Build the Rust worker against the protoc that ships with the build (#10881)

* worker: compile plugin.proto with the protoc that ships with the build

seaweed-volume already does this: protoc-bin-vendored carries the binary, so
the build needs no package manager and every build sees the same version. An
explicit PROTOC still wins, which is what lets the lance crates - whose own
build scripts read the same variable - share it.

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

* ci: point the worker builds at the vendored protoc

The jobs installed protobuf-compiler for lance's build scripts. They read
PROTOC, so pointing it at the binary protoc-bin-vendored already puts in the
registry serves them without a system package - one less apt call on the way
to a release, and the same protoc a developer's build uses.

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

* 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

@@ -49,11 +49,6 @@ jobs:
           # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
           echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
 
-      # lance's build scripts compile their own protos, and unlike seaweed-volume
-      # they do not vendor a protoc to do it with.
-      - name: Install protoc
-        run: sudo apt-get install -y protobuf-compiler
-
       - name: Cache cargo registry and target
         uses: actions/cache@v6
         with:
@@ -66,6 +61,21 @@ jobs:
           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
+          # The version from the lock, not whatever else a restored cache holds.
+          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
+          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
+          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
+          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build normal variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}

.github/workflows/container_latest.yml

@@ -93,11 +93,6 @@ jobs:
           # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
           echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
 
-      # lance's build scripts compile their own protos, and unlike seaweed-volume
-      # they do not vendor a protoc to do it with.
-      - name: Install protoc
-        run: sudo apt-get install -y protobuf-compiler
-
       - name: Cache cargo registry and target
         uses: actions/cache@v6
         with:
@@ -110,6 +105,21 @@ jobs:
           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
+          # The version from the lock, not whatever else a restored cache holds.
+          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
+          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
+          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
+          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build large-disk variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}

.github/workflows/container_release_unified.yml

@@ -77,11 +77,6 @@ jobs:
           # Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
           echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
 
-      # lance's build scripts compile their own protos, and unlike seaweed-volume
-      # they do not vendor a protoc to do it with.
-      - name: Install protoc
-        run: sudo apt-get install -y protobuf-compiler
-
       - name: Cache cargo registry and target
         uses: actions/cache@v6
         with:
@@ -94,6 +89,21 @@ jobs:
           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
+          # The version from the lock, not whatever else a restored cache holds.
+          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
+          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
+          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
+          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build large-disk variant
         env:
           SEAWEEDFS_COMMIT: ${{ github.sha }}

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

@@ -36,11 +36,6 @@ jobs:
       - name: Install Rust toolchain
         uses: dtolnay/rust-toolchain@stable
 
-      # lance's build scripts compile their own protos, and unlike seaweed-volume
-      # they do not vendor a protoc to do it with.
-      - name: Install protoc
-        run: sudo apt-get install -y protobuf-compiler
-
       # 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
@@ -58,6 +53,21 @@ jobs:
           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
+          # The version from the lock, not whatever else a restored cache holds.
+          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
+          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
+          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
+          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
+          echo "PROTOC=$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

.github/workflows/rust_binaries_release.yml

@@ -152,11 +152,6 @@ jobs:
           sudo apt-get install -y gcc-aarch64-linux-gnu
           echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
 
-      # lance's build scripts compile their own protos, and unlike seaweed-volume
-      # they do not vendor a protoc to do it with.
-      - name: Install protoc
-        run: sudo apt-get install -y protobuf-compiler
-
       - name: Cache cargo registry and target
         uses: actions/cache@v6
         with:
@@ -168,6 +163,21 @@ jobs:
           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
+          # The version from the lock, not whatever else a restored cache holds.
+          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
+          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
+          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
+          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
+          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
+
       - name: Build the Rust maintenance worker
         run: |
           cd seaweed-worker

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 +12,17 @@ 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, in their own build-script
+processes, which nothing our build script sets can reach. They need a protoc of
+their own: either one on PATH — `brew install protobuf`, `apt install
+protobuf-compiler` — or `PROTOC` naming one. CI points it at the vendored
+binary for the runner's platform, resolved from the version in `Cargo.lock`.
+
 ## Running
 
     cargo run -p weed-lance-worker -- --admin 127.0.0.1:23646

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()