bench.yml

# Runs after every commit to `develop` (or in other words, _after_ every pull request merges).

name: Benchmarks

on:
  push:
    branches: [develop]

permissions:
  id-token: write  # enables AWS-GitHub OIDC
  actions: read
  contents: write

jobs:
  commit-metadata:
    runs-on: ubuntu-latest
    timeout-minutes: 120
    steps:
      - uses: actions/checkout@v6
      - name: Setup AWS CLI
        uses: aws-actions/configure-aws-credentials@v5
        with:
          role-to-assume: arn:aws:iam::245040174862:role/GitHubBenchmarkRole
          aws-region: us-east-1
      - name: Upload Commit Metadata
        shell: bash
        run: |
          set -Eeu -o pipefail -x

          sudo apt-get update && sudo apt-get install -y jq
          bash scripts/commit-json.sh > new-commit.json
          bash scripts/cat-s3.sh vortex-ci-benchmark-results commits.json new-commit.json

  bench:
    timeout-minutes: 120
    runs-on: >-
      ${{ github.repository == 'vortex-data/vortex'
          && format('runs-on={0}/runner=bench-dedicated/extras=s3-cache/tag={1}', github.run_id, matrix.benchmark.id)
          || 'ubuntu-latest' }}
    strategy:
      matrix:
        benchmark:
          - id: random-access-bench
            name: Random Access
            build_args: "--features lance"
            formats: "parquet,lance,vortex"
          - id: compress-bench
            name: Compression
            build_args: "--features lance"
            formats: "parquet,lance,vortex"
    steps:
      - uses: runs-on/action@v2
        if: github.repository == 'vortex-data/vortex'
        with:
          sccache: s3
      - uses: actions/checkout@v6
      - name: Setup benchmark environment
        run: sudo bash scripts/setup-benchmark.sh
      - uses: ./.github/actions/setup-rust
        with:
          repo-token: ${{ secrets.GITHUB_TOKEN }}

      - name: Install DuckDB
        run: |
          wget -qO- https://github.com/duckdb/duckdb/releases/download/v1.4.2/duckdb_cli-linux-amd64.zip | funzip > duckdb
          chmod +x duckdb
          echo "$PWD" >> $GITHUB_PATH

      - uses: ./.github/actions/system-info

      - name: Build binary
        shell: bash
        env:
          RUSTFLAGS: "-C target-cpu=native -C force-frame-pointers=yes"
        run: |
          cargo build --bin ${{ matrix.benchmark.id }} --profile release_debug ${{ matrix.benchmark.build_args }}

      - name: Setup Polar Signals
        uses: polarsignals/gh-actions-ps-profiling@v0.8.1
        with:
          polarsignals_cloud_token: ${{ secrets.POLAR_SIGNALS_API_KEY }}
          labels: "branch=${{ github.ref_name }};gh_run_id=${{ github.run_id }};benchmark=${{ matrix.benchmark.id }}"
          project_uuid: "e5d846e1-b54c-46e7-9174-8bf055a3af56"
          profiling_frequency: 199
          extra_args: "--off-cpu-threshold=0.03"  # Personally tuned by @brancz

      - name: Run ${{ matrix.benchmark.name }} benchmark
        shell: bash
        env:
          RUST_BACKTRACE: full
        run: |
          target/release_debug/${{ matrix.benchmark.id }} --formats ${{ matrix.benchmark.formats }} -d gh-json -o results.json

      - name: Setup AWS CLI
        uses: aws-actions/configure-aws-credentials@v5
        with:
          role-to-assume: arn:aws:iam::245040174862:role/GitHubBenchmarkRole
          aws-region: us-east-1

      - name: Upload Benchmark Results
        shell: bash
        run: |
          bash scripts/cat-s3.sh vortex-ci-benchmark-results data.json.gz results.json

      - name: Alert incident.io
        if: failure()
        uses: ./.github/actions/alert-incident-io
        with:
          api-key: ${{ secrets.INCIDENT_IO_ALERT_TOKEN }}
          alert-title: "${{ matrix.benchmark.name }} benchmark failed on develop"
          deduplication-key: ci-bench-${{ matrix.benchmark.id }}-failure

  sql:
    uses: ./.github/workflows/sql-benchmarks.yml
    secrets: inherit
    with:
      mode: "develop"
      benchmark_matrix: |
        [
          {
            "id": "clickbench-nvme",
            "subcommand": "clickbench",
            "name": "Clickbench on NVME",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
            "build_lance": true
          },
          {
            "id": "tpch-nvme",
            "subcommand": "tpch",
            "name": "TPC-H SF=1 on NVME",
            "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
            "scale_factor": "1.0",
            "build_lance": true
          },
          {
            "id": "tpch-s3",
            "subcommand": "tpch",
            "name": "TPC-H SF=1 on S3",
            "local_dir": "vortex-bench/data/tpch/1.0",
            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/tpch/1.0/",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
            "scale_factor": "1.0"
          },
          {
            "id": "tpch-nvme-10",
            "subcommand": "tpch",
            "name": "TPC-H SF=10 on NVME",
            "targets": "datafusion:arrow,datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,datafusion:lance,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
            "scale_factor": "10.0",
            "build_lance": true
          },
          {
            "id": "tpch-s3-10",
            "subcommand": "tpch",
            "name": "TPC-H SF=10 on S3",
            "local_dir": "vortex-bench/data/tpch/10.0",
            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/tpch/10.0/",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
            "scale_factor": "10.0"
          },
          {
            "id": "tpcds-nvme",
            "subcommand": "tpcds",
            "name": "TPC-DS SF=1 on NVME",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact,duckdb:duckdb",
            "scale_factor": "1.0"
          },
          {
            "id": "statpopgen",
            "subcommand": "statpopgen",
            "name": "Statistical and Population Genetics",
            "local_dir": "vortex-bench/data/statpopgen",
            "targets": "duckdb:parquet,duckdb:vortex,duckdb:vortex-compact",
            "scale_factor": "100"
          },
          {
            "id": "fineweb",
            "subcommand": "fineweb",
            "name": "FineWeb NVMe",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact"
          },
          {
            "id": "fineweb-s3",
            "subcommand": "fineweb",
            "name": "FineWeb S3",
            "local_dir": "vortex-bench/data/fineweb",
            "remote_storage": "s3://vortex-ci-benchmark-datasets/${{github.ref_name}}/${{github.run_id}}/fineweb/",
            "targets": "datafusion:parquet,datafusion:vortex,datafusion:vortex-compact,duckdb:parquet,duckdb:vortex,duckdb:vortex-compact"
          },
          {
            "id": "polarsignals",
            "subcommand": "polarsignals",
            "name": "PolarSignals Profiling",
            "targets": "datafusion:vortex",
            "scale_factor": "1"
          },
        ]