Move security.toml to example and secure keys

This reverts commit 551a31e156.

.github/pull_request_template.md

@@ -12,7 +12,7 @@
 # Checks
 - [ ] I have added unit tests if possible.
 - [ ] I will add related wiki document changes and link to this PR after merging.
-- [ ] All AI code review comments have been addressed. No more comments to fix if reviewed again. Reviewer may request additional gemini and copilot reviews.
+- [ ] All AI code review comments have been addressed. No more comments to fix if reviewed again.
 
 # Checks for AI generated PRs
 - [ ] I have reviewed every line of code.

.github/workflows/container_dev.yml

@@ -3,6 +3,7 @@ name: "docker: build dev containers"
 on:
   push:
     branches: [ master ]
+  workflow_dispatch: {}
 
 permissions:
   contents: read

.github/workflows/container_latest.yml

@@ -4,58 +4,29 @@ on:
   push:
     tags:
       - '*'
-  workflow_dispatch:
-    inputs:
-      source_ref:
-        description: 'Git ref to build (branch, tag, or commit SHA)'
-        required: true
-        default: 'master'
-      image_tag:
-        description: 'Docker tag to publish (without variant suffix)'
-        required: true
-        default: 'latest'
-      variant:
-        description: 'Variant to build manually'
-        required: true
-        type: choice
-        default: all
-        options:
-          - all
-          - standard
-          - large_disk
+  workflow_dispatch: {}
 
 permissions:
   contents: read
 
 jobs:
-  setup:
-    runs-on: ubuntu-latest
-    outputs:
-      variants: ${{ steps.set-variants.outputs.variants }}
-    steps:
-      - name: Select variants for this run
-        id: set-variants
-        run: |
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ] && [ "${{ github.event.inputs.variant }}" != "all" ]; then
-            variants="[\"${{ github.event.inputs.variant }}\"]"
-          else
-            variants='["standard","large_disk"]'
-          fi
-          echo "variants=$variants" >> "$GITHUB_OUTPUT"
-
   build:
-    needs: [setup]
     runs-on: ubuntu-latest
     strategy:
       matrix:
         platform: [amd64, arm64, arm, 386]
-        variant: ${{ fromJSON(needs.setup.outputs.variants) }}
-
+        include:
+          - platform: amd64
+            qemu: false
+          - platform: arm64
+            qemu: true
+          - platform: arm
+            qemu: true
+          - platform: 386
+            qemu: true
     steps:
       - name: Checkout
         uses: actions/checkout@v6
-        with:
-          ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
       - name: Free Disk Space
         run: |
           echo "Available disk space before cleanup:"
@@ -72,18 +43,6 @@ jobs:
           [ -d /go/pkg ] && rm -rf /go/pkg || true
           echo "Available disk space after cleanup:"
           df -h
-      
-      - name: Configure variant
-        id: config
-        run: |
-          if [ "${{ matrix.variant }}" == "large_disk" ]; then
-            echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
-            echo "build_args=TAGS=5BytesOffset" >> $GITHUB_OUTPUT
-          else
-            echo "tag_suffix=" >> $GITHUB_OUTPUT
-            echo "build_args=" >> $GITHUB_OUTPUT
-          fi
-
       - name: Docker meta
         id: docker_meta
         uses: docker/metadata-action@v5
@@ -91,13 +50,13 @@ jobs:
           images: |
             chrislusf/seaweedfs
             ghcr.io/chrislusf/seaweedfs
-          tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
+          tags: type=raw,value=latest
           labels: |
             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
-        if: matrix.platform != 'amd64'
+        if: matrix.qemu
         uses: docker/setup-qemu-action@v3
       - name: Create BuildKit config
         run: |
@@ -123,7 +82,7 @@ jobs:
           registry: ghcr.io
           username: ${{ secrets.GHCR_USERNAME }}
           password: ${{ secrets.GHCR_TOKEN }}
-      - name: Build ${{ matrix.platform }} ${{ matrix.variant }}
+      - name: Build ${{ matrix.platform }}
         uses: docker/build-push-action@v6
         env:
           DOCKER_BUILDKIT: 1
@@ -133,14 +92,13 @@ jobs:
           file: ./docker/Dockerfile.go_build
           platforms: linux/${{ matrix.platform }}
           # Push to GHCR only during build to avoid Docker Hub rate limits
-          tags: ghcr.io/chrislusf/seaweedfs:${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}${{ steps.config.outputs.tag_suffix }}-${{ matrix.platform }}
+          tags: ghcr.io/chrislusf/seaweedfs:latest-${{ matrix.platform }}
           labels: ${{ steps.docker_meta.outputs.labels }}
-          cache-from: type=gha,scope=${{ matrix.variant }}-${{ matrix.platform }}
-          cache-to: type=gha,mode=max,scope=${{ matrix.variant }}-${{ matrix.platform }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
           build-args: |
             BUILDKIT_INLINE_CACHE=1
-            BRANCH=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.sha }}
-            ${{ steps.config.outputs.build_args }}
+            BRANCH=${{ github.sha }}
       - name: Clean up build artifacts
         if: always()
         run: |
@@ -151,26 +109,11 @@ jobs:
 
   create-manifest:
     runs-on: ubuntu-latest
-    needs: [setup, build]
+    needs: [build]
     if: github.event_name != 'pull_request'
-    strategy:
-      matrix:
-        variant: ${{ fromJSON(needs.setup.outputs.variants) }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
-        with:
-          ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
-      
-      - name: Configure variant
-        id: config
-        run: |
-          if [ "${{ matrix.variant }}" == "large_disk" ]; then
-            echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
-          else
-            echo "tag_suffix=" >> $GITHUB_OUTPUT
-          fi
-
       - name: Docker meta
         id: docker_meta
         uses: docker/metadata-action@v5
@@ -178,7 +121,7 @@ jobs:
           images: |
             chrislusf/seaweedfs
             ghcr.io/chrislusf/seaweedfs
-          tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
+          tags: type=raw,value=latest
       - name: Login to Docker Hub
         uses: docker/login-action@v3
         with:
@@ -199,16 +142,13 @@ jobs:
           crane version
       - name: Create and push manifest
         run: |
-          SUFFIX="${{ steps.config.outputs.tag_suffix }}"
-          BASE_TAG="${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}"
-          
           # Create manifest on GHCR first (no rate limits)
           echo "Creating GHCR manifest (no rate limits)..."
-          docker buildx imagetools create -t ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} \
-            ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-amd64 \
-            ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm64 \
-            ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm \
-            ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-386
+          docker buildx imagetools create -t ghcr.io/chrislusf/seaweedfs:latest \
+            ghcr.io/chrislusf/seaweedfs:latest-amd64 \
+            ghcr.io/chrislusf/seaweedfs:latest-arm64 \
+            ghcr.io/chrislusf/seaweedfs:latest-arm \
+            ghcr.io/chrislusf/seaweedfs:latest-386
           
           # Copy the complete multi-arch image from GHCR to Docker Hub
           # This only requires one pull from GHCR (no rate limit) and one push to Docker Hub
@@ -244,16 +184,16 @@ jobs:
           # Use crane or skopeo to copy, fallback to docker if not available
           if command -v crane &> /dev/null; then
             echo "Using crane to copy..."
-            retry_with_backoff crane copy ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
+            retry_with_backoff crane copy ghcr.io/chrislusf/seaweedfs:latest chrislusf/seaweedfs:latest
           elif command -v skopeo &> /dev/null; then
             echo "Using skopeo to copy..."
-            retry_with_backoff skopeo copy --all docker://ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} docker://chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
+            retry_with_backoff skopeo copy --all docker://ghcr.io/chrislusf/seaweedfs:latest docker://chrislusf/seaweedfs:latest
           else
             echo "Using docker buildx imagetools (pulling 4 images from Docker Hub)..."
             # Fallback: create manifest directly on Docker Hub (pulls from Docker Hub - rate limited)
-            retry_with_backoff docker buildx imagetools create -t chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} \
-              ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-amd64 \
-              ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm64 \
-              ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm \
-              ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-386
+            retry_with_backoff docker buildx imagetools create -t chrislusf/seaweedfs:latest \
+              ghcr.io/chrislusf/seaweedfs:latest-amd64 \
+              ghcr.io/chrislusf/seaweedfs:latest-arm64 \
+              ghcr.io/chrislusf/seaweedfs:latest-arm \
+              ghcr.io/chrislusf/seaweedfs:latest-386
           fi

.github/workflows/container_release1.yml

@@ -0,0 +1,152 @@
+name: "docker: build release containers for normal volume"
+
+# DISABLED: Merged into container_release_unified.yml
+on:
+  workflow_dispatch:
+    inputs:
+      force_run:
+        description: 'This workflow is disabled. Use container_release_unified.yml instead'
+        required: true
+        default: 'disabled'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform: [amd64, arm64, arm, 386]
+        include:
+          - platform: amd64
+            qemu: false
+          - platform: arm64
+            qemu: true
+          - platform: arm
+            qemu: true
+          - platform: 386
+            qemu: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Free Disk Space
+        run: |
+          echo "Available disk space before cleanup:"
+          df -h
+          # Remove pre-installed tools
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
+          # Clean package managers
+          sudo apt-get clean
+          sudo rm -rf /var/lib/apt/lists/*
+          # Clean Docker aggressively
+          sudo docker system prune -af --volumes
+          # Clean Go cache if it exists
+          [ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
+          [ -d /go/pkg ] && rm -rf /go/pkg || true
+          echo "Available disk space after cleanup:"
+          df -h
+      - name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag
+          flavor: latest=false
+      - name: Set up QEMU
+        if: matrix.qemu
+        uses: docker/setup-qemu-action@v3
+      - 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@v3
+        with:
+          buildkitd-config: /tmp/buildkitd.toml
+      - name: Login to Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Build ${{ matrix.platform }}
+        uses: docker/build-push-action@v6
+        env:
+          DOCKER_BUILDKIT: 1
+        with:
+          context: ./docker
+          push: ${{ github.event_name != 'pull_request' }}
+          file: ./docker/Dockerfile.go_build
+          platforms: linux/${{ matrix.platform }}
+          tags: ${{ steps.docker_meta.outputs.tags }}-${{ matrix.platform }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: |
+            BUILDKIT_INLINE_CACHE=1
+            BRANCH=${{ github.sha }}
+      - name: Clean up build artifacts
+        if: always()
+        run: |
+          # Clean up Docker build cache and temporary files
+          sudo docker system prune -f
+          # Remove Go build cache
+          sudo rm -rf /tmp/go-build*
+
+  create-manifest:
+    runs-on: ubuntu-latest
+    needs: [build]
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag
+          flavor: latest=false
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Create and push manifest
+        run: |
+          # Function to retry command with exponential backoff
+          retry_with_backoff() {
+            local max_attempts=5
+            local timeout=1
+            local attempt=1
+            local exit_code=0
+            
+            while [ $attempt -le $max_attempts ]; do
+              if "$@"; then
+                return 0
+              else
+                exit_code=$?
+              fi
+              
+              if [ $attempt -lt $max_attempts ]; then
+                echo "Attempt $attempt failed. Retrying in ${timeout}s..." >&2
+                sleep $timeout
+                timeout=$((timeout * 2))
+              fi
+              
+              attempt=$((attempt + 1))
+            done
+            
+            echo "Command failed after $max_attempts attempts" >&2
+            return $exit_code
+          }
+          
+          # Create manifest with retry
+          retry_with_backoff docker buildx imagetools create -t ${{ steps.docker_meta.outputs.tags }} \
+            ${{ steps.docker_meta.outputs.tags }}-amd64 \
+            ${{ steps.docker_meta.outputs.tags }}-arm64 \
+            ${{ steps.docker_meta.outputs.tags }}-arm \
+            ${{ steps.docker_meta.outputs.tags }}-386

.github/workflows/container_release2.yml

@@ -0,0 +1,153 @@
+name: "docker: build release containers for large volume"
+
+# DISABLED: Merged into container_release_unified.yml
+on:
+  workflow_dispatch:
+    inputs:
+      force_run:
+        description: 'This workflow is disabled. Use container_release_unified.yml instead'
+        required: true
+        default: 'disabled'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform: [amd64, arm64, arm, 386]
+        include:
+          - platform: amd64
+            qemu: false
+          - platform: arm64
+            qemu: true
+          - platform: arm
+            qemu: true
+          - platform: 386
+            qemu: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Free Disk Space
+        run: |
+          echo "Available disk space before cleanup:"
+          df -h
+          # Remove pre-installed tools
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
+          # Clean package managers
+          sudo apt-get clean
+          sudo rm -rf /var/lib/apt/lists/*
+          # Clean Docker aggressively
+          sudo docker system prune -af --volumes
+          # Clean Go cache if it exists
+          [ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
+          [ -d /go/pkg ] && rm -rf /go/pkg || true
+          echo "Available disk space after cleanup:"
+          df -h
+      - name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag,suffix=_large_disk
+          flavor: latest=false
+      - name: Set up QEMU
+        if: matrix.qemu
+        uses: docker/setup-qemu-action@v3
+      - 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@v3
+        with:
+          buildkitd-config: /tmp/buildkitd.toml
+      - name: Login to Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Build ${{ matrix.platform }}
+        uses: docker/build-push-action@v6
+        env:
+          DOCKER_BUILDKIT: 1
+        with:
+          context: ./docker
+          push: ${{ github.event_name != 'pull_request' }}
+          file: ./docker/Dockerfile.go_build
+          build-args: |
+            TAGS=5BytesOffset
+            BUILDKIT_INLINE_CACHE=1
+            BRANCH=${{ github.sha }}
+          platforms: linux/${{ matrix.platform }}
+          tags: ${{ steps.docker_meta.outputs.tags }}-${{ matrix.platform }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+      - name: Clean up build artifacts
+        if: always()
+        run: |
+          # Clean up Docker build cache and temporary files
+          sudo docker system prune -f
+          # Remove Go build cache
+          sudo rm -rf /tmp/go-build*
+
+  create-manifest:
+    runs-on: ubuntu-latest
+    needs: [build]
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+      - name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag,suffix=_large_disk
+          flavor: latest=false
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Create and push manifest
+        run: |
+          # Function to retry command with exponential backoff
+          retry_with_backoff() {
+            local max_attempts=5
+            local timeout=1
+            local attempt=1
+            local exit_code=0
+            
+            while [ $attempt -le $max_attempts ]; do
+              if "$@"; then
+                return 0
+              else
+                exit_code=$?
+              fi
+              
+              if [ $attempt -lt $max_attempts ]; then
+                echo "Attempt $attempt failed. Retrying in ${timeout}s..." >&2
+                sleep $timeout
+                timeout=$((timeout * 2))
+              fi
+              
+              attempt=$((attempt + 1))
+            done
+            
+            echo "Command failed after $max_attempts attempts" >&2
+            return $exit_code
+          }
+          
+          # Create manifest with retry
+          retry_with_backoff docker buildx imagetools create -t ${{ steps.docker_meta.outputs.tags }} \
+            ${{ steps.docker_meta.outputs.tags }}-amd64 \
+            ${{ steps.docker_meta.outputs.tags }}-arm64 \
+            ${{ steps.docker_meta.outputs.tags }}-arm \
+            ${{ steps.docker_meta.outputs.tags }}-386

.github/workflows/container_release3.yml

@@ -0,0 +1,73 @@
+name: "docker: build release containers for rocksdb"
+
+# DISABLED: Merged into container_release_unified.yml
+on:
+  workflow_dispatch:
+    inputs:
+      force_run:
+        description: 'This workflow is disabled. Use container_release_unified.yml instead'
+        required: true
+        default: 'disabled'
+
+permissions:
+  contents: read
+
+jobs:
+
+  build-large-release-container_rocksdb:
+    runs-on: [ubuntu-latest]
+
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v6
+      -
+        name: Free Disk Space
+        run: |
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc
+          sudo docker system prune -af
+      -
+        name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag,suffix=_large_disk_rocksdb
+          flavor: latest=false
+          labels: |
+            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: 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@v3
+        with:
+          buildkitd-config: /tmp/buildkitd.toml
+      -
+        name: Login to Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      -
+        name: Build
+        uses: docker/build-push-action@v6
+        with:
+          context: ./docker
+          push: ${{ github.event_name != 'pull_request' }}
+          file: ./docker/Dockerfile.rocksdb_large
+          build-args: |
+            BRANCH=${{ github.sha }}
+          platforms: linux/amd64
+          tags: ${{ steps.docker_meta.outputs.tags }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/container_release4.yml

@@ -0,0 +1,72 @@
+name: "docker: build release containers for all tags"
+
+# DISABLED: Merged into container_release_unified.yml
+on:
+  workflow_dispatch:
+    inputs:
+      force_run:
+        description: 'This workflow is disabled. Use container_release_unified.yml instead'
+        required: true
+        default: 'disabled'
+
+permissions:
+  contents: read
+
+jobs:
+  build-default-release-container:
+    runs-on: [ubuntu-latest]
+
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v6
+      -
+        name: Free Disk Space
+        run: |
+          echo "Before cleanup:"
+          df -h
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /opt/hostedtoolcache/CodeQL
+          sudo docker system prune -af
+          echo "After cleanup:"
+          df -h
+      -
+        name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            chrislusf/seaweedfs
+          tags: |
+            type=ref,event=tag,suffix=_full
+          flavor: |
+            latest=false
+          labels: |
+            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 Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      -
+        name: Login to Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      -
+        name: Build
+        uses: docker/build-push-action@v6
+        with:
+          context: ./docker
+          push: ${{ github.event_name != 'pull_request' }}
+          file: ./docker/Dockerfile.go_build
+          build-args: TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
+          platforms: linux/amd64
+          tags: ${{ steps.docker_meta.outputs.tags }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/container_release5.yml

@@ -0,0 +1,62 @@
+name: "docker: build release containers for all tags and large volume"
+
+# DISABLED: Merged into container_release_unified.yml
+on:
+  workflow_dispatch:
+    inputs:
+      force_run:
+        description: 'This workflow is disabled. Use container_release_unified.yml instead'
+        required: true
+        default: 'disabled'
+
+permissions:
+  contents: read
+
+jobs:
+  build-default-release-container:
+    runs-on: [ubuntu-latest]
+
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v6
+      -
+        name: Free Disk Space
+        run: |
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc
+          sudo docker system prune -af
+      -
+        name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: chrislusf/seaweedfs
+          tags: type=ref,event=tag,suffix=_large_disk_full
+          flavor: latest=false
+          labels: |
+            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 Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      -
+        name: Login to Docker Hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      -
+        name: Build
+        uses: docker/build-push-action@v6
+        with:
+          context: ./docker
+          push: ${{ github.event_name != 'pull_request' }}
+          file: ./docker/Dockerfile.go_build
+          build-args: TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
+          platforms: linux/amd64
+          tags: ${{ steps.docker_meta.outputs.tags }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/container_release_unified.yml

@@ -4,35 +4,11 @@ on:
   push:
     tags:
       - '*'
-  workflow_dispatch:
-    inputs:
-      variant:
-        description: 'Variant to build manually'
-        required: true
-        type: choice
-        default: all
-        options:
-          - all
-          - normal
-          - large_disk
-          - full
-          - large_disk_full
-          - rocksdb
-      release_tag:
-        description: 'Release tag to publish (e.g. 3.93)'
-        required: true
-        default: ''
-      rocksdb_version:
-        description: 'RocksDB git tag to use when variant=rocksdb'
-        required: false
-        default: 'v10.10.1'
+  workflow_dispatch: {}
 
 permissions:
   contents: read
 
-env:
-  RELEASE_TAG: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.release_tag || github.ref_name }}
-
 # Limit concurrent builds to avoid rate limits
 concurrency:
   group: release-${{ github.ref }}
@@ -83,11 +59,9 @@ jobs:
             
     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: Free Disk Space
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         run: |
           echo "Available disk space before cleanup:"
           df -h
@@ -101,14 +75,13 @@ jobs:
           df -h
           
       - name: Docker meta
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         id: docker_meta
         uses: docker/metadata-action@v5
         with:
           images: |
             chrislusf/seaweedfs
             ghcr.io/chrislusf/seaweedfs
-          tags: type=raw,value=${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
+          tags: type=ref,event=tag,suffix=${{ matrix.tag_suffix }}
           flavor: latest=false
           labels: |
             org.opencontainers.image.title=seaweedfs
@@ -116,11 +89,10 @@ jobs:
             org.opencontainers.image.vendor=Chris Lu
             
       - name: Set up QEMU
-        if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && contains(matrix.platforms, 'arm')
+        if: contains(matrix.platforms, 'arm')
         uses: docker/setup-qemu-action@v3
         
       - name: Create BuildKit config
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         run: |
           cat > /tmp/buildkitd.toml <<EOF
           [registry."docker.io"]
@@ -128,20 +100,19 @@ jobs:
           EOF
           
       - name: Set up Docker Buildx
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         uses: docker/setup-buildx-action@v3
         with:
           buildkitd-config: /tmp/buildkitd.toml
           
       - 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'
+        if: github.event_name != 'pull_request'
         uses: docker/login-action@v3
         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'
+        if: github.event_name != 'pull_request'
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
@@ -149,7 +120,6 @@ jobs:
           password: ${{ secrets.GHCR_TOKEN }}
           
       - name: Build and push ${{ matrix.variant }}
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         uses: docker/build-push-action@v6
         env:
           DOCKER_BUILDKIT: 1
@@ -160,7 +130,7 @@ jobs:
           platforms: ${{ matrix.platforms }}
           # Push to GHCR to avoid Docker Hub rate limits on pulls
           tags: |
-            ghcr.io/chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
+            ghcr.io/chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }}
           labels: ${{ steps.docker_meta.outputs.labels }}
           cache-from: type=gha,scope=${{ matrix.variant }}
           cache-to: type=gha,mode=max,scope=${{ matrix.variant }}
@@ -168,10 +138,9 @@ jobs:
             ${{ matrix.build_args }}
             BUILDKIT_INLINE_CACHE=1
             BRANCH=${{ github.sha }}
-            ${{ matrix.variant == 'rocksdb' && format('ROCKSDB_VERSION={0}', github.event.inputs.rocksdb_version || 'v10.10.1') || '' }}
             
       - name: Clean up build artifacts
-        if: always() && (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant)
+        if: always()
         run: |
           sudo docker system prune -f
           sudo rm -rf /tmp/go-build*
@@ -197,14 +166,12 @@ 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@v3
         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@v3
         with:
           registry: ghcr.io
@@ -212,7 +179,6 @@ jobs:
           password: ${{ secrets.GHCR_TOKEN }}
           
       - name: Install crane
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         run: |
           cd $(mktemp -d)
           curl -sL "https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz" | tar xz
@@ -220,7 +186,6 @@ jobs:
           crane version
           
       - name: Copy ${{ matrix.variant }} from GHCR to Docker Hub
-        if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         run: |
           # Function to retry with exponential backoff
           retry_with_backoff() {
@@ -253,15 +218,14 @@ jobs:
           # This is much more efficient than pulling/pushing individual arch images
           echo "Copying ${{ matrix.variant }} from GHCR to Docker Hub..."
           retry_with_backoff crane copy \
-            ghcr.io/chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }} \
-            chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
+            ghcr.io/chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }} \
+            chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }}
           
           echo "✓ Successfully copied ${{ matrix.variant }} to Docker Hub"
 
   helm-release:
     runs-on: ubuntu-latest
     needs: [copy-to-dockerhub]
-    if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
     permissions:
       contents: write
       pages: write
@@ -275,3 +239,7 @@ jobs:
           target_dir: helm
           branch: gh-pages
           helm_version: "3.18.4"
+
+
+
+

.github/workflows/container_rocksdb_version.yml

@@ -4,9 +4,9 @@ on:
   workflow_dispatch:
     inputs:
       rocksdb_version:
-        description: 'RocksDB git tag or branch to build (e.g. v10.10.1)'
+        description: 'RocksDB git tag or branch to build (e.g. v10.5.1)'
         required: true
-        default: 'v10.10.1'
+        default: 'v10.5.1'
       seaweedfs_ref:
         description: 'SeaweedFS git tag, branch, or commit to build'
         required: true

.github/workflows/depsreview.yml

@@ -11,4 +11,4 @@ jobs:
       - name: 'Checkout Repository'
         uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8
       - name: 'Dependency Review'
-        uses: actions/dependency-review-action@05fe4576374b728f0c523d6a13d64c25081e0803
+        uses: actions/dependency-review-action@3c4e3dcb1aa7874d2c16be7d79418e9b7efd6261

.github/workflows/go.yml

@@ -15,20 +15,24 @@ permissions:
 
 jobs:
 
-  vet:
-    name: Go Vet
+  build:
+    name: Build
     runs-on: ubuntu-latest
     steps:
+
     - name: Set up Go 1.x
       uses: actions/setup-go@a5f9b05d2d216f63e13859e0d847461041025775 # v2
       with:
         go-version: ^1.13
       id: go
+
     - name: Check out code into the Go module directory
       uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v2
+
     - name: Get dependencies
       run: |
         cd weed; go get -v -t -d ./...
+
     - name: Go Vet (excluding protobuf lock copying)
       run: |
         cd weed
@@ -38,30 +42,8 @@ jobs:
         # Fail only if there are actual vet errors (not counting the filtered lock warnings)
         if grep -q "vet:" vet-output.txt; then exit 1; fi
 
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    steps:
-    - name: Set up Go 1.x
-      uses: actions/setup-go@a5f9b05d2d216f63e13859e0d847461041025775 # v2
-      with:
-        go-version: ^1.13
-      id: go
-    - name: Check out code into the Go module directory
-      uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v2
     - name: Build
       run: cd weed; go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v .
 
-  test:
-    name: Test
-    runs-on: ubuntu-latest
-    steps:
-    - name: Set up Go 1.x
-      uses: actions/setup-go@a5f9b05d2d216f63e13859e0d847461041025775 # v2
-      with:
-        go-version: ^1.13
-      id: go
-    - name: Check out code into the Go module directory
-      uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v2
     - name: Test
       run: cd weed; go test -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v ./...

.github/workflows/helm_ci.yml

@@ -27,7 +27,7 @@ jobs:
 
       - uses: actions/setup-python@v6
         with:
-          python-version: '3.10'
+          python-version: '3.9'
           check-latest: true
 
       - name: Set up chart-testing
@@ -119,7 +119,7 @@ jobs:
           echo "✅ All template rendering tests passed!"
 
       - name: Create kind cluster
-        uses: helm/kind-action@v1.14.0
+        uses: helm/kind-action@v1.13.0
 
       - name: Run chart-testing (install)
         run: ct install --target-branch ${{ github.event.repository.default_branch }} --all --chart-dirs k8s/charts

.github/workflows/helm_manual_release.yml

@@ -1,25 +0,0 @@
-name: "helm: manual release"
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  pages: write
-
-jobs:
-  helm-release:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Publish Helm charts
-        uses: stefanprodan/helm-gh-pages@v1.7.0
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          charts_dir: k8s/charts
-          target_dir: helm
-          branch: gh-pages
-          helm_version: "3.18.4"

.github/workflows/java_integration_tests.yml

@@ -111,7 +111,7 @@ jobs:
           
           # Wait for S3 API
           for i in {1..30}; do
-            if curl -s http://localhost:8333/healthz > /dev/null 2>&1; then
+            if curl -s http://localhost:8333/ > /dev/null 2>&1; then
               echo "✓ S3 API is ready"
               break
             fi

.github/workflows/plugin-workers.yml

@@ -1,39 +0,0 @@
-name: "Plugin Worker Integration Tests"
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
-
-permissions:
-  contents: read
-
-jobs:
-  plugin-worker:
-    name: "Plugin Worker: ${{ matrix.worker }}"
-    runs-on: ubuntu-22.04
-    timeout-minutes: 10
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - worker: erasure_coding
-            path: test/plugin_workers/erasure_coding
-          - worker: vacuum
-            path: test/plugin_workers/vacuum
-          - worker: volume_balance
-            path: test/plugin_workers/volume_balance
-
-    steps:
-      - name: Set up Go 1.x
-        uses: actions/setup-go@v6
-        with:
-          go-version: ^1.26
-        id: go
-
-      - name: Check out code into the Go module directory
-        uses: actions/checkout@v6
-
-      - name: Run plugin worker tests
-        run: go test -v ./${{ matrix.path }}

.github/workflows/s3-example-integration-tests.yml

@@ -39,14 +39,6 @@ jobs:
           echo "=== Running S3 Integration Tests ==="
           go test -v -timeout=60s -run TestS3Integration ./...
 
-      - name: Run S3 DeleteBucketNotEmpty Tests
-        timeout-minutes: 15
-        working-directory: test/s3/normal
-        run: |
-          set -x
-          echo "=== Running S3 DeleteBucketNotEmpty Tests ==="
-          go test -v -timeout=60s -run TestS3DeleteBucketNotEmpty ./...
-
       - name: Run IAM Integration Tests
         timeout-minutes: 15
         working-directory: test/s3/normal

.github/workflows/s3-go-tests.yml

@@ -461,8 +461,6 @@ jobs:
           export S3_ENDPOINT="http://localhost:8006"
           export S3_ACCESS_KEY="0555b35654ad1656d804"
           export S3_SECRET_KEY="h7GhxuBLTrlhVUyxSPUKUV8r/2EI4ngqJxD7iBdBYLhwluN30JaT3Q=="
-          export AWS_ACCESS_KEY_ID="$S3_ACCESS_KEY"
-          export AWS_SECRET_ACCESS_KEY="$S3_SECRET_KEY"
           
           # Run the specific test that is equivalent to AWS S3 tagging behavior
           make test-with-server || {

.github/workflows/s3-keycloak-tests.yml

@@ -97,7 +97,7 @@ jobs:
           # Verify service accessibility
           echo "=== Verifying Service Accessibility ==="
           curl -f http://localhost:8080/realms/master
-          curl -s http://localhost:8333/healthz
+          curl -s http://localhost:8333
           echo "✅ SeaweedFS S3 API is responding (IAM-protected endpoint)"
           
           # Run Keycloak-specific tests

.github/workflows/s3-proxy-signature-tests.yml

@@ -1,122 +0,0 @@
-name: "S3 Proxy Signature Tests"
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
-
-concurrency:
-  group: ${{ github.head_ref || github.ref }}/s3-proxy-signature-tests
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  proxy-signature-tests:
-    name: S3 Proxy Signature Verification Tests
-    runs-on: ubuntu-22.04
-    timeout-minutes: 15
-    steps:
-      - name: Check out code into the Go module directory
-        uses: actions/checkout@v6
-
-      - name: Set up Go 1.x
-        uses: actions/setup-go@v6
-        with:
-          go-version-file: 'go.mod'
-        id: go
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build SeaweedFS binary for Linux
-        run: |
-          set -x
-          CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -buildvcs=false -v -o test/s3/proxy_signature/weed ./weed
-
-      - name: Run S3 Proxy Signature Tests
-        timeout-minutes: 10
-        working-directory: test/s3/proxy_signature
-        run: |
-          set -x
-          echo "Starting Docker Compose services..."
-          docker compose up -d --build
-          
-          # Check if containers are running
-          echo "Checking container status..."
-          docker compose ps
-          
-          # Wait for services to be ready
-          echo "Waiting for nginx proxy to be ready..."
-          PROXY_READY=0
-          for i in $(seq 1 30); do
-            if curl -s http://localhost:9000/ > /dev/null 2>&1; then
-              echo "Proxy is ready"
-              PROXY_READY=1
-              break
-            fi
-            echo "Waiting for proxy... ($i/30)"
-            sleep 1
-          done
-          if [ $PROXY_READY -eq 0 ]; then
-            echo "ERROR: Proxy failed to become ready after 30 seconds"
-            echo "Docker compose logs:"
-            docker compose logs --no-color || true
-            exit 1
-          fi
-          
-          # Wait for SeaweedFS to be ready
-          echo "Waiting for SeaweedFS S3 gateway to be ready via proxy..."
-          S3_READY=0
-          for i in $(seq 1 30); do
-            # Check logs first for startup message (weed mini says "S3 service is ready")
-            if docker compose logs seaweedfs 2>&1 | grep -qE "S3 (gateway|service).*(started|ready)"; then
-              echo "SeaweedFS S3 gateway is ready"
-              S3_READY=1
-              break
-            fi
-            # Fallback: check headers via proxy (which is already ready)
-            if curl -s -I http://localhost:9000/ | grep -qi "SeaweedFS"; then
-              echo "SeaweedFS S3 gateway is responding via proxy"
-              S3_READY=1
-              break
-            fi
-            echo "Waiting for S3 gateway... ($i/30)"
-            sleep 1
-          done
-          if [ $S3_READY -eq 0 ]; then
-            echo "ERROR: SeaweedFS S3 gateway failed to become ready after 30 seconds"
-            echo "Latest seaweedfs logs:"
-            docker compose logs --no-color --tail 20 seaweedfs || true
-            exit 1
-          fi
-          
-          # Run the test script inside AWS CLI container
-          echo "Running test script..."
-          docker run --rm --network host \
-            --entrypoint bash \
-            amazon/aws-cli:latest \
-            -c "$(cat test.sh)"
-          
-          TEST_RESULT=$?
-          
-          # Cleanup
-          docker compose down
-          
-          exit $TEST_RESULT
-
-      - name: Cleanup on failure
-        if: failure()
-        working-directory: test/s3/proxy_signature
-        run: |
-          echo "Cleaning up Docker containers..."
-          ls -al weed || true
-          ldd weed || true
-          echo "Docker compose logs:"
-          docker compose logs --no-color || true
-          echo "Container status before cleanup:"
-          docker ps -a
-          echo "Stopping services..."
-          docker compose down || true

.github/workflows/s3-spark-tests.yml

@@ -1,80 +0,0 @@
-name: "S3 Spark Integration Tests"
-
-on:
-  pull_request:
-    paths:
-      - 'weed/s3api/**'
-      - 'test/s3/spark/**'
-      - 'test/s3tables/testutil/**'
-      - '.github/workflows/s3-spark-tests.yml'
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.head_ref }}/s3-spark-tests
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-jobs:
-  s3-spark-issue-repro-tests:
-    name: S3 Spark Issue Reproduction Tests
-    runs-on: ubuntu-22.04
-    timeout-minutes: 45
-
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Set up Go
-        uses: actions/setup-go@v6
-        with:
-          go-version-file: 'go.mod'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Pre-pull Spark image
-        run: docker pull apache/spark:3.5.8
-
-      - name: Run S3 Spark integration tests
-        working-directory: test/s3/spark
-        timeout-minutes: 35
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting S3 Spark Integration Tests ==="
-
-          go test -v -timeout 30m . 2>&1 | tee test-output.log || {
-            echo "S3 Spark integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3/spark
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker|spark)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: s3-spark-test-logs
-          path: test/s3/spark/test-output.log
-          retention-days: 3

.github/workflows/s3-tables-tests.yml

@@ -1,625 +0,0 @@
-name: "S3 Tables Integration Tests"
-
-on:
-  pull_request:
-  
-concurrency:
-  group: ${{ github.head_ref }}/s3-tables-tests
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-
-jobs:
-  s3-tables-tests:
-    name: S3 Tables 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'
-        id: go
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run S3 Tables Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/table-buckets
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting S3 Tables Tests ==="
-          
-          # Run S3 Tables integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "S3 Tables integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/table-buckets
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: s3-tables-test-logs
-          path: test/s3tables/table-buckets/test-output.log
-          retention-days: 3
-
-  iceberg-catalog-tests:
-    name: Iceberg Catalog 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'
-        id: go
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Run Iceberg Catalog Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/catalog
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting Iceberg Catalog Tests ==="
-          
-          # Run Iceberg catalog integration tests using Makefile (handles build)
-          make test 2>&1 | tee test-output.log || {
-            echo "Iceberg catalog integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/catalog
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: iceberg-catalog-test-logs
-          path: test/s3tables/catalog/test-output.log
-          retention-days: 3
-
-  trino-iceberg-catalog-tests:
-    name: Trino Iceberg Catalog 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'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Pre-pull Trino image
-        run: docker pull trinodb/trino:479
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run Trino Iceberg Catalog Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/catalog_trino
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting Trino Iceberg Catalog Tests ==="
-          
-          # Run Trino + Iceberg catalog integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "Trino Iceberg catalog integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/catalog_trino
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: trino-iceberg-catalog-test-logs
-          path: test/s3tables/catalog_trino/test-output.log
-          retention-days: 3
-
-  spark-iceberg-catalog-tests:
-    name: Spark Iceberg Catalog 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'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Pre-pull Spark image
-        run: docker pull apache/spark:3.5.1
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run Spark Iceberg Catalog Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/catalog_spark
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting Spark Iceberg Catalog Tests ==="
-          
-          # Run Spark + Iceberg catalog integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "Spark Iceberg catalog integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/catalog_spark
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: spark-iceberg-catalog-test-logs
-          path: test/s3tables/catalog_spark/test-output.log
-          retention-days: 3
-
-  risingwave-catalog-tests:
-    name: RisingWave Catalog 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'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Pre-pull RisingWave image
-        run: |
-          docker pull risingwavelabs/risingwave:v2.5.0
-          docker pull postgres:16-alpine
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run RisingWave Catalog Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/catalog_risingwave
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting RisingWave Catalog Tests ==="
-          
-          # Run RisingWave catalog integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "RisingWave catalog integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/catalog_risingwave
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: risingwave-catalog-test-logs
-          path: test/s3tables/catalog_risingwave/test-output.log
-          retention-days: 3
-
-  sts-integration-tests:
-    name: STS 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'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Pre-pull Python image
-        run: docker pull python:3
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run STS Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/sts_integration
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting STS Integration Tests ==="
-          
-          # Run STS integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "STS integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/sts_integration
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: sts-integration-test-logs
-          path: test/s3tables/sts_integration/test-output.log
-          retention-days: 3
-
-  lakekeeper-integration-tests:
-    name: Lakekeeper 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'
-        id: go
-
-      - name: Set up Docker
-        uses: docker/setup-buildx-action@v3
-
-      - name: Pre-pull Python image
-        run: docker pull python:3
-        
-      - name: Pre-pull LocalStack image (if needed)
-        run: docker pull localstack/localstack:latest || true
-
-      - name: Run go mod tidy
-        run: go mod tidy
-
-      - name: Install SeaweedFS
-        run: |
-          go install -buildvcs=false ./weed
-
-      - name: Run Lakekeeper Integration Tests
-        timeout-minutes: 25
-        working-directory: test/s3tables/lakekeeper
-        run: |
-          set -x
-          set -o pipefail
-          echo "=== System Information ==="
-          uname -a
-          free -h
-          df -h
-          echo "=== Starting Lakekeeper Integration Tests ==="
-          
-          # Run Lakekeeper integration tests
-          go test -v -timeout 20m . 2>&1 | tee test-output.log || {
-            echo "Lakekeeper integration tests failed"
-            exit 1
-          }
-
-      - name: Show test output on failure
-        if: failure()
-        working-directory: test/s3tables/lakekeeper
-        run: |
-          echo "=== Test Output ==="
-          if [ -f test-output.log ]; then
-            tail -200 test-output.log
-          fi
-          
-          echo "=== Process information ==="
-          ps aux | grep -E "(weed|test|docker)" || true
-
-      - name: Upload test logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: lakekeeper-integration-test-logs
-          path: test/s3tables/lakekeeper/test-output.log
-          retention-days: 3
-
-  s3-tables-build-verification:
-    name: S3 Tables Build Verification
-    runs-on: ubuntu-22.04
-    timeout-minutes: 15
-    
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Set up Go
-        uses: actions/setup-go@v6
-        with:
-          go-version-file: 'go.mod'
-        id: go
-
-      - name: Verify S3 Tables Package Builds
-        run: |
-          set -x
-          echo "=== Building S3 Tables package ==="
-          go build ./weed/s3api/s3tables || {
-            echo "S3 Tables package build failed"
-            exit 1
-          }
-          echo "S3 Tables package built successfully"
-
-      - name: Verify S3 API Integration Builds
-        run: |
-          set -x
-          echo "=== Building S3 API with S3 Tables integration ==="
-          go build ./weed/s3api || {
-            echo "S3 API build with S3 Tables failed"
-            exit 1
-          }
-          echo "S3 API with S3 Tables integration built successfully"
-
-      - name: Run Go Tests for S3 Tables Package
-        run: |
-          set -x
-          echo "=== Running Go unit tests for S3 Tables ==="
-          go test -v -race -timeout 5m ./weed/s3api/s3tables/... || {
-            echo "S3 Tables unit tests failed"
-            exit 1
-          }
-          echo "S3 Tables unit tests passed"
-
-      - name: Verify Iceberg Package Builds
-        run: |
-          set -x
-          echo "=== Building Iceberg package ==="
-          go build ./weed/s3api/iceberg || {
-            echo "Iceberg package build failed"
-            exit 1
-          }
-          echo "Iceberg package built successfully"
-
-      - name: Run Go Tests for Iceberg Package
-        run: |
-          set -x
-          echo "=== Running Go unit tests for Iceberg ==="
-          go test -v -race -timeout 5m ./weed/s3api/iceberg/... || {
-            echo "Iceberg unit tests failed"
-            exit 1
-          }
-          echo "Iceberg unit tests passed"
-
-  s3-tables-fmt-check:
-    name: S3 Tables Format Check
-    runs-on: ubuntu-22.04
-    timeout-minutes: 10
-    
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Set up Go
-        uses: actions/setup-go@v6
-        with:
-          go-version-file: 'go.mod'
-        id: go
-
-      - name: Check Go Format
-        run: |
-          set -x
-          echo "=== Checking S3 Tables Go format ==="
-          unformatted=$(gofmt -l ./weed/s3api/s3tables)
-          if [ -n "$unformatted" ]; then
-            echo "Go format check failed - files need formatting"
-            echo "$unformatted"
-            exit 1
-          fi
-          echo "All S3 Tables files are properly formatted"
-
-      - name: Check S3 Tables Test Format
-        run: |
-          set -x
-          echo "=== Checking S3 Tables test format ==="
-          unformatted=$(gofmt -l ./test/s3tables)
-          if [ -n "$unformatted" ]; then
-            echo "Go format check failed for tests"
-            echo "$unformatted"
-            exit 1
-          fi
-          echo "All S3 Tables test files are properly formatted"
-
-      - name: Check Iceberg Format
-        run: |
-          set -x
-          echo "=== Checking Iceberg Go format ==="
-          unformatted=$(gofmt -l ./weed/s3api/iceberg)
-          if [ -n "$unformatted" ]; then
-            echo "Go format check failed for Iceberg - files need formatting"
-            echo "$unformatted"
-            exit 1
-          fi
-          echo "All Iceberg files are properly formatted"
-
-  s3-tables-vet:
-    name: S3 Tables Go Vet Check
-    runs-on: ubuntu-22.04
-    timeout-minutes: 10
-    
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Set up Go
-        uses: actions/setup-go@v6
-        with:
-          go-version-file: 'go.mod'
-        id: go
-
-      - name: Run Go Vet
-        run: |
-          set -x
-          echo "=== Running go vet on S3 Tables package ==="
-          go vet ./weed/s3api/s3tables/... || {
-            echo "go vet check failed"
-            exit 1
-          }
-          echo "go vet checks passed"
-
-      - name: Run Go Vet on Tests
-        run: |
-          set -x
-          echo "=== Running go vet on S3 Tables tests ==="
-          go vet ./test/s3tables/... || {
-            echo "go vet check failed for tests"
-            exit 1
-          }
-          echo "go vet checks passed for tests"
-
-      - name: Run Go Vet on Iceberg
-        run: |
-          set -x
-          echo "=== Running go vet on Iceberg package ==="
-          go vet ./weed/s3api/iceberg/... || {
-            echo "go vet check failed for Iceberg"
-            exit 1
-          }
-          echo "go vet checks passed for Iceberg"

.github/workflows/test-s3-over-https-using-awscli.yml

@@ -35,7 +35,7 @@ jobs:
           set -e
           mkdir -p /tmp/data
           ./weed -v=3 server -s3 -dir=/tmp/data -s3.config=../docker/compose/s3.json -master.peers=none > weed.log 2>&1 &
-          until curl -s http://localhost:8333/healthz > /dev/null; do sleep 1; done
+          until curl -s http://localhost:8333/ > /dev/null; do sleep 1; done
 
       - name: Setup Caddy
         run: |
@@ -54,7 +54,7 @@ jobs:
       - name: Start Caddy
         run: |
           ./caddy start
-          until curl -fsS --insecure https://localhost:8443/healthz > /dev/null; do sleep 1; done
+          until curl -fsS --insecure https://localhost:8443 > /dev/null; do sleep 1; done
 
       - name: Create Bucket
         run: |

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

@@ -1,122 +0,0 @@
-name: "Volume Server Integration Tests"
-
-on:
-  pull_request:
-    branches: [ master ]
-    paths:
-      - 'test/volume_server/**'
-      - 'weed/server/**'
-      - 'weed/storage/**'
-      - 'weed/pb/volume_server.proto'
-      - 'weed/pb/volume_server_pb/**'
-      - '.github/workflows/volume-server-integration-tests.yml'
-  push:
-    branches: [ master, main ]
-    paths:
-      - 'test/volume_server/**'
-      - 'weed/server/**'
-      - 'weed/storage/**'
-      - 'weed/pb/volume_server.proto'
-      - 'weed/pb/volume_server_pb/**'
-      - '.github/workflows/volume-server-integration-tests.yml'
-
-concurrency:
-  group: ${{ github.head_ref || github.ref }}/volume-server-integration-tests
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-env:
-  GO_VERSION: '1.24'
-  TEST_TIMEOUT: '30m'
-
-jobs:
-  volume-server-integration-tests:
-    name: Volume Server Integration Tests (${{ matrix.test-type }} - Shard ${{ matrix.shard }})
-    runs-on: ubuntu-22.04
-    timeout-minutes: 45
-    strategy:
-      fail-fast: false
-      matrix:
-        test-type: [grpc, http]
-        shard: [1, 2, 3]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v6
-
-      - name: Set up Go ${{ env.GO_VERSION }}
-        uses: actions/setup-go@v6
-        with:
-          go-version: ${{ env.GO_VERSION }}
-
-      - name: Build SeaweedFS binary
-        run: |
-          cd weed
-          go build -o weed .
-          chmod +x weed
-          ./weed version
-
-      - name: Run volume server integration tests
-        env:
-          WEED_BINARY: ${{ github.workspace }}/weed/weed
-        run: |
-          if [ "${{ matrix.test-type }}" == "grpc" ]; then
-            if [ "${{ matrix.shard }}" == "1" ]; then
-              TEST_PATTERN="^Test[A-H]"
-            elif [ "${{ matrix.shard }}" == "2" ]; then
-              TEST_PATTERN="^Test[I-S]"
-            else
-              TEST_PATTERN="^Test[T-Z]"
-            fi
-          else
-            if [ "${{ matrix.shard }}" == "1" ]; then
-              TEST_PATTERN="^Test[A-G]"
-            elif [ "${{ matrix.shard }}" == "2" ]; then
-              TEST_PATTERN="^Test[H-R]"
-            else
-              TEST_PATTERN="^Test[S-Z]"
-            fi
-          fi
-          echo "Running volume server integration tests for ${{ matrix.test-type }} (Shard ${{ matrix.shard }}, pattern: ${TEST_PATTERN})..."
-          go test -v -count=1 -timeout=${{ env.TEST_TIMEOUT }} ./test/volume_server/${{ matrix.test-type }}/... -run "${TEST_PATTERN}"
-
-      - name: Collect logs on failure
-        if: failure()
-        run: |
-          mkdir -p /tmp/volume-server-it-logs
-          find /tmp -maxdepth 1 -type d -name "seaweedfs_volume_server_it_*" -print -exec cp -r {} /tmp/volume-server-it-logs/ \; || true
-
-      - name: Archive logs on failure
-        if: failure()
-        uses: actions/upload-artifact@v6
-        with:
-          name: volume-server-integration-test-logs
-          path: /tmp/volume-server-it-logs/
-          if-no-files-found: warn
-          retention-days: 7
-
-      - name: Test summary
-        if: always()
-        run: |
-          if [ "${{ matrix.test-type }}" == "grpc" ]; then
-            if [ "${{ matrix.shard }}" == "1" ]; then
-              TEST_PATTERN="^Test[A-H]"
-            elif [ "${{ matrix.shard }}" == "2" ]; then
-              TEST_PATTERN="^Test[I-S]"
-            else
-              TEST_PATTERN="^Test[T-Z]"
-            fi
-          else
-            if [ "${{ matrix.shard }}" == "1" ]; then
-              TEST_PATTERN="^Test[A-G]"
-            elif [ "${{ matrix.shard }}" == "2" ]; then
-              TEST_PATTERN="^Test[H-R]"
-            else
-              TEST_PATTERN="^Test[S-Z]"
-            fi
-          fi
-          echo "## Volume Server Integration Test Summary (${{ matrix.test-type }} - Shard ${{ matrix.shard }})" >> "$GITHUB_STEP_SUMMARY"
-          echo "- Suite: test/volume_server/${{ matrix.test-type }} (Pattern: ${TEST_PATTERN})" >> "$GITHUB_STEP_SUMMARY"
-          echo "- Command: go test -v -count=1 -timeout=${{ env.TEST_TIMEOUT }} ./test/volume_server/${{ matrix.test-type }}/... -run \"${TEST_PATTERN}\"" >> "$GITHUB_STEP_SUMMARY"

Makefile

@@ -1,4 +1,4 @@
-.PHONY: test admin-generate admin-build admin-clean admin-dev admin-run admin-test admin-fmt admin-help weed-commands
+.PHONY: test admin-generate admin-build admin-clean admin-dev admin-run admin-test admin-fmt admin-help
 
 BINARY = weed
 ADMIN_DIR = weed/admin
@@ -11,9 +11,6 @@ all: install
 install: admin-generate
 	cd weed; go install
 
-weed-commands:
-	cd weed && $(MAKE) weed-db weed-sql
-
 warp_install:
 	go install github.com/minio/warp@v0.7.6
 
@@ -43,7 +40,7 @@ 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..."

cmd/weed-db/main.go

@@ -1,7 +0,0 @@
-package main
-
-import "os"
-
-func main() {
-	os.Exit(Run(os.Args[1:]))
-}

cmd/weed-sql/main.go

@@ -1,7 +0,0 @@
-package main
-
-import "os"
-
-func main() {
-	os.Exit(Run(os.Args[1:]))
-}

docker/Dockerfile.local

@@ -4,6 +4,7 @@ COPY  ./weed /usr/bin/weed
 RUN chmod +x /usr/bin/weed && ls -la /usr/bin/weed
 RUN mkdir -p /etc/seaweedfs
 COPY ./filer.toml /etc/seaweedfs/filer.toml
+COPY ./security.toml.example /etc/seaweedfs/security.toml.example
 COPY ./entrypoint.sh /entrypoint.sh
 
 # Install dependencies and create non-root user

docker/Dockerfile.rocksdb_dev_env

@@ -3,7 +3,7 @@ FROM golang:1.24 AS builder
 RUN apt-get update
 RUN apt-get install -y build-essential libsnappy-dev zlib1g-dev libbz2-dev libgflags-dev liblz4-dev libzstd-dev
 
-ARG ROCKSDB_VERSION=v10.10.1
+ARG ROCKSDB_VERSION=v10.5.1
 ENV ROCKSDB_VERSION=${ROCKSDB_VERSION}
 
 # build RocksDB

docker/Dockerfile.rocksdb_large

@@ -3,7 +3,7 @@ FROM golang:1.24 AS builder
 RUN apt-get update
 RUN apt-get install -y build-essential libsnappy-dev zlib1g-dev libbz2-dev libgflags-dev liblz4-dev libzstd-dev
 
-ARG ROCKSDB_VERSION=v10.10.1
+ARG ROCKSDB_VERSION=v10.5.1
 ENV ROCKSDB_VERSION=${ROCKSDB_VERSION}
 
 # build RocksDB

docker/compose/BLOCK_GETTING_STARTED.md

@@ -1,247 +0,0 @@
-# SeaweedFS Block Storage -- Getting Started
-
-Block storage exposes SeaweedFS volumes as `/dev/sdX` block devices via iSCSI.
-You can format them with ext4/xfs, mount them, and use them like any disk.
-
-## Prerequisites
-
-- Linux host with `open-iscsi` installed
-- Docker with compose plugin (`docker compose`)
-
-```bash
-# Install iSCSI initiator (Ubuntu/Debian)
-sudo apt-get install -y open-iscsi
-
-# Verify
-sudo systemctl start iscsid
-```
-
-## Quick Start (5 minutes)
-
-### 1. Build the image
-
-```bash
-# From the seaweedfs repo root
-GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -o docker/compose/weed ./weed
-cd docker
-docker build -f Dockerfile.local -t seaweedfs-block:local .
-```
-
-### 2. Start the cluster
-
-```bash
-cd docker/compose
-
-# Set HOST_IP to your machine's IP (for remote iSCSI clients)
-# Use 127.0.0.1 for local-only testing
-HOST_IP=127.0.0.1 docker compose -f local-block-compose.yml up -d
-```
-
-Wait ~5 seconds for the volume server to register with the master.
-
-### 3. Create a block volume
-
-```bash
-curl -s -X POST http://localhost:9333/block/volume \
-  -H "Content-Type: application/json" \
-  -d '{"name":"myvolume","size_bytes":1073741824}'
-```
-
-This creates a 1GB block volume, auto-assigns it as primary, and starts the
-iSCSI target. The response includes the IQN and iSCSI address.
-
-### 4. Connect via iSCSI
-
-```bash
-# Discover targets
-sudo iscsiadm -m discovery -t sendtargets -p 127.0.0.1:3260
-
-# Login
-sudo iscsiadm -m node -T iqn.2024-01.com.seaweedfs:vol.myvolume \
-  -p 127.0.0.1:3260 --login
-
-# Find the new device
-lsblk | grep sd
-```
-
-### 5. Format and mount
-
-```bash
-# Format with ext4
-sudo mkfs.ext4 /dev/sdX
-
-# Mount
-sudo mkdir -p /mnt/myvolume
-sudo mount /dev/sdX /mnt/myvolume
-
-# Use it like any filesystem
-echo "hello" | sudo tee /mnt/myvolume/test.txt
-```
-
-### 6. Cleanup
-
-```bash
-sudo umount /mnt/myvolume
-sudo iscsiadm -m node -T iqn.2024-01.com.seaweedfs:vol.myvolume \
-  -p 127.0.0.1:3260 --logout
-docker compose -f local-block-compose.yml down -v
-```
-
-## API Reference
-
-All endpoints are on the master server (default: port 9333).
-
-### Create volume
-
-```
-POST /block/volume
-Content-Type: application/json
-
-{
-  "name": "myvolume",
-  "size_bytes": 1073741824,
-  "disk_type": "ssd",
-  "replica_placement": "001",
-  "durability_mode": "best_effort"
-}
-```
-
-| Field | Required | Default | Description |
-|-------|----------|---------|-------------|
-| `name` | yes | -- | Volume name (alphanumeric + hyphens) |
-| `size_bytes` | yes | -- | Volume size in bytes |
-| `disk_type` | no | `""` | Disk type hint: `ssd`, `hdd` |
-| `replica_placement` | no | `000` | SeaweedFS placement: `000` (no replica), `001` (1 replica same rack) |
-| `durability_mode` | no | `best_effort` | `best_effort`, `sync_all`, `sync_quorum` |
-| `replica_factor` | no | `2` | Number of copies: 1, 2, or 3 |
-
-### List volumes
-
-```
-GET /block/volumes
-```
-
-Returns JSON array of all block volumes with status, role, epoch, IQN, etc.
-
-### Lookup volume
-
-```
-GET /block/volume/{name}
-```
-
-### Delete volume
-
-```
-DELETE /block/volume/{name}
-```
-
-### Assign role
-
-```
-POST /block/assign
-Content-Type: application/json
-
-{
-  "name": "myvolume",
-  "epoch": 2,
-  "role": "primary",
-  "lease_ttl_ms": 30000
-}
-```
-
-Roles: `primary`, `replica`, `stale`, `rebuilding`.
-
-### Cluster status
-
-```
-GET /block/status
-```
-
-Returns volume count, server count, failover stats, queue depth.
-
-## Remote Client Setup
-
-To connect from a remote machine (not the Docker host):
-
-1. Set `HOST_IP` to the Docker host's network-reachable IP:
-   ```bash
-   HOST_IP=192.168.1.100 docker compose -f local-block-compose.yml up -d
-   ```
-
-2. On the client machine:
-   ```bash
-   sudo iscsiadm -m discovery -t sendtargets -p 192.168.1.100:3260
-   sudo iscsiadm -m node -T iqn.2024-01.com.seaweedfs:vol.myvolume \
-     -p 192.168.1.100:3260 --login
-   ```
-
-## Volume Lifecycle
-
-```
-create  -->  primary (serving I/O via iSCSI)
-                |
-           unmount/remount OK (lease auto-renewed by master)
-                |
-         assign replica  -->  WAL shipping active
-                |
-          kill primary   -->  promote replica  -->  new primary
-                |
-          old primary    -->  rebuild from new primary
-```
-
-Key points:
-- **Lease renewal is automatic.** The master continuously renews the primary's
-  write lease via the heartbeat stream. Unmount/remount works without manual
-  intervention.
-- **Epoch fencing.** Each role change bumps the epoch. Old primaries cannot
-  write after being demoted -- even if they still have the lease.
-- **Volumes survive container restart.** Data is stored in the Docker volume
-  at `/data/blocks/`. The volume server re-registers with the master on restart.
-
-## Troubleshooting
-
-**iSCSI login fails with "No records found"**
-- Run discovery first: `sudo iscsiadm -m discovery -t sendtargets -p HOST:3260`
-
-**Device not appearing after login**
-- Check `dmesg | tail` for SCSI errors
-- Verify the volume is assigned as primary: `curl http://HOST:9333/block/volumes`
-
-**I/O errors on write**
-- Check volume role is `primary` (not `none` or `stale`)
-- Check master is running (lease renewal requires master heartbeat)
-
-**Stuck iSCSI session after container restart**
-- Force logout: `sudo iscsiadm -m node -T IQN -p HOST:PORT --logout`
-- If stuck: `sudo ss -K dst HOST dport = 3260` to kill the TCP connection
-- Then re-discover and login
-
-## Docker Compose Reference
-
-```yaml
-# local-block-compose.yml
-services:
-  master:
-    image: seaweedfs-block:local
-    ports:
-      - "9333:9333"      # HTTP API
-      - "19333:19333"     # gRPC
-    command: ["master", "-ip=master", "-ip.bind=0.0.0.0", "-mdir=/data"]
-
-  volume:
-    image: seaweedfs-block:local
-    ports:
-      - "8280:8080"       # Volume HTTP
-      - "18280:18080"     # Volume gRPC
-      - "3260:3260"       # iSCSI target
-    command: >
-      volume -ip=volume -master=master:9333 -dir=/data
-      -block.dir=/data/blocks
-      -block.listen=0.0.0.0:3260
-      -block.portal=${HOST_IP:-127.0.0.1}:3260,1
-```
-
-Key flags:
-- `-block.dir`: Directory for `.blk` volume files
-- `-block.listen`: iSCSI target listen address (inside container)
-- `-block.portal`: iSCSI portal address reported to clients (must be reachable)

docker/compose/local-block-compose.yml

@@ -1,38 +0,0 @@
-## SeaweedFS Block Storage — Docker Compose
-##
-## Usage:
-##   HOST_IP=192.168.1.100 docker compose -f local-block-compose.yml up -d
-##
-## The HOST_IP is used for iSCSI discovery so external clients can connect.
-## If running on the same host, you can use: HOST_IP=127.0.0.1
-
-services:
-  master:
-    image: seaweedfs-block:local
-    entrypoint: ["/usr/bin/weed"]
-    ports:
-      - "9333:9333"
-      - "19333:19333"
-    command: ["master", "-ip=master", "-ip.bind=0.0.0.0", "-mdir=/data"]
-
-  volume:
-    image: seaweedfs-block:local
-    ports:
-      - "8280:8080"
-      - "18280:18080"
-      - "3260:3260"
-    entrypoint: ["/bin/sh", "-c"]
-    command:
-      - >
-        mkdir -p /data/blocks &&
-        exec /usr/bin/weed volume
-        -ip=volume
-        -master=master:9333
-        -ip.bind=0.0.0.0
-        -port=8080
-        -dir=/data
-        -block.dir=/data/blocks
-        -block.listen=0.0.0.0:3260
-        -block.portal=${HOST_IP:-127.0.0.1}:3260,1
-    depends_on:
-      - master

docker/entrypoint.sh

@@ -1,2 +1,101 @@
 #!/bin/sh
-exec /usr/bin/weed "$@"
+
+# Enable FIPS 140-3 mode by default (Go 1.24+)
+# To disable: docker run -e GODEBUG=fips140=off ...
+export GODEBUG="${GODEBUG:+$GODEBUG,}fips140=on"
+
+# Fix permissions for mounted volumes
+# If /data is mounted from host, it might have different ownership
+# Fix this by ensuring seaweed user owns the directory
+if [ "$(id -u)" = "0" ]; then
+  # Running as root, check and fix permissions if needed
+  SEAWEED_UID=$(id -u seaweed)
+  SEAWEED_GID=$(id -g seaweed)
+  
+  # Verify seaweed user and group exist
+  if [ -z "$SEAWEED_UID" ] || [ -z "$SEAWEED_GID" ]; then
+    echo "Error: 'seaweed' user or group not found. Cannot fix permissions." >&2
+    exit 1
+  fi
+  
+  DATA_UID=$(stat -c '%u' /data 2>/dev/null)
+  DATA_GID=$(stat -c '%g' /data 2>/dev/null)
+  
+  # Only run chown -R if ownership doesn't match (much faster for subsequent starts)
+    echo "Fixing /data ownership for seaweed user (uid=$SEAWEED_UID, gid=$SEAWEED_GID)"
+    if ! chown -R seaweed:seaweed /data; then
+      echo "Warning: Failed to change ownership of /data. This may cause permission errors." >&2
+      echo "If /data is read-only or has mount issues, the application may fail to start." >&2
+    fi
+  
+  # Use su-exec to drop privileges and run as seaweed user
+  exec su-exec seaweed "$0" "$@"
+fi
+
+isArgPassed() {
+  arg="$1"
+  argWithEqualSign="$1="
+  shift
+  while [ $# -gt 0 ]; do
+    passedArg="$1"
+    shift
+    case $passedArg in
+    "$arg")
+      return 0
+      ;;
+    "$argWithEqualSign"*)
+      return 0
+      ;;
+    esac
+  done
+  return 1
+}
+
+case "$1" in
+
+  'master')
+  	ARGS="-mdir=/data -volumePreallocate -volumeSizeLimitMB=1024"
+  	shift
+  	exec /usr/bin/weed -logtostderr=true master $ARGS $@
+	;;
+
+  'volume')
+  	ARGS="-dir=/data -max=0"
+  	if isArgPassed "-max" "$@"; then
+  	  ARGS="-dir=/data"
+  	fi
+  	shift
+  	exec /usr/bin/weed -logtostderr=true volume $ARGS $@
+	;;
+
+  'server')
+  	ARGS="-dir=/data -volume.max=0 -master.volumePreallocate -master.volumeSizeLimitMB=1024"
+  	if isArgPassed "-volume.max" "$@"; then
+  	  ARGS="-dir=/data -master.volumePreallocate -master.volumeSizeLimitMB=1024"
+  	fi
+ 	shift
+  	exec /usr/bin/weed -logtostderr=true server $ARGS $@
+  	;;
+
+  'filer')
+  	ARGS=""
+  	shift
+  	exec /usr/bin/weed -logtostderr=true filer $ARGS $@
+	;;
+
+  's3')
+  	ARGS="-domainName=$S3_DOMAIN_NAME -key.file=$S3_KEY_FILE -cert.file=$S3_CERT_FILE"
+  	shift
+  	exec /usr/bin/weed -logtostderr=true s3 $ARGS $@
+	;;
+
+  'shell')
+  	ARGS="-cluster=$SHELL_CLUSTER -filer=$SHELL_FILER -filerGroup=$SHELL_FILER_GROUP -master=$SHELL_MASTER -options=$SHELL_OPTIONS"
+  	shift
+  	exec echo "$@" | /usr/bin/weed -logtostderr=true shell $ARGS
+  ;;
+
+  *)
+  	exec /usr/bin/weed $@
+	;;
+esac

docker/entrypoint_e2e.sh

@@ -33,7 +33,7 @@ isArgPassed() {
 case "$1" in
 
   'master')
-  	ARGS="-mdir=/data -volumeSizeLimitMB=1024"
+  	ARGS="-mdir=/data -volumePreallocate -volumeSizeLimitMB=1024"
   	shift
   	exec /usr/bin/weed -logtostderr=true master $ARGS "$@"
 	;;
@@ -48,9 +48,9 @@ case "$1" in
 	;;
 
   'server')
-  	ARGS="-dir=/data -volume.max=0 -master.volumeSizeLimitMB=1024"
+  	ARGS="-dir=/data -volume.max=0 -master.volumePreallocate -master.volumeSizeLimitMB=1024"
   	if isArgPassed "-volume.max" "$@"; then
-  	  ARGS="-dir=/data -master.volumeSizeLimitMB=1024"
+  	  ARGS="-dir=/data -master.volumePreallocate -master.volumeSizeLimitMB=1024"
   	fi
  	shift
   	exec /usr/bin/weed -logtostderr=true server $ARGS "$@"

docker/seaweedfs-dev-compose.yml

@@ -42,12 +42,3 @@ services:
       - master
       - volume
       - filer
-  admin:
-    image: chrislusf/seaweedfs:dev # use a remote dev image
-    ports:
-      - 23646:23646
-    command: 'admin -master=master:9333'
-    depends_on:
-      - master
-      - volume
-      - filer

docker/security.toml.example

@@ -13,22 +13,22 @@ values = "*"
 # - the Master server generates the JWT, which can be used to write a certain file on a volume server
 # - the Volume server validates the JWT on writing
 # the jwt defaults to expire after 10 seconds.
-# [jwt.signing]
-# key = "V1JJVEVTRUNSRVRFWEFNUExFMTIzNDU2Nzg5MDEy" # Example: WRITESECRETEXAMPLE123456789012
+[jwt.signing]
+key = "<REPLACE_AT_RUNTIME>"
 # this jwt signing key is read by master and volume server, and it is used for read operations:
 # - the Master server generates the JWT, which can be used to read a certain file on a volume server
 # - the Volume server validates the JWT on reading
-# [jwt.signing.read]
-# key = "UkVBRFNFQ1JFVUVYQU1QTEUxMjM0NTY3ODkwMTI=" # Example: READSECRETEXAMPLE123456789012
+[jwt.signing.read]
+key = "<REPLACE_AT_RUNTIME>"
 # If this JWT key is configured, Filer only accepts writes over HTTP if they are signed with this JWT:
 # - f.e. the S3 API Shim generates the JWT
 # - the Filer server validates the JWT on writing
 # the jwt defaults to expire after 10 seconds.
-# [jwt.filer_signing]
-# key = "RklMRVJXUklURVNFQ1JFVEVYQU1QTEUxMjM0NTY3OA==" # Example: FILERWRITESECRETEXAMPLE12345678
+[jwt.filer_signing]
+key = "<REPLACE_AT_RUNTIME>"
 # If this JWT key is configured, Filer only accepts reads over HTTP if they are signed with this JWT:
 # - f.e. the S3 API Shim generates the JWT
-# - the Filer server validates the JWT on reading
+# - the Filer server validates the JWT on writing
 # the jwt defaults to expire after 10 seconds.
-# [jwt.filer_signing.read]
-# key = "RklMRVJSRUFEU0VDUkVURVhBTVBMRTEyMzQ1Njc4OQ==" # Example: FILERREADSECRETEXAMPLE123456789
+[jwt.filer_signing.read]
+key = "<REPLACE_AT_RUNTIME>"

go.mod

@@ -5,7 +5,7 @@ go 1.24.9
 require (
 	cloud.google.com/go v0.123.0 // indirect
 	cloud.google.com/go/pubsub v1.50.1
-	cloud.google.com/go/storage v1.59.2
+	cloud.google.com/go/storage v1.59.1
 	github.com/Shopify/sarama v1.38.1
 	github.com/aws/aws-sdk-go v1.55.8
 	github.com/beorn7/perks v1.0.1 // indirect
@@ -46,10 +46,10 @@ require (
 	github.com/jmespath/go-jmespath v0.4.0 // indirect
 	github.com/json-iterator/go v1.1.12
 	github.com/karlseguin/ccache/v2 v2.0.8
-	github.com/klauspost/compress v1.18.4
+	github.com/klauspost/compress v1.18.2
 	github.com/klauspost/reedsolomon v1.13.0
 	github.com/kurin/blazer v0.5.3
-	github.com/linxGnu/grocksdb v1.10.7
+	github.com/linxGnu/grocksdb v1.10.3
 	github.com/mailru/easyjson v0.9.1 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
@@ -86,20 +86,20 @@ require (
 	github.com/xdg-go/scram v1.1.2 // indirect
 	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 v3.6.7
+	go.etcd.io/etcd/client/v3 v3.6.6
 	go.mongodb.org/mongo-driver v1.17.6
 	go.opencensus.io v0.24.0 // indirect
 	gocloud.dev v0.44.0
 	gocloud.dev/pubsub/natspubsub v0.44.0
 	gocloud.dev/pubsub/rabbitpubsub v0.44.0
-	golang.org/x/crypto v0.48.0
+	golang.org/x/crypto v0.47.0
 	golang.org/x/exp v0.0.0-20251023183803-a4bb9ffd2546
-	golang.org/x/image v0.36.0
+	golang.org/x/image v0.35.0
 	golang.org/x/net v0.49.0
 	golang.org/x/oauth2 v0.34.0
-	golang.org/x/sys v0.41.0
-	golang.org/x/text v0.34.0 // indirect
-	golang.org/x/tools v0.41.0 // indirect
+	golang.org/x/sys v0.40.0
+	golang.org/x/text v0.33.0 // indirect
+	golang.org/x/tools v0.40.0 // indirect
 	golang.org/x/xerrors v0.0.0-20240903120638-7835f813f4da // indirect
 	google.golang.org/api v0.258.0
 	google.golang.org/genproto v0.0.0-20250922171735-9219d122eba9 // indirect
@@ -109,7 +109,7 @@ require (
 	modernc.org/b v1.0.0 // indirect
 	modernc.org/mathutil v1.7.1
 	modernc.org/memory v1.11.0 // indirect
-	modernc.org/sqlite v1.46.1
+	modernc.org/sqlite v1.44.3
 	modernc.org/strutil v1.2.1
 )
 
@@ -120,7 +120,6 @@ require (
 	github.com/ThreeDotsLabs/watermill v1.5.1
 	github.com/a-h/templ v0.3.977
 	github.com/apache/cassandra-gocql-driver/v2 v2.0.0
-	github.com/apache/iceberg-go v0.4.0
 	github.com/apple/foundationdb/bindings/go v0.0.0-20250911184653-27f7192f47c3
 	github.com/arangodb/go-driver v1.6.9
 	github.com/armon/go-metrics v0.4.1
@@ -129,31 +128,32 @@ require (
 	github.com/aws/aws-sdk-go-v2/credentials v1.19.7
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0
 	github.com/cognusion/imaging v1.0.2
-	github.com/container-storage-interface/spec v1.10.0
 	github.com/fluent/fluent-logger-golang v1.10.1
-	github.com/getsentry/sentry-go v0.42.0
+	github.com/getsentry/sentry-go v0.40.0
+	github.com/gin-contrib/sessions v1.0.4
+	github.com/gin-gonic/gin v1.11.0
 	github.com/go-ldap/ldap/v3 v3.4.12
-	github.com/golang-jwt/jwt/v5 v5.3.1
+	github.com/golang-jwt/jwt/v5 v5.3.0
 	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/jhump/protoreflect v1.18.0
+	github.com/jhump/protoreflect v1.17.0
+	github.com/lib/pq v1.10.9
 	github.com/linkedin/goavro/v2 v2.14.1
-	github.com/mattn/go-sqlite3 v1.14.34
+	github.com/mattn/go-sqlite3 v1.14.33
 	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
+	github.com/parquet-go/parquet-go v0.26.4
 	github.com/pkg/sftp v1.13.10
 	github.com/rabbitmq/amqp091-go v1.10.0
-	github.com/rclone/rclone v1.73.1
+	github.com/rclone/rclone v1.72.1
 	github.com/rdleal/intervalst v1.5.0
-	github.com/redis/go-redis/v9 v9.18.0
+	github.com/redis/go-redis/v9 v9.17.2
 	github.com/schollz/progressbar/v3 v3.19.0
 	github.com/seaweedfs/go-fuse/v2 v2.9.1
-	github.com/shirou/gopsutil/v4 v4.26.1
+	github.com/shirou/gopsutil/v4 v4.25.12
 	github.com/tarantool/go-tarantool/v2 v2.4.1
-	github.com/testcontainers/testcontainers-go v0.39.0
 	github.com/tikv/client-go/v2 v2.0.7
 	github.com/xeipuuv/gojsonschema v1.2.0
 	github.com/ydb-platform/ydb-go-sdk-auth-environ v0.5.1
@@ -168,129 +168,76 @@ require (
 require github.com/k0kubun/colorstring v0.0.0-20150214042306-9440f1994b88 // indirect
 
 require (
-	atomicgo.dev/cursor v0.2.0 // indirect
-	atomicgo.dev/keyboard v0.2.9 // indirect
-	atomicgo.dev/schedule v0.1.0 // indirect
 	cloud.google.com/go/longrunning v0.7.0 // indirect
 	cloud.google.com/go/pubsub/v2 v2.2.1 // indirect
-	dario.cat/mergo v1.0.2 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/keyvault/internal v0.7.1 // indirect
-	github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c // indirect
-	github.com/Azure/go-autorest v14.2.0+incompatible // indirect
-	github.com/Azure/go-autorest/autorest/to v0.4.1 // indirect
-	github.com/FilenCloudDienste/filen-sdk-go v0.0.37 // indirect
 	github.com/a1ex3/zstd-seekable-format-go/pkg v0.10.0 // indirect
 	github.com/anchore/go-lzo v0.1.0 // indirect
-	github.com/antlr4-go/antlr/v4 v4.13.1 // indirect
-	github.com/apache/arrow-go/v18 v18.4.1 // indirect
-	github.com/apache/thrift v0.22.0 // indirect
 	github.com/aws/aws-sdk-go-v2/service/signin v1.0.5 // indirect
 	github.com/bahlo/generic-list-go v0.2.0 // indirect
 	github.com/bazelbuild/rules_go v0.46.0 // indirect
 	github.com/biogo/store v0.0.0-20201120204734-aad293a2328f // indirect
 	github.com/blevesearch/snowballstem v0.9.0 // indirect
 	github.com/boombuler/barcode v1.1.0 // indirect
+	github.com/bufbuild/protocompile v0.14.1 // indirect
 	github.com/buger/jsonparser v1.1.1 // indirect
 	github.com/cenkalti/backoff/v5 v5.0.3 // indirect
 	github.com/clipperhouse/stringish v0.1.1 // indirect
 	github.com/clipperhouse/uax29/v2 v2.3.0 // indirect
-	github.com/cockroachdb/apd/v3 v3.2.1 // indirect
+	github.com/cockroachdb/apd/v3 v3.1.0 // indirect
 	github.com/cockroachdb/errors v1.11.3 // indirect
 	github.com/cockroachdb/logtags v0.0.0-20241215232642-bb51bb14a506 // indirect
 	github.com/cockroachdb/redact v1.1.5 // indirect
 	github.com/cockroachdb/version v0.0.0-20250314144055-3860cd14adf2 // indirect
-	github.com/containerd/console v1.0.5 // indirect
-	github.com/containerd/errdefs v1.0.0 // indirect
-	github.com/containerd/errdefs/pkg v0.3.0 // indirect
-	github.com/containerd/log v0.1.0 // indirect
-	github.com/containerd/platforms v1.0.0-rc.1 // indirect
-	github.com/cpuguy83/dockercfg v0.3.2 // indirect
 	github.com/dave/dst v0.27.2 // indirect
 	github.com/diskfs/go-diskfs v1.7.0 // indirect
-	github.com/distribution/reference v0.6.0 // indirect
-	github.com/docker/docker v28.5.0+incompatible // indirect
-	github.com/docker/go-connections v0.6.0 // indirect
-	github.com/docker/go-units v0.5.0 // indirect
-	github.com/dromara/dongle v1.0.1 // indirect
-	github.com/gin-gonic/gin v1.11.0 // indirect
 	github.com/go-asn1-ber/asn1-ber v1.5.8-0.20250403174932-29230038a667 // indirect
 	github.com/go-git/go-billy/v5 v5.6.2 // indirect
 	github.com/goccy/go-yaml v1.18.0 // indirect
 	github.com/golang/geo v0.0.0-20210211234256-740aa86cb551 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
-	github.com/gookit/color v1.5.4 // indirect
 	github.com/gopherjs/gopherjs v1.17.2 // indirect
 	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
-	github.com/hamba/avro/v2 v2.30.0 // indirect
 	github.com/hashicorp/go-rootcerts v1.0.2 // indirect
 	github.com/hashicorp/go-secure-stdlib/parseutil v0.2.0 // indirect
 	github.com/hashicorp/go-secure-stdlib/strutil v0.1.2 // indirect
 	github.com/hashicorp/go-sockaddr v1.0.7 // indirect
 	github.com/hashicorp/hcl v1.0.1-vault-7 // indirect
-	github.com/iceber/iouring-go v0.0.0-20230403020409-002cfd2e2a90 // indirect
-	github.com/internxt/rclone-adapter v0.0.0-20260213125353-6f59c89fcb7c // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
 	github.com/jackc/puddle/v2 v2.2.2 // indirect
 	github.com/jaegertracing/jaeger v1.47.0 // indirect
-	github.com/jhump/protoreflect/v2 v2.0.0-beta.1 // indirect
 	github.com/jtolds/gls v4.20.0+incompatible // indirect
-	github.com/klauspost/asmfmt v1.3.2 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
-	github.com/lib/pq v1.11.1 // indirect
-	github.com/lithammer/fuzzysearch v1.1.8 // indirect
 	github.com/lithammer/shortuuid/v3 v3.0.7 // indirect
-	github.com/magiconair/properties v1.8.10 // indirect
-	github.com/minio/asm2plan9s v0.0.0-20200509001527-cdd76441f9d8 // indirect
-	github.com/minio/c2goasm v0.0.0-20190812172519-36a3d3bbc4f3 // indirect
-	github.com/moby/docker-image-spec v1.3.1 // indirect
-	github.com/moby/go-archive v0.1.0 // indirect
-	github.com/moby/patternmatcher v0.6.0 // indirect
-	github.com/moby/sys/sequential v0.6.0 // indirect
-	github.com/moby/sys/user v0.4.0 // indirect
-	github.com/moby/sys/userns v0.1.0 // indirect
-	github.com/moby/term v0.5.2 // indirect
-	github.com/morikuni/aec v1.0.0 // indirect
-	github.com/opencontainers/go-digest v1.0.0 // indirect
-	github.com/opencontainers/image-spec v1.1.1 // indirect
 	github.com/openzipkin/zipkin-go v0.4.3 // indirect
 	github.com/parquet-go/bitpack v1.0.0 // indirect
 	github.com/parquet-go/jsonlite v1.0.0 // indirect
-	github.com/pawelgaczynski/giouring v0.0.0-20230826085535-69588b89acb9 // indirect
-	github.com/petermattis/goid v0.0.0-20260113132338-7c7de50cc741 // indirect
+	github.com/petermattis/goid v0.0.0-20180202154549-b0b1615b78e5 // indirect
 	github.com/pierrre/geohash v1.0.0 // indirect
 	github.com/pquerna/otp v1.5.0 // indirect
-	github.com/pterm/pterm v0.12.81 // indirect
+	github.com/quic-go/qpack v0.6.0 // indirect
 	github.com/quic-go/quic-go v0.57.0 // indirect
-	github.com/rclone/Proton-API-Bridge v1.0.1-0.20260127174007-77f974840d11 // indirect
-	github.com/rclone/go-proton-api v1.0.1-0.20260127173028-eb465cac3b18 // indirect
 	github.com/rogpeppe/go-internal v1.14.1 // indirect
 	github.com/ryanuber/go-glob v1.0.0 // indirect
 	github.com/sasha-s/go-deadlock v0.3.1 // indirect
 	github.com/smarty/assertions v1.15.0 // indirect
 	github.com/stretchr/objx v0.5.2 // indirect
-	github.com/substrait-io/substrait v0.69.0 // indirect
-	github.com/substrait-io/substrait-go/v4 v4.4.0 // indirect
-	github.com/substrait-io/substrait-protobuf/go v0.71.0 // indirect
-	github.com/twpayne/go-geom v1.6.1 // indirect
-	github.com/twpayne/go-kml/v3 v3.2.1 // indirect
-	github.com/tyler-smith/go-bip39 v1.1.0 // indirect
+	github.com/twpayne/go-geom v1.4.1 // indirect
+	github.com/twpayne/go-kml v1.5.2 // indirect
 	github.com/ulikunitz/xz v0.5.15 // indirect
 	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
-	github.com/xeipuuv/gojsonpointer v0.0.0-20190905194746-02993c407bfb // indirect
+	github.com/xeipuuv/gojsonpointer v0.0.0-20180127040702-4e3ac2762d5f // indirect
 	github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 // indirect
-	github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect
 	github.com/zeebo/xxh3 v1.0.2 // indirect
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.37.0 // indirect
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.37.0 // indirect
 	go.opentelemetry.io/otel/exporters/zipkin v1.36.0 // indirect
 	go.opentelemetry.io/proto/otlp v1.7.0 // indirect
-	go.uber.org/mock v0.5.2 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
-	golang.org/x/mod v0.32.0 // indirect
-	golang.org/x/telemetry v0.0.0-20260109210033-bd525da824e2 // indirect
+	golang.org/x/mod v0.31.0 // indirect
 	gonum.org/v1/gonum v0.16.0 // indirect
 )
 
@@ -301,13 +248,13 @@ require (
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
 	cloud.google.com/go/iam v1.5.3 // indirect
 	cloud.google.com/go/monitoring v1.24.2 // indirect
-	filippo.io/edwards25519 v1.1.1 // indirect
+	filippo.io/edwards25519 v1.1.0 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0
 	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1
 	github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 // indirect
-	github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.4
+	github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v1.6.3
 	github.com/Azure/azure-sdk-for-go/sdk/storage/azfile v1.5.3 // indirect
-	github.com/Azure/go-ntlmssp v0.1.0 // indirect
+	github.com/Azure/go-ntlmssp v0.0.2-0.20251110135918-10b7b7e7cd26 // indirect
 	github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 // indirect
 	github.com/Files-com/files-sdk-go/v3 v3.2.264 // indirect
 	github.com/GoogleCloudPlatform/opentelemetry-operations-go/detectors/gcp v1.30.0 // indirect
@@ -349,12 +296,15 @@ require (
 	github.com/bradenaw/juniper v0.15.3 // indirect
 	github.com/bradfitz/iter v0.0.0-20191230175014-e8f45d346db8 // indirect
 	github.com/buengese/sgzip v0.1.1 // indirect
+	github.com/bytedance/sonic v1.14.0 // indirect
+	github.com/bytedance/sonic/loader v0.3.0 // indirect
 	github.com/calebcase/tmpfile v1.0.3 // indirect
 	github.com/chilts/sid v0.0.0-20190607042430-660e94789ec9 // indirect
-	github.com/cloudflare/circl v1.6.3 // indirect
+	github.com/cloudflare/circl v1.6.1 // indirect
 	github.com/cloudinary/cloudinary-go/v2 v2.13.0 // indirect
 	github.com/cloudsoda/go-smb2 v0.0.0-20250228001242-d4c70e6251cc // indirect
 	github.com/cloudsoda/sddl v0.0.0-20250224235906-926454e91efc // indirect
+	github.com/cloudwego/base64x v0.1.6 // indirect
 	github.com/cncf/xds/go v0.0.0-20251022180443-0feb69152e9f // indirect
 	github.com/colinmarc/hdfs/v2 v2.4.0 // indirect
 	github.com/creasty/defaults v1.8.0 // indirect
@@ -374,7 +324,8 @@ require (
 	github.com/flynn/noise v1.1.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.11 // indirect
 	github.com/geoffgarside/ber v1.2.0 // indirect
-	github.com/go-chi/chi/v5 v5.2.5 // indirect
+	github.com/gin-contrib/sse v1.1.0 // indirect
+	github.com/go-chi/chi/v5 v5.2.3 // 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-logr/logr v1.4.3 // indirect
@@ -393,11 +344,12 @@ require (
 	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 v0.3.7 // indirect
+	github.com/gorilla/context v1.1.2 // indirect
 	github.com/gorilla/schema v1.4.1 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
-	github.com/gorilla/sessions v1.4.0
+	github.com/gorilla/sessions v1.4.0 // indirect
 	github.com/grpc-ecosystem/go-grpc-middleware v1.4.0 // indirect
-	github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.3 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.1 // indirect
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
 	github.com/hashicorp/go-hclog v1.6.3 // indirect
 	github.com/hashicorp/go-immutable-radix v1.3.1 // indirect
@@ -405,6 +357,8 @@ require (
 	github.com/hashicorp/go-msgpack/v2 v2.1.2 // indirect
 	github.com/hashicorp/go-retryablehttp v0.7.8 // indirect
 	github.com/hashicorp/golang-lru v0.6.0 // indirect
+	github.com/henrybear327/Proton-API-Bridge v1.0.0 // indirect
+	github.com/henrybear327/go-proton-api v1.0.0 // indirect
 	github.com/jcmturner/aescts/v2 v2.0.0 // indirect
 	github.com/jcmturner/dnsutils/v2 v2.0.0 // indirect
 	github.com/jcmturner/goidentity/v6 v6.0.1 // indirect
@@ -446,7 +400,7 @@ require (
 	github.com/pelletier/go-toml/v2 v2.2.4 // indirect
 	github.com/pengsrc/go-shared v0.2.1-0.20190131101655-1999055a4a14 // indirect
 	github.com/philhofer/fwd v1.2.0 // indirect
-	github.com/pierrec/lz4/v4 v4.1.25
+	github.com/pierrec/lz4/v4 v4.1.22
 	github.com/pingcap/errors v0.11.5-0.20211224045212-9687c2b0f87c // indirect
 	github.com/pingcap/failpoint v0.0.0-20220801062533-2eaa32854a6c // indirect
 	github.com/pingcap/kvproto v0.0.0-20230403051650-e166ae588106 // indirect
@@ -462,7 +416,7 @@ require (
 	github.com/sabhiram/go-gitignore v0.0.0-20210923224102-525f6e181f06 // indirect
 	github.com/sagikazarmark/locafero v0.11.0 // indirect
 	github.com/samber/lo v1.52.0 // indirect
-	github.com/seaweedfs/cockroachdb-parser v0.0.0-20260225204133-2f342c5ea564
+	github.com/seaweedfs/cockroachdb-parser v0.0.0-20251021184156-909763b17138
 	github.com/skratchdot/open-golang v0.0.0-20200116055534-eef842397966 // indirect
 	github.com/sony/gobreaker v1.0.0 // indirect
 	github.com/sourcegraph/conc v0.3.1-0.20240121214520-5f936abd7ae8 // indirect
@@ -477,7 +431,9 @@ require (
 	github.com/tinylib/msgp v1.5.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.16 // indirect
 	github.com/tklauser/numcpus v0.11.0 // indirect
-	github.com/twmb/murmur3 v1.1.8 // indirect
+	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
+	github.com/twmb/murmur3 v1.1.3 // indirect
+	github.com/ugorji/go/codec v1.3.0 // indirect
 	github.com/unknwon/goconfig v1.0.0 // indirect
 	github.com/vmihailenco/msgpack/v5 v5.4.1 // indirect
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
@@ -491,7 +447,7 @@ 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 v3.6.7 // indirect
+	go.etcd.io/etcd/api/v3 v3.6.6 // indirect
 	go.opentelemetry.io/auto/sdk v1.2.1 // indirect
 	go.opentelemetry.io/contrib/detectors/gcp v1.38.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.63.0 // indirect
@@ -502,10 +458,11 @@ require (
 	go.opentelemetry.io/otel/sdk/metric v1.38.0 // indirect
 	go.opentelemetry.io/otel/trace v1.38.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.27.1 // indirect
-	golang.org/x/term v0.40.0 // indirect
+	go.uber.org/zap v1.27.0 // indirect
+	golang.org/x/arch v0.20.0 // indirect
+	golang.org/x/term v0.39.0 // indirect
 	golang.org/x/time v0.14.0 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20251124214823-79d6a2a48846 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20251111163417-95abcf5c77ba // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20251213004720-97cd9d5aeac2 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
 	gopkg.in/validator.v2 v2.0.1 // indirect
@@ -523,14 +480,3 @@ require (
 )
 
 // replace github.com/seaweedfs/raft => /Users/chrislu/go/src/github.com/seaweedfs/raft
-
-// V2 engine bridge modules (Phase 07)
-require (
-	github.com/seaweedfs/seaweedfs/sw-block/engine/replication v0.0.0
-	github.com/seaweedfs/seaweedfs/sw-block/bridge/blockvol v0.0.0
-)
-
-replace (
-	github.com/seaweedfs/seaweedfs/sw-block/engine/replication => ./sw-block/engine/replication
-	github.com/seaweedfs/seaweedfs/sw-block/bridge/blockvol => ./sw-block/bridge/blockvol
-)

k8s/charts/seaweedfs/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v1
 description: SeaweedFS
 name: seaweedfs
-appVersion: "4.13"
+appVersion: "4.07"
 # Dev note: Trigger a helm chart release by `git tag -a helm-<version>`
-version: 4.0.413
+version: 4.0.407

k8s/charts/seaweedfs/README.md

@@ -1,5 +1,6 @@
 # SEAWEEDFS - helm chart (2.x+)
 
+## Getting Started
 
 ### Add the helm repo
 
@@ -212,9 +213,8 @@ To enable workers, add the following to your values.yaml:
 worker:
   enabled: true
   replicas: 2  # Scale based on workload
-  jobType: "vacuum,volume_balance,erasure_coding"  # Job types this worker can handle
-  maxDetect: 1  # Maximum concurrent detection requests
-  maxExecute: 4  # Maximum concurrent execution jobs per worker
+  capabilities: "vacuum,balance,erasure_coding"  # Tasks this worker can handle
+  maxConcurrent: 3  # Maximum concurrent tasks per worker
   
   # Working directory for task execution
   # Default: "/tmp/seaweedfs-worker"
@@ -249,14 +249,14 @@ worker:
       memory: "2Gi"
 ```
 
-### Worker Job Types
+### Worker Capabilities
 
-Workers can be configured with different job types:
+Workers can be configured with different capabilities:
 - **vacuum**: Reclaim deleted file space
-- **volume_balance**: Balance volumes across volume servers
+- **balance**: Balance volumes across volume servers
 - **erasure_coding**: Handle erasure coding operations
 
-You can configure workers with all job types or create specialized worker pools with specific job types.
+You can configure workers with all capabilities or create specialized worker pools with specific capabilities.
 
 ### Worker Deployment Strategy
 
@@ -265,11 +265,11 @@ For production deployments, consider:
 1. **Multiple Workers**: Deploy 2+ worker replicas for high availability
 2. **Resource Allocation**: Workers need sufficient CPU/memory for maintenance tasks
 3. **Storage**: Workers need temporary storage for vacuum and balance operations (size depends on volume size)
-4. **Specialized Workers**: Create separate worker deployments for different job types if needed
+4. **Specialized Workers**: Create separate worker deployments for different capabilities if needed
 
 Example specialized worker configuration:
 
-For specialized worker pools, deploy separate Helm releases with different job types:
+For specialized worker pools, deploy separate Helm releases with different capabilities:
 
 **values-worker-vacuum.yaml** (for vacuum operations):
 ```yaml
@@ -288,8 +288,8 @@ admin:
 worker:
   enabled: true
   replicas: 2
-  jobType: "vacuum"
-  maxExecute: 2
+  capabilities: "vacuum"
+  maxConcurrent: 2
   # REQUIRED: Point to the admin service of your main SeaweedFS release
   # Replace <namespace> with the namespace where your main seaweedfs is deployed
   # Example: If deploying in namespace "production":
@@ -314,8 +314,8 @@ admin:
 worker:
   enabled: true
   replicas: 1
-  jobType: "volume_balance"
-  maxExecute: 1
+  capabilities: "balance"
+  maxConcurrent: 1
   # REQUIRED: Point to the admin service of your main SeaweedFS release
   # Replace <namespace> with the namespace where your main seaweedfs is deployed
   # Example: If deploying in namespace "production":
@@ -324,7 +324,6 @@ worker:
 ```
 
 Deploy the specialized workers as separate releases:
-### Specialized Worker Deployment
 ```bash
 # Deploy vacuum workers
 helm install seaweedfs-worker-vacuum seaweedfs/seaweedfs -f values-worker-vacuum.yaml
@@ -333,22 +332,6 @@ helm install seaweedfs-worker-vacuum seaweedfs/seaweedfs -f values-worker-vacuum
 helm install seaweedfs-worker-balance seaweedfs/seaweedfs -f values-worker-balance.yaml
 ```
 
-## OpenShift Support
-
-SeaweedFS can be deployed on OpenShift or any cluster enforcing the Kubernetes "restricted" Pod Security Standard. By default, OpenShift blocks containers that run as root or use `hostPath` volumes.
-
-To deploy on OpenShift, use the provided `openshift-values.yaml` which overrides the default configuration to:
-1. Use `PersistentVolumeClaims` instead of `hostPath`.
-2. Enable `runAsNonRoot` and omit hardcoded UIDs to allow OpenShift to assign valid UIDs automatically.
-3. Apply appropriate `seccompProfile` and drop capabilities.
-
-Usage:
-```bash
-helm install seaweedfs seaweedfs/seaweedfs \
-  -n seaweedfs --create-namespace \
-  -f openshift-values.yaml
-```
-
 ## Enterprise
 
 For enterprise users, please visit [seaweedfs.com](https://seaweedfs.com) for the SeaweedFS Enterprise Edition, 

k8s/charts/seaweedfs/openshift-values.yaml

@@ -1,116 +0,0 @@
-# openshift-values.yaml
-#
-# Example overrides for deploying SeaweedFS on OpenShift (or any cluster
-# enforcing the Kubernetes "restricted" Pod Security Standard).
-#
-# OpenShift's default "restricted" SCC blocks containers that:
-#   - Run as UID 0 (root)
-#   - Request privilege escalation
-#   - Use hostPath volumes
-#   - Omit a seccompProfile
-#
-# These overrides satisfy all four requirements by:
-#   1. Replacing hostPath volumes with PersistentVolumeClaims (or emptyDir for logs)
-#   2. Enabling runAsNonRoot: true. By omitting runAsUser, OpenShift will
-#      automatically assign a valid UID from the namespace's allocated range.
-#   3. Dropping all Linux capabilities and setting allowPrivilegeEscalation: false
-#   4. Enabling RuntimeDefault seccompProfile
-#
-# Usage:
-#   helm install seaweedfs seaweedfs/seaweedfs \
-#     -n seaweedfs --create-namespace \
-#     -f openshift-values.yaml
-#
-# Adjust storageClass and sizes to match your cluster's available StorageClasses.
-# On OpenShift you can discover them with: oc get storageclass
-
-master:
-  data:
-    type: "persistentVolumeClaim"
-    size: "10Gi"
-    storageClass: ""        # leave empty to use the cluster default StorageClass
-
-  logs:
-    type: "emptyDir"        # avoids hostPath; use persistentVolumeClaim if you need log persistence
-
-  podSecurityContext:
-    enabled: true
-    # On OpenShift, we omit runAsUser/runAsGroup/fsGroup to let the admission
-    # controller assign them automatically based on the namespace's SCC.
-    runAsNonRoot: true
-
-  containerSecurityContext:
-    enabled: true
-    allowPrivilegeEscalation: false
-    capabilities:
-      drop: ["ALL"]
-    runAsNonRoot: true
-    seccompProfile:
-      type: RuntimeDefault
-
-volume:
-  dataDirs:
-    - name: data1
-      type: "persistentVolumeClaim"
-      size: "100Gi"
-      storageClass: ""      # leave empty to use the cluster default StorageClass
-      maxVolumes: 0
-
-  logs:
-    type: "emptyDir"
-
-  podSecurityContext:
-    enabled: true
-    # On OpenShift, we omit runAsUser/runAsGroup/fsGroup to let the admission
-    # controller assign them automatically based on the namespace's SCC.
-    runAsNonRoot: true
-
-  containerSecurityContext:
-    enabled: true
-    allowPrivilegeEscalation: false
-    capabilities:
-      drop: ["ALL"]
-    runAsNonRoot: true
-    seccompProfile:
-      type: RuntimeDefault
-
-filer:
-  data:
-    type: "persistentVolumeClaim"
-    size: "25Gi"
-    storageClass: ""        # leave empty to use the cluster default StorageClass
-
-  logs:
-    type: "emptyDir"
-
-  podSecurityContext:
-    enabled: true
-    # On OpenShift, we omit runAsUser/runAsGroup/fsGroup to let the admission
-    # controller assign them automatically based on the namespace's SCC.
-    runAsNonRoot: true
-
-  containerSecurityContext:
-    enabled: true
-    allowPrivilegeEscalation: false
-    capabilities:
-      drop: ["ALL"]
-    runAsNonRoot: true
-    seccompProfile:
-      type: RuntimeDefault
-
-# S3 gateway (if enabled)
-s3:
-  podSecurityContext:
-    enabled: true
-    # On OpenShift, we omit runAsUser/runAsGroup/fsGroup to let the admission
-    # controller assign them automatically based on the namespace's SCC.
-    runAsNonRoot: true
-
-  containerSecurityContext:
-    enabled: true
-    allowPrivilegeEscalation: false
-    capabilities:
-      drop: ["ALL"]
-    runAsNonRoot: true
-    seccompProfile:
-      type: RuntimeDefault

k8s/charts/seaweedfs/templates/admin/admin-ingress.yaml

@@ -42,11 +42,11 @@ spec:
         backend:
 {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
           service:
-            name: {{ include "seaweedfs.componentName" (list . "admin") }}
+            name: {{ include "seaweedfs.fullname" . }}-admin
             port:
               number: {{ .Values.admin.port }}
 {{- else }}
-          serviceName: {{ include "seaweedfs.componentName" (list . "admin") }}
+          serviceName: {{ include "seaweedfs.fullname" . }}-admin
           servicePort: {{ .Values.admin.port }}
 {{- end }}
 {{- end }}

k8s/charts/seaweedfs/templates/admin/admin-service.yaml

@@ -2,7 +2,7 @@
 apiVersion: v1
 kind: Service
 metadata:
-  name: {{ include "seaweedfs.componentName" (list . "admin") }}
+  name: {{ printf "%s-admin" (include "seaweedfs.fullname" .) | trunc 63 | trimSuffix "-" }}
   namespace: {{ .Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}

k8s/charts/seaweedfs/templates/admin/admin-statefulset.yaml

@@ -8,7 +8,7 @@
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
-  name: {{ include "seaweedfs.componentName" (list . "admin") }}
+  name: {{ include "seaweedfs.fullname" . }}-admin
   namespace: {{ .Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
@@ -21,7 +21,7 @@ metadata:
     {{- toYaml .Values.admin.annotations | nindent 4 }}
 {{- end }}
 spec:
-  serviceName: {{ include "seaweedfs.componentName" (list . "admin") }}
+  serviceName: {{ include "seaweedfs.fullname" . }}-admin
   podManagementPolicy: {{ .Values.admin.podManagementPolicy }}
   replicas: {{ .Values.admin.replicas }}
   selector:

k8s/charts/seaweedfs/templates/cosi/cosi-bucket-class.yaml

@@ -6,10 +6,6 @@ metadata:
   name: {{ .Values.cosi.bucketClassName }}
 driverName: {{ .Values.cosi.driverName }}
 deletionPolicy: Delete
-{{- with .Values.cosi.bucketClassParameters }}
-parameters:
-  {{- toYaml . | nindent 2 }}
-{{- end }}
 ---
 kind: BucketAccessClass
 apiVersion: objectstorage.k8s.io/v1alpha1

k8s/charts/seaweedfs/templates/cosi/cosi-deployment.yaml

@@ -57,7 +57,7 @@ spec:
       priorityClassName: {{ .Values.cosi.priorityClassName | quote }}
       {{- end }}
       enableServiceLinks: false
-      serviceAccountName: {{ include "seaweedfs.componentName" (list . "objectstorage-provisioner") }}
+      serviceAccountName: {{ .Values.global.serviceAccountName }}-objectstorage-provisioner
       {{- if .Values.cosi.initContainers }}
       initContainers:
         {{ tpl .Values.cosi.initContainers . | nindent 8 | trim }}
@@ -78,16 +78,16 @@ spec:
               {{- else if .Values.s3.ingress.enabled }}
               value: "{{ printf "https://%s" .Values.s3.ingress.host }}"
               {{- else if .Values.s3.enabled }}
-              value: "{{ printf "https://%s.%s.svc" (include "seaweedfs.componentName" (list . "s3")) .Release.Namespace }}"
+              value: "{{ printf "https://%s-s3.%s.svc" (include "seaweedfs.fullname" .) .Release.Namespace }}"
               {{- else }}
-              value: "{{ printf "https://%s.%s.svc" (include "seaweedfs.componentName" (list . "filer")) .Release.Namespace }}"
+              value: "{{ printf "https://%s-filer.%s.svc" (include "seaweedfs.fullname" .) .Release.Namespace }}"
               {{- end }}
             {{- with .Values.cosi.region }}
             - name: REGION
               value: "{{ . }}"
             {{- end }}
             - name: SEAWEEDFS_FILER
-              value: "{{ include "seaweedfs.componentName" (list . "filer") }}:{{ .Values.filer.grpcPort }}"
+              value: "{{ include "seaweedfs.fullname" . }}-filer:{{ .Values.filer.grpcPort }}"
             {{- if .Values.global.enableSecurity }}
             - name: WEED_GRPC_CLIENT_KEY
               value: /usr/local/share/ca-certificates/client/tls.key

k8s/charts/seaweedfs/templates/filer/filer-ingress.yaml

@@ -2,7 +2,7 @@
 {{- $filerEnabled := or .Values.filer.enabled .Values.allInOne.enabled }}
 {{- if and $filerEnabled .Values.filer.ingress.enabled }}
 {{- /* Determine service name based on deployment mode */}}
-{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "filer")) .Values.allInOne.enabled }}
+{{- $serviceName := ternary (printf "%s-all-in-one" (include "seaweedfs.fullname" .)) (printf "%s-filer" (include "seaweedfs.fullname" .)) .Values.allInOne.enabled }}
 {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
 apiVersion: networking.k8s.io/v1
 {{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion }}

k8s/charts/seaweedfs/templates/filer/filer-statefulset.yaml

@@ -2,7 +2,7 @@
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
-  name: {{ include "seaweedfs.componentName" (list . "filer") }}
+  name: {{ include "seaweedfs.fullname" . }}-filer
   namespace: {{ .Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
@@ -15,7 +15,7 @@ metadata:
     {{- toYaml .Values.filer.annotations | nindent 4 }}
 {{- end }}
 spec:
-  serviceName: {{ include "seaweedfs.componentName" (list . "filer") }}
+  serviceName: {{ include "seaweedfs.fullname" . }}-filer
   podManagementPolicy: {{ .Values.filer.podManagementPolicy }}
   replicas: {{ .Values.filer.replicas }}
   {{- if (gt (int .Values.filer.updatePartition) 0) }}

k8s/charts/seaweedfs/templates/master/master-ingress.yaml

@@ -33,15 +33,15 @@ spec:
             backend:
 {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
               service:
-                name: {{ include "seaweedfs.componentName" (list . "master") }}
+                name: {{ include "seaweedfs.fullname" . }}-master
                 port:
                   number: {{ .Values.master.port }}
                   #name:
 {{- else }}
-              serviceName: {{ include "seaweedfs.componentName" (list . "master") }}
+              serviceName: {{ include "seaweedfs.fullname" . }}-master
               servicePort: {{ .Values.master.port }}
 {{- end }}
-{{- if .Values.master.ingress.host }}
+{{- if .Values.filer.ingress.host }}
       host: {{ .Values.master.ingress.host }}
 {{- end }}
 {{- end }}

k8s/charts/seaweedfs/templates/master/master-service.yaml

@@ -9,7 +9,6 @@ metadata:
     app.kubernetes.io/component: master
     helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
     app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
   annotations:
     service.alpha.kubernetes.io/tolerate-unready-endpoints: "true"
 {{- if .Values.master.annotations }}

k8s/charts/seaweedfs/templates/master/master-statefulset.yaml

@@ -2,7 +2,7 @@
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
-  name: {{ include "seaweedfs.componentName" (list . "master") }}
+  name: {{ include "seaweedfs.fullname" . }}-master
   namespace: {{ .Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
@@ -15,7 +15,7 @@ metadata:
     {{- toYaml .Values.master.annotations | nindent 4 }}
 {{- end }}
 spec:
-  serviceName: {{ include "seaweedfs.componentName" (list . "master") }}
+  serviceName: {{ include "seaweedfs.fullname" . }}-master
   podManagementPolicy: {{ .Values.master.podManagementPolicy }}
   replicas: {{ .Values.master.replicas }}
   {{- if (gt (int .Values.master.updatePartition) 0) }}
@@ -183,7 +183,7 @@ spec:
               {{- if .Values.master.garbageThreshold }}
               -garbageThreshold={{ .Values.master.garbageThreshold }} \
               {{- end }}
-              -ip=${POD_NAME}.{{ include "seaweedfs.componentName" (list . "master") }}.{{ .Release.Namespace }} \
+              -ip=${POD_NAME}.${SEAWEEDFS_FULLNAME}-master.{{ .Release.Namespace }} \
               -peers={{ include "seaweedfs.masterServers" . }} \
               {{- range .Values.master.extraArgs }}
               {{ . }} \

k8s/charts/seaweedfs/templates/s3/s3-deployment.yaml

@@ -149,10 +149,7 @@ spec:
               {{- if .Values.s3.auditLogConfig }}
               -auditLogConfig=/etc/sw/s3_auditLogConfig.json \
               {{- end }}
-              -filer={{ include "seaweedfs.componentName" (list . "filer-client") }}.{{ .Release.Namespace }}:{{ .Values.filer.port }} \
-              {{- if .Values.s3.icebergPort }}
-              -port.iceberg={{ .Values.s3.icebergPort }} \
-              {{- end }}
+              -filer={{ include "seaweedfs.fullname" . }}-filer-client.{{ .Release.Namespace }}:{{ .Values.filer.port }} \
               {{- range .Values.s3.extraArgs }}
               {{ . }} \
               {{- end }}
@@ -195,10 +192,6 @@ spec:
             - containerPort: {{ .Values.s3.httpsPort }}
               name: swfs-s3-tls
             {{- end }}
-            {{- if .Values.s3.icebergPort }}
-            - containerPort: {{ .Values.s3.icebergPort }}
-              name: swfs-iceberg
-            {{- end }}
             {{- if .Values.s3.metricsPort }}
             - containerPort: {{ .Values.s3.metricsPort }}
               name: metrics

k8s/charts/seaweedfs/templates/s3/s3-iceberg-ingress.yaml

@@ -1,61 +0,0 @@
-{{- define "seaweedfs.s3.iceberg.ingress.paths" -}}
-paths:
-- path: {{ .Values.s3.icebergIngress.path | quote }}
-  pathType: {{ .Values.s3.icebergIngress.pathType | quote }}
-  backend:
-    {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
-    service:
-      name: {{ include "seaweedfs.componentName" (list . "s3") }}
-      port:
-        number: {{ .Values.s3.icebergPort }}
-    {{- else }}
-    serviceName: {{ include "seaweedfs.componentName" (list . "s3") }}
-    servicePort: {{ .Values.s3.icebergPort }}
-    {{- end }}
-{{- end -}}
-{{- if and .Values.s3.enabled .Values.s3.icebergPort .Values.s3.icebergIngress.enabled }}
-{{- $hosts := list }}
-{{- if kindIs "slice" .Values.s3.icebergIngress.host }}
-  {{- $hosts = .Values.s3.icebergIngress.host }}
-{{- else if .Values.s3.icebergIngress.host }}
-  {{- $hosts = list .Values.s3.icebergIngress.host }}
-{{- end }}
-{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
-apiVersion: networking.k8s.io/v1
-{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion }}
-apiVersion: networking.k8s.io/v1beta1
-{{- else }}
-apiVersion: extensions/v1beta1
-{{- end }}
-kind: Ingress
-metadata:
-  name: ingress-{{ include "seaweedfs.fullname" . }}-s3-iceberg
-  namespace: {{ .Release.Namespace }}
-  {{- with .Values.s3.icebergIngress.annotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
-  labels:
-    app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
-    app.kubernetes.io/component: s3-iceberg
-spec:
-  {{- if .Values.s3.icebergIngress.className }}
-  ingressClassName: {{ .Values.s3.icebergIngress.className | quote }}
-  {{- end }}
-  tls:
-    {{ .Values.s3.icebergIngress.tls | default list | toYaml | nindent 6}}
-  rules:
-{{- if $hosts }}
-{{- range $host := $hosts }}
-  - host: {{ $host | quote }}
-    http:
-      {{- include "seaweedfs.s3.iceberg.ingress.paths" $ | nindent 6 }}
-{{- end }}
-{{- else }}
-  - http:
-      {{- include "seaweedfs.s3.iceberg.ingress.paths" . | nindent 4 }}
-{{- end }}
-{{- end }}

k8s/charts/seaweedfs/templates/s3/s3-ingress.yaml

@@ -2,7 +2,7 @@
 {{- $s3Enabled := or .Values.s3.enabled (and .Values.filer.s3.enabled (not .Values.allInOne.enabled)) (and .Values.allInOne.enabled .Values.allInOne.s3.enabled) }}
 {{- if and $s3Enabled .Values.s3.ingress.enabled }}
 {{- /* Determine service name based on deployment mode */}}
-{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "s3")) .Values.allInOne.enabled }}
+{{- $serviceName := ternary (printf "%s-all-in-one" (include "seaweedfs.fullname" .)) (printf "%s-s3" (include "seaweedfs.fullname" .)) .Values.allInOne.enabled }}
 {{- $s3Port := .Values.allInOne.s3.port | default .Values.s3.port }}
 {{- /* Build hosts list - support both legacy .host (string) and new .hosts (array) for backwards compatibility */}}
 {{- $hosts := list }}

k8s/charts/seaweedfs/templates/s3/s3-secret.yaml

@@ -1,30 +1,14 @@
 {{- if or (and (or .Values.s3.enabled .Values.allInOne.enabled) .Values.s3.enableAuth (not .Values.s3.existingConfigSecret)) (and .Values.filer.s3.enabled .Values.filer.s3.enableAuth (not .Values.filer.s3.existingConfigSecret)) }}
 {{- $secretName := printf "%s-s3-secret" (include "seaweedfs.fullname" .) }}
-{{- $legacySecretName := "seaweedfs-s3-secret" }}
-{{- $lookupName := $secretName }}
-{{- if .Values.s3.reuseLegacySecret }}
-{{-   $lookupName = default $legacySecretName .Values.s3.legacySecretName }}
-{{- end }}
-{{- $existingSecret := lookup "v1" "Secret" .Release.Namespace $lookupName }}
+{{- $existingSecret := lookup "v1" "Secret" .Release.Namespace (default $secretName .Values.s3.legacySecretName) }}
 {{- $reuse := false }}
 {{- if and .Values.s3.reuseLegacySecret $existingSecret }}
 {{- $reuse = true }}
 {{- end }}
-{{- $creds := .Values.s3.credentials | default dict -}}
-{{- $adminCreds := $creds.admin | default dict -}}
-{{- $access_key_admin := $adminCreds.accessKey -}}
-{{- $secret_key_admin := $adminCreds.secretKey -}}
-{{- if not (and $access_key_admin $secret_key_admin) -}}
-  {{- $access_key_admin = include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "admin_access_key_id" "length" 20 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
-  {{- $secret_key_admin = include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "admin_secret_access_key" "length" 40 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
-{{- end -}}
-{{- $readCreds := $creds.read | default dict -}}
-{{- $access_key_read := $readCreds.accessKey -}}
-{{- $secret_key_read := $readCreds.secretKey -}}
-{{- if not (and $access_key_read $secret_key_read) -}}
-  {{- $access_key_read = include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "read_access_key_id" "length" 20 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
-  {{- $secret_key_read = include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "read_secret_access_key" "length" 40 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
-{{- end -}}
+{{- $access_key_admin := include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "admin_access_key_id" "length" 20 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
+{{- $secret_key_admin := include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "admin_secret_access_key" "length" 40 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
+{{- $access_key_read := include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "read_access_key_id" "length" 20 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
+{{- $secret_key_read := include "getOrGeneratePassword" (dict "namespace" .Release.Namespace "secretName" $secretName "key" "read_secret_access_key" "length" 40 "existingSecret" (ternary $existingSecret nil $reuse)) -}}
 apiVersion: v1
 kind: Secret
 type: Opaque
@@ -54,4 +38,4 @@ stringData:
   s3_auditLogConfig.json: |
     {{ toJson .Values.s3.auditLogConfig | nindent 4 }}
   {{- end }}
-{{- end }}
+{{- end }}

k8s/charts/seaweedfs/templates/s3/s3-service.yaml

@@ -9,27 +9,17 @@ metadata:
     app.kubernetes.io/component: s3
     helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
     app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
 {{- if .Values.s3.annotations }}
   annotations:
     {{- toYaml .Values.s3.annotations | nindent 4 }}
 {{- end }}
 spec:
   internalTrafficPolicy: {{ .Values.s3.internalTrafficPolicy | default "Cluster" }}
-  {{- if and (semverCompare ">=1.31-0" .Capabilities.KubeVersion.GitVersion) (or .Values.s3.trafficDistribution .Values.filer.s3.trafficDistribution) }}
-  trafficDistribution: {{ include "seaweedfs.trafficDistribution" . }}
-  {{- end }}
   ports:
   - name: "swfs-s3"
     port: {{ if .Values.s3.enabled }}{{ .Values.s3.port }}{{ else }}{{ .Values.filer.s3.port }}{{ end }}
     targetPort: {{ if .Values.s3.enabled }}{{ .Values.s3.port }}{{ else }}{{ .Values.filer.s3.port }}{{ end }}
     protocol: TCP
-{{- if and .Values.s3.enabled .Values.s3.icebergPort }}
-  - name: "swfs-iceberg"
-    port: {{ .Values.s3.icebergPort }}
-    targetPort: {{ .Values.s3.icebergPort }}
-    protocol: TCP
-{{- end }}
 {{- if and .Values.s3.enabled .Values.s3.httpsPort }}
   - name: "swfs-s3-tls"
     port: {{ .Values.s3.httpsPort }}

k8s/charts/seaweedfs/templates/sftp/sftp-deployment.yaml

@@ -171,7 +171,7 @@ spec:
               -key.file=/usr/local/share/ca-certificates/client/tls.key \
               {{- end }}
               -userStoreFile=/etc/sw/seaweedfs_sftp_config \
-              -filer={{ include "seaweedfs.componentName" (list . "filer-client") }}.{{ .Release.Namespace }}:{{ .Values.filer.port }}
+              -filer={{ include "seaweedfs.fullname" . }}-filer-client.{{ .Release.Namespace }}:{{ .Values.filer.port }}
           volumeMounts:
             {{- if or (eq .Values.sftp.logs.type "hostPath") (eq .Values.sftp.logs.type "emptyDir") }}
             - name: logs

k8s/charts/seaweedfs/templates/sftp/sftp-service.yaml

@@ -6,7 +6,6 @@ metadata:
   namespace: {{ .Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
     app.kubernetes.io/component: sftp
     helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
     app.kubernetes.io/managed-by: {{ .Release.Service }}

k8s/charts/seaweedfs/templates/shared/_helpers.tpl

@@ -17,22 +17,6 @@ be used as a full name.
 {{- end -}}
 {{- end -}}
 
-{{/*
-Create a truncated component name.
-Usage: {{ include "seaweedfs.componentName" (list . "component-suffix") }}
-*/}}
-{{- define "seaweedfs.componentName" -}}
-{{- $context := index . 0 -}}
-{{- $suffix := index . 1 -}}
-{{- if gt (len $suffix) 61 -}}
-{{-   fail (printf "Suffix '%s' is too long for componentName helper. Max length is 61." $suffix) -}}
-{{- end -}}
-{{- $fullname := include "seaweedfs.fullname" $context -}}
-{{- $maxLen := sub 62 (len $suffix) | int -}}
-{{- $truncatedFullname := trunc $maxLen $fullname | trimSuffix "-" -}}
-{{- printf "%s-%s" $truncatedFullname $suffix -}}
-{{- end -}}
-
 {{/*
 Create chart name and version as used by the chart label.
 */}}
@@ -135,9 +119,7 @@ Inject extra environment vars in the format key:value, if populated
 {{- $repositoryName := default .Values.image.repository .Values.global.repository | toString -}}
 {{- $name := .Values.global.imageName | toString -}}
 {{- $tag := default .Chart.AppVersion .Values.image.tag  | toString -}}
-{{- if .Values.image.repository -}}
-{{-   $name = $repositoryName -}}
-{{- else if $repositoryName -}}
+{{- if $repositoryName -}}
 {{-   $name = printf "%s/%s" (trimSuffix "/" $repositoryName) (base $name) -}}
 {{- end -}}
 {{- if $registryName -}}
@@ -279,7 +261,7 @@ If allInOne is enabled, point to the all-in-one service; otherwise, point to the
 {{- if .Values.allInOne.enabled -}}
 {{-   $serviceNameSuffix = "-all-in-one" -}}
 {{- end -}}
-{{- printf "%s.%s:%d" (printf "%s%s" (include "seaweedfs.fullname" .) $serviceNameSuffix | trunc 63 | trimSuffix "-") .Release.Namespace (int .Values.master.port) -}}
+{{- printf "%s%s.%s:%d" (include "seaweedfs.fullname" .) $serviceNameSuffix .Release.Namespace (int .Values.master.port) -}}
 {{- end -}}
 
 {{/*
@@ -291,19 +273,19 @@ If allInOne is enabled, point to the all-in-one service; otherwise, point to the
 {{- if .Values.allInOne.enabled -}}
 {{-   $serviceNameSuffix = "-all-in-one" -}}
 {{- end -}}
-{{- printf "%s.%s:%d" (printf "%s%s" (include "seaweedfs.fullname" .) $serviceNameSuffix | trunc 63 | trimSuffix "-") .Release.Namespace (int .Values.filer.port) -}}
+{{- printf "%s%s.%s:%d" (include "seaweedfs.fullname" .) $serviceNameSuffix .Release.Namespace (int .Values.filer.port) -}}
 {{- end -}}
 
 {{/*
 Generate comma-separated list of master server addresses.
 Usage: {{ include "seaweedfs.masterServers" . }}
-Output example: my-release-master-0.my-release-master.namespace:9333,my-release-master-1...
+Output example: ${SEAWEEDFS_FULLNAME}-master-0.${SEAWEEDFS_FULLNAME}-master.namespace:9333,${SEAWEEDFS_FULLNAME}-master-1...
 */}}
 {{- define "seaweedfs.masterServers" -}}
-{{- $masterName := include "seaweedfs.componentName" (list . "master") -}}
+{{- $fullname := include "seaweedfs.fullname" . -}}
 {{- range $index := until (.Values.master.replicas | int) -}}
 {{- if $index }},{{ end -}}
-{{ $masterName }}-{{ $index }}.{{ $masterName }}.{{ $.Release.Namespace }}:{{ $.Values.master.port }}
+${SEAWEEDFS_FULLNAME}-master-{{ $index }}.${SEAWEEDFS_FULLNAME}-master.{{ $.Release.Namespace }}:{{ $.Values.master.port }}
 {{- end -}}
 {{- end -}}
 
@@ -325,12 +307,3 @@ Create the name of the service account to use
 {{- define "seaweedfs.serviceAccountName" -}}
 {{- .Values.global.serviceAccountName | default "seaweedfs" -}}
 {{- end -}}
-
-{{/* Generate a compatible trafficDistribution value due to "PreferClose" fast deprecation in k8s v1.35 */}}
-{{- define "seaweedfs.trafficDistribution" -}}
-{{- if .Values.s3.trafficDistribution -}}
-{{- and (eq .Values.s3.trafficDistribution "PreferClose") (semverCompare ">=1.35-0" .Capabilities.KubeVersion.GitVersion) | ternary "PreferSameZone" .Values.s3.trafficDistribution -}}
-{{- else if .Values.filer.s3.trafficDistribution -}}
-{{- and (eq .Values.filer.s3.trafficDistribution "PreferClose") (semverCompare ">=1.35-0" .Capabilities.KubeVersion.GitVersion) | ternary "PreferSameZone" .Values.filer.s3.trafficDistribution -}}
-{{- end -}}
-{{- end -}}

k8s/charts/seaweedfs/templates/shared/post-install-bucket-hook.yaml

@@ -3,15 +3,6 @@
 {{- $s3Enabled := false }}
 {{- $enableAuth := false }}
 {{- $existingConfigSecret := "" }}
-{{- $bucketsFolder := "/buckets" }}
-{{- $bucketEnvVars := merge (dict) (.Values.global.extraEnvironmentVars | default dict) }}
-{{- if .Values.allInOne.enabled }}
-  {{- $bucketEnvVars = merge (.Values.allInOne.extraEnvironmentVars | default dict) $bucketEnvVars }}
-{{- else }}
-  {{- $bucketEnvVars = merge (.Values.filer.extraEnvironmentVars | default dict) $bucketEnvVars }}
-{{- end }}
-{{- $bucketsFolder = default $bucketsFolder (get $bucketEnvVars "WEED_FILER_BUCKETS_FOLDER") }}
-{{- $bucketsFolder = trimSuffix "/" $bucketsFolder }}
 
 {{- /* Check allInOne mode first */}}
 {{- if .Values.allInOne.enabled }}
@@ -24,18 +15,14 @@
     {{- $existingConfigSecret = or .Values.allInOne.s3.existingConfigSecret .Values.s3.existingConfigSecret .Values.filer.s3.existingConfigSecret }}
   {{- end }}
 {{- else if .Values.master.enabled }}
-  {{- /* Check if embedded (in filer) or standalone S3 gateway is enabled */}}
-  {{- if or .Values.filer.s3.enabled .Values.s3.enabled }}
+  {{- /* Check standalone filer.s3 mode */}}
+  {{- if .Values.filer.s3.enabled }}
     {{- $s3Enabled = true }}
-    {{- if .Values.s3.createBuckets }}
-      {{- $createBuckets = .Values.s3.createBuckets }}
-      {{- $enableAuth = .Values.s3.enableAuth }}
-      {{- $existingConfigSecret = .Values.s3.existingConfigSecret }}
-    {{- else if .Values.filer.s3.createBuckets }}
+    {{- if .Values.filer.s3.createBuckets }}
       {{- $createBuckets = .Values.filer.s3.createBuckets }}
-      {{- $enableAuth = .Values.filer.s3.enableAuth }}
-      {{- $existingConfigSecret = .Values.filer.s3.existingConfigSecret }}
     {{- end }}
+    {{- $enableAuth = .Values.filer.s3.enableAuth }}
+    {{- $existingConfigSecret = .Values.filer.s3.existingConfigSecret }}
   {{- end }}
 {{- end }}
 
@@ -49,7 +36,7 @@ metadata:
     app.kubernetes.io/managed-by: {{ .Release.Service | quote }}
     app.kubernetes.io/instance: {{ .Release.Name | quote }}
   annotations:
-    "helm.sh/hook": post-install,post-upgrade
+    "helm.sh/hook": post-install
     "helm.sh/hook-weight": "-5"
     "helm.sh/hook-delete-policy": hook-succeeded
 spec:
@@ -117,50 +104,10 @@ spec:
             wait_for_service "http://$WEED_CLUSTER_SW_MASTER{{ .Values.master.readinessProbe.httpGet.path }}"
             wait_for_service "http://$WEED_CLUSTER_SW_FILER{{ .Values.filer.readinessProbe.httpGet.path }}"
             {{- end }}
-          set -o pipefail
           {{- range $createBuckets }}
-            {{- $bucketName := .name }}
-            {{- $bucketLock := or .lock .objectLock .withLock }}
-            bucket_list=$(/bin/echo 's3.bucket.list' | /usr/bin/weed shell) || { echo "Error listing s3 buckets"; exit 1; }
-            if echo "$bucket_list" | awk '{print $1}' | grep -Fxq "{{ $bucketName }}"; then
-              echo "Bucket '{{ $bucketName }}' already exists, skipping creation."
-            else
-              echo "Creating bucket '{{ $bucketName }}'..."
-              /bin/echo 's3.bucket.create --name {{ $bucketName }}{{- if $bucketLock }} --withLock{{- end }}' | /usr/bin/weed shell
-            fi
-          {{- end }}
-          {{- range $createBuckets }}
-          {{- $bucketLock := or .lock .objectLock .withLock }}
-          {{- if $bucketLock }}
-            /bin/echo 's3.bucket.lock -name {{ .name }} -enable' | /usr/bin/weed shell
-          {{- end }}
-          {{- end }}
-          {{- range $createBuckets }}
-          {{- $bucketVersioning := "" }}
-          {{- if kindIs "bool" .versioning }}
-            {{- if .versioning }}
-              {{- $bucketVersioning = "Enabled" }}
-            {{- end }}
-          {{- else if kindIs "string" .versioning }}
-            {{- $versioningLower := lower .versioning }}
-            {{- if eq $versioningLower "enabled" "enable" "true" }}
-              {{- $bucketVersioning = "Enabled" }}
-            {{- else if eq $versioningLower "suspended" "disable" "false" }}
-              {{- $bucketVersioning = "Suspended" }}
-            {{- else if or (eq .versioning "Enabled") (eq .versioning "Suspended") }}
-              {{- $bucketVersioning = .versioning }}
-            {{- else }}
-              {{- fail (printf "Invalid versioning value for bucket %s: %s. Must be 'Enabled' or 'Suspended'" .name .versioning) }}
-            {{- end }}
-          {{- end }}
-          {{- if $bucketVersioning }}
-            /bin/echo 's3.bucket.versioning -name {{ .name }} -status {{ $bucketVersioning }}' | /usr/bin/weed shell
-          {{- end }}
-          {{- end }}
-          {{- range $createBuckets }}
-          {{- if .ttl }}
-            /bin/echo 'fs.configure -locationPrefix={{ $bucketsFolder }}/{{ .name }}/ -ttl={{ .ttl }} -apply' | /usr/bin/weed shell
-          {{- end }}
+            /bin/echo \
+            "s3.bucket.create --name {{ .name }}" |\
+            /usr/bin/weed shell
           {{- end }}
           {{- range $createBuckets }}
           {{- if .anonymousRead }}

k8s/charts/seaweedfs/templates/shared/secret-seaweedfs-db.yaml

@@ -15,6 +15,7 @@ metadata:
     app.kubernetes.io/instance: {{ .Release.Name }}
 stringData:
   user: "YourSWUser"
-  # auto-generated password
-  password: {{ randAlphaNum 10 | sha256sum | b64enc | trunc 32 }}
+  password: "HardCodedPassword"
+  # better to random generate and create in DB
+  # password: {{ randAlphaNum 10 | sha256sum | b64enc | trunc 32 }}
 {{- end }}

k8s/charts/seaweedfs/templates/shared/security-configmap.yaml

@@ -48,7 +48,7 @@ data:
     {{- if .Values.global.securityConfig.jwtSigning.filerRead }}
     # If this JWT key is configured, Filer only accepts reads over HTTP if they are signed with this JWT:
     # - f.e. the S3 API Shim generates the JWT
-    # - the Filer server validates the JWT on reading
+    # - the Filer server validates the JWT on writing
     # the jwt defaults to expire after 10 seconds.
     [jwt.filer_signing.read]
     key = "{{ dig "jwt" "filer_signing" "read" "key" (randAlphaNum 10 | b64enc) $securityConfig }}"

k8s/charts/seaweedfs/templates/shared/service-account.yaml

@@ -3,10 +3,6 @@ kind: ServiceAccount
 metadata:
   name: {{ include "seaweedfs.serviceAccountName" . }}
   namespace: {{ .Release.Namespace }}
-  {{- with .Values.global.serviceAccountAnnotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
     helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}

k8s/charts/seaweedfs/templates/volume/volume-ingress.yaml

@@ -42,11 +42,11 @@ spec:
         backend:
 {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
           service:
-            name: {{ include "seaweedfs.componentName" (list . "volume") }}
+            name: {{ include "seaweedfs.fullname" . }}-volume
             port:
               number: {{ .Values.volume.port }}
 {{- else }}
-          serviceName: {{ include "seaweedfs.componentName" (list . "volume") }}
+          serviceName: {{ include "seaweedfs.fullname" . }}-volume
           servicePort: {{ .Values.volume.port }}
 {{- end }}
 {{- end }}

k8s/charts/seaweedfs/templates/volume/volume-service.yaml

@@ -12,7 +12,6 @@ metadata:
   namespace: {{ $.Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" $ }}
-    app.kubernetes.io/instance: {{ $.Release.Name }}
     app.kubernetes.io/component: {{ $volumeName }}
     helm.sh/chart: {{ $.Chart.Name }}-{{ $.Chart.Version | replace "+" "_" }}
     app.kubernetes.io/managed-by: {{ $.Release.Service }}

k8s/charts/seaweedfs/templates/volume/volume-statefulset.yaml

@@ -8,7 +8,7 @@
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
-  name: {{ include "seaweedfs.componentName" (list $ $volumeName) }}
+  name: {{ include "seaweedfs.fullname" $ }}-{{ $volumeName }}
   namespace: {{ $.Release.Namespace }}
   labels:
     app.kubernetes.io/name: {{ template "seaweedfs.name" $ }}
@@ -21,7 +21,7 @@ metadata:
     {{- toYaml $volume.annotations | nindent 4 }}
 {{- end }}
 spec:
-  serviceName: {{ include "seaweedfs.componentName" (list $ $volumeName) }}
+  serviceName: {{ include "seaweedfs.fullname" $ }}-{{ $volumeName }}
   replicas: {{ $volume.replicas }}
   podManagementPolicy: {{ $volume.podManagementPolicy }}
   selector:
@@ -197,7 +197,7 @@ spec:
                 -fileSizeLimitMB={{ $volume.fileSizeLimitMB }} \
                 {{- end }}
                 -minFreeSpacePercent={{ $volume.minFreeSpacePercent }} \
-                -ip=${POD_NAME}.{{ include "seaweedfs.componentName" (list $ $volumeName) }}.{{ $.Release.Namespace }} \
+                -ip=${POD_NAME}.${SEAWEEDFS_FULLNAME}-{{ $volumeName }}.{{ $.Release.Namespace }} \
                 -compactionMBps={{ $volume.compactionMBps }} \
                 -master={{ include "seaweedfs.masterServerArg" $ }} \
                 {{- range $volume.extraArgs }}

k8s/charts/seaweedfs/templates/worker/worker-deployment.yaml

@@ -134,17 +134,13 @@ spec:
               {{- if .Values.worker.adminServer }}
               -admin={{ .Values.worker.adminServer }} \
               {{- else }}
-              -admin={{ template "seaweedfs.fullname" . }}-admin.{{ .Release.Namespace }}:{{ .Values.admin.port }}{{ if .Values.admin.grpcPort }}.{{ .Values.admin.grpcPort }}{{ end }} \
+              -admin={{ template "seaweedfs.name" . }}-admin.{{ .Release.Namespace }}:{{ .Values.admin.port }}{{ if .Values.admin.grpcPort }}.{{ .Values.admin.grpcPort }}{{ end }} \
               {{- end }}
-              -jobType={{ .Values.worker.jobType }} \
-              -maxDetect={{ .Values.worker.maxDetect }} \
-              -maxExecute={{ .Values.worker.maxExecute }} \
-              -workingDir={{ .Values.worker.workingDir }}{{- if or .Values.worker.metricsPort .Values.worker.metricsIp .Values.worker.extraArgs }} \{{ end }}
+              -capabilities={{ .Values.worker.capabilities }} \
+              -maxConcurrent={{ .Values.worker.maxConcurrent }} \
+              -workingDir={{ .Values.worker.workingDir }}{{- if or .Values.worker.metricsPort .Values.worker.extraArgs }} \{{ end }}
               {{- if .Values.worker.metricsPort }}
-              -metricsPort={{ .Values.worker.metricsPort }}{{- if or .Values.worker.metricsIp .Values.worker.extraArgs }} \{{ end }}
-              {{- end }}
-              {{- if .Values.worker.metricsIp }}
-              -metricsIp={{ .Values.worker.metricsIp }}{{- if .Values.worker.extraArgs }} \{{ end }}
+              -metricsPort={{ .Values.worker.metricsPort }}{{- if .Values.worker.extraArgs }} \{{ end }}
               {{- end }}
               {{- range $index, $arg := .Values.worker.extraArgs }}
               {{ $arg }}{{- if lt $index (sub (len $.Values.worker.extraArgs) 1) }} \{{ end }}

k8s/charts/seaweedfs/values.yaml

@@ -20,7 +20,6 @@ global:
       filerRead: false
   # we will use this serviceAccountName for all ClusterRoles/ClusterRoleBindings
   serviceAccountName: "seaweedfs"
-  serviceAccountAnnotations: {}
   automountServiceAccountToken: true
   certificates:
     duration: 87600h
@@ -891,22 +890,12 @@ filer:
     # set to the name of an existing kubernetes Secret with the s3 json config file
     # should have a secret key called seaweedfs_s3_config with an inline json configure
     existingConfigSecret: null
-    # To provide explicit credentials for the S3 gateway, set them under
-    # the top-level s3.credentials key (not filer.s3.credentials).
-    # The s3-secret.yaml template only reads from .Values.s3.credentials.
-    # See: s3.credentials.admin.accessKey, s3.credentials.read.accessKey
     auditLogConfig: {}
-    # You may specify buckets to be created during the install or upgrade process.
+    # You may specify buckets to be created during the install process.
     # Buckets may be exposed publicly by setting `anonymousRead` to `true`
-    # ttl format: [1-255][m|h|d|w|M|y] (e.g., 7d)
-    # objectLock enables S3 Object Lock (irreversible, forces versioning)
-    # versioning: Enabled or Suspended (or true to enable)
     # createBuckets:
     #   - name: bucket-a
     #     anonymousRead: true
-    #     ttl: 7d
-    #     objectLock: true
-    #     versioning: Enabled
     #   - name: bucket-b
     #     anonymousRead: false
 
@@ -920,39 +909,13 @@ s3:
   # add additional https port
   httpsPort: 0
   metricsPort: 9327
-  # Iceberg catalog REST port (Apache Iceberg REST Catalog API)
-  # Set to a port number to enable, or 0/null to disable
-  icebergPort: null
   loggingOverrideLevel: null
   # enable user & permission to s3 (need to inject to all services)
   enableAuth: false
   # set to the name of an existing kubernetes Secret with the s3 json config file
   # should have a secret key called seaweedfs_s3_config with an inline json config
   existingConfigSecret: null
-  # Optionally provide explicit credentials for the S3 gateway.
-  # When set, these are used in the generated s3 secret instead of
-  # auto-generating random credentials.
-  # credentials:
-  #   admin:
-  #     accessKey: ""
-  #     secretKey: ""
-  #   read:
-  #     accessKey: ""
-  #     secretKey: ""
   auditLogConfig: {}
-  # You may specify buckets to be created during the install or upgrade process.
-  # Buckets may be exposed publicly by setting `anonymousRead` to `true`
-  # ttl format: [1-255][m|h|d|w|M|y] (e.g., 7d)
-  # objectLock enables S3 Object Lock (irreversible, forces versioning)
-  # versioning: Enabled or Suspended (or true to enable)
-  # createBuckets:
-  #   - name: bucket-a
-  #     anonymousRead: true
-  #     ttl: 7d
-  #     objectLock: true
-  #     versioning: Enabled
-  #   - name: bucket-b
-  #     anonymousRead: false
 
   # Suffix of the host name, {bucket}.{domainName}
   domainName: ""
@@ -1080,15 +1043,6 @@ s3:
     annotations: {}
     tls: []
 
-  icebergIngress:
-    enabled: false
-    className: ""
-    host: "seaweedfs-iceberg.cluster.local"
-    path: "/"
-    pathType: Prefix
-    annotations: {}
-    tls: []
-
 sftp:
   enabled: false
   imageOverride: null
@@ -1297,20 +1251,17 @@ worker:
   replicas: 1
   loggingOverrideLevel: null
   metricsPort: 9327
-  metricsIp: ""  # If empty, defaults to 0.0.0.0
 
   # 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 capabilities - comma-separated list
+  # Available: vacuum, balance, erasure_coding
+  # Default: "vacuum,balance,erasure_coding" (all capabilities)
+  capabilities: "vacuum,balance,erasure_coding"
 
-  # Maximum number of concurrent detection requests
-  maxDetect: 1
-
-  # Maximum number of concurrent execution jobs
-  maxExecute: 4
+  # Maximum number of concurrent tasks
+  maxConcurrent: 3
 
   # Working directory for task execution
   workingDir: "/tmp/seaweedfs-worker"
@@ -1448,22 +1399,12 @@ allInOne:
     # Set to the name of an existing kubernetes Secret with the s3 json config file
     # should have a secret key called seaweedfs_s3_config with an inline json config
     existingConfigSecret: null
-    # To provide explicit credentials for the S3 gateway, set them under
-    # the top-level s3.credentials key (not allInOne.s3.credentials).
-    # The s3-secret.yaml template only reads from .Values.s3.credentials.
-    # See: s3.credentials.admin.accessKey, s3.credentials.read.accessKey
     auditLogConfig: null  # S3 audit log configuration (null inherits from s3.auditLogConfig)
     # You may specify buckets to be created during the install process.
     # Buckets may be exposed publicly by setting `anonymousRead` to `true`
-    # ttl format: [1-255][m|h|d|w|M|y] (e.g., 7d)
-    # objectLock enables S3 Object Lock (irreversible, forces versioning)
-    # versioning: Enabled or Suspended (or true to enable)
     # createBuckets:
     #   - name: bucket-a
     #     anonymousRead: true
-    #     ttl: 7d
-    #     objectLock: true
-    #     versioning: Enabled
     #   - name: bucket-b
     #     anonymousRead: false
 
@@ -1629,8 +1570,6 @@ cosi:
   image: "ghcr.io/seaweedfs/seaweedfs-cosi-driver:v0.1.2"
   driverName: "seaweedfs.objectstorage.k8s.io"
   bucketClassName: "seaweedfs"
-  # Optional parameters to pass to the default BucketClass (e.g., diskType for tiered storage)
-  bucketClassParameters: {}
   endpoint: ""
   region: ""
 

learn/projects/sw-block/phases/phase-5-dev-log.md

@@ -1,104 +0,0 @@
-# Phase 5 Dev Log
-
-Append-only communication between agents. Newest entries at bottom.
-Each entry: `[date] [role] message`
-
-Roles: `DEV`, `REVIEWER`, `TESTER`, `ARCHITECT`
-
----
-
-[2026-03-03] [DEV] CP5-1 ALUA + multipath complete. Added ALUA provider + REPORT TPG (implicit ALUA), VPD 0x83
-NAA+TPG+RTP descriptors, TPGS=01 in INQUIRY, standby write fencing, and -tpg-id flag. Added UUID to VolumeInfo for
-shared NAA. Added multipath config and setup script. 4 multipath integration tests added. 10 ALUA unit tests added
-(SCSI tests total 53). Reviewer fixes applied: RoleNone maps to Active/Optimized to avoid single-node regression;
-REPORT TPG advertises T_SUP when state is Transitioning; TPG ID validation; non-ASCII log fix. Added 2 tests:
-alua_role_none_allows_writes and alua_report_tpg_transitioning. All unit tests pass, Linux cross-compile verified.
-
-[2026-03-03] [TESTER] CP5-1 adversarial suite: 16 tests added/validated (state boundaries, VPD 0x83, REPORT TPG,
-concurrency, INQUIRY invariants). All 16 PASS. No regressions in engine + iSCSI tests.
-
-[2026-03-03] [DEV] CP5-2 CoW snapshots completed. Fixes applied from review: DeleteSnapshot pauses flusher before
-closing delta; RestoreSnapshot checks PauseAndFlush error + defers Resume; CreateSnapshot holds snapMu across check/insert;
-Delete/Restore use beginOp/endOp; lock order documented (flushMu -> snapMu); non-ASCII punctuation removed; persistSuperblock
-now returns error and callers propagate. All tests passing (known pre-existing flaky
-rebuild_full_extent_midcopy_writes under full-suite load).
-
-[2026-03-03] [TESTER] CP5-2 QA adversarial suite: 22 tests in 5 groups (races, role rejection, edge cases, lifecycle,
-restore correctness) all PASS. Confirms fixes for delete_during_flush_cow, concurrent_create_same_id, and restore path
-nextLSN reset.
-
-[2026-03-03] [DEV] CP5-3 implementation complete. CHAP: ValidateCHAPConfig with ErrCHAPSecretEmpty and CLI guard
-requires -chap-secret when -chap-user is set. Login SecurityNeg echoes AuthMethod=CHAP on second PDU after verify; test
-assertion added. Metrics adapter docs clarify counters count attempts; /metrics inherits admin auth noted in header
-comment. All CP5-3 tests pass; only pre-existing flaky rebuild_catchup_concurrent_writes observed under full suite.
-
-[2026-03-03] [TESTER] CP5-3 QA adversarial: 28 tests added (16 CHAP + 12 resize) all PASS. No new bugs. Full
-regression clean except pre-existing flaky rebuild_catchup_concurrent_writes.
-
-[2026-03-03] [TESTER] Failover latency probe (10 iterations, m01->M02) shows bimodal iSCSI login time dominates pause.
-Promote avg 16ms (8-20ms), FirstIO avg 12ms (6-19ms), login avg 552ms with bimodal split (~130-180ms vs ~1170ms).
-Total avg 588ms, min 99ms, max/P99 1217ms. Conclusion: storage path is fast; pause is iSCSI client reconnect.
-Multipath should keep failover near ~100-200ms; otherwise tune open-iscsi/login timeout and avoid stale portals.
-
-[2026-03-03] [DEV] CP5-4 failure injection + distributed consistency tests implemented. 5 new files:
-- `test/fault_test.go` — 7 failure injection tests (F1-F7)
-- `test/fault_helpers.go` — netem, iptables, diskfill, WAL corrupt helpers
-- `test/consistency_test.go` — 17 distributed consistency tests (C1-C17)
-- `test/pgcrash_test.go` — Postgres crash loop (50 iterations, replicated failover)
-- `test/pg_helper.go` — Postgres lifecycle helper (initdb, start, stop, pgbench, mount)
-
-Port assignments: iSCSI 3280-3281, admin 8100-8101, replData 9031, replCtrl 9032 (fault/consistency);
-iSCSI 3290-3291, admin 8110-8111, replData 9041, replCtrl 9042 (pgcrash).
-
-[2026-03-03] [TESTER] CP5-4 QA on m01/M02 remote environment. Multiple issues found and fixed:
-
-**BUG-CP54-1: Lease expiry during PgCrashLoop bootstrap** — 30s lease too short for initdb+pgbench
-(which generate hundreds of fsyncs through distributed group commit). Postgres PANIC after exactly 30s.
-Fix: increased bootstrap lease to 600000ms (10min), iteration leases to 120000ms (2min).
-
-**BUG-CP54-2: SCP volume copy auth failure** — pgcrash_test.go hardcoded `id_rsa` SSH key path.
-Fix: use `clientNode.KeyFile` and `*flagSSHUser` for cross-node scp.
-
-**BUG-CP54-3: Replica volume file permission denied** — scp as root created root-owned file,
-but iscsi-target runs as testdev. Fix: added `chown` after scp.
-
-**BUG-CP54-4: C2 EpochMonotonicThreePromotions data mismatch** — dd with `oflag=direct` doesn't
-issue SYNCHRONIZE CACHE, so WAL buffer not fsync'd before kill-9. Data lost on restart.
-Fix: added `conv=fdatasync` to dd writes in C2 test.
-
-**BUG-CP54-5: PG start failure on promoted replica** — WAL shipper degrades under pgbench fdatasync
-pressure (5s barrier timeout too short for burst writes). Promoted replica has incomplete PG data.
-Fix: added `e2fsck -y` before mount in pg_helper.go; made pg start failures non-fatal with
-mkfs+initdb reinit fallback.
-
-**BUG-CP54-6: pgbench_branches relation missing after failover** — Data divergence from degraded
-replication left pgbench database with missing tables. Fix: added dropdb+recreate fallback when
-pgbench init fails.
-
-Final combined run: **25/25 ALL PASS** (994.8s total on m01/M02):
-- TestConsistency: 17/17 PASS (194.6s)
-- TestFault: 7/7 PASS (75.5s)
-- TestPgCrashLoop: PASS — 48/49 recovered, 1 reinit (723.9s)
-
-Known limitation: WAL shipper barrier timeout (5s) causes degradation under heavy fdatasync
-workloads (pgbench). Data divergence occurs on ~50% of failovers without full rebuild between
-role swaps. This is expected behavior — production deployments would use a master-driven rebuild
-after each failover.
-
-[2026-03-03] [TESTER] CP5-4 QA review identified gap: no clean failover test proving PG data
-survives with volume-copy replication. Added `CleanFailoverNoDataLoss` test to pgcrash_test.go:
-- Bootstrap 500 rows on primary (no replication — avoids WAL shipper degradation from PG background writes)
-- Copy volume to replica, set up replication, verify with lightweight dd write
-- Kill primary, promote replica, start PG on promoted replica
-- Verify: 500 rows intact, content correct (first="row-1", last="row-500"), post-failover INSERT works
-- Proves full stack: PG → ext4 → iSCSI → BlockVol → volume copy → failover → WAL recovery → ext4 → PG recovery
-
-Design note: PG cannot run under active replication without degrading the WAL shipper (background
-checkpointer/WAL writer generate continuous iSCSI writes that hit 5s barrier timeout). The test
-separates data creation (bootstrap without replication) from replication verification (dd only).
-
-Final combined run with CleanFailoverNoDataLoss: **26/26 ALL PASS** (1067.7s total on m01/M02):
-- TestConsistency: 17/17 PASS (194.7s)
-- TestFault: 7/7 PASS (75.6s)
-- TestPgCrashLoop/CleanFailoverNoDataLoss: PASS (90.3s)
-- TestPgCrashLoop/ReplicatedFailover50: PASS — 48/49 recovered, 1 reinit (706.3s)

learn/projects/sw-block/phases/phase-5-progress.md

@@ -1,80 +0,0 @@
-# Phase 5 Progress
-
-## Status
-- CP5-1 through CP5-4 complete. Phase 5 DONE.
-
-## Completed
-- CP5-1: ALUA implicit support, REPORT TARGET PORT GROUPS, VPD 0x83 descriptors, write fencing on standby.
-- CP5-1: Multipath config + setup script, 4 multipath integration tests.
-- CP5-1: Reviewer fixes (RoleNone write regression, T_SUP flag, TPG ID validation, ASCII log).
-- CP5-1: 10 ALUA unit tests + 16 adversarial tests (all PASS).
-- CP5-2: CoW snapshots implemented with flusher-based CoW, delta files, and recovery.
-- CP5-2: Review fixes applied (PauseAndFlush safety, snapMu race fix, beginOp/endOp, lock order doc, error propagation).
-- CP5-2: 10 unit tests + 22 adversarial tests (all PASS).
-- CP5-3: CHAP auth, online resize, Prometheus metrics, admin endpoints.
-- CP5-3: Review fixes applied (empty secret validation, AuthMethod echo, docs).
-- CP5-3: 12 dev tests + 28 QA adversarial tests (all PASS).
-- CP5-4: Failure injection (7 tests) + distributed consistency (17 tests) + Postgres crash loop (50 iters).
-- CP5-4: 6 bugs found and fixed (lease expiry, scp auth, permissions, fdatasync, pg reinit, pgbench tables).
-- CP5-4: 26/26 tests ALL PASS on m01/M02 remote environment (1067.7s combined).
-- CP5-4: Added CleanFailoverNoDataLoss (500 PG rows survive failover via volume copy).
-
-## In Progress
-- None.
-
-## Blockers
-- None.
-
-## Next Steps
-- Phase 5 complete. Ready for Phase 6 (NVMe-oF) or other priorities.
-
-## Notes
-- SCSI test count: 53 (12 ALUA). Integration multipath tests require multipath-tools + sg3_utils.
-- Known flaky: rebuild_full_extent_midcopy_writes under full-suite CPU contention (pre-existing).
-- Known flaky: rebuild_catchup_concurrent_writes (WAL_RECYCLED timing, pre-existing).
-- Known limitation: WAL shipper barrier timeout (5s) causes degradation under heavy fdatasync
-  workloads. PgCrashLoop shows ~50% data divergence per failover without full rebuild. Expected
-  behavior — production would use master-driven rebuild after each failover.
-- Failover latency probe (10 iters): promote+first I/O ~30ms; total pause dominated by iSCSI
-  login (avg 552ms, bimodal 130-180ms vs ~1170ms). Multipath should keep pause near 100-200ms;
-  otherwise tune open-iscsi login timeout and avoid stale portals.
-
-## CP5-4 Test Catalog
-
-### Failure Injection (`test/fault_test.go`)
-| ID | Test | What it proves |
-|----|------|----------------|
-| F1 | PowerLossDuringFio | fdatasync'd data survives kill-9 + failover |
-| F2 | DiskFullENOSPC | reads survive ENOSPC, writes recover after space freed |
-| F3 | WALCorruption | WAL recovery discards corrupted tail, early data intact |
-| F4 | ReplicaDownDuringWrites | primary keeps serving after replica crash mid-write |
-| F5 | SlowNetworkBarrierTimeout | writes continue under 200ms netem delay (remote only) |
-| F6 | NetworkPartitionSelfFence | primary self-fences on iptables partition (remote only) |
-| F7 | SnapshotDuringFailover | snapshot + replication interaction, both patterns survive |
-
-### Distributed Consistency (`test/consistency_test.go`)
-| ID | Test | What it proves |
-|----|------|----------------|
-| C1 | EpochPersistedOnPromotion | epoch survives kill-9 + restart (superblock persistence) |
-| C2 | EpochMonotonicThreePromotions | 3 failovers, epoch 1→2→3, data from all phases intact |
-| C3 | StaleEpochWALRejected | replica at epoch=2 rejects WAL entries from epoch=1 |
-| C4 | LeaseExpiredWriteRejected | writes fail after lease expiry |
-| C5 | LeaseRenewalUnderJitter | lease survives 100ms netem jitter with 30s TTL (remote) |
-| C6 | PromotionDataIntegrityChecksum | 10MB byte-for-byte match after failover |
-| C7 | PromotionPostgresRecovery | postgres recovers from crash (single-node, no repl) |
-| C8 | DeadZoneNoWrites | fencing gap verified between old/new primary |
-| C9 | RebuildWALCatchup | WAL catch-up rebuild after brief replica outage |
-| C10 | RebuildFullExtent | full extent rebuild after heavy writes |
-| C11 | RebuildDuringActiveWrites | fio uninterrupted during rebuild |
-| C12 | GracefulDemoteNoDataLoss | data intact after demote + re-promote |
-| C13 | RapidRoleFlip10x | 10 rapid epoch bumps, no crash or panic |
-| C14 | LeaseTimerRealExpiry | lease transitions true→false at ~5s mark |
-| C15 | DistGroupCommitEndToEnd | replica WAL advances during fdatasync fio |
-| C16 | DistGroupCommitReplicaCrash | primary continues in degraded mode |
-| C17 | DistGroupCommitBarrierVerify | replica LSN >= primary after fdatasync |
-
-### Postgres Crash Loop (`test/pgcrash_test.go`)
-| ID | Test | What it proves |
-|----|------|----------------|
-| PG1 | CleanFailoverNoDataLoss | 500 PG rows survive volume-copy failover, content verified |
-| PG2 | ReplicatedFailover50 | 49 kill→promote→recover→pgbench cycles, PG recovers |

learn/projects/sw-block/phases/phase-6-dev-log.md

@@ -1,202 +0,0 @@
-# Phase 6 Dev Log
-
-Append-only communication between agents. Newest entries at bottom.
-Each entry: `[date] [role] message`
-
-Roles: `DEV`, `REVIEWER`, `TESTER`, `ARCHITECT`
-
----
-
-[2026-03-03] [DEV] CP6-1 implementation complete. 7 tasks (Task 0-6) delivered:
-- Task 0: Extracted BlockVolAdapter to shared `blockvol/adapter.go` (exported fields, ALUA methods,
-  RoleToALUA/UUIDToNAA helpers). Added DisconnectVolume(iqn) to TargetServer (kills sessions + removes
-  volume). Added Session.TargetIQN() accessor. Updated standalone binary to use shared adapter. 3 adapter tests.
-- Task 1: VolumeManager -- multi-volume BlockVol + shared TargetServer lifecycle. sync.Once start guard,
-  atomic ready flag, IQN sanitization with hash suffix for collision avoidance. 10 tests.
-- Task 2: CSI Identity service (GetPluginInfo, GetPluginCapabilities, Probe). 3 tests.
-- Task 3: CSI Controller service (CreateVolume with idempotency + size mismatch, DeleteVolume). 4 tests.
-- Task 4: CSI Node service (Stage/Unstage/Publish/Unpublish) with ISCSIUtil/MountUtil interfaces. 7 tests.
-- Task 5: gRPC server + binary entry point (unix/tcp socket, signal handler, graceful shutdown).
-- Task 6: K8s manifests (DaemonSet, StorageClass, RBAC, example PVC) + smoke-test.sh.
-Total: 12 new Go files, 2 modified, 4 YAML, 1 shell script, 25+3=28 tests. CSI spec v1.10.0 added.
-
-[2026-03-03] [REVIEWER] CP6-1 review returned 5 findings:
-1. (High) CreateVolume not idempotent after restart -- only checks in-memory map, misses existing .blk files.
-2. (Medium) NodePublishVolume doesn't validate empty StagingTargetPath.
-3. (Medium) NodeStageVolume resource leak -- OpenVolume not cleaned up on discovery/login/mount failure.
-4. (Medium) Target start race -- ListenAndServe in goroutine, ready=true set before bind confirmed.
-5. (Low) IQN collision -- truncation without hash suffix causes identical IQNs for long names.
-Open Q1: How should CreateVolume handle pre-existing .blk files on disk?
-Open Q2: What happens in NodeUnstageVolume if unmount succeeds but logout fails?
-
-[2026-03-03] [DEV] All 5 review findings + 2 open questions resolved:
-- Finding 1: CreateVolume now checks os.Stat for existing .blk files, adopts via OpenBlockVol.
-  Added ErrVolumeSizeMismatch. Controller maps it to codes.AlreadyExists.
-- Finding 2: Added stagingPath=="" check in NodePublishVolume returning InvalidArgument.
-- Finding 3: Added success flag + deferred CloseVolume after OpenVolume in NodeStageVolume.
-- Finding 4: Listener created synchronously via net.Listen before ready=true. Serve in goroutine.
-- Finding 5: SanitizeIQN appends SHA256 hash suffix (8 hex chars) when truncating to 64.
-- Open Q1: Pre-existing files adopted as idempotent success if size >= requested.
-- Open Q2: NodeUnstageVolume uses best-effort cleanup (firstErr pattern), always attempts CloseVolume.
-3 new tests: CreateIdempotentAfterRestart, IQNCollision, StageLoginFailureCleanup, PublishMissingStagingPath.
-All 25 CSI tests + full regression PASS.
-
-[2026-03-03] [TESTER] CP6-1 QA adversarial suite: 30 tests in qa_csi_test.go. 26 PASS, 4 FAIL confirming 5 bugs.
-Groups: QA-VM (8), QA-CTRL (5), QA-NODE (7), QA-SRV (3), QA-ID (1), QA-IQN (5), QA-X (1).
-Bugs: BUG-QA-1 snapshot leak, BUG-QA-2/3 sync.Once restart, BUG-QA-4 LimitBytes ignored, BUG-QA-5 case divergence.
-
-[2026-03-03] [DEV] All 5 QA bugs fixed:
-- BUG-QA-1: DeleteVolume now globs+removes volPath+".snap.*" (both tracked and untracked paths).
-- BUG-QA-2+3: Replaced sync.Once+atomic.Bool with managerState enum (stopped/starting/ready/failed).
-  Start() retryable after failure or Stop(). Stop() sets state=stopped, nils target.
-  Goroutine captures target locally before launch (prevents nil deref after Stop).
-- BUG-QA-4: Controller CreateVolume validates LimitBytes. When RequiredBytes=0 and LimitBytes set,
-  uses LimitBytes as target size. Rejects RequiredBytes > LimitBytes and post-rounding overflow.
-- BUG-QA-5: sanitizeFilename now lowercases (matching SanitizeIQN). "VolA" and "vola" produce
-  same file and same IQN — treated as same volume via file adoption path.
-- QA-CTRL-4 test updated from bug-detection to behavior-documentation (NotFound is by design;
-  volumes re-tracked via CreateVolume after restart).
-All 54 CSI tests + full regression PASS (blockvol 63s, iscsi 2.3s, csi 0.4s).
-
-[2026-03-03] [DEV] CP6-2 complete. See separate CP6-2 entries in progress.md.
-
-[2026-03-04] [TESTER] CSI Testing Ladder Levels 2-4 complete on M02 (192.168.1.184):
-
-**Level 2: csi-sanity gRPC Conformance**
-- cross-compiled block-csi (linux/amd64), installed csi-sanity on M02
-- Result: 33 Passed, 0 Failed, 58 Skipped (optional RPCs), 1 Pending
-- 6 bugs found and fixed: empty VolumeCapabilities validation (3 RPCs), bind mount for NodePublish,
-  target path removal in NodeUnpublish, IsMounted check before unmount
-- All 226 unit tests updated with VolumeCapabilities/VolumeCapability in requests
-
-**Level 3: Integration Smoke**
-- Verified via csi-sanity's "should work" tests exercising real iSCSI on M02
-- 489 real SCSI commands processed (READ_10, WRITE_10, SYNC_CACHE, INQUIRY, etc.)
-- Full lifecycle: Create → Stage (discovery+login+mkfs+mount) → Publish → Unpublish → Unstage (unmount+logout) → Delete
-- Clean state: no leftover sessions, mounts, or volume files
-
-**Level 4: k3s PVC→Pod**
-- Installed k3s v1.34.4 on M02, deployed CSI DaemonSet (block-csi + csi-provisioner + registrar)
-- DaemonSet uses nsenter wrappers for host iscsiadm/mount/umount/blkid/mountpoint/mkfs.ext4
-- Test: PVC (100Mi) → Pod writes "hello sw-block" → md5 7be761488cf480c966077c7aca4ea3ed
-  → Pod deleted → PVC retained → New pod reads same data → PASS
-- 1 additional bug: IsLoggedIn didn't handle iscsiadm exit code 21 (nsenter suppresses output)
-  → Fixed by checking ExitError.ExitCode() == 21 directly
-
-Code changes from Levels 2-4:
-- controller.go: +VolumeCapabilities validation in CreateVolume, ValidateVolumeCapabilities
-- node.go: +VolumeCapability nil check, BindMount for publish, IsMounted+RemoveAll in unpublish
-- iscsi_util.go: +BindMount interface+impl (real+mock), IsLoggedIn exit code 21 handling
-- controller_test.go, node_test.go, qa_csi_test.go, qa_cp62_test.go: testVolCaps()/testVolCap() helpers
-
-[2026-03-04] [DEV] CP6-3 Review 1+2 findings fixed (12 total, 5 High, 5 Medium, 2 Low):
-- R1-1 (High): AllocateBlockVolume now returns ReplicaDataAddr/CtrlAddr/RebuildListenAddr from ReplicationPorts().
-- R1-2 (High): setupPrimaryReplication now calls vol.StartRebuildServer(rebuildAddr) with deterministic port.
-- R1-3 (High): VS sends periodic full block heartbeat (5×sleepInterval) enabling assignment confirmation.
-- R2-F1 (High): LastLeaseGrant moved to entry initializer before Register (was after → stale-lease race).
-- R1-4 (Medium): BlockService.CollectBlockVolumeHeartbeat fills ReplicaDataAddr/CtrlAddr from replStates.
-- R1-5 (Medium): UpdateFullHeartbeat refreshes LastLeaseGrant on every heartbeat.
-- R2-F2 (Medium): Deferred promotion timers stored and cancelled on VS reconnect (prevents split-brain).
-- R2-F3 (Medium): SwapPrimaryReplica uses blockvol.RoleToWire(blockvol.RolePrimary) instead of uint32(1).
-- R2-F4 (Medium): DeleteBlockVolume now deletes replica (best-effort, non-fatal).
-- R2-F5 (Medium): SwapPrimaryReplica computes epoch+1 atomically inside lock, returns newEpoch.
-- R2-F6 (Low): Removed redundant string(server) casts.
-- R2-F7 (Low): Documented rebuild feedback as future work.
-All 293 tests PASS: blockvol (24s), csi (1.6s), iscsi (2.6s), server (3.3s).
-
-[2026-03-04] [DEV] CP6-3 implementation complete. 8 tasks (Task 0-7) delivered:
-- Task 0: Proto extension — replica/rebuild address fields in master.proto, volume_server.proto,
-  generated pb.go files, wire types, converters. AssignmentsToProto batch helper. 8 tests.
-- Task 1: Assignment queue — BlockAssignmentQueue with retain-until-confirmed (F1).
-  Enqueue/Peek/Confirm/ConfirmFromHeartbeat. Stale epoch pruning. Wired into HeartbeatResponse. 11 tests.
-- Task 2: VS assignment receiver — extracts block_volume_assignments from HeartbeatResponse,
-  calls BlockService.ProcessAssignments.
-- Task 3: BlockService replication — ProcessAssignments dispatches HandleAssignment +
-  setupPrimaryReplication/setupReplicaReceiver/startRebuild. Deterministic ports via FNV hash (F3).
-  Heartbeat reports replica addresses (F5). 9 tests.
-- Task 4: Registry replica + CreateVolume — SetReplica/ClearReplica/SwapPrimaryReplica.
-  CreateBlockVolume creates primary + replica, enqueues assignments. Single-copy mode (F4). 10 tests.
-- Task 5: Failover — failoverBlockVolumes on VS disconnect. Lease-aware promotion (F2):
-  promote only after lease expires, deferred via time.AfterFunc. SwapPrimaryReplica + epoch bump.
-  11 failover tests.
-- Task 6: ControllerPublish — ControllerPublishVolume returns fresh primary address via LookupVolume.
-  ControllerUnpublishVolume no-op. PUBLISH_UNPUBLISH_VOLUME capability. NodeStageVolume prefers
-  publish_context over volume_context. 8 tests.
-- Task 7: Rebuild on recovery — recoverBlockVolumes on VS reconnect drains pendingRebuilds,
-  enqueues Rebuilding assignments. 10 tests (shared file with Task 5).
-Total: 4 new files, ~15 modified, 67 new tests. All 5 review findings (F1-F5) addressed.
-All tests PASS: blockvol (43s), csi (1.4s), iscsi (2.5s), server (3.2s).
-Cumulative Phase 6: 293 tests.
-
-[2026-03-04] [TESTER] CP6-3 QA adversarial suite: 48 tests in qa_block_cp63_test.go. 47 PASS, 1 FAIL confirming 1 bug.
-Groups: QA-Queue (8), QA-Reg (7), QA-Failover (7), QA-Create (5), QA-Rebuild (3), QA-Integration (2), QA-Edge (5), QA-Master (5), QA-VS (6).
-
-**BUG-QA-CP63-1 (Medium): `SetReplica` leaks old replica server in `byServer` index.**
-- When calling `SetReplica("vol1", "vs3", ...)` on a volume whose replica was previously `vs2`,
-  `vs2` remains in the `byServer` index. `ListByServer("vs2")` still returns `vol1`.
-- Impact: `PickServer` over-counts old replica server's volume count (wrong placement).
-  Failover could trigger on stale index entries.
-- Fix: Added `removeFromServer(oldReplicaServer, name)` before setting new replica in `SetReplica()`.
-- File: `master_block_registry.go:285` (3 lines added).
-- Test: `TestQA_Reg_SetReplicaTwice_ReplacesOld`.
-
-All 48 QA tests + full regression PASS: blockvol (23s), csi (1.1s), iscsi (2.5s), server (4.8s).
-Cumulative Phase 6: 293 + 48 = 341 tests.
-
-[2026-03-04] [TESTER] CP6-3 integration tests: 8 tests in integration_block_test.go. All 8 PASS.
-
-**Required Tests:**
-1. `TestIntegration_FailoverCSIPublish` — Create replicated vol → kill primary → verify
-   LookupBlockVolume (CSI ControllerPublishVolume path) returns promoted replica's iSCSI addr.
-2. `TestIntegration_RebuildOnRecovery` — Failover → reconnect old primary → verify Rebuilding
-   assignment enqueued with correct epoch → confirm via heartbeat.
-3. `TestIntegration_AssignmentDeliveryConfirmation` — Create replicated vol → verify pending
-   assignments → wrong epoch doesn't confirm → correct heartbeat confirms → queue cleared.
-
-**Nice-to-have Tests:**
-4. `TestIntegration_LeaseAwarePromotion` — Lease not expired → promotion deferred → after TTL → promoted.
-5. `TestIntegration_ReplicaFailureSingleCopy` — Replica alloc fails → single-copy mode → no replica
-   assignments → failover is no-op (no replica to promote).
-6. `TestIntegration_TransientDisconnectNoSplitBrain` — VS disconnects with active lease → deferred
-   timer → VS reconnects → timer cancelled → no promotion (split-brain prevented).
-
-**Extra coverage:**
-7. `TestIntegration_FullLifecycle` — Create → publish → confirm assignments → failover → re-publish
-   → confirm → recover → rebuild → confirm → delete. Full 11-phase lifecycle.
-8. `TestIntegration_DoubleFailover` — Primary dies → promoted → promoted replica also dies → original
-   server re-promoted (epoch=3).
-9. `TestIntegration_MultiVolumeFailoverRebuild` — 3 volumes across 2 servers → kill one server → all
-   primaries promoted → reconnect → rebuild assignments for each.
-
-All 349 server+QA+integration tests PASS (6.8s).
-Cumulative Phase 6: 293 + 48 + 8 = 349 tests.
-
-[2026-03-05] [TESTER] CP6-3 real integration tests on M02 (192.168.1.184): 3 tests, all PASS.
-
-**Bug found during testing: RoleNone → RoleRebuilding transition not allowed.**
-- After VS restart, volume is RoleNone. Master sends Rebuilding assignment, but both
-  `validTransitions` (role.go) and `HandleAssignment` (promotion.go) rejected this path.
-- Fix: Added `RoleRebuilding: true` to `validTransitions[RoleNone]` in role.go.
-  Added `RoleNone → RoleRebuilding` case in HandleAssignment (promotion.go) with
-  SetEpoch + SetMasterEpoch + SetRole.
-- Infrastructure: Added `action:"connect"` to admin.go `/rebuild` endpoint to start
-  rebuild client (calls `blockvol.StartRebuild` in background goroutine).
-  Added `StartRebuildClient` method to ha_target.go.
-
-**Tests (cp63_test.go, `//go:build integration`):**
-1. `FailoverCSIAddressSwitch` (3.2s) — Write data A → kill primary → promote replica
-   → client re-discovers at new iSCSI address → verify data A → write data B →
-   verify A+B. Simulates CSI ControllerPublishVolume address-switch flow.
-2. `RebuildDataConsistency` (5.3s) — Write A (replicated) → kill replica → write B
-   (missed) → restart replica as Rebuilding → start rebuild server on primary →
-   connect rebuild client → wait for role→replica → kill primary → promote rebuilt
-   replica → verify A+B intact. Full end-to-end rebuild with data verification.
-3. `FullLifecycleFailoverRebuild` (6.4s) — Write A → kill primary → promote replica
-   → write B → start rebuild server → restart old primary as Rebuilding → rebuild
-   → write C → kill new primary → promote rebuilt old-primary → verify A+B intact.
-   11-phase lifecycle simulating master's failover→recoverBlockVolumes→rebuild flow.
-
-Existing 7 HA tests: all PASS (no regression). Total real integration: 10 tests on M02.
-Code changes: role.go (+1 line), promotion.go (+7 lines), admin.go (+15 lines),
-ha_target.go (+20 lines), cp63_test.go (new, ~350 lines).
-

learn/projects/sw-block/phases/phase-6-progress.md

@@ -1,526 +0,0 @@
-# Phase 6 Progress
-
-## Status
-- CP6-1 complete. 54 CSI tests (25 dev + 30 QA - 1 removed).
-- CP6-2 complete. 172 CP6-2 tests (118 dev/review + 54 QA). 1 QA bug found and fixed.
-- **Phase 6 cumulative: 226 tests, all PASS.**
-
-## Completed
-- CP6-1 Task 0: Extracted BlockVolAdapter to shared `blockvol/adapter.go`, added DisconnectVolume to TargetServer, added Session.TargetIQN().
-- CP6-1 Task 1: VolumeManager (multi-volume BlockVol + shared TargetServer lifecycle). 10 tests.
-- CP6-1 Task 2: CSI Identity service (GetPluginInfo, GetPluginCapabilities, Probe). 3 tests.
-- CP6-1 Task 3: CSI Controller service (CreateVolume, DeleteVolume, ValidateVolumeCapabilities). 4 tests.
-- CP6-1 Task 4: CSI Node service (NodeStageVolume, NodeUnstageVolume, NodePublishVolume, NodeUnpublishVolume). 7 tests.
-- CP6-1 Task 5: gRPC server + binary entry point (`csi/cmd/block-csi/main.go`).
-- CP6-1 Task 6: K8s manifests (DaemonSet, StorageClass, RBAC, example PVC) + smoke-test.sh.
-- CP6-1 Review fixes: 5 findings + 2 open questions resolved, 3 new tests added.
-  - Finding 1: CreateVolume idempotency after restart (adopts existing .blk files on disk).
-  - Finding 2: NodePublishVolume validates empty StagingTargetPath.
-  - Finding 3: Resource leak cleanup on error paths (success flag + deferred CloseVolume).
-  - Finding 4: Synchronous listener creation (bind errors surface immediately).
-  - Finding 5: IQN collision avoidance (SHA256 hash suffix on truncation).
-
-- CP6-1 QA adversarial: 30 tests in qa_csi_test.go. 5 bugs found and fixed:
-  - BUG-QA-1 (Medium): DeleteVolume leaked .snap.* delta files. Fixed: glob+remove snapshot files.
-  - BUG-QA-2 (High): Start not retryable after failure (sync.Once). Fixed: state machine.
-  - BUG-QA-3 (High): Stop then Start broken (sync.Once already fired). Fixed: same state machine.
-  - BUG-QA-4 (Low): CreateVolume ignored LimitBytes. Fixed: validate and cap size.
-  - BUG-QA-5 (Medium): sanitizeFilename case divergence with SanitizeIQN. Fixed: lowercase both.
-  - Additional: goroutine captured m.target by reference (nil after Stop). Fixed: local capture.
-
-- CP6-2 complete. All 7 tasks done. 63 CSI tests + 48 server block tests = 111 CP6-2 tests, all PASS.
-
-## CP6-2: Control-Plane Integration
-
-### Completed Tasks
-
-- **Task 0: Proto Extension + Code Generation** — block volume messages in master.proto/volume_server.proto, Go stubs regenerated, conversion helpers + 5 tests.
-- **Task 1: Master Block Volume Registry** — in-memory registry with Pending→Active status tracking, full/delta heartbeat reconciliation, per-name inflight lock (TOCTOU prevention), placement (fewest volumes), block-capable server tracking. 11 tests.
-- **Task 2: Volume Server Block Volume gRPC** — AllocateBlockVolume/DeleteBlockVolume gRPC handlers on VolumeServer, CreateBlockVol/DeleteBlockVol on BlockService, shared naming (blockvol/naming.go). 5 tests.
-- **Task 3: Master Block Volume RPC Handlers** — CreateBlockVolume (idempotent, inflight lock, retry up to 3 servers), DeleteBlockVolume (idempotent), LookupBlockVolume. Mock VS call injection for testability. 9 tests.
-- **Task 4: Heartbeat Wiring** — block volume fields in heartbeat stream, volume server sends initial full heartbeat + deltas, master processes via UpdateFullHeartbeat/UpdateDeltaHeartbeat.
-- **Task 5: CSI Controller Refactor** — VolumeBackend interface (LocalVolumeBackend + MasterVolumeClient), controller uses backend instead of VolumeManager, returns volume_context with iscsiAddr+iqn, mode flag (controller/node/all). 5 backend tests.
-- **Task 6: CSI Node Refactor + K8s Manifests** — Node reads volume_context for remote targets, staged volume tracking with IQN derivation fallback on restart, split K8s manifests (csi-driver.yaml, csi-controller.yaml Deployment, csi-node.yaml DaemonSet). 4 new node tests (11 total).
-
-### New Files (CP6-2)
-| File | Description |
-|------|-------------|
-| `blockvol/naming.go` | Shared SanitizeIQN + SanitizeFilename |
-| `blockvol/naming_test.go` | 4 naming tests |
-| `blockvol/block_heartbeat_proto.go` | Go wire type ↔ proto conversion |
-| `blockvol/block_heartbeat_proto_test.go` | 5 conversion tests |
-| `server/master_block_registry.go` | Block volume registry + placement |
-| `server/master_block_registry_test.go` | 11 registry tests |
-| `server/volume_grpc_block.go` | VS block volume gRPC handlers |
-| `server/volume_grpc_block_test.go` | 5 VS tests |
-| `server/master_grpc_server_block.go` | Master block volume RPC handlers |
-| `server/master_grpc_server_block_test.go` | 9 master handler tests |
-| `csi/volume_backend.go` | VolumeBackend interface + clients |
-| `csi/volume_backend_test.go` | 5 backend tests |
-| `csi/deploy/csi-controller.yaml` | Controller Deployment manifest |
-| `csi/deploy/csi-node.yaml` | Node DaemonSet manifest |
-
-### Modified Files (CP6-2)
-| File | Changes |
-|------|---------|
-| `pb/master.proto` | Block volume messages, Heartbeat fields 24-27, RPCs |
-| `pb/volume_server.proto` | AllocateBlockVolume, VolumeServerDeleteBlockVolume |
-| `server/master_server.go` | BlockVolumeRegistry + VS call fields |
-| `server/master_grpc_server.go` | Block volume heartbeat processing |
-| `server/volume_grpc_client_to_master.go` | Block volume in heartbeat stream |
-| `server/volume_server_block.go` | CreateBlockVol/DeleteBlockVol on BlockService |
-| `csi/controller.go` | VolumeBackend instead of VolumeManager |
-| `csi/controller_test.go` | Updated for VolumeBackend |
-| `csi/node.go` | Remote target support + staged volume tracking |
-| `csi/node_test.go` | 4 new remote target tests |
-| `csi/server.go` | Mode flag, MasterAddr, VolumeBackend config |
-| `csi/cmd/block-csi/main.go` | --master, --mode flags |
-| `csi/deploy/csi-driver.yaml` | CSIDriver object only (split out workloads) |
-| `csi/qa_csi_test.go` | Updated for VolumeBackend |
-
-### CP6-2 Review Fixes
-All findings from both reviewers addressed. 4 new tests added (118 total CP6-2 tests).
-
-| # | Finding | Severity | Fix |
-|---|---------|----------|-----|
-| R1-F1 | DeleteBlockVol doesn't terminate active sessions | High | Use DisconnectVolume instead of RemoveVolume |
-| R1-F2 | Block registry server list never pruned | Medium | UnmarkBlockCapable on VS disconnect in SendHeartbeat defer |
-| R1-F3 | Block volume status never updates after create | Medium | Mark StatusActive immediately after successful VS allocate |
-| R1-F4 | IQN generation on startup scan doesn't sanitize | Low | Apply blockvol.SanitizeIQN(name) in scan path |
-| R1-F5/R2-F3 | CreateBlockVol idempotent path skips TargetServer | Medium | Re-add adapter to TargetServer on idempotent path |
-| R2-F1 | UpdateFullHeartbeat doesn't update SizeBytes | Low | Copy info.VolumeSize to existing.SizeBytes |
-| R2-F2 | inflightEntry.done channel is dead code | Low | Removed done channel, simplified to empty struct |
-| R2-F4 | CreateBlockVolume idempotent check doesn't validate size | Medium | Return error if existing size < requested size |
-| R2-F5 | Full + delta heartbeat can fire on same message | Low | Changed second `if` to `else if` + comment |
-| R2-F6 | NodeUnstageVolume deletes staged entry before cleanup | Medium | Delete from staged map only after successful cleanup |
-
-New tests: TestMaster_CreateIdempotentSizeMismatch, TestRegistry_UnmarkDeadServer, TestRegistry_FullHeartbeatUpdatesSizeBytes, TestNode_UnstageRetryKeepsStagedEntry.
-
-### CP6-2 QA Adversarial Tests
-54 tests across 2 files. 1 bug found and fixed.
-
-| File | Tests | Areas |
-|------|-------|-------|
-| `server/qa_block_cp62_test.go` | 22 | Registry (8), Master RPCs (8), VS BlockService (6) |
-| `csi/qa_cp62_test.go` | 32 | Node remote (6), Controller backend (5), Backend (2), Naming (2), Lifecycle (4), Server/Driver (2), VolumeManager (4), Edge cases (7) |
-
-**BUG-QA-CP62-1 (Medium): `NewCSIDriver` accepts invalid mode strings.**
-- `NewCSIDriver(DriverConfig{Mode: "invalid"})` returns nil error. Driver runs with only identity server — no controller, no node. K8s reports capabilities but all operations fail `Unimplemented`.
-- Fix: Added `switch` validation after mode defaulting. Returns `"csi: invalid mode %q, must be controller/node/all"`.
-- Test: `TestQA_ModeInvalid`.
-
-**Final CP6-2 test count: 118 dev/review + 54 QA = 172 CP6-2 tests, all PASS.**
-
-**Cumulative Phase 6 test count: 54 CP6-1 + 172 CP6-2 = 226 tests.**
-
-## CSI Testing Ladder
-
-| Level | What | Tools | Status |
-|-------|------|-------|--------|
-| 1. Unit tests | Mock iscsiadm/mount. Confirm idempotency, error handling, edge cases. | `go test` | DONE (226 tests) |
-| 2. gRPC conformance | `csi-sanity` tool validates all CSI RPCs against spec. No K8s needed. | [csi-sanity](https://github.com/kubernetes-csi/csi-test) | DONE (33 pass, 58 skip) |
-| 3. Integration smoke | Full iSCSI lifecycle with real filesystem (via csi-sanity "should work" tests). | csi-sanity + iscsiadm | DONE (489 SCSI cmds) |
-| 4. Single-node K8s (k3s) | Deploy CSI DaemonSet on k3s. PVC → Pod → write data → delete/recreate → verify persistence. | k3s v1.34.4 | DONE |
-| 5. Failure/chaos | Kill CSI controller pod; ensure no IO outage for existing volumes. Node restart with staged volumes. | chaos-mesh or manual | TODO |
-| 6. K8s E2E suite | SIG-Storage tests validate provisioning, attach/detach, resize, snapshots. | `e2e.test` binary | TODO |
-
-### Level 2: csi-sanity Conformance (M02)
-
-**Result: 33 Passed, 0 Failed, 58 Skipped, 1 Pending.**
-
-Run on M02 (192.168.1.184) with block-csi in local mode. Used helper scripts for staging/target path management.
-
-Bugs found and fixed during csi-sanity:
-| # | Bug | Severity | Fix |
-|---|-----|----------|-----|
-| BUG-SANITY-1 | CreateVolume accepted empty VolumeCapabilities | Medium | Added `len(req.VolumeCapabilities) == 0` check |
-| BUG-SANITY-2 | ValidateVolumeCapabilities accepted empty VolumeCapabilities | Medium | Same check added |
-| BUG-SANITY-3 | NodeStageVolume accepted nil VolumeCapability | Medium | Added nil check |
-| BUG-SANITY-4 | NodePublishVolume used `mount -t ext4` instead of bind mount | High | Added BindMount method to MountUtil interface |
-| BUG-SANITY-5 | NodeUnpublishVolume didn't remove target path | Medium | Added os.RemoveAll per CSI spec |
-| BUG-SANITY-6 | NodeUnpublishVolume failed on unmounted path | Medium | Added IsMounted check before unmount |
-
-All existing unit tests updated with VolumeCapabilities/VolumeCapability in test requests.
-
-### Level 3: Integration Smoke (M02)
-
-Verified through csi-sanity's full lifecycle tests which exercised real iSCSI:
-- 489 real SCSI commands processed (READ_10, WRITE_10, SYNC_CACHE, INQUIRY, etc.)
-- Full cycle: CreateVolume → NodeStageVolume (iSCSI login + mkfs.ext4 + mount) → NodePublishVolume → NodeUnpublishVolume → NodeUnstageVolume (unmount + iSCSI logout) → DeleteVolume
-- Clean state verified: no leftover iSCSI sessions, mounts, or volume files
-
-### Level 4: k3s PVC→Pod (M02)
-
-**Result: PASS — data persists across pod deletion/recreation.**
-
-k3s v1.34.4 single-node on M02. CSI deployed as DaemonSet with 3 containers:
-1. block-csi (privileged, nsenter wrappers for host iscsiadm/mount/umount/mkfs/blkid/mountpoint)
-2. csi-provisioner (v5.1.0, --node-deployment for single-node)
-3. csi-node-driver-registrar (v2.12.0)
-
-Test sequence:
-1. Created PVC (100Mi, sw-block StorageClass) → Bound
-2. Created pod → wrote "hello sw-block" to /data/test.txt → md5: `7be761488cf480c966077c7aca4ea3ed`
-3. Deleted pod (PVC retained) → iSCSI session cleanly closed
-4. Recreated pod with same PVC → read "hello sw-block" → same md5 verified
-5. Appended "persistence works!" → confirmed read-write
-
-Additional bug fixed during k3s testing:
-| # | Bug | Severity | Fix |
-|---|-----|----------|-----|
-| BUG-K3S-1 | IsLoggedIn didn't handle iscsiadm exit code 21 (nsenter suppresses output) | Medium | Added `exitErr.ExitCode() == 21` check |
-
-DaemonSet manifest: `learn/projects/sw-block/test/csi-k3s-node.yaml`
-
-- CP6-3 complete. 67 CP6-3 tests. All PASS.
-
-## CP6-3: Failover + Rebuild in Kubernetes
-
-### Completed Tasks
-
-- **Task 0: Proto Extension + Wire Type Updates** — Added replica_data_addr, replica_ctrl_addr to BlockVolumeInfoMessage/BlockVolumeAssignment; rebuild_addr to BlockVolumeAssignment; replica_server to Create/LookupBlockVolumeResponse; replica fields to AllocateBlockVolumeResponse. Updated wire types and converters. 8 tests.
-- **Task 1: Master Assignment Queue + Delivery** — BlockAssignmentQueue with Enqueue/Peek/Confirm/ConfirmFromHeartbeat. Retain-until-confirmed pattern (F1): assignments resent on every heartbeat until VS confirms via matching (path, epoch, role). Stale epoch pruning during Peek. Wired into HeartbeatResponse delivery. 11 tests.
-- **Task 2: VS Assignment Receiver Wiring** — VS extracts block_volume_assignments from HeartbeatResponse and calls BlockService.ProcessAssignments.
-- **Task 3: BlockService Replication Support** — ProcessAssignments dispatches to HandleAssignment + setupPrimaryReplication/setupReplicaReceiver/startRebuild per role. ReplicationPorts deterministic hash (F3). Heartbeat reports replica addresses (F5). 9 tests.
-- **Task 4: Registry Replica Tracking + CreateVolume** — Added SetReplica/ClearReplica/SwapPrimaryReplica to registry. CreateBlockVolume creates on 2 servers (primary + replica), enqueues assignments. Single-copy mode if only 1 server or replica fails (F4). LookupBlockVolume returns ReplicaServer. 10 tests.
-- **Task 5: Master Failover Detection** — failoverBlockVolumes on VS disconnect. Lease-aware promotion (F2): promote only after LastLeaseGrant + LeaseTTL expires. Deferred promotion via time.AfterFunc for unexpired leases. promoteReplica swaps primary/replica, bumps epoch, enqueues new primary assignment. 11 tests.
-- **Task 6: ControllerPublishVolume/UnpublishVolume** — ControllerPublishVolume calls backend.LookupVolume, returns publish_context{iscsiAddr, iqn}. ControllerUnpublishVolume is no-op. Added PUBLISH_UNPUBLISH_VOLUME capability. NodeStageVolume prefers publish_context over volume_context (reflects current primary after failover). 8 tests.
-- **Task 7: Rebuild on Recovery** — recoverBlockVolumes on VS reconnect drains pendingRebuilds, sets reconnected server as replica, enqueues Rebuilding assignments. 10 tests (shared with Task 5 test file).
-
-### Design Review Findings Addressed
-
-| # | Finding | Severity | Resolution |
-|---|---------|----------|------------|
-| F1 | Assignment delivery can be dropped | Critical | Retain-until-confirmed: Peek+Confirm pattern, assignments resent every heartbeat |
-| F2 | Failover without lease check → split-brain | Critical | Gate promotion on `now > lastLeaseGrant + leaseTTL`; deferred promotion for unexpired leases |
-| F3 | Replication ports change on VS restart | Critical | Deterministic port = FNV hash of path, offset from base iSCSI port |
-| F4 | Partial create (replica fails) | Medium | Single-copy mode with ReplicaServer="", skip replica assignments |
-| F5 | UpdateFullHeartbeat ignores replica addresses | Medium | VS includes replica_data/ctrl in InfoMessage; registry updates on heartbeat |
-
-### Code Review 1 Findings Addressed
-
-| # | Finding | Severity | Resolution |
-|---|---------|----------|------------|
-| R1-1 | AllocateBlockVolume missing repl addrs | High | AllocateBlockVolume now returns ReplicaDataAddr/CtrlAddr/RebuildListenAddr from ReplicationPorts() |
-| R1-2 | Primary never starts rebuild server | High | setupPrimaryReplication now calls vol.StartRebuildServer(rebuildAddr) |
-| R1-3 | Assignment queue never confirms after startup | High | VS sends periodic full block heartbeat (5×sleepInterval tick) enabling master confirmation |
-| R1-4 | Replica addresses not reported in heartbeat | Medium | BlockService.CollectBlockVolumeHeartbeat wraps store's collector, fills ReplicaDataAddr/CtrlAddr from replStates |
-| R1-5 | Lease never refreshed after create | Medium | UpdateFullHeartbeat refreshes LastLeaseGrant on every heartbeat; periodic block heartbeats keep it current |
-
-### Code Review 2 Findings Addressed
-
-| # | Finding | Severity | Resolution |
-|---|---------|----------|------------|
-| R2-F1 | LastLeaseGrant set AFTER Register → stale-lease race | High | Moved to entry initializer BEFORE Register |
-| R2-F2 | Deferred promotion timer has no cancellation | Medium | Timers stored in blockFailoverState.deferredTimers; cancelled in recoverBlockVolumes on reconnect |
-| R2-F3 | SwapPrimaryReplica hardcodes uint32(1) | Medium | Changed to blockvol.RoleToWire(blockvol.RolePrimary) |
-| R2-F4 | DeleteBlockVolume doesn't delete replica | Medium | Added best-effort replica delete (non-fatal if replica VS is down) |
-| R2-F5 | promoteReplica reads epoch without lock | Medium | SwapPrimaryReplica now computes epoch+1 atomically inside lock, returns newEpoch |
-| R2-F6 | Redundant string(server) casts | Low | Removed — servers already typed as string |
-| R2-F7 | startRebuild goroutine has no feedback path | Low | Documented as future work (VS could report via heartbeat) |
-
-### New Files (CP6-3)
-
-| File | Description |
-|------|-------------|
-| `server/master_block_assignment_queue.go` | Assignment queue with retain-until-confirmed |
-| `server/master_block_assignment_queue_test.go` | 11 queue tests |
-| `server/master_block_failover.go` | Failover detection + rebuild on recovery |
-| `server/master_block_failover_test.go` | 21 failover + rebuild tests |
-
-### Modified Files (CP6-3)
-
-| File | Changes |
-|------|---------|
-| `pb/master.proto` | Replica/rebuild fields on assignment/info/response messages |
-| `pb/volume_server.proto` | Replica/rebuild fields on AllocateBlockVolumeResponse |
-| `pb/master_pb/master.pb.go` | New fields + getters |
-| `pb/volume_server_pb/volume_server.pb.go` | New fields + getters |
-| `storage/blockvol/block_heartbeat.go` | ReplicaDataAddr/CtrlAddr on InfoMessage, RebuildAddr on Assignment |
-| `storage/blockvol/block_heartbeat_proto.go` | Updated converters + AssignmentsToProto |
-| `server/master_server.go` | blockAssignmentQueue, blockFailover, blockAllocResult struct |
-| `server/master_grpc_server.go` | Assignment delivery in heartbeat, failover on disconnect, recovery on reconnect |
-| `server/master_grpc_server_block.go` | Replica creation, assignment enqueueing, tryCreateReplica; R2-F1 LastLeaseGrant fix; R2-F4 replica delete; R2-F6 cast cleanup |
-| `server/master_block_registry.go` | Replica fields, lease fields, SetReplica/ClearReplica/SwapPrimaryReplica; R2-F3 RoleToWire; R2-F5 atomic epoch; R1-5 lease refresh |
-| `server/volume_grpc_client_to_master.go` | Assignment processing from HeartbeatResponse; R1-3 periodic block heartbeat tick |
-| `server/volume_grpc_block.go` | R1-1 replication ports in AllocateBlockVolumeResponse |
-| `server/volume_server_block.go` | ProcessAssignments, replication setup, ReplicationPorts; R1-2 StartRebuildServer; R1-4 CollectBlockVolumeHeartbeat with repl addrs |
-| `server/master_block_failover.go` | R2-F2 deferred timer cancellation; R2-F5 new SwapPrimaryReplica API; R2-F7 rebuild feedback comment |
-| `storage/store_blockvol.go` | WithVolume (exported) |
-| `csi/controller.go` | ControllerPublishVolume/UnpublishVolume, PUBLISH_UNPUBLISH capability |
-| `csi/node.go` | Prefer publish_context over volume_context |
-
-### CP6-3 Test Count
-
-| File | New Tests |
-|------|-----------|
-| `blockvol/block_heartbeat_proto_test.go` | 7 |
-| `server/master_block_assignment_queue_test.go` | 11 |
-| `server/volume_server_block_test.go` | 9 |
-| `server/master_block_registry_test.go` | 5 |
-| `server/master_grpc_server_block_test.go` | 6 |
-| `server/master_block_failover_test.go` | 21 |
-| `csi/controller_test.go` | 6 |
-| `csi/node_test.go` | 2 |
-| **Total CP6-3** | **67** |
-
-**Cumulative Phase 6 test count: 54 CP6-1 + 172 CP6-2 + 67 CP6-3 = 293 tests.**
-
-### CP6-3 QA Adversarial Tests
-48 tests in `server/qa_block_cp63_test.go`. 1 bug found and fixed.
-
-| Group | Tests | Areas |
-|-------|-------|-------|
-| Assignment Queue | 8 | Wrong epoch confirm, partial heartbeat confirm, same-path different roles, concurrent ops |
-| Registry | 7 | Double swap, swap no-replica, concurrent swap+lookup, SetReplica replace, heartbeat clobber |
-| Failover | 7 | Deferred cancel on reconnect, double disconnect, mixed lease states, volume deleted during timer |
-| Create+Delete | 5 | Lease non-zero after create, replica delete on vol delete, replica delete failure |
-| Rebuild | 3 | Double reconnect, nil failover state, full cycle |
-| Integration | 2 | Failover enqueues assignment, heartbeat confirms failover assignment |
-| Edge Cases | 5 | Epoch monotonic, cancel timers no rebuilds, replica server dies, empty batch |
-| Master-level | 5 | Delete VS unreachable, sanitized name, concurrent create/delete, all VS fail, slow allocate |
-| VS-level | 6 | Concurrent create, concurrent create/delete, delete cleans snapshots, sanitization collision, idempotent re-add, nil block service |
-
-**BUG-QA-CP63-1 (Medium): `SetReplica` leaks old replica server in `byServer` index.**
-- `SetReplica` didn't remove old replica server from `byServer` when replacing with a new one.
-- Fix: Added `removeFromServer(oldReplicaServer, name)` before setting new replica (3 lines).
-- Test: `TestQA_Reg_SetReplicaTwice_ReplacesOld`.
-
-**Final CP6-3 test count: 67 dev/review + 48 QA = 115 CP6-3 tests, all PASS.**
-
-### CP6-3 Integration Tests
-8 tests in `server/integration_block_test.go`. Full cross-component flows.
-
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | FailoverCSIPublish | LookupBlockVolume returns new iSCSI addr after failover |
-| 2 | RebuildOnRecovery | Rebuilding assignment enqueued + heartbeat confirms it |
-| 3 | AssignmentDeliveryConfirmation | Queue retains until heartbeat confirms matching (path, epoch) |
-| 4 | LeaseAwarePromotion | Promotion deferred until lease TTL expires |
-| 5 | ReplicaFailureSingleCopy | Single-copy mode: no replica assignments, failover is no-op |
-| 6 | TransientDisconnectNoSplitBrain | Deferred timer cancelled on reconnect, no split-brain |
-| 7 | FullLifecycle | 11-phase lifecycle: create→publish→confirm→failover→re-publish→recover→rebuild→delete |
-| 8 | DoubleFailover | Two successive failovers: epoch 1→2→3 |
-| 9 | MultiVolumeFailoverRebuild | 3 volumes, kill 1 server, rebuild all affected |
-
-**Final CP6-3 test count: 67 dev/review + 48 QA + 8 mock integration + 3 real integration = 126 CP6-3 tests, all PASS.**
-
-**Cumulative Phase 6 with QA: 54 CP6-1 + 172 CP6-2 + 126 CP6-3 = 352 tests.**
-
-### CP6-3 Real Integration Tests (M02)
-3 tests in `blockvol/test/cp63_test.go`, run on M02 (192.168.1.184) with real iSCSI.
-
-**Bug found: RoleNone → RoleRebuilding transition not allowed.**
-After VS restart, volume is RoleNone. Master sends Rebuilding assignment, but both
-`validTransitions` (role.go) and `HandleAssignment` (promotion.go) rejected this path.
-- Fix: Added `RoleRebuilding: true` to `validTransitions[RoleNone]` in role.go.
-  Added `RoleNone → RoleRebuilding` case in HandleAssignment with SetEpoch + SetRole.
-- Admin API: Added `action:"connect"` to `/rebuild` endpoint (starts rebuild client).
-
-| # | Test | Time | What it proves |
-|---|------|------|----------------|
-| 1 | FailoverCSIAddressSwitch | 3.2s | Write A → kill primary → promote replica → re-discover at new iSCSI address → verify A → write B → verify A+B. Simulates CSI ControllerPublishVolume address-switch. |
-| 2 | RebuildDataConsistency | 5.3s | Write A (replicated) → kill replica → write B (missed) → restart replica as Rebuilding → rebuild server + client → wait role→Replica → kill primary → promote rebuilt → verify A+B. Full end-to-end rebuild with data verification. |
-| 3 | FullLifecycleFailoverRebuild | 6.4s | Write A → kill primary → promote → write B → rebuild old primary → write C → kill new primary → promote old → verify A+B. 11-phase lifecycle: failover→recoverBlockVolumes→rebuild. |
-
-All 7 existing HA tests: PASS (no regression). Total real integration: 10 tests on M02.
-
-## In Progress
-- None.
-
-## Blockers
-- None.
-
-## Next Steps
-- CP6-4: Soak testing, lease renewal timers, monitoring dashboards.
-
-## Notes
-- CSI spec dependency: `github.com/container-storage-interface/spec v1.10.0`.
-- Architecture: CSI binary embeds TargetServer + BlockVol in-process (loopback iSCSI).
-- Interface-based ISCSIUtil/MountUtil for unit testing without real iscsiadm/mount.
-- k3s deployment requires: hostNetwork, hostPID, privileged, /dev mount, nsenter wrappers for host commands.
-- Known pre-existing flaky: `TestQAPhase4ACP1/role_concurrent_transitions` (unrelated to CSI).
-
-## CP6-1 Test Catalog
-
-### VolumeManager (`csi/volume_manager_test.go`) — 10 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | CreateOpenClose | Create, verify IQN, close, reopen lifecycle |
-| 2 | DeleteRemovesFile | .blk file removed on delete |
-| 3 | DuplicateCreate | Same size idempotent; different size returns ErrVolumeSizeMismatch |
-| 4 | ListenAddr | Non-empty listen address after start |
-| 5 | OpenNonExistent | Error on opening non-existent volume |
-| 6 | CloseAlreadyClosed | Idempotent close of non-tracked volume |
-| 7 | ConcurrentCreateDelete | 10 parallel create+delete, no races |
-| 8 | SanitizeIQN | Special char replacement, truncation to 64 chars |
-| 9 | CreateIdempotentAfterRestart | Existing .blk file adopted on restart |
-| 10 | IQNCollision | Long names with same prefix get distinct IQNs via hash suffix |
-
-### Identity (`csi/identity_test.go`) — 3 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | GetPluginInfo | Returns correct driver name + version |
-| 2 | GetPluginCapabilities | Returns CONTROLLER_SERVICE capability |
-| 3 | Probe | Returns ready=true |
-
-### Controller (`csi/controller_test.go`) — 4 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | CreateVolume | Volume created and tracked |
-| 2 | CreateIdempotent | Same name+size succeeds, different size returns AlreadyExists |
-| 3 | DeleteVolume | Volume removed after delete |
-| 4 | DeleteNotFound | Delete non-existent returns success (CSI spec) |
-
-### Node (`csi/node_test.go`) — 7 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | StageUnstage | Full stage flow (discovery+login+mount) and unstage (unmount+logout+close) |
-| 2 | PublishUnpublish | Bind mount from staging to target path |
-| 3 | StageIdempotent | Already-mounted staging path returns OK without side effects |
-| 4 | StageLoginFailure | iSCSI login error propagated as Internal |
-| 5 | StageMkfsFailure | mkfs error propagated as Internal |
-| 6 | StageLoginFailureCleanup | Volume closed after login failure (no resource leak) |
-| 7 | PublishMissingStagingPath | Empty StagingTargetPath returns InvalidArgument |
-
-### Adapter (`blockvol/adapter_test.go`) — 3 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | AdapterALUAProvider | ALUAState/TPGroupID/DeviceNAA correct values |
-| 2 | RoleToALUA | All role→ALUA state mappings |
-| 3 | UUIDToNAA | NAA-6 byte layout from UUID |
-
-## CP6-2 Test Catalog
-
-### Registry (`server/master_block_registry_test.go`) — 11 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | RegisterLookup | Register + Lookup returns entry |
-| 2 | DuplicateRegister | Second register same name errors |
-| 3 | Unregister | Unregister removes entry |
-| 4 | ListByServer | Returns only entries for given server |
-| 5 | FullHeartbeat | Marks active, removes stale, adds new |
-| 6 | DeltaHeartbeat | Add/remove deltas applied correctly |
-| 7 | PickServer | Fewest-volumes placement |
-| 8 | Inflight | AcquireInflight blocks duplicate, ReleaseInflight unblocks |
-| 9 | BlockCapable | MarkBlockCapable / UnmarkBlockCapable tracking |
-| 10 | UnmarkDeadServer | R1-F2 regression test |
-| 11 | FullHeartbeatUpdatesSizeBytes | R2-F1 regression test |
-
-### Master RPCs (`server/master_grpc_server_block_test.go`) — 9 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | CreateHappyPath | Create → register → lookup works |
-| 2 | CreateIdempotent | Same name+size returns same entry |
-| 3 | CreateIdempotentSizeMismatch | Same name, smaller size → error |
-| 4 | CreateInflightBlock | Concurrent create same name → one fails |
-| 5 | Delete | Delete → VS called → unregistered |
-| 6 | DeleteNotFound | Delete non-existent → success |
-| 7 | Lookup | Lookup returns entry |
-| 8 | LookupNotFound | Lookup non-existent → NotFound |
-| 9 | CreateRetryNextServer | First VS fails → retries on next |
-
-### VS Block gRPC (`server/volume_grpc_block_test.go`) — 5 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | Allocate | Create via gRPC returns path+iqn+addr |
-| 2 | AllocateEmptyName | Empty name → error |
-| 3 | AllocateZeroSize | Zero size → error |
-| 4 | Delete | Delete via gRPC succeeds |
-| 5 | DeleteNilService | Nil blockService → error |
-
-### Naming (`blockvol/naming_test.go`) — 4 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | SanitizeFilename | Lowercases, replaces invalid chars |
-| 2 | SanitizeIQN | Lowercases, replaces, truncates with hash |
-| 3 | IQNMaxLength | 64-char names pass through unchanged |
-| 4 | IQNHashDeterministic | Same input → same hash suffix |
-
-### Proto conversion (`blockvol/block_heartbeat_proto_test.go`) — 5 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | RoundTrip | Go→proto→Go preserves all fields |
-| 2 | NilSafe | Nil input → nil output |
-| 3 | ShortRoundTrip | Short info round-trip |
-| 4 | AssignmentRoundTrip | Assignment round-trip |
-| 5 | SliceHelpers | Slice conversion helpers |
-
-### Backend (`csi/volume_backend_test.go`) — 5 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | LocalCreate | LocalVolumeBackend.CreateVolume creates + returns info |
-| 2 | LocalDelete | LocalVolumeBackend.DeleteVolume removes volume |
-| 3 | LocalLookup | LocalVolumeBackend.LookupVolume returns info |
-| 4 | LocalLookupNotFound | Lookup non-existent returns not-found |
-| 5 | LocalDeleteNotFound | Delete non-existent returns success |
-
-### Node remote (`csi/node_test.go` additions) — 4 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | StageRemoteTarget | volume_context drives iSCSI instead of local mgr |
-| 2 | UnstageRemoteTarget | Staged map IQN used for logout |
-| 3 | UnstageAfterRestart | IQN derived from iqnPrefix when staged map empty |
-| 4 | UnstageRetryKeepsStagedEntry | R2-F6 regression: staged entry preserved on failure |
-
-### QA Server (`server/qa_block_cp62_test.go`) — 22 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | Reg_FullHeartbeatCrossTalk | Heartbeat from s2 doesn't remove s1 volumes |
-| 2 | Reg_FullHeartbeatEmptyServer | Empty heartbeat marks server block-capable |
-| 3 | Reg_ConcurrentHeartbeatAndRegister | 10 goroutines heartbeat+register, no races |
-| 4 | Reg_DeltaHeartbeatUnknownPath | Delta for unknown path is no-op |
-| 5 | Reg_PickServerTiebreaker | PickServer returns first server on tie |
-| 6 | Reg_ReregisterDifferentServer | Re-register same name on different server fails |
-| 7 | Reg_InflightIndependence | Inflight lock for vol-a doesn't block vol-b |
-| 8 | Reg_BlockCapableServersAfterUnmark | Unmark removes from block-capable list |
-| 9 | Master_DeleteVSUnreachable | Delete fails if VS delete fails (no orphan) |
-| 10 | Master_CreateSanitizedName | Names with special chars go through |
-| 11 | Master_ConcurrentCreateDelete | Concurrent create+delete on same name, no panic |
-| 12 | Master_AllVSFailNoOrphan | All 3 servers fail → error, no registry entry |
-| 13 | Master_SlowAllocateBlocksSecond | Inflight lock blocks concurrent same-name create |
-| 14 | Master_CreateZeroSize | Zero size → InvalidArgument |
-| 15 | Master_CreateEmptyName | Empty name → InvalidArgument |
-| 16 | Master_EmptyNameValidation | Whitespace-only name → InvalidArgument |
-| 17 | VS_ConcurrentCreate | 20 goroutines create same vol, no crash |
-| 18 | VS_ConcurrentCreateDelete | 20 goroutines create+delete interleaved |
-| 19 | VS_DeleteCleansSnapshots | Delete removes .snap.* files |
-| 20 | VS_SanitizationCollision | Idempotent create after sanitization matches |
-| 21 | VS_CreateIdempotentReaddTarget | Idempotent create re-adds adapter to TargetServer |
-| 22 | VS_GrpcNilBlockService | Nil blockService returns error (not panic) |
-
-### QA CSI (`csi/qa_cp62_test.go`) — 32 tests
-| # | Test | What it proves |
-|---|------|----------------|
-| 1 | Node_RemoteUnstageNoCloseVolume | Remote unstage doesn't call CloseVolume |
-| 2 | Node_RemoteUnstageFailPreservesStaged | Failed unstage preserves staged entry |
-| 3 | Node_ConcurrentStageUnstage | 20 concurrent stage+unstage, no races |
-| 4 | Node_RemotePortalUsedCorrectly | Remote portal used for discovery (not local) |
-| 5 | Node_PartialVolumeContext | Missing iqn falls back to local mgr |
-| 6 | Node_UnstageNoMgrNoPrefix | No mgr + no prefix → empty IQN (graceful) |
-| 7 | Ctrl_VolumeContextPresent | CreateVolume returns iscsiAddr+iqn in context |
-| 8 | Ctrl_ValidateUsesBackend | ValidateVolumeCapabilities uses backend lookup |
-| 9 | Ctrl_CreateLargerSizeRejected | Existing vol + larger size → AlreadyExists |
-| 10 | Ctrl_ExactBlockSizeBoundary | Exact 4MB boundary succeeds |
-| 11 | Ctrl_ConcurrentCreate | 10 concurrent creates, one succeeds |
-| 12 | Backend_LookupAfterRestart | Volume found after VolumeManager restart |
-| 13 | Backend_DeleteThenLookup | Lookup after delete → not found |
-| 14 | Naming_CrossLayerConsistency | CSI and blockvol SanitizeIQN produce same result |
-| 15 | Naming_LongNameHashCollision | Two 70-char names → distinct IQNs |
-| 16 | RemoteLifecycleFull | Full remote stage→publish→unpublish→unstage→delete |
-| 17 | ModeControllerNoMgr | Controller mode with masterAddr, no local mgr |
-| 18 | ModeNodeOnly | Node mode creates mgr but no controller |
-| 19 | ModeInvalid | Invalid mode → error (BUG-QA-CP62-1) |
-| 20 | Srv_AllModeLocalBackend | All mode without master uses local backend |
-| 21 | Srv_DoubleStop | Double Stop doesn't panic |
-| 22 | VM_CreateAfterStop | Create after stop returns error |
-| 23 | VM_OpenNonExistent | Open non-existent returns error |
-| 24 | VM_ListenAddrAfterStop | ListenAddr after stop returns empty |
-| 25 | VM_VolumeIQNSanitized | VolumeIQN applies sanitization |
-| 26 | Edge_MinSize | Minimum 4MB volume succeeds |
-| 27 | Edge_BelowMinSize | Below minimum → error |
-| 28 | Edge_RequiredEqualsLimit | Required == limit succeeds |
-| 29 | Edge_RoundingExceedsLimit | Rounding up exceeds limit → error |
-| 30 | Edge_EmptyVolumeIDNode | Empty volumeID → InvalidArgument |
-| 31 | Node_PublishWithoutStaging | Publish unstaged vol → still works (mock) |
-| 32 | Node_DoubleUnstage | Double unstage → idempotent success |

seaweedfs-rdma-sidecar/rdma-engine/Cargo.lock

@@ -211,9 +211,9 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
 
 [[package]]
 name = "bytes"
-version = "1.11.1"
+version = "1.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
+checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
 
 [[package]]
 name = "cast"

seaweedfs-rdma-sidecar/rdma-engine/Cargo.toml

@@ -41,7 +41,7 @@ chrono = { version = "0.4", features = ["serde"] }
 
 # Memory management and utilities
 memmap2 = "0.9"
-bytes = "1.11"
+bytes = "1.0"
 parking_lot = "0.12"  # Fast mutexes
 
 # IPC and networking

sw-block/.gocache_v2/README

@@ -1,4 +0,0 @@
-This directory holds cached build artifacts from the Go build system.
-Run "go clean -cache" if the directory is getting too large.
-Run "go clean -fuzzcache" to delete the fuzz cache.
-See go.dev to learn more about Go.

sw-block/.gocache_v2/trim.txt

@@ -1 +0,0 @@
-1774577367

sw-block/.private/README.md

@@ -1,27 +0,0 @@
-# .private
-
-Private working area for `sw-block`.
-
-Use this for:
-- phase development notes
-- roadmap/progress tracking
-- draft handoff notes
-- temporary design comparisons
-- prototype scratch work not ready for `design/` or `prototype/`
-
-Recommended layout:
-- `.private/phase/`: phase-by-phase development notes
-- `.private/roadmap/`: short-term and medium-term execution notes
-- `.private/handoff/`: notes for `sw`, `qa`, or future sessions
-
-Phase protocol:
-- each phase should normally have:
-  - `phase-xx.md`
-  - `phase-xx-log.md`
-  - `phase-xx-decisions.md`
-- details are defined in `.private/phase/README.md`
-
-Promotion rules:
-- stable vision/design docs go to `../design/`
-- real prototype code stays in `../prototype/`
-- `.private/` is for working material, not source of truth

sw-block/.private/phase/README.md

@@ -1,36 +0,0 @@
-# Phase Dev
-
-Use this directory for private phase development notes.
-
-## Phase Protocol
-
-Each phase should use this file set:
-
-- `phase-01.md`
-  - plan
-  - scope
-  - progress
-  - active tasks
-  - exit criteria
-- `phase-01-log.md`
-  - dated development log
-  - experiments
-  - test runs
-  - failures and findings
-- `phase-01-decisions.md`
-  - key algorithm decisions
-  - tradeoffs
-  - rejected alternatives
-
-Suggested naming pattern:
-- `phase-01.md`
-- `phase-01-log.md`
-- `phase-01-decisions.md`
-- `phase-02.md`
-- `phase-02-log.md`
-- `phase-02-decisions.md`
-
-Rule of use:
-1. if it is what we are doing -> `phase-xx.md`
-2. if it is what happened -> `phase-xx-log.md`
-3. if it is why we chose something -> `phase-xx-decisions.md`

sw-block/.private/phase/phase-01-decisions.md

@@ -1,97 +0,0 @@
-# Phase 01 Decisions
-
-Date: 2026-03-26
-Status: active
-
-## Purpose
-
-Capture the key design decisions made during Phase 01 simulator work.
-
-## Initial Decisions
-
-### 1. `design/` vs `.private/phase/`
-
-Decision:
-- `sw-block/design/` holds shared design truth
-- `sw-block/.private/phase/` holds execution planning and progress
-
-Reason:
-- design backlog and execution checklist should not be mixed
-
-### 2. Scenario source of truth
-
-Decision:
-- `sw-block/design/v2_scenarios.md` is the scenario backlog and coverage matrix
-
-Reason:
-- all contributors need one visible scenario list
-
-### 3. Phase 01 priority
-
-Decision:
-- first close:
-  - `S19`
-  - `S20`
-
-Reason:
-- they are the biggest remaining distributed lineage/partition scenarios
-
-### 4. Current simulator scope
-
-Decision:
-- use the simulator as a V2 design-validation tool, not a product/perf harness
-
-Reason:
-- current goal is correctness and protocol coverage, not productization
-
-### 5. Phase execution format
-
-Decision:
-- keep phase execution in three files:
-  - `phase-xx.md`
-  - `phase-xx-log.md`
-  - `phase-xx-decisions.md`
-
-Reason:
-- separates plan, evidence, and reasoning
-- reduces drift between roadmap and findings
-
-### 6. Design backlog vs execution plan
-
-Decision:
-- `sw-block/design/v2_scenarios.md` remains the source of truth for scenario backlog and coverage
-- `.private/phase/phase-01.md` is the execution layer for `sw`
-
-Reason:
-- design truth should be stable and shareable
-- execution tasks should be easier to edit without polluting design docs
-
-### 7. Immediate Phase 01 priorities
-
-Decision:
-- prioritize:
-  - `S19` chain of custody across multiple promotions
-  - `S20` live partition with competing writes
-
-Reason:
-- these are the biggest remaining distributed-lineage gaps after current simulator milestone
-
-### 8. Coverage status should be conservative
-
-Decision:
-- mark scenarios as `partial` unless the test actually exercises the core protocol obligation, not just a simplified happy path
-
-Reason:
-- avoids overstating simulator coverage
-- keeps the backlog honest for follow-up strengthening
-
-### 9. Protocol-version comparison belongs in the simulator
-
-Decision:
-- compare `V1`, `V1.5`, and `V2` using the same scenario set where possible
-
-Reason:
-- this is the clearest way to show:
-  - where V1 breaks
-  - where V1.5 improves but still strains
-  - why V2 is architecturally cleaner

sw-block/.private/phase/phase-01-log.md

@@ -1,67 +0,0 @@
-# Phase 01 Log
-
-Date: 2026-03-26
-Status: active
-
-## Log Protocol
-
-Use dated entries like:
-
-## 2026-03-26
-- work completed
-- tests run
-- failures found
-- seeds/traces worth keeping
-- follow-up items
-
-## Initial State
-
-- Phase 01 created from the earlier `phase-01-v2-scenarios.md` working note
-- scenario source of truth remains:
-  - `sw-block/design/v2_scenarios.md`
-- current active asks for `sw`:
-  - `S19`
-  - `S20`
-
-## 2026-03-26
-
-- created Phase 01 file set:
-  - `phase-01.md`
-  - `phase-01-log.md`
-  - `phase-01-decisions.md`
-- promoted scenario execution checklist into `phase-01.md`
-- kept `sw-block/design/v2_scenarios.md` as the shared backlog and coverage matrix
-- current simulator milestone:
-  - `fsmv2` passing
-  - `volumefsm` passing
-  - `distsim` passing
-  - randomized `distsim` seeds passing
-  - event/interleaving simulator work present in `sw-block/prototype/distsim/simulator.go`
-- current immediate development priority for `sw`:
-  - implement `S19`
-  - implement `S20`
-- `sw` added Phase 01 P0/P1 scenario tests in `distsim`:
-  - `S19`
-  - `S20`
-  - `S5`
-  - `S6`
-  - `S18`
-  - stronger `S12`
-- review result:
-  - `S19` looks solid
-  - stronger `S12` now looks solid
-  - `S20`, `S5`, `S6`, `S18` are better classified as `partial` than fully closed
-- updated `v2_scenarios.md` coverage matrix to reflect actual status
-- next development focus:
-  - P2 scenarios
-  - stronger versions of current partial scenarios
-- added protocol-version comparison design:
-  - `sw-block/design/protocol-version-simulation.md`
-- added minimal protocol policy prototype in `distsim`:
-  - `ProtocolV1`
-  - `ProtocolV15`
-  - `ProtocolV2`
-  - focused on:
-    - catch-up policy
-    - tail-chasing outcome policy
-    - restart/rejoin policy

sw-block/.private/phase/phase-01-v2-scenarios.md

@@ -1,11 +0,0 @@
-# Deprecated
-
-This file is deprecated.
-
-Use instead:
-- `phase-01.md`
-- `phase-01-log.md`
-- `phase-01-decisions.md`
-
-The scenario source of truth remains:
-- `sw-block/design/v2_scenarios.md`

sw-block/.private/phase/phase-01.md

@@ -1,164 +0,0 @@
-# Phase 01
-
-Date: 2026-03-26
-Status: completed
-Purpose: drive V2 simulator development by closing the scenario backlog in `sw-block/design/v2_scenarios.md`
-
-## Goal
-
-Make the V2 simulator cover the important protocol scenarios as explicitly as possible.
-
-This phase is about:
-- simulator fidelity
-- scenario coverage
-- invariant quality
-
-This phase is not about:
-- product integration
-- SPDK
-- raw allocator
-- production transport
-
-## Source Of Truth
-
-Design/source-of-truth:
-- `sw-block/design/v2_scenarios.md`
-
-Prototype code:
-- `sw-block/prototype/fsmv2/`
-- `sw-block/prototype/volumefsm/`
-- `sw-block/prototype/distsim/`
-
-## Assigned Tasks For `sw`
-
-### P0
-
-1. `S19` chain of custody across multiple promotions
-- add fixed test(s)
-- verify committed data from `A -> B -> C`
-- update coverage matrix
-
-2. `S20` live partition with competing writes
-- add fixed test(s)
-- stale side must not advance committed lineage
-- update coverage matrix
-
-### P1
-
-3. `S5` flapping replica stays recoverable
-- repeated disconnect/reconnect
-- no unnecessary rebuild while recovery remains possible
-
-4. `S6` tail-chasing under load
-- primary keeps writing while replica catches up
-- explicit outcome:
-  - converge and promote
-  - or abort to rebuild
-
-5. `S18` primary restart without failover
-- same-lineage restart behavior
-- no stale session assumptions
-
-6. stronger `S12`
-- more than one promotion candidate
-- choose valid lineage, not merely highest apparent LSN
-
-### P2
-
-7. protocol-version comparison support
-- model:
-  - `V1`
-  - `V1.5`
-  - `V2`
-- use the same scenario set to show:
-  - V1 breaks
-  - V1.5 improves but still strains
-  - V2 handles recovery more explicitly
-
-8. richer Smart WAL scenarios
-- time-varying `ExtentReferenced` availability
-- recoverable then unrecoverable transitions
-
-9. delayed/drop network scenarios beyond simple disconnect
-
-10. multi-node reservation expiry / rebuild timeout cases
-
-## Invariants To Preserve
-
-After every scenario or random run, preserve:
-
-1. committed data is durable per policy
-2. uncommitted data is not revived as committed
-3. stale epoch traffic does not mutate current lineage
-4. recovered/promoted node matches reference state at target `LSN`
-5. committed prefix remains contiguous
-
-## Required Updates Per Task
-
-For each completed scenario:
-
-1. add or update test(s)
-2. update `sw-block/design/v2_scenarios.md`
-   - package
-   - test name
-   - status
-3. note any missing simulator capability
-
-## Current Progress
-
-Already in place before this phase:
-- `fsmv2` local FSM prototype
-- `volumefsm` orchestrator prototype
-- `distsim` distributed simulator
-- randomized `distsim` runs
-- first event/interleaving simulator work in `distsim/simulator.go`
-
-Open focus:
-- `S19` covered in `distsim`
-- `S20` partially covered in `distsim`
-- `S5` partially covered in `distsim`
-- `S6` partially covered in `distsim`
-- `S18` partially covered in `distsim`
-- stronger `S12` covered in `distsim`
-- protocol-version comparison design added in:
-  - `sw-block/design/protocol-version-simulation.md`
-- remaining focus is now P2 plus stronger versions of partial scenarios
-
-## Phase Status
-
-### P0
-
-- `S19` chain of custody across multiple promotions: done
-- `S20` live partition with competing writes: partial
-
-### P1
-
-- `S5` flapping replica stays recoverable: partial
-- `S6` tail-chasing under load: partial
-- `S18` primary restart without failover: partial
-- stronger `S12`: done
-
-### P2
-
-- active next step:
-  - protocol-version comparison support
-  - stronger versions of current partial scenarios
-
-## Exit Criteria
-
-Phase 01 is done when:
-
-1. `S19` and `S20` are covered
-2. `S5`, `S6`, `S18`, and stronger `S12` are at least partially covered
-3. coverage matrix in `v2_scenarios.md` is current
-4. random simulation still passes after added scenarios
-
-## Completion Note
-
-Phase 01 completed with:
-- `S19` covered
-- stronger `S12` covered
-- `S20`, `S5`, `S6`, `S18` strengthened but correctly left as `partial`
-
-Next execution phase:
-- `sw-block/.private/phase/phase-02.md`

sw-block/.private/phase/phase-02-decisions.md

@@ -1,51 +0,0 @@
-# Phase 02 Decisions
-
-Date: 2026-03-26
-Status: active
-
-## Decision 1: Extend `distsim` Instead Of Forking A New Protocol Simulator
-
-Reason:
-- current `distsim` already has:
-  - node/storage model
-  - coordinator/epoch model
-  - reference oracle
-  - randomized runs
-- the missing layer is protocol-state fidelity, not a new simulation foundation
-
-Implication:
-- add lightweight per-node replication state and protocol decisions to `distsim`
-- do not build a separate fourth simulator yet
-
-## Decision 2: Keep Coverage Status Conservative
-
-Reason:
-- `S20`, `S6`, and `S18` currently prove important safety properties
-- but they do not yet fully assert message-level or explicit state-transition behavior
-
-Implication:
-- leave them `partial` until the model can assert protocol behavior directly
-
-## Decision 3: Use Versioned Scenario Comparison To Justify V2
-
-Reason:
-- the simulator should not only say "V2 works"
-- it should show:
-  - where `V1` fails
-  - where `V1.5` improves but still strains
-  - why `V2` is worth the complexity
-
-Implication:
-- Phase 02 includes explicit `V1` / `V1.5` / `V2` scenario comparison work
-
-## Decision 4: V2 Must Not Be Described As "Always Catch-Up"
-
-Reason:
-- that wording is too optimistic and hides the real V2 design rule
-- V2 is better because it makes recoverability explicit, not because it retries forever
-
-Implication:
-- describe V2 as:
-  - catch-up if explicitly recoverable
-  - otherwise explicit rebuild
-- keep this wording consistent in tests and docs

sw-block/.private/phase/phase-02-log.md

@@ -1,93 +0,0 @@
-# Phase 02 Log
-
-Date: 2026-03-26
-Status: active
-
-## 2026-03-26
-
-- Phase 02 created to move `distsim` from final-state safety validation toward explicit protocol-state simulation.
-- Initial focus:
-  - close `S20`, `S6`, and `S18` at protocol level
-  - compare `V1`, `V1.5`, and `V2` on the same scenarios
-- Known model gap at phase start:
-  - current `distsim` is strong at final-state safety invariants
-  - current `distsim` is weaker at mid-flow protocol assertions and message-level rejection reasons
-- Phase 02 progress now in place:
-  - delivery accept/reject tracking
-  - protocol-level stale-epoch rejection assertions
-  - explicit non-convergent catch-up state transition assertions
-  - initial version-comparison tests for disconnect, tail-chasing, and restart/rejoin policy
-- Next simulator target:
-  - reproduce real `V1.5` address-instability and control-plane-recovery failures as named scenarios
-- Immediate coding asks for `sw`:
-  - changed-address restart failure in `V1.5`
-  - same-address transient outage comparison across `V1` / `V1.5` / `V2`
-  - slow control-plane reassignment scenario derived from `CP13-8 T4b`
-- Local housekeeping done:
-  - corrected V2 wording from "always catch-up" to "catch-up if explicitly recoverable; otherwise rebuild"
-  - added explicit brief-disconnect and changed-address restart policy helpers
-  - verified `distsim` test suite still passes with the Windows-safe runner
-- Scenario status update:
-  - `S20` now covered via protocol-level stale-traffic rejection + committed-prefix stability
-  - `S6` now covered via explicit `CatchingUp -> NeedsRebuild` assertions
-  - `S18` now covered via explicit stale `MsgBarrierAck` rejection + prefix stability
-- Next asks for `sw` after this closure:
-  - changed-address restart scenario tied directly to `CP13-8 T4b`
-  - same-address transient outage comparison across `V1` / `V1.5` / `V2`
-  - slow control-plane reassignment scenario
-  - Smart WAL recoverable -> unrecoverable transition scenarios
-- Additional closure completed:
-  - `S5` now covered with both:
-    - repeated recoverable flapping
-    - budget-exceeded escalation to `NeedsRebuild`
-  - Smart WAL transitions now exercised with:
-    - recoverable -> unrecoverable during active recovery
-    - mixed `WALInline` + `ExtentReferenced` success
-    - time-varying payload availability
-- Updated next asks for `sw`:
-  - changed-address restart scenario tied directly to `CP13-8 T4b`
-  - same-address transient outage comparison across `V1` / `V1.5` / `V2`
-  - slow control-plane reassignment scenario
-  - delayed/drop network beyond simple disconnect
-  - multi-node reservation expiry / rebuild timeout cases
-- Additional Phase 02 coverage delivered:
-  - delayed stale messages after promote/failover
-  - delayed stale barrier ack rejection
-  - selective write-drop with barrier delivery under `sync_all`
-  - multi-node mixed reservation expiry outcome
-  - multi-node `NeedsRebuild` / snapshot rebuild recovery
-  - partial rebuild timeout / retry completion
-- Remaining asks are now narrower:
-  - changed-address restart scenario tied directly to `CP13-8 T4b`
-  - same-address transient outage comparison across `V1` / `V1.5` / `V2`
-  - slow control-plane reassignment scenario
-  - stronger coordinator candidate-selection scenarios
-- Additional closure after review:
-  - safe default promotion selector now refuses `NeedsRebuild` candidates
-  - explicit desperate-promotion API separated from safe selection
-  - changed-address and slow-control-plane comparison tests now prove actual data divergence / healing, not only policy shape
-- New next-step assignment:
-  - strengthen model depth around endpoint identity and control-plane reassignment
-  - replace abstract repair helpers with more explicit event flow where practical
-  - reduce direct recovery state injection in comparison tests
-  - extend candidate selection from ranking into validity rules
-
-## 2026-03-27
-
-- Phase 02 core simulator hardening is effectively complete.
-- Delivered since the previous checkpoint:
-  - endpoint identity / endpoint-version modeling
-  - stale-endpoint rejection in delivery path
-  - heartbeat -> coordinator detect -> assignment-update control-plane flow
-  - recovery-session trigger API for `V1.5` and `V2`
-  - explicit candidate eligibility checks:
-    - running
-    - epoch alignment
-    - state eligibility
-    - committed-prefix sufficiency
-  - safe default promotion now rejects candidates without the committed prefix
-- Current `distsim` status at latest review:
-  - 73 tests passing
-- Manager bookkeeping decision:
-  - keep Phase 02 active only for doc maintenance / wrap-up
-  - treat further simulator depth as likely Phase 03 work, not unbounded Phase 02 scope creep

sw-block/.private/phase/phase-02.md

@@ -1,191 +0,0 @@
-# Phase 02
-
-Date: 2026-03-27
-Status: active
-Purpose: extend the V2 simulator from final-state safety checking into protocol-state simulation that can reproduce `V1`, `V1.5`, and `V2` behavior on the same scenarios
-
-## Goal
-
-Make the simulator model enough node-local replication state and message-level behavior to:
-
-1. reproduce `V1` / `V1.5` failure modes
-2. show why those failures are structural
-3. close the current `partial` V2 scenarios with stronger protocol assertions
-
-This phase is about:
-- protocol-version comparison
-- per-node replication state
-- message-level fencing / accept / reject behavior
-- explicit catch-up abort / rebuild transitions
-
-This phase is not about:
-- product integration
-- production transport
-- SPDK
-- raw allocator
-
-## Source Of Truth
-
-Design/source-of-truth:
-- `sw-block/design/v2_scenarios.md`
-- `sw-block/design/protocol-version-simulation.md`
-- `sw-block/design/v1-v15-v2-simulator-goals.md`
-
-Prototype code:
-- `sw-block/prototype/distsim/`
-
-## Assigned Tasks For `sw`
-
-### P0
-
-1. Add per-node replication state to `distsim`
-- minimum states:
-  - `InSync`
-  - `Lagging`
-  - `CatchingUp`
-  - `NeedsRebuild`
-  - `Rebuilding`
-- keep state lightweight; do not clone full `fsmv2` into `distsim`
-
-2. Add message-level protocol decisions
-- stale-epoch write / ship / barrier traffic must be explicitly rejected
-- record whether a message was:
-  - accepted
-  - rejected by epoch
-  - rejected by state
-
-3. Add explicit catch-up abort / rebuild entry
-- non-convergent catch-up must move to explicit modeled failure:
-  - `NeedsRebuild`
-  - or equivalent abort outcome
-
-### P1
-
-4. Re-close `S20` at protocol level
-- stale-side writes must go through protocol delivery path
-- prove stale-side traffic cannot advance committed lineage
-
-5. Re-close `S6` at protocol level
-- assert explicit abort/escalation on non-convergence
-- not only final-state safety
-
-6. Re-close `S18` at protocol level
-- assert committed-prefix behavior around delayed old ack / restart races
-- not only final-state oracle checks
-
-### P2
-
-7. Expand protocol-version comparison
-- run selected scenarios under:
-  - `V1`
-  - `V1.5`
-  - `V2`
-- at minimum:
-  - brief disconnect
-  - restart with changed address
-  - tail-chasing
-
-8. Add V1.5-derived failure scenarios
-- replica restart with changed receiver address
-- same-address transient outage
-- slow control-plane recovery vs fast local reconnect
-
-9. Prepare richer recovery modeling
-- time-varying recoverability
-- reservation loss during active catch-up
-- rebuild timeout / retry in mixed-state cluster
-
-## Invariants To Preserve
-
-After every scenario or random run, preserve:
-
-1. committed data is durable per policy
-2. uncommitted data is not revived as committed
-3. stale epoch traffic does not mutate current lineage
-4. recovered/promoted node matches reference state at target `LSN`
-5. committed prefix remains contiguous
-6. protocol-state transitions are explicit, not inferred from final data only
-
-## Required Updates Per Task
-
-For each completed task:
-
-1. add or update test(s)
-2. update `sw-block/design/v2_scenarios.md`
-   - package
-   - test name
-   - status
-   - source if new scenario was derived from V1/V1.5 behavior
-3. add a short note to:
-   - `sw-block/.private/phase/phase-02-log.md`
-4. if a design choice changed, record it in:
-   - `sw-block/.private/phase/phase-02-decisions.md`
-
-## Current Progress
-
-Already in place before this phase:
-- `distsim` final-state safety invariants
-- randomized simulation
-- event/interleaving simulator work
-- initial `ProtocolVersion` / policy scaffold
-- `S19` covered
-- stronger `S12` covered
-
-Known partials to close in this phase:
-- none in the current named backlog slice
-
-Delivered in this phase so far:
-- delivery accept/reject tracking added
-- protocol-level rejection assertions added
-- explicit `CatchingUp -> NeedsRebuild` state transition tested
-- selected protocol-version comparison tests added
-- `S20`, `S6`, and `S18` moved from `partial` to `covered`
-- Smart WAL transition scenarios added
-- `S5` moved from `partial` to `covered`
-- endpoint identity / endpoint-version modeling added
-- explicit heartbeat -> detect -> assignment-update control-plane flow added for changed-address restart
-- explicit recovery-session triggers added for `V1.5` and `V2`
-- promotion selection now uses explicit eligibility, including committed-prefix gating
-- safe and desperate promotion paths are separated
-- full `distsim` suite at latest review: 73 tests passing
-
-Remaining focus for `sw`:
-- Phase 02 core scope is now largely delivered
-- remaining work should be treated as future-strengthening, not baseline closure
-- if more simulator depth is needed next, it should likely start as Phase 03:
-  - timeout semantics
-  - timer races
-  - richer event/interleaving behavior
-  - stronger endpoint/control-plane realism beyond the current abstract model
-
-## Immediate Next Tasks For `sw`
-
-1. Add a documented compare artifact for new scenarios
-- for each new `V1` / `V1.5` / `V2` comparison:
-  - record scenario name
-  - what fails in `V1`
-  - what improves in `V1.5`
-  - what is explicit in `V2`
-- keep `sw-block/design/v1-v15-v2-comparison.md` updated
-
-2. Keep the coverage matrix honest
-- do not mark a scenario `covered` unless the test asserts protocol behavior directly
-- final-state oracle checks alone are not enough
-
-3. Prepare Phase 03 proposal instead of broadening ad hoc
-- if more depth is needed, define it cleanly first:
-  - timers / timeout events
-  - event ordering races
-  - richer endpoint lifecycle
-  - recovery-session uniqueness across competing triggers
-
-## Exit Criteria
-
-Phase 02 is done when:
-
-1. `S5`, `S6`, `S18`, and `S20` are covered at protocol level
-2. `distsim` can reproduce at least one `V1` failure, one `V1.5` failure, and the corresponding `V2` behavior on the same named scenario
-3. protocol-level rejection/accept behavior is asserted in tests, not only inferred from final-state oracle checks
-4. coverage matrix in `v2_scenarios.md` is current
-5. changed-address and reconnect scenarios are modeled through explicit endpoint / control-plane behavior rather than helper-only abstraction
-6. promotion selection uses explicit eligibility, including committed-prefix safety

sw-block/.private/phase/phase-03-decisions.md

@@ -1,97 +0,0 @@
-# Phase 03 Decisions
-
-Date: 2026-03-27
-Status: initial
-
-## Why Phase 03 Exists
-
-Phase 02 already covered the main protocol-state story:
-
-- V1 / V1.5 / V2 comparison
-- stale traffic rejection
-- catch-up vs rebuild
-- changed-address restart control-plane flow
-- committed-prefix-safe promotion eligibility
-
-The next simulator problems are different:
-
-- timer semantics
-- timeout races
-- event ordering under contention
-
-That deserves a separate phase so the model boundary stays clear.
-
-## Initial Boundary
-
-### `distsim`
-
-Keep for:
-
-- protocol correctness
-- reference-state validation
-- recoverability logic
-- promotion / lineage rules
-
-### `eventsim`
-
-Grow for:
-
-- explicit event queue behavior
-- timeout events
-- equal-time scheduling choices
-- race exploration
-
-## Working Rule
-
-Do not move all scenarios into `eventsim`.
-
-Only move or duplicate scenarios when:
-
-- timer or event ordering is the real bug surface
-- `distsim` abstraction hides the important behavior
-
-## Accepted Phase 03 Decisions
-
-### Same-tick rule
-
-Within one tick:
-
-- data/message delivery is evaluated before timeout firing
-
-Meaning:
-
-- if an ack arrives in the same tick as a timeout deadline, the ack wins and may cancel the timeout
-
-This is now an explicit simulator rule, not accidental behavior.
-
-### Timeout authority
-
-Not every timeout that reaches its deadline still has authority to mutate state.
-
-So we now distinguish:
-
-- `FiredTimeouts`
-  - timeout had authority and changed the model
-- `IgnoredTimeouts`
-  - timeout reached deadline but was stale and ignored
-
-This keeps replay/debug output honest.
-
-### Late barrier ack rule
-
-Once a barrier instance times out:
-
-- it is marked expired
-- late ack for that barrier instance is rejected
-
-That prevents a stale ack from reviving old durability state.
-
-### Review gate rule for timer work
-
-Timer/race work is easy to get subtly wrong while still having green tests.
-
-So timer-related work is not accepted until:
-
-- code path is reviewed
-- tests assert the real protocol obligation
-- stale and authoritative timer behavior are clearly distinguished

sw-block/.private/phase/phase-03-log.md

@@ -1,36 +0,0 @@
-# Phase 03 Log
-
-Date: 2026-03-27
-Status: active
-
-## 2026-03-27
-
-- Phase 03 created after Phase 02 core scope was effectively delivered.
-- Reason for new phase:
-  - remaining simulator work is about timer semantics and race behavior, not basic protocol-state coverage
-- Initial target:
-  - define `distsim` vs `eventsim` split more clearly
-  - add explicit timeout semantics
-  - add timer-race scenarios without bloating `distsim` ad hoc
-- P0 delivered:
-  - timeout model added for barrier / catch-up / reservation
-  - timeout-backed scenarios added
-  - same-tick ordering rule defined as data-before-timers
-- First review result:
-  - timeout semantics accepted only after making cancellation model-driven
-  - late barrier ack after timeout required explicit rejection
-- P0 hardening delivered:
-  - recovery timeout cancellation moved into model logic
-  - stale late barrier ack rejected via expired-barrier tracking
-  - stale vs authoritative timeout distinction added:
-    - `FiredTimeouts`
-    - `IgnoredTimeouts`
-- P1 delivered and reviewed:
-  - promotion vs stale timeout race
-  - rebuild completion vs epoch bump race
-  - trace builder moved into reusable code
-- Current suite state at latest accepted review:
-  - 86 `distsim` tests passing
-- Manager decision:
-  - Phase 03 P0/P1 are accepted
-  - next work should move to deliberate P2 selection rather than broadening the phase ad hoc

sw-block/.private/phase/phase-03.md

@@ -1,193 +0,0 @@
-# Phase 03
-
-Date: 2026-03-27
-Status: active
-Purpose: define the next simulator tier after Phase 02, focused on timeout semantics, timer races, and a cleaner split between protocol simulation and event/interleaving simulation
-
-## Goal
-
-Phase 03 exists to cover behavior that current `distsim` still abstracts away:
-
-1. timeout semantics
-2. timer races
-3. event ordering under competing triggers
-4. clearer separation between:
-   - protocol / lineage simulation
-   - event / race simulation
-
-This phase should not reopen already-closed Phase 02 protocol scope unless a clear bug is found.
-
-## Why A New Phase
-
-Phase 02 already delivered:
-
-- protocol-state assertions
-- V1 / V1.5 / V2 comparison scenarios
-- endpoint identity modeling
-- control-plane assignment-update flow
-- committed-prefix-aware promotion eligibility
-
-What remains is different in character:
-
-- timers
-- delayed events racing with each other
-- timeout-triggered state changes
-- more explicit event scheduling
-
-That deserves a new phase boundary.
-
-## Source Of Truth
-
-Design/source-of-truth:
-- `sw-block/design/v2_scenarios.md`
-- `sw-block/design/v2-dist-fsm.md`
-- `sw-block/design/v2-scenario-sources-from-v1.md`
-- `sw-block/design/v1-v15-v2-comparison.md`
-
-Current prototype base:
-- `sw-block/prototype/distsim/`
-- `sw-block/prototype/distsim/simulator.go`
-
-## Scope
-
-### In scope
-
-1. timeout semantics
-- barrier timeout
-- catch-up timeout
-- reservation expiry timeout
-- rebuild timeout
-
-2. timer races
-- delayed ack vs timeout
-- timeout vs promotion
-- reconnect vs timeout
-- catch-up completion vs expiry
-- rebuild completion vs epoch bump
-
-3. simulator split clarification
-- `distsim` keeps:
-  - protocol correctness
-  - lineage
-  - recoverability
-  - reference-state checking
-- `eventsim` grows into:
-  - event scheduling
-  - timer firing
-  - same-time interleavings
-  - race exploration
-
-### Out of scope
-
-- production integration
-- real transport
-- real disk timings
-- SPDK
-- raw allocator
-
-## Assigned Tasks For `sw`
-
-### P0
-
-1. Write a concrete `eventsim` scope note in code/docs
-- define what stays in `distsim`
-- define what moves to `eventsim`
-- avoid overlap and duplicated semantics
-
-2. Add minimal timeout event model
-- first-class timeout event type(s)
-- at minimum:
-  - barrier timeout
-  - catch-up timeout
-  - reservation expiry
-
-3. Add timeout-backed scenarios
-- stale delayed ack vs timeout
-- catch-up timeout before convergence
-- reservation expiry during active recovery
-
-### P1
-
-4. Add race-focused tests
-- promotion vs delayed stale ack
-- rebuild completion vs epoch bump
-- reconnect success vs timeout firing
-
-5. Keep traces debuggable
-- failing runs must dump:
-  - seed
-  - event order
-  - timer events
-  - node states
-  - committed prefix
-
-### P2
-
-6. Decide whether selected `distsim` scenarios should also exist in `eventsim`
-- only when timer/event ordering is the real point
-- do not duplicate every scenario blindly
-
-## Current Progress
-
-Delivered in this phase so far:
-
-- `eventsim` scope note added in code
-- explicit timeout model added:
-  - barrier timeout
-  - catch-up timeout
-  - reservation timeout
-- timeout-backed scenarios added and reviewed
-- same-tick rule made explicit:
-  - data before timers
-- recovery timeout cancellation is now model-driven, not test-driven
-- stale barrier ack after timeout is explicitly rejected
-- stale timeouts are separated from authoritative timeouts:
-  - `FiredTimeouts`
-  - `IgnoredTimeouts`
-- race-focused scenarios added and reviewed:
-  - promotion vs stale catch-up timeout
-  - promotion vs stale barrier timeout
-  - rebuild completion vs epoch bump
-  - epoch bump vs stale catch-up timeout
-- reusable trace builder added for replay/debug support
-- current `distsim` suite at latest review:
-  - 86 tests passing
-
-Remaining focus for `sw`:
-
-- Phase 03 P0 and P1 are effectively complete
-- Phase 03 P2 is also effectively complete after review
-- any further simulator work should now be narrow and evidence-driven
-- recommended next simulator additions only:
-  - control-plane latency parameter
-  - sustained-write convergence / tail-chasing load test
-  - one multi-promotion lineage extension
-
-## Invariants To Preserve
-
-1. committed data remains durable per policy
-2. uncommitted data is never revived as committed
-3. stale epoch traffic never mutates current lineage
-4. committed prefix remains contiguous
-5. timeout-triggered transitions are explicit and explainable
-6. races do not silently bypass fencing or rebuild boundaries
-
-## Required Updates Per Task
-
-For each completed task:
-
-1. add or update tests
-2. update `sw-block/design/v2_scenarios.md` if scenario coverage changed
-3. add a short note to:
-   - `sw-block/.private/phase/phase-03-log.md`
-4. if the simulator boundary changed, record it in:
-   - `sw-block/.private/phase/phase-03-decisions.md`
-
-## Exit Criteria
-
-Phase 03 is done when:
-
-1. timeout semantics exist as explicit simulator behavior
-2. at least three important timer-race scenarios are modeled and tested
-3. `distsim` vs `eventsim` responsibilities are clearly separated
-4. failure traces from race/timeout scenarios are replayable enough to debug

sw-block/.private/phase/phase-04-decisions.md

@@ -1,200 +0,0 @@
-# Phase 04 Decisions
-
-Date: 2026-03-27
-Status: complete
-
-## First Slice Decision
-
-The first standalone V2 implementation slice is:
-
-- per-replica sender ownership
-- one active recovery session per replica per epoch
-
-## Why Not Start In V1
-
-V1/V1.5 remains:
-
-- production line
-- maintenance/fix line
-
-It should not be the place where V2 architecture is first implemented.
-
-## Why This Slice
-
-This slice:
-
-- directly addresses the clearest V1.5 structural pain
-- maps cleanly to the V2-boundary tests
-- is narrow enough to implement without dragging in the entire future architecture
-
-## Accepted P0 Refinements
-
-### Sender epoch coherence
-
-Sender-owned epoch is real state, not decoration.
-
-So:
-
-- reconcile/update paths must refresh sender epoch
-- stale active session must be invalidated on epoch advance
-
-### Session lifecycle
-
-The first slice should not use a totally loose lifecycle shell.
-
-So:
-
-- session phase changes now follow an explicit transition map
-- invalid jumps are rejected
-
-### Session attach rule
-
-Attaching a session at the wrong epoch is invalid.
-
-So:
-
-- `AttachSession(epoch, kind)` must reject epoch mismatch with the owning sender
-
-## Accepted P1 Refinements
-
-### Session identity fencing
-
-The standalone V2 slice must reject stale completion by explicit session identity.
-
-So:
-
-- `RecoverySession` has stable unique identity
-- sender completion must be by session ID, not by "current pointer"
-- stale session results are rejected at the sender authority boundary
-
-### Ownership vs execution
-
-Ownership creation is not the same as execution start.
-
-So:
-
-- `AttachSession()` and `SupersedeSession()` establish ownership only
-- `BeginConnect()` is the first execution-state mutation
-
-### Completion authority
-
-An ID match alone is not enough to complete recovery.
-
-So:
-
-- completion must require a valid completion-ready phase
-- normal completion requires converged catch-up
-- zero-gap fast completion is allowed explicitly from handshake
-
-## P2 Direction
-
-The next prototype step is not broader simulation.
-
-It is:
-
-- recovery outcome branching
-- assignment-intent orchestration
-- prototype-level end-to-end recovery flow
-
-## Accepted P2 Refinements
-
-### Recovery boundary
-
-Recovery classification must use a lineage-safe boundary, not a raw primary WAL head.
-
-So:
-
-- handshake outcome classification uses committed/safe recovery boundary
-- stale or divergent extra tail must not be treated as zero-gap by default
-
-### Stale assignment fencing
-
-Assignment intent must not create current live sessions from stale epoch input.
-
-So:
-
-- stale assignment epoch is rejected
-- assignment result distinguishes:
-  - created
-  - superseded
-  - failed
-
-### Phase discipline on outcome classification
-
-The outcome API must respect execution entry rules.
-
-So:
-
-- handshake-with-outcome requires valid connecting phase before acting
-
-## P3 Direction
-
-The next prototype step is:
-
-- minimal historical-data model
-- recoverability proof
-- explicit safe-boundary / divergent-tail handling
-
-## Accepted P3 Refinements
-
-### Recoverability proof
-
-The historical-data prototype must prove why catch-up is allowed.
-
-So:
-
-- recoverability now checks retained start, end within head, and contiguous coverage
-- rebuild fallback is backed by executable unrecoverability
-
-### Historical state after recycling
-
-Retained-prefix modeling needs a base state, not only remaining WAL entries.
-
-So:
-
-- tail advance captures a base snapshot
-- historical state reconstruction uses snapshot + retained WAL
-
-### Divergent tail handling
-
-Replica-ahead state must not collapse directly to `InSync`.
-
-So:
-
-- divergent tail requires explicit truncation
-- completion is gated on recorded truncation when required
-
-## P4 Direction
-
-The next prototype step is:
-
-- prototype scenario closure
-- acceptance-criteria to prototype traceability
-- explicit expression of the 4 V2-boundary cases against `enginev2`
-
-## Accepted P4 Refinements
-
-### Prototype scenario closure
-
-The prototype must stop being only a set of local mechanisms.
-
-So:
-
-- acceptance criteria are mapped to prototype evidence
-- key V2-boundary scenarios are expressed directly against `enginev2`
-- prototype behavior is reviewable scenario-by-scenario
-
-### Phase 04 completion decision
-
-Phase 04 has now met its intended prototype scope:
-
-- ownership
-- execution gating
-- outcome branching
-- minimal historical-data model
-- prototype scenario closure
-
-So:
-
-- no broad new Phase 04 work should be added
-- next work should move to `Phase 4.5` gate-hardening

sw-block/.private/phase/phase-04-log.md

@@ -1,76 +0,0 @@
-# Phase 04 Log
-
-Date: 2026-03-27
-Status: complete
-
-## 2026-03-27
-
-- Phase 04 created to start the first standalone V2 implementation slice.
-- Decision:
-  - do not begin in `weed/storage/blockvol/`
-  - begin under `sw-block/`
-- first slice chosen:
-  - per-replica sender ownership
-  - explicit recovery-session ownership
-- Initial slice delivered under `sw-block/prototype/enginev2/`:
-  - sender
-  - recovery session
-  - sender group
-- First review found:
-  - sender/session epoch coherence gap
-  - session lifecycle was shell-only, not enforcing real transitions
-  - attach-session epoch mismatch was not rejected
-- Follow-up delivered and accepted:
-  - reconcile updates preserved sender epoch
-  - epoch bump invalidates stale session
-  - session transition map enforced
-  - attach-session rejects epoch mismatch
-  - enginev2 tests increased to 26 passing
-- Phase 04a created to close the ownership-validation gap:
-  - explicit session identity in `distsim`
-  - bridge tests into `enginev2`
-- Phase 04a ownership problem closed well enough:
-  - stale completion rejected by session ID
-  - endpoint invalidation includes `CtrlAddr`
-  - boundary doc aligned with real simulator/prototype evidence
-- Phase 04 P1 delivered and accepted:
-  - sender-owned execution APIs added
-  - all execution APIs fence on `sessionID`
-  - completion now requires valid completion point
-  - attach/supersede now establish ownership only
-  - handshake range validation added
-  - enginev2 tests increased to 46 passing
-- Phase 04 P2 delivered and accepted:
-  - outcome branching added:
-    - `OutcomeZeroGap`
-    - `OutcomeCatchUp`
-    - `OutcomeNeedsRebuild`
-  - assignment-intent orchestration added
-  - stale assignment epoch now rejected
-  - assignment result now distinguishes created / superseded / failed
-  - end-to-end prototype recovery tests added
-  - zero-gap classification tightened:
-    - exact equality to committed boundary only
-    - replica-ahead is not zero-gap
-  - enginev2 tests increased to 63 passing
-- Phase 04 P3 delivered and accepted:
-  - `WALHistory` added as minimal historical-data model
-  - recoverability proof strengthened:
-    - retained start
-    - end within head
-    - contiguous coverage
-  - base snapshot added for correct `StateAt()` after tail advance
-  - divergent-tail truncation made explicit in sender/session execution
-  - WAL-backed prototype recovery tests added
-  - enginev2 tests increased to 83 passing
-- Phase 04 P4 delivered and accepted:
-  - acceptance criteria mapped to prototype evidence
-  - V2-boundary scenarios expressed against `enginev2`
-  - prototype scenario closure achieved
-  - enginev2 tests increased to 95 passing
-- Phase 04 is now complete for its intended prototype scope.
-- Next recommended phase:
-  - `Phase 4.5`
-  - tighten bounded `CatchUp`
-  - formalize `Rebuild`
-  - strengthen crash-consistency / recoverability / liveness proof

sw-block/.private/phase/phase-04.md

@@ -1,216 +0,0 @@
-# Phase 04
-
-Date: 2026-03-27
-Status: complete
-Purpose: start the first standalone V2 implementation slice under `sw-block/`, centered on per-replica sender ownership and explicit recovery-session ownership
-
-## Goal
-
-Build the first real V2 implementation slice without destabilizing V1.
-
-This slice should prove:
-
-1. per-replica sender identity
-2. explicit one-session-per-replica recovery ownership
-3. endpoint/assignment-driven recovery updates
-4. clean handoff between normal sender and recovery session
-
-## Why This Phase Exists
-
-The simulator and design work are now strong enough to support a narrow implementation slice.
-
-We should not start with:
-
-- Smart WAL
-- new storage engine
-- frontend integration
-
-We should start with the ownership problem that most clearly separates V2 from V1.5.
-
-## Source Of Truth
-
-Design:
-- `sw-block/docs/archive/design/v2-first-slice-session-ownership.md`
-- `sw-block/design/v2-acceptance-criteria.md`
-- `sw-block/design/v2-open-questions.md`
-
-Simulator reference:
-- `sw-block/prototype/distsim/`
-
-## Scope
-
-### In scope
-
-1. per-replica sender owner object
-2. explicit recovery session object
-3. session lifecycle rules
-4. endpoint update handling
-5. basic tests for sender/session ownership
-
-### Out of scope
-
-- Smart WAL in production code
-- real block backend redesign
-- V1 integration
-- frontend publication
-
-## Assigned Tasks For `sw`
-
-### P0
-
-1. create standalone V2 implementation area under `sw-block/`
-- recommended:
-  - `sw-block/prototype/enginev2/`
-
-2. define sender/session types
-- sender owner per replica
-- recovery session per replica per epoch
-
-3. implement basic lifecycle
-- create sender
-- attach session
-- supersede stale session
-- close session on success / invalidation
-
-## Current Progress
-
-Delivered in this phase so far:
-
-- standalone V2 area created under:
-  - `sw-block/prototype/enginev2/`
-- core types added:
-  - `Sender`
-  - `RecoverySession`
-  - `SenderGroup`
-- sender/session lifecycle shell implemented
-- per-replica ownership implemented
-- endpoint-change invalidation implemented
-- sender epoch coherence implemented
-- session epoch attach validation implemented
-- session phase transitions now enforce a real transition map
-- session identity fencing implemented
-- stale completion rejected by session ID
-- execution APIs implemented:
-  - `BeginConnect`
-  - `RecordHandshake`
-  - `RecordHandshakeWithOutcome`
-  - `BeginCatchUp`
-  - `RecordCatchUpProgress`
-  - `CompleteSessionByID`
-- completion authority tightened:
-  - catch-up must converge
-  - zero-gap handshake fast path allowed
-- attach/supersede now establish ownership only
-- sender-group orchestration tests added
-- recovery outcome branching implemented:
-  - `OutcomeZeroGap`
-  - `OutcomeCatchUp`
-  - `OutcomeNeedsRebuild`
-- assignment-intent orchestration implemented:
-  - reconcile + recovery target session creation
-  - stale assignment epoch rejected
-  - created/superseded/failed outcomes distinguished
-- P2 data-boundary correction accepted:
-  - zero-gap now requires exact equality to committed boundary
-  - replica-ahead is not zero-gap
-- minimal historical-data prototype implemented:
-  - `WALHistory`
-  - retained-prefix / recycled-range semantics
-  - executable recoverability proof
-  - base snapshot for historical state after tail advance
-- explicit safe-boundary handling implemented:
-  - divergent tail requires truncation before `InSync`
-  - truncation recorded via sender-owned execution API
-- WAL-backed prototype tests added:
-  - catch-up recovery with data verification
-  - rebuild fallback with proof of unrecoverability
-  - truncate-then-`InSync` with committed-boundary verification
-- current `enginev2` test state at latest review:
--  - 95 tests passing
-- prototype scenario closure completed:
-  - acceptance criteria mapped to prototype evidence
-  - V2-boundary scenarios expressed against `enginev2`
-  - small end-to-end prototype harness added
-
-Next phase:
-
-- `Phase 4.5`
-  - bounded `CatchUp`
-  - first-class `Rebuild`
-  - crash-consistency / recoverability / liveness proof hardening
-- do not integrate into V1 production tree yet
-
-### P1
-
-4. implement endpoint update handling
-- changed-address update must refresh the right sender owner
-
-5. implement epoch invalidation
-- stale session must stop after epoch bump
-
-6. add tests matching the slice acceptance
-
-### P2
-
-7. add recovery outcome branching
-- distinguish:
-  - zero-gap fast completion
-  - positive-gap catch-up completion
-  - unrecoverable gap / `NeedsRebuild`
-
-8. add assignment-intent driven orchestration
-- move beyond raw reconcile-only tests
-- make sender-group react to explicit recovery intent
-
-9. add prototype-level end-to-end flow tests
-- assignment/update
-- session creation
-- execution
-- completion / invalidation
-- rebuild escalation
-
-### P3
-
-10. add minimal historical-data prototype
-- retained prefix/window
-- minimal recoverability state
-- explicit "why catch-up is allowed" proof
-
-11. make safe-boundary data handling explicit
-- divergent tail cleanup / truncate rule
-- or equivalent explicit boundary handling before `InSync`
-
-12. strengthen recoverability/rebuild tests
-- executable proof of:
-- recoverable gap
-- unrecoverable gap
-- rebuild fallback boundary
-
-### P4
-
-13. close prototype scenario coverage
-- map key acceptance criteria onto `enginev2` scenarios/tests
-- make prototype evidence reviewable scenario-by-scenario
-
-14. express the 4 V2-boundary cases against the prototype
-- changed-address identity-preserving recovery
-- `NeedsRebuild` persistence
-- catch-up without overwriting safe data
-- repeated disconnect/reconnect cycles
-
-15. add one small prototype harness if needed
-- enough to show assignment -> recovery -> outcome flow end-to-end
-- no product/backend integration yet
-
-## Exit Criteria
-
-Phase 04 is done when:
-
-1. standalone V2 sender/session slice exists under `sw-block/`
-2. sender ownership is per replica, not set-global
-3. one active recovery session per replica per epoch is enforced
-4. endpoint update and epoch invalidation are tested
-5. sender-owned execution flow is validated
-6. recovery outcome branching exists at prototype level
-7. minimal historical-data / recoverability model exists at prototype level
-8. prototype scenario closure is achieved for key V2 acceptance cases

sw-block/.private/phase/phase-04a-decisions.md

@@ -1,49 +0,0 @@
-# Phase 04a Decisions
-
-Date: 2026-03-27
-Status: initial
-
-## Core Decision
-
-The next must-fix validation problem is:
-
-- sender/session ownership semantics
-
-This outranks:
-
-- more timing realism
-- more WAL detail
-- broader scenario growth
-
-## Why
-
-V2's core claim over V1.5 is not only:
-
-- better recovery policy
-
-It is also:
-
-- stable per-replica sender identity
-- one active recovery owner
-- stale work cannot mutate current state
-
-If those ownership rules are not validated, the simulator can overstate confidence.
-
-## Validation Rule
-
-For this phase, a scenario is only complete when it is expressed at two levels:
-
-1. simulator ownership model (`distsim`)
-2. standalone implementation slice (`enginev2`)
-
-Real `weed/` adversarial tests remain the system-level gate.
-
-## Scope Discipline
-
-Do not expand this phase into:
-
-- generic simulator feature growth
-- Smart WAL design growth
-- V1 integration work
-
-Keep it focused on the ownership model.

sw-block/.private/phase/phase-04a-log.md

@@ -1,22 +0,0 @@
-# Phase 04a Log
-
-Date: 2026-03-27
-Status: active
-
-## 2026-03-27
-
-- Phase 04a created as a narrow validation phase.
-- Reason:
-  - the biggest remaining V2 validation gap is ownership semantics
-  - not general scenario count
-  - not more timer realism
-  - not more WAL detail
-- Scope chosen:
-  - sender identity
-  - recovery session identity
-  - supersede / invalidate rules
-  - stale completion rejection
-  - `distsim` to `enginev2` bridge tests
-- This phase is intentionally separate from broad Phase 04 implementation growth.
-- Goal:
-  - gain confidence that V2 is validated as owned session/sender protocol state, not only as policy

sw-block/.private/phase/phase-04a.md

@@ -1,113 +0,0 @@
-# Phase 04a
-
-Date: 2026-03-27
-Status: active
-Purpose: close the critical V2 ownership-validation gap by making sender/session ownership explicit in both simulation and the standalone `enginev2` slice
-
-## Goal
-
-Validate the core V2 claim more deeply:
-
-1. one stable sender identity per replica
-2. one active recovery session per replica
-3. endpoint change, epoch bump, and supersede rules invalidate stale work
-4. stale late results from old sessions cannot mutate current state
-
-This phase is not about adding broad new simulator surface.
-It is about proving the ownership model that is supposed to make V2 better than V1.5.
-
-## Why This Phase Exists
-
-Current simulation is already strong on:
-
-- quorum / commit rules
-- stale epoch rejection
-- catch-up vs rebuild
-- timeout / race ordering
-- changed-address recovery at the policy level
-
-The remaining critical risk is narrower:
-
-- the simulator still validates V2 strongly as policy
-- but not yet strongly enough as owned sender/session protocol state
-
-That is the highest-value validation gap to close before trusting V2 too much.
-
-## Source Of Truth
-
-Design:
-- `sw-block/docs/archive/design/v2-first-slice-session-ownership.md`
-- `sw-block/design/v2-acceptance-criteria.md`
-- `sw-block/design/v2-open-questions.md`
-- `sw-block/design/protocol-development-process.md`
-
-Simulator / prototype:
-- `sw-block/prototype/distsim/`
-- `sw-block/prototype/enginev2/`
-
-Historical / review context:
-- `learn/projects/sw-block/phases/phase-13-v2-boundary-tests.md`
-- `sw-block/design/v2-scenario-sources-from-v1.md`
-
-## Scope
-
-### In scope
-
-1. explicit sender/session identity validation in `distsim`
-2. explicit stale-session invalidation rules
-3. bridge tests from `distsim` scenarios to `enginev2` sender/session invariants
-4. doc cleanup so V2-boundary tests point to real simulator and `enginev2` coverage
-
-### Out of scope
-
-- Smart WAL expansion
-- broad new timing realism
-- TCP / disk realism
-- V1 production integration
-- new backend/storage engine work
-
-## Critical Questions To Close
-
-1. can an old session completion mutate state after a new session supersedes it?
-2. does endpoint change invalidate or supersede the active session cleanly?
-3. does epoch bump remove all authority from prior sessions?
-4. can duplicate recovery triggers create overlapping active sessions?
-
-## Assigned Tasks For `sw`
-
-### P0
-
-1. add explicit session identity to `distsim`
-- model session ID or equivalent ownership token
-- make stale session results rejectable by identity, not just by coarse state
-
-2. add ownership scenarios to `distsim`
-- endpoint change during active catch-up
-- epoch bump during active catch-up
-- stale late completion from old session
-- duplicate recovery trigger while a session is already active
-
-3. add bridge tests in `enginev2`
-- same-address reconnect preserves sender identity
-- endpoint bump supersedes or invalidates active session
-- epoch bump rejects stale completion
-- only one active session per sender
-
-### P1
-
-4. tighten `learn/projects/sw-block/phases/phase-13-v2-boundary-tests.md`
-- point to actual `distsim` scenarios
-- point to actual `enginev2` bridge tests
-- state what remains real-engine-only
-
-5. only add simulator mechanics if a bridge test exposes a real ownership gap
-
-## Exit Criteria
-
-Phase 04a is done when:
-
-1. `distsim` explicitly validates sender/session ownership invariants
-2. `enginev2` has bridge tests for the same invariants
-3. stale session work is shown unable to mutate current sender state
-4. V2-boundary doc no longer has stale simulator references
-5. we can say with confidence that V2 ownership semantics, not just V2 policy, are validated at prototype level

sw-block/.private/phase/phase-05-decisions.md

@@ -1,94 +0,0 @@
-# Phase 05 Decisions
-
-## Decision 1: Real V2 engine work lives under `sw-block/engine/replication/`
-
-The first real engine slice is established under:
-
-- `sw-block/engine/replication/`
-
-This keeps V2 separate from:
-
-- `sw-block/prototype/`
-- `weed/storage/blockvol/`
-
-## Decision 2: Slice 1 is accepted
-
-Accepted scope:
-
-1. stable per-replica sender identity
-2. stable recovery-session identity
-3. stale authority fencing
-4. endpoint / epoch invalidation
-5. ownership registry
-
-## Decision 3: Stable identity must not be address-shaped
-
-The engine registry is now keyed by stable `ReplicaID`, not mutable endpoint address.
-
-This is a required structural break from the V1/V1.5 identity-loss pattern.
-
-## Decision 4: Slice 2 is accepted
-
-Accepted scope:
-
-1. connect / handshake / catch-up flow
-2. zero-gap / catch-up / needs-rebuild branching
-3. stale execution rejection during active recovery
-4. bounded catch-up semantics in engine path
-5. rebuild execution shell
-
-## Decision 5: Slice 3 owns real recoverability inputs
-
-Slice 3 should be the point where:
-
-1. recoverable vs unrecoverable gap uses real engine inputs
-2. trusted-base / rebuild-source decision uses real engine data inputs
-3. truncation / safe-boundary handling is tied to real engine state
-4. historical correctness at recovery target is validated from engine inputs
-
-## Decision 6: Slice 3 is accepted
-
-Accepted scope:
-
-1. real engine recoverability input path
-2. trusted-base / rebuild-source decision from engine data inputs
-3. truncation / safe-boundary handling tied to engine state
-4. recoverability gating without overclaiming full historical reconstruction in engine
-
-## Decision 7: Slice 3 should replace carried-forward heuristics where appropriate
-
-In particular:
-
-1. simple rebuild-source heuristics carried from prototype should not become permanent engine policy
-2. Slice 3 should tighten these decisions against real engine recoverability inputs
-
-## Decision 8: Slice 4 is the engine integration closure slice
-
-Next focus:
-
-1. real assignment/control intent entry path
-2. engine observability / debug surface
-3. focused integration tests for V2-boundary cases
-4. validation against selected real failure classes from `learn/projects/sw-block/` and `weed/storage/block*`
-
-## Decision 9: Slice 4 is accepted
-
-Accepted scope:
-
-1. real orchestrator entry path
-2. assignment/update-driven recovery through that path
-3. engine observability / causal recovery logging
-4. diagnosable V2-boundary integration tests
-
-## Decision 10: Phase 05 is complete
-
-Reason:
-
-1. ownership core is accepted
-2. recovery execution core is accepted
-3. data / recoverability core is accepted
-4. integration closure is accepted
-
-Next:
-
-- `Phase 06` broader engine implementation stage

sw-block/.private/phase/phase-05-log.md

@@ -1,78 +0,0 @@
-# Phase 05 Log
-
-## 2026-03-29
-
-### Opened
-
-`Phase 05` opened as:
-
-- V2 engine planning + Slice 1 ownership core
-
-### Accepted
-
-1. engine module location
-   - `sw-block/engine/replication/`
-
-2. Slice 1 ownership core
-   - stable per-replica sender identity
-   - stable recovery-session identity
-   - sender/session fencing
-   - endpoint / epoch invalidation
-   - ownership registry
-
-3. Slice 1 identity correction
-   - registry now keyed by stable `ReplicaID`
-   - mutable `Endpoint` separated from identity
-   - real changed-`DataAddr` preservation covered by test
-
-4. Slice 1 encapsulation
-   - mutable sender/session authority state no longer exposed directly
-   - snapshot/read-only inspection path in place
-
-5. Slice 2 recovery execution core
-   - connect / handshake / catch-up flow
-   - explicit zero-gap / catch-up / needs-rebuild branching
-   - stale execution rejection during active recovery
-   - bounded catch-up semantics
-   - rebuild execution shell
-
-6. Slice 2 validation
-   - corrected tester summary accepted
-   - `12` ownership tests + `18` recovery tests = `30` total
-   - Slice 2 accepted for progression to Slice 3 planning
-
-7. Slice 3 data / recoverability core
-   - `RetainedHistory` introduced as engine-level recoverability input
-   - history-driven sender APIs added for handshake and rebuild-source selection
-   - trusted-base decision now requires both checkpoint trust and replayable tail
-   - truncation remains a completion gate / protocol boundary
-
-8. Slice 3 validation
-   - corrected tester summary accepted
-   - `12` ownership tests + `18` recovery tests + `18` recoverability tests = `48` total
-   - accepted boundary:
-     - engine proves historical-correctness prerequisites
-     - simulator retains stronger historical reconstruction proof
-   - Slice 3 accepted for progression to Slice 4 planning
-
-9. Slice 4 integration closure
-   - `RecoveryOrchestrator` added as integrated engine entry path
-   - assignment/update-driven recovery is exercised through orchestrator
-   - observability surface added:
-     - `RegistryStatus`
-     - `SenderStatus`
-     - `SessionSnapshot`
-     - `RecoveryLog`
-   - causal recovery logging now covers invalidation, escalation, truncation, completion, rebuild transitions
-
-10. Slice 4 validation
-   - corrected tester summary accepted
-   - `12` ownership tests + `18` recovery tests + `18` recoverability tests + `11` integration tests = `59` total
-   - Slice 4 accepted
-   - `Phase 05` accepted as complete
-
-### Next
-
-1. `Phase 06` planning
-2. broader engine implementation stage
-3. real-engine integration against selected `weed/storage/block*` constraints and failure classes

sw-block/.private/phase/phase-05.md

@@ -1,356 +0,0 @@
-# Phase 05
-
-Date: 2026-03-29
-Status: complete
-Purpose: begin the real V2 engine track under `sw-block/` by moving from prototype proof to the first engine slice
-
-## Why This Phase Exists
-
-The project has now completed:
-
-1. V2 design/FSM closure
-2. V2 protocol/simulator validation
-3. Phase 04 prototype closure
-4. Phase 4.5 evidence hardening
-
-So the next step is no longer:
-
-- extend prototype breadth
-
-The next step is:
-
-- start disciplined real V2 engine work
-
-## Phase Goal
-
-Start the real V2 engine line under `sw-block/` with:
-
-1. explicit engine module location
-2. Slice 1 ownership-core boundaries
-3. first engine ownership-core implementation
-4. engine-side validation tied back to accepted prototype invariants
-
-## Relationship To Previous Phases
-
-`Phase 05` is built on:
-
-- `sw-block/docs/archive/design/v2-engine-readiness-review.md`
-- `sw-block/docs/archive/design/v2-engine-slicing-plan.md`
-- `sw-block/.private/phase/phase-04.md`
-- `sw-block/.private/phase/phase-4.5.md`
-
-This is a new implementation phase.
-
-It is not:
-
-1. more prototype expansion
-2. V1 integration
-3. backend redesign
-
-## Scope
-
-### In scope
-
-1. choose real V2 engine module location under `sw-block/`
-2. define Slice 1 file/module boundaries
-3. write short engine ownership-core spec
-4. start Slice 1 implementation:
-   - stable per-replica sender object
-   - stable recovery-session object
-   - session identity fencing
-   - endpoint / epoch invalidation
-   - ownership registry / sender-group equivalent
-5. add focused engine-side ownership/fencing tests
-
-### Out of scope
-
-1. Smart WAL expansion
-2. full storage/backend redesign
-3. full rebuild-source decision logic
-4. V1 production integration
-5. performance work
-6. full product integration
-
-## Planned Slices
-
-### P0: Engine Planning Setup
-
-1. choose real V2 engine module location under `sw-block/`
-2. define Slice 1 file/module boundaries
-3. write ownership-core spec
-4. map 3-5 acceptance scenarios to Slice 1 expectations
-
-Status:
-
-- accepted
-- engine module location chosen: `sw-block/engine/replication/`
-- Slice 1 boundaries are explicit enough to start implementation
-
-### P1: Slice 1 Ownership Core
-
-1. implement stable per-replica sender object
-2. implement stable recovery-session object
-3. implement sender/session identity fencing
-4. implement endpoint / epoch invalidation
-5. implement ownership registry
-
-Status:
-
-- accepted
-- stable `ReplicaID` is now explicit and separate from mutable `Endpoint`
-- engine registry is keyed by stable identity, not address-shaped strings
-- real changed-`DataAddr` preservation is covered by test
-
-### P2: Slice 1 Validation
-
-1. engine-side tests for ownership/fencing
-2. changed-address case
-3. stale-session rejection case
-4. epoch-bump invalidation case
-5. traceability back to accepted prototype behavior
-
-Status:
-
-- accepted
-- Slice 1 ownership/fencing tests are in place and passing
-- acceptance/gate mapping is strong enough to move to Slice 2
-
-### P3: Slice 2 Planning Setup
-
-1. define Slice 2 boundaries explicitly
-2. distinguish Slice 2 core from carried-forward prototype support
-3. map Slice 2 engine expectations from accepted prototype evidence
-4. prepare Slice 2 validation targets
-
-Status:
-
-- accepted
-- Slice 2 recovery execution core is implemented and validated
-- corrected tester summary accepted:
-  - `12` ownership tests
-  - `18` recovery tests
-  - `30` total
-
-### P4: Slice 3 Planning Setup
-
-1. define Slice 3 boundaries explicitly
-2. connect recovery decisions to real engine recoverability inputs
-3. make trusted-base / rebuild-source decision use real engine data inputs
-4. prepare Slice 3 validation targets
-
-Status:
-
-- accepted
-- Slice 3 data / recoverability core is implemented and validated
-- corrected tester summary accepted:
-  - `12` ownership tests
-  - `18` recovery tests
-  - `18` recoverability tests
-  - `48` total
-- important boundary preserved:
-  - engine proves historical-correctness prerequisites
-  - full historical reconstruction proof remains simulator-side
-
-## Slice 3 Guardrails
-
-Slice 3 is the point where V2 must move from:
-
-- recovery automaton is coherent
-
-to:
-
-- recovery basis is provable
-
-So Slice 3 must stay tight.
-
-### Guardrail 1: No optimistic watermark in place of recoverability proof
-
-Do not accept:
-
-- loose head/tail watermarks
-- "looks retained enough"
-- heuristic recoverability
-
-Slice 3 should prove:
-
-1. why a gap is recoverable
-2. why a gap is unrecoverable
-
-### Guardrail 2: No current extent state pretending to be historical correctness
-
-Do not accept:
-
-- current extent image as substitute for target-LSN truth
-- checkpoint/base state that leaks newer state into older historical queries
-
-Slice 3 should prove historical correctness at the actual recovery target.
-
-### Guardrail 3: No `snapshot + tail` without trusted-base proof
-
-Do not accept:
-
-- "snapshot exists" as sufficient
-
-Require:
-
-1. trusted base exists
-2. trusted base covers the required base state
-3. retained tail can be replayed continuously from that base to the target
-
-If not, recovery must use:
-
-- `FullBase`
-
-### Guardrail 4: Truncation is protocol boundary, not cleanup policy
-
-Do not treat truncation as:
-
-- optional cleanup
-- post-recovery tidying
-
-Treat truncation as:
-
-1. divergent tail removal
-2. explicit safe-boundary restoration
-3. prerequisite for safe `InSync` / recovery completion where applicable
-
-### P5: Slice 4 Planning Setup
-
-1. define Slice 4 boundaries explicitly
-2. connect engine control/recovery core to real assignment/control intent entry path
-3. add engine observability / debug surface for ownership and recovery failures
-4. prepare integration validation against V2-boundary failure classes
-
-Status:
-
-- accepted
-- Slice 4 integration closure is implemented and validated
-- corrected tester summary accepted:
-  - `12` ownership tests
-  - `18` recovery tests
-  - `18` recoverability tests
-  - `11` integration tests
-  - `59` total
-
-## Slice 4 Guardrails
-
-Slice 4 should close integration, not just add an entry point and some logs.
-
-### Guardrail 1: Entry path must actually drive recovery
-
-Do not accept:
-
-- tests that manually push sender/session state while only pretending to use integration entry points
-
-Require:
-
-1. real assignment/control intent entry path
-2. session creation / invalidation / restart triggered through that path
-3. recovery flow driven from that path, not only from unit-level helper calls
-
-### Guardrail 2: Changed-address must survive the real entry path
-
-Do not accept:
-
-- changed-address correctness proven only at local object level
-
-Require:
-
-1. stable `ReplicaID` survives real assignment/update entry path
-2. endpoint update invalidates old session correctly
-3. new recovery session is created correctly on updated endpoint
-
-### Guardrail 3: Observability must show protocol causality
-
-Do not accept:
-
-- only state snapshots
-- only phase dumps
-
-Require observability that can explain:
-
-1. why recovery entered `NeedsRebuild`
-2. why a session was superseded
-3. why a completion or progress update was rejected
-4. why endpoint / epoch change caused invalidation
-
-### Guardrail 4: Failure replay must be explainable
-
-Do not accept:
-
-- a replay that reproduces failure but cannot explain the cause from engine observability
-
-Require:
-
-1. selected failure-class replays through the real entry path
-2. observability sufficient to explain the control/recovery decision
-3. reviewability against key V2-boundary failures
-
-## Exit Criteria
-
-Phase 05 Slice 1 is done when:
-
-1. the real V2 engine module location is chosen
-2. Slice 1 boundaries are explicit
-3. engine ownership core exists under `sw-block/`
-4. engine-side ownership/fencing tests pass
-5. Slice 1 evidence is reviewable against prototype expectations
-
-This bar is now met.
-
-Phase 05 Slice 2 is done when:
-
-1. engine-side recovery execution flow exists
-2. zero-gap / catch-up / needs-rebuild branching is explicit
-3. stale execution is rejected during active recovery
-4. bounded catch-up semantics are enforced in engine path
-5. rebuild execution shell is validated
-
-This bar is now met.
-
-Phase 05 Slice 3 is done when:
-
-1. recoverable vs unrecoverable gap uses real engine recoverability inputs
-2. trusted-base / rebuild-source decision uses real engine data inputs
-3. truncation / safe-boundary handling is tied to real engine state
-4. history-driven engine APIs exist for recovery decisions
-5. Slice 3 validation is reviewable without overclaiming full historical reconstruction
-
-This bar is now met.
-
-Phase 05 Slice 4 is done when:
-
-1. real assignment/control intent entry path exists
-2. changed-address recovery works through the real entry path
-3. observability explains protocol causality, not only state snapshots
-4. selected V2-boundary failures are replayable and diagnosable through engine integration tests
-
-This bar is now met.
-
-## Assignment For `sw`
-
-Phase 05 is now complete.
-
-Next phase:
-
-- `Phase 06` broader engine implementation stage
-
-## Assignment For `tester`
-
-Phase 05 validation is complete.
-
-Next phase:
-
-- `Phase 06` engine implementation validation against real-engine constraints and failure classes
-
-## Management Rule
-
-`Phase 05` should stay narrow.
-
-It should start the engine line with:
-
-1. ownership
-2. fencing
-3. validation
-
-It should not try to absorb later slices early.

sw-block/.private/phase/phase-06-decisions.md

@@ -1,68 +0,0 @@
-# Phase 06 Decisions
-
-## Decision 1: Phase 06 is broader engine implementation, not new design
-
-The protocol shape and engine core contracts were already accepted.
-
-Phase 06 implemented around them.
-
-## Decision 2: Phase 06 must connect to real constraints
-
-This phase explicitly used:
-
-1. `learn/projects/sw-block/` for failure gates and test lineage
-2. `weed/storage/block*` for real implementation constraints
-
-without importing V1 structure as the V2 design template.
-
-## Decision 3: Phase 06 should replace key synchronous conveniences
-
-The accepted Slice 4 convenience flows were sufficient for closure work, but broader engine work required real step boundaries.
-
-This is now satisfied via planner/executor separation.
-
-## Decision 4: Phase 06 ends with a runnable engine stage decision
-
-Result:
-
-- yes, the project now has a broader runnable engine stage that is ready to proceed to real-system integration / product-path work
-
-## Decision 5: Phase 06 P0 is accepted
-
-Accepted scope:
-
-1. adapter/module boundaries
-2. convenience-flow classification
-3. initial real-engine stage framing
-
-## Decision 6: Phase 06 P1 is accepted
-
-Accepted scope:
-
-1. storage/control adapter interfaces
-2. `RecoveryDriver` planner/resource-acquisition layer
-3. full-base and WAL retention resource contracts
-4. fail-closed preconditions on planning paths
-
-## Decision 7: Phase 06 P2 is accepted
-
-Accepted scope:
-
-1. explicit planner/executor split on top of `RecoveryPlan`
-2. executor-owned cleanup symmetry on success/failure/cancellation
-3. plan-bound rebuild execution with no policy re-derivation at execute time
-4. synchronous orchestrator completion helpers remain test-only convenience
-
-## Decision 8: Phase 06 P3 is accepted
-
-Accepted scope:
-
-1. selected real failure classes validated through the engine path
-2. cross-layer engine/storage proof validation
-3. diagnosable failure when proof or resource acquisition cannot be established
-
-## Decision 9: Phase 06 is complete
-
-Next step:
-
-- `Phase 07` real-system integration / product-path decision

sw-block/.private/phase/phase-06-log.md

@@ -1,51 +0,0 @@
-# Phase 06 Log
-
-## 2026-03-30
-
-### Opened
-
-`Phase 06` opened as:
-
-- broader engine implementation stage
-
-### Starting basis
-
-1. `Phase 05`: complete
-2. engine core and integration closure accepted
-3. next work moves from slice proof to broader runnable engine stage
-
-### Accepted
-
-1. Phase 06 P0
-   - adapter/module boundaries defined
-   - convenience flows explicitly classified
-
-2. Phase 06 P1
-   - storage/control adapter surfaces defined
-   - `RecoveryDriver` added as planner/resource-acquisition layer
-   - full-base rebuild now has explicit resource contract
-   - WAL pin contract tied to actual recovery need
-   - driver preconditions fail closed
-
-3. Phase 06 P2
-   - explicit planner/executor split accepted
-   - executor owns release symmetry on success, failure, and cancellation
-   - rebuild execution now consumes plan-bound source/target values
-   - tester final validation accepted with reduced-but-sufficient rebuild failure-path coverage
-
-4. Phase 06 P3
-   - selected real failure classes validated through the engine path
-   - changed-address restart now uses plan cancellation and re-plan flow
-   - stale execution is caught through the executor-managed loop
-   - cross-layer trusted-base / replayable-tail proof path validated end-to-end
-   - rebuild planning failures now clean up sessions and remain diagnosable
-
-### Closed
-
-`Phase 06` closed as complete.
-
-### Next
-
-1. Phase 07 real-system integration / product-path decision
-2. service-slice integration against real control/storage surroundings
-3. first product-path gating decision

sw-block/.private/phase/phase-06.md

@@ -1,193 +0,0 @@
-# Phase 06
-
-Date: 2026-03-30
-Status: complete
-Purpose: move from validated engine slices to the first broader runnable V2 engine stage
-
-## Why This Phase Exists
-
-`Phase 05` established and validated:
-
-1. ownership core
-2. recovery execution core
-3. recoverability/data gating core
-4. integration closure
-
-What still does not exist is a broader engine stage that can run with:
-
-1. real control-plane inputs
-2. real persistence/backing inputs
-3. non-trivial execution loops instead of only synchronous convenience paths
-
-So `Phase 06` exists to turn the accepted engine shape into the first broader runnable engine stage.
-
-Phase 06 must connect the accepted engine core to real control and real storage truth, not just wrap current abstractions with adapters.
-
-## Phase Goal
-
-Build the first broader V2 engine stage without reopening protocol shape.
-
-This phase should focus on:
-
-1. real engine adapters around the accepted core
-2. asynchronous or stepwise execution paths where Slice 4 used synchronous helpers
-3. real retained-history / checkpoint input plumbing
-4. validation against selected real failure classes and real implementation constraints
-
-## Overall Roadmap
-
-Completed:
-
-1. Phase 01-03: design + simulator
-2. Phase 04: prototype closure
-3. Phase 4.5: evidence hardening
-4. Phase 05: engine slice closure
-5. Phase 06: broader engine implementation stage
-
-Next:
-
-1. Phase 07: real-system integration / product-path decision
-
-This roadmap should stay strict:
-
-- no return to broad prototype expansion
-- no uncontrolled engine sprawl
-
-## Scope
-
-### In scope
-
-1. control-plane adapter into `sw-block/engine/replication/`
-2. retained-history / checkpoint adapter into engine recoverability APIs
-3. replacement of synchronous convenience flows with explicit engine steps where needed
-4. engine error taxonomy and observability tightening
-5. validation against selected real failure classes from:
-   - `learn/projects/sw-block/`
-   - `weed/storage/block*`
-
-### Out of scope
-
-1. Smart WAL expansion
-2. full backend redesign
-3. performance optimization as primary goal
-4. V1 replacement rollout
-5. full product integration
-
-## Phase 06 Items
-
-### P0: Engine Stage Plan
-
-Status:
-
-- accepted
-- module boundaries now explicit:
-  - `adapter.go`
-  - `driver.go`
-  - `orchestrator.go` classification
-- convenience flows are now classified as:
-  - test-only convenience wrapper
-  - stepwise engine task
-  - planner/executor split
-
-### P1: Control / History Adapters
-
-Status:
-
-- accepted
-- `StorageAdapter` boundary exists and is exercised by tests
-- full-base rebuild now has a real pin/release contract
-- WAL pinning is tied to actual recovery contract, not loose watermark use
-- planner fails closed on missing sender / missing session / wrong session kind
-
-### P2: Execution Driver
-
-Status:
-
-- accepted
-- executor now owns resource lifecycle on success / failure / cancellation
-- catch-up execution is stepwise and budget-checked per progress step
-- rebuild execution consumes plan-bound source/target values and does not re-derive policy at execute time
-- `CompleteCatchUp` / `CompleteRebuild` remain test-only convenience wrappers
-- tester validation accepted with reduced-but-sufficient rebuild failure-path coverage
-
-### P3: Validation Against Real Failure Classes
-
-Status:
-
-- accepted
-- changed-address restart now validated through planner/executor path with plan cancellation
-- stale epoch/session during active execution now validated through the executor-managed loop
-- cross-layer trusted-base / replayable-tail proof path validated end-to-end
-- rebuild fallback and pin-failure cleanup now fail closed and are diagnosable
-
-## Guardrails
-
-### Guardrail 1: Do not reopen protocol shape
-
-Phase 06 implemented around accepted engine slices and did not reopen:
-
-1. sender/session authority model
-2. bounded catch-up contract
-3. recoverability/truncation boundary
-
-### Guardrail 2: Do not let adapters smuggle V1 structure back in
-
-V1 code and docs remain:
-
-1. constraints
-2. failure gates
-3. integration references
-
-not the V2 architecture template.
-
-### Guardrail 3: Prefer explicit engine steps over synchronous convenience
-
-Key convenience helpers remain test-only. Real engine work now has explicit planner/executor boundaries.
-
-### Guardrail 4: Keep evidence quality high
-
-Phase 06 improved:
-
-1. cross-layer traceability
-2. diagnosability
-3. real-failure validation
-
-without growing protocol surface.
-
-### Guardrail 5: Do not fake storage truth with metadata-only adapters
-
-Phase 06 now requires:
-
-1. trusted base to come from storage-side truth
-2. replayable tail to be grounded in retention state
-3. observable rejection when those proofs cannot be established
-
-## Exit Criteria
-
-Phase 06 is done when:
-
-1. engine has real control/history adapters into the accepted core
-2. engine has real storage/base adapters into the accepted core
-3. key synchronous convenience paths are explicitly classified or replaced by real engine steps where necessary
-4. selected real failure classes are validated against the engine stage
-5. at least one cross-layer storage/engine proof path is validated end-to-end
-6. engine observability remains good enough to explain recovery causality
-
-Status:
-
-- met
-
-## Closeout
-
-`Phase 06` is complete.
-
-It established:
-
-1. a broader runnable engine stage around the accepted Phase 05 core
-2. real planner/executor/resource contracts
-3. validated failure-class behavior through the engine path
-4. diagnosable proof rejection and cleanup behavior
-
-Next step:
-
-- `Phase 07` real-system integration / product-path decision