mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-07 23:07:34 -04:00
fix(ci): shard single-arch backend matrix under GitHub's 256-job limit (#10703)
GitHub Actions refuses to instantiate a matrix that would generate more than 256 jobs. It does so silently: the job hangs forever at "Waiting for pending jobs" and the whole run is marked `failure` while every other job stays green. This is exactly what happened on the v4.6.1 tag build (run 28786533892): the single-arch build matrix had grown to 268 entries, so `backend-jobs-singlearch` (and its downstream merge) never produced a single job, and the release build "failed" with no failing job to point at. The single-arch list is the one that grows unbounded as backends are added, so shard it across a fixed number of matrix jobs (SINGLEARCH_SHARDS=4, ~67 entries each today, headroom to ~1020 backends). Each merge shard `needs:` only its matching build shard, preserving the "merge waits only on its own build" property that keeps slow CUDA/ROCm builds from gating multi-arch manifest assembly. changed-backends.js now emits per-shard matrix/has-* outputs and throws loudly if a shard ever reaches the 256 limit (telling the maintainer to bump SINGLEARCH_SHARDS and add matching job blocks) instead of letting GitHub drop the overflow silently. backend.yml and backend_pr.yml define the four build + four merge shard jobs; multi-arch and darwin groups are untouched. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
@@ -209,23 +209,75 @@ function splitByArch(entries) {
|
||||
return { multiarch, singlearch };
|
||||
}
|
||||
|
||||
// GitHub Actions refuses to instantiate a matrix with more than 256 jobs. When
|
||||
// it happens the job doesn't error visibly — it hangs forever at "Waiting for
|
||||
// pending jobs" and the whole run is marked `failure` while every *other* job
|
||||
// stays green (seen on the v4.6.1 tag build, run 28786533892: 268 single-arch
|
||||
// entries, zero single-arch jobs ever created). The single-arch list is the
|
||||
// one that grows unbounded as backends are added, so we shard it across a
|
||||
// fixed number of matrix jobs instead of feeding one oversized matrix.
|
||||
//
|
||||
// SINGLEARCH_SHARDS MUST equal the number of backend-jobs-singlearch-<n>
|
||||
// (and backend-merge-jobs-singlearch-<n>) blocks defined in backend.yml and
|
||||
// backend_pr.yml. Bump all three together.
|
||||
const SINGLEARCH_SHARDS = 4;
|
||||
const GHA_MATRIX_LIMIT = 256;
|
||||
|
||||
// Split `arr` into exactly `shards` balanced, contiguous chunks. Earlier chunks
|
||||
// absorb the remainder when the length doesn't divide evenly; trailing chunks
|
||||
// may be empty when there are fewer entries than shards (those emit a
|
||||
// has-backends-singlearch-<n>=false flag so their job is skipped).
|
||||
function chunkEqually(arr, shards) {
|
||||
const out = [];
|
||||
const base = Math.floor(arr.length / shards);
|
||||
const rem = arr.length % shards;
|
||||
let idx = 0;
|
||||
for (let i = 0; i < shards; i++) {
|
||||
const size = base + (i < rem ? 1 : 0);
|
||||
out.push(arr.slice(idx, idx + size));
|
||||
idx += size;
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
// Emit the sharded single-arch build + merge matrices and their has-* gates.
|
||||
// Called with the full or filtered single-arch entry list.
|
||||
function emitSinglearchShards(singlearch) {
|
||||
const shards = chunkEqually(singlearch, SINGLEARCH_SHARDS);
|
||||
for (let i = 0; i < SINGLEARCH_SHARDS; i++) {
|
||||
const shard = shards[i];
|
||||
// Fail loudly rather than let GitHub silently drop the overflow: a shard at
|
||||
// or above the limit means SINGLEARCH_SHARDS (and the matching job blocks in
|
||||
// both workflows) need to grow.
|
||||
if (shard.length >= GHA_MATRIX_LIMIT) {
|
||||
throw new Error(
|
||||
`single-arch shard ${i + 1} has ${shard.length} entries (>= ${GHA_MATRIX_LIMIT}, ` +
|
||||
`GitHub's per-matrix job limit). Increase SINGLEARCH_SHARDS in ` +
|
||||
`scripts/changed-backends.js and add matching backend-jobs-singlearch-<n> / ` +
|
||||
`backend-merge-jobs-singlearch-<n> blocks to backend.yml and backend_pr.yml.`
|
||||
);
|
||||
}
|
||||
const merge = computeMergeMatrix(shard);
|
||||
const n = i + 1;
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch-${n}=${shard.length > 0 ? 'true' : 'false'}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch-${n}=${merge.include.length > 0 ? 'true' : 'false'}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch-${n}=${JSON.stringify({ include: shard })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch-${n}=${JSON.stringify(merge)}\n`);
|
||||
}
|
||||
}
|
||||
|
||||
function emitFullMatrix() {
|
||||
const { multiarch, singlearch } = splitByArch(includes);
|
||||
const mergeMatrixMultiarch = computeMergeMatrix(multiarch);
|
||||
const mergeMatrixSinglearch = computeMergeMatrix(singlearch);
|
||||
const hasMergesMultiarch = mergeMatrixMultiarch.include.length > 0 ? 'true' : 'false';
|
||||
const hasMergesSinglearch = mergeMatrixSinglearch.include.length > 0 ? 'true' : 'false';
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=true\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${singlearch.length > 0 ? 'true' : 'false'}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${multiarch.length > 0 ? 'true' : 'false'}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=true\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-multiarch=${hasMergesMultiarch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch=${hasMergesSinglearch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: includesDarwin })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-multiarch=${JSON.stringify(mergeMatrixMultiarch)}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch=${JSON.stringify(mergeMatrixSinglearch)}\n`);
|
||||
emitSinglearchShards(singlearch);
|
||||
for (const backend of allBackendPaths.keys()) {
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `${backend}=true\n`);
|
||||
}
|
||||
@@ -249,29 +301,23 @@ function emitFilteredMatrix(changedFiles) {
|
||||
console.log("Filtered files Darwin:", filteredDarwin);
|
||||
|
||||
const { multiarch, singlearch } = splitByArch(filtered);
|
||||
const hasBackendsSinglearch = singlearch.length > 0 ? 'true' : 'false';
|
||||
const hasBackendsMultiarch = multiarch.length > 0 ? 'true' : 'false';
|
||||
const hasBackendsDarwin = filteredDarwin.length > 0 ? 'true' : 'false';
|
||||
console.log("Has single-arch backends?:", hasBackendsSinglearch);
|
||||
console.log("Has single-arch backends?:", singlearch.length > 0 ? 'true' : 'false');
|
||||
console.log("Has multi-arch backends?:", hasBackendsMultiarch);
|
||||
console.log("Has Darwin backends?:", hasBackendsDarwin);
|
||||
|
||||
const mergeMatrixMultiarch = computeMergeMatrix(multiarch);
|
||||
const mergeMatrixSinglearch = computeMergeMatrix(singlearch);
|
||||
const hasMergesMultiarch = mergeMatrixMultiarch.include.length > 0 ? 'true' : 'false';
|
||||
const hasMergesSinglearch = mergeMatrixSinglearch.include.length > 0 ? 'true' : 'false';
|
||||
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=false\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${hasBackendsSinglearch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${hasBackendsMultiarch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=${hasBackendsDarwin}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-multiarch=${hasMergesMultiarch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch=${hasMergesSinglearch}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: filteredDarwin })}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-multiarch=${JSON.stringify(mergeMatrixMultiarch)}\n`);
|
||||
fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch=${JSON.stringify(mergeMatrixSinglearch)}\n`);
|
||||
emitSinglearchShards(singlearch);
|
||||
|
||||
// Per-backend boolean outputs
|
||||
for (const [backend, pathPrefix] of allBackendPaths) {
|
||||
|
||||
Reference in New Issue
Block a user