docs: say what the worker build needs from protoc

The lance crates' build scripts are the ones that need it, not ours, and they
take the same vendored binary.

Claude-Session: https://claude.ai/code/session_01Rkp1Mw5E89Jp6dzJFYiMrm

.github/workflows/container_dev.yml

@@ -6,6 +6,7 @@ on:
     paths:
       - 'weed/**'
       - 'seaweed-volume/**'
+      - 'seaweed-worker/**'
       - 'docker/**'
       - 'go.mod'
       - 'go.sum'
@@ -16,7 +17,7 @@ permissions:
 
 jobs:
 
-  # ── Pre-build Rust volume server binaries natively ──────────────────
+  # ── Pre-build the Rust binaries natively ────────────────────────────
   build-rust-binaries:
     runs-on: ubuntu-22.04
     strategy:
@@ -55,10 +56,23 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             seaweed-volume/target
-          key: rust-docker-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+            seaweed-worker/target/${{ matrix.target }}/release
+          key: rust-docker-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock', 'seaweed-worker/Cargo.lock') }}
           restore-keys: |
             rust-docker-dev-${{ matrix.target }}-
 
+      # lance's build scripts compile their own protos and look for a protoc.
+      # Point them at the one protoc-bin-vendored ships, which seaweed-worker's
+      # own build already uses, so no job depends on a system package and every
+      # build sees the same version.
+      - name: Use the vendored protoc
+        run: |
+          cd seaweed-worker
+          cargo fetch
+          protoc=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-linux-x86_64*/bin/protoc' | head -1)
+          test -x "$protoc" || { echo "no vendored protoc in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build normal variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}
@@ -67,11 +81,19 @@ jobs:
           cargo build --release --target ${{ matrix.target }} --no-default-features
           cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
 
+      - name: Build the Rust maintenance worker
+        run: |
+          cd seaweed-worker
+          cargo build --release -p weed-lance-worker --target ${{ matrix.target }}
+          cp target/${{ matrix.target }}/release/weed-worker ../weed-worker-${{ matrix.arch }}
+
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
         with:
-          name: rust-volume-${{ matrix.arch }}
-          path: weed-volume-normal-${{ matrix.arch }}
+          name: rust-bins-${{ matrix.arch }}
+          path: |
+            weed-volume-normal-${{ matrix.arch }}
+            weed-worker-${{ matrix.arch }}
 
   build-dev-containers:
     needs: [build-rust-binaries]
@@ -84,7 +106,7 @@ jobs:
       - name: Download pre-built Rust binaries
         uses: actions/download-artifact@v8
         with:
-          pattern: rust-volume-*
+          pattern: rust-bins-*
           merge-multiple: true
           path: ./rust-bins
 
@@ -98,7 +120,16 @@ jobs:
               echo "Placed pre-built Rust binary for ${arch}"
             fi
           done
+          mkdir -p docker/weed-worker-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-worker-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-worker-prebuilt/weed-worker-${arch}"
+              echo "Placed pre-built Rust worker for ${arch}"
+            fi
+          done
           ls -la docker/weed-volume-prebuilt/
+          ls -la docker/weed-worker-prebuilt/
 
       - name: Docker meta
         id: docker_meta

.github/workflows/container_latest.yml

@@ -59,7 +59,7 @@ jobs:
             echo "publish=true" >> "$GITHUB_OUTPUT"
           fi
 
-  # ── Pre-build Rust volume server binaries natively ──────────────────
+  # ── Pre-build the Rust binaries natively ────────────────────────────
   build-rust-binaries:
     runs-on: ubuntu-22.04
     strategy:
@@ -100,10 +100,23 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             seaweed-volume/target
-          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+            seaweed-worker/target/${{ matrix.target }}/release
+          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock', 'seaweed-worker/Cargo.lock') }}
           restore-keys: |
             rust-docker-${{ matrix.target }}-
 
+      # lance's build scripts compile their own protos and look for a protoc.
+      # Point them at the one protoc-bin-vendored ships, which seaweed-worker's
+      # own build already uses, so no job depends on a system package and every
+      # build sees the same version.
+      - name: Use the vendored protoc
+        run: |
+          cd seaweed-worker
+          cargo fetch
+          protoc=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-linux-x86_64*/bin/protoc' | head -1)
+          test -x "$protoc" || { echo "no vendored protoc in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build large-disk variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}
@@ -120,13 +133,20 @@ jobs:
           cargo build --release --target ${{ matrix.target }} --no-default-features
           cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
 
+      - name: Build the Rust maintenance worker
+        run: |
+          cd seaweed-worker
+          cargo build --release -p weed-lance-worker --target ${{ matrix.target }}
+          cp target/${{ matrix.target }}/release/weed-worker ../weed-worker-${{ matrix.arch }}
+
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
         with:
-          name: rust-volume-${{ matrix.arch }}
+          name: rust-bins-${{ matrix.arch }}
           path: |
             weed-volume-large-disk-${{ matrix.arch }}
             weed-volume-normal-${{ matrix.arch }}
+            weed-worker-${{ matrix.arch }}
 
   build:
     needs: [setup, build-rust-binaries]
@@ -174,7 +194,7 @@ jobs:
       - name: Download pre-built Rust binaries
         uses: actions/download-artifact@v8
         with:
-          pattern: rust-volume-*
+          pattern: rust-bins-*
           merge-multiple: true
           path: ./rust-bins
 
@@ -188,7 +208,16 @@ jobs:
               echo "Placed pre-built Rust binary for ${arch}"
             fi
           done
+          mkdir -p docker/weed-worker-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-worker-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-worker-prebuilt/weed-worker-${arch}"
+              echo "Placed pre-built Rust worker for ${arch}"
+            fi
+          done
           ls -la docker/weed-volume-prebuilt/
+          ls -la docker/weed-worker-prebuilt/
 
       - name: Docker meta
         id: docker_meta
@@ -286,7 +315,7 @@ jobs:
         if: needs.setup.outputs.publish != 'true'
         uses: actions/download-artifact@v8
         with:
-          pattern: rust-volume-*
+          pattern: rust-bins-*
           merge-multiple: true
           path: ./rust-bins
       - name: Place Rust binaries in Docker context for local scan
@@ -304,7 +333,16 @@ jobs:
               echo "Placed pre-built Rust binary for ${arch}"
             fi
           done
+          mkdir -p docker/weed-worker-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-worker-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-worker-prebuilt/weed-worker-${arch}"
+              echo "Placed pre-built Rust worker for ${arch}"
+            fi
+          done
           ls -la docker/weed-volume-prebuilt/
+          ls -la docker/weed-worker-prebuilt/
       - name: Create BuildKit config for local scan build
         if: needs.setup.outputs.publish != 'true'
         run: |

.github/workflows/container_release_unified.yml

@@ -42,9 +42,10 @@ concurrency:
 
 jobs:
 
-  # ── Pre-build Rust volume server binaries natively ──────────────────
-  # Cross-compiles for amd64 and arm64 without QEMU, turning a 5-hour
-  # emulated cargo build into ~15 minutes of native compilation.
+  # ── Pre-build the Rust binaries natively ────────────────────────────
+  # The volume server and the Rust maintenance worker, cross-compiled for
+  # amd64 and arm64 without QEMU, turning a 5-hour emulated cargo build into
+  # ~15 minutes of native compilation.
   build-rust-binaries:
     runs-on: ubuntu-22.04
     strategy:
@@ -83,10 +84,23 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             seaweed-volume/target
-          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
+            seaweed-worker/target/${{ matrix.target }}/release
+          key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock', 'seaweed-worker/Cargo.lock') }}
           restore-keys: |
             rust-docker-${{ matrix.target }}-
 
+      # lance's build scripts compile their own protos and look for a protoc.
+      # Point them at the one protoc-bin-vendored ships, which seaweed-worker's
+      # own build already uses, so no job depends on a system package and every
+      # build sees the same version.
+      - name: Use the vendored protoc
+        run: |
+          cd seaweed-worker
+          cargo fetch
+          protoc=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-linux-x86_64*/bin/protoc' | head -1)
+          test -x "$protoc" || { echo "no vendored protoc in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build large-disk variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}
@@ -103,13 +117,20 @@ jobs:
           cargo build --release --target ${{ matrix.target }} --no-default-features
           cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
 
+      - name: Build the Rust maintenance worker
+        run: |
+          cd seaweed-worker
+          cargo build --release -p weed-lance-worker --target ${{ matrix.target }}
+          cp target/${{ matrix.target }}/release/weed-worker ../weed-worker-${{ matrix.arch }}
+
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
         with:
-          name: rust-volume-${{ matrix.arch }}
+          name: rust-bins-${{ matrix.arch }}
           path: |
             weed-volume-large-disk-${{ matrix.arch }}
             weed-volume-normal-${{ matrix.arch }}
+            weed-worker-${{ matrix.arch }}
 
   # One job per (variant, platform) on a native runner, pushed by digest;
   # the merge job stitches the digests into one multi-arch tag.
@@ -155,7 +176,7 @@ jobs:
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
         uses: actions/download-artifact@v8
         with:
-          pattern: rust-volume-*
+          pattern: rust-bins-*
           merge-multiple: true
           path: ./rust-bins
 
@@ -170,7 +191,16 @@ jobs:
               echo "Placed pre-built Rust binary for ${arch}"
             fi
           done
+          mkdir -p docker/weed-worker-prebuilt
+          for arch in amd64 arm64; do
+            src="./rust-bins/weed-worker-${arch}"
+            if [ -f "$src" ]; then
+              cp "$src" "docker/weed-worker-prebuilt/weed-worker-${arch}"
+              echo "Placed pre-built Rust worker for ${arch}"
+            fi
+          done
           ls -la docker/weed-volume-prebuilt/
+          ls -la docker/weed-worker-prebuilt/
 
       - name: Free Disk Space
         if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant

.github/workflows/rust-worker-tests.yml

@@ -0,0 +1,79 @@
+name: "Rust Plugin Worker Tests"
+
+on:
+  pull_request:
+    branches: [ master ]
+    paths:
+      - 'seaweed-worker/**'
+      - 'weed/pb/plugin.proto'
+      - '.github/workflows/rust-worker-tests.yml'
+  push:
+    branches: [ master, main ]
+    paths:
+      - 'seaweed-worker/**'
+      - 'weed/pb/plugin.proto'
+      - '.github/workflows/rust-worker-tests.yml'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  rust-worker-build:
+    name: Rust Plugin Worker Build and Unit Tests
+    runs-on: ubuntu-22.04
+    timeout-minutes: 45
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v7
+        with:
+          persist-credentials: false
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+
+      # cargo tracks its own inputs but not the runner's C toolchain, so a cached
+      # target/ can carry C objects built against a different glibc than we link against.
+      - name: Fingerprint build toolchain
+        id: toolchain
+        run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"
+
+      - name: Cache cargo registry and target
+        uses: actions/cache@v6
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            seaweed-worker/target/release
+          key: rust-worker-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-worker/Cargo.lock') }}
+          restore-keys: |
+            rust-worker-${{ steps.toolchain.outputs.fingerprint }}-
+
+      # lance's build scripts compile their own protos and look for a protoc.
+      # Point them at the one protoc-bin-vendored ships, which seaweed-worker's
+      # own build already uses, so no job depends on a system package and every
+      # build sees the same version.
+      - name: Use the vendored protoc
+        run: |
+          cd seaweed-worker
+          cargo fetch
+          protoc=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-linux-x86_64*/bin/protoc' | head -1)
+          test -x "$protoc" || { echo "no vendored protoc in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
+      # The release profile is what ships, and it is where the release and the
+      # container builds would otherwise discover a break for the first time.
+      - name: Build the plugin workers
+        run: cd seaweed-worker && cargo build --release
+
+      # The tests that need a live gateway skip themselves without one, the way
+      # the Go integration tests skip without Docker; the lifecycle suite in
+      # test/s3tables/lifecycle is what runs them against a real cluster.
+      # Release, so this reuses the build above rather than compiling lance,
+      # arrow and datafusion a second time in another profile.
+      - name: Run unit tests
+        run: cd seaweed-worker && cargo test --release --workspace

.github/workflows/rust_binaries_release.yml

@@ -1,4 +1,4 @@
-name: "rust: build versioned volume server binaries"
+name: "rust: build versioned binaries"
 
 on:
   push:
@@ -113,6 +113,99 @@ jobs:
             weed-volume_${{ matrix.asset_suffix }}.tar.gz
             weed-volume_${{ matrix.asset_suffix }}.tar.gz.md5
 
+  # The Rust maintenance worker: Linux only, because it runs beside the cluster
+  # it maintains rather than on a laptop, and its dependency tree (lance, arrow,
+  # datafusion) makes every extra target an expensive build.
+  build-rust-worker-linux:
+    permissions:
+      contents: write
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        include:
+          - target: x86_64-unknown-linux-gnu
+            asset_suffix: linux_amd64
+          - target: aarch64-unknown-linux-gnu
+            asset_suffix: linux_arm64
+            cross: true
+
+    steps:
+      - uses: actions/checkout@v7
+        with:
+          # The upload step is handed a token explicitly; a cargo build script
+          # should not find another one sitting in the checkout's git config.
+          persist-credentials: false
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          targets: ${{ matrix.target }}
+
+      - name: Install cross-compilation tools
+        if: matrix.cross
+        run: |
+          sudo dpkg --add-architecture arm64
+          sudo sed -i 's/^deb /deb [arch=amd64] /' /etc/apt/sources.list
+          echo "deb [arch=arm64] http://ports.ubuntu.com/ jammy main restricted universe multiverse" | sudo tee /etc/apt/sources.list.d/arm64.list
+          echo "deb [arch=arm64] http://ports.ubuntu.com/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/arm64.list
+          sudo apt-get update
+          sudo apt-get install -y gcc-aarch64-linux-gnu
+          echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
+
+      - name: Cache cargo registry and target
+        uses: actions/cache@v6
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            seaweed-worker/target/${{ matrix.target }}/release
+          key: rust-worker-release-${{ matrix.target }}-${{ hashFiles('seaweed-worker/Cargo.lock') }}
+          restore-keys: |
+            rust-worker-release-${{ matrix.target }}-
+
+      # lance's build scripts compile their own protos and look for a protoc.
+      # Point them at the one protoc-bin-vendored ships, which seaweed-worker's
+      # own build already uses, so no job depends on a system package and every
+      # build sees the same version.
+      - name: Use the vendored protoc
+        run: |
+          cd seaweed-worker
+          cargo fetch
+          protoc=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-linux-x86_64*/bin/protoc' | head -1)
+          test -x "$protoc" || { echo "no vendored protoc in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
+      - name: Build the Rust maintenance worker
+        run: |
+          cd seaweed-worker
+          cargo build --release -p weed-lance-worker --target ${{ matrix.target }}
+
+      - name: Package binary
+        run: |
+          cp seaweed-worker/target/${{ matrix.target }}/release/weed-worker weed-worker
+          tar czf weed-worker_${{ matrix.asset_suffix }}.tar.gz weed-worker
+          rm weed-worker
+          md5sum weed-worker_${{ matrix.asset_suffix }}.tar.gz > weed-worker_${{ matrix.asset_suffix }}.tar.gz.md5
+
+      - name: Upload release assets
+        if: startsWith(github.ref, 'refs/tags/')
+        uses: softprops/action-gh-release@v3
+        with:
+          files: |
+            weed-worker_${{ matrix.asset_suffix }}.tar.gz
+            weed-worker_${{ matrix.asset_suffix }}.tar.gz.md5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Upload artifacts
+        if: ${{ !startsWith(github.ref, 'refs/tags/') }}
+        uses: actions/upload-artifact@v7
+        with:
+          name: rust-worker-${{ matrix.asset_suffix }}
+          path: |
+            weed-worker_${{ matrix.asset_suffix }}.tar.gz
+            weed-worker_${{ matrix.asset_suffix }}.tar.gz.md5
+
   build-rust-volume-darwin:
     permissions:
       contents: write

docker/Dockerfile.go_build

@@ -29,6 +29,7 @@ FROM alpine:3.23 as rust_builder
 ARG TARGETARCH
 ARG TAGS
 COPY weed-volume-prebuilt/ /prebuilt/
+COPY weed-worker-prebuilt/ /prebuilt-worker/
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/seaweed-volume /build/seaweed-volume
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/weed /build/weed
 WORKDIR /build/seaweed-volume
@@ -47,16 +48,30 @@ RUN if [ -f "/prebuilt/weed-volume-${TARGETARCH}" ]; then \
       echo "Skipping Rust build for $TARGETARCH (unsupported)" && \
       touch /weed-volume; \
     fi
+# The Rust maintenance worker is taken pre-built or not at all: the lance jobs
+# it carries pull in arrow and datafusion, a far larger dependency tree than
+# the image build can carry, so an architecture CI did not build for gets the
+# same empty placeholder the entrypoint refuses to exec.
+RUN if [ -f "/prebuilt-worker/weed-worker-${TARGETARCH}" ]; then \
+      echo "Using pre-built Rust worker for ${TARGETARCH}" && \
+      cp "/prebuilt-worker/weed-worker-${TARGETARCH}" /weed-worker; \
+    else \
+      echo "No pre-built Rust worker for ${TARGETARCH}" && \
+      touch /weed-worker; \
+    fi
+
 # Pre-built binaries arrive via GitHub Actions artifacts, which drop the
 # executable bit, so the copied file is 0644 and exec fails with "Permission
-# denied". Restore it (no-op for the empty placeholder, which stays size 0).
-RUN chmod 0755 /weed-volume
+# denied". Restore it (no-op for the empty placeholders, which stay size 0).
+RUN chmod 0755 /weed-volume /weed-worker
 
 FROM alpine AS final
 LABEL author="Chris Lu"
 COPY --from=builder /go/bin/weed /usr/bin/
 # Copy Rust volume server binary (real binary on amd64/arm64, empty placeholder on other platforms)
 COPY --from=rust_builder /weed-volume /usr/bin/weed-volume
+# Same for the Rust maintenance worker, which serves Lance table buckets
+COPY --from=rust_builder /weed-worker /usr/bin/weed-worker
 RUN mkdir -p /etc/seaweedfs
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer.toml /etc/seaweedfs/filer.toml
 COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh

docker/entrypoint.sh

@@ -90,6 +90,16 @@ case "$1" in
   	exec /usr/bin/weed-volume $ARGS $@
 	;;
 
+  'worker-rust')
+  	shift
+  	if [ ! -s /usr/bin/weed-worker ]; then
+  	  echo "Error: Rust maintenance worker is not available on this platform ($(uname -m))." >&2
+  	  echo "Use 'worker' for the Go maintenance worker instead." >&2
+  	  exit 1
+  	fi
+  	exec /usr/bin/weed-worker "$@"
+	;;
+
   'server')
   	ARGS="-dir=/data -volume.max=0 -master.volumeSizeLimitMB=1024"
   	if isArgPassed "-volume.max" "$@"; then

seaweed-worker/Cargo.lock

@@ -4666,6 +4666,70 @@ dependencies = [
  "prost 0.14.4",
 ]
 
+[[package]]
+name = "protoc-bin-vendored"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d1c381df33c98266b5f08186583660090a4ffa0889e76c7e9a5e175f645a67fa"
+dependencies = [
+ "protoc-bin-vendored-linux-aarch_64",
+ "protoc-bin-vendored-linux-ppcle_64",
+ "protoc-bin-vendored-linux-s390_64",
+ "protoc-bin-vendored-linux-x86_32",
+ "protoc-bin-vendored-linux-x86_64",
+ "protoc-bin-vendored-macos-aarch_64",
+ "protoc-bin-vendored-macos-x86_64",
+ "protoc-bin-vendored-win32",
+]
+
+[[package]]
+name = "protoc-bin-vendored-linux-aarch_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c350df4d49b5b9e3ca79f7e646fde2377b199e13cfa87320308397e1f37e1a4c"
+
+[[package]]
+name = "protoc-bin-vendored-linux-ppcle_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a55a63e6c7244f19b5c6393f025017eb5d793fd5467823a099740a7a4222440c"
+
+[[package]]
+name = "protoc-bin-vendored-linux-s390_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1dba5565db4288e935d5330a07c264a4ee8e4a5b4a4e6f4e83fad824cc32f3b0"
+
+[[package]]
+name = "protoc-bin-vendored-linux-x86_32"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8854774b24ee28b7868cd71dccaae8e02a2365e67a4a87a6cd11ee6cdbdf9cf5"
+
+[[package]]
+name = "protoc-bin-vendored-linux-x86_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b38b07546580df720fa464ce124c4b03630a6fb83e05c336fea2a241df7e5d78"
+
+[[package]]
+name = "protoc-bin-vendored-macos-aarch_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "89278a9926ce312e51f1d999fee8825d324d603213344a9a706daa009f1d8092"
+
+[[package]]
+name = "protoc-bin-vendored-macos-x86_64"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "81745feda7ccfb9471d7a4de888f0652e806d5795b61480605d4943176299756"
+
+[[package]]
+name = "protoc-bin-vendored-win32"
+version = "3.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95067976aca6421a523e491fce939a3e65249bac4b977adee0ee9771568e8aa3"
+
 [[package]]
 name = "quick-xml"
 version = "0.39.4"
@@ -5379,6 +5443,7 @@ dependencies = [
  "prometheus",
  "prost 0.13.5",
  "prost-types 0.13.5",
+ "protoc-bin-vendored",
  "tokio",
  "tokio-stream",
  "tonic",

seaweed-worker/README.md

@@ -12,6 +12,18 @@ one.
 `core` knows nothing about any job. A second worker is a new crate beside
 `lance` that depends on it, not a fork of the protocol.
 
+## Building
+
+`core` compiles `plugin.proto` with the protoc that protoc-bin-vendored ships,
+the way seaweed-volume does, so it needs no system install. The lance crates
+compile protos of their own and look for a protoc on PATH or in `PROTOC`, and
+they honour the same vendored one:
+
+    PROTOC=$(find ~/.cargo/registry/src -path '*protoc-bin-vendored-*/bin/protoc' | head -1) \
+      cargo build --release
+
+which is what CI does. A protoc from the platform's package manager works too.
+
 ## Running
 
     cargo run -p weed-lance-worker -- --admin 127.0.0.1:23646
@@ -20,6 +32,22 @@ The admin's *HTTP* address is what an operator has; the gRPC port is derived
 from it the way the Go side does. Dialling the HTTP port fails as "frame with
 invalid size", which reads like a protocol bug rather than a wrong port.
 
+The binary is `weed-worker`, not `weed-lance-worker`: it is the Rust side of
+`weed worker`, and lance is the first family of jobs it carries rather than the
+only one it ever will.
+
+Released builds do not need a toolchain. The worker ships inside the SeaweedFS
+image, beside the Rust volume server, under the verb that mirrors
+`volume-rust`:
+
+    docker run chrislusf/seaweedfs worker-rust --admin admin:23646
+
+and as `weed-worker_linux_{amd64,arm64}.tar.gz` on each GitHub release. Both are
+linux amd64/arm64 only — lance, arrow and datafusion make every extra target an
+expensive build, and the worker runs beside the cluster it maintains. On an
+architecture without a build the image carries an empty placeholder and the
+entrypoint says so rather than failing as "not found".
+
 ## Metrics
 
     cargo run -p weed-lance-worker -- --admin 127.0.0.1:23646 --metrics-port 9328

seaweed-worker/crates/core/Cargo.toml

@@ -21,3 +21,7 @@ tracing.workspace = true
 
 [build-dependencies]
 tonic-build.workspace = true
+# Ships protoc with the build so neither CI nor a developer needs a system
+# install, and so the version is pinned rather than whatever the platform's
+# package manager happens to carry. The same crate seaweed-volume uses.
+protoc-bin-vendored = "3"

seaweed-worker/crates/core/build.rs

@@ -1,4 +1,12 @@
 fn main() -> Result<(), Box<dyn std::error::Error>> {
+    // Use the protoc that ships with protoc-bin-vendored rather than a system
+    // one, so the build needs no package manager and always sees the same
+    // version. An explicit PROTOC still wins, for packagers supplying their own
+    // and for the lance crates, whose own build scripts read the same variable.
+    if std::env::var_os("PROTOC").is_none() {
+        std::env::set_var("PROTOC", protoc_bin_vendored::protoc_bin_path()?);
+    }
+
     // Compiled straight out of the Go tree, the way seaweed-volume already reads
     // filer.proto, so the contract cannot drift from a vendored copy.
     tonic_build::configure()

seaweed-worker/crates/lance/Cargo.toml

@@ -7,8 +7,11 @@ description = "SeaweedFS maintenance worker for Lance tables"
 [lib]
 name = "weed_lance_worker"
 
+# The binary is not named for lance: it is the Rust side of `weed worker`, and
+# the job families it registers will outgrow this crate. When a second one
+# arrives the bin target moves to a crate of its own under the same name.
 [[bin]]
-name = "weed-lance-worker"
+name = "weed-worker"
 path = "src/main.rs"
 
 [dependencies]

seaweed-worker/crates/lance/src/main.rs

@@ -13,8 +13,8 @@ use weed_lance_worker::metrics::LanceMetrics;
 /// language and an operator should not have to learn a second set of names.
 #[derive(Parser, Debug)]
 #[command(
-    name = "weed-lance-worker",
-    about = "SeaweedFS maintenance worker for Lance tables"
+    name = "weed-worker",
+    about = "SeaweedFS maintenance worker"
 )]
 struct Args {
     /// Admin server gRPC address.