benchmark.yml

name: Benchmark

on:
  pull_request:
    paths:
      - crates/**
      - Cargo.toml
      - py-polars/tests/benchmark/**
      - .github/workflows/benchmark.yml
  push:
    branches:
      - main
    paths:
      - crates/**
      - Cargo.toml
      - py-polars/tests/benchmark/**
      - .github/workflows/benchmark.yml

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

env:
  SCCACHE_GHA_ENABLED: 'true'
  RUSTC_WRAPPER: sccache
  RUST_BACKTRACE: 1

jobs:
  main:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Set up Graphviz
        uses: ts-graphviz/setup-graphviz@v2

      - name: Create virtual environment
        run: |
          curl -LsSf https://astral.sh/uv/install.sh | sh
          uv venv
          echo "$GITHUB_WORKSPACE/.venv/bin" >> $GITHUB_PATH
          echo "VIRTUAL_ENV=$GITHUB_WORKSPACE/.venv" >> $GITHUB_ENV

      - name: Install Python dependencies
        working-directory: py-polars
        run: |
          # Install typing-extensions separately whilst the `--extra-index-url` in `requirements-ci.txt`
          # doesn't have an up-to-date typing-extensions, see
          # https://github.com/astral-sh/uv/issues/6028#issuecomment-2287232150
          uv pip install -U typing-extensions 
          uv pip install --compile-bytecode -r requirements-dev.txt -r requirements-ci.txt --verbose

      - name: Set up Rust
        run: rustup show

      - name: Cache Rust
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: py-polars
          save-if: ${{ github.ref_name == 'main' }}

      - name: Run sccache-cache
        uses: mozilla-actions/sccache-action@v0.0.4

      - name: Install Polars release build
        env:
          RUSTFLAGS: -C embed-bitcode -D warnings
        working-directory: py-polars
        run: maturin develop --release -- -C codegen-units=8 -C lto=thin -C target-cpu=native

      - name: Set wheel size
        run: |
          WHEEL_SIZE=$(ls -l py-polars/polars/polars*.so | awk '{ print $5 }')
          echo "WHEEL_SIZE=$WHEEL_SIZE" >> $GITHUB_ENV

      - name: Wheel size txt
        if: github.ref_name == 'main'
        run: |
          echo "$GITHUB_RUN_ID $WHEEL_SIZE" > wheel_sizes.txt

      - name: Upload wheel sizes artifact (main only)
        if: github.ref_name == 'main'
        uses: actions/upload-artifact@v4
        with:
          name: wheel-size
          path: wheel_sizes.txt

      - name: Download main wheel size
        uses: actions/download-artifact@v4
        with:
          name: wheel-size
        continue-on-error: true 

      - name: Extract previous wheel size
        if: github.ref_name != 'main'
        id: load_previous_size
        run: |
          ls -la 
          if [[ -f wheel_sizes.txt ]]; then
            PREVIOUS_WHEEL_SIZE=$(tail -n 1 wheel_sizes.txt | awk '{ print $2 }')
            echo "PREVIOUS_WHEEL_SIZE=$PREVIOUS_WHEEL_SIZE" >> $GITHUB_ENV
          else
            echo "PREVIOUS_WHEEL_SIZE=Unknown" >> $GITHUB_ENV
          fi
        continue-on-error: true 

      - name: Comment wheel size
        uses: actions/github-script@v7
        if: github.ref_name != 'main'
        with:
          script: |
              const previousSize = process.env.PREVIOUS_WHEEL_SIZE || 'Unknown';
              const currentSize = process.env.WHEEL_SIZE || 'Unknown';

              // Convert to MB
              const previousSizeMB = previousSize !== 'Unknown' ? (previousSize / 1024 / 1024).toFixed(4) : 'Unknown';
              const currentSizeMB = currentSize !== 'Unknown' ? (currentSize / 1024 / 1024).toFixed(4) : 'Unknown';

              let commentBody = `The previous uncompressed lib size was **${previousSizeMB} MB**.\nThe current uncompressed lib size after this PR is **${currentSizeMB} MB**.`;

              // Calculate percentage increase if both sizes are available
              if (previousSize !== 'Unknown' && currentSize !== '') {
                const increase = ((currentSize - previousSize) / previousSize) * 100;
                commentBody += `\nThis represents a **${increase.toFixed(2)}% increase** in size.`;
              }

              const { data: comments } = await github.rest.issues.listComments({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: context.issue.number,
              });

              // Look for an existing comment
              const existingComment = comments.find(comment =>
                comment.body.includes('The previous uncompressed lib size was')
              );

              if (existingComment) {
                // Update the existing comment
                await github.rest.issues.updateComment({
                  owner: context.repo.owner,
                  repo: context.repo.repo,
                  comment_id: existingComment.id,
                  body: commentBody,
                });
              } else {
                // Create a new comment
                await github.rest.issues.createComment({
                  owner: context.repo.owner,
                  repo: context.repo.repo,
                  issue_number: context.issue.number,
                  body: commentBody,
                });
              }
        continue-on-error: true 

      - name: Run benchmark tests
        uses: CodSpeedHQ/action@v3
        with:
          working-directory: py-polars
          run: pytest -m benchmark --codspeed -v

      - name: Run non-benchmark tests
        working-directory: py-polars
        run: pytest -m 'not benchmark and not debug' -n auto --dist loadgroup

      - name: Run non-benchmark tests on new streaming engine
        working-directory: py-polars
        env:
          POLARS_AUTO_NEW_STREAMING: 1
        run: pytest -n auto --dist loadgroup -m "not may_fail_auto_streaming and not slow and not write_disk and not release and not docs and not hypothesis and not benchmark and not ci_only"