pipeline-performance-test.yml

name: Trigger and Run Pipeline Performance Test

on:
  pull_request:
    types: [labeled]

jobs:
  performance-test:
    runs-on: ubuntu-latest

    steps:
    - name: Check if 'performance' label was added
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: echo "Performance label detected. Running performance test."

    - name: Clone test repo
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        git clone https://x-access-token:${{ secrets.GH_TAGGING_TOKEN }}@github.com/kedro-org/pipeline-performance-test.git

    - name: Set up Python 3.11
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      uses: actions/setup-python@v5
      with:
        python-version: '3.11'

    - name: Install dependencies
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        pip install kedro
        pip install uv
        cd pipeline-performance-test/performance-test
        pip install -r requirements.txt

    - name: Run performance test and capture time for latest Kedro release
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        cd pipeline-performance-test/performance-test
        total_time_release=0.0
        for i in {1..10}; do
          { time kedro run; } 2> release_time_output.txt
          real_time_release=$(grep real release_time_output.txt | awk '{print $2}' | sed 's/[^0-9.]//g')
          total_time_release=$(echo "$total_time_release + $real_time_release" | bc)
        done
        average_time_release=$(echo "scale=3; $total_time_release / 10" | bc)
        echo "average_time_release=${average_time_release}" >> $GITHUB_ENV

    - name: Pull specific branch from Kedro and install it
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        git clone --branch ${{ github.event.pull_request.head.ref }} https://github.com/kedro-org/kedro.git
        cd kedro
        make install

    - name: Run performance test and capture time for specific Kedro branch
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        cd pipeline-performance-test/performance-test
        total_time_branch=0.0
        for i in {1..10}; do
          { time kedro run --params=hook_delay=0,dataset_load_delay=0,file_save_delay=0; } 2> branch_time_output.txt
          real_time_branch=$(grep real branch_time_output.txt | awk '{print $2}' | sed 's/[^0-9.]//g')
          total_time_branch=$(echo "$total_time_branch + $real_time_branch" | bc)
        done
        average_time_branch=$(echo "scale=3; $total_time_branch / 10" | bc)
        echo "average_time_branch=${average_time_branch}" >> $GITHUB_ENV

    - name: Extract and format real time from release version
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: echo "Average elapsed time for Kedro release version test was ${average_time_release} seconds"

    - name: Extract and format real time from specific branch
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: echo "Average elapsed time for specific branch test was ${average_time_branch} seconds"

    - name: Clean up time output files
      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
      run: |
        rm pipeline-performance-test/performance-test/release_time_output.txt pipeline-performance-test/performance-test/branch_time_output.txt