benchmark.yml

name: Benchmark

on:
  push:
    branches: [ dev ]
  workflow_dispatch:
    inputs:
      duration:
        description: Benchmark duration per preset (seconds)
        required: false
        default: '30'

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

env:
  GIT_CONFIG_COUNT: 1
  GIT_CONFIG_KEY_0: init.defaultBranch
  GIT_CONFIG_VALUE_0: main

jobs:
  benchmark:
    permissions:
      contents: read
      statuses: write
    runs-on: blacksmith-2vcpu-ubuntu-2404
    timeout-minutes: 90
    steps:
    - uses: actions/checkout@v4

    - name: Setup Nix
      uses: ./.github/actions/setup-nix

    - name: Start headless Wayland compositor
      run: |
        mkdir -p /tmp/runtime-runner
        chmod 700 /tmp/runtime-runner
        export XDG_RUNTIME_DIR=/tmp/runtime-runner
        nix develop --command weston --socket=headless --backend=headless-backend.so --width=1280 --height=720 &
        {
          echo "WAYLAND_DISPLAY=headless"
          echo "XDG_RUNTIME_DIR=/tmp/runtime-runner"
        } >> "$GITHUB_ENV"
        sleep 5

    - name: Run benchmark suite
      id: run_benchmark
      env:
        ZIG_GLOBAL_CACHE_DIR: ${{ github.workspace }}/.zig-cache-global
        XDG_RUNTIME_DIR: /tmp/runtime-runner
        WAYLAND_DISPLAY: headless
        ZIGCRAFT_SAFE_MODE: '1'
        BENCHMARK_DURATION: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.duration || '30' }}
      run: |
        LVP_PATH=$(nix build --no-link --print-out-paths nixpkgs#mesa.drivers)/share/vulkan/icd.d/lvp_icd.x86_64.json
        LAYER_PATH=$(nix build --no-link --print-out-paths nixpkgs#vulkan-validation-layers)/share/vulkan/explicit_layer.d
        export VK_ICD_FILENAMES=$LVP_PATH
        export VK_LAYER_PATH=$LAYER_PATH
        nix develop --command bash scripts/run_benchmark.sh --duration "$BENCHMARK_DURATION" --presets low,medium,high --output-dir benchmark-results

    - name: Compare against baseline
      id: compare
      run: |
        for preset in low medium high; do
          bash scripts/compare_benchmarks.sh docs/benchmarks/baseline.json "benchmark-results/${preset}.json" --preset "$preset"
        done

    - name: Upload benchmark artifacts
      if: always()
      uses: actions/upload-artifact@v7
      with:
        name: benchmark-results
        path: benchmark-results
        retention-days: 30

    - name: Publish commit status
      if: always()
      uses: actions/github-script@v9
      env:
        BENCHMARK_RUN_OUTCOME: ${{ steps.run_benchmark.outcome }}
        BENCHMARK_COMPARE_OUTCOME: ${{ steps.compare.outcome }}
      with:
        script: |
          const runOutcome = process.env.BENCHMARK_RUN_OUTCOME;
          const compareOutcome = process.env.BENCHMARK_COMPARE_OUTCOME;
          const failed = runOutcome === 'failure' || compareOutcome === 'failure';
          const description = failed
            ? 'Benchmark regression or runtime failure'
            : compareOutcome === 'skipped'
              ? 'Benchmark completed (baseline placeholder)'
              : 'Benchmark completed';

          await github.rest.repos.createCommitStatus({
            owner: context.repo.owner,
            repo: context.repo.repo,
            sha: context.sha,
            state: failed ? 'failure' : 'success',
            context: 'performance/benchmark',
            description,
          });