performance.yml

name: PR performance

on:
  pull_request:
    branches: [master]
    types: [opened, synchronize, reopened, ready_for_review]
  workflow_dispatch:
    inputs:
      pull_request:
        description: Pull request number to compare with its current base
        required: true
        type: string
      runtime:
        description: Target runtime
        type: choice
        options: [net10.0, net8.0, both]
        default: net10.0

permissions:
  contents: read
  pull-requests: read

concurrency:
  group: performance-${{ github.event.pull_request.number || inputs.pull_request }}
  cancel-in-progress: true

jobs:
  revisions:
    runs-on: ubuntu-24.04
    outputs:
      number: ${{ steps.pr.outputs.number }}
      base: ${{ steps.pr.outputs.base }}
      head: ${{ steps.pr.outputs.head }}
      head-repo: ${{ steps.pr.outputs.head-repo }}
      runtimes: ${{ steps.pr.outputs.runtimes }}
    steps:
      - uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7
        id: pr
        env:
          REQUESTED_PR: ${{ inputs.pull_request }}
          REQUESTED_RUNTIME: ${{ inputs.runtime }}
        with:
          script: |
            const text = process.env.REQUESTED_PR;
            if (context.eventName === 'workflow_dispatch' && !/^[1-9][0-9]*$/.test(text)) throw new Error('Invalid PR number');
            const pr = context.eventName === 'pull_request' ? context.payload.pull_request :
              (await github.rest.pulls.get({...context.repo, pull_number: Number(text)})).data;
            if (pr.base.ref !== 'master' || pr.base.repo.full_name !== `${context.repo.owner}/${context.repo.repo}`) throw new Error('Expected a PR targeting master in this repository');
            core.setOutput('number', pr.number);
            core.setOutput('base', pr.base.sha);
            core.setOutput('head', pr.head.sha);
            core.setOutput('head-repo', pr.head.repo.full_name);
            const runtime = process.env.REQUESTED_RUNTIME || 'net10.0';
            if (!['net10.0', 'net8.0', 'both'].includes(runtime)) throw new Error('Invalid runtime');
            core.setOutput('runtimes', JSON.stringify(runtime === 'both' ? ['net8.0', 'net10.0'] : [runtime]));

  benchmark:
    needs: revisions
    runs-on: ubuntu-24.04
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        runtime: ${{ fromJSON(needs.revisions.outputs.runtimes) }}
    env:
      PR_NUMBER: ${{ needs.revisions.outputs.number }}
      DOTNET_CLI_TELEMETRY_OPTOUT: 1
      DOTNET_NOLOGO: 1
      DOTNET_TieredCompilation: 0
      DOTNET_ReadyToRun: 0
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
        with:
          ref: ${{ needs.revisions.outputs.base }}
          path: baseline
          persist-credentials: false
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
        with:
          repository: ${{ needs.revisions.outputs.head-repo }}
          ref: ${{ needs.revisions.outputs.head }}
          path: candidate
          persist-credentials: false
      - uses: actions/setup-dotnet@67a3573c9a986a3f9c594539f4ab511d57bb3ce9 # v4
        with:
          dotnet-version: 10.0.301
          # The extended .NET 8 pass needs the runtime as well as the pinned SDK.
      - if: matrix.runtime == 'net8.0'
        uses: actions/setup-dotnet@67a3573c9a986a3f9c594539f4ab511d57bb3ce9 # v4
        with:
          dotnet-version: 8.0.422
      - name: Select one frozen harness
        shell: bash
        run: |
          suite=test/FastExpressionCompiler.Benchmarks/Regression
          harness="baseline/$suite"
          if [ ! -f "$harness/run.py" ]; then harness="candidate/$suite"; fi
          echo "PERFORMANCE_HARNESS=$harness" >> "$GITHUB_ENV"
      - name: Harness and policy tests
        shell: bash
        run: |
          python3 -m unittest discover -s "$PERFORMANCE_HARNESS/tests" -v
          node --test "$PERFORMANCE_HARNESS/tests/publish.test.cjs"
      - name: Benchmark exact base and PR head in both orders
        id: measure
        continue-on-error: true
        env:
          RUNTIME: ${{ matrix.runtime }}
        shell: bash
        run: python3 "$PERFORMANCE_HARNESS/run.py" --baseline baseline --candidate candidate --runtime "$RUNTIME" --output results
      - name: Compare (reporting only)
        if: always() && steps.measure.outcome != 'skipped'
        shell: bash
        run: |
          status=0
          python3 "$PERFORMANCE_HARNESS/compare.py" --input results || status=$?
          if [ -f results/report.md ]; then cat results/report.md >> "$GITHUB_STEP_SUMMARY"; fi
          exit "$status"
      - name: Upload comment data
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
        with:
          name: performance-report-${{ matrix.runtime }}-${{ github.run_attempt }}
          path: results/report.json
          if-no-files-found: warn
          retention-days: 14
      - name: Upload complete benchmark evidence
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
        with:
          name: performance-data-${{ matrix.runtime }}-${{ github.run_attempt }}
          path: |
            results/context.json
            results/sources.json
            results/report.md
            results/logs
            results/runs
          if-no-files-found: warn
          retention-days: 14