greptimedb/.github/workflows/query-regression.yml

name: Query Regression

on:
  workflow_dispatch:
    inputs:
      case:
        description: Query perf case path(s) in candidate checkout, or all
        required: true
        default: all
      base_ref:
        description: Base ref/sha to build
        required: true
        default: main
      candidate_ref:
        description: Candidate ref/sha to build (empty = current ref)
        required: false
        default: ""
      allow_large_fixture:
        description: Pass --allow-large-fixture to runner
        type: boolean
        default: true
      http_timeout:
        description: Runner HTTP timeout seconds
        required: true
        default: "300"
      cargo_profile:
        description: Cargo profile to build base and candidate binaries with
        required: true
        type: choice
        default: nightly
        options:
          - nightly
          - release
          - dev
      runner:
        description: Self-hosted runner label or ARC runner scale set for this query regression run
        required: true
        type: choice
        default: perf-regression-8-cores
        options:
          - perf-regression-8-cores
  pull_request:
    types: [labeled]

permissions:
  contents: read

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

jobs:
  query-regression:
    if: >-
      ${{ github.event_name == 'workflow_dispatch' ||
           (github.event_name == 'pull_request' &&
            !github.event.pull_request.draft &&
            contains(github.event.pull_request.labels.*.name, 'query-regression') &&
            (github.event.action != 'labeled' || github.event.label.name == 'query-regression')) }}
    runs-on: ${{ github.event_name == 'workflow_dispatch' && inputs.runner || 'perf-regression-8-cores' }}
    timeout-minutes: 180
    env:
      CARGO_PROFILE: ${{ github.event_name == 'pull_request' && 'nightly' || inputs.cargo_profile }}
      CARGO_TARGET_DIR: ${{ github.workspace }}/query-regression-target
      CARGO_BUILD_RUSTFLAGS: "-C link-arg=-fuse-ld=mold"
      BASE_REF: ${{ github.event_name == 'pull_request' && github.event.pull_request.base.sha || inputs.base_ref }}
      CANDIDATE_REF: ${{ github.event_name == 'pull_request' && format('refs/pull/{0}/merge', github.event.pull_request.number) || inputs.candidate_ref || github.ref }}
    steps:
      - name: Checkout base source
        uses: actions/checkout@v4
        with:
          repository: ${{ github.repository }}
          ref: ${{ env.BASE_REF }}
          path: src
          persist-credentials: false

      - name: Preserve trusted query regression scripts
        run: |
          mkdir -p query-regression-trusted-scripts
          cp src/.github/scripts/query-regression-pr-metadata.py \
            query-regression-trusted-scripts/query-regression-pr-metadata.py
          cp src/.github/scripts/query-regression-summary.py \
            query-regression-trusted-scripts/query-regression-summary.py

      - uses: arduino/setup-protoc@v3
        with:
          repo-token: ${{ secrets.GITHUB_TOKEN }}

      - uses: actions-rust-lang/setup-rust-toolchain@v1
        with:
          cache: false

      - uses: astral-sh/setup-uv@v5

      - name: Rust cache
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: src
          shared-key: query-regression
          cache-all-crates: "true"
          save-if: false

      - name: Build base greptime
        working-directory: src
        run: |
          cargo build --profile "${CARGO_PROFILE}" -p cmd --bin greptime
          target_dir="${CARGO_PROFILE}"
          if [[ "${CARGO_PROFILE}" == "dev" ]]; then
            target_dir="debug"
          fi
          mkdir -p "${GITHUB_WORKSPACE}/query-regression-bins/base"
          cp "${CARGO_TARGET_DIR}/${target_dir}/greptime" \
            "${GITHUB_WORKSPACE}/query-regression-bins/base/greptime"

      - name: Switch source to candidate
        working-directory: src
        run: |
          git fetch --no-tags --prune --depth=1 origin "${CANDIDATE_REF}"
          git reset --hard FETCH_HEAD
          git clean -ffdx

      - name: Build candidate greptime and fixture generators
        working-directory: src
        run: |
          cargo build --profile "${CARGO_PROFILE}" -p cmd --bin greptime --bin query_perf_fixture --bin prom_remote_write_fixture
          target_dir="${CARGO_PROFILE}"
          if [[ "${CARGO_PROFILE}" == "dev" ]]; then
            target_dir="debug"
          fi
          mkdir -p "${GITHUB_WORKSPACE}/query-regression-bins/candidate"
          cp "${CARGO_TARGET_DIR}/${target_dir}/greptime" \
            "${GITHUB_WORKSPACE}/query-regression-bins/candidate/greptime"
          cp "${CARGO_TARGET_DIR}/${target_dir}/query_perf_fixture" \
            "${GITHUB_WORKSPACE}/query-regression-bins/candidate/query_perf_fixture"
          cp "${CARGO_TARGET_DIR}/${target_dir}/prom_remote_write_fixture" \
            "${GITHUB_WORKSPACE}/query-regression-bins/candidate/prom_remote_write_fixture"

      - name: Run query regression
        id: run
        env:
          CASE_PATHS: ${{ github.event_name == 'pull_request' && 'all' || inputs.case }}
          HTTP_TIMEOUT: ${{ github.event_name == 'pull_request' && '300' || inputs.http_timeout }}
          ALLOW_LARGE_FIXTURE: ${{ github.event_name == 'pull_request' && 'true' || inputs.allow_large_fixture }}
          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
          CASE_NAME: ${{ github.event_name == 'pull_request' && 'default case set' || inputs.case }}
          BASE_BIN: ${{ github.workspace }}/query-regression-bins/base/greptime
          CANDIDATE_BIN: ${{ github.workspace }}/query-regression-bins/candidate/greptime
          FIXTURE_GENERATOR: ${{ github.workspace }}/query-regression-bins/candidate/query_perf_fixture
          REMOTE_WRITE_GENERATOR: ${{ github.workspace }}/query-regression-bins/candidate/prom_remote_write_fixture
        run: >-
          uv run --no-project python src/.github/scripts/query-regression-run.py
          --base-src src
          --candidate-src src
          --summary-script query-regression-trusted-scripts/query-regression-summary.py

      - name: Write PR metadata for trusted comment workflow
        if: ${{ always() && github.event_name == 'pull_request' }}
        env:
          PR_NUMBER: ${{ github.event.pull_request.number }}
          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
          HEAD_REPO: ${{ github.event.pull_request.head.repo.full_name }}
          BASE_REPO: ${{ github.event.pull_request.base.repo.full_name }}
          RUN_ID: ${{ github.run_id }}
          RUN_ATTEMPT: ${{ github.run_attempt }}
        run: uv run --no-project python query-regression-trusted-scripts/query-regression-pr-metadata.py

      - name: Upload query regression artifacts
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: query-regression-report
          path: |
            query-regression-work/**
            query-regression-summary.md
          if-no-files-found: warn

      - name: Upload trusted comment artifact
        if: ${{ always() && github.event_name == 'pull_request' }}
        uses: actions/upload-artifact@v4
        with:
          name: query-regression-comment
          path: |
            query-regression-pr.json
            query-regression-work/**/query-regression-report.json
          if-no-files-found: warn
          retention-days: 7

      - name: Fail on regression failure
        if: ${{ steps.run.outputs.status != '0' }}
        run: exit 1