test-replace-failed-postgresql.yaml

---
name: Test replace failed PostgreSQL
on:
  pull_request:
    paths:
      - .github/workflows/**/*
      - spec/**/*
      - lib/**/*
      - tasks/**/*
      - functions/**/*
      - types/**/*
      - plans/**/*
      - hiera/**/*
      - manifests/**/*
      - templates/**/*
      - files/**/*
      - metadata.json
      - Rakefile
      - Gemfile
      - provision.yaml
      - .rspec
      - .rubocop.yml
      - .puppet-lint.rc
      - .fixtures.yml
    branches: [main]
  workflow_dispatch: {}
jobs:
  test-replace-failed-postgresql:
    name: PE ${{ matrix.version }} ${{ matrix.architecture }} on ${{ matrix.image }}
    runs-on: ubuntu-latest
    env:
      BOLT_GEM: true
      BOLT_DISABLE_ANALYTICS: true
      LANG: en_US.UTF-8
    strategy:
      fail-fast: false
      matrix:
        architecture: [extra-large-with-dr-and-spare-replica]
        install_architecture: [extra-large-with-dr]
        version: [2021.7.9, 2023.8.2, 2025.2.0]
        image: [almalinux-cloud/almalinux-8]
    steps:
      - name: Checkout Source
        uses: actions/checkout@v4
        with:
          ref: ${{ github.head_ref }}
      - name: Activate Ruby 2.7
        uses: ruby/setup-ruby@v1
        with:
          ruby-version: '2.7'
          bundler-cache: true
      - name: Print bundle environment
        if: ${{ github.repository_owner == 'puppetlabs' }}
        run: |
          echo ::group::info:bundler
            bundle env
          echo ::endgroup::
      - name: Provision test cluster
        timeout-minutes: 15
        run: |
          echo ::group::prepare
            mkdir -p $HOME/.ssh
            echo 'Host *'                      >  $HOME/.ssh/config
            echo '    ServerAliveInterval 150' >> $HOME/.ssh/config
            echo '    ServerAliveCountMax 2'   >> $HOME/.ssh/config
            bundle exec rake spec_prep
          echo ::endgroup::
          echo ::group::provision
            bundle exec bolt plan run peadm_spec::provision_test_cluster \
              --modulepath spec/fixtures/modules \
              provider=provision_service \
              image=${{ matrix.image }} \
              architecture=${{ matrix.architecture }} \
              --log-level trace
          echo ::endgroup::
          echo ::group::info:request
            cat request.json || true; echo
          echo ::endgroup::
          echo ::group::info:inventory
            sed -e 's/password: .*/password: "[redacted]"/' < spec/fixtures/litmus_inventory.yaml || true
          echo ::endgroup::
          echo ::group::certnames
            bundle exec bolt plan run peadm_spec::add_inventory_hostnames \
            --inventory spec/fixtures/litmus_inventory.yaml \
            --modulepath spec/fixtures/modules \
            --no-host-key-check \
            inventory_file=spec/fixtures/litmus_inventory.yaml
          echo ::endgroup::            
      - name: Output contents of litmus_inventory.yaml
        run: |
          cat spec/fixtures/litmus_inventory.yaml
      - name: Install PE on test cluster
        timeout-minutes: 120
        run: |
          bundle exec bolt plan run peadm_spec::install_test_cluster \
            --inventoryfile spec/fixtures/litmus_inventory.yaml \
            --modulepath spec/fixtures/modules \
            architecture=${{ matrix.install_architecture }} \
            version=${{ matrix.version }} \
            console_password=${{ secrets.CONSOLE_PASSWORD }} \
            code_manager_auto_configure=true
      - name: Replace failed PostgreSQL
        run: |
          echo ::group::prepare
            mkdir -p $HOME/.ssh
            echo 'Host *'                      >  $HOME/.ssh/config
            echo '    ServerAliveInterval 150' >> $HOME/.ssh/config
            echo '    ServerAliveCountMax 2'   >> $HOME/.ssh/config
            bundle exec rake spec_prep
          echo ::endgroup::
          bundle exec bolt plan run peadm_spec::test_replace_failed_postgres \
            --inventoryfile spec/fixtures/litmus_inventory.yaml \
            --modulepath spec/fixtures/modules \
            primary_host=$(yq '.groups[].targets[] | select(.vars.role == "primary") | .name' spec/fixtures/litmus_inventory.yaml) \
            replica_host=$(yq '.groups[].targets[] | select(.vars.role == "replica") | .name' spec/fixtures/litmus_inventory.yaml) \
            working_postgresql_host=$(yq '.groups[].targets[] | select(.vars.role == "replica-pdb-postgresql") | .name' spec/fixtures/litmus_inventory.yaml) \
            failed_postgresql_host=$(yq '.groups[].targets[] | select(.vars.role == "primary-pdb-postgresql") | .name' spec/fixtures/litmus_inventory.yaml) \
            replacement_postgresql_host=$(yq '.groups[].targets[] | select(.vars.role == "spare-replica") | .name' spec/fixtures/litmus_inventory.yaml) \
          --no-host-key-check
      - name: Tear down PE XL DR test cluster
        if: ${{ always() }}
        continue-on-error: true
        run: |-
          if [ -f spec/fixtures/litmus_inventory.yaml ]; then
            echo ::group::tear_down
              bundle exec rake 'litmus:tear_down'
            echo ::endgroup::
            echo ::group::info:request
              cat request.json || true; echo
            echo ::endgroup::
          fi