	})
+
+	t.Run("malformed_policy", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {"TestApp"},
+			"Policy":  {"not-valid-json"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		var errResp STSErrorTestResponse
+		require.NoError(t, xml.Unmarshal(body, &errResp), "Failed to parse: %s", string(body))
+		assert.Equal(t, "MalformedPolicyDocument", errResp.Error.Code)
+	})
+
+	t.Run("anonymous_rejected", func(t *testing.T) {
+		// GetFederationToken requires SigV4, anonymous should fail
+		resp, err := callSTSAPI(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {"TestApp"},
+		})
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		assert.NotEqual(t, http.StatusOK, resp.StatusCode)
+	})
+}
+
+// TestSTSGetFederationTokenRejectTemporaryCredentials tests that temporary
+// credentials (session tokens) are rejected by GetFederationToken
+func TestSTSGetFederationTokenRejectTemporaryCredentials(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	if !isSTSEndpointRunning(t) {
+		t.Skip("SeaweedFS STS endpoint is not running at", TestSTSEndpoint)
+	}
+
+	if !isGetFederationTokenImplemented(t) {
+		t.Skip("GetFederationToken not implemented")
+	}
+
+	accessKey, secretKey := getTestCredentials()
+
+	// First, obtain temporary credentials via AssumeRole
+	resp, err := callSTSAPIWithSigV4(t, url.Values{
+		"Action":          {"AssumeRole"},
+		"Version":         {"2011-06-15"},
+		"RoleArn":         {"arn:aws:iam::role/admin"},
+		"RoleSessionName": {"temp-session"},
+	}, accessKey, secretKey)
+	require.NoError(t, err)
+	defer resp.Body.Close()
+
+	body, err := io.ReadAll(resp.Body)
+	require.NoError(t, err)
+
+	if resp.StatusCode != http.StatusOK {
+		t.Skipf("AssumeRole failed (may not be configured): status=%d body=%s", resp.StatusCode, string(body))
+	}
+
+	var assumeResp AssumeRoleTestResponse
+	require.NoError(t, xml.Unmarshal(body, &assumeResp), "Parse AssumeRole response: %s", string(body))
+
+	tempAccessKey := assumeResp.Result.Credentials.AccessKeyId
+	tempSecretKey := assumeResp.Result.Credentials.SecretAccessKey
+	tempSessionToken := assumeResp.Result.Credentials.SessionToken
+	require.NotEmpty(t, tempAccessKey)
+	require.NotEmpty(t, tempSessionToken)
+
+	// Now try GetFederationToken with the temporary credentials
+	// Include X-Amz-Security-Token header which marks this as a temp credential call
+	params := url.Values{
+		"Action":  {"GetFederationToken"},
+		"Version": {"2011-06-15"},
+		"Name":    {"ShouldFail"},
+	}
+
+	reqBody := params.Encode()
+	req, err := http.NewRequest(http.MethodPost, TestSTSEndpoint+"/", strings.NewReader(reqBody))
+	require.NoError(t, err)
+
+	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+	req.Header.Set("X-Amz-Security-Token", tempSessionToken)
+
+	creds := credentials.NewStaticCredentials(tempAccessKey, tempSecretKey, tempSessionToken)
+	signer := v4.NewSigner(creds)
+	_, err = signer.Sign(req, strings.NewReader(reqBody), "sts", "us-east-1", time.Now())
+	require.NoError(t, err)
+
+	client := &http.Client{Timeout: 30 * time.Second}
+	resp2, err := client.Do(req)
+	require.NoError(t, err)
+	defer resp2.Body.Close()
+
+	body2, _ := io.ReadAll(resp2.Body)
+	assert.Equal(t, http.StatusForbidden, resp2.StatusCode,
+		"GetFederationToken should reject temporary credentials: %s", string(body2))
+	assert.Contains(t, string(body2), "temporary credentials",
+		"Error should mention temporary credentials")
+}
+
+// TestSTSGetFederationTokenSuccess tests a successful GetFederationToken call
+// and verifies the returned credentials can be used to access S3
+func TestSTSGetFederationTokenSuccess(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	if !isSTSEndpointRunning(t) {
+		t.Skip("SeaweedFS STS endpoint is not running at", TestSTSEndpoint)
+	}
+
+	if !isGetFederationTokenImplemented(t) {
+		t.Skip("GetFederationToken not implemented")
+	}
+
+	accessKey, secretKey := getTestCredentials()
+
+	t.Run("basic_success", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":  {"GetFederationToken"},
+			"Version": {"2011-06-15"},
+			"Name":    {"AppClient"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, err := io.ReadAll(resp.Body)
+		require.NoError(t, err)
+		t.Logf("Response status: %d, body: %s", resp.StatusCode, string(body))
+
+		if resp.StatusCode != http.StatusOK {
+			var errResp STSErrorTestResponse
+			_ = xml.Unmarshal(body, &errResp)
+			t.Fatalf("GetFederationToken failed: code=%s message=%s", errResp.Error.Code, errResp.Error.Message)
+		}
+
+		var stsResp GetFederationTokenTestResponse
+		require.NoError(t, xml.Unmarshal(body, &stsResp), "Parse response: %s", string(body))
+
+		creds := stsResp.Result.Credentials
+		assert.NotEmpty(t, creds.AccessKeyId)
+		assert.NotEmpty(t, creds.SecretAccessKey)
+		assert.NotEmpty(t, creds.SessionToken)
+		assert.NotEmpty(t, creds.Expiration)
+
+		fedUser := stsResp.Result.FederatedUser
+		assert.Contains(t, fedUser.Arn, "federated-user/AppClient")
+		assert.Contains(t, fedUser.FederatedUserId, "AppClient")
+	})
+
+	t.Run("with_custom_duration", func(t *testing.T) {
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":          {"GetFederationToken"},
+			"Version":         {"2011-06-15"},
+			"Name":            {"DurationTest"},
+			"DurationSeconds": {"3600"},
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		t.Logf("Response status: %d, body: %s", resp.StatusCode, string(body))
+
+		if resp.StatusCode == http.StatusOK {
+			var stsResp GetFederationTokenTestResponse
+			require.NoError(t, xml.Unmarshal(body, &stsResp))
+			assert.NotEmpty(t, stsResp.Result.Credentials.AccessKeyId)
+
+			// Verify expiration is roughly 1 hour from now
+			expTime, err := time.Parse(time.RFC3339, stsResp.Result.Credentials.Expiration)
+			require.NoError(t, err)
+			diff := time.Until(expTime)
+			assert.InDelta(t, 3600, diff.Seconds(), 60,
+				"Expiration should be ~1 hour from now")
+		}
+	})
+
+	t.Run("with_36_hour_duration", func(t *testing.T) {
+		// GetFederationToken allows up to 36 hours (unlike AssumeRole's 12h max)
+		resp, err := callSTSAPIWithSigV4(t, url.Values{
+			"Action":          {"GetFederationToken"},
+			"Version":         {"2011-06-15"},
+			"Name":            {"LongDuration"},
+			"DurationSeconds": {"129600"}, // 36 hours
+		}, accessKey, secretKey)
+		require.NoError(t, err)
+		defer resp.Body.Close()
+
+		body, _ := io.ReadAll(resp.Body)
+		if resp.StatusCode == http.StatusOK {
+			var stsResp GetFederationTokenTestResponse
+			require.NoError(t, xml.Unmarshal(body, &stsResp))
+
+			expTime, err := time.Parse(time.RFC3339, stsResp.Result.Credentials.Expiration)
+			require.NoError(t, err)
+			diff := time.Until(expTime)
+			assert.InDelta(t, 129600, diff.Seconds(), 60,
+				"Expiration should be ~36 hours from now")
+		} else {
+			// Duration should not cause a rejection
+			var errResp STSErrorTestResponse
+			_ = xml.Unmarshal(body, &errResp)
+			assert.NotContains(t, errResp.Error.Message, "DurationSeconds",
+				"36-hour duration should be accepted by GetFederationToken")
+		}
+	})
+}
+
+// TestSTSGetFederationTokenWithSessionPolicy tests that vended credentials
+// are scoped down by an inline session policy
+func TestSTSGetFederationTokenWithSessionPolicy(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	if !isSTSEndpointRunning(t) {
+		t.Skip("SeaweedFS STS endpoint is not running at", TestSTSEndpoint)
+	}
+
+	if !isGetFederationTokenImplemented(t) {
+		t.Skip("GetFederationToken not implemented")
+	}
+
+	accessKey, secretKey := getTestCredentials()
+
+	// Create a test bucket using admin credentials
+	adminSess, err := session.NewSession(&aws.Config{
+		Region:           aws.String("us-east-1"),
+		Endpoint:         aws.String(TestSTSEndpoint),
+		DisableSSL:       aws.Bool(true),
+		S3ForcePathStyle: aws.Bool(true),
+		Credentials:      credentials.NewStaticCredentials(accessKey, secretKey, ""),
+	})
+	require.NoError(t, err)
+
+	adminS3 := s3.New(adminSess)
+	bucket := fmt.Sprintf("fed-token-test-%d", time.Now().UnixNano())
+
+	_, err = adminS3.CreateBucket(&s3.CreateBucketInput{Bucket: aws.String(bucket)})
+	require.NoError(t, err)
+	defer adminS3.DeleteBucket(&s3.DeleteBucketInput{Bucket: aws.String(bucket)})
+
+	_, err = adminS3.PutObject(&s3.PutObjectInput{
+		Bucket: aws.String(bucket),
+		Key:    aws.String("test.txt"),
+		Body:   strings.NewReader("hello"),
+	})
+	require.NoError(t, err)
+	defer adminS3.DeleteObject(&s3.DeleteObjectInput{Bucket: aws.String(bucket), Key: aws.String("test.txt")})
+
+	// Get federated credentials with a session policy that only allows GetObject
+	sessionPolicy := fmt.Sprintf(`{
+		"Version": "2012-10-17",
+		"Statement": [{
+			"Effect": "Allow",
+			"Action": ["s3:GetObject"],
+			"Resource": ["arn:aws:s3:::%s/*"]
+		}]
+	}`, bucket)
+
+	resp, err := callSTSAPIWithSigV4(t, url.Values{
+		"Action":  {"GetFederationToken"},
+		"Version": {"2011-06-15"},
+		"Name":    {"ScopedClient"},
+		"Policy":  {sessionPolicy},
+	}, accessKey, secretKey)
+	require.NoError(t, err)
+	defer resp.Body.Close()
+
+	body, _ := io.ReadAll(resp.Body)
+	t.Logf("GetFederationToken response: status=%d body=%s", resp.StatusCode, string(body))
+
+	if resp.StatusCode != http.StatusOK {
+		t.Skipf("GetFederationToken failed (may need IAM policy config): %s", string(body))
+	}
+
+	var stsResp GetFederationTokenTestResponse
+	require.NoError(t, xml.Unmarshal(body, &stsResp))
+
+	fedCreds := stsResp.Result.Credentials
+	require.NotEmpty(t, fedCreds.AccessKeyId)
+	require.NotEmpty(t, fedCreds.SessionToken)
+
+	// Create S3 client with the federated credentials
+	fedSess, err := session.NewSession(&aws.Config{
+		Region:           aws.String("us-east-1"),
+		Endpoint:         aws.String(TestSTSEndpoint),
+		DisableSSL:       aws.Bool(true),
+		S3ForcePathStyle: aws.Bool(true),
+		Credentials: credentials.NewStaticCredentials(
+			fedCreds.AccessKeyId, fedCreds.SecretAccessKey, fedCreds.SessionToken),
+	})
+	require.NoError(t, err)
+
+	fedS3 := s3.New(fedSess)
+
+	// GetObject should succeed (allowed by session policy)
+	getResp, err := fedS3.GetObject(&s3.GetObjectInput{
+		Bucket: aws.String(bucket),
+		Key:    aws.String("test.txt"),
+	})
+	if err == nil {
+		defer getResp.Body.Close()
+		t.Log("GetObject with federated credentials succeeded (as expected)")
+	} else {
+		t.Logf("GetObject with federated credentials: %v (session policy enforcement may vary)", err)
+	}
+
+	// PutObject should be denied (not allowed by session policy)
+	_, err = fedS3.PutObject(&s3.PutObjectInput{
+		Bucket: aws.String(bucket),
+		Key:    aws.String("denied.txt"),
+		Body:   strings.NewReader("should fail"),
+	})
+	if err != nil {
+		t.Log("PutObject correctly denied with federated credentials")
+		assert.Contains(t, err.Error(), "AccessDenied",
+			"PutObject should be denied by session policy")
+	} else {
+		// Clean up if unexpectedly succeeded
+		adminS3.DeleteObject(&s3.DeleteObjectInput{Bucket: aws.String(bucket), Key: aws.String("denied.txt")})
+		t.Log("PutObject unexpectedly succeeded — session policy enforcement may not be active")
+	}
+}

test/s3/normal/s3_integration_test.go

@@ -7,7 +7,6 @@ import (
 	"encoding/base64"
 	"fmt"
 	"math/rand"
-	"net"
 	"net/http"
 	"os"
 	"os/exec"
@@ -25,6 +24,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
 	"github.com/seaweedfs/seaweedfs/weed/command"
 	"github.com/seaweedfs/seaweedfs/weed/glog"
@@ -112,37 +112,16 @@ func TestS3Integration(t *testing.T) {
 }
 
 // findAvailablePort finds an available port by binding to port 0
-func findAvailablePort() (int, error) {
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		return 0, err
-	}
-	defer listener.Close()
-
-	addr := listener.Addr().(*net.TCPAddr)
-	return addr.Port, nil
-}
 
 // startMiniCluster starts a weed mini instance directly without exec.
 // Extra flags (e.g. "-s3.allowDeleteBucketNotEmpty=false") can be appended via extraArgs.
 func startMiniCluster(t *testing.T, extraArgs ...string) (*TestCluster, error) {
-	// Find available ports
-	masterPort, err := findAvailablePort()
-	if err != nil {
-		return nil, fmt.Errorf("failed to find master port: %v", err)
-	}
-	volumePort, err := findAvailablePort()
-	if err != nil {
-		return nil, fmt.Errorf("failed to find volume port: %v", err)
-	}
-	filerPort, err := findAvailablePort()
-	if err != nil {
-		return nil, fmt.Errorf("failed to find filer port: %v", err)
-	}
-	s3Port, err := findAvailablePort()
-	if err != nil {
-		return nil, fmt.Errorf("failed to find s3 port: %v", err)
-	}
+	// Allocate non-colliding ports (including gRPC offsets) for weed mini.
+	ports := testutil.MustFreeMiniPorts(t, []string{"Master", "Volume", "Filer", "S3"})
+	masterPort := ports[0]
+	volumePort := ports[1]
+	filerPort := ports[2]
+	s3Port := ports[3]
 	// Create temporary directory for test data
 	testDir := t.TempDir()
 
@@ -167,7 +146,7 @@ func startMiniCluster(t *testing.T, extraArgs ...string) (*TestCluster, error) {
 
 	// Create empty security.toml to disable JWT authentication in tests
 	securityToml := filepath.Join(testDir, "security.toml")
-	err = os.WriteFile(securityToml, []byte("# Empty security config for testing\n"), 0644)
+	err := os.WriteFile(securityToml, []byte("# Empty security config for testing\n"), 0644)
 	if err != nil {
 		cancel()
 		return nil, fmt.Errorf("failed to create security.toml: %v", err)
@@ -233,10 +212,9 @@ func startMiniCluster(t *testing.T, extraArgs ...string) (*TestCluster, error) {
 	}()
 
 	// Wait for S3 service to be ready
-	err = waitForS3Ready(cluster.s3Endpoint, 30*time.Second)
-	if err != nil {
+	if !testutil.WaitForService(cluster.s3Endpoint, 30*time.Second) {
 		cancel()
-		return nil, fmt.Errorf("S3 service failed to start: %v", err)
+		return nil, fmt.Errorf("S3 service failed to start at %s", cluster.s3Endpoint)
 	}
 
 	// If VOLUME_SERVER_IMPL=rust, start a Rust volume server alongside weed mini
@@ -277,14 +255,12 @@ func (c *TestCluster) startRustVolumeServer(t *testing.T) error {
 		return fmt.Errorf("resolve rust volume binary: %v", err)
 	}
 
-	rustVolumePort, err := findAvailablePort()
+	rustPorts, err := testutil.AllocatePorts(2)
 	if err != nil {
-		return fmt.Errorf("find rust volume port: %v", err)
-	}
-	rustVolumeGrpcPort, err := findAvailablePort()
-	if err != nil {
-		return fmt.Errorf("find rust volume grpc port: %v", err)
+		return fmt.Errorf("find rust volume ports: %v", err)
 	}
+	rustVolumePort := rustPorts[0]
+	rustVolumeGrpcPort := rustPorts[1]
 
 	rustVolumeDir := filepath.Join(c.dataDir, "rust-volume")
 	if err := os.MkdirAll(rustVolumeDir, 0o755); err != nil {
@@ -377,25 +353,6 @@ func (c *TestCluster) Stop() {
 	}
 }
 
-// waitForS3Ready waits for the S3 service to be ready
-func waitForS3Ready(endpoint string, timeout time.Duration) error {
-	client := &http.Client{Timeout: 1 * time.Second}
-	deadline := time.Now().Add(timeout)
-
-	for time.Now().Before(deadline) {
-		resp, err := client.Get(endpoint)
-		if err == nil {
-			resp.Body.Close()
-			// Wait a bit more to ensure service is fully ready
-			time.Sleep(500 * time.Millisecond)
-			return nil
-		}
-		time.Sleep(200 * time.Millisecond)
-	}
-
-	return fmt.Errorf("timeout waiting for S3 service at %s", endpoint)
-}
-
 // Test functions
 
 func testCreateBucket(t *testing.T, cluster *TestCluster) {

test/s3/policy/policy_test.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"errors"
 	"fmt"
-	"net"
 	"net/http"
 	"os"
 	"os/exec"
@@ -21,6 +20,7 @@ import (
 	"github.com/aws/aws-sdk-go/aws/session"
 	"github.com/aws/aws-sdk-go/service/iam"
 	"github.com/aws/aws-sdk-go/service/s3"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
 	"github.com/seaweedfs/seaweedfs/weed/command"
 	"github.com/seaweedfs/seaweedfs/weed/glog"
@@ -703,43 +703,13 @@ func uniqueName(prefix string) string {
 
 // --- Test setup helpers ---
 
-func findAvailablePort() (int, error) {
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		return 0, err
-	}
-	defer listener.Close()
-	addr := listener.Addr().(*net.TCPAddr)
-	return addr.Port, nil
-}
-
-// findAvailablePortPair finds an available http port P such that P and P+10000 (grpc) are both available
-func findAvailablePortPair() (int, int, error) {
-	httpPort, err := findAvailablePort()
-	if err != nil {
-		return 0, 0, err
-	}
-	for i := 0; i < 100; i++ {
-		grpcPort, err := findAvailablePort()
-		if err != nil {
-			return 0, 0, err
-		}
-		if grpcPort != httpPort {
-			return httpPort, grpcPort, nil
-		}
-	}
-	return 0, 0, fmt.Errorf("failed to find available port pair")
-}
 
 func startMiniCluster(t *testing.T) (*TestCluster, error) {
-	masterPort, masterGrpcPort, err := findAvailablePortPair()
-	require.NoError(t, err)
-	volumePort, volumeGrpcPort, err := findAvailablePortPair()
-	require.NoError(t, err)
-	filerPort, filerGrpcPort, err := findAvailablePortPair()
-	require.NoError(t, err)
-	s3Port, s3GrpcPort, err := findAvailablePortPair()
-	require.NoError(t, err)
+	ports := testutil.MustAllocatePorts(t, 8)
+	masterPort, masterGrpcPort := ports[0], ports[1]
+	volumePort, volumeGrpcPort := ports[2], ports[3]
+	filerPort, filerGrpcPort := ports[4], ports[5]
+	s3Port, s3GrpcPort := ports[6], ports[7]
 
 	testDir := t.TempDir()
 
@@ -760,7 +730,7 @@ func startMiniCluster(t *testing.T) (*TestCluster, error) {
 
 	// Disable authentication for tests
 	securityToml := filepath.Join(testDir, "security.toml")
-	err = os.WriteFile(securityToml, []byte("# Empty security config\n"), 0644)
+	err := os.WriteFile(securityToml, []byte("# Empty security config\n"), 0644)
 	require.NoError(t, err)
 
 	// Configure credential store for IAM tests
@@ -819,10 +789,9 @@ enabled = true
 	}()
 
 	// Wait for S3
-	err = waitForS3Ready(cluster.s3Endpoint, 60*time.Second)
-	if err != nil {
+	if !testutil.WaitForService(cluster.s3Endpoint, 60*time.Second) {
 		cancel()
-		return nil, err
+		return nil, fmt.Errorf("timeout waiting for S3 at %s", cluster.s3Endpoint)
 	}
 
 	// If VOLUME_SERVER_IMPL=rust, start a Rust volume server alongside weed mini
@@ -837,19 +806,6 @@ enabled = true
 	return cluster, nil
 }
 
-func waitForS3Ready(endpoint string, timeout time.Duration) error {
-	client := &http.Client{Timeout: 1 * time.Second}
-	deadline := time.Now().Add(timeout)
-	for time.Now().Before(deadline) {
-		resp, err := client.Get(endpoint)
-		if err == nil {
-			resp.Body.Close()
-			return nil
-		}
-		time.Sleep(200 * time.Millisecond)
-	}
-	return fmt.Errorf("timeout waiting for S3")
-}
 
 // startRustVolumeServer starts a Rust volume server that registers with the same master.
 func (c *TestCluster) startRustVolumeServer(t *testing.T) error {
@@ -860,14 +816,12 @@ func (c *TestCluster) startRustVolumeServer(t *testing.T) error {
 		return fmt.Errorf("resolve rust volume binary: %v", err)
 	}
 
-	rustVolumePort, err := findAvailablePort()
+	rustPorts, err := testutil.AllocatePorts(2)
 	if err != nil {
-		return fmt.Errorf("find rust volume port: %v", err)
-	}
-	rustVolumeGrpcPort, err := findAvailablePort()
-	if err != nil {
-		return fmt.Errorf("find rust volume grpc port: %v", err)
+		return fmt.Errorf("find rust volume ports: %v", err)
 	}
+	rustVolumePort := rustPorts[0]
+	rustVolumeGrpcPort := rustPorts[1]
 
 	rustVolumeDir := filepath.Join(c.dataDir, "rust-volume")
 	if err := os.MkdirAll(rustVolumeDir, 0o755); err != nil {

test/s3/spark/issue_8285_repro_test.go

@@ -70,7 +70,8 @@ print("WRITE_COUNT=" + str(count))
 		"issue-8285/output/_temporary/0/",
 		"issue-8285/output/_temporary/0/_temporary/",
 	}
-	lingering := waitForObjectsToDisappear(t, env, "test", temporaryCandidates, 35*time.Second)
+	// Empty folder cleanup has a 2m default delay + 30s processor interval
+	lingering := waitForObjectsToDisappear(t, env, "test", temporaryCandidates, 3*time.Minute)
 	if len(lingering) > 0 {
 		t.Fatalf("issue #8285 regression detected: lingering temporary directories: %v", lingering)
 	}

test/s3/spark/setup_test.go

@@ -14,7 +14,7 @@ import (
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/testcontainers/testcontainers-go"
 )
 
@@ -94,9 +94,10 @@ func (env *TestEnvironment) StartSeaweedFS(t *testing.T) {
 		t.Fatalf("failed to create temp directory: %v", err)
 	}
 
-	env.masterPort = testutil.MustFreeMiniPort(t, "Master")
-	env.filerPort = testutil.MustFreeMiniPort(t, "Filer")
-	env.s3Port = testutil.MustFreeMiniPort(t, "S3")
+	ports := testutil.MustFreeMiniPorts(t, []string{"Master", "Filer", "S3"})
+	env.masterPort = ports[0]
+	env.filerPort = ports[1]
+	env.s3Port = ports[2]
 
 	bindIP := testutil.FindBindIP()
 	iamConfigPath, err := testutil.WriteIAMConfig(env.seaweedfsDataDir, env.accessKey, env.secretKey)

test/s3/sse/Makefile

@@ -98,8 +98,8 @@ start-seaweedfs: check-binary
 	# Create S3 configuration with SSE-KMS support
 	@printf '{"identities":[{"name":"%s","credentials":[{"accessKey":"%s","secretKey":"%s"}],"actions":["Admin","Read","Write"]}],"kms":{"type":"%s","configs":{"keyId":"%s","encryptionContext":{},"bucketKey":false}}}' "$(ACCESS_KEY)" "$(ACCESS_KEY)" "$(SECRET_KEY)" "$(KMS_TYPE)" "$(KMS_KEY_ID)" > /tmp/seaweedfs-sse-s3.json
 	
-	# Start weed mini
-	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) $(SEAWEEDFS_BINARY) mini \
+	# Start weed mini (WEED_S3_SSE_KEY enables SSE-S3 encryption)
+	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) WEED_S3_SSE_KEY=test-sse-s3-key $(SEAWEEDFS_BINARY) mini \
 		-dir=/tmp/seaweedfs-test-sse \
 		-s3.port=$(S3_PORT) \
 		-s3.config=/tmp/seaweedfs-sse-s3.json \
@@ -337,8 +337,9 @@ start-seaweedfs-ci: check-binary
 	     s3-config-template.json > /tmp/seaweedfs-s3.json
 	
 	# Start weed mini with embedded S3 using the JSON config (with verbose logging)
+	# WEED_S3_SSE_KEY enables SSE-S3 encryption for testing (KEK derived via HKDF)
 	@echo "Starting weed mini with embedded S3..."
-	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) GLOG_v=4 $(SEAWEEDFS_BINARY) mini \
+	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) WEED_S3_SSE_KEY=test-sse-s3-key GLOG_v=4 $(SEAWEEDFS_BINARY) mini \
 		-dir=/tmp/seaweedfs-test-sse \
 		-s3.port=$(S3_PORT) \
 		-s3.config=/tmp/seaweedfs-s3.json \
@@ -482,7 +483,7 @@ test-volume-encryption: build-weed
 	     -e 's/SECRET_KEY_PLACEHOLDER/$(SECRET_KEY)/g' \
 	     s3-config-template.json > /tmp/seaweedfs-s3.json
 	@echo "Starting weed mini with S3 volume encryption..."
-	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) GLOG_v=4 $(SEAWEEDFS_BINARY) mini \
+	@AWS_ACCESS_KEY_ID=$(ACCESS_KEY) AWS_SECRET_ACCESS_KEY=$(SECRET_KEY) WEED_S3_SSE_KEY=test-sse-s3-key GLOG_v=4 $(SEAWEEDFS_BINARY) mini \
 		-dir=/tmp/seaweedfs-test-sse \
 		-s3.port=$(S3_PORT) \
 		-s3.config=/tmp/seaweedfs-s3.json \

test/s3/versioning/s3_versioning_pagination_stress_test.go

@@ -289,6 +289,157 @@ func TestVersioningPaginationMultipleObjectsManyVersions(t *testing.T) {
 	})
 }
 
+// TestVersioningPaginationDeepDirectoryHierarchy tests that paginated ListObjectVersions
+// correctly skips directory subtrees before the key-marker. This reproduces the
+// real-world scenario where Veeam backup objects are spread across many subdirectories
+// (e.g., Mailboxes/<uuid>/ItemsData/<file>) and pagination becomes exponentially
+// slower as the marker advances through the tree.
+//
+// Run with: ENABLE_STRESS_TESTS=true go test -v -run TestVersioningPaginationDeepDirectoryHierarchy -timeout 10m
+func TestVersioningPaginationDeepDirectoryHierarchy(t *testing.T) {
+	if os.Getenv("ENABLE_STRESS_TESTS") != "true" {
+		t.Skip("Skipping stress test. Set ENABLE_STRESS_TESTS=true to run.")
+	}
+
+	client := getS3Client(t)
+	bucketName := getNewBucketName()
+
+	createBucket(t, client, bucketName)
+	defer deleteBucket(t, client, bucketName)
+
+	enableVersioning(t, client, bucketName)
+	checkVersioningStatus(t, client, bucketName, types.BucketVersioningStatusEnabled)
+
+	// Create a deep directory structure mimicking Veeam 365 backup layout:
+	// Backup/Organizations/<org>/Mailboxes/<mailbox>/ItemsData/<file>
+	numMailboxes := 20
+	filesPerMailbox := 5
+	totalObjects := numMailboxes * filesPerMailbox
+	orgPrefix := "Backup/Organizations/org-001/Mailboxes"
+
+	t.Logf("Creating %d objects across %d subdirectories (depth=6)...", totalObjects, numMailboxes)
+	startTime := time.Now()
+
+	allKeys := make([]string, 0, totalObjects)
+	for i := 0; i < numMailboxes; i++ {
+		mailboxId := fmt.Sprintf("mbx-%03d", i)
+		for j := 0; j < filesPerMailbox; j++ {
+			key := fmt.Sprintf("%s/%s/ItemsData/file-%03d.dat", orgPrefix, mailboxId, j)
+			_, err := client.PutObject(context.TODO(), &s3.PutObjectInput{
+				Bucket: aws.String(bucketName),
+				Key:    aws.String(key),
+				Body:   strings.NewReader(fmt.Sprintf("content-%d-%d", i, j)),
+			})
+			require.NoError(t, err)
+			allKeys = append(allKeys, key)
+		}
+	}
+	t.Logf("Created %d objects in %v", totalObjects, time.Since(startTime))
+
+	// Test 1: Paginate through all versions with a broad prefix and small maxKeys.
+	// This forces multiple pages that must skip earlier subdirectory trees.
+	t.Run("PaginateAcrossSubdirectories", func(t *testing.T) {
+		maxKeys := int32(10) // Force many pages to exercise marker skipping
+		var allVersions []types.ObjectVersion
+		var keyMarker, versionIdMarker *string
+		pageCount := 0
+		pageStartTimes := make([]time.Duration, 0)
+
+		for {
+			pageStart := time.Now()
+			resp, err := client.ListObjectVersions(context.TODO(), &s3.ListObjectVersionsInput{
+				Bucket:          aws.String(bucketName),
+				Prefix:          aws.String(orgPrefix + "/"),
+				MaxKeys:         aws.Int32(maxKeys),
+				KeyMarker:       keyMarker,
+				VersionIdMarker: versionIdMarker,
+			})
+			pageDuration := time.Since(pageStart)
+			require.NoError(t, err)
+			pageCount++
+			pageStartTimes = append(pageStartTimes, pageDuration)
+
+			allVersions = append(allVersions, resp.Versions...)
+			t.Logf("Page %d: %d versions in %v (marker: %v)",
+				pageCount, len(resp.Versions), pageDuration,
+				keyMarker)
+
+			if resp.IsTruncated == nil || !*resp.IsTruncated {
+				break
+			}
+			keyMarker = resp.NextKeyMarker
+			versionIdMarker = resp.NextVersionIdMarker
+		}
+
+		assert.Greater(t, pageCount, 1, "Should require multiple pages")
+
+		// Verify listed keys exactly match the keys we created (same elements, same order)
+		listedKeys := make([]string, 0, len(allVersions))
+		for _, v := range allVersions {
+			listedKeys = append(listedKeys, *v.Key)
+		}
+		assert.Equal(t, allKeys, listedKeys,
+			"Listed version keys should exactly match created keys")
+
+		// Check that later pages don't take dramatically longer than earlier ones.
+		// Before the fix, later pages were exponentially slower because they
+		// re-traversed the entire tree. With the fix, all pages should be similar.
+		if len(pageStartTimes) >= 4 {
+			firstQuarter := pageStartTimes[0]
+			lastQuarter := pageStartTimes[len(pageStartTimes)-1]
+			t.Logf("First page: %v, Last page: %v, Ratio: %.1fx",
+				firstQuarter, lastQuarter,
+				float64(lastQuarter)/float64(firstQuarter))
+			// Allow generous 10x ratio to avoid flakiness; before the fix
+			// the ratio was 100x+ on large datasets
+			if lastQuarter > firstQuarter*10 && lastQuarter > 500*time.Millisecond {
+				t.Errorf("Last page took %.1fx longer than first page (%v vs %v) — possible pagination regression",
+					float64(lastQuarter)/float64(firstQuarter), lastQuarter, firstQuarter)
+			}
+		}
+	})
+
+	// Test 2: Paginate with delimiter to verify CommonPrefixes interaction
+	t.Run("PaginateWithDelimiterAcrossSubdirs", func(t *testing.T) {
+		maxKeys := int32(5)
+		var allPrefixes []string
+		var keyMarker *string
+		pageCount := 0
+
+		for {
+			resp, err := client.ListObjectVersions(context.TODO(), &s3.ListObjectVersionsInput{
+				Bucket:    aws.String(bucketName),
+				Prefix:    aws.String(orgPrefix + "/"),
+				Delimiter: aws.String("/"),
+				MaxKeys:   aws.Int32(maxKeys),
+				KeyMarker: keyMarker,
+			})
+			require.NoError(t, err)
+			pageCount++
+
+			for _, cp := range resp.CommonPrefixes {
+				allPrefixes = append(allPrefixes, *cp.Prefix)
+			}
+
+			if resp.IsTruncated == nil || !*resp.IsTruncated {
+				break
+			}
+			keyMarker = resp.NextKeyMarker
+		}
+
+		assert.Greater(t, pageCount, 1, "Should require multiple pages with maxKeys=%d", maxKeys)
+
+		// Build the exact expected prefixes
+		expectedPrefixes := make([]string, 0, numMailboxes)
+		for i := 0; i < numMailboxes; i++ {
+			expectedPrefixes = append(expectedPrefixes,
+				fmt.Sprintf("%s/mbx-%03d/", orgPrefix, i))
+		}
+		assert.Equal(t, expectedPrefixes, allPrefixes,
+			"CommonPrefixes should exactly match expected mailbox prefixes")
+	})
+}
+
 // listAllVersions is a helper to list all versions of a specific object using pagination
 func listAllVersions(t *testing.T, client *s3.Client, bucketName, objectKey string) []types.ObjectVersion {
 	var allVersions []types.ObjectVersion

test/s3tables/catalog/duckdb_oauth_test.go

@@ -0,0 +1,465 @@
+package catalog
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/testutil"
+)
+
+// oauthTestEnv holds a weed mini instance started with IAM credentials
+// so that the OAuth token endpoint is functional.
+type oauthTestEnv struct {
+	seaweedDir     string
+	weedBinary     string
+	dataDir        string
+	bindIP         string
+	s3Port         int
+	s3GrpcPort     int
+	icebergPort    int
+	masterPort     int
+	masterGrpcPort int
+	filerPort      int
+	filerGrpcPort  int
+	volumePort     int
+	volumeGrpcPort int
+	webdavPort     int
+	weedProcess    *exec.Cmd
+	weedCancel     context.CancelFunc
+	accessKey      string
+	secretKey      string
+}
+
+func newOAuthTestEnv(t *testing.T) *oauthTestEnv {
+	t.Helper()
+
+	wd, err := os.Getwd()
+	if err != nil {
+		t.Fatalf("get working directory: %v", err)
+	}
+
+	seaweedDir := wd
+	for i := 0; i < 6; i++ {
+		if _, err := os.Stat(filepath.Join(seaweedDir, "go.mod")); err == nil {
+			break
+		}
+		seaweedDir = filepath.Dir(seaweedDir)
+	}
+
+	weedBinary := filepath.Join(seaweedDir, "weed", "weed")
+	if info, err := os.Stat(weedBinary); err != nil || info.IsDir() {
+		weedBinary = "weed"
+		if _, err := exec.LookPath(weedBinary); err != nil {
+			t.Skip("weed binary not found, skipping integration test")
+		}
+	}
+
+	dataDir, err := os.MkdirTemp("", "seaweed-oauth-test-*")
+	if err != nil {
+		t.Fatalf("create temp dir: %v", err)
+	}
+
+	bindIP := testutil.FindBindIP()
+	ports := testutil.MustAllocatePorts(t, 10)
+
+	return &oauthTestEnv{
+		seaweedDir:     seaweedDir,
+		weedBinary:     weedBinary,
+		dataDir:        dataDir,
+		bindIP:         bindIP,
+		masterPort:     ports[0],
+		masterGrpcPort: ports[1],
+		volumePort:     ports[2],
+		volumeGrpcPort: ports[3],
+		filerPort:      ports[4],
+		filerGrpcPort:  ports[5],
+		s3Port:         ports[6],
+		s3GrpcPort:     ports[7],
+		icebergPort:    ports[8],
+		webdavPort:     ports[9],
+		accessKey:      "AKIAIOSFODNN7EXAMPLE",
+		secretKey:      "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
+	}
+}
+
+func (env *oauthTestEnv) start(t *testing.T) {
+	t.Helper()
+
+	iamConfigPath, err := testutil.WriteIAMConfig(env.dataDir, env.accessKey, env.secretKey)
+	if err != nil {
+		t.Fatalf("write IAM config: %v", err)
+	}
+
+	securityToml := filepath.Join(env.dataDir, "security.toml")
+	if err := os.WriteFile(securityToml, []byte("# Empty security config for testing\n"), 0644); err != nil {
+		t.Fatalf("write security.toml: %v", err)
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	env.weedCancel = cancel
+
+	cmd := exec.CommandContext(ctx, env.weedBinary, "mini",
+		"-master.port", fmt.Sprintf("%d", env.masterPort),
+		"-master.port.grpc", fmt.Sprintf("%d", env.masterGrpcPort),
+		"-volume.port", fmt.Sprintf("%d", env.volumePort),
+		"-volume.port.grpc", fmt.Sprintf("%d", env.volumeGrpcPort),
+		"-filer.port", fmt.Sprintf("%d", env.filerPort),
+		"-filer.port.grpc", fmt.Sprintf("%d", env.filerGrpcPort),
+		"-s3.port", fmt.Sprintf("%d", env.s3Port),
+		"-s3.port.grpc", fmt.Sprintf("%d", env.s3GrpcPort),
+		"-s3.port.iceberg", fmt.Sprintf("%d", env.icebergPort),
+		"-webdav.port", fmt.Sprintf("%d", env.webdavPort),
+		"-s3.config", iamConfigPath,
+		"-ip", env.bindIP,
+		"-ip.bind", "0.0.0.0",
+		"-dir", env.dataDir,
+	)
+	cmd.Dir = env.dataDir
+	cmd.Stdout = os.Stdout
+	cmd.Stderr = os.Stderr
+	cmd.Env = append(os.Environ(),
+		"AWS_ACCESS_KEY_ID="+env.accessKey,
+		"AWS_SECRET_ACCESS_KEY="+env.secretKey,
+	)
+
+	if err := cmd.Start(); err != nil {
+		cancel()
+		t.Fatalf("start weed mini: %v", err)
+	}
+	env.weedProcess = cmd
+
+	icebergURL := fmt.Sprintf("http://%s:%d/v1/config", env.bindIP, env.icebergPort)
+	if !testutil.WaitForService(icebergURL, 30*time.Second) {
+		cancel()
+		cmd.Wait()
+		t.Fatalf("Iceberg REST API did not become ready at %s", icebergURL)
+	}
+}
+
+func (env *oauthTestEnv) cleanup(t *testing.T) {
+	t.Helper()
+	if env.weedCancel != nil {
+		env.weedCancel()
+	}
+	if env.weedProcess != nil {
+		env.weedProcess.Wait()
+	}
+	if env.dataDir != "" {
+		os.RemoveAll(env.dataDir)
+	}
+}
+
+func (env *oauthTestEnv) icebergURL() string {
+	return fmt.Sprintf("http://%s:%d", env.bindIP, env.icebergPort)
+}
+
+// TestOAuthTokenEndpoint tests the /v1/oauth/tokens endpoint directly via HTTP.
+func TestOAuthTokenEndpoint(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	env := newOAuthTestEnv(t)
+	defer env.cleanup(t)
+	env.start(t)
+
+	t.Run("valid credentials", func(t *testing.T) {
+		token := requestOAuthToken(t, env, env.accessKey, env.secretKey)
+		if token == "" {
+			t.Fatal("expected non-empty token")
+		}
+	})
+
+	t.Run("invalid secret", func(t *testing.T) {
+		resp, err := http.PostForm(env.icebergURL()+"/v1/oauth/tokens", url.Values{
+			"grant_type":    {"client_credentials"},
+			"client_id":     {env.accessKey},
+			"client_secret": {"wrong-secret"},
+		})
+		if err != nil {
+			t.Fatalf("POST /v1/oauth/tokens: %v", err)
+		}
+		defer resp.Body.Close()
+
+		if resp.StatusCode != http.StatusUnauthorized {
+			body, _ := io.ReadAll(resp.Body)
+			t.Fatalf("expected 401, got %d: %s", resp.StatusCode, body)
+		}
+	})
+
+	t.Run("missing grant_type", func(t *testing.T) {
+		resp, err := http.PostForm(env.icebergURL()+"/v1/oauth/tokens", url.Values{
+			"client_id":     {env.accessKey},
+			"client_secret": {env.secretKey},
+		})
+		if err != nil {
+			t.Fatalf("POST /v1/oauth/tokens: %v", err)
+		}
+		defer resp.Body.Close()
+
+		if resp.StatusCode != http.StatusBadRequest {
+			body, _ := io.ReadAll(resp.Body)
+			t.Fatalf("expected 400, got %d: %s", resp.StatusCode, body)
+		}
+	})
+
+	t.Run("bearer token auth on catalog endpoint", func(t *testing.T) {
+		token := requestOAuthToken(t, env, env.accessKey, env.secretKey)
+
+		// Use the token to call the catalog
+		req, err := http.NewRequest(http.MethodGet, env.icebergURL()+"/v1/namespaces", nil)
+		if err != nil {
+			t.Fatalf("create request: %v", err)
+		}
+		req.Header.Set("Authorization", "Bearer "+token)
+
+		resp, err := http.DefaultClient.Do(req)
+		if err != nil {
+			t.Fatalf("GET /v1/namespaces with Bearer: %v", err)
+		}
+		defer resp.Body.Close()
+
+		// Auth should pass. We accept 200 (success) or 500 (missing warehouse bucket
+		// is an internal error, not an auth error). Reject 401/403/404/405.
+		body, _ := io.ReadAll(resp.Body)
+		switch resp.StatusCode {
+		case http.StatusOK, http.StatusInternalServerError:
+			t.Logf("Bearer token auth succeeded, status=%d", resp.StatusCode)
+		default:
+			t.Fatalf("Bearer auth failed unexpectedly: status=%d body=%s", resp.StatusCode, body)
+		}
+	})
+}
+
+// TestDuckDBOAuthIntegration tests that DuckDB can connect to the Iceberg REST
+// catalog using the OAuth2 client_credentials flow (CREATE SECRET with client_id
+// and client_secret). This is the scenario reported in issue #9015.
+func TestDuckDBOAuthIntegration(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+	if !testutil.HasDocker() {
+		t.Skip("Docker not available, skipping DuckDB OAuth integration test")
+	}
+
+	env := newOAuthTestEnv(t)
+	defer env.cleanup(t)
+	env.start(t)
+
+	// Create a table bucket and namespace so DuckDB has something to query
+	bucketName := "duckdb-oauth-" + randomSuffix()
+	createTableBucketViaShell(t, env, bucketName)
+
+	// Create a namespace via the Iceberg REST API using OAuth token
+	token := requestOAuthToken(t, env, env.accessKey, env.secretKey)
+	createNamespaceWithToken(t, env, token, bucketName, "testns")
+
+	sqlContent := fmt.Sprintf(`
+INSTALL iceberg;
+LOAD iceberg;
+
+CREATE SECRET iceberg_secret (
+    TYPE ICEBERG,
+    ENDPOINT 'http://host.docker.internal:%d',
+    CLIENT_ID '%s',
+    CLIENT_SECRET '%s',
+    SCOPE 's3://%s/'
+);
+
+CREATE SECRET s3_secret (
+    TYPE S3,
+    KEY_ID '%s',
+    SECRET '%s',
+    ENDPOINT 'host.docker.internal:%d',
+    URL_STYLE 'path',
+    USE_SSL false,
+    SCOPE 's3://%s/'
+);
+
+SELECT 'OAuth token obtained successfully' as status;
+
+-- Try listing namespaces via the Iceberg catalog
+SELECT * FROM iceberg_scan('iceberg_secret', ALLOW_MOVED_PATHS => TRUE) LIMIT 0;
+`, env.icebergPort, env.accessKey, env.secretKey, bucketName,
+		env.accessKey, env.secretKey, env.s3Port, bucketName)
+
+	sqlFile := filepath.Join(env.dataDir, "duckdb_oauth_test.sql")
+	if err := os.WriteFile(sqlFile, []byte(sqlContent), 0644); err != nil {
+		t.Fatalf("write SQL file: %v", err)
+	}
+
+	// Run DuckDB in Docker.
+	// We use a simple test: get a token, create a secret, and verify the
+	// Iceberg extension can communicate with the catalog.
+	// The simpler fallback test just verifies CREATE SECRET succeeds (no 404).
+	fallbackSQL := fmt.Sprintf(`
+INSTALL iceberg;
+LOAD iceberg;
+
+CREATE SECRET (
+    TYPE ICEBERG,
+    ENDPOINT 'http://host.docker.internal:%d',
+    CLIENT_ID '%s',
+    CLIENT_SECRET '%s'
+);
+
+SELECT 'DuckDB Iceberg OAuth secret created successfully' as result;
+`, env.icebergPort, env.accessKey, env.secretKey)
+
+	fallbackFile := filepath.Join(env.dataDir, "duckdb_oauth_fallback.sql")
+	if err := os.WriteFile(fallbackFile, []byte(fallbackSQL), 0644); err != nil {
+		t.Fatalf("write fallback SQL file: %v", err)
+	}
+
+	// Try the full SQL script first (CREATE SECRET + catalog access).
+	// Fall back to the simple CREATE SECRET test if iceberg_scan isn't supported.
+	cmd := exec.Command("docker", "run", "--rm",
+		"-v", fmt.Sprintf("%s:/test", env.dataDir),
+		"--add-host", "host.docker.internal:host-gateway",
+		"--entrypoint", "duckdb",
+		"duckdb/duckdb:latest",
+		"-init", "/test/duckdb_oauth_test.sql",
+		"-c", "SELECT 1",
+	)
+
+	output, err := cmd.CombinedOutput()
+	outputStr := string(output)
+	t.Logf("DuckDB output:\n%s", outputStr)
+
+	if err != nil {
+		if strings.Contains(outputStr, "iceberg extension is not available") ||
+			strings.Contains(outputStr, "Failed to load") {
+			t.Skip("Skipping: Iceberg extension not available in DuckDB Docker image")
+		}
+		// The key check: the old error was "HTTP NotFound_404" on /v1/oauth/tokens.
+		// With our fix, this should no longer happen.
+		if strings.Contains(outputStr, "NotFound_404") && strings.Contains(outputStr, "/v1/oauth/tokens") {
+			t.Fatal("OAuth token endpoint returned 404 - the fix is not working")
+		}
+		// If iceberg_scan failed but CREATE SECRET worked, fall back to simpler test
+		if strings.Contains(outputStr, "OAuth token obtained successfully") {
+			t.Logf("Full SQL had partial success (token obtained), iceberg_scan may not be supported. Continuing.")
+		} else {
+			// Try the fallback script that only tests CREATE SECRET
+			t.Logf("Full SQL failed, trying fallback CREATE SECRET test...")
+			fallbackCmd := exec.Command("docker", "run", "--rm",
+				"-v", fmt.Sprintf("%s:/test", env.dataDir),
+				"--add-host", "host.docker.internal:host-gateway",
+				"--entrypoint", "duckdb",
+				"duckdb/duckdb:latest",
+				"-init", "/test/duckdb_oauth_fallback.sql",
+				"-c", "SELECT 1",
+			)
+			fallbackOutput, fallbackErr := fallbackCmd.CombinedOutput()
+			fallbackStr := string(fallbackOutput)
+			t.Logf("DuckDB fallback output:\n%s", fallbackStr)
+
+			if fallbackErr != nil {
+				if strings.Contains(fallbackStr, "NotFound_404") && strings.Contains(fallbackStr, "/v1/oauth/tokens") {
+					t.Fatal("OAuth token endpoint returned 404 - the fix is not working")
+				}
+				t.Fatalf("DuckDB fallback also failed: %v\nOutput: %s", fallbackErr, fallbackStr)
+			}
+			if !strings.Contains(fallbackStr, "DuckDB Iceberg OAuth secret created successfully") {
+				t.Errorf("expected success message in fallback output, got:\n%s", fallbackStr)
+			}
+			return
+		}
+	}
+
+	if strings.Contains(outputStr, "OAuth token obtained successfully") {
+		t.Logf("DuckDB OAuth CREATE SECRET succeeded")
+	} else {
+		t.Errorf("expected OAuth success message in output, got:\n%s", outputStr)
+	}
+}
+
+// requestOAuthToken obtains a bearer token from the OAuth endpoint.
+func requestOAuthToken(t *testing.T, env *oauthTestEnv, accessKey, secretKey string) string {
+	t.Helper()
+
+	resp, err := http.PostForm(env.icebergURL()+"/v1/oauth/tokens", url.Values{
+		"grant_type":    {"client_credentials"},
+		"client_id":     {accessKey},
+		"client_secret": {secretKey},
+	})
+	if err != nil {
+		t.Fatalf("POST /v1/oauth/tokens: %v", err)
+	}
+	defer resp.Body.Close()
+
+	body, _ := io.ReadAll(resp.Body)
+
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("OAuth token request failed: status=%d body=%s", resp.StatusCode, body)
+	}
+
+	var tokenResp struct {
+		AccessToken string `json:"access_token"`
+		TokenType   string `json:"token_type"`
+		ExpiresIn   int    `json:"expires_in"`
+	}
+	if err := json.Unmarshal(body, &tokenResp); err != nil {
+		t.Fatalf("decode token response: %v", err)
+	}
+
+	if tokenResp.AccessToken == "" {
+		t.Fatal("got empty access_token")
+	}
+	if tokenResp.TokenType != "bearer" {
+		t.Errorf("expected token_type=bearer, got %s", tokenResp.TokenType)
+	}
+	return tokenResp.AccessToken
+}
+
+// createTableBucketViaShell creates a table bucket using weed shell,
+// which bypasses S3 auth. This is the same approach used by the Trino tests.
+func createTableBucketViaShell(t *testing.T, env *oauthTestEnv, bucketName string) {
+	t.Helper()
+
+	cmd := exec.Command(env.weedBinary, "shell",
+		fmt.Sprintf("-master=%s:%d.%d", env.bindIP, env.masterPort, env.masterGrpcPort),
+	)
+	cmd.Stdin = strings.NewReader(fmt.Sprintf("s3tables.bucket -create -name %s -account 000000000000\nexit\n", bucketName))
+	output, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("create table bucket %s via weed shell: %v\nOutput: %s", bucketName, err, output)
+	}
+	t.Logf("Created table bucket %s", bucketName)
+}
+
+// createNamespaceWithToken creates a namespace using a Bearer token.
+func createNamespaceWithToken(t *testing.T, env *oauthTestEnv, token, bucketName, namespace string) {
+	t.Helper()
+
+	path := fmt.Sprintf("/v1/%s/namespaces", bucketName)
+	body := fmt.Sprintf(`{"namespace":["%s"]}`, namespace)
+	req, err := http.NewRequest(http.MethodPost, env.icebergURL()+path, strings.NewReader(body))
+	if err != nil {
+		t.Fatalf("create request: %v", err)
+	}
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+token)
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatalf("create namespace: %v", err)
+	}
+	defer resp.Body.Close()
+
+	respBody, _ := io.ReadAll(resp.Body)
+	if resp.StatusCode != http.StatusOK && resp.StatusCode != http.StatusConflict {
+		t.Fatalf("create namespace failed: status=%d body=%s", resp.StatusCode, respBody)
+	}
+	t.Logf("Created namespace %s in bucket %s", namespace, bucketName)
+}

test/s3tables/catalog/iceberg_catalog_test.go

@@ -9,7 +9,6 @@ import (
 	"flag"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"os"
 	"os/exec"
@@ -17,6 +16,8 @@ import (
 	"strings"
 	"testing"
 	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 // sharedEnv is the single TestEnvironment shared across all tests in this package.
@@ -69,23 +70,6 @@ type TestEnvironment struct {
 	dockerAvailable bool
 }
 
-// hasDocker checks if Docker is available
-func hasDocker() bool {
-	cmd := exec.Command("docker", "version")
-	return cmd.Run() == nil
-}
-
-// getFreePort returns an available ephemeral port and its listener
-func getFreePort() (int, net.Listener, error) {
-	listener, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		return 0, nil, err
-	}
-
-	addr := listener.Addr().(*net.TCPAddr)
-	return addr.Port, listener, nil
-}
-
 // newTestEnvironmentForMain creates a TestEnvironment without calling t.Fatalf so it
 // can be used from TestMain (which has no *testing.T).
 func newTestEnvironmentForMain() (*TestEnvironment, error) {
@@ -118,95 +102,27 @@ func newTestEnvironmentForMain() (*TestEnvironment, error) {
 		return nil, fmt.Errorf("create temp dir: %w", err)
 	}
 
-	// Allocate free ephemeral ports for each service
-	var listeners []net.Listener
-	closeListeners := func() {
-		for _, l := range listeners {
-			l.Close()
-		}
-	}
-
-	var l net.Listener
-	s3Port, l, err := getFreePort()
+	// Allocate 9 unique ports atomically: s3, iceberg, s3Grpc, master, masterGrpc,
+	// filer, filerGrpc, volume, volumeGrpc
+	ports, err := testutil.AllocatePorts(9)
 	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for S3: %w", err)
+		return nil, fmt.Errorf("allocate ports: %w", err)
 	}
-	listeners = append(listeners, l)
-
-	icebergPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Iceberg: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	s3GrpcPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for S3 gRPC: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	masterPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Master: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	masterGrpcPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Master gRPC: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	filerPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Filer: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	filerGrpcPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Filer gRPC: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	volumePort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Volume: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	volumeGrpcPort, l, err := getFreePort()
-	if err != nil {
-		closeListeners()
-		return nil, fmt.Errorf("get free port for Volume gRPC: %w", err)
-	}
-	listeners = append(listeners, l)
-
-	// Release the port reservations so weed mini can bind to them
-	closeListeners()
 
 	return &TestEnvironment{
 		seaweedDir:      seaweedDir,
 		weedBinary:      weedBinary,
 		dataDir:         dataDir,
-		s3Port:          s3Port,
-		s3GrpcPort:      s3GrpcPort,
-		icebergPort:     icebergPort,
-		masterPort:      masterPort,
-		masterGrpcPort:  masterGrpcPort,
-		filerPort:       filerPort,
-		filerGrpcPort:   filerGrpcPort,
-		volumePort:      volumePort,
-		volumeGrpcPort:  volumeGrpcPort,
-		dockerAvailable: hasDocker(),
+		s3Port:          ports[0],
+		s3GrpcPort:      ports[1],
+		icebergPort:     ports[2],
+		masterPort:      ports[3],
+		masterGrpcPort:  ports[4],
+		filerPort:       ports[5],
+		filerGrpcPort:   ports[6],
+		volumePort:      ports[7],
+		volumeGrpcPort:  ports[8],
+		dockerAvailable: testutil.HasDocker(),
 	}, nil
 }
 

test/s3tables/catalog_risingwave/setup_test.go

@@ -18,7 +18,7 @@ import (
 
 	v4 "github.com/aws/aws-sdk-go-v2/aws/signer/v4"
 	"github.com/aws/aws-sdk-go-v2/credentials"
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 var (
@@ -114,11 +114,12 @@ func (env *TestEnvironment) StartSeaweedFS(t *testing.T) {
 		t.Fatalf("failed to create temp directory: %v", err)
 	}
 
-	env.masterPort = testutil.MustFreeMiniPort(t, "Master")
-	env.filerPort = testutil.MustFreeMiniPort(t, "Filer")
-	env.s3Port = testutil.MustFreeMiniPort(t, "S3")
-	env.icebergRestPort = testutil.MustFreeMiniPort(t, "Iceberg")
-	env.risingwavePort = testutil.MustFreeMiniPort(t, "RisingWave")
+	ports := testutil.MustFreeMiniPorts(t, []string{"Master", "Filer", "S3", "Iceberg", "RisingWave"})
+	env.masterPort = ports[0]
+	env.filerPort = ports[1]
+	env.s3Port = ports[2]
+	env.icebergRestPort = ports[3]
+	env.risingwavePort = ports[4]
 
 	env.bindIP = testutil.FindBindIP()
 

test/s3tables/catalog_spark/setup_test.go

@@ -16,7 +16,7 @@ import (
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/testcontainers/testcontainers-go"
 )
 
@@ -90,10 +90,11 @@ func (env *TestEnvironment) StartSeaweedFS(t *testing.T) {
 		t.Fatalf("failed to create temp directory: %v", err)
 	}
 
-	env.masterPort = testutil.MustFreeMiniPort(t, "Master")
-	env.filerPort = testutil.MustFreeMiniPort(t, "Filer")
-	env.s3Port = testutil.MustFreeMiniPort(t, "S3")
-	env.icebergRestPort = testutil.MustFreeMiniPort(t, "Iceberg")
+	ports := testutil.MustFreeMiniPorts(t, []string{"Master", "Filer", "S3", "Iceberg"})
+	env.masterPort = ports[0]
+	env.filerPort = ports[1]
+	env.s3Port = ports[2]
+	env.icebergRestPort = ports[3]
 
 	bindIP := testutil.FindBindIP()
 

test/s3tables/catalog_spark/spark_operations_test.go

@@ -277,3 +277,80 @@ print(f"Count at snapshot: {count}")
 
 	t.Logf(">>> Time travel test passed")
 }
+
+// TestSparkMultiLevelNamespace tests that multi-level namespaces produce correct
+// S3 paths (dot-separated) so that Spark can read back the data it writes.
+// Regression test for https://github.com/seaweedfs/seaweedfs/issues/8959
+func TestSparkMultiLevelNamespace(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	env, _, _ := setupSparkTestEnv(t)
+
+	// Use a two-level namespace like "analytics.daily"
+	nsLevel1 := "analytics_" + randomString(4)
+	nsLevel2 := "daily_" + randomString(4)
+	multiNs := fmt.Sprintf("%s.%s", nsLevel1, nsLevel2)
+	tableName := "events_" + randomString(4)
+
+	// Create multi-level namespace
+	t.Logf(">>> Creating multi-level namespace: %s", multiNs)
+	createNsSQL := fmt.Sprintf(`
+spark.sql("CREATE NAMESPACE iceberg.%s")
+print("Namespace created")
+`, multiNs)
+	output := runSparkPySQL(t, env.sparkContainer, createNsSQL, env.icebergRestPort, env.s3Port)
+	if !strings.Contains(output, "Namespace created") {
+		t.Fatalf("multi-level namespace creation failed, output: %s", output)
+	}
+
+	// Create table under multi-level namespace
+	t.Logf(">>> Creating table under multi-level namespace")
+	createTableSQL := fmt.Sprintf(`
+spark.sql("""
+CREATE TABLE iceberg.%s.%s (
+    id INT,
+    event STRING,
+    ts TIMESTAMP
+)
+USING iceberg
+""")
+print("Table created")
+`, multiNs, tableName)
+	output = runSparkPySQL(t, env.sparkContainer, createTableSQL, env.icebergRestPort, env.s3Port)
+	if !strings.Contains(output, "Table created") {
+		t.Fatalf("table creation under multi-level namespace failed, output: %s", output)
+	}
+
+	// Insert data
+	t.Logf(">>> Inserting data into multi-level namespace table")
+	insertSQL := fmt.Sprintf(`
+spark.sql("""
+INSERT INTO iceberg.%s.%s VALUES
+    (1, 'click', TIMESTAMP '2025-01-01 00:00:00'),
+    (2, 'view',  TIMESTAMP '2025-01-01 01:00:00'),
+    (3, 'click', TIMESTAMP '2025-01-02 00:00:00')
+""")
+print("Data inserted")
+`, multiNs, tableName)
+	output = runSparkPySQL(t, env.sparkContainer, insertSQL, env.icebergRestPort, env.s3Port)
+	if !strings.Contains(output, "Data inserted") {
+		t.Fatalf("data insertion failed, output: %s", output)
+	}
+
+	// Query data back — this is the key test: if the namespace path separator
+	// was wrong (\x1F instead of "."), Spark would not find the data files.
+	t.Logf(">>> Querying data from multi-level namespace table")
+	querySQL := fmt.Sprintf(`
+result = spark.sql("SELECT COUNT(*) as count FROM iceberg.%s.%s")
+count = result.collect()[0]['count']
+print(f"Row count: {count}")
+`, multiNs, tableName)
+	output = runSparkPySQL(t, env.sparkContainer, querySQL, env.icebergRestPort, env.s3Port)
+	if !strings.Contains(output, "Row count: 3") {
+		t.Errorf("expected row count 3 from multi-level namespace table, got output: %s", output)
+	}
+
+	t.Logf(">>> Multi-level namespace test passed")
+}

test/s3tables/catalog_trino/trino_catalog_test.go

@@ -17,7 +17,7 @@ import (
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 type TestEnvironment struct {
@@ -40,7 +40,6 @@ type TestEnvironment struct {
 	dockerAvailable bool
 	accessKey       string
 	secretKey       string
-	closers         []io.Closer
 }
 
 func TestTrinoIcebergCatalog(t *testing.T) {
@@ -82,6 +81,101 @@ func TestTrinoIcebergCatalog(t *testing.T) {
 	runTrinoSQL(t, env.trinoContainer, fmt.Sprintf("SHOW TABLES FROM iceberg.%s", schemaName))
 }
 
+// TestTrinoMultiLevelNamespace tests that multi-level namespaces (dot-separated)
+// produce correct S3 paths so Trino can read back data it writes.
+// Regression test for https://github.com/seaweedfs/seaweedfs/issues/8959
+func TestTrinoMultiLevelNamespace(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping integration test in short mode")
+	}
+
+	env := NewTestEnvironment(t)
+	defer env.Cleanup(t)
+
+	if !env.dockerAvailable {
+		t.Skip("Docker not available, skipping Trino integration test")
+	}
+
+	t.Logf(">>> Starting SeaweedFS...")
+	env.StartSeaweedFS(t)
+
+	tableBucket := "iceberg-tables"
+	createTableBucket(t, env, tableBucket)
+
+	configDir := env.writeTrinoConfig(t, tableBucket, withNestedNamespace())
+	env.startTrinoContainer(t, configDir)
+	waitForTrino(t, env.trinoContainer, 60*time.Second)
+
+	// Use a two-level namespace: "analytics.daily"
+	nsLevel1 := "analytics_" + randomString(4)
+	nsLevel2 := "daily_" + randomString(4)
+	flatNs := fmt.Sprintf("%s.%s", nsLevel1, nsLevel2)
+	// Trino uses double-quoted schema names for multi-level namespaces
+	multiNs := fmt.Sprintf(`"%s"`, flatNs)
+	tableName := "events_" + randomString(4)
+
+	// Create multi-level namespace (schema)
+	t.Logf(">>> Creating multi-level schema: %s", flatNs)
+	runTrinoSQL(t, env.trinoContainer, fmt.Sprintf("CREATE SCHEMA IF NOT EXISTS iceberg.%s", multiNs))
+
+	// Verify the schema shows up
+	output := runTrinoSQL(t, env.trinoContainer, "SHOW SCHEMAS FROM iceberg")
+	if !strings.Contains(output, flatNs) {
+		t.Fatalf("Expected schema %s in output:\n%s", flatNs, output)
+	}
+
+	// Create table with explicit location to avoid non-empty location conflict.
+	// The location uses the dot-separated namespace — if #8959 regresses
+	// (unit separator instead of dot), data would be written to the wrong path.
+	tableLocation := fmt.Sprintf("s3://%s/%s/%s_%s", tableBucket, flatNs, tableName, randomString(6))
+	t.Logf(">>> Creating table at location: %s", tableLocation)
+	createSQL := fmt.Sprintf(`CREATE TABLE IF NOT EXISTS iceberg.%s.%s (
+		id INTEGER,
+		event VARCHAR,
+		ts TIMESTAMP(6)
+	) WITH (
+		format = 'PARQUET',
+		location = '%s'
+	)`, multiNs, tableName, tableLocation)
+	runTrinoSQLAllowExists(t, env.trinoContainer, createSQL)
+
+	// Insert data
+	t.Logf(">>> Inserting data into multi-level namespace table")
+	runTrinoSQL(t, env.trinoContainer, fmt.Sprintf(`
+		INSERT INTO iceberg.%s.%s VALUES
+			(1, 'click', TIMESTAMP '2025-01-01 00:00:00'),
+			(2, 'view',  TIMESTAMP '2025-01-01 01:00:00'),
+			(3, 'click', TIMESTAMP '2025-01-02 00:00:00')
+	`, multiNs, tableName))
+
+	// Query data back — if the namespace path separator were wrong (\x1F
+	// instead of "."), the metadata location would point to a non-existent
+	// S3 path and this query would fail.
+	t.Logf(">>> Querying data from multi-level namespace table")
+	countOutput := runTrinoSQL(t, env.trinoContainer, fmt.Sprintf(
+		"SELECT count(*) FROM iceberg.%s.%s", multiNs, tableName))
+	rowCount := mustParseCSVInt64(t, countOutput)
+	if rowCount != 3 {
+		t.Fatalf("expected row count 3, got %d", rowCount)
+	}
+
+	// Verify the S3 file path contains the dot-separated namespace, not \x1F.
+	filesOutput := runTrinoSQL(t, env.trinoContainer, fmt.Sprintf(
+		`SELECT file_path FROM iceberg.%s."%s$files" LIMIT 1`, multiNs, tableName))
+	filePath := strings.TrimSpace(filesOutput)
+	if filePath == "" {
+		t.Fatalf("expected at least one data file, got empty output")
+	}
+	if !strings.Contains(filePath, flatNs+"/") {
+		t.Errorf("expected file path to contain dot-separated namespace %q, got: %s", flatNs, filePath)
+	}
+	if strings.Contains(filePath, "\x1F") {
+		t.Errorf("file path contains unit separator (\\x1F), expected dot separator: %s", filePath)
+	}
+
+	t.Logf(">>> Trino multi-level namespace test passed")
+}
+
 func NewTestEnvironment(t *testing.T) *TestEnvironment {
 	t.Helper()
 
@@ -119,19 +213,24 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 
 	bindIP := testutil.FindBindIP()
 
-	env := &TestEnvironment{
-		seaweedDir: seaweedDir,
-		weedBinary: weedBinary,
-		dataDir:    dataDir,
-		bindIP:     bindIP,
-		closers:    []io.Closer{},
-	}
+	// 9 ports: master(2), volume(2), filer(2), s3(2), iceberg(1)
+	ports := testutil.MustAllocatePorts(t, 9)
 
-	env.masterPort, env.masterGrpcPort = env.mustFreePortPair("Master")
-	env.volumePort, env.volumeGrpcPort = env.mustFreePortPair("Volume")
-	env.filerPort, env.filerGrpcPort = env.mustFreePortPair("Filer")
-	env.s3Port, env.s3GrpcPort = env.mustFreePortPair("S3")
-	env.icebergPort = env.mustFreePort("Iceberg")
+	env := &TestEnvironment{
+		seaweedDir:     seaweedDir,
+		weedBinary:     weedBinary,
+		dataDir:        dataDir,
+		bindIP:         bindIP,
+		masterPort:     ports[0],
+		masterGrpcPort: ports[1],
+		volumePort:     ports[2],
+		volumeGrpcPort: ports[3],
+		filerPort:      ports[4],
+		filerGrpcPort:  ports[5],
+		s3Port:         ports[6],
+		s3GrpcPort:     ports[7],
+		icebergPort:    ports[8],
+	}
 
 	env.dockerAvailable = hasDocker()
 	env.accessKey = "AKIAIOSFODNN7EXAMPLE"
@@ -140,47 +239,6 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 	return env
 }
 
-func (env *TestEnvironment) mustFreePort(name string) int {
-	port, closer, err := getFreePort()
-	if err != nil {
-		panic(fmt.Sprintf("Failed to get free port for %s: %v", name, err))
-	}
-	env.closers = append(env.closers, closer)
-	return port
-}
-
-func (env *TestEnvironment) mustFreePortPair(name string) (int, int) {
-	httpPort, httpCloser, grpcPort, grpcCloser, err := findAvailablePortPair()
-	if err != nil {
-		panic(fmt.Sprintf("Failed to get free port pair for %s: %v", name, err))
-	}
-	env.closers = append(env.closers, httpCloser, grpcCloser)
-	return httpPort, grpcPort
-}
-
-func mustFreePort(t *testing.T, name string) int {
-	t.Helper()
-
-	port, closer, err := getFreePort()
-	if err != nil {
-		t.Fatalf("Failed to get free port for %s: %v", name, err)
-	}
-	closer.Close()
-	return port
-}
-
-func mustFreePortPair(t *testing.T, name string) (int, int) {
-	t.Helper()
-
-	httpPort, httpCloser, grpcPort, grpcCloser, err := findAvailablePortPair()
-	if err != nil {
-		t.Fatalf("Failed to get free port pair for %s: %v", name, err)
-	}
-	httpCloser.Close()
-	grpcCloser.Close()
-	return httpPort, grpcPort
-}
-
 func (env *TestEnvironment) StartSeaweedFS(t *testing.T) {
 	t.Helper()
 
@@ -198,12 +256,6 @@ func (env *TestEnvironment) StartSeaweedFS(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	env.weedCancel = cancel
 
-	// Close all port listeners right before starting the weed process
-	for _, closer := range env.closers {
-		closer.Close()
-	}
-	env.closers = nil
-
 	cmd := exec.CommandContext(ctx, env.weedBinary, "mini",
 		"-master.port", fmt.Sprintf("%d", env.masterPort),
 		"-master.port.grpc", fmt.Sprintf("%d", env.masterGrpcPort),
@@ -332,18 +384,32 @@ func testIcebergRestAPI(t *testing.T, env *TestEnvironment) {
 	}
 }
 
-func (env *TestEnvironment) writeTrinoConfig(t *testing.T, warehouseBucket string) string {
+func (env *TestEnvironment) writeTrinoConfig(t *testing.T, warehouseBucket string, opts ...func(*trinoConfigOptions)) string {
 	t.Helper()
 
-	configDir := filepath.Join(env.dataDir, "trino")
+	o := trinoConfigOptions{}
+	for _, fn := range opts {
+		fn(&o)
+	}
+
+	dirName := "trino"
+	if o.nestedNamespace {
+		dirName = "trino-nested"
+	}
+	configDir := filepath.Join(env.dataDir, dirName)
 	if err := os.MkdirAll(configDir, 0755); err != nil {
 		t.Fatalf("Failed to create Trino config dir: %v", err)
 	}
 
+	nestedLine := ""
+	if o.nestedNamespace {
+		nestedLine = "\niceberg.rest-catalog.nested-namespace-enabled=true"
+	}
+
 	config := fmt.Sprintf(`connector.name=iceberg
 iceberg.catalog.type=rest
 iceberg.rest-catalog.uri=http://host.docker.internal:%d
-iceberg.rest-catalog.warehouse=s3://%s
+iceberg.rest-catalog.warehouse=s3://%s%s
 iceberg.file-format=PARQUET
 iceberg.unique-table-location=true
 
@@ -358,7 +424,7 @@ s3.region=us-west-2
 
 # REST catalog authentication
 iceberg.rest-catalog.security=SIGV4
-`, env.icebergPort, warehouseBucket, env.s3Port, env.accessKey, env.secretKey)
+`, env.icebergPort, warehouseBucket, nestedLine, env.s3Port, env.accessKey, env.secretKey)
 
 	if err := os.WriteFile(filepath.Join(configDir, "iceberg.properties"), []byte(config), 0644); err != nil {
 		t.Fatalf("Failed to write Trino config: %v", err)
@@ -367,6 +433,14 @@ iceberg.rest-catalog.security=SIGV4
 	return configDir
 }
 
+type trinoConfigOptions struct {
+	nestedNamespace bool
+}
+
+func withNestedNamespace() func(*trinoConfigOptions) {
+	return func(o *trinoConfigOptions) { o.nestedNamespace = true }
+}
+
 func (env *TestEnvironment) startTrinoContainer(t *testing.T, configDir string) {
 	t.Helper()
 
@@ -514,29 +588,6 @@ func hasDocker() bool {
 	return cmd.Run() == nil
 }
 
-func findAvailablePortPair() (int, io.Closer, int, io.Closer, error) {
-	httpPort, httpCloser, err := getFreePort()
-	if err != nil {
-		return 0, nil, 0, nil, err
-	}
-	grpcPort, grpcCloser, err := getFreePort()
-	if err != nil {
-		httpCloser.Close()
-		return 0, nil, 0, nil, err
-	}
-	return httpPort, httpCloser, grpcPort, grpcCloser, nil
-}
-
-func getFreePort() (int, io.Closer, error) {
-	listener, err := net.Listen("tcp", "0.0.0.0:0")
-	if err != nil {
-		return 0, nil, err
-	}
-
-	addr := listener.Addr().(*net.TCPAddr)
-	return addr.Port, listener, nil
-}
-
 func randomString(length int) string {
 	const charset = "abcdefghijklmnopqrstuvwxyz0123456789"
 	b := make([]byte, length)

test/s3tables/lakekeeper/lakekeeper_test.go

@@ -25,7 +25,7 @@ import (
 	s3types "github.com/aws/aws-sdk-go-v2/service/s3/types"
 	"github.com/aws/aws-sdk-go-v2/service/sts"
 
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
 )
 
@@ -115,10 +115,13 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 
 	bindIP := testutil.FindBindIP()
 
-	masterPort, masterGrpcPort := testutil.MustFreePortPair(t, "Master")
-	volumePort, volumeGrpcPort := testutil.MustFreePortPair(t, "Volume")
-	filerPort, filerGrpcPort := testutil.MustFreePortPair(t, "Filer")
-	s3Port, s3GrpcPort := testutil.MustFreePortPair(t, "S3")
+	// Allocate all ports in a single batch to prevent the OS from recycling
+	// a released port, which can cause two services to get the same port.
+	ports := testutil.MustAllocatePorts(t, 8)
+	masterPort, masterGrpcPort := ports[0], ports[1]
+	volumePort, volumeGrpcPort := ports[2], ports[3]
+	filerPort, filerGrpcPort := ports[4], ports[5]
+	s3Port, s3GrpcPort := ports[6], ports[7]
 
 	return &TestEnvironment{
 		seaweedDir:     seaweedDir,

test/s3tables/maintenance/maintenance_integration_test.go

@@ -16,7 +16,6 @@ import (
 	"flag"
 	"fmt"
 	"io"
-	"net"
 	"net/http"
 	"os"
 	"path"
@@ -40,6 +39,7 @@ import (
 	"google.golang.org/grpc"
 	"google.golang.org/grpc/credentials/insecure"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/weed/command"
 	"github.com/seaweedfs/seaweedfs/weed/filer"
 	"github.com/seaweedfs/seaweedfs/weed/glog"
@@ -92,7 +92,7 @@ func TestMain(m *testing.M) {
 }
 
 func startCluster(testDir string, extraArgs []string) (*testCluster, error) {
-	ports, err := findPorts(10)
+	ports, err := testutil.AllocatePorts(10)
 	if err != nil {
 		return nil, err
 	}
@@ -201,26 +201,6 @@ func (c *testCluster) filerConn(t *testing.T) (*grpc.ClientConn, filer_pb.Seawee
 	return conn, filer_pb.NewSeaweedFilerClient(conn)
 }
 
-func findPorts(n int) ([]int, error) {
-	ls := make([]*net.TCPListener, n)
-	ps := make([]int, n)
-	for i := 0; i < n; i++ {
-		l, err := net.Listen("tcp", "127.0.0.1:0")
-		if err != nil {
-			for j := 0; j < i; j++ {
-				ls[j].Close()
-			}
-			return nil, err
-		}
-		ls[i] = l.(*net.TCPListener)
-		ps[i] = ls[i].Addr().(*net.TCPAddr).Port
-	}
-	for _, l := range ls {
-		l.Close()
-	}
-	return ps, nil
-}
-
 func waitReady(endpoint string, timeout time.Duration) error {
 	client := &http.Client{Timeout: 1 * time.Second}
 	deadline := time.Now().Add(timeout)

test/s3tables/polaris/polaris_env_test.go

@@ -19,7 +19,7 @@ import (
 	"github.com/aws/aws-sdk-go-v2/credentials"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
 
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 const (
@@ -89,11 +89,14 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 
 	bindIP := testutil.FindBindIP()
 
-	masterPort, masterGrpcPort := testutil.MustFreePortPair(t, "Master")
-	volumePort, volumeGrpcPort := testutil.MustFreePortPair(t, "Volume")
-	filerPort, filerGrpcPort := testutil.MustFreePortPair(t, "Filer")
-	s3Port, s3GrpcPort := testutil.MustFreePortPair(t, "S3")
-	polarisPort, polarisAdminPort := testutil.MustFreePortPair(t, "Polaris")
+	// Allocate all ports in a single batch to prevent the OS from recycling
+	// a released port, which can cause two services to get the same port.
+	ports := testutil.MustAllocatePorts(t, 10)
+	masterPort, masterGrpcPort := ports[0], ports[1]
+	volumePort, volumeGrpcPort := ports[2], ports[3]
+	filerPort, filerGrpcPort := ports[4], ports[5]
+	s3Port, s3GrpcPort := ports[6], ports[7]
+	polarisPort, polarisAdminPort := ports[8], ports[9]
 
 	return &TestEnvironment{
 		seaweedDir:       seaweedDir,

test/s3tables/sts_integration/sts_integration_test.go

@@ -9,7 +9,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/seaweedfs/seaweedfs/test/s3tables/testutil"
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 )
 
 // TestEnvironment mirrors the one in trino_catalog_test.go but simplified
@@ -93,10 +93,13 @@ func NewTestEnvironment(t *testing.T) *TestEnvironment {
 
 	bindIP := testutil.FindBindIP()
 
-	masterPort, masterGrpcPort := testutil.MustFreePortPair(t, "Master")
-	volumePort, volumeGrpcPort := testutil.MustFreePortPair(t, "Volume")
-	filerPort, filerGrpcPort := testutil.MustFreePortPair(t, "Filer")
-	s3Port, s3GrpcPort := testutil.MustFreePortPair(t, "S3") // Changed to use testutil.MustFreePortPair
+	// Allocate all ports in a single batch to prevent the OS from recycling
+	// a released port, which can cause two services to get the same port.
+	ports := testutil.MustAllocatePorts(t, 8)
+	masterPort, masterGrpcPort := ports[0], ports[1]
+	volumePort, volumeGrpcPort := ports[2], ports[3]
+	filerPort, filerGrpcPort := ports[4], ports[5]
+	s3Port, s3GrpcPort := ports[6], ports[7]
 
 	return &TestEnvironment{
 		seaweedDir:      seaweedDir,

test/s3tables/table-buckets/s3tables_integration_test.go

@@ -3,7 +3,6 @@ package s3tables
 import (
 	"context"
 	"fmt"
-	"net"
 	"net/http"
 	"os"
 	"path/filepath"
@@ -18,6 +17,7 @@ import (
 
 	"flag"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/weed/command"
 	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/s3api/s3tables"
@@ -590,40 +590,12 @@ func testTargetOperations(t *testing.T, client *S3TablesClient) {
 
 // Helper functions
 
-// findAvailablePorts finds n available ports by binding to port 0 multiple times
-// It keeps the listeners open until all ports are found to ensure uniqueness
-func findAvailablePorts(n int) ([]int, error) {
-	listeners := make([]*net.TCPListener, n)
-	ports := make([]int, n)
-
-	// Open all listeners to ensure we get unique ports
-	for i := 0; i < n; i++ {
-		listener, err := net.Listen("tcp", "127.0.0.1:0")
-		if err != nil {
-			// Close valid listeners before returning error
-			for j := 0; j < i; j++ {
-				listeners[j].Close()
-			}
-			return nil, err
-		}
-		listeners[i] = listener.(*net.TCPListener)
-		ports[i] = listeners[i].Addr().(*net.TCPAddr).Port
-	}
-
-	// Close all listeners
-	for _, l := range listeners {
-		l.Close()
-	}
-
-	return ports, nil
-}
-
 // startMiniClusterInDir starts a weed mini instance using testDir as the data
 // directory. It does not require a *testing.T so it can be called from TestMain.
 // extraArgs are appended to the default mini command flags.
 func startMiniClusterInDir(testDir string, extraArgs []string) (*TestCluster, error) {
 	// We need 10 unique ports: Master(2), Volume(2), Filer(2), S3(2), Admin(2)
-	ports, err := findAvailablePorts(10)
+	ports, err := testutil.AllocatePorts(10)
 	if err != nil {
 		return nil, fmt.Errorf("failed to find available ports: %v", err)
 	}

test/s3tables/testutil/docker.go

@@ -1,81 +0,0 @@
-package testutil
-
-import (
-	"context"
-	"fmt"
-	"net"
-	"net/http"
-	"os/exec"
-	"testing"
-	"time"
-)
-
-func HasDocker() bool {
-	cmd := exec.Command("docker", "version")
-	return cmd.Run() == nil
-}
-
-func MustFreePortPair(t *testing.T, name string) (int, int) {
-	httpPort, grpcPort, err := findAvailablePortPair()
-	if err != nil {
-		t.Fatalf("Failed to get free port pair for %s: %v", name, err)
-	}
-	return httpPort, grpcPort
-}
-
-func findAvailablePortPair() (int, int, error) {
-	httpPort, err := GetFreePort()
-	if err != nil {
-		return 0, 0, err
-	}
-	grpcPort, err := GetFreePort()
-	if err != nil {
-		return 0, 0, err
-	}
-	return httpPort, grpcPort, nil
-}
-
-func GetFreePort() (int, error) {
-	listener, err := net.Listen("tcp", "0.0.0.0:0")
-	if err != nil {
-		return 0, err
-	}
-	defer listener.Close()
-	return listener.Addr().(*net.TCPAddr).Port, nil
-}
-
-func WaitForService(url string, timeout time.Duration) bool {
-	client := &http.Client{Timeout: 2 * time.Second}
-	ctx, cancel := context.WithTimeout(context.Background(), timeout)
-	defer cancel()
-
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
-
-	for {
-		select {
-		case <-ctx.Done():
-			return false
-		case <-ticker.C:
-			resp, err := client.Get(url)
-			if err == nil {
-				resp.Body.Close()
-				return true
-			}
-		}
-	}
-}
-
-func WaitForPort(port int, timeout time.Duration) bool {
-	deadline := time.Now().Add(timeout)
-	address := fmt.Sprintf("127.0.0.1:%d", port)
-	for time.Now().Before(deadline) {
-		conn, err := net.DialTimeout("tcp", address, 500*time.Millisecond)
-		if err == nil {
-			_ = conn.Close()
-			return true
-		}
-		time.Sleep(100 * time.Millisecond)
-	}
-	return false
-}

test/testutil/helpers.go

@@ -1,17 +1,25 @@
 package testutil
 
 import (
+	"context"
 	"fmt"
-	"math/rand"
 	"net"
+	"net/http"
 	"os"
+	"os/exec"
 	"path/filepath"
-	"testing"
 	"time"
 )
 
 const SeaweedMiniStartupTimeout = 45 * time.Second
 
+func HasDocker() bool {
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+	cmd := exec.CommandContext(ctx, "docker", "version")
+	return cmd.Run() == nil
+}
+
 func FindBindIP() string {
 	addrs, err := net.InterfaceAddrs()
 	if err != nil {
@@ -60,34 +68,38 @@ func WriteIAMConfig(dir, accessKey, secretKey string) (string, error) {
 	return iamConfigPath, nil
 }
 
-func MustFreeMiniPort(t *testing.T, name string) int {
-	t.Helper()
+func WaitForService(url string, timeout time.Duration) bool {
+	client := &http.Client{Timeout: 2 * time.Second}
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
 
-	const (
-		minPort = 10000
-		maxPort = 55000
-	)
-	r := rand.New(rand.NewSource(time.Now().UnixNano()))
+	ticker := time.NewTicker(500 * time.Millisecond)
+	defer ticker.Stop()
 
-	for i := 0; i < 1000; i++ {
-		port := minPort + r.Intn(maxPort-minPort)
-
-		listener, err := net.Listen("tcp", fmt.Sprintf("127.0.0.1:%d", port))
-		if err != nil {
-			continue
+	for {
+		select {
+		case <-ctx.Done():
+			return false
+		case <-ticker.C:
+			resp, err := client.Get(url)
+			if err == nil {
+				resp.Body.Close()
+				return true
+			}
 		}
-		_ = listener.Close()
-
-		grpcPort := port + 10000
-		grpcListener, err := net.Listen("tcp", fmt.Sprintf("127.0.0.1:%d", grpcPort))
-		if err != nil {
-			continue
-		}
-		_ = grpcListener.Close()
-
-		return port
 	}
+}
 
-	t.Fatalf("failed to get free weed mini port for %s", name)
-	return 0
+func WaitForPort(port int, timeout time.Duration) bool {
+	deadline := time.Now().Add(timeout)
+	address := fmt.Sprintf("127.0.0.1:%d", port)
+	for time.Now().Before(deadline) {
+		conn, err := net.DialTimeout("tcp", address, 500*time.Millisecond)
+		if err == nil {
+			_ = conn.Close()
+			return true
+		}
+		time.Sleep(100 * time.Millisecond)
+	}
+	return false
 }

test/testutil/ports.go

@@ -0,0 +1,120 @@
+// Package testutil provides shared test utilities for SeaweedFS integration tests.
+package testutil
+
+import (
+	"fmt"
+	"math/rand"
+	"net"
+	"testing"
+)
+
+// GrpcPortOffset is the offset weed mini uses to derive gRPC ports from HTTP ports.
+const GrpcPortOffset = 10000
+
+// AllocatePorts allocates count unique free ports atomically.
+// All listeners are held open until every port is obtained, preventing
+// the OS from recycling a port between successive allocations.
+func AllocatePorts(count int) ([]int, error) {
+	listeners := make([]net.Listener, 0, count)
+	ports := make([]int, 0, count)
+	for i := 0; i < count; i++ {
+		l, err := net.Listen("tcp", "127.0.0.1:0")
+		if err != nil {
+			for _, ll := range listeners {
+				_ = ll.Close()
+			}
+			return nil, err
+		}
+		listeners = append(listeners, l)
+		ports = append(ports, l.Addr().(*net.TCPAddr).Port)
+	}
+	for _, l := range listeners {
+		_ = l.Close()
+	}
+	return ports, nil
+}
+
+// MustAllocatePorts is a testing wrapper for AllocatePorts.
+func MustAllocatePorts(t *testing.T, count int) []int {
+	t.Helper()
+	ports, err := AllocatePorts(count)
+	if err != nil {
+		t.Fatalf("Failed to allocate %d free ports: %v", count, err)
+	}
+	return ports
+}
+
+// AllocateMiniPorts allocates n free ports where each port and its gRPC
+// counterpart (port + GrpcPortOffset) are available and don't collide
+// with any other allocated port or its gRPC counterpart. All listeners
+// are held open until the entire batch is allocated, preventing the OS
+// from recycling ports between allocations. Use this when ports will be
+// passed to weed mini without explicit gRPC port flags, so mini will
+// derive gRPC ports as HTTP + 10000.
+func AllocateMiniPorts(count int) ([]int, error) {
+	const (
+		minPort = 10000
+		maxPort = 55000
+	)
+	reserved := make(map[int]bool)
+	ports := make([]int, 0, count)
+	var listeners []net.Listener
+	defer func() {
+		for _, l := range listeners {
+			l.Close()
+		}
+	}()
+
+	for idx := 0; idx < count; idx++ {
+		found := false
+		for i := 0; i < 1000; i++ {
+			port := minPort + rand.Intn(maxPort-minPort)
+			grpcPort := port + GrpcPortOffset
+
+			if reserved[port] || reserved[grpcPort] {
+				continue
+			}
+
+			l1, err := net.Listen("tcp", fmt.Sprintf("127.0.0.1:%d", port))
+			if err != nil {
+				continue
+			}
+
+			l2, err := net.Listen("tcp", fmt.Sprintf("127.0.0.1:%d", grpcPort))
+			if err != nil {
+				l1.Close()
+				continue
+			}
+
+			listeners = append(listeners, l1, l2)
+			reserved[port] = true
+			reserved[grpcPort] = true
+			ports = append(ports, port)
+			found = true
+			break
+		}
+		if !found {
+			return nil, fmt.Errorf("failed to allocate mini port %d of %d", idx+1, count)
+		}
+	}
+
+	return ports, nil
+}
+
+// MustFreeMiniPorts allocates n ports suitable for weed mini, ensuring
+// each port's gRPC offset (port + 10000) doesn't collide with any other
+// allocated port. names is used only for error messages.
+func MustFreeMiniPorts(t *testing.T, names []string) []int {
+	t.Helper()
+	ports, err := AllocateMiniPorts(len(names))
+	if err != nil {
+		t.Fatalf("failed to allocate mini ports for %v: %v", names, err)
+	}
+	return ports
+}
+
+// MustFreeMiniPort allocates a single weed mini port.
+func MustFreeMiniPort(t *testing.T, name string) int {
+	t.Helper()
+	return MustFreeMiniPorts(t, []string{name})[0]
+}

test/volume_server/framework/cluster.go

@@ -18,6 +18,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 )
 
@@ -84,12 +85,14 @@ func StartSingleVolumeCluster(t testing.TB, profile matrix.Profile) *Cluster {
 		t.Fatalf("write security config: %v", err)
 	}
 
-	masterPort, masterGrpcPort, err := allocateMasterPortPair()
+	miniPorts, err := testutil.AllocateMiniPorts(1)
 	if err != nil {
 		t.Fatalf("allocate master port pair: %v", err)
 	}
+	masterPort := miniPorts[0]
+	masterGrpcPort := masterPort + testutil.GrpcPortOffset
 
-	ports, err := allocatePorts(3)
+	ports, err := testutil.AllocatePorts(3)
 	if err != nil {
 		t.Fatalf("allocate ports: %v", err)
 	}
@@ -269,44 +272,6 @@ func stopProcess(cmd *exec.Cmd) {
 	}
 }
 
-func allocatePorts(count int) ([]int, error) {
-	listeners := make([]net.Listener, 0, count)
-	ports := make([]int, 0, count)
-	for i := 0; i < count; i++ {
-		l, err := net.Listen("tcp", "127.0.0.1:0")
-		if err != nil {
-			for _, ll := range listeners {
-				_ = ll.Close()
-			}
-			return nil, err
-		}
-		listeners = append(listeners, l)
-		ports = append(ports, l.Addr().(*net.TCPAddr).Port)
-	}
-	for _, l := range listeners {
-		_ = l.Close()
-	}
-	return ports, nil
-}
-
-func allocateMasterPortPair() (int, int, error) {
-	for masterPort := 10000; masterPort <= 55535; masterPort++ {
-		masterGrpcPort := masterPort + 10000
-		l1, err := net.Listen("tcp", net.JoinHostPort("127.0.0.1", strconv.Itoa(masterPort)))
-		if err != nil {
-			continue
-		}
-		l2, err := net.Listen("tcp", net.JoinHostPort("127.0.0.1", strconv.Itoa(masterGrpcPort)))
-		if err != nil {
-			_ = l1.Close()
-			continue
-		}
-		_ = l2.Close()
-		_ = l1.Close()
-		return masterPort, masterGrpcPort, nil
-	}
-	return 0, 0, errors.New("unable to find available master port pair")
-}
 
 func newWorkDir() (dir string, keepLogs bool, err error) {
 	keepLogs = os.Getenv("VOLUME_SERVER_IT_KEEP_LOGS") == "1"

test/volume_server/framework/cluster_mixed.go

@@ -0,0 +1,371 @@
+package framework
+
+import (
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"sync"
+	"testing"
+
+	"github.com/seaweedfs/seaweedfs/test/testutil"
+	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
+)
+
+// MixedVolumeCluster wraps a Go master + a mix of Go and Rust volume servers
+// for integration testing. Go servers occupy indices [0, goCount) and Rust
+// servers occupy indices [goCount, goCount+rustCount).
+type MixedVolumeCluster struct {
+	testingTB testing.TB
+	profile   matrix.Profile
+
+	weedBinary       string // Go weed binary (master + Go volume servers)
+	rustVolumeBinary string // Rust volume binary
+
+	baseDir   string
+	configDir string
+	logsDir   string
+	keepLogs  bool
+
+	masterPort     int
+	masterGrpcPort int
+
+	volumePorts     []int
+	volumeGrpcPorts []int
+	volumePubPorts  []int
+	isRust          []bool // which servers are Rust
+
+	masterCmd  *exec.Cmd
+	volumeCmds []*exec.Cmd
+
+	cleanupOnce sync.Once
+}
+
+// StartMixedVolumeCluster starts a cluster with 1 Go master, goCount Go volume
+// servers, and rustCount Rust volume servers. Go servers come first in the index.
+func StartMixedVolumeCluster(t testing.TB, profile matrix.Profile, goCount, rustCount int) *MixedVolumeCluster {
+	t.Helper()
+
+	if goCount < 0 || rustCount < 0 {
+		t.Fatalf("goCount and rustCount must be non-negative, got go=%d rust=%d", goCount, rustCount)
+	}
+	total := goCount + rustCount
+	if total < 2 {
+		t.Fatalf("need at least 2 volume servers, got %d", total)
+	}
+
+	weedBinary, err := FindOrBuildWeedBinary()
+	if err != nil {
+		t.Fatalf("resolve weed binary: %v", err)
+	}
+
+	// Only build the Rust binary when Rust servers are requested.
+	var rustBinary string
+	if rustCount > 0 {
+		rustBinary, err = FindOrBuildRustBinary()
+		if err != nil {
+			t.Skipf("skipping mixed cluster test: rust binary unavailable: %v", err)
+		}
+	}
+
+	baseDir, keepLogs, err := newWorkDir()
+	if err != nil {
+		t.Fatalf("create temp test directory: %v", err)
+	}
+
+	configDir := filepath.Join(baseDir, "config")
+	logsDir := filepath.Join(baseDir, "logs")
+	masterDataDir := filepath.Join(baseDir, "master")
+
+	dirs := []string{configDir, logsDir, masterDataDir}
+	for i := 0; i < total; i++ {
+		dirs = append(dirs, filepath.Join(baseDir, fmt.Sprintf("volume%d", i)))
+	}
+	for _, dir := range dirs {
+		if mkErr := os.MkdirAll(dir, 0o755); mkErr != nil {
+			t.Fatalf("create %s: %v", dir, mkErr)
+		}
+	}
+
+	if err = writeSecurityConfig(configDir, profile); err != nil {
+		t.Fatalf("write security config: %v", err)
+	}
+
+	miniPorts, err := testutil.AllocateMiniPorts(1)
+	if err != nil {
+		t.Fatalf("allocate master port pair: %v", err)
+	}
+	masterPort := miniPorts[0]
+	masterGrpcPort := masterPort + testutil.GrpcPortOffset
+
+	// 2 ports per server (admin, grpc); add 1 more when public port is split out.
+	portsPerServer := 2
+	if profile.SplitPublicPort {
+		portsPerServer = 3
+	}
+	ports, err := testutil.AllocatePorts(total * portsPerServer)
+	if err != nil {
+		t.Fatalf("allocate volume ports: %v", err)
+	}
+
+	isRust := make([]bool, total)
+	for i := goCount; i < total; i++ {
+		isRust[i] = true
+	}
+
+	c := &MixedVolumeCluster{
+		testingTB:        t,
+		profile:          profile,
+		weedBinary:       weedBinary,
+		rustVolumeBinary: rustBinary,
+		baseDir:          baseDir,
+		configDir:        configDir,
+		logsDir:          logsDir,
+		keepLogs:         keepLogs,
+		masterPort:       masterPort,
+		masterGrpcPort:   masterGrpcPort,
+		volumePorts:      make([]int, total),
+		volumeGrpcPorts:  make([]int, total),
+		volumePubPorts:   make([]int, total),
+		isRust:           isRust,
+		volumeCmds:       make([]*exec.Cmd, total),
+	}
+
+	for i := 0; i < total; i++ {
+		baseIdx := i * portsPerServer
+		c.volumePorts[i] = ports[baseIdx]
+		c.volumeGrpcPorts[i] = ports[baseIdx+1]
+		if profile.SplitPublicPort {
+			c.volumePubPorts[i] = ports[baseIdx+2]
+		} else {
+			c.volumePubPorts[i] = c.volumePorts[i] // reuse admin port
+		}
+	}
+
+	// Start master
+	if err = c.startMaster(masterDataDir); err != nil {
+		c.Stop()
+		t.Fatalf("start master: %v", err)
+	}
+	helper := &Cluster{logsDir: logsDir}
+	if err = helper.waitForHTTP(c.MasterURL() + "/dir/status"); err != nil {
+		masterLog := helper.tailLog("master.log")
+		c.Stop()
+		t.Fatalf("wait for master readiness: %v\nmaster log tail:\n%s", err, masterLog)
+	}
+
+	// Start volume servers
+	for i := 0; i < total; i++ {
+		volumeDataDir := filepath.Join(baseDir, fmt.Sprintf("volume%d", i))
+		if isRust[i] {
+			err = c.startRustVolume(i, volumeDataDir)
+		} else {
+			err = c.startGoVolume(i, volumeDataDir)
+		}
+		if err != nil {
+			logTail := helper.tailLog(fmt.Sprintf("volume%d.log", i))
+			c.Stop()
+			t.Fatalf("start volume server %d (rust=%v): %v\nlog tail:\n%s", i, isRust[i], err, logTail)
+		}
+
+		// Rust uses /healthz, Go uses /status
+		healthURL := c.VolumeAdminURL(i) + "/status"
+		if isRust[i] {
+			healthURL = c.VolumeAdminURL(i) + "/healthz"
+		}
+		if err = helper.waitForHTTP(healthURL); err != nil {
+			logTail := helper.tailLog(fmt.Sprintf("volume%d.log", i))
+			c.Stop()
+			t.Fatalf("wait for volume server %d readiness: %v\nlog tail:\n%s", i, err, logTail)
+		}
+		if err = helper.waitForTCP(c.VolumeGRPCAddress(i)); err != nil {
+			logTail := helper.tailLog(fmt.Sprintf("volume%d.log", i))
+			c.Stop()
+			t.Fatalf("wait for volume server %d grpc readiness: %v\nlog tail:\n%s", i, err, logTail)
+		}
+	}
+
+	t.Cleanup(func() {
+		c.Stop()
+	})
+
+	return c
+}
+
+func (c *MixedVolumeCluster) Stop() {
+	if c == nil {
+		return
+	}
+	c.cleanupOnce.Do(func() {
+		for i := len(c.volumeCmds) - 1; i >= 0; i-- {
+			stopProcess(c.volumeCmds[i])
+		}
+		stopProcess(c.masterCmd)
+		if !c.keepLogs && !c.testingTB.Failed() {
+			_ = os.RemoveAll(c.baseDir)
+		} else if c.baseDir != "" {
+			c.testingTB.Logf("mixed volume server integration logs kept at %s", c.baseDir)
+		}
+	})
+}
+
+func (c *MixedVolumeCluster) startMaster(dataDir string) error {
+	logFile, err := os.Create(filepath.Join(c.logsDir, "master.log"))
+	if err != nil {
+		return err
+	}
+
+	args := []string{
+		"-config_dir=" + c.configDir,
+		"master",
+		"-ip=127.0.0.1",
+		"-port=" + strconv.Itoa(c.masterPort),
+		"-port.grpc=" + strconv.Itoa(c.masterGrpcPort),
+		"-mdir=" + dataDir,
+		"-peers=none",
+		"-volumeSizeLimitMB=" + strconv.Itoa(testVolumeSizeLimitMB),
+		"-defaultReplication=000",
+	}
+
+	c.masterCmd = exec.Command(c.weedBinary, args...)
+	c.masterCmd.Dir = c.baseDir
+	c.masterCmd.Stdout = logFile
+	c.masterCmd.Stderr = logFile
+	if err = c.masterCmd.Start(); err != nil {
+		logFile.Close()
+		return err
+	}
+	logFile.Close() // child inherited the fd
+	return nil
+}
+
+func (c *MixedVolumeCluster) startGoVolume(index int, dataDir string) error {
+	logName := fmt.Sprintf("volume%d.log", index)
+	logFile, err := os.Create(filepath.Join(c.logsDir, logName))
+	if err != nil {
+		return err
+	}
+
+	args := []string{
+		"-config_dir=" + c.configDir,
+		"volume",
+		"-ip=127.0.0.1",
+		"-port=" + strconv.Itoa(c.volumePorts[index]),
+		"-port.grpc=" + strconv.Itoa(c.volumeGrpcPorts[index]),
+		"-port.public=" + strconv.Itoa(c.volumePubPorts[index]),
+		"-dir=" + dataDir,
+		"-max=16",
+		"-master=127.0.0.1:" + strconv.Itoa(c.masterPort),
+		"-readMode=" + c.profile.ReadMode,
+		"-concurrentUploadLimitMB=" + strconv.Itoa(c.profile.ConcurrentUploadLimitMB),
+		"-concurrentDownloadLimitMB=" + strconv.Itoa(c.profile.ConcurrentDownloadLimitMB),
+	}
+	if c.profile.InflightUploadTimeout > 0 {
+		args = append(args, "-inflightUploadDataTimeout="+c.profile.InflightUploadTimeout.String())
+	}
+	if c.profile.InflightDownloadTimeout > 0 {
+		args = append(args, "-inflightDownloadDataTimeout="+c.profile.InflightDownloadTimeout.String())
+	}
+
+	cmd := exec.Command(c.weedBinary, args...)
+	cmd.Dir = c.baseDir
+	cmd.Stdout = logFile
+	cmd.Stderr = logFile
+	if err = cmd.Start(); err != nil {
+		logFile.Close()
+		return err
+	}
+	logFile.Close() // child inherited the fd
+	c.volumeCmds[index] = cmd
+	return nil
+}
+
+func (c *MixedVolumeCluster) startRustVolume(index int, dataDir string) error {
+	logName := fmt.Sprintf("volume%d.log", index)
+	logFile, err := os.Create(filepath.Join(c.logsDir, logName))
+	if err != nil {
+		return err
+	}
+
+	args := rustVolumeArgs(
+		c.profile,
+		c.configDir,
+		c.masterPort,
+		c.volumePorts[index],
+		c.volumeGrpcPorts[index],
+		c.volumePubPorts[index],
+		dataDir,
+	)
+
+	cmd := exec.Command(c.rustVolumeBinary, args...)
+	cmd.Dir = c.baseDir
+	cmd.Stdout = logFile
+	cmd.Stderr = logFile
+	if err = cmd.Start(); err != nil {
+		logFile.Close()
+		return err
+	}
+	logFile.Close() // child inherited the fd
+	c.volumeCmds[index] = cmd
+	return nil
+}
+
+// --- accessor methods (mirror MultiVolumeCluster) ---
+
+func (c *MixedVolumeCluster) MasterAddress() string {
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.masterPort))
+}
+
+func (c *MixedVolumeCluster) MasterURL() string {
+	return "http://" + c.MasterAddress()
+}
+
+func (c *MixedVolumeCluster) VolumeAdminAddress(index int) string {
+	if index < 0 || index >= len(c.volumePorts) {
+		return ""
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePorts[index]))
+}
+
+func (c *MixedVolumeCluster) VolumePublicAddress(index int) string {
+	if index < 0 || index >= len(c.volumePubPorts) {
+		return ""
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePubPorts[index]))
+}
+
+func (c *MixedVolumeCluster) VolumeGRPCAddress(index int) string {
+	if index < 0 || index >= len(c.volumeGrpcPorts) {
+		return ""
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumeGrpcPorts[index]))
+}
+
+func (c *MixedVolumeCluster) VolumeAdminURL(index int) string {
+	return "http://" + c.VolumeAdminAddress(index)
+}
+
+func (c *MixedVolumeCluster) VolumePublicURL(index int) string {
+	return "http://" + c.VolumePublicAddress(index)
+}
+
+func (c *MixedVolumeCluster) BaseDir() string {
+	return c.baseDir
+}
+
+// VolumeServerAddress returns SeaweedFS server address format: ip:httpPort.grpcPort
+func (c *MixedVolumeCluster) VolumeServerAddress(index int) string {
+	if index < 0 || index >= len(c.volumePorts) {
+		return ""
+	}
+	return fmt.Sprintf("%s.%d", c.VolumeAdminAddress(index), c.volumeGrpcPorts[index])
+}
+
+func (c *MixedVolumeCluster) IsRust(index int) bool {
+	if index < 0 || index >= len(c.isRust) {
+		return false
+	}
+	return c.isRust[index]
+}

test/volume_server/framework/cluster_multi.go

@@ -10,6 +10,7 @@ import (
 	"sync"
 	"testing"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 )
 
@@ -74,10 +75,12 @@ func StartMultiVolumeCluster(t testing.TB, profile matrix.Profile, serverCount i
 		t.Fatalf("write security config: %v", err)
 	}
 
-	masterPort, masterGrpcPort, err := allocateMasterPortPair()
+	miniPorts, err := testutil.AllocateMiniPorts(1)
 	if err != nil {
 		t.Fatalf("allocate master port pair: %v", err)
 	}
+	masterPort := miniPorts[0]
+	masterGrpcPort := masterPort + testutil.GrpcPortOffset
 
 	// Allocate ports for all volume servers (3 ports per server: admin, grpc, public)
 	// If SplitPublicPort is true, we need an additional port per server
@@ -86,7 +89,7 @@ func StartMultiVolumeCluster(t testing.TB, profile matrix.Profile, serverCount i
 		portsPerServer = 4
 	}
 	totalPorts := serverCount * portsPerServer
-	ports, err := allocatePorts(totalPorts)
+	ports, err := testutil.AllocatePorts(totalPorts)
 	if err != nil {
 		t.Fatalf("allocate volume ports: %v", err)
 	}

test/volume_server/framework/cluster_multi_rust.go

@@ -10,6 +10,7 @@ import (
 	"sync"
 	"testing"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 )
 
@@ -85,10 +86,12 @@ func StartRustMultiVolumeCluster(t testing.TB, profile matrix.Profile, serverCou
 		t.Fatalf("write security config: %v", err)
 	}
 
-	masterPort, masterGrpcPort, err := allocateMasterPortPair()
+	miniPorts, err := testutil.AllocateMiniPorts(1)
 	if err != nil {
 		t.Fatalf("allocate master port pair: %v", err)
 	}
+	masterPort := miniPorts[0]
+	masterGrpcPort := masterPort + testutil.GrpcPortOffset
 
 	// Allocate ports for all volume servers (3 ports per server: admin, grpc, public)
 	// If SplitPublicPort is true, we need an additional port per server
@@ -97,7 +100,7 @@ func StartRustMultiVolumeCluster(t testing.TB, profile matrix.Profile, serverCou
 		portsPerServer = 4
 	}
 	totalPorts := serverCount * portsPerServer
-	ports, err := allocatePorts(totalPorts)
+	ports, err := testutil.AllocatePorts(totalPorts)
 	if err != nil {
 		t.Fatalf("allocate volume ports: %v", err)
 	}

test/volume_server/framework/cluster_rust.go

@@ -12,6 +12,7 @@ import (
 	"sync"
 	"testing"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 )
 
@@ -79,12 +80,14 @@ func StartRustVolumeCluster(t testing.TB, profile matrix.Profile) *RustCluster {
 		t.Fatalf("write security config: %v", err)
 	}
 
-	masterPort, masterGrpcPort, err := allocateMasterPortPair()
+	miniPorts, err := testutil.AllocateMiniPorts(1)
 	if err != nil {
 		t.Fatalf("allocate master port pair: %v", err)
 	}
+	masterPort := miniPorts[0]
+	masterGrpcPort := masterPort + testutil.GrpcPortOffset
 
-	ports, err := allocatePorts(3)
+	ports, err := testutil.AllocatePorts(3)
 	if err != nil {
 		t.Fatalf("allocate ports: %v", err)
 	}

test/volume_server/framework/cluster_with_filer.go

@@ -9,6 +9,7 @@ import (
 	"strconv"
 	"testing"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 )
 
@@ -25,7 +26,7 @@ func StartSingleVolumeClusterWithFiler(t testing.TB, profile matrix.Profile) *Cl
 
 	baseCluster := StartSingleVolumeCluster(t, profile)
 
-	ports, err := allocatePorts(2)
+	ports, err := testutil.AllocatePorts(2)
 	if err != nil {
 		t.Fatalf("allocate filer ports: %v", err)
 	}

test/volume_server/framework/volume_fixture.go

@@ -80,6 +80,42 @@ func EnableMaintenanceMode(t testing.TB, ctx context.Context, client volume_serv
 	}
 }
 
+// CorruptDatFile truncates a volume's .dat file to just the superblock (8 bytes)
+// so that needle reads fail during a full scrub due to data file size mismatch.
+func CorruptDatFile(t testing.TB, baseDir string, volumeID uint32) {
+	t.Helper()
+	datPath := filepath.Join(baseDir, "volume", fmt.Sprintf("%d.dat", volumeID))
+	// Truncate to superblock size only, removing all needle data.
+	if err := os.Truncate(datPath, 8); err != nil {
+		t.Fatalf("truncate dat file for corruption: %v", err)
+	}
+}
+
+// CorruptEcxFile appends garbage bytes to a volume's .ecx file on disk so
+// that CheckIndexFile detects a size mismatch during EC index scrub.
+func CorruptEcxFile(t testing.TB, baseDir string, volumeID uint32) {
+	t.Helper()
+	ecxPath := filepath.Join(baseDir, "volume", fmt.Sprintf("%d.ecx", volumeID))
+	f, err := os.OpenFile(ecxPath, os.O_WRONLY|os.O_APPEND, 0644)
+	if err != nil {
+		t.Fatalf("open ecx file for corruption: %v", err)
+	}
+	defer f.Close()
+	if _, err := f.Write([]byte{0xDE, 0xAD}); err != nil {
+		t.Fatalf("corrupt ecx file: %v", err)
+	}
+}
+
+// CorruptEcShardFile truncates an EC shard file to 1 byte so that local shard
+// reads fail during an EC scrub.
+func CorruptEcShardFile(t testing.TB, baseDir string, volumeID uint32, shardID int) {
+	t.Helper()
+	shardPath := filepath.Join(baseDir, "volume", fmt.Sprintf("%d.ec%02d", volumeID, shardID))
+	if err := os.Truncate(shardPath, 1); err != nil {
+		t.Fatalf("truncate EC shard file %s: %v", shardPath, err)
+	}
+}
+
 func ReadBytes(t testing.TB, client *http.Client, volumeURL, fid string) *http.Response {
 	t.Helper()
 

test/volume_server/grpc/erasure_coding_test.go

@@ -752,6 +752,87 @@ func TestEcShardsCopyFromPeerSuccess(t *testing.T) {
 	}
 }
 
+// TestEcIndexConsistencyAfterEncode verifies that every needle indexed in .ecx
+// can be read back correctly from EC shards after VolumeEcShardsGenerate.
+// This catches the race condition fixed in this PR where .ecx could reference
+// data not present in EC shards.
+func TestEcIndexConsistencyAfterEncode(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(130)
+	framework.AllocateVolume(t, grpcClient, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+
+	// Upload multiple needles of varying sizes
+	type testNeedle struct {
+		fid     string
+		payload []byte
+	}
+	needles := []testNeedle{
+		{framework.NewFileID(volumeID, 1001, 0xAABB0001), []byte("small-needle-1")},
+		{framework.NewFileID(volumeID, 1002, 0xAABB0002), make([]byte, 1024)},     // 1KB
+		{framework.NewFileID(volumeID, 1003, 0xAABB0003), make([]byte, 64*1024)},   // 64KB
+		{framework.NewFileID(volumeID, 1004, 0xAABB0004), make([]byte, 256*1024)},  // 256KB
+		{framework.NewFileID(volumeID, 1005, 0xAABB0005), []byte("small-needle-2")},
+	}
+
+	// Fill larger payloads with recognizable data
+	for i := range needles {
+		for j := range needles[i].payload {
+			needles[i].payload[j] = byte(i*37 + j%251)
+		}
+	}
+
+	for _, n := range needles {
+		resp := framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), n.fid, n.payload)
+		_ = framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload %s expected 201, got %d", n.fid, resp.StatusCode)
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	// EC encode
+	_, err := grpcClient.VolumeEcShardsGenerate(ctx, &volume_server_pb.VolumeEcShardsGenerateRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsGenerate failed: %v", err)
+	}
+
+	// Mount all data shards so reads go through the EC path
+	_, err = grpcClient.VolumeEcShardsMount(ctx, &volume_server_pb.VolumeEcShardsMountRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+		ShardIds:   []uint32{0, 1, 2, 3, 4, 5, 6, 7, 8, 9},
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsMount failed: %v", err)
+	}
+
+	// Read every needle back from EC shards and verify payload
+	for _, n := range needles {
+		readResp := framework.ReadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), n.fid)
+		readBody := framework.ReadAllAndClose(t, readResp)
+		if readResp.StatusCode != http.StatusOK {
+			t.Fatalf("EC read %s expected 200, got %d", n.fid, readResp.StatusCode)
+		}
+		if string(readBody) != string(n.payload) {
+			t.Fatalf("EC read %s payload mismatch: got %d bytes, want %d bytes", n.fid, len(readBody), len(n.payload))
+		}
+	}
+}
+
 func TestEcShardsCopyFailsWhenSourceUnavailable(t *testing.T) {
 	if testing.Short() {
 		t.Skip("skipping integration test in short mode")

test/volume_server/grpc/fetch_remote_s3_test.go

@@ -4,7 +4,6 @@ import (
 	"bytes"
 	"context"
 	"fmt"
-	"net"
 	"os"
 	"os/exec"
 	"path/filepath"
@@ -17,6 +16,7 @@ import (
 	"github.com/aws/aws-sdk-go/aws/session"
 	"github.com/aws/aws-sdk-go/service/s3"
 
+	"github.com/seaweedfs/seaweedfs/test/testutil"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
 	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
 	"github.com/seaweedfs/seaweedfs/weed/pb/remote_pb"
@@ -24,29 +24,6 @@ import (
 )
 
 // findAvailablePort finds a free TCP port on localhost.
-func findAvailablePort() (int, error) {
-	l, err := net.Listen("tcp", "127.0.0.1:0")
-	if err != nil {
-		return 0, err
-	}
-	port := l.Addr().(*net.TCPAddr).Port
-	l.Close()
-	return port, nil
-}
-
-// waitForPort waits until a TCP port is listening, up to timeout.
-func waitForPort(port int, timeout time.Duration) error {
-	deadline := time.Now().Add(timeout)
-	for time.Now().Before(deadline) {
-		conn, err := net.DialTimeout("tcp", fmt.Sprintf("127.0.0.1:%d", port), 500*time.Millisecond)
-		if err == nil {
-			conn.Close()
-			return nil
-		}
-		time.Sleep(200 * time.Millisecond)
-	}
-	return fmt.Errorf("port %d not listening after %v", port, timeout)
-}
 
 // startWeedMini starts a weed mini subprocess and returns the S3 endpoint and cleanup func.
 func startWeedMini(t *testing.T) (s3Endpoint string, cleanup func()) {
@@ -60,10 +37,11 @@ func startWeedMini(t *testing.T) (s3Endpoint string, cleanup func()) {
 		}
 	}
 
-	miniMasterPort, _ := findAvailablePort()
-	miniVolumePort, _ := findAvailablePort()
-	miniFilerPort, _ := findAvailablePort()
-	miniS3Port, _ := findAvailablePort()
+	miniPorts := testutil.MustFreeMiniPorts(t, []string{"Master", "Volume", "Filer", "S3"})
+	miniMasterPort := miniPorts[0]
+	miniVolumePort := miniPorts[1]
+	miniFilerPort := miniPorts[2]
+	miniS3Port := miniPorts[3]
 	miniDir := t.TempDir()
 	os.WriteFile(filepath.Join(miniDir, "security.toml"), []byte("# empty\n"), 0644)
 
@@ -89,11 +67,11 @@ func startWeedMini(t *testing.T) (s3Endpoint string, cleanup func()) {
 		t.Fatalf("start weed mini: %v", err)
 	}
 
-	if err := waitForPort(miniS3Port, 30*time.Second); err != nil {
+	if !testutil.WaitForPort(miniS3Port, 30*time.Second) {
 		cancel()
 		miniCmd.Wait()
 		logFile.Close()
-		t.Fatalf("weed mini S3 not ready: %v", err)
+		t.Fatalf("weed mini S3 not ready on port %d", miniS3Port)
 	}
 	t.Logf("weed mini S3 ready on port %d", miniS3Port)
 

test/volume_server/grpc/mixed_balance_test.go

@@ -0,0 +1,567 @@
+package volume_server_grpc_test
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+	"testing"
+	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
+	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
+	"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
+)
+
+// deleteAndWaitForTombstone issues an HTTP DELETE for the given fid on
+// volumeURL, asserts a successful response, then polls with GET until
+// the file returns 404 (tombstone visible) or the timeout elapses.
+func deleteAndWaitForTombstone(t *testing.T, httpClient *http.Client, volumeURL, fid string) {
+	t.Helper()
+	req, err := http.NewRequest(http.MethodDelete, fmt.Sprintf("%s/%s", volumeURL, fid), nil)
+	if err != nil {
+		t.Fatalf("build delete request for %s: %v", fid, err)
+	}
+	resp := framework.DoRequest(t, httpClient, req)
+	framework.ReadAllAndClose(t, resp)
+	if resp.StatusCode != http.StatusAccepted && resp.StatusCode != http.StatusOK {
+		t.Fatalf("delete %s: expected 200 or 202, got %d", fid, resp.StatusCode)
+	}
+	// Poll until GET returns 404 (tombstone flushed to disk).
+	deadline := time.Now().Add(5 * time.Second)
+	for time.Now().Before(deadline) {
+		getResp := framework.ReadBytes(t, httpClient, volumeURL, fid)
+		status := getResp.StatusCode
+		framework.ReadAllAndClose(t, getResp)
+		if status == http.StatusNotFound {
+			return
+		}
+		time.Sleep(50 * time.Millisecond)
+	}
+	t.Fatalf("delete %s: tombstone not visible after 5s", fid)
+}
+
+// TestMixedBalanceCopyGoToRust verifies that VolumeCopy works from a Go volume
+// server to a Rust volume server. This is the core operation behind volume
+// balancing in a mixed Go+Rust cluster.
+func TestMixedBalanceCopyGoToRust(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartMixedVolumeCluster(t, matrix.P1(), 1, 1)
+
+	// server 0 = Go, server 1 = Rust
+	conn0, goClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(0))
+	defer conn0.Close()
+	conn1, rustClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(1))
+	defer conn1.Close()
+
+	httpClient := framework.NewHTTPClient()
+
+	const volumeID = uint32(50)
+
+	// Allocate volume on Go server and upload test data
+	framework.AllocateVolume(t, goClient, volumeID, "")
+
+	testFiles := []struct {
+		key    uint64
+		cookie uint32
+		data   []byte
+	}{
+		{1, 0xAABBCCDD, []byte("hello from Go server")},
+		{2, 0x11223344, []byte("second file for balance test")},
+		{3, 0xDEADBEEF, make([]byte, 4096)}, // larger file
+	}
+
+	for _, f := range testFiles {
+		fid := framework.NewFileID(volumeID, f.key, f.cookie)
+		resp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(0), fid, f.data)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload %s: expected 201, got %d: %s", fid, resp.StatusCode, body)
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	// Read source volume status before copy
+	sourceStatus, err := goClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus on Go server: %v", err)
+	}
+	t.Logf("Source: dat=%d idx=%d files=%d version=%d",
+		sourceStatus.GetDatFileSize(), sourceStatus.GetIdxFileSize(),
+		sourceStatus.GetFileCount(), sourceStatus.GetVersion())
+
+	// Copy volume from Go (server 0) to Rust (server 1)
+	copyStream, err := rustClient.VolumeCopy(ctx, &volume_server_pb.VolumeCopyRequest{
+		VolumeId:       volumeID,
+		SourceDataNode: cluster.VolumeServerAddress(0),
+	})
+	if err != nil {
+		t.Fatalf("VolumeCopy call failed: %v", err)
+	}
+
+	var lastAppendAtNs uint64
+	for {
+		resp, recvErr := copyStream.Recv()
+		if recvErr != nil {
+			if recvErr != io.EOF {
+				t.Fatalf("VolumeCopy recv error: %v", recvErr)
+			}
+			break
+		}
+		if resp.GetLastAppendAtNs() != 0 {
+			lastAppendAtNs = resp.GetLastAppendAtNs()
+		}
+	}
+	t.Logf("VolumeCopy completed, lastAppendAtNs=%d", lastAppendAtNs)
+
+	// Verify: read volume status from Rust server
+	targetStatus, err := rustClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus on Rust server: %v", err)
+	}
+	t.Logf("Target: dat=%d idx=%d files=%d version=%d",
+		targetStatus.GetDatFileSize(), targetStatus.GetIdxFileSize(),
+		targetStatus.GetFileCount(), targetStatus.GetVersion())
+
+	if sourceStatus.GetDatFileSize() != targetStatus.GetDatFileSize() {
+		t.Fatalf("dat file size mismatch: source=%d target=%d",
+			sourceStatus.GetDatFileSize(), targetStatus.GetDatFileSize())
+	}
+	if sourceStatus.GetIdxFileSize() != targetStatus.GetIdxFileSize() {
+		t.Fatalf("idx file size mismatch: source=%d target=%d",
+			sourceStatus.GetIdxFileSize(), targetStatus.GetIdxFileSize())
+	}
+	if sourceStatus.GetFileCount() != targetStatus.GetFileCount() {
+		t.Fatalf("file count mismatch: source=%d target=%d",
+			sourceStatus.GetFileCount(), targetStatus.GetFileCount())
+	}
+
+	// Verify data can be read from Rust server
+	for _, f := range testFiles {
+		fid := framework.NewFileID(volumeID, f.key, f.cookie)
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusOK {
+			t.Fatalf("read %s from Rust server: expected 200, got %d", fid, resp.StatusCode)
+		}
+		if !bytes.Equal(body, f.data) {
+			t.Fatalf("read %s from Rust server: content mismatch (got %d bytes, want %d)", fid, len(body), len(f.data))
+		}
+	}
+}
+
+// TestMixedBalanceCopyRustToGo verifies that VolumeCopy works from a Rust
+// volume server to a Go volume server.
+func TestMixedBalanceCopyRustToGo(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartMixedVolumeCluster(t, matrix.P1(), 1, 1)
+
+	conn0, goClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(0))
+	defer conn0.Close()
+	conn1, rustClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(1))
+	defer conn1.Close()
+
+	httpClient := framework.NewHTTPClient()
+
+	const volumeID = uint32(51)
+
+	// Allocate volume on Rust server and upload test data
+	framework.AllocateVolume(t, rustClient, volumeID, "")
+
+	testFiles := []struct {
+		key    uint64
+		cookie uint32
+		data   []byte
+	}{
+		{1, 0xAABBCCDD, []byte("hello from Rust server")},
+		{2, 0x11223344, []byte("second file for reverse balance")},
+	}
+
+	for _, f := range testFiles {
+		fid := framework.NewFileID(volumeID, f.key, f.cookie)
+		resp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid, f.data)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload %s: expected 201, got %d: %s", fid, resp.StatusCode, body)
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	sourceStatus, err := rustClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus on Rust server: %v", err)
+	}
+
+	// Copy volume from Rust (server 1) to Go (server 0)
+	copyStream, err := goClient.VolumeCopy(ctx, &volume_server_pb.VolumeCopyRequest{
+		VolumeId:       volumeID,
+		SourceDataNode: cluster.VolumeServerAddress(1),
+	})
+	if err != nil {
+		t.Fatalf("VolumeCopy call failed: %v", err)
+	}
+	for {
+		_, recvErr := copyStream.Recv()
+		if recvErr != nil {
+			if recvErr != io.EOF {
+				t.Fatalf("VolumeCopy recv error: %v", recvErr)
+			}
+			break
+		}
+	}
+
+	targetStatus, err := goClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus on Go server: %v", err)
+	}
+
+	if sourceStatus.GetDatFileSize() != targetStatus.GetDatFileSize() {
+		t.Fatalf("dat file size mismatch: source=%d target=%d",
+			sourceStatus.GetDatFileSize(), targetStatus.GetDatFileSize())
+	}
+	if sourceStatus.GetIdxFileSize() != targetStatus.GetIdxFileSize() {
+		t.Fatalf("idx file size mismatch: source=%d target=%d",
+			sourceStatus.GetIdxFileSize(), targetStatus.GetIdxFileSize())
+	}
+	if sourceStatus.GetFileCount() != targetStatus.GetFileCount() {
+		t.Fatalf("file count mismatch: source=%d target=%d",
+			sourceStatus.GetFileCount(), targetStatus.GetFileCount())
+	}
+
+	// Verify data can be read from Go server
+	for _, f := range testFiles {
+		fid := framework.NewFileID(volumeID, f.key, f.cookie)
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(0), fid)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusOK {
+			t.Fatalf("read %s from Go server: expected 200, got %d", fid, resp.StatusCode)
+		}
+		if !bytes.Equal(body, f.data) {
+			t.Fatalf("read %s from Go server: content mismatch (got %d bytes, want %d)", fid, len(body), len(f.data))
+		}
+	}
+}
+
+// TestMixedBalanceCopyWithDeletes verifies that VolumeCopy correctly handles
+// volumes that have both active and deleted needles.
+func TestMixedBalanceCopyWithDeletes(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartMixedVolumeCluster(t, matrix.P1(), 1, 1)
+
+	conn0, goClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(0))
+	defer conn0.Close()
+	conn1, rustClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(1))
+	defer conn1.Close()
+
+	httpClient := framework.NewHTTPClient()
+
+	const volumeID = uint32(52)
+	framework.AllocateVolume(t, goClient, volumeID, "")
+
+	// Upload files
+	for i := uint64(1); i <= 5; i++ {
+		fid := framework.NewFileID(volumeID, i, 0x12340000+uint32(i))
+		resp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(0), fid, []byte(fmt.Sprintf("file-%d", i)))
+		framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload file %d: expected 201, got %d", i, resp.StatusCode)
+		}
+	}
+
+	// Delete some files and wait for tombstones to be visible
+	for _, key := range []uint64{2, 4} {
+		fid := framework.NewFileID(volumeID, key, 0x12340000+uint32(key))
+		deleteAndWaitForTombstone(t, httpClient, cluster.VolumeAdminURL(0), fid)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	sourceStatus, err := goClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus: %v", err)
+	}
+	t.Logf("Source after deletes: dat=%d idx=%d files=%d",
+		sourceStatus.GetDatFileSize(), sourceStatus.GetIdxFileSize(),
+		sourceStatus.GetFileCount())
+
+	// Copy volume from Go to Rust
+	copyStream, err := rustClient.VolumeCopy(ctx, &volume_server_pb.VolumeCopyRequest{
+		VolumeId:       volumeID,
+		SourceDataNode: cluster.VolumeServerAddress(0),
+	})
+	if err != nil {
+		t.Fatalf("VolumeCopy: %v", err)
+	}
+	var lastAppendAtNs uint64
+	for {
+		resp, recvErr := copyStream.Recv()
+		if recvErr != nil {
+			if recvErr != io.EOF {
+				t.Fatalf("VolumeCopy recv error: %v", recvErr)
+			}
+			break
+		}
+		if resp.GetLastAppendAtNs() != 0 {
+			lastAppendAtNs = resp.GetLastAppendAtNs()
+		}
+	}
+	if lastAppendAtNs == 0 {
+		t.Fatalf("VolumeCopy did not return a lastAppendAtNs timestamp")
+	}
+	t.Logf("VolumeCopy completed, lastAppendAtNs=%d", lastAppendAtNs)
+
+	targetStatusAfterCopy, err := rustClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus on Rust: %v", err)
+	}
+	t.Logf("Target after copy: dat=%d idx=%d files=%d",
+		targetStatusAfterCopy.GetDatFileSize(), targetStatusAfterCopy.GetIdxFileSize(),
+		targetStatusAfterCopy.GetFileCount())
+
+	if sourceStatus.GetDatFileSize() != targetStatusAfterCopy.GetDatFileSize() {
+		t.Fatalf("dat file size mismatch: source=%d target=%d",
+			sourceStatus.GetDatFileSize(), targetStatusAfterCopy.GetDatFileSize())
+	}
+	if sourceStatus.GetIdxFileSize() != targetStatusAfterCopy.GetIdxFileSize() {
+		t.Fatalf("idx file size mismatch: source=%d target=%d",
+			sourceStatus.GetIdxFileSize(), targetStatusAfterCopy.GetIdxFileSize())
+	}
+
+	// Tail from the copy checkpoint — source is unchanged (deletes happened
+	// before copy), so tailing should not append any data.
+	_, err = rustClient.VolumeTailReceiver(ctx, &volume_server_pb.VolumeTailReceiverRequest{
+		VolumeId:           volumeID,
+		SinceNs:            lastAppendAtNs,
+		IdleTimeoutSeconds: 3,
+		SourceVolumeServer: cluster.VolumeServerAddress(0),
+	})
+	if err != nil {
+		t.Fatalf("VolumeTailReceiver: %v", err)
+	}
+
+	targetStatusAfterTail, err := rustClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("ReadVolumeFileStatus after tail: %v", err)
+	}
+	if targetStatusAfterTail.GetDatFileSize() != targetStatusAfterCopy.GetDatFileSize() {
+		t.Fatalf("dat grew after tail: before=%d after=%d",
+			targetStatusAfterCopy.GetDatFileSize(), targetStatusAfterTail.GetDatFileSize())
+	}
+	if targetStatusAfterTail.GetIdxFileSize() != targetStatusAfterCopy.GetIdxFileSize() {
+		t.Fatalf("idx grew after tail: before=%d after=%d",
+			targetStatusAfterCopy.GetIdxFileSize(), targetStatusAfterTail.GetIdxFileSize())
+	}
+
+	// Verify surviving files are readable from Rust
+	for _, key := range []uint64{1, 3, 5} {
+		fid := framework.NewFileID(volumeID, key, 0x12340000+uint32(key))
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusOK {
+			t.Fatalf("read surviving file %d from Rust: expected 200, got %d", key, resp.StatusCode)
+		}
+		expected := fmt.Sprintf("file-%d", key)
+		if string(body) != expected {
+			t.Fatalf("data mismatch for file %d: got %q want %q", key, body, expected)
+		}
+	}
+
+	// Verify deleted files return 404
+	for _, key := range []uint64{2, 4} {
+		fid := framework.NewFileID(volumeID, key, 0x12340000+uint32(key))
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid)
+		framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusNotFound {
+			t.Fatalf("read deleted file %d from Rust: expected 404, got %d", key, resp.StatusCode)
+		}
+	}
+}
+
+// TestMixedBalanceFullMoveGoToRust exercises the complete volume balance move
+// flow: mark readonly → copy → tail → verify sizes → delete source.
+// This mirrors the steps in balance_task.go Execute().
+func TestMixedBalanceFullMoveGoToRust(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartMixedVolumeCluster(t, matrix.P1(), 1, 1)
+
+	conn0, goClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(0))
+	defer conn0.Close()
+	conn1, rustClient := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress(1))
+	defer conn1.Close()
+
+	httpClient := framework.NewHTTPClient()
+
+	const volumeID = uint32(53)
+	framework.AllocateVolume(t, goClient, volumeID, "")
+
+	// Upload test data
+	for i := uint64(1); i <= 5; i++ {
+		fid := framework.NewFileID(volumeID, i, 0xABCD0000+uint32(i))
+		resp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(0), fid, []byte(fmt.Sprintf("balance-move-file-%d", i)))
+		framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload file %d: expected 201, got %d", i, resp.StatusCode)
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+
+	// Step 1: Copy volume to Rust server (source stays writable so we can
+	// delete after copy to exercise the tail tombstone path)
+	copyStream, err := rustClient.VolumeCopy(ctx, &volume_server_pb.VolumeCopyRequest{
+		VolumeId:       volumeID,
+		SourceDataNode: cluster.VolumeServerAddress(0),
+	})
+	if err != nil {
+		t.Fatalf("VolumeCopy: %v", err)
+	}
+	var lastAppendAtNs uint64
+	for {
+		resp, recvErr := copyStream.Recv()
+		if recvErr != nil {
+			if recvErr != io.EOF {
+				t.Fatalf("VolumeCopy recv: %v", recvErr)
+			}
+			break
+		}
+		if resp.GetLastAppendAtNs() != 0 {
+			lastAppendAtNs = resp.GetLastAppendAtNs()
+		}
+	}
+	t.Logf("Copy done, lastAppendAtNs=%d", lastAppendAtNs)
+
+	// Step 2: Delete file 3 on the source AFTER copy. This creates a
+	// tombstone needle that the tail step must propagate to the Rust server.
+	deleteAndWaitForTombstone(t, httpClient, cluster.VolumeAdminURL(0),
+		framework.NewFileID(volumeID, 3, 0xABCD0003))
+
+	// Step 3: Mark source readonly so no further writes arrive during tail
+	_, err = goClient.VolumeMarkReadonly(ctx, &volume_server_pb.VolumeMarkReadonlyRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("mark readonly: %v", err)
+	}
+
+	// Read source status (the reference for post-tail verification)
+	sourceStatus, err := goClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("read source status: %v", err)
+	}
+	t.Logf("Source: dat=%d idx=%d files=%d",
+		sourceStatus.GetDatFileSize(), sourceStatus.GetIdxFileSize(),
+		sourceStatus.GetFileCount())
+
+	// Step 4: Tail for updates — this must pick up the delete tombstone
+	_, err = rustClient.VolumeTailReceiver(ctx, &volume_server_pb.VolumeTailReceiverRequest{
+		VolumeId:           volumeID,
+		SinceNs:            lastAppendAtNs,
+		IdleTimeoutSeconds: 5,
+		SourceVolumeServer: cluster.VolumeServerAddress(0),
+	})
+	if err != nil {
+		t.Fatalf("VolumeTailReceiver: %v", err)
+	}
+
+	// Step 5: Verify dat/idx sizes match after tail.
+	// We compare file sizes (byte-level correctness) rather than file_count
+	// because the tail writes the tombstone via the write path (which
+	// increments file_count) while the source used the delete path (which
+	// only increments deletion_count). This is consistent with Go behavior.
+	targetStatus, err := rustClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("read target status: %v", err)
+	}
+	t.Logf("Target: dat=%d idx=%d files=%d",
+		targetStatus.GetDatFileSize(), targetStatus.GetIdxFileSize(),
+		targetStatus.GetFileCount())
+
+	if sourceStatus.GetDatFileSize() != targetStatus.GetDatFileSize() {
+		t.Fatalf("dat size mismatch after tail: source=%d target=%d",
+			sourceStatus.GetDatFileSize(), targetStatus.GetDatFileSize())
+	}
+	if sourceStatus.GetIdxFileSize() != targetStatus.GetIdxFileSize() {
+		t.Fatalf("idx size mismatch after tail: source=%d target=%d",
+			sourceStatus.GetIdxFileSize(), targetStatus.GetIdxFileSize())
+	}
+
+	// Step 6: Delete volume from source
+	_, err = goClient.VolumeDelete(ctx, &volume_server_pb.VolumeDeleteRequest{
+		VolumeId: volumeID,
+	})
+	if err != nil {
+		t.Fatalf("delete source volume: %v", err)
+	}
+
+	// Verify source volume is gone
+	_, err = goClient.ReadVolumeFileStatus(ctx, &volume_server_pb.ReadVolumeFileStatusRequest{
+		VolumeId: volumeID,
+	})
+	if err == nil {
+		t.Fatalf("expected error reading deleted source volume, got nil")
+	}
+	t.Logf("Source volume deleted successfully (error as expected: %v)", err)
+
+	// Verify all surviving data is readable from Rust (the new home)
+	for _, key := range []uint64{1, 2, 4, 5} {
+		fid := framework.NewFileID(volumeID, key, 0xABCD0000+uint32(key))
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid)
+		body := framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusOK {
+			t.Fatalf("read file %d from Rust after move: expected 200, got %d", key, resp.StatusCode)
+		}
+		expected := fmt.Sprintf("balance-move-file-%d", key)
+		if string(body) != expected {
+			t.Fatalf("data mismatch for file %d after move: got %q want %q", key, body, expected)
+		}
+	}
+
+	// Verify deleted file is 404 on Rust (tombstone propagated via tail)
+	{
+		fid := framework.NewFileID(volumeID, 3, 0xABCD0003)
+		resp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(1), fid)
+		framework.ReadAllAndClose(t, resp)
+		if resp.StatusCode != http.StatusNotFound {
+			t.Fatalf("deleted file 3 on Rust: expected 404, got %d", resp.StatusCode)
+		}
+	}
+
+	t.Logf("Full balance move completed: volume %d moved from Go to Rust, source purged", volumeID)
+}

test/volume_server/grpc/scrub_integration_test.go

@@ -0,0 +1,416 @@
+package volume_server_grpc_test
+
+import (
+	"context"
+	"net/http"
+	"testing"
+	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
+	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
+	"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
+	"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
+)
+
+// --- Normal volume scrub tests ---
+
+func TestScrubVolumeFullHealthy(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(200)
+	framework.AllocateVolume(t, grpcClient, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(volumeID, 1, 1), []byte("data-one")))
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(volumeID, 2, 2), []byte("data-two")))
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(volumeID, 3, 3), []byte("data-three")))
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubVolume(ctx, &volume_server_pb.ScrubVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_FULL,
+	})
+	if err != nil {
+		t.Fatalf("ScrubVolume FULL on healthy volume failed: %v", err)
+	}
+	if resp.GetTotalVolumes() != 1 {
+		t.Fatalf("expected total_volumes=1, got %d", resp.GetTotalVolumes())
+	}
+	if resp.GetTotalFiles() != 3 {
+		t.Fatalf("expected total_files=3, got %d", resp.GetTotalFiles())
+	}
+	if len(resp.GetBrokenVolumeIds()) != 0 {
+		t.Fatalf("expected no broken volumes, got %v: %v", resp.GetBrokenVolumeIds(), resp.GetDetails())
+	}
+}
+
+func TestScrubVolumeFullCorruptData(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(201)
+	framework.AllocateVolume(t, grpcClient, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(volumeID, 1, 1), []byte("important data")))
+
+	framework.CorruptDatFile(t, clusterHarness.BaseDir(), volumeID)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubVolume(ctx, &volume_server_pb.ScrubVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_FULL,
+	})
+	if err != nil {
+		t.Fatalf("ScrubVolume FULL on corrupt volume failed: %v", err)
+	}
+	if len(resp.GetBrokenVolumeIds()) == 0 {
+		t.Fatalf("expected broken volume after data corruption, got none")
+	}
+	if len(resp.GetDetails()) == 0 {
+		t.Fatalf("expected error details for corrupt volume")
+	}
+}
+
+func TestScrubVolumeMixedHealthy(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const healthyVol = uint32(202)
+	const corruptVol = uint32(203)
+	framework.AllocateVolume(t, grpcClient, healthyVol, "")
+	framework.AllocateVolume(t, grpcClient, corruptVol, "")
+
+	httpClient := framework.NewHTTPClient()
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(healthyVol, 1, 1), []byte("healthy")))
+	framework.ReadAllAndClose(t, framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), framework.NewFileID(corruptVol, 1, 1), []byte("will corrupt")))
+
+	framework.CorruptIndexFile(t, clusterHarness.BaseDir(), corruptVol)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubVolume(ctx, &volume_server_pb.ScrubVolumeRequest{
+		VolumeIds: []uint32{healthyVol, corruptVol},
+		Mode:      volume_server_pb.VolumeScrubMode_INDEX,
+	})
+	if err != nil {
+		t.Fatalf("ScrubVolume INDEX on mixed volumes failed: %v", err)
+	}
+	if resp.GetTotalVolumes() != 2 {
+		t.Fatalf("expected total_volumes=2, got %d", resp.GetTotalVolumes())
+	}
+	if len(resp.GetBrokenVolumeIds()) != 1 {
+		t.Fatalf("expected exactly 1 broken volume, got %v", resp.GetBrokenVolumeIds())
+	}
+	if resp.GetBrokenVolumeIds()[0] != corruptVol {
+		t.Fatalf("expected broken volume %d, got %d", corruptVol, resp.GetBrokenVolumeIds()[0])
+	}
+}
+
+func TestScrubVolumeMissingVolumeReturnsError(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	_, err := grpcClient.ScrubVolume(ctx, &volume_server_pb.ScrubVolumeRequest{
+		VolumeIds: []uint32{99999},
+		Mode:      volume_server_pb.VolumeScrubMode_FULL,
+	})
+	if err == nil {
+		t.Fatalf("ScrubVolume should fail for missing volume")
+	}
+}
+
+// --- EC volume scrub tests ---
+
+// ecSetup creates a volume, uploads data, generates EC shards, and mounts all of them.
+func ecSetup(t *testing.T, grpcClient volume_server_pb.VolumeServerClient, httpClient *http.Client, volumeURL string, volumeID uint32) {
+	t.Helper()
+	framework.AllocateVolume(t, grpcClient, volumeID, "")
+
+	fid := framework.NewFileID(volumeID, 1, 0xABCD0001)
+	uploadResp := framework.UploadBytes(t, httpClient, volumeURL, fid, []byte("ec-scrub-test-data-payload"))
+	_ = framework.ReadAllAndClose(t, uploadResp)
+	if uploadResp.StatusCode != http.StatusCreated {
+		t.Fatalf("upload expected 201, got %d", uploadResp.StatusCode)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	_, err := grpcClient.VolumeEcShardsGenerate(ctx, &volume_server_pb.VolumeEcShardsGenerateRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsGenerate failed: %v", err)
+	}
+
+	allShards := make([]uint32, erasure_coding.TotalShardsCount)
+	for i := range allShards {
+		allShards[i] = uint32(i)
+	}
+	_, err = grpcClient.VolumeEcShardsMount(ctx, &volume_server_pb.VolumeEcShardsMountRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+		ShardIds:   allShards,
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsMount all shards failed: %v", err)
+	}
+}
+
+func TestScrubEcVolumeIndexHealthy(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(210)
+	httpClient := framework.NewHTTPClient()
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeID)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_INDEX,
+	})
+	if err != nil {
+		t.Fatalf("ScrubEcVolume INDEX on healthy volume failed: %v", err)
+	}
+	if resp.GetTotalVolumes() != 1 {
+		t.Fatalf("expected total_volumes=1, got %d", resp.GetTotalVolumes())
+	}
+	if len(resp.GetBrokenVolumeIds()) != 0 {
+		t.Fatalf("expected no broken volumes, got %v: %v", resp.GetBrokenVolumeIds(), resp.GetDetails())
+	}
+}
+
+func TestScrubEcVolumeLocalHealthy(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(211)
+	httpClient := framework.NewHTTPClient()
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeID)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_LOCAL,
+	})
+	if err != nil {
+		t.Fatalf("ScrubEcVolume LOCAL on healthy volume failed: %v", err)
+	}
+	if resp.GetTotalVolumes() != 1 {
+		t.Fatalf("expected total_volumes=1, got %d", resp.GetTotalVolumes())
+	}
+	if resp.GetTotalFiles() != 1 {
+		t.Fatalf("expected total_files=1, got %d", resp.GetTotalFiles())
+	}
+	if len(resp.GetBrokenVolumeIds()) != 0 {
+		t.Fatalf("expected no broken volumes, got %v: %v", resp.GetBrokenVolumeIds(), resp.GetDetails())
+	}
+	if len(resp.GetBrokenShardInfos()) != 0 {
+		t.Fatalf("expected no broken shards, got %v", resp.GetBrokenShardInfos())
+	}
+}
+
+func TestScrubEcVolumeLocalCorruptShard(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(212)
+	httpClient := framework.NewHTTPClient()
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeID)
+
+	// Corrupt shard 0 by truncating it.
+	framework.CorruptEcShardFile(t, clusterHarness.BaseDir(), volumeID, 0)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	resp, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_LOCAL,
+	})
+	if err != nil {
+		t.Fatalf("ScrubEcVolume LOCAL on corrupt shard failed: %v", err)
+	}
+	if len(resp.GetBrokenVolumeIds()) == 0 {
+		t.Fatalf("expected broken volume after shard corruption")
+	}
+	if len(resp.GetBrokenShardInfos()) == 0 {
+		t.Fatalf("expected broken shard info after shard corruption")
+	}
+	// Verify all reported broken shards belong to the corrupted volume.
+	for _, si := range resp.GetBrokenShardInfos() {
+		if si.GetVolumeId() != volumeID {
+			t.Fatalf("broken shard info for unexpected volume %d, want %d", si.GetVolumeId(), volumeID)
+		}
+	}
+}
+
+func TestScrubEcVolumeAutoSelectWithEcPresent(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeIDA = uint32(213)
+	const volumeIDB = uint32(214)
+	httpClient := framework.NewHTTPClient()
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeIDA)
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeIDB)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	// Auto-select (empty VolumeIds) should find both EC volumes.
+	resp, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		Mode: volume_server_pb.VolumeScrubMode_INDEX,
+	})
+	if err != nil {
+		t.Fatalf("ScrubEcVolume auto-select failed: %v", err)
+	}
+	if resp.GetTotalVolumes() < 2 {
+		t.Fatalf("expected at least 2 EC volumes via auto-select, got %d", resp.GetTotalVolumes())
+	}
+	if len(resp.GetBrokenVolumeIds()) != 0 {
+		t.Fatalf("expected no broken volumes, got %v", resp.GetBrokenVolumeIds())
+	}
+}
+
+func TestScrubEcVolumeUnsupportedMode(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(215)
+	httpClient := framework.NewHTTPClient()
+	ecSetup(t, grpcClient, httpClient, clusterHarness.VolumeAdminURL(), volumeID)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	_, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode(99),
+	})
+	if err == nil {
+		t.Fatalf("ScrubEcVolume should fail for unsupported mode")
+	}
+}
+
+func TestScrubEcVolumeIndexCorruptEcx(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	clusterHarness := framework.StartVolumeCluster(t, matrix.P1())
+	conn, grpcClient := framework.DialVolumeServer(t, clusterHarness.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(216)
+	framework.AllocateVolume(t, grpcClient, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+	fid := framework.NewFileID(volumeID, 1, 0xABCD0001)
+	uploadResp := framework.UploadBytes(t, httpClient, clusterHarness.VolumeAdminURL(), fid, []byte("ec-ecx-corrupt-test"))
+	_ = framework.ReadAllAndClose(t, uploadResp)
+	if uploadResp.StatusCode != http.StatusCreated {
+		t.Fatalf("upload expected 201, got %d", uploadResp.StatusCode)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+
+	// Generate EC shards (this creates the .ecx file on disk).
+	_, err := grpcClient.VolumeEcShardsGenerate(ctx, &volume_server_pb.VolumeEcShardsGenerateRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsGenerate failed: %v", err)
+	}
+
+	// Corrupt the .ecx file BEFORE mounting, so the corrupted size is loaded.
+	framework.CorruptEcxFile(t, clusterHarness.BaseDir(), volumeID)
+
+	// Now mount shards - the ecx file size will reflect the corruption.
+	allShards := make([]uint32, erasure_coding.TotalShardsCount)
+	for i := range allShards {
+		allShards[i] = uint32(i)
+	}
+	_, err = grpcClient.VolumeEcShardsMount(ctx, &volume_server_pb.VolumeEcShardsMountRequest{
+		VolumeId:   volumeID,
+		Collection: "",
+		ShardIds:   allShards,
+	})
+	if err != nil {
+		t.Fatalf("VolumeEcShardsMount failed: %v", err)
+	}
+
+	resp, err := grpcClient.ScrubEcVolume(ctx, &volume_server_pb.ScrubEcVolumeRequest{
+		VolumeIds: []uint32{volumeID},
+		Mode:      volume_server_pb.VolumeScrubMode_INDEX,
+	})
+	if err != nil {
+		t.Fatalf("ScrubEcVolume INDEX on corrupt ecx failed: %v", err)
+	}
+	if len(resp.GetBrokenVolumeIds()) == 0 {
+		t.Fatalf("expected broken volume after ECX corruption")
+	}
+}

weed/admin/dash/admin_data.go

@@ -45,6 +45,7 @@ type ObjectStoreUser struct {
 	SecretKey   string   `json:"secret_key"`
 	Permissions []string `json:"permissions"`
 	PolicyNames []string `json:"policy_names"`
+	IsStatic    bool     `json:"is_static"` // loaded from static config file, not editable
 }
 
 type ObjectStoreUsersData struct {

weed/admin/dash/admin_server.go

@@ -867,6 +867,24 @@ func (s *AdminServer) DeleteS3Bucket(bucketName string) error {
 	})
 }
 
+// IsStaticUser checks if a user is a static identity by loading the
+// configuration from the credential manager and checking the IsStatic flag.
+func (s *AdminServer) IsStaticUser(username string) bool {
+	if s.credentialManager == nil {
+		return false
+	}
+	s3cfg, err := s.credentialManager.LoadConfiguration(context.Background())
+	if err != nil {
+		return false
+	}
+	for _, ident := range s3cfg.Identities {
+		if ident.Name == username {
+			return ident.IsStatic
+		}
+	}
+	return false
+}
+
 // GetObjectStoreUsers retrieves object store users from identity.json
 func (s *AdminServer) GetObjectStoreUsers(ctx context.Context) ([]ObjectStoreUser, error) {
 	if s.credentialManager == nil {
@@ -890,6 +908,7 @@ func (s *AdminServer) GetObjectStoreUsers(ctx context.Context) ([]ObjectStoreUse
 		user := ObjectStoreUser{
 			Username:    identity.Name,
 			Permissions: identity.Actions,
+			IsStatic:    identity.IsStatic,
 		}
 
 		// Set email from account if available

weed/admin/dash/config_persistence.go

@@ -1091,7 +1091,7 @@ func (cp *ConfigPersistence) loadTaskStateLocked(taskID string) (*maintenance.Ma
 	// Convert protobuf to maintenance task
 	task := cp.protobufToMaintenanceTask(taskStateFile.Task)
 
-	glog.V(2).Infof("Loaded task state for task %s from %s", taskID, taskFilePath)
+	glog.V(3).Infof("Loaded task state for task %s from %s", taskID, taskFilePath)
 	return task, nil
 }
 
@@ -1135,6 +1135,43 @@ func (cp *ConfigPersistence) loadAllTaskStatesLocked() ([]*maintenance.Maintenan
 	return tasks, nil
 }
 
+// DeleteAllTaskStates removes all task state .pb files from disk without reading them.
+// Used at startup to clean up stale files from previous runs — the scanner will
+// re-detect any tasks that are still needed from live cluster state.
+func (cp *ConfigPersistence) DeleteAllTaskStates() error {
+	cp.tasksMu.Lock()
+	defer cp.tasksMu.Unlock()
+
+	if cp.dataDir == "" {
+		return nil
+	}
+
+	tasksDir := filepath.Join(cp.dataDir, TasksSubdir)
+	entries, err := os.ReadDir(tasksDir)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return nil
+		}
+		return fmt.Errorf("failed to read tasks directory: %w", err)
+	}
+
+	var removed int
+	for _, entry := range entries {
+		if !entry.IsDir() && filepath.Ext(entry.Name()) == ".pb" {
+			if err := os.Remove(filepath.Join(tasksDir, entry.Name())); err != nil && !os.IsNotExist(err) {
+				glog.Warningf("Failed to delete task file %s: %v", entry.Name(), err)
+			} else {
+				removed++
+			}
+		}
+	}
+
+	if removed > 0 {
+		glog.Infof("Cleaned up %d stale task files from disk", removed)
+	}
+	return nil
+}
+
 // DeleteTaskState removes a task state file from disk
 func (cp *ConfigPersistence) DeleteTaskState(taskID string) error {
 	cp.tasksMu.Lock()

weed/admin/dash/types.go

@@ -447,11 +447,6 @@ type QueueStats = maintenance.QueueStats
 type WorkerDetailsData = maintenance.WorkerDetailsData
 type WorkerPerformance = maintenance.WorkerPerformance
 
-// GetTaskIcon returns the icon CSS class for a task type from its UI provider
-func GetTaskIcon(taskType MaintenanceTaskType) string {
-	return maintenance.GetTaskIcon(taskType)
-}
-
 // Status constants (these are still static)
 const (
 	TaskStatusPending    = maintenance.TaskStatusPending

weed/admin/dash/user_management.go

@@ -3,13 +3,13 @@ package dash
 import (
 	"context"
 	"crypto/rand"
-	"encoding/base64"
 	"errors"
 	"fmt"
 	"strings"
 	"time"
 
 	"github.com/seaweedfs/seaweedfs/weed/credential"
+	"github.com/seaweedfs/seaweedfs/weed/iam"
 	"github.com/seaweedfs/seaweedfs/weed/pb/iam_pb"
 )
 
@@ -175,7 +175,7 @@ func (s *AdminServer) GetObjectStoreUserDetails(username string) (*UserDetails,
 
 	ctx := context.Background()
 
-	// Get user using credential manager
+	// Get user using credential manager (resolves static users via filer gRPC)
 	identity, err := s.credentialManager.GetUser(ctx, username)
 	if err != nil {
 		if err == credential.ErrUserNotFound {
@@ -435,10 +435,13 @@ func generateAccessKey() string {
 }
 
 func generateSecretKey() string {
-	// Generate 40-character secret key (AWS standard)
-	b := make([]byte, 30) // 30 bytes = 40 characters in base64
-	rand.Read(b)
-	return base64.StdEncoding.EncodeToString(b)
+	// Use the IAM helper to generate URL-safe secret keys (no +, / characters)
+	// that won't break S3 signature authentication
+	key, err := iam.GenerateSecretAccessKey()
+	if err != nil {
+		panic(fmt.Sprintf("failed to generate secret key: %v", err))
+	}
+	return key
 }
 
 func generateAccountId() string {

weed/admin/dash/user_management_test.go

@@ -74,9 +74,16 @@ func TestGenerateSecretKey(t *testing.T) {
 	key1 := generateSecretKey()
 	key2 := generateSecretKey()
 
-	// Check length (base64 encoding of 30 bytes = 40 characters)
-	if len(key1) != 40 {
-		t.Errorf("Expected secret key length 40, got %d", len(key1))
+	// Check length (IAM standard secret key length)
+	if len(key1) != 42 {
+		t.Errorf("Expected secret key length 42, got %d", len(key1))
+	}
+
+	// Check that key contains only URL-safe characters (no +, /)
+	for _, c := range key1 {
+		if c == '+' || c == '/' || c == '=' {
+			t.Errorf("Secret key contains non-URL-safe character: %c", c)
+		}
 	}
 
 	// Check uniqueness

weed/admin/handlers/cluster_handlers.go

@@ -312,29 +312,6 @@ func (h *ClusterHandlers) ShowClusterFilers(w http.ResponseWriter, r *http.Reque
 	}
 }
 
-// ShowClusterBrokers renders the cluster message brokers page
-func (h *ClusterHandlers) ShowClusterBrokers(w http.ResponseWriter, r *http.Request) {
-	// Get cluster brokers data
-	brokersData, err := h.adminServer.GetClusterBrokers()
-	if err != nil {
-		writeJSONError(w, http.StatusInternalServerError, "Failed to get cluster brokers: "+err.Error())
-		return
-	}
-
-	username := usernameOrDefault(r)
-	brokersData.Username = username
-
-	// Render HTML template
-	w.Header().Set("Content-Type", "text/html")
-	brokersComponent := app.ClusterBrokers(*brokersData)
-	viewCtx := layout.NewViewContext(r, username, dash.CSRFTokenFromContext(r.Context()))
-	layoutComponent := layout.Layout(viewCtx, brokersComponent)
-	if err := layoutComponent.Render(r.Context(), w); err != nil {
-		writeJSONError(w, http.StatusInternalServerError, "Failed to render template: "+err.Error())
-		return
-	}
-}
-
 // GetClusterTopology returns the cluster topology as JSON
 func (h *ClusterHandlers) GetClusterTopology(w http.ResponseWriter, r *http.Request) {
 	topology, err := h.adminServer.GetClusterTopology()

weed/admin/handlers/mq_handlers.go

@@ -78,34 +78,6 @@ func (h *MessageQueueHandlers) ShowTopics(w http.ResponseWriter, r *http.Request
 	}
 }
 
-// ShowSubscribers renders the message queue subscribers page
-func (h *MessageQueueHandlers) ShowSubscribers(w http.ResponseWriter, r *http.Request) {
-	// Get subscribers data
-	subscribersData, err := h.adminServer.GetSubscribers()
-	if err != nil {
-		writeJSONError(w, http.StatusInternalServerError, "Failed to get subscribers: "+err.Error())
-		return
-	}
-
-	// Set username
-	username := dash.UsernameFromContext(r.Context())
-	if username == "" {
-		username = "admin"
-	}
-	subscribersData.Username = username
-
-	// Render HTML template
-	w.Header().Set("Content-Type", "text/html")
-	subscribersComponent := app.Subscribers(*subscribersData)
-	viewCtx := layout.NewViewContext(r, username, dash.CSRFTokenFromContext(r.Context()))
-	layoutComponent := layout.Layout(viewCtx, subscribersComponent)
-	err = layoutComponent.Render(r.Context(), w)
-	if err != nil {
-		writeJSONError(w, http.StatusInternalServerError, "Failed to render template: "+err.Error())
-		return
-	}
-}
-
 // ShowTopicDetails renders the topic details page
 func (h *MessageQueueHandlers) ShowTopicDetails(w http.ResponseWriter, r *http.Request) {
 	// Get topic parameters from URL

weed/admin/handlers/user_handlers.go

@@ -93,6 +93,11 @@ func (h *UserHandlers) UpdateUser(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
+	if h.adminServer.IsStaticUser(username) {
+		writeJSONError(w, http.StatusForbidden, "Cannot modify static user "+username+" (loaded from config file)")
+		return
+	}
+
 	var req dash.UpdateUserRequest
 	if err := decodeJSONBody(newJSONMaxReader(w, r), &req); err != nil {
 		writeJSONError(w, http.StatusBadRequest, "Invalid request: "+err.Error())
@@ -120,6 +125,11 @@ func (h *UserHandlers) DeleteUser(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
+	if h.adminServer.IsStaticUser(username) {
+		writeJSONError(w, http.StatusForbidden, "Cannot delete static user "+username+" (loaded from config file)")
+		return
+	}
+
 	err := h.adminServer.DeleteObjectStoreUser(username)
 	if err != nil {
 		glog.Errorf("Failed to delete user %s: %v", username, err)

weed/admin/maintenance/config_verification.go

@@ -1,124 +0,0 @@
-package maintenance
-
-import (
-	"fmt"
-
-	"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
-)
-
-// VerifyProtobufConfig demonstrates that the protobuf configuration system is working
-func VerifyProtobufConfig() error {
-	// Create configuration manager
-	configManager := NewMaintenanceConfigManager()
-	config := configManager.GetConfig()
-
-	// Verify basic configuration
-	if !config.Enabled {
-		return fmt.Errorf("expected config to be enabled by default")
-	}
-
-	if config.ScanIntervalSeconds != 30*60 {
-		return fmt.Errorf("expected scan interval to be 1800 seconds, got %d", config.ScanIntervalSeconds)
-	}
-
-	// Verify policy configuration
-	if config.Policy == nil {
-		return fmt.Errorf("expected policy to be configured")
-	}
-
-	if config.Policy.GlobalMaxConcurrent != 4 {
-		return fmt.Errorf("expected global max concurrent to be 4, got %d", config.Policy.GlobalMaxConcurrent)
-	}
-
-	// Verify task policies
-	vacuumPolicy := config.Policy.TaskPolicies["vacuum"]
-	if vacuumPolicy == nil {
-		return fmt.Errorf("expected vacuum policy to be configured")
-	}
-
-	if !vacuumPolicy.Enabled {
-		return fmt.Errorf("expected vacuum policy to be enabled")
-	}
-
-	// Verify typed configuration access
-	vacuumConfig := vacuumPolicy.GetVacuumConfig()
-	if vacuumConfig == nil {
-		return fmt.Errorf("expected vacuum config to be accessible")
-	}
-
-	if vacuumConfig.GarbageThreshold != 0.3 {
-		return fmt.Errorf("expected garbage threshold to be 0.3, got %f", vacuumConfig.GarbageThreshold)
-	}
-
-	// Verify helper functions work
-	if !IsTaskEnabled(config.Policy, "vacuum") {
-		return fmt.Errorf("expected vacuum task to be enabled via helper function")
-	}
-
-	maxConcurrent := GetMaxConcurrent(config.Policy, "vacuum")
-	if maxConcurrent != 2 {
-		return fmt.Errorf("expected vacuum max concurrent to be 2, got %d", maxConcurrent)
-	}
-
-	// Verify erasure coding configuration
-	ecPolicy := config.Policy.TaskPolicies["erasure_coding"]
-	if ecPolicy == nil {
-		return fmt.Errorf("expected EC policy to be configured")
-	}
-
-	ecConfig := ecPolicy.GetErasureCodingConfig()
-	if ecConfig == nil {
-		return fmt.Errorf("expected EC config to be accessible")
-	}
-
-	// Verify configurable EC fields only
-	if ecConfig.FullnessRatio <= 0 || ecConfig.FullnessRatio > 1 {
-		return fmt.Errorf("expected EC config to have valid fullness ratio (0-1), got %f", ecConfig.FullnessRatio)
-	}
-
-	return nil
-}
-
-// GetProtobufConfigSummary returns a summary of the current protobuf configuration
-func GetProtobufConfigSummary() string {
-	configManager := NewMaintenanceConfigManager()
-	config := configManager.GetConfig()
-
-	summary := fmt.Sprintf("SeaweedFS Protobuf Maintenance Configuration:\n")
-	summary += fmt.Sprintf("  Enabled: %v\n", config.Enabled)
-	summary += fmt.Sprintf("  Scan Interval: %d seconds\n", config.ScanIntervalSeconds)
-	summary += fmt.Sprintf("  Max Retries: %d\n", config.MaxRetries)
-	summary += fmt.Sprintf("  Global Max Concurrent: %d\n", config.Policy.GlobalMaxConcurrent)
-	summary += fmt.Sprintf("  Task Policies: %d configured\n", len(config.Policy.TaskPolicies))
-
-	for taskType, policy := range config.Policy.TaskPolicies {
-		summary += fmt.Sprintf("    %s: enabled=%v, max_concurrent=%d\n",
-			taskType, policy.Enabled, policy.MaxConcurrent)
-	}
-
-	return summary
-}
-
-// CreateCustomConfig demonstrates creating a custom protobuf configuration
-func CreateCustomConfig() *worker_pb.MaintenanceConfig {
-	return &worker_pb.MaintenanceConfig{
-		Enabled:             true,
-		ScanIntervalSeconds: 60 * 60, // 1 hour
-		MaxRetries:          5,
-		Policy: &worker_pb.MaintenancePolicy{
-			GlobalMaxConcurrent: 8,
-			TaskPolicies: map[string]*worker_pb.TaskPolicy{
-				"custom_vacuum": {
-					Enabled:       true,
-					MaxConcurrent: 4,
-					TaskConfig: &worker_pb.TaskPolicy_VacuumConfig{
-						VacuumConfig: &worker_pb.VacuumTaskConfig{
-							GarbageThreshold:  0.5,
-							MinVolumeAgeHours: 48,
-						},
-					},
-				},
-			},
-		},
-	}
-}

weed/admin/maintenance/maintenance_config_proto.go

@@ -1,24 +1,9 @@
 package maintenance
 
 import (
-	"fmt"
-	"time"
-
 	"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
 )
 
-// MaintenanceConfigManager handles protobuf-based configuration
-type MaintenanceConfigManager struct {
-	config *worker_pb.MaintenanceConfig
-}
-
-// NewMaintenanceConfigManager creates a new config manager with defaults
-func NewMaintenanceConfigManager() *MaintenanceConfigManager {
-	return &MaintenanceConfigManager{
-		config: DefaultMaintenanceConfigProto(),
-	}
-}
-
 // DefaultMaintenanceConfigProto returns default configuration as protobuf
 func DefaultMaintenanceConfigProto() *worker_pb.MaintenanceConfig {
 	return &worker_pb.MaintenanceConfig{
@@ -34,253 +19,3 @@ func DefaultMaintenanceConfigProto() *worker_pb.MaintenanceConfig {
 		Policy: nil,
 	}
 }
-
-// GetConfig returns the current configuration
-func (mcm *MaintenanceConfigManager) GetConfig() *worker_pb.MaintenanceConfig {
-	return mcm.config
-}
-
-// Type-safe configuration accessors
-
-// GetVacuumConfig returns vacuum-specific configuration for a task type
-func (mcm *MaintenanceConfigManager) GetVacuumConfig(taskType string) *worker_pb.VacuumTaskConfig {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		if vacuumConfig := policy.GetVacuumConfig(); vacuumConfig != nil {
-			return vacuumConfig
-		}
-	}
-	// Return defaults if not configured
-	return &worker_pb.VacuumTaskConfig{
-		GarbageThreshold:  0.3,
-		MinVolumeAgeHours: 24,
-	}
-}
-
-// GetErasureCodingConfig returns EC-specific configuration for a task type
-func (mcm *MaintenanceConfigManager) GetErasureCodingConfig(taskType string) *worker_pb.ErasureCodingTaskConfig {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		if ecConfig := policy.GetErasureCodingConfig(); ecConfig != nil {
-			return ecConfig
-		}
-	}
-	// Return defaults if not configured
-	return &worker_pb.ErasureCodingTaskConfig{
-		FullnessRatio:    0.95,
-		QuietForSeconds:  3600,
-		MinVolumeSizeMb:  100,
-		CollectionFilter: "",
-	}
-}
-
-// GetBalanceConfig returns balance-specific configuration for a task type
-func (mcm *MaintenanceConfigManager) GetBalanceConfig(taskType string) *worker_pb.BalanceTaskConfig {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		if balanceConfig := policy.GetBalanceConfig(); balanceConfig != nil {
-			return balanceConfig
-		}
-	}
-	// Return defaults if not configured
-	return &worker_pb.BalanceTaskConfig{
-		ImbalanceThreshold: 0.2,
-		MinServerCount:     2,
-	}
-}
-
-// GetReplicationConfig returns replication-specific configuration for a task type
-func (mcm *MaintenanceConfigManager) GetReplicationConfig(taskType string) *worker_pb.ReplicationTaskConfig {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		if replicationConfig := policy.GetReplicationConfig(); replicationConfig != nil {
-			return replicationConfig
-		}
-	}
-	// Return defaults if not configured
-	return &worker_pb.ReplicationTaskConfig{
-		TargetReplicaCount: 2,
-	}
-}
-
-// Typed convenience methods for getting task configurations
-
-// GetVacuumTaskConfigForType returns vacuum configuration for a specific task type
-func (mcm *MaintenanceConfigManager) GetVacuumTaskConfigForType(taskType string) *worker_pb.VacuumTaskConfig {
-	return GetVacuumTaskConfig(mcm.config.Policy, MaintenanceTaskType(taskType))
-}
-
-// GetErasureCodingTaskConfigForType returns erasure coding configuration for a specific task type
-func (mcm *MaintenanceConfigManager) GetErasureCodingTaskConfigForType(taskType string) *worker_pb.ErasureCodingTaskConfig {
-	return GetErasureCodingTaskConfig(mcm.config.Policy, MaintenanceTaskType(taskType))
-}
-
-// GetBalanceTaskConfigForType returns balance configuration for a specific task type
-func (mcm *MaintenanceConfigManager) GetBalanceTaskConfigForType(taskType string) *worker_pb.BalanceTaskConfig {
-	return GetBalanceTaskConfig(mcm.config.Policy, MaintenanceTaskType(taskType))
-}
-
-// GetReplicationTaskConfigForType returns replication configuration for a specific task type
-func (mcm *MaintenanceConfigManager) GetReplicationTaskConfigForType(taskType string) *worker_pb.ReplicationTaskConfig {
-	return GetReplicationTaskConfig(mcm.config.Policy, MaintenanceTaskType(taskType))
-}
-
-// Helper methods
-
-func (mcm *MaintenanceConfigManager) getTaskPolicy(taskType string) *worker_pb.TaskPolicy {
-	if mcm.config.Policy != nil && mcm.config.Policy.TaskPolicies != nil {
-		return mcm.config.Policy.TaskPolicies[taskType]
-	}
-	return nil
-}
-
-// IsTaskEnabled returns whether a task type is enabled
-func (mcm *MaintenanceConfigManager) IsTaskEnabled(taskType string) bool {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		return policy.Enabled
-	}
-	return false
-}
-
-// GetMaxConcurrent returns the max concurrent limit for a task type
-func (mcm *MaintenanceConfigManager) GetMaxConcurrent(taskType string) int32 {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		return policy.MaxConcurrent
-	}
-	return 1 // Default
-}
-
-// GetRepeatInterval returns the repeat interval for a task type in seconds
-func (mcm *MaintenanceConfigManager) GetRepeatInterval(taskType string) int32 {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		return policy.RepeatIntervalSeconds
-	}
-	return mcm.config.Policy.DefaultRepeatIntervalSeconds
-}
-
-// GetCheckInterval returns the check interval for a task type in seconds
-func (mcm *MaintenanceConfigManager) GetCheckInterval(taskType string) int32 {
-	if policy := mcm.getTaskPolicy(taskType); policy != nil {
-		return policy.CheckIntervalSeconds
-	}
-	return mcm.config.Policy.DefaultCheckIntervalSeconds
-}
-
-// Duration accessor methods
-
-// GetScanInterval returns the scan interval as a time.Duration
-func (mcm *MaintenanceConfigManager) GetScanInterval() time.Duration {
-	return time.Duration(mcm.config.ScanIntervalSeconds) * time.Second
-}
-
-// GetWorkerTimeout returns the worker timeout as a time.Duration
-func (mcm *MaintenanceConfigManager) GetWorkerTimeout() time.Duration {
-	return time.Duration(mcm.config.WorkerTimeoutSeconds) * time.Second
-}
-
-// GetTaskTimeout returns the task timeout as a time.Duration
-func (mcm *MaintenanceConfigManager) GetTaskTimeout() time.Duration {
-	return time.Duration(mcm.config.TaskTimeoutSeconds) * time.Second
-}
-
-// GetRetryDelay returns the retry delay as a time.Duration
-func (mcm *MaintenanceConfigManager) GetRetryDelay() time.Duration {
-	return time.Duration(mcm.config.RetryDelaySeconds) * time.Second
-}
-
-// GetCleanupInterval returns the cleanup interval as a time.Duration
-func (mcm *MaintenanceConfigManager) GetCleanupInterval() time.Duration {
-	return time.Duration(mcm.config.CleanupIntervalSeconds) * time.Second
-}
-
-// GetTaskRetention returns the task retention period as a time.Duration
-func (mcm *MaintenanceConfigManager) GetTaskRetention() time.Duration {
-	return time.Duration(mcm.config.TaskRetentionSeconds) * time.Second
-}
-
-// ValidateMaintenanceConfigWithSchema validates protobuf maintenance configuration using ConfigField rules
-func ValidateMaintenanceConfigWithSchema(config *worker_pb.MaintenanceConfig) error {
-	if config == nil {
-		return fmt.Errorf("configuration cannot be nil")
-	}
-
-	// Get the schema to access field validation rules
-	schema := GetMaintenanceConfigSchema()
-
-	// Validate each field individually using the ConfigField rules
-	if err := validateFieldWithSchema(schema, "enabled", config.Enabled); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "scan_interval_seconds", int(config.ScanIntervalSeconds)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "worker_timeout_seconds", int(config.WorkerTimeoutSeconds)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "task_timeout_seconds", int(config.TaskTimeoutSeconds)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "retry_delay_seconds", int(config.RetryDelaySeconds)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "max_retries", int(config.MaxRetries)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "cleanup_interval_seconds", int(config.CleanupIntervalSeconds)); err != nil {
-		return err
-	}
-
-	if err := validateFieldWithSchema(schema, "task_retention_seconds", int(config.TaskRetentionSeconds)); err != nil {
-		return err
-	}
-
-	// Validate policy fields if present
-	if config.Policy != nil {
-		// Note: These field names might need to be adjusted based on the actual schema
-		if err := validatePolicyField("global_max_concurrent", int(config.Policy.GlobalMaxConcurrent)); err != nil {
-			return err
-		}
-
-		if err := validatePolicyField("default_repeat_interval_seconds", int(config.Policy.DefaultRepeatIntervalSeconds)); err != nil {
-			return err
-		}
-
-		if err := validatePolicyField("default_check_interval_seconds", int(config.Policy.DefaultCheckIntervalSeconds)); err != nil {
-			return err
-		}
-	}
-
-	return nil
-}
-
-// validateFieldWithSchema validates a single field using its ConfigField definition
-func validateFieldWithSchema(schema *MaintenanceConfigSchema, fieldName string, value interface{}) error {
-	field := schema.GetFieldByName(fieldName)
-	if field == nil {
-		// Field not in schema, skip validation
-		return nil
-	}
-
-	return field.ValidateValue(value)
-}
-
-// validatePolicyField validates policy fields (simplified validation for now)
-func validatePolicyField(fieldName string, value int) error {
-	switch fieldName {
-	case "global_max_concurrent":
-		if value < 1 || value > 20 {
-			return fmt.Errorf("Global Max Concurrent must be between 1 and 20, got %d", value)
-		}
-	case "default_repeat_interval":
-		if value < 1 || value > 168 {
-			return fmt.Errorf("Default Repeat Interval must be between 1 and 168 hours, got %d", value)
-		}
-	case "default_check_interval":
-		if value < 1 || value > 168 {
-			return fmt.Errorf("Default Check Interval must be between 1 and 168 hours, got %d", value)
-		}
-	}
-	return nil
-}

weed/admin/maintenance/maintenance_queue.go

@@ -33,80 +33,16 @@ func (mq *MaintenanceQueue) SetPersistence(persistence TaskPersistence) {
 	glog.V(1).Infof("Maintenance queue configured with task persistence")
 }
 
-// LoadTasksFromPersistence loads tasks from persistent storage on startup
+// LoadTasksFromPersistence is called on startup. Previous task states are NOT loaded
+// into memory — the maintenance scanner will re-detect current needs from the live
+// cluster state. Stale task files from previous runs are deleted from disk.
 func (mq *MaintenanceQueue) LoadTasksFromPersistence() error {
-	if mq.persistence == nil {
-		glog.V(1).Infof("No task persistence configured, skipping task loading")
-		return nil
-	}
-
-	mq.mutex.Lock()
-	defer mq.mutex.Unlock()
-
-	glog.Infof("Loading tasks from persistence...")
-
-	tasks, err := mq.persistence.LoadAllTaskStates()
-	if err != nil {
-		return fmt.Errorf("failed to load task states: %w", err)
-	}
-
-	glog.Infof("DEBUG LoadTasksFromPersistence: Found %d tasks in persistence", len(tasks))
-
-	// Reset task maps
-	mq.tasks = make(map[string]*MaintenanceTask)
-	mq.pendingTasks = make([]*MaintenanceTask, 0)
-
-	// Load tasks by status
-	for _, task := range tasks {
-		glog.Infof("DEBUG LoadTasksFromPersistence: Loading task %s (type: %s, status: %s, scheduled: %v)", task.ID, task.Type, task.Status, task.ScheduledAt)
-		mq.tasks[task.ID] = task
-
-		switch task.Status {
-		case TaskStatusPending:
-			glog.Infof("DEBUG LoadTasksFromPersistence: Adding task %s to pending queue", task.ID)
-			mq.pendingTasks = append(mq.pendingTasks, task)
-		case TaskStatusAssigned, TaskStatusInProgress:
-			// For assigned/in-progress tasks, we need to check if the worker is still available
-			// If not, we should fail them and make them eligible for retry
-			if task.WorkerID != "" {
-				if _, exists := mq.workers[task.WorkerID]; !exists {
-					glog.Warningf("Task %s was assigned to unavailable worker %s, marking as failed", task.ID, task.WorkerID)
-					task.Status = TaskStatusFailed
-					task.Error = "Worker unavailable after restart"
-					completedTime := time.Now()
-					task.CompletedAt = &completedTime
-
-					// Check if it should be retried
-					if task.RetryCount < task.MaxRetries {
-						task.RetryCount++
-						task.Status = TaskStatusPending
-						task.WorkerID = ""
-						task.StartedAt = nil
-						task.CompletedAt = nil
-						task.Error = ""
-						task.ScheduledAt = time.Now().Add(1 * time.Minute) // Retry after restart delay
-						glog.Infof("DEBUG LoadTasksFromPersistence: Retrying task %s, adding to pending queue", task.ID)
-						mq.pendingTasks = append(mq.pendingTasks, task)
-					}
-				}
-			}
-		}
-
-		// Sync task with ActiveTopology for capacity tracking
-		if mq.integration != nil {
-			mq.integration.SyncTask(task)
+	if mq.persistence != nil {
+		if err := mq.persistence.DeleteAllTaskStates(); err != nil {
+			glog.Warningf("Failed to clean up old task files: %v", err)
 		}
 	}
-
-	// Sort pending tasks by priority and schedule time
-	sort.Slice(mq.pendingTasks, func(i, j int) bool {
-		if mq.pendingTasks[i].Priority != mq.pendingTasks[j].Priority {
-			return mq.pendingTasks[i].Priority > mq.pendingTasks[j].Priority
-		}
-		return mq.pendingTasks[i].ScheduledAt.Before(mq.pendingTasks[j].ScheduledAt)
-	})
-
-	glog.Infof("Loaded %d tasks from persistence (%d pending)", len(tasks), len(mq.pendingTasks))
+	glog.Infof("Task queue initialized (previous tasks will be re-detected by scanner)")
 	return nil
 }
 
@@ -119,6 +55,14 @@ func (mq *MaintenanceQueue) saveTaskState(task *MaintenanceTask) {
 	}
 }
 
+func (mq *MaintenanceQueue) deleteTaskState(taskID string) {
+	if mq.persistence != nil {
+		if err := mq.persistence.DeleteTaskState(taskID); err != nil {
+			glog.V(2).Infof("Failed to delete task state for %s: %v", taskID, err)
+		}
+	}
+}
+
 // cleanupCompletedTasks removes old completed tasks beyond the retention limit
 func (mq *MaintenanceQueue) cleanupCompletedTasks() {
 	if mq.persistence != nil {
@@ -128,10 +72,24 @@ func (mq *MaintenanceQueue) cleanupCompletedTasks() {
 	}
 }
 
+const MaxTasksPerType = 100
+
 // AddTask adds a new maintenance task to the queue with deduplication
 func (mq *MaintenanceQueue) AddTask(task *MaintenanceTask) {
 	mq.mutex.Lock()
 
+	// Enforce per-type capacity limit (only counting active tasks)
+	if mq.countActiveTasksByType(task.Type) >= MaxTasksPerType {
+		// Purge terminal tasks first, then recheck
+		mq.purgeTerminalTasksLocked()
+		if mq.countActiveTasksByType(task.Type) >= MaxTasksPerType {
+			mq.mutex.Unlock()
+			glog.V(1).Infof("Task skipped (type %s at capacity %d): volume %d on %s",
+				task.Type, MaxTasksPerType, task.VolumeID, task.Server)
+			return
+		}
+	}
+
 	// Enforce one queued/active task per volume (across all task types).
 	if mq.hasQueuedOrActiveTaskForVolume(task.VolumeID) {
 		mq.mutex.Unlock()
@@ -197,6 +155,30 @@ func (mq *MaintenanceQueue) AddTask(task *MaintenanceTask) {
 		taskSnapshot.ID, taskSnapshot.Type, taskSnapshot.VolumeID, taskSnapshot.Server, taskSnapshot.Priority, scheduleInfo, taskSnapshot.Reason)
 }
 
+// countActiveTasksByType returns the number of active (non-terminal) tasks of a given type. Caller must hold mq.mutex.
+func (mq *MaintenanceQueue) countActiveTasksByType(taskType MaintenanceTaskType) int {
+	count := 0
+	for _, t := range mq.tasks {
+		if t.Type == taskType {
+			switch t.Status {
+			case TaskStatusPending, TaskStatusAssigned, TaskStatusInProgress:
+				count++
+			}
+		}
+	}
+	return count
+}
+
+// purgeTerminalTasksLocked removes terminal tasks from the in-memory map. Caller must hold mq.mutex.
+func (mq *MaintenanceQueue) purgeTerminalTasksLocked() {
+	for id, task := range mq.tasks {
+		switch task.Status {
+		case TaskStatusCompleted, TaskStatusFailed, TaskStatusCancelled:
+			delete(mq.tasks, id)
+		}
+	}
+}
+
 // hasQueuedOrActiveTaskForVolume checks if any pending/assigned/in-progress task already exists for this volume.
 // Caller must hold mq.mutex.
 func (mq *MaintenanceQueue) hasQueuedOrActiveTaskForVolume(volumeID uint32) bool {
@@ -273,6 +255,9 @@ func (mq *MaintenanceQueue) CancelPendingTasksByType(taskType MaintenanceTaskTyp
 
 // AddTasksFromResults converts detection results to tasks and adds them to the queue
 func (mq *MaintenanceQueue) AddTasksFromResults(results []*TaskDetectionResult) {
+	// Purge terminal tasks from memory before adding new ones
+	mq.purgeTerminalTasks()
+
 	for _, result := range results {
 		// Validate that task has proper typed parameters
 		if result.TypedParams == nil {
@@ -297,6 +282,21 @@ func (mq *MaintenanceQueue) AddTasksFromResults(results []*TaskDetectionResult)
 	}
 }
 
+// purgeTerminalTasks removes completed/failed/cancelled tasks from memory.
+// Terminal tasks are already deleted from disk by CompleteTask, so this
+// only needs to clean up the in-memory map.
+func (mq *MaintenanceQueue) purgeTerminalTasks() {
+	mq.mutex.Lock()
+	before := len(mq.tasks)
+	mq.purgeTerminalTasksLocked()
+	purged := before - len(mq.tasks)
+	mq.mutex.Unlock()
+
+	if purged > 0 {
+		glog.V(1).Infof("Purged %d terminal tasks from memory", purged)
+	}
+}
+
 // GetNextTask returns the next available task for a worker
 func (mq *MaintenanceQueue) GetNextTask(workerID string, capabilities []MaintenanceTaskType) *MaintenanceTask {
 	// Use read lock for initial checks and search
@@ -570,7 +570,6 @@ func (mq *MaintenanceQueue) CompleteTask(taskID string, error string) {
 		}
 	}
 	taskStatus := task.Status
-	taskCount := len(mq.tasks)
 	// Snapshot task state while lock is still held to avoid data race
 	var taskToSaveSnapshot *MaintenanceTask
 	if taskToSave != nil {
@@ -578,9 +577,18 @@ func (mq *MaintenanceQueue) CompleteTask(taskID string, error string) {
 	}
 	mq.mutex.Unlock()
 
-	// Save task state to persistence outside the lock
+	// Only persist non-terminal tasks (retries). Completed/failed tasks stay
+	// in memory for the UI but are not written to disk — they would just
+	// accumulate and slow down future startups.
 	if taskToSaveSnapshot != nil {
-		mq.saveTaskState(taskToSaveSnapshot)
+		switch taskStatus {
+		case TaskStatusPending:
+			// Retry — save so the task survives a restart
+			mq.saveTaskState(taskToSaveSnapshot)
+		case TaskStatusCompleted, TaskStatusFailed, TaskStatusCancelled:
+			// Terminal — delete the file if one exists from a previous state
+			mq.deleteTaskState(taskToSaveSnapshot.ID)
+		}
 	}
 
 	if logFn != nil {
@@ -591,13 +599,6 @@ func (mq *MaintenanceQueue) CompleteTask(taskID string, error string) {
 	if taskStatus != TaskStatusPending {
 		mq.removePendingOperation(taskID)
 	}
-
-	// Periodically cleanup old completed tasks (when total task count is a multiple of 10)
-	if taskStatus == TaskStatusCompleted {
-		if taskCount%10 == 0 {
-			go mq.cleanupCompletedTasks()
-		}
-	}
 }
 
 // isNonRetriableError returns true for errors that will never succeed on retry,
@@ -1055,28 +1056,6 @@ func (mq *MaintenanceQueue) getMaxConcurrentForTaskType(taskType MaintenanceTask
 	return 1
 }
 
-// getRunningTasks returns all currently running tasks
-func (mq *MaintenanceQueue) getRunningTasks() []*MaintenanceTask {
-	var runningTasks []*MaintenanceTask
-	for _, task := range mq.tasks {
-		if task.Status == TaskStatusAssigned || task.Status == TaskStatusInProgress {
-			runningTasks = append(runningTasks, task)
-		}
-	}
-	return runningTasks
-}
-
-// getAvailableWorkers returns all workers that can take more work
-func (mq *MaintenanceQueue) getAvailableWorkers() []*MaintenanceWorker {
-	var availableWorkers []*MaintenanceWorker
-	for _, worker := range mq.workers {
-		if worker.Status == "active" && worker.CurrentLoad < worker.MaxConcurrent {
-			availableWorkers = append(availableWorkers, worker)
-		}
-	}
-	return availableWorkers
-}
-
 // trackPendingOperation adds a task to the pending operations tracker
 func (mq *MaintenanceQueue) trackPendingOperation(task *MaintenanceTask) {
 	if mq.integration == nil {

weed/admin/maintenance/maintenance_queue_test.go

@@ -693,10 +693,11 @@ func (m *MockPersistence) SaveTaskState(task *MaintenanceTask) error
 func (m *MockPersistence) LoadTaskState(taskID string) (*MaintenanceTask, error)    { return nil, nil }
 func (m *MockPersistence) LoadAllTaskStates() ([]*MaintenanceTask, error)           { return m.tasks, nil }
 func (m *MockPersistence) DeleteTaskState(taskID string) error                      { return nil }
+func (m *MockPersistence) DeleteAllTaskStates() error                               { return nil }
 func (m *MockPersistence) CleanupCompletedTasks() error                             { return nil }
 func (m *MockPersistence) SaveTaskPolicy(taskType string, policy *TaskPolicy) error { return nil }
 
-func TestMaintenanceQueue_LoadTasksCapacitySync(t *testing.T) {
+func TestMaintenanceQueue_LoadTasksStartsEmpty(t *testing.T) {
 	// Setup
 	policy := &MaintenancePolicy{
 		TaskPolicies: map[string]*worker_pb.TaskPolicy{
@@ -704,56 +705,25 @@ func TestMaintenanceQueue_LoadTasksCapacitySync(t *testing.T) {
 		},
 	}
 	mq := NewMaintenanceQueue(policy)
-	integration := NewMaintenanceIntegration(mq, policy)
-	mq.SetIntegration(integration)
-	at := integration.GetActiveTopology()
 
-	topologyInfo := &master_pb.TopologyInfo{
-		DataCenterInfos: []*master_pb.DataCenterInfo{
-			{
-				Id: "dc1",
-				RackInfos: []*master_pb.RackInfo{
-					{
-						Id: "rack1",
-						DataNodeInfos: []*master_pb.DataNodeInfo{
-							{
-								Id: "server1",
-								DiskInfos: map[string]*master_pb.DiskInfo{
-									"hdd1": {DiskId: 1, VolumeCount: 1, MaxVolumeCount: 10},
-									"hdd2": {DiskId: 2, VolumeCount: 0, MaxVolumeCount: 10},
-								},
-							},
-						},
-					},
-				},
-			},
-		},
-	}
-	at.UpdateTopology(topologyInfo)
-
-	// Setup mock persistence with a pending task
-	taskID := "load_test_123"
+	// Setup mock persistence with tasks — these should NOT be loaded
 	mockTask := &MaintenanceTask{
-		ID:     taskID,
+		ID:     "old_task_123",
 		Type:   "balance",
 		Status: TaskStatusPending,
-		TypedParams: &worker_pb.TaskParams{
-			TaskId:  taskID,
-			Sources: []*worker_pb.TaskSource{{Node: "server1", DiskId: 1}},
-			Targets: []*worker_pb.TaskTarget{{Node: "server1", DiskId: 2}},
-		},
 	}
 	mq.SetPersistence(&MockPersistence{tasks: []*MaintenanceTask{mockTask}})
 
-	// Load tasks
+	// LoadTasksFromPersistence should be a no-op — scanner will re-detect
 	err := mq.LoadTasksFromPersistence()
 	if err != nil {
-		t.Fatalf("Failed to load tasks: %v", err)
+		t.Fatalf("LoadTasksFromPersistence failed: %v", err)
 	}
 
-	// Verify capacity is reserved in ActiveTopology after loading (9 left)
-	if at.GetEffectiveAvailableCapacity("server1", 2) != 9 {
-		t.Errorf("Expected capacity 9 after loading tasks, got %d", at.GetEffectiveAvailableCapacity("server1", 2))
+	// Queue should be empty — tasks will be re-detected by scanner
+	stats := mq.GetStats()
+	if stats.TotalTasks != 0 {
+		t.Errorf("Expected 0 tasks after startup, got %d", stats.TotalTasks)
 	}
 }
 

weed/admin/maintenance/maintenance_scanner.go

@@ -32,21 +32,18 @@ func NewMaintenanceScanner(adminClient AdminClient, policy *MaintenancePolicy, q
 
 // ScanForMaintenanceTasks analyzes the cluster and generates maintenance tasks
 func (ms *MaintenanceScanner) ScanForMaintenanceTasks() ([]*TaskDetectionResult, error) {
-	// Get volume health metrics
-	volumeMetrics, err := ms.getVolumeHealthMetrics()
+	// Get volume health metrics directly in task-system format, along with topology info
+	taskMetrics, topologyInfo, err := ms.getVolumeHealthMetrics()
 	if err != nil {
 		return nil, fmt.Errorf("failed to get volume health metrics: %w", err)
 	}
 
 	// Use task system for all task types
 	if ms.integration != nil {
-		// Convert metrics to task system format
-		taskMetrics := ms.convertToTaskMetrics(volumeMetrics)
-
 		// Update topology information for complete cluster view (including empty servers)
 		// This must happen before task detection to ensure EC placement can consider all servers
-		if ms.lastTopologyInfo != nil {
-			if err := ms.integration.UpdateTopologyInfo(ms.lastTopologyInfo); err != nil {
+		if topologyInfo != nil {
+			if err := ms.integration.UpdateTopologyInfo(topologyInfo); err != nil {
 				glog.Errorf("Failed to update topology info for empty servers: %v", err)
 				// Don't fail the scan - continue with just volume-bearing servers
 			} else {
@@ -70,9 +67,12 @@ func (ms *MaintenanceScanner) ScanForMaintenanceTasks() ([]*TaskDetectionResult,
 	return []*TaskDetectionResult{}, nil
 }
 
-// getVolumeHealthMetrics collects health information for all volumes
-func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*VolumeHealthMetrics, error) {
-	var metrics []*VolumeHealthMetrics
+// getVolumeHealthMetrics collects health information for all volumes.
+// Returns metrics in task-system format directly (no intermediate copy) and
+// the topology info for updating the active topology.
+func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*types.VolumeHealthMetrics, *master_pb.TopologyInfo, error) {
+	var metrics []*types.VolumeHealthMetrics
+	var topologyInfo *master_pb.TopologyInfo
 
 	glog.V(1).Infof("Collecting volume health metrics from master")
 	err := ms.adminClient.WithMasterClient(func(client master_pb.SeaweedClient) error {
@@ -89,30 +89,28 @@ func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*VolumeHealthMetrics,
 
 		volumeSizeLimitBytes := uint64(resp.VolumeSizeLimitMb) * 1024 * 1024 // Convert MB to bytes
 
-		// Track all nodes discovered in topology
-		var allNodesInTopology []string
-		var nodesWithVolumes []string
-		var nodesWithoutVolumes []string
+		// Track node counts for summary logging (avoid accumulating full ID slices)
+		var totalNodes, nodesWithVolumes, nodesWithoutVolumes int
 
 		for _, dc := range resp.TopologyInfo.DataCenterInfos {
-			glog.V(2).Infof("Processing datacenter: %s", dc.Id)
+			glog.V(3).Infof("Processing datacenter: %s", dc.Id)
 			for _, rack := range dc.RackInfos {
-				glog.V(2).Infof("Processing rack: %s in datacenter: %s", rack.Id, dc.Id)
+				glog.V(3).Infof("Processing rack: %s in datacenter: %s", rack.Id, dc.Id)
 				for _, node := range rack.DataNodeInfos {
-					allNodesInTopology = append(allNodesInTopology, node.Id)
-					glog.V(2).Infof("Found volume server in topology: %s (disks: %d)", node.Id, len(node.DiskInfos))
+					totalNodes++
+					glog.V(3).Infof("Found volume server in topology: %s (disks: %d)", node.Id, len(node.DiskInfos))
 
 					hasVolumes := false
 					// Process each disk on this node
 					for diskType, diskInfo := range node.DiskInfos {
 						if len(diskInfo.VolumeInfos) > 0 {
 							hasVolumes = true
-							glog.V(2).Infof("Volume server %s disk %s has %d volumes", node.Id, diskType, len(diskInfo.VolumeInfos))
+							glog.V(3).Infof("Volume server %s disk %s has %d volumes", node.Id, diskType, len(diskInfo.VolumeInfos))
 						}
 
 						// Process volumes on this specific disk
 						for _, volInfo := range diskInfo.VolumeInfos {
-							metric := &VolumeHealthMetrics{
+							metric := &types.VolumeHealthMetrics{
 								VolumeID:         volInfo.Id,
 								Server:           node.Id,
 								ServerAddress:    node.Address,
@@ -138,7 +136,7 @@ func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*VolumeHealthMetrics,
 							}
 							metric.Age = time.Since(metric.LastModified)
 
-							glog.V(3).Infof("Volume %d on %s:%s (ID %d): size=%d, limit=%d, fullness=%.2f",
+							glog.V(4).Infof("Volume %d on %s:%s (ID %d): size=%d, limit=%d, fullness=%.2f",
 								metric.VolumeID, metric.Server, metric.DiskType, metric.DiskId, metric.Size, volumeSizeLimitBytes, metric.FullnessRatio)
 
 							metrics = append(metrics, metric)
@@ -146,29 +144,27 @@ func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*VolumeHealthMetrics,
 					}
 
 					if hasVolumes {
-						nodesWithVolumes = append(nodesWithVolumes, node.Id)
+						nodesWithVolumes++
 					} else {
-						nodesWithoutVolumes = append(nodesWithoutVolumes, node.Id)
+						nodesWithoutVolumes++
 						glog.V(1).Infof("Volume server %s found in topology but has no volumes", node.Id)
 					}
 				}
 			}
 		}
 
-		glog.Infof("Topology discovery complete:")
-		glog.Infof("  - Total volume servers in topology: %d (%v)", len(allNodesInTopology), allNodesInTopology)
-		glog.Infof("  - Volume servers with volumes: %d (%v)", len(nodesWithVolumes), nodesWithVolumes)
-		glog.Infof("  - Volume servers without volumes: %d (%v)", len(nodesWithoutVolumes), nodesWithoutVolumes)
+		glog.Infof("Topology discovery: %d volume servers (%d with volumes, %d without)",
+			totalNodes, nodesWithVolumes, nodesWithoutVolumes)
 
-		// Store topology info for volume shard tracker
-		ms.lastTopologyInfo = resp.TopologyInfo
+		// Return topology info as a local value (not retained on the scanner struct)
+		topologyInfo = resp.TopologyInfo
 
 		return nil
 	})
 
 	if err != nil {
 		glog.Errorf("Failed to get volume health metrics: %v", err)
-		return nil, err
+		return nil, nil, err
 	}
 
 	glog.V(1).Infof("Successfully collected metrics for %d actual volumes with disk ID information", len(metrics))
@@ -176,13 +172,13 @@ func (ms *MaintenanceScanner) getVolumeHealthMetrics() ([]*VolumeHealthMetrics,
 	// Count actual replicas and identify EC volumes
 	ms.enrichVolumeMetrics(metrics)
 
-	return metrics, nil
+	return metrics, topologyInfo, nil
 }
 
 // enrichVolumeMetrics adds additional information like replica counts
-func (ms *MaintenanceScanner) enrichVolumeMetrics(metrics []*VolumeHealthMetrics) {
+func (ms *MaintenanceScanner) enrichVolumeMetrics(metrics []*types.VolumeHealthMetrics) {
 	// Group volumes by ID to count replicas
-	volumeGroups := make(map[uint32][]*VolumeHealthMetrics)
+	volumeGroups := make(map[uint32][]*types.VolumeHealthMetrics)
 	for _, metric := range metrics {
 		volumeGroups[metric.VolumeID] = append(volumeGroups[metric.VolumeID], metric)
 	}
@@ -193,41 +189,9 @@ func (ms *MaintenanceScanner) enrichVolumeMetrics(metrics []*VolumeHealthMetrics
 		for _, replica := range replicas {
 			replica.ReplicaCount = replicaCount
 		}
-		glog.V(3).Infof("Volume %d has %d replicas", volumeID, replicaCount)
+		glog.V(4).Infof("Volume %d has %d replicas", volumeID, replicaCount)
 	}
 
 	// TODO: Identify EC volumes by checking volume structure
 	// This would require querying volume servers for EC shard information
 }
-
-// convertToTaskMetrics converts existing volume metrics to task system format
-func (ms *MaintenanceScanner) convertToTaskMetrics(metrics []*VolumeHealthMetrics) []*types.VolumeHealthMetrics {
-	var simplified []*types.VolumeHealthMetrics
-
-	for _, metric := range metrics {
-		simplified = append(simplified, &types.VolumeHealthMetrics{
-			VolumeID:         metric.VolumeID,
-			Server:           metric.Server,
-			ServerAddress:    metric.ServerAddress,
-			DiskType:         metric.DiskType,
-			DiskId:           metric.DiskId,
-			DataCenter:       metric.DataCenter,
-			Rack:             metric.Rack,
-			Collection:       metric.Collection,
-			Size:             metric.Size,
-			DeletedBytes:     metric.DeletedBytes,
-			GarbageRatio:     metric.GarbageRatio,
-			LastModified:     metric.LastModified,
-			Age:              metric.Age,
-			ReplicaCount:     metric.ReplicaCount,
-			ExpectedReplicas: metric.ExpectedReplicas,
-			IsReadOnly:       metric.IsReadOnly,
-			HasRemoteCopy:    metric.HasRemoteCopy,
-			IsECVolume:       metric.IsECVolume,
-			FullnessRatio:    metric.FullnessRatio,
-		})
-	}
-
-	glog.V(2).Infof("Converted %d volume metrics with disk ID information for task detection", len(simplified))
-	return simplified
-}

weed/admin/maintenance/maintenance_types.go

@@ -2,15 +2,11 @@ package maintenance
 
 import (
 	"html/template"
-	"sort"
 	"sync"
 	"time"
 
-	"github.com/seaweedfs/seaweedfs/weed/glog"
 	"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
 	"github.com/seaweedfs/seaweedfs/weed/pb/worker_pb"
-	"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
-	"github.com/seaweedfs/seaweedfs/weed/worker/types"
 )
 
 // AdminClient interface defines what the maintenance system needs from the admin server
@@ -21,51 +17,6 @@ type AdminClient interface {
 // MaintenanceTaskType represents different types of maintenance operations
 type MaintenanceTaskType string
 
-// GetRegisteredMaintenanceTaskTypes returns all registered task types as MaintenanceTaskType values
-// sorted alphabetically for consistent menu ordering
-func GetRegisteredMaintenanceTaskTypes() []MaintenanceTaskType {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-	var taskTypes []MaintenanceTaskType
-
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		maintenanceTaskType := MaintenanceTaskType(string(workerTaskType))
-		taskTypes = append(taskTypes, maintenanceTaskType)
-	}
-
-	// Sort task types alphabetically to ensure consistent menu ordering
-	sort.Slice(taskTypes, func(i, j int) bool {
-		return string(taskTypes[i]) < string(taskTypes[j])
-	})
-
-	return taskTypes
-}
-
-// GetMaintenanceTaskType returns a specific task type if it's registered, or empty string if not found
-func GetMaintenanceTaskType(taskTypeName string) MaintenanceTaskType {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		if string(workerTaskType) == taskTypeName {
-			return MaintenanceTaskType(taskTypeName)
-		}
-	}
-
-	return MaintenanceTaskType("")
-}
-
-// IsMaintenanceTaskTypeRegistered checks if a task type is registered
-func IsMaintenanceTaskTypeRegistered(taskType MaintenanceTaskType) bool {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		if string(workerTaskType) == string(taskType) {
-			return true
-		}
-	}
-
-	return false
-}
-
 // MaintenanceTaskPriority represents task execution priority
 type MaintenanceTaskPriority int
 
@@ -179,6 +130,7 @@ type TaskPersistence interface {
 	LoadTaskState(taskID string) (*MaintenanceTask, error)
 	LoadAllTaskStates() ([]*MaintenanceTask, error)
 	DeleteTaskState(taskID string) error
+	DeleteAllTaskStates() error
 	CleanupCompletedTasks() error
 
 	// Policy persistence
@@ -200,14 +152,6 @@ func GetTaskPolicy(mp *MaintenancePolicy, taskType MaintenanceTaskType) *TaskPol
 	return mp.TaskPolicies[string(taskType)]
 }
 
-// SetTaskPolicy sets the policy for a specific task type
-func SetTaskPolicy(mp *MaintenancePolicy, taskType MaintenanceTaskType, policy *TaskPolicy) {
-	if mp.TaskPolicies == nil {
-		mp.TaskPolicies = make(map[string]*TaskPolicy)
-	}
-	mp.TaskPolicies[string(taskType)] = policy
-}
-
 // IsTaskEnabled returns whether a task type is enabled
 func IsTaskEnabled(mp *MaintenancePolicy, taskType MaintenanceTaskType) bool {
 	policy := GetTaskPolicy(mp, taskType)
@@ -235,84 +179,6 @@ func GetRepeatInterval(mp *MaintenancePolicy, taskType MaintenanceTaskType) int
 	return int(policy.RepeatIntervalSeconds)
 }
 
-// GetVacuumTaskConfig returns the vacuum task configuration
-func GetVacuumTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType) *worker_pb.VacuumTaskConfig {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy == nil {
-		return nil
-	}
-	return policy.GetVacuumConfig()
-}
-
-// GetErasureCodingTaskConfig returns the erasure coding task configuration
-func GetErasureCodingTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType) *worker_pb.ErasureCodingTaskConfig {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy == nil {
-		return nil
-	}
-	return policy.GetErasureCodingConfig()
-}
-
-// GetBalanceTaskConfig returns the balance task configuration
-func GetBalanceTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType) *worker_pb.BalanceTaskConfig {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy == nil {
-		return nil
-	}
-	return policy.GetBalanceConfig()
-}
-
-// GetReplicationTaskConfig returns the replication task configuration
-func GetReplicationTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType) *worker_pb.ReplicationTaskConfig {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy == nil {
-		return nil
-	}
-	return policy.GetReplicationConfig()
-}
-
-// Note: GetTaskConfig was removed - use typed getters: GetVacuumTaskConfig, GetErasureCodingTaskConfig, GetBalanceTaskConfig, or GetReplicationTaskConfig
-
-// SetVacuumTaskConfig sets the vacuum task configuration
-func SetVacuumTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType, config *worker_pb.VacuumTaskConfig) {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy != nil {
-		policy.TaskConfig = &worker_pb.TaskPolicy_VacuumConfig{
-			VacuumConfig: config,
-		}
-	}
-}
-
-// SetErasureCodingTaskConfig sets the erasure coding task configuration
-func SetErasureCodingTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType, config *worker_pb.ErasureCodingTaskConfig) {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy != nil {
-		policy.TaskConfig = &worker_pb.TaskPolicy_ErasureCodingConfig{
-			ErasureCodingConfig: config,
-		}
-	}
-}
-
-// SetBalanceTaskConfig sets the balance task configuration
-func SetBalanceTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType, config *worker_pb.BalanceTaskConfig) {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy != nil {
-		policy.TaskConfig = &worker_pb.TaskPolicy_BalanceConfig{
-			BalanceConfig: config,
-		}
-	}
-}
-
-// SetReplicationTaskConfig sets the replication task configuration
-func SetReplicationTaskConfig(mp *MaintenancePolicy, taskType MaintenanceTaskType, config *worker_pb.ReplicationTaskConfig) {
-	policy := GetTaskPolicy(mp, taskType)
-	if policy != nil {
-		policy.TaskConfig = &worker_pb.TaskPolicy_ReplicationConfig{
-			ReplicationConfig: config,
-		}
-	}
-}
-
 // SetTaskConfig sets a configuration value for a task type (legacy method - use typed setters above)
 // Note: SetTaskConfig was removed - use typed setters: SetVacuumTaskConfig, SetErasureCodingTaskConfig, SetBalanceTaskConfig, or SetReplicationTaskConfig
 
@@ -341,12 +207,11 @@ type MaintenanceQueue struct {
 
 // MaintenanceScanner analyzes the cluster and generates maintenance tasks
 type MaintenanceScanner struct {
-	adminClient      AdminClient
-	policy           *MaintenancePolicy
-	queue            *MaintenanceQueue
-	lastScan         map[MaintenanceTaskType]time.Time
-	integration      *MaintenanceIntegration
-	lastTopologyInfo *master_pb.TopologyInfo
+	adminClient AdminClient
+	policy      *MaintenancePolicy
+	queue       *MaintenanceQueue
+	lastScan    map[MaintenanceTaskType]time.Time
+	integration *MaintenanceIntegration
 }
 
 // TaskDetectionResult represents the result of scanning for maintenance needs
@@ -475,180 +340,6 @@ type ClusterReplicationTask struct {
 	Metadata        map[string]string `json:"metadata,omitempty"`
 }
 
-// BuildMaintenancePolicyFromTasks creates a maintenance policy with configurations
-// from all registered tasks using their UI providers
-func BuildMaintenancePolicyFromTasks() *MaintenancePolicy {
-	policy := &MaintenancePolicy{
-		TaskPolicies:                 make(map[string]*TaskPolicy),
-		GlobalMaxConcurrent:          4,
-		DefaultRepeatIntervalSeconds: 6 * 3600,  // 6 hours in seconds
-		DefaultCheckIntervalSeconds:  12 * 3600, // 12 hours in seconds
-	}
-
-	// Get all registered task types from the UI registry
-	uiRegistry := tasks.GetGlobalUIRegistry()
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-
-	for taskType, provider := range uiRegistry.GetAllProviders() {
-		// Convert task type to maintenance task type
-		maintenanceTaskType := MaintenanceTaskType(string(taskType))
-
-		// Get the default configuration from the UI provider
-		defaultConfig := provider.GetCurrentConfig()
-
-		// Create task policy from UI configuration
-		taskPolicy := &TaskPolicy{
-			Enabled:               true, // Default enabled
-			MaxConcurrent:         2,    // Default concurrency
-			RepeatIntervalSeconds: policy.DefaultRepeatIntervalSeconds,
-			CheckIntervalSeconds:  policy.DefaultCheckIntervalSeconds,
-		}
-
-		// Extract configuration using TaskConfig interface - no more map conversions!
-		if taskConfig, ok := defaultConfig.(interface{ ToTaskPolicy() *worker_pb.TaskPolicy }); ok {
-			// Use protobuf directly for clean, type-safe config extraction
-			pbTaskPolicy := taskConfig.ToTaskPolicy()
-			taskPolicy.Enabled = pbTaskPolicy.Enabled
-			taskPolicy.MaxConcurrent = pbTaskPolicy.MaxConcurrent
-			if pbTaskPolicy.RepeatIntervalSeconds > 0 {
-				taskPolicy.RepeatIntervalSeconds = pbTaskPolicy.RepeatIntervalSeconds
-			}
-			if pbTaskPolicy.CheckIntervalSeconds > 0 {
-				taskPolicy.CheckIntervalSeconds = pbTaskPolicy.CheckIntervalSeconds
-			}
-		}
-
-		// Also get defaults from scheduler if available (using types.TaskScheduler explicitly)
-		var scheduler types.TaskScheduler = typesRegistry.GetScheduler(taskType)
-		if scheduler != nil {
-			if taskPolicy.MaxConcurrent <= 0 {
-				taskPolicy.MaxConcurrent = int32(scheduler.GetMaxConcurrent())
-			}
-			// Convert default repeat interval to seconds
-			if repeatInterval := scheduler.GetDefaultRepeatInterval(); repeatInterval > 0 {
-				taskPolicy.RepeatIntervalSeconds = int32(repeatInterval.Seconds())
-			}
-		}
-
-		// Also get defaults from detector if available (using types.TaskDetector explicitly)
-		var detector types.TaskDetector = typesRegistry.GetDetector(taskType)
-		if detector != nil {
-			// Convert scan interval to check interval (seconds)
-			if scanInterval := detector.ScanInterval(); scanInterval > 0 {
-				taskPolicy.CheckIntervalSeconds = int32(scanInterval.Seconds())
-			}
-		}
-
-		policy.TaskPolicies[string(maintenanceTaskType)] = taskPolicy
-		glog.V(3).Infof("Built policy for task type %s: enabled=%v, max_concurrent=%d",
-			maintenanceTaskType, taskPolicy.Enabled, taskPolicy.MaxConcurrent)
-	}
-
-	glog.V(2).Infof("Built maintenance policy with %d task configurations", len(policy.TaskPolicies))
-	return policy
-}
-
-// SetPolicyFromTasks sets the maintenance policy from registered tasks
-func SetPolicyFromTasks(policy *MaintenancePolicy) {
-	if policy == nil {
-		return
-	}
-
-	// Build new policy from tasks
-	newPolicy := BuildMaintenancePolicyFromTasks()
-
-	// Copy task policies
-	policy.TaskPolicies = newPolicy.TaskPolicies
-
-	glog.V(1).Infof("Updated maintenance policy with %d task configurations from registered tasks", len(policy.TaskPolicies))
-}
-
-// GetTaskIcon returns the icon CSS class for a task type from its UI provider
-func GetTaskIcon(taskType MaintenanceTaskType) string {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-	uiRegistry := tasks.GetGlobalUIRegistry()
-
-	// Convert MaintenanceTaskType to TaskType
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		if string(workerTaskType) == string(taskType) {
-			// Get the UI provider for this task type
-			provider := uiRegistry.GetProvider(workerTaskType)
-			if provider != nil {
-				return provider.GetIcon()
-			}
-			break
-		}
-	}
-
-	// Default icon if no UI provider found
-	return "fas fa-cog text-muted"
-}
-
-// GetTaskDisplayName returns the display name for a task type from its UI provider
-func GetTaskDisplayName(taskType MaintenanceTaskType) string {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-	uiRegistry := tasks.GetGlobalUIRegistry()
-
-	// Convert MaintenanceTaskType to TaskType
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		if string(workerTaskType) == string(taskType) {
-			// Get the UI provider for this task type
-			provider := uiRegistry.GetProvider(workerTaskType)
-			if provider != nil {
-				return provider.GetDisplayName()
-			}
-			break
-		}
-	}
-
-	// Fallback to the task type string
-	return string(taskType)
-}
-
-// GetTaskDescription returns the description for a task type from its UI provider
-func GetTaskDescription(taskType MaintenanceTaskType) string {
-	typesRegistry := tasks.GetGlobalTypesRegistry()
-	uiRegistry := tasks.GetGlobalUIRegistry()
-
-	// Convert MaintenanceTaskType to TaskType
-	for workerTaskType := range typesRegistry.GetAllDetectors() {
-		if string(workerTaskType) == string(taskType) {
-			// Get the UI provider for this task type
-			provider := uiRegistry.GetProvider(workerTaskType)
-			if provider != nil {
-				return provider.GetDescription()
-			}
-			break
-		}
-	}
-
-	// Fallback to a generic description
-	return "Configure detailed settings for " + string(taskType) + " tasks."
-}
-
-// BuildMaintenanceMenuItems creates menu items for all registered task types
-func BuildMaintenanceMenuItems() []*MaintenanceMenuItem {
-	var menuItems []*MaintenanceMenuItem
-
-	// Get all registered task types
-	registeredTypes := GetRegisteredMaintenanceTaskTypes()
-
-	for _, taskType := range registeredTypes {
-		menuItem := &MaintenanceMenuItem{
-			TaskType:    taskType,
-			DisplayName: GetTaskDisplayName(taskType),
-			Description: GetTaskDescription(taskType),
-			Icon:        GetTaskIcon(taskType),
-			IsEnabled:   IsMaintenanceTaskTypeRegistered(taskType),
-			Path:        "/maintenance/config/" + string(taskType),
-		}
-
-		menuItems = append(menuItems, menuItem)
-	}
-
-	return menuItems
-}
-
 // Helper functions to extract configuration fields
 
 // Note: Removed getVacuumConfigField, getErasureCodingConfigField, getBalanceConfigField, getReplicationConfigField

weed/admin/maintenance/maintenance_worker.go

@@ -1,421 +0,0 @@
-package maintenance
-
-import (
-	"context"
-	"fmt"
-	"os"
-	"sync"
-	"time"
-
-	"github.com/seaweedfs/seaweedfs/weed/glog"
-	"github.com/seaweedfs/seaweedfs/weed/worker"
-	"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
-	"github.com/seaweedfs/seaweedfs/weed/worker/types"
-
-	// Import task packages to trigger their auto-registration
-	_ "github.com/seaweedfs/seaweedfs/weed/worker/tasks/balance"
-	_ "github.com/seaweedfs/seaweedfs/weed/worker/tasks/erasure_coding"
-	_ "github.com/seaweedfs/seaweedfs/weed/worker/tasks/vacuum"
-)
-
-// MaintenanceWorkerService manages maintenance task execution
-// TaskExecutor defines the function signature for task execution
-type TaskExecutor func(*MaintenanceWorkerService, *MaintenanceTask) error
-
-// TaskExecutorFactory creates a task executor for a given worker service
-type TaskExecutorFactory func() TaskExecutor
-
-// Global registry for task executor factories
-var taskExecutorFactories = make(map[MaintenanceTaskType]TaskExecutorFactory)
-var executorRegistryMutex sync.RWMutex
-var executorRegistryInitOnce sync.Once
-
-// initializeExecutorFactories dynamically registers executor factories for all auto-registered task types
-func initializeExecutorFactories() {
-	executorRegistryInitOnce.Do(func() {
-		// Get all registered task types from the global registry
-		typesRegistry := tasks.GetGlobalTypesRegistry()
-
-		var taskTypes []MaintenanceTaskType
-		for workerTaskType := range typesRegistry.GetAllDetectors() {
-			// Convert types.TaskType to MaintenanceTaskType by string conversion
-			maintenanceTaskType := MaintenanceTaskType(string(workerTaskType))
-			taskTypes = append(taskTypes, maintenanceTaskType)
-		}
-
-		// Register generic executor for all task types
-		for _, taskType := range taskTypes {
-			RegisterTaskExecutorFactory(taskType, createGenericTaskExecutor)
-		}
-
-		glog.V(1).Infof("Dynamically registered generic task executor for %d task types: %v", len(taskTypes), taskTypes)
-	})
-}
-
-// RegisterTaskExecutorFactory registers a factory function for creating task executors
-func RegisterTaskExecutorFactory(taskType MaintenanceTaskType, factory TaskExecutorFactory) {
-	executorRegistryMutex.Lock()
-	defer executorRegistryMutex.Unlock()
-	taskExecutorFactories[taskType] = factory
-	glog.V(2).Infof("Registered executor factory for task type: %s", taskType)
-}
-
-// GetTaskExecutorFactory returns the factory for a task type
-func GetTaskExecutorFactory(taskType MaintenanceTaskType) (TaskExecutorFactory, bool) {
-	// Ensure executor factories are initialized
-	initializeExecutorFactories()
-
-	executorRegistryMutex.RLock()
-	defer executorRegistryMutex.RUnlock()
-	factory, exists := taskExecutorFactories[taskType]
-	return factory, exists
-}
-
-// GetSupportedExecutorTaskTypes returns all task types with registered executor factories
-func GetSupportedExecutorTaskTypes() []MaintenanceTaskType {
-	// Ensure executor factories are initialized
-	initializeExecutorFactories()
-
-	executorRegistryMutex.RLock()
-	defer executorRegistryMutex.RUnlock()
-
-	taskTypes := make([]MaintenanceTaskType, 0, len(taskExecutorFactories))
-	for taskType := range taskExecutorFactories {
-		taskTypes = append(taskTypes, taskType)
-	}
-	return taskTypes
-}
-
-// createGenericTaskExecutor creates a generic task executor that uses the task registry
-func createGenericTaskExecutor() TaskExecutor {
-	return func(mws *MaintenanceWorkerService, task *MaintenanceTask) error {
-		return mws.executeGenericTask(task)
-	}
-}
-
-// init does minimal initialization - actual registration happens lazily
-func init() {
-	// Executor factory registration will happen lazily when first accessed
-	glog.V(1).Infof("Maintenance worker initialized - executor factories will be registered on first access")
-}
-
-type MaintenanceWorkerService struct {
-	workerID      string
-	address       string
-	adminServer   string
-	capabilities  []MaintenanceTaskType
-	maxConcurrent int
-	currentTasks  map[string]*MaintenanceTask
-	queue         *MaintenanceQueue
-	adminClient   AdminClient
-	running       bool
-	stopChan      chan struct{}
-
-	// Task execution registry
-	taskExecutors map[MaintenanceTaskType]TaskExecutor
-
-	// Task registry for creating task instances
-	taskRegistry *tasks.TaskRegistry
-}
-
-// NewMaintenanceWorkerService creates a new maintenance worker service
-func NewMaintenanceWorkerService(workerID, address, adminServer string) *MaintenanceWorkerService {
-	// Get all registered maintenance task types dynamically
-	capabilities := GetRegisteredMaintenanceTaskTypes()
-
-	worker := &MaintenanceWorkerService{
-		workerID:      workerID,
-		address:       address,
-		adminServer:   adminServer,
-		capabilities:  capabilities,
-		maxConcurrent: 2, // Default concurrent task limit
-		currentTasks:  make(map[string]*MaintenanceTask),
-		stopChan:      make(chan struct{}),
-		taskExecutors: make(map[MaintenanceTaskType]TaskExecutor),
-		taskRegistry:  tasks.GetGlobalTaskRegistry(), // Use global registry with auto-registered tasks
-	}
-
-	// Initialize task executor registry
-	worker.initializeTaskExecutors()
-
-	glog.V(1).Infof("Created maintenance worker with %d registered task types", len(worker.taskRegistry.GetAll()))
-
-	return worker
-}
-
-// executeGenericTask executes a task using the task registry instead of hardcoded methods
-func (mws *MaintenanceWorkerService) executeGenericTask(task *MaintenanceTask) error {
-	glog.V(2).Infof("Executing generic task %s: %s for volume %d", task.ID, task.Type, task.VolumeID)
-
-	// Validate that task has proper typed parameters
-	if task.TypedParams == nil {
-		return fmt.Errorf("task %s has no typed parameters - task was not properly planned (insufficient destinations)", task.ID)
-	}
-
-	// Convert MaintenanceTask to types.TaskType
-	taskType := types.TaskType(string(task.Type))
-
-	// Create task instance using the registry
-	taskInstance, err := mws.taskRegistry.Get(taskType).Create(task.TypedParams)
-	if err != nil {
-		return fmt.Errorf("failed to create task instance: %w", err)
-	}
-
-	// Update progress to show task has started
-	mws.updateTaskProgress(task.ID, 5)
-
-	// Execute the task
-	err = taskInstance.Execute(context.Background(), task.TypedParams)
-	if err != nil {
-		return fmt.Errorf("task execution failed: %w", err)
-	}
-
-	// Update progress to show completion
-	mws.updateTaskProgress(task.ID, 100)
-
-	glog.V(2).Infof("Generic task %s completed successfully", task.ID)
-	return nil
-}
-
-// initializeTaskExecutors sets up the task execution registry dynamically
-func (mws *MaintenanceWorkerService) initializeTaskExecutors() {
-	mws.taskExecutors = make(map[MaintenanceTaskType]TaskExecutor)
-
-	// Get all registered executor factories and create executors
-	executorRegistryMutex.RLock()
-	defer executorRegistryMutex.RUnlock()
-
-	for taskType, factory := range taskExecutorFactories {
-		executor := factory()
-		mws.taskExecutors[taskType] = executor
-		glog.V(3).Infof("Initialized executor for task type: %s", taskType)
-	}
-
-	glog.V(2).Infof("Initialized %d task executors", len(mws.taskExecutors))
-}
-
-// RegisterTaskExecutor allows dynamic registration of new task executors
-func (mws *MaintenanceWorkerService) RegisterTaskExecutor(taskType MaintenanceTaskType, executor TaskExecutor) {
-	if mws.taskExecutors == nil {
-		mws.taskExecutors = make(map[MaintenanceTaskType]TaskExecutor)
-	}
-	mws.taskExecutors[taskType] = executor
-	glog.V(1).Infof("Registered executor for task type: %s", taskType)
-}
-
-// GetSupportedTaskTypes returns all task types that this worker can execute
-func (mws *MaintenanceWorkerService) GetSupportedTaskTypes() []MaintenanceTaskType {
-	return GetSupportedExecutorTaskTypes()
-}
-
-// Start begins the worker service
-func (mws *MaintenanceWorkerService) Start() error {
-	mws.running = true
-
-	// Register with admin server
-	worker := &MaintenanceWorker{
-		ID:            mws.workerID,
-		Address:       mws.address,
-		Capabilities:  mws.capabilities,
-		MaxConcurrent: mws.maxConcurrent,
-	}
-
-	if mws.queue != nil {
-		mws.queue.RegisterWorker(worker)
-	}
-
-	// Start worker loop
-	go mws.workerLoop()
-
-	glog.Infof("Maintenance worker %s started at %s", mws.workerID, mws.address)
-	return nil
-}
-
-// Stop terminates the worker service
-func (mws *MaintenanceWorkerService) Stop() {
-	mws.running = false
-	close(mws.stopChan)
-
-	// Wait for current tasks to complete or timeout
-	timeout := time.NewTimer(30 * time.Second)
-	defer timeout.Stop()
-
-	for len(mws.currentTasks) > 0 {
-		select {
-		case <-timeout.C:
-			glog.Warningf("Worker %s stopping with %d tasks still running", mws.workerID, len(mws.currentTasks))
-			return
-		case <-time.After(time.Second):
-			// Check again
-		}
-	}
-
-	glog.Infof("Maintenance worker %s stopped", mws.workerID)
-}
-
-// workerLoop is the main worker event loop
-func (mws *MaintenanceWorkerService) workerLoop() {
-	heartbeatTicker := time.NewTicker(30 * time.Second)
-	defer heartbeatTicker.Stop()
-
-	taskRequestTicker := time.NewTicker(5 * time.Second)
-	defer taskRequestTicker.Stop()
-
-	for mws.running {
-		select {
-		case <-mws.stopChan:
-			return
-		case <-heartbeatTicker.C:
-			mws.sendHeartbeat()
-		case <-taskRequestTicker.C:
-			mws.requestTasks()
-		}
-	}
-}
-
-// sendHeartbeat sends heartbeat to admin server
-func (mws *MaintenanceWorkerService) sendHeartbeat() {
-	if mws.queue != nil {
-		mws.queue.UpdateWorkerHeartbeat(mws.workerID)
-	}
-}
-
-// requestTasks requests new tasks from the admin server
-func (mws *MaintenanceWorkerService) requestTasks() {
-	if len(mws.currentTasks) >= mws.maxConcurrent {
-		return // Already at capacity
-	}
-
-	if mws.queue != nil {
-		task := mws.queue.GetNextTask(mws.workerID, mws.capabilities)
-		if task != nil {
-			mws.executeTask(task)
-		}
-	}
-}
-
-// executeTask executes a maintenance task
-func (mws *MaintenanceWorkerService) executeTask(task *MaintenanceTask) {
-	mws.currentTasks[task.ID] = task
-
-	go func() {
-		defer func() {
-			delete(mws.currentTasks, task.ID)
-		}()
-
-		glog.Infof("Worker %s executing task %s: %s", mws.workerID, task.ID, task.Type)
-
-		// Execute task using dynamic executor registry
-		var err error
-		if executor, exists := mws.taskExecutors[task.Type]; exists {
-			err = executor(mws, task)
-		} else {
-			err = fmt.Errorf("unsupported task type: %s", task.Type)
-			glog.Errorf("No executor registered for task type: %s", task.Type)
-		}
-
-		// Report task completion
-		if mws.queue != nil {
-			errorMsg := ""
-			if err != nil {
-				errorMsg = err.Error()
-			}
-			mws.queue.CompleteTask(task.ID, errorMsg)
-		}
-
-		if err != nil {
-			glog.Errorf("Worker %s failed to execute task %s: %v", mws.workerID, task.ID, err)
-		} else {
-			glog.Infof("Worker %s completed task %s successfully", mws.workerID, task.ID)
-		}
-	}()
-}
-
-// updateTaskProgress updates the progress of a task
-func (mws *MaintenanceWorkerService) updateTaskProgress(taskID string, progress float64) {
-	if mws.queue != nil {
-		mws.queue.UpdateTaskProgress(taskID, progress)
-	}
-}
-
-// GetStatus returns the current status of the worker
-func (mws *MaintenanceWorkerService) GetStatus() map[string]interface{} {
-	return map[string]interface{}{
-		"worker_id":      mws.workerID,
-		"address":        mws.address,
-		"running":        mws.running,
-		"capabilities":   mws.capabilities,
-		"max_concurrent": mws.maxConcurrent,
-		"current_tasks":  len(mws.currentTasks),
-		"task_details":   mws.currentTasks,
-	}
-}
-
-// SetQueue sets the maintenance queue for the worker
-func (mws *MaintenanceWorkerService) SetQueue(queue *MaintenanceQueue) {
-	mws.queue = queue
-}
-
-// SetAdminClient sets the admin client for the worker
-func (mws *MaintenanceWorkerService) SetAdminClient(client AdminClient) {
-	mws.adminClient = client
-}
-
-// SetCapabilities sets the worker capabilities
-func (mws *MaintenanceWorkerService) SetCapabilities(capabilities []MaintenanceTaskType) {
-	mws.capabilities = capabilities
-}
-
-// SetMaxConcurrent sets the maximum concurrent tasks
-func (mws *MaintenanceWorkerService) SetMaxConcurrent(max int) {
-	mws.maxConcurrent = max
-}
-
-// SetHeartbeatInterval sets the heartbeat interval (placeholder for future use)
-func (mws *MaintenanceWorkerService) SetHeartbeatInterval(interval time.Duration) {
-	// Future implementation for configurable heartbeat
-}
-
-// SetTaskRequestInterval sets the task request interval (placeholder for future use)
-func (mws *MaintenanceWorkerService) SetTaskRequestInterval(interval time.Duration) {
-	// Future implementation for configurable task requests
-}
-
-// MaintenanceWorkerCommand represents a standalone maintenance worker command
-type MaintenanceWorkerCommand struct {
-	workerService *MaintenanceWorkerService
-}
-
-// NewMaintenanceWorkerCommand creates a new worker command
-func NewMaintenanceWorkerCommand(workerID, address, adminServer string) *MaintenanceWorkerCommand {
-	return &MaintenanceWorkerCommand{
-		workerService: NewMaintenanceWorkerService(workerID, address, adminServer),
-	}
-}
-
-// Run starts the maintenance worker as a standalone service
-func (mwc *MaintenanceWorkerCommand) Run() error {
-	// Generate or load persistent worker ID if not provided
-	if mwc.workerService.workerID == "" {
-		// Get current working directory for worker ID persistence
-		wd, err := os.Getwd()
-		if err != nil {
-			return fmt.Errorf("failed to get working directory: %w", err)
-		}
-
-		workerID, err := worker.GenerateOrLoadWorkerID(wd)
-		if err != nil {
-			return fmt.Errorf("failed to generate or load worker ID: %w", err)
-		}
-		mwc.workerService.workerID = workerID
-	}
-
-	// Start the worker service
-	err := mwc.workerService.Start()
-	if err != nil {
-		return fmt.Errorf("failed to start maintenance worker: %w", err)
-	}
-
-	// Wait for interrupt signal
-	select {}
-}

weed/admin/plugin/plugin.go

@@ -122,6 +122,7 @@ type Plugin struct {
 type streamSession struct {
 	workerID  string
 	outgoing  chan *plugin_pb.AdminToWorkerMessage
+	done      chan struct{}
 	closeOnce sync.Once
 }
 
@@ -274,6 +275,7 @@ func (r *Plugin) WorkerStream(stream plugin_pb.PluginControlService_WorkerStream
 	session := &streamSession{
 		workerID: workerID,
 		outgoing: make(chan *plugin_pb.AdminToWorkerMessage, r.outgoingBuffer),
+		done:     make(chan struct{}),
 	}
 	r.putSession(session)
 	defer r.cleanupSession(workerID)
@@ -908,8 +910,10 @@ func (r *Plugin) sendLoop(
 			return nil
 		case <-r.shutdownCh:
 			return nil
-		case msg, ok := <-session.outgoing:
-			if !ok {
+		case <-session.done:
+			return nil
+		case msg := <-session.outgoing:
+			if msg == nil {
 				return nil
 			}
 			if err := stream.Send(msg); err != nil {
@@ -930,6 +934,8 @@ func (r *Plugin) sendToWorker(workerID string, message *plugin_pb.AdminToWorkerM
 	select {
 	case <-r.shutdownCh:
 		return fmt.Errorf("plugin is shutting down")
+	case <-session.done:
+		return fmt.Errorf("worker %s session is closed", workerID)
 	case session.outgoing <- message:
 		return nil
 	case <-time.After(r.sendTimeout):
@@ -1425,7 +1431,7 @@ func CloneConfigValueMap(in map[string]*plugin_pb.ConfigValue) map[string]*plugi
 
 func (s *streamSession) close() {
 	s.closeOnce.Do(func() {
-		close(s.outgoing)
+		close(s.done)
 	})
 }