tests.yaml

name: Tests
on:
  push:
    branches: [main]
    tags:
      - v*
  pull_request:
    branches: [main]

jobs:
  lint:
    name: Lint golang code
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Ensure go version
        uses: actions/setup-go@v5
        with:
          go-version-file: "go.mod"
          check-latest: true
      - name: fmt check
        run: test -z $(go fmt ./...)
      - name: lint
        run: make lint
      - name: Install pre-commit
        run: |
          pip install pre-commit
          pre-commit install
      - name: Run pre-commit hooks
        run: pre-commit run --all-files

  unit-tests:
    name: Run go tests
    runs-on: ubuntu-latest
    steps:
      - name: checkout
        uses: actions/checkout@v4
      - name: Ensure go version
        uses: actions/setup-go@v5
        with:
          go-version-file: "go.mod"
          check-latest: true
      - name: run tests
        run: go test -json ./... > test.json
      - name: Annotate tests
        if: always()
        uses: guyarb/golang-test-annoations@v0.8.0
        with:
          test-results: test.json

  shellcheck:
    name: Lint bash code with shellcheck
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Run ShellCheck
        uses: bewuethr/shellcheck-action@v2

  # This ensures the latest code works with the manifests built from tree.
  # It is useful for two things:
  # - Test manifests changes (obviously), ensuring they don't break existing clusters
  # - Ensure manifests work with the latest versions even with no manifest change
  #     (compared to helm charts, manifests cannot easily template changes based on versions)
  # Helm charts are _trailing_ releases, while manifests are done during development.
  # This test uses the "command" reboot-method.
  e2e-manifests-command:
    name: End-to-End test with kured with code and manifests from HEAD (command)
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        job:
          - {kubernetes: "1.30", concurrency: 1}
          - {kubernetes: "1.29", concurrency: 1}
          - {kubernetes: "1.30", concurrency: 2}
          - {kubernetes: "1.29", concurrency: 2}
    steps:
      - uses: actions/checkout@v4
      - name: Ensure go version
        uses: actions/setup-go@v5
        with:
          go-version-file: "go.mod"
          check-latest: true
      - name: Set up QEMU
        uses: docker/setup-qemu-action@v3
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
      - name: Find current tag version
        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
        id: tags
      - name: Build artifacts
        run: |
          VERSION="${{ steps.tags.outputs.sha_short }}" make image
          VERSION="${{ steps.tags.outputs.sha_short }}" make manifest

      - name: Workaround "Failed to attach 1 to compat systemd cgroup /actions_job/..." on gh actions
        run: |
          sudo bash << EOF
              cp /etc/docker/daemon.json /etc/docker/daemon.json.old
              echo '{}' > /etc/docker/daemon.json
              systemctl restart docker || journalctl --no-pager -n 500
              systemctl status docker
          EOF

      # Default name for helm/kind-action kind clusters is "chart-testing"
      - name: Create kind cluster with 5 nodes
        uses: helm/kind-action@v1.10.0
        with:
          config: .github/kind-cluster-${{ matrix.job.kubernetes }}.yaml
          version: v0.14.0

      - name: Preload previously built images onto kind cluster
        run: kind load docker-image ghcr.io/${{ github.repository }}:${{ steps.tags.outputs.sha_short }} --name chart-testing

      - name: Install Alertmanager
        run: |
          kubectl apply -f test/alertmanager.yaml

      - name: Install Kured
        run: |
          curl -fsSL -o get_helm.sh https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3
          chmod 700 get_helm.sh
          ./get_helm.sh

          helm repo add kubereboot https://kubereboot.github.io/charts
          helm install -n kube-system kured kubereboot/kured --set configuration.period=10s --set configuration.concurrency=${{ matrix.job.concurrency }}

      - name: Ensure kured is ready
        uses: nick-invision/retry@v3.0.0
        with:
          timeout_minutes: 10
          max_attempts: 10
          retry_wait_seconds: 60
          # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE should all be = to cluster_size
          command: "kubectl get ds -n kube-system kured | grep -E 'kured.*5.*5.*5.*5.*5'"

      - name: Install kured-alert-silencer with kubectl
        run: |
          kubectl apply -f install/kubernetes/rbac.yaml && kubectl apply -f install/kubernetes/deployment.yaml

      - name: Create reboot sentinel files
        run: |
          ./test/kind/create-reboot-sentinels.sh

      - name: Follow reboot until success
        env:
          DEBUG: true
        run: |
          ./test/kind/follow-coordinated-reboot.sh

      - name: Check all silences were created
        run: |
          ./test/kind/check-silences.sh

  rerun-failed-jobs:
    runs-on: ubuntu-latest
    needs:
      - e2e-manifests-command
    if: failure()
    steps:
      - name: Rerun failed jobs in the current workflow
        env:
          GH_REPO: ${{ github.repository }}
          GH_TOKEN: ${{ github.token }}
        run: gh workflow run retry-workflow.yaml -F run_id=${{ github.run_id }}