constellation/.github/actions/constellation_create/action.yml

name: Constellation create
description: Create a new Constellation cluster using latest OS image.

inputs:
  workerNodesCount:
    description: "Number of worker nodes to spawn."
    required: true
  controlNodesCount:
    description: "Number of control-plane nodes to spawn."
    required: true
  cloudProvider:
    description: "Either 'gcp', 'aws' or 'azure'."
    required: true
  machineType:
    description: "Machine type of VM to spawn."
    required: false
  cliVersion:
    description: "Version of the CLI"
    required: true
  osImage:
    description: "OS image to use."
    required: true
  isDebugImage:
    description: "Is OS img a debug img?"
    required: true
  kubernetesVersion:
    description: "Kubernetes version to create the cluster from."
    required: false
  artifactNameSuffix:
    description: "Suffix for artifact naming."
    required: true
  fetchMeasurements:
    default: "false"
    description: "Update measurements via the 'constellation config fetch-measurements' command."
  azureSNPEnforcementPolicy:
    required: false
    description: "Azure SNP enforcement policy."
  test:
    description: "The e2e test payload."
    required: true
  azureClusterCreateCredentials:
    description: "Azure credentials authorized to create a Constellation cluster."
    required: true
  azureIAMCreateCredentials:
    description: "Azure credentials authorized to create an IAM configuration."
    required: true
  refStream:
    description: "Reference and stream of the image in use"
    required: false

outputs:
  kubeconfig:
    description: "The kubeconfig for the cluster."
    value: ${{ steps.constellation-init.outputs.KUBECONFIG }}
  osImageUsed:
    description: "The OS image used in the cluster."
    value: ${{ steps.setImage.outputs.image }}

runs:
  using: "composite"
  steps:
    - name: Set constellation name
      shell: bash
      run: |
        yq eval -i "(.name) = \"e2e-test\"" constellation-conf.yaml        

    - name: Set Azure SNP enforcement policy
      if: inputs.azureSNPEnforcementPolicy != ''
      shell: bash
      run: |
        if [[ ${{ inputs.cloudProvider }} != 'azure' ]]; then
          echo "SNP enforcement policy is only supported for Azure"
          exit 1
        fi
        yq eval -i "(.attestation.azureSEVSNP.firmwareSignerConfig.enforcementPolicy) \
          = \"${{ inputs.azureSNPEnforcementPolicy }}\"" constellation-conf.yaml        

    - name: Set image
      id: setImage
      shell: bash
      env:
        imageInput: ${{ inputs.osImage }}
      run: |
        if [[ -z "${imageInput}" ]]; then
          echo "No image specified. Using default image from config."
          image=$(yq eval ".image" constellation-conf.yaml)
          echo "image=${image}" | tee -a "$GITHUB_OUTPUT"
          exit 0
        fi

        yq eval -i "(.image) = \"${imageInput}\"" constellation-conf.yaml
        echo "image=${imageInput}" | tee -a "$GITHUB_OUTPUT"        

    - name: Update measurements for non-stable images
      if: inputs.fetchMeasurements
      shell: bash
      run: |
        constellation config fetch-measurements --debug --insecure        

    - name: Set instanceType
      if: inputs.machineType && inputs.machineType != 'default'
      shell: bash
      run: |
        yq eval -i "(.nodeGroups[] | .instanceType) = \"${{ inputs.machineType }}\"" constellation-conf.yaml        

    - name: Set node count
      shell: bash
      run: |
        yq eval -i "(.nodeGroups[] | select(.role == \"control-plane\") | .initialCount) = ${{ inputs.controlNodesCount }}" constellation-conf.yaml
        yq eval -i "(.nodeGroups[] | select(.role == \"worker\") | .initialCount) = ${{ inputs.workerNodesCount }}" constellation-conf.yaml        

    - name: Enable debugCluster flag
      if: inputs.isDebugImage == 'true'
      shell: bash
      run: |
        yq eval -i '(.debugCluster) = true' constellation-conf.yaml        

    # Uses --force flag since the CLI currently does not have a pre-release version and is always on the latest released version.
    # However, many of our pipelines work on prerelease images. Thus the used images are newer than the CLI's version.
    # This makes the version validation in the CLI fail.
    - name: Constellation create
      shell: bash
      run: |
        echo "Creating cluster using config:"
        cat constellation-conf.yaml
        sudo sh -c 'echo "127.0.0.1 license.confidential.cloud" >> /etc/hosts' || true
        constellation create -y --force --debug --tf-log=DEBUG        

    - name: Cdbg deploy
      if: inputs.isDebugImage == 'true'
      uses: ./.github/actions/cdbg_deploy
      with:
        cloudProvider: ${{ inputs.cloudProvider }}
        test: ${{ inputs.test }}
        azureClusterCreateCredentials: ${{ inputs.azureClusterCreateCredentials }}
        azureIAMCreateCredentials: ${{ inputs.azureIAMCreateCredentials }}
        refStream: ${{ inputs.refStream }}
        kubernetesVersion: ${{ inputs.kubernetesVersion }}

    - name: Constellation init
      id: constellation-init
      shell: bash
      run: |
        constellation init --force --debug
        echo "KUBECONFIG=$(pwd)/constellation-admin.conf" | tee -a $GITHUB_OUTPUT        

    - name: Wait for nodes to join and become ready
      shell: bash
      env:
        KUBECONFIG: "${{ steps.constellation-init.outputs.KUBECONFIG }}"
        JOINTIMEOUT: "1200" # 20 minutes timeout for all nodes to join
      run: |
        echo "::group::Wait for nodes"
        NODES_COUNT=$((${{ inputs.controlNodesCount }} + ${{ inputs.workerNodesCount }}))
        JOINWAIT=0
        until [[ "$(kubectl get nodes -o json | jq '.items | length')" == "${NODES_COUNT}" ]] || [[ $JOINWAIT -gt $JOINTIMEOUT ]];
        do
            echo "$(kubectl get nodes -o json | jq '.items | length')/"${NODES_COUNT}" nodes have joined.. waiting.."
            JOINWAIT=$((JOINWAIT+30))
            sleep 30
        done
        if [[ $JOINWAIT -gt $JOINTIMEOUT ]]; then
            echo "Timed out waiting for nodes to join"
            exit 1
        fi
        echo "$(kubectl get nodes -o json | jq '.items | length')/"${NODES_COUNT}" nodes have joined"
        if ! kubectl wait --for=condition=ready --all nodes --timeout=20m; then
          kubectl get pods -n kube-system
          kubectl get events -n kube-system
          echo "::error::kubectl wait timed out before all nodes became ready"
          echo "::endgroup::"
          exit 1
        fi
        echo "::endgroup::"        

    - name: Download boot logs
      if: always()
      continue-on-error: true
      shell: bash
      env:
        CSP: ${{ inputs.cloudProvider }}
      run: |
        echo "::group::Download boot logs"
        CONSTELL_UID=$(yq '.infrastructure.uid' constellation-state.yaml)
        case $CSP in
          azure)
            AZURE_RESOURCE_GROUP=$(yq eval ".provider.azure.resourceGroup" constellation-conf.yaml)
            ./.github/actions/constellation_create/az-logs.sh ${AZURE_RESOURCE_GROUP}
            ;;
          gcp)
            GCP_ZONE=$(yq eval ".provider.gcp.zone" constellation-conf.yaml)
            ./.github/actions/constellation_create/gcp-logs.sh ${GCP_ZONE} ${CONSTELL_UID}
            ;;
          aws)
            ./.github/actions/constellation_create/aws-logs.sh us-east-2 ${CONSTELL_UID}
            ;;
        esac
        echo "::endgroup::"        

    - name: Upload boot logs
      if: always() && !env.ACT
      continue-on-error: true
      uses: actions/upload-artifact@a8a3f3ad30e3422c9c7b888a15615d19a852ae32 # v3.1.3
      with:
        name: serial-logs-${{ inputs.artifactNameSuffix }}
        path: |
          *.log
          !terraform.log