From 02f6d919c8f00afd156e5089c122bff02e98412f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 22 Jul 2026 19:13:07 +0800 Subject: [PATCH] ci: remove primary setup overhead --- ...evidence-based-larger-hosted-runners.i18n.yaml | 4 ++-- ...-07-22-evidence-based-larger-hosted-runners.md | 2 +- ...-22-evidence-based-larger-hosted-runners.zh.md | 2 +- .github/workflows/ci.yml | 15 +++++++-------- 4 files changed, 11 insertions(+), 12 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 d151088a0a..b53f173de2 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: 6170aca3c2675069a74d951b11273ed5d2731de8 -2026-07-22-evidence-based-larger-hosted-runners.zh.md: bd2095b17bdb954382b455bd160405a10be56ddb +2026-07-22-evidence-based-larger-hosted-runners.md: f395a2d702e7d0bf2ad74fe0125952da220f799c +2026-07-22-evidence-based-larger-hosted-runners.zh.md: 476c13573b2fc9484e5c20adb0c398be4dfe80d6 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 6170aca3c2..f395a2d702 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 16 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. +- `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 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. 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 bd2095b17b..476c13573b 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 16 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。 +- `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 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。 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index deba685f81..ffc95ea849 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -38,27 +38,25 @@ jobs: DSH_COVERAGE_MAX_WORKERS: '12' DSH_ESLINT_CACHE: '1' DSH_ESLINT_CONCURRENCY: '16' - DSH_GATE_CONCURRENCY: '16' + DSH_GATE_CONCURRENCY: '12' DSH_PUBLINT_CONCURRENCY: '16' DSH_SNAPSHOT_MAX_CONCURRENCY: '8' steps: - uses: actions/checkout@v6 + with: + persist-credentials: false - uses: actions/setup-node@v6 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: - path: ${{ steps.pnpm-store.outputs.path }} + # 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 key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }} restore-keys: | ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm- @@ -72,6 +70,7 @@ jobs: - name: Install dependencies and prepare bubblewrap run: | + corepack enable pnpm install --frozen-lockfile & install_pid=$! bash scripts/prepare-ci-bubblewrap.sh &