kured/.github/workflows/on-pr.yaml

name: PR
on:
  pull_request:
  push:

jobs:
  pr-gotest:
    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@v0.7.0
        with:
          test-results: test.json

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

  pr-lint-code:
    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: Lint cmd folder
      uses: Jerome1337/golint-action@v1.0.3
      with:
        golint-path: './cmd/...'
    - name: Lint pkg folder
      uses: Jerome1337/golint-action@v1.0.3
      with:
        golint-path: './pkg/...'

  pr-check-docs-links:
    name: Check docs for incorrect links
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
    - name: Link Checker
      uses: lycheeverse/lychee-action@c053181aa0c3d17606addfe97a9075a32723548a
      env:
        GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
      with:
        args: --verbose --no-progress '*.md' '*.yaml' '*/*/*.go' --exclude-link-local
        fail: true

  # This should not be made a mandatory test
  # It is only used to make us aware of any potential security failure, that
  # should trigger a bump of the image in build/.
  pr-vuln-scan:
    name: Build image and scan it against known vulnerabilities
    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: Set up QEMU
        uses: docker/setup-qemu-action@v3
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
      - name: Setup GoReleaser
        run: make bootstrap-tools
      - name: Find current tag version
        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
        id: tags
      - name: Build image
        run: VERSION="${{ steps.tags.outputs.sha_short }}" make image
      - name: Run Trivy vulnerability scanner
        uses: aquasecurity/trivy-action@d43c1f16c00cfd3978dde6c07f4bbcf9eb6993ca
        with:
          image-ref: 'ghcr.io/${{ github.repository }}:${{ steps.tags.outputs.sha_short }}'
          format: 'table'
          exit-code: '1'
          ignore-unfixed: true
          vuln-type: 'os,library'
          severity: 'CRITICAL,HIGH'

  # 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:
        kubernetes:
          - "1.27"
          - "1.28"
          - "1.29"
    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: Setup GoReleaser
        run: make bootstrap-tools
      - 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@v1.8.0
        with:
          config: .github/kind-cluster-${{ matrix.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: Do not wait for an hour before detecting the rebootSentinel
        run: |
          sed -i 's/#\(.*\)--period=1h/\1--period=30s/g' kured-ds.yaml

      - name: Install kured with kubectl
        run: |
          kubectl apply -f kured-rbac.yaml && kubectl apply -f kured-ds.yaml

      - name: Ensure kured is ready
        uses: nick-invision/retry@v2.9.0
        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: Create reboot sentinel files
        run: |
          ./tests/kind/create-reboot-sentinels.sh

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


  # 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 "signal" reboot-method.
  e2e-manifests-signal:
    name: End-to-End test with kured with code and manifests from HEAD (signal)
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        kubernetes:
          - "1.27"
          - "1.28"
          - "1.29"
    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: Setup GoReleaser
        run: make bootstrap-tools
      - 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@v1.8.0
        with:
          config: .github/kind-cluster-${{ matrix.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: Do not wait for an hour before detecting the rebootSentinel
        run: |
          sed -i 's/#\(.*\)--period=1h/\1--period=30s/g' kured-ds-signal.yaml

      - name: Install kured with kubectl
        run: |
          kubectl apply -f kured-rbac.yaml && kubectl apply -f kured-ds-signal.yaml

      - name: Ensure kured is ready
        uses: nick-invision/retry@v2.9.0
        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: Create reboot sentinel files
        run: |
          ./tests/kind/create-reboot-sentinels.sh

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



  # 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.
  # Concurrency = 2
  e2e-manifests-concurent:
    name: End-to-End test with kured with code and manifests from HEAD (concurrent)
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        kubernetes:
          - "1.27"
          - "1.28"
          - "1.29"
    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: Setup GoReleaser
        run: make bootstrap-tools
      - 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@v1.8.0
        with:
          config: .github/kind-cluster-${{ matrix.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: Do not wait for an hour before detecting the rebootSentinel
        run: |
          sed -i 's/#\(.*\)--period=1h/\1--period=30s/g' kured-ds.yaml
          sed -i 's/#\(.*\)--concurrency=1/\1--concurrency=2/g' kured-ds.yaml

      - name: Install kured with kubectl
        run: |
          kubectl apply -f kured-rbac.yaml && kubectl apply -f kured-ds.yaml

      - name: Ensure kured is ready
        uses: nick-invision/retry@v2.9.0
        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: Create reboot sentinel files
        run: |
          ./tests/kind/create-reboot-sentinels.sh

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