From 17983d72bb525dc44852ede33b20cf41c23dce15 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 22 Jul 2026 19:37:45 +0800 Subject: [PATCH] ci: use process-safe coverage pools --- ...ence-based-larger-hosted-runners.i18n.yaml | 4 +- ...22-evidence-based-larger-hosted-runners.md | 4 +- ...evidence-based-larger-hosted-runners.zh.md | 4 +- .github/workflows/ci.yml | 11 +++-- vitest.config.ts | 44 ++++++++++++++++++- 5 files changed, 56 insertions(+), 11 deletions(-) diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml index b53f173de2..3561f39a33 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-22-evidence-based-larger-hosted-runners.md: f395a2d702e7d0bf2ad74fe0125952da220f799c -2026-07-22-evidence-based-larger-hosted-runners.zh.md: 476c13573b2fc9484e5c20adb0c398be4dfe80d6 +2026-07-22-evidence-based-larger-hosted-runners.md: 2fac4d1c14e3f1eabef9f915e53ff737c0e7ee20 +2026-07-22-evidence-based-larger-hosted-runners.zh.md: 33ca3b823d2bf235f9896b92868bd7a1f0688a76 diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md index f395a2d702..2fac4d1c14 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.md @@ -16,7 +16,7 @@ The organization keeps twelve x64 larger-runner pools in the repo-restricted `ds Production CI uses five larger-runner executions and one standard-runner aggregator. The primary Node inventory is not sharded: -- `node 24 / complete` uses one 96-core Linux runner. One checkout, setup, cache restore, and install feeds all 42 primary gates. `run-gates` starts up to 12 independent gates; ESLint uses 16 workers, coverage uses at most 12, and snapshot replay uses at most 8. Build starts as soon as the first short gates release scheduler slots, while snapshot replay and publication consumers retain explicit dependencies on emitted `lib/` output. Pull requests restore pnpm and ESLint caches without saving them, so cache compression and upload do not extend the required job; the master serial references refresh those caches outside the pull-request critical path. The read-only job does not persist checkout credentials and restores the stable pnpm store root directly, avoiding a separate store-discovery step. +- `node 24 / complete` uses one 96-core Linux runner. One checkout, setup, cache restore, and install feeds all 42 primary gates. `run-gates` starts up to 12 independent gates; ESLint uses 16 workers, coverage uses at most 12, and snapshot replay uses at most 8. Build starts as soon as the first short gates release scheduler slots, while snapshot replay and publication consumers retain explicit dependencies on emitted `lib/` output. Pull requests restore pnpm and ESLint caches without saving them, so cache compression and upload do not extend the required job; the master serial references refresh those caches outside the pull-request critical path. The read-only job does not persist checkout credentials. - Node 22.19 and Node 26 use the 4- and 32-core Linux pools for their runtime compatibility smokes. Python 3.10 uses the 8-core Linux pool for the complete keyless SDK suite. These are environment contracts, not slices of the primary Node gate inventory. - `windows node 24 / complete` uses one 32-core Windows runner. One setup feeds the required package build, required production site build, and complete observational portability inventory. Required failures fail the job; observational failures are reported as non-blocking. ESLint stays single-threaded because 16 ESLint workers took 174.54 seconds, coverage uses at most 12 workers, and the outer scheduler retains 16 slots. The job restores only the small master-refreshed ESLint cache and performs a clean pnpm install instead of restoring or saving the many-file package store. @@ -42,7 +42,7 @@ The larger client package graph makes cache mechanics and scheduler pressure par Two host effects remain part of the decision. A standard Node 26 job once spent 36 of its 67 seconds in `Set up job`, which is why environment contracts use distinct larger-runner pools instead of standard capacity. A Linux candidate spent 18 seconds registering a 50 KB Bubblewrap package because the hosted image scanned 202,507 package-database files. [`scripts/prepare-ci-bubblewrap.sh`](../../../../scripts/prepare-ci-bubblewrap.sh) instead verifies and extracts the pinned payload into the ephemeral runner directory, runs a functional confinement probe, and overlaps that preparation with dependency installation. -Coverage remains capped at 12 forks. Thirty-two forks crashed Node 24's CJS lexer twice, and a later 16-fork run reproduced the worker loss and invalid coverage result. Twelve forks preserve process headroom without becoming the single-host critical path. +Each coverage project is capped at 12 workers, and the process-bound project contains exactly four suite files. Thirty-two forks crashed Node 24's CJS lexer twice, and a later 16-fork run reproduced the worker loss and invalid coverage result. The single Vitest invocation therefore uses threads for the broad inventory and reserves forks for suites that exercise process-global state or `process` APIs. That narrow fork inventory includes the local bash process-plumbing suite: under aggregate gate contention its thread worker completed every test but intermittently missed the stdin-error callback needed for per-file function coverage. This preserves the suites' isolation contracts and deterministic coverage while avoiding forked execution for ordinary test files. The workflow retains two manual measurement suites. `suite=larger-runner-benchmark` compares isolated critical lanes across every size, and `suite=consolidated-runner-benchmark` compares whole aggregates. Complete serial Linux, macOS, and Windows references run only when `master` moves; pull requests run only the optimized jobs. diff --git a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md index 476c13573b..33ca3b823d 100644 --- a/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md +++ b/.agents/notes/implemented/process/2026-07-22-evidence-based-larger-hosted-runners.zh.md @@ -16,7 +16,7 @@ Status: implemented 生产 CI 包含 5 次大型运行器执行和 1 个标准运行器聚合作业。主 Node 门禁清单不再分片： -- `node 24 / complete` 使用一台 96 核 Linux 运行器。只需执行一次代码检出、设置、缓存恢复和安装，即可供全部 42 项主门禁使用。`run-gates` 最多同时启动 12 项相互独立的门禁；ESLint 使用 16 个工作线程，覆盖率最多使用 12 个，快照回放最多使用 8 个。第一批短门禁释放调度器槽位后，构建会立即启动，而快照回放和发布消费方仍显式依赖生成的 `lib/` 输出。拉取请求会恢复 pnpm 和 ESLint 缓存但不保存，因此缓存压缩和上传不会延长必需作业；master 上的串行参考会在拉取请求关键路径之外刷新这些缓存。该只读作业不会持久化代码检出凭据，并直接恢复固定的 pnpm 存储根目录，因此无需再单独执行存储路径探测步骤。 +- `node 24 / complete` 使用一台 96 核 Linux 运行器。只需执行一次代码检出、设置、缓存恢复和安装，即可供全部 42 项主门禁使用。`run-gates` 最多同时启动 12 项相互独立的门禁；ESLint 使用 16 个工作线程，覆盖率最多使用 12 个，快照回放最多使用 8 个。第一批短门禁释放调度器槽位后，构建会立即启动，而快照回放和发布消费方仍显式依赖生成的 `lib/` 输出。拉取请求会恢复 pnpm 和 ESLint 缓存但不保存，因此缓存压缩和上传不会延长必需作业；master 上的串行参考会在拉取请求关键路径之外刷新这些缓存。该只读作业不会持久化代码检出凭据。 - Node 22.19 和 Node 26 分别使用 4 核和 32 核 Linux 池运行各自的运行时兼容性冒烟测试。Python 3.10 使用 8 核 Linux 池运行完整的无密钥 SDK 套件。这些作业属于环境契约，并非主 Node 门禁清单的分片。 - `windows node 24 / complete` 使用一台 32 核 Windows 运行器。一次设置供必需的包构建、必需的生产网站构建以及完整的观测性可移植性清单共用。任何必需项失败都会使作业失败；观测项失败则报告为非阻塞。ESLint 保持单线程，因为 16 个 ESLint 工作线程耗时 174.54 秒；覆盖率最多使用 12 个工作线程，外层调度器则保留 16 个槽位。该作业仅恢复由 master 刷新的较小 ESLint 缓存，并在干净环境中执行 pnpm 安装，而不恢复或保存包含大量文件的包存储。 @@ -42,7 +42,7 @@ Windows 仓库工作在超过 16 核后收益很小，但 32 核池可以让完 两项主机效应仍构成这项决策的依据。一个标准 Node 26 作业曾在总共 67 秒的耗时中，把 36 秒用在 `Set up job` 上，因此各项环境契约使用不同的大型运行器池，而非标准容量。一个 Linux 候选作业在注册 50 KB 的 Bubblewrap 包时耗时 18 秒，因为托管映像扫描了 202,507 个包数据库文件。[`scripts/prepare-ci-bubblewrap.sh`](../../../../scripts/prepare-ci-bubblewrap.sh) 改为验证固定包内容并将其解压到临时运行器目录，执行功能性隔离探针，并让这项准备工作与依赖安装重叠执行。 -覆盖率仍限制为 12 个 fork。32 个 fork 曾两次导致 Node 24 的 CJS 词法分析器崩溃，后来一次使用 16 个 fork 的运行又复现了工作进程丢失和无效的覆盖率结果。12 个 fork 能保留进程余量，同时不会成为单机关键路径。 +每个覆盖率项目均将工作线程上限设为 12 个，其中进程约束项目恰好包含 4 个套件文件。32 个 fork 曾两次导致 Node 24 的 CJS 词法分析器崩溃，后来一次使用 16 个 fork 的运行又复现了工作进程丢失和无效的覆盖率结果。因此，单次 Vitest 调用会对大范围测试清单使用线程，只为涉及进程全局状态或 `process` API 的套件保留 fork。这份有限的 fork 清单还包含本地 bash 进程通路套件：在聚合门禁争用资源时，该套件的工作线程虽然完成并通过了所有测试，却会间歇性漏记逐文件函数覆盖率所需的 stdin 错误回调。这样既能保留这些套件的隔离契约和覆盖率结果的确定性，又能避免以 fork 方式执行普通测试文件。 工作流保留 2 项手动测量套件。`suite=larger-runner-benchmark` 比较所有规格下相互独立的关键通道，`suite=consolidated-runner-benchmark` 比较完整聚合流程。只有在 `master` 移动时，才运行完整的 Linux、macOS 和 Windows 串行参考；拉取请求只运行优化后的作业。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index ffc95ea849..4a0476c824 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -50,13 +50,17 @@ jobs: with: node-version: ${{ env.PRIMARY_NODE_VERSION }} + - name: Enable corepack and resolve pnpm store path + id: pnpm-store + run: | + corepack enable + echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT" + # Pull requests consume the default-branch cache but do not put cache # compression and upload on the paid latency-critical path. - uses: actions/cache/restore@v4 with: - # Cache the versioned store through its stable parent so selecting - # the current pnpm store does not require a separate runner step. - path: ~/.local/share/pnpm/store + path: ${{ steps.pnpm-store.outputs.path }} key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} restore-keys: | ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- @@ -70,7 +74,6 @@ jobs: - name: Install dependencies and prepare bubblewrap run: | - corepack enable pnpm install --frozen-lockfile & install_pid=$! bash scripts/prepare-ci-bubblewrap.sh & diff --git a/vitest.config.ts b/vitest.config.ts index dc9061c45a..51ced4b19f 100644 --- a/vitest.config.ts +++ b/vitest.config.ts @@ -22,6 +22,21 @@ const windowsCoverageExclusions = process.platform === 'win32' ] : [] +const testIncludes = [ + 'packages/*/*/tests/**/*.spec.{ts,tsx}', + 'examples/*/tests/**/*.spec.ts', + 'scripts/**/*.spec.ts', +] + +// These suites exercise process-global state or process APIs that worker threads cannot isolate. +// Keep the narrow exception in forks while the rest of the inventory avoids per-file processes. +const processBoundTests = [ + 'packages/bash/bash-local/tests/run.spec.ts', + 'packages/context/time-context/tests/time-context.spec.ts', + 'packages/ui/app-boot/tests/app-boot.spec.ts', + 'packages/workflow/workflow-workerthread/tests/session.spec.ts', +] + export default defineConfig({ // Native path resolution reads each package's nearest tsconfig, but only the root defines // workspace paths. Keep this plugin pinned to the root map so bare package imports resolve @@ -32,8 +47,35 @@ export default defineConfig({ test: { setupFiles: ['./scripts/test-invariants.ts'], // .tsx: client component specs (jsdom via per-file @vitest-environment pragma). - include: ['packages/*/*/tests/**/*.spec.{ts,tsx}', 'examples/*/tests/**/*.spec.ts', 'scripts/**/*.spec.ts'], + include: testIncludes, exclude: windowsUnsupportedPackages.map(path => `${path}/tests/**/*.spec.ts`), + // One coverage invocation aggregates both projects. Most suites use threads + // for lower startup/IPC overhead; only explicit process-bound suites fork. + projects: [ + { + plugins: [tsconfigPaths({ projects: ['./tsconfig.vitest.json'] })], + test: { + name: 'thread-safe', + pool: 'threads', + setupFiles: ['./scripts/test-invariants.ts'], + include: testIncludes, + exclude: [ + ...windowsUnsupportedPackages.map(path => `${path}/tests/**/*.spec.ts`), + ...processBoundTests, + ], + }, + }, + { + plugins: [tsconfigPaths({ projects: ['./tsconfig.vitest.json'] })], + test: { + name: 'process-bound', + pool: 'forks', + setupFiles: ['./scripts/test-invariants.ts'], + include: processBoundTests, + exclude: windowsUnsupportedPackages.map(path => `${path}/tests/**/*.spec.ts`), + }, + }, + ], coverage: { provider: 'v8', // Coverage measures OUR runtime source. Types-only files carry no