e2e-ci.yaml

name: E2E Prometheus Federator

on:
  workflow_dispatch:
    inputs:
      enable_tmate:
        description: 'Enable debugging via tmate'
        required: false
        default: "false"
      debug:
        description: "Enable debug logs"
        required: false
        default: "false"
      k3s_version:
        description: "Version of k3s to use for the underlying cluster, should exist in https://hub.docker.com/r/rancher/k3s/tags"
        required: false
  pull_request:
    paths-ignore:
      - 'docs/**'
      - 'scripts/**'
      - '*.md'
      - '*.dapper'
      - '.gitignore'
      - 'CODEOWNERS'
      - 'LICENSE'
      - 'Makefile'

env:
  GOARCH: amd64
  CGO_ENABLED: 0
  SETUP_GO_VERSION: '^1.18'
  YQ_VERSION: v4.25.1
  E2E_CI: true
  REPO: rancher
  TAG: dev
  APISERVER_PORT: 8001
  DEFAULT_SLEEP_TIMEOUT_SECONDS: 10
  KUBECTL_WAIT_TIMEOUT: 300s
  DEBUG: ${{ github.event.inputs.debug || false }}

permissions:
  contents: write

jobs:
  e2e-prometheus-federator:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        k3s_version:
          # k3d version list k3s | sed 's/+/-/' | sort -h
          - ${{ github.event.inputs.k3s_version || 'v1.20.15-k3s1' }}
    steps:
      -
        uses: actions/checkout@v3
        with:
          fetch-depth: 0
      - uses: actions/setup-go@v4
        with:
          go-version: '>=1.17.0'
      - uses: azure/setup-kubectl@v3
      - uses: azure/setup-helm@v3
      -
        name: Install mikefarah/yq
        run: |
          sudo wget https://github.com/mikefarah/yq/releases/download/${YQ_VERSION}/yq_linux_amd64 -O /usr/bin/yq && sudo chmod +x /usr/bin/yq;
      -
        name: Perform CI
        run: |
          REPO=${REPO} TAG=${TAG} ./scripts/build;
          REPO=${REPO} TAG=${TAG} ./scripts/package;
      -
        name: Provision k3d Cluster
        uses: AbsaOSS/k3d-action@v2
        # k3d will automatically create a network named k3d-test-cluster-1 with the range 172.18.0.0/16
        with:
          cluster-name: "e2e-ci-prometheus-federator"
          args: >-
            --agents 1
            --network "nw01"
            --image docker.io/rancher/k3s:${{matrix.k3s_version}}
      -
        name: Import Images Into k3d
        run: |
          k3d image import ${REPO}/prometheus-federator:${TAG} -c e2e-ci-prometheus-federator;
      -
        name: Setup kubectl context
        run: |
          kubectl config use-context k3d-e2e-ci-prometheus-federator;
      -
        name: Set Up Tmate Debug Session
        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.enable_tmate == 'true' }}
        uses: mxschmitt/action-tmate@v3
        timeout-minutes: 15
        with:
          limit-access-to-actor: true
      -
        name: Install Rancher Monitoring
        run: ./.github/workflows/e2e/scripts/install-monitoring.sh;
      - 
        name: Check if Rancher Monitoring is up
        run: ./.github/workflows/e2e/scripts/validate-monitoring.sh;
      -
        name: Install Prometheus Federator
        run: ./.github/workflows/e2e/scripts/install-federator.sh;
      - 
        name: Check if Prometheus Federator is up
        run: ./.github/workflows/e2e/scripts/validate-federator.sh;
      -
        name: Check if Project Registration Namespace is auto-created on namespace detection
        run: ./.github/workflows/e2e/scripts/create-project-namespace.sh;

      # Commenting out for failure in CI but not locally
      # -
      #   name: Create Project Monitoring Stack via ProjectHelmChart CR
      #   run: ./.github/workflows/e2e/scripts/create-projecthelmchart.sh;
      # - 
      #   name: Check if the Project Prometheus Stack is up
      #   run: ./.github/workflows/e2e/scripts/validate-project-monitoring.sh;
      # - 
      #   name: Wait for 8 minutes for enough scraping to be done to continue
      #   run: |
      #     for i in {1..48}; do sleep 10; echo "Waited $((i*10)) seconds for metrics to be populated"...; done;
      # -
      #   name: Validate Project Prometheus Targets
      #   run: ./.github/workflows/e2e/scripts/validate-project-prometheus-targets.sh;
      # -
      #   name: Validate Project Grafana Datasources
      #   run: ./.github/workflows/e2e/scripts/validate-project-grafana-datasource.sh;
      # -
      #   name: Validate Project Grafana Dashboards
      #   run: ./.github/workflows/e2e/scripts/validate-project-grafana-dashboards.sh;
      # #-
      #   #name: Validate Project Grafana Dashboard Data
      #   #run: ./.github/workflows/e2e/scripts/validate-project-grafana-dashboard-data.sh;
      # -
      #   name: Validate Project Prometheus Alerts
      #   run: ./.github/workflows/e2e/scripts/validate-project-prometheus-alerts.sh;
      # -
      #   name: Validate Project Alertmanager
      #   run: ./.github/workflows/e2e/scripts/validate-project-alertmanager.sh;
      # - 
      #   name: Delete Project Prometheus Stack
      #   run: ./.github/workflows/e2e/scripts/delete-projecthelmchart.sh;
      - 
        name: Uninstall Prometheus Federator
        run: ./.github/workflows/e2e/scripts/uninstall-federator.sh;
      - name: Generate artifacts on failure
        if: failure()
        run: ./.github/workflows/e2e/scripts/generate-artifacts.sh;
      - name: Upload logs and manifests on failure
        if: failure()
        uses: actions/upload-artifact@v3
        with:
          name: artifacts
          path: artifacts/
          retention-days: 1
      - 
        name: Delete k3d cluster
        if: always()
        run: k3d cluster delete e2e-ci-prometheus-federator