benchmark.yaml

name: Performance Benchmark
on:
  pull_request:
    types: [opened, synchronize, reopened]
    paths-ignore:
      - '*.md'
      - '.github/workflows/*'
  workflow_dispatch:
    inputs:
      before_image:
        description: 'Before image (baseline). Defaults to latest release.'
        required: false
        type: string
      after_image:
        description: 'After image (candidate). Defaults to building from source.'
        required: false
        type: string
  workflow_call:
    inputs:
      after_image:
        required: true
        type: string
      before_image:
        required: false
        type: string

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

jobs:
  benchmark:
    runs-on: ubuntu-large
    permissions:
      pull-requests: write
      contents: read
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Set up Go
        uses: actions/setup-go@v5
        with:
          go-version: "1.25"

      - name: Install Kind
        run: |
          curl -Lo ./kind https://kind.sigs.k8s.io/dl/v0.27.0/kind-linux-amd64
          chmod +x ./kind
          sudo mv ./kind /usr/local/bin/kind

      - name: Install Helm
        run: |
          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash

      - name: Resolve before image
        id: before-image
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          if [[ -n "${{ inputs.before_image }}" ]]; then
            echo "BEFORE_IMAGE=${{ inputs.before_image }}" >> "$GITHUB_OUTPUT"
          else
            LATEST_TAG=$(gh api repos/${{ github.repository }}/releases/latest --jq '.tag_name')
            echo "BEFORE_IMAGE=quay.io/kubescape/node-agent:${LATEST_TAG}" >> "$GITHUB_OUTPUT"
          fi

      - name: Build after image
        id: after-image
        if: ${{ !inputs.after_image }}
        run: |
          curl https://github.com/inspektor-gadget/inspektor-gadget/releases/download/v0.48.1/ig_0.48.1_amd64.deb -LO && sudo dpkg -i ig_0.48.1_amd64.deb
          make gadgets
          make binary
          make docker-build IMAGE=quay.io/kubescape/node-agent TAG=bench-${{ github.sha }}
          echo "AFTER_IMAGE=quay.io/kubescape/node-agent:bench-${{ github.sha }}" >> "$GITHUB_OUTPUT"

      - name: Set after image from input
        id: after-image-input
        if: ${{ inputs.after_image }}
        run: |
          echo "AFTER_IMAGE=${{ inputs.after_image }}" >> "$GITHUB_OUTPUT"

      - name: Determine after image
        id: resolve-after
        run: |
          AFTER="${{ steps.after-image.outputs.AFTER_IMAGE || steps.after-image-input.outputs.AFTER_IMAGE }}"
          echo "AFTER_IMAGE=${AFTER}" >> "$GITHUB_OUTPUT"

      - name: Load after image into Kind
        if: ${{ !inputs.after_image }}
        run: |
          # Kind cluster is created by dedup-bench.sh, but we need to pre-load the image
          # The script's load_image function handles this automatically
          echo "After image will be loaded by dedup-bench.sh"

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

      - name: Install Python dependencies
        run: pip install -r benchmark/requirements.txt

      - name: Run benchmark
        env:
          BEFORE_IMAGE: ${{ steps.before-image.outputs.BEFORE_IMAGE }}
          AFTER_IMAGE: ${{ steps.resolve-after.outputs.AFTER_IMAGE }}
          OUTPUT_DIR: ${{ github.workspace }}/benchmark-output
        run: |
          chmod +x benchmark/dedup-bench.sh
          benchmark/dedup-bench.sh "$BEFORE_IMAGE" "$AFTER_IMAGE"

      - name: Generate markdown report
        if: always()
        run: |
          python3 benchmark/compare-metrics.py --format markdown \
            "${{ github.workspace }}/benchmark-output/before" \
            "${{ github.workspace }}/benchmark-output/after" > report.md || true

      - name: Quality gate - check for performance degradation
        if: always()
        run: |
          python3 benchmark/compare-metrics.py --check \
            "${{ github.workspace }}/benchmark-output/before" \
            "${{ github.workspace }}/benchmark-output/after"

      - name: Comment on PR
        uses: peter-evans/create-or-update-comment@v4
        if: github.event_name == 'pull_request' && always()
        with:
          issue-number: ${{ github.event.pull_request.number }}
          body-path: report.md
          comment-tag: benchmark-results

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        if: always()
        with:
          name: benchmark-results
          path: ${{ github.workspace }}/benchmark-output/
          retention-days: 30