eks.yaml

name: EKS (ENI)

# Any change in triggers needs to be reflected in the concurrency group.
on:
  ### FOR TESTING PURPOSES
  # This workflow runs in the context of `main`, and ignores changes to
  # workflow files in PRs. For testing changes to this workflow from a PR:
  # - Make sure the PR uses a branch from the base repository (requires write
  #   privileges). It will not work with a branch from a fork (missing secrets).
  # - Uncomment the `pull_request` event below, commit separately with a `DO
  #   NOT MERGE` message, and push to the PR. As long as the commit is present,
  #   any push to the PR will trigger this workflow.
  # - Don't forget to remove the `DO NOT MERGE` commit once satisfied. The run
  #   will disappear from the PR checks: please provide a direct link to the
  #   successful workflow run (can be found from Actions tab) in a comment.
  #
  # pull_request: {}
  ###
  pull_request_target: {}
  # Run every 6 hours
  schedule:
    - cron:  '0 1/6 * * *'

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || 'scheduled' }}
  cancel-in-progress: true

env:
  region: us-east-2
  eksctl_version: v0.147.0
  # renovate: datasource=github-releases depName=cilium/cilium
  cilium_version: v1.16.2
  kubectl_version: v1.23.6

jobs:
  installation-and-connectivity:
    name: EKS Installation and Connectivity Test
    if: ${{ github.repository == 'cilium/cilium-cli' }}
    runs-on: ubuntu-24.04
    permissions:
      # To be able to request the JWT from GitHub's OIDC provider
      id-token: write
    timeout-minutes: 60
    steps:
      - name: Set cluster name
        run: |
          echo "clusterName=${{ github.repository_owner }}-${{ github.event.repository.name }}-${{ github.run_id }}-${{ github.run_attempt }}" >> $GITHUB_ENV

      - name: Checkout
        uses: actions/checkout@d632683dd7b4114ad314bca15554477dd762a938 # v4.2.0

      - name: Install kubectl
        run: |
          curl -sLO "https://dl.k8s.io/release/${{ env.kubectl_version }}/bin/linux/amd64/kubectl"
          curl -sLO "https://dl.k8s.io/${{ env.kubectl_version }}/bin/linux/amd64/kubectl.sha256"
          echo "$(cat kubectl.sha256)  kubectl" | sha256sum --check
          sudo install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl
          kubectl version --client

      - name: Install eksctl CLI
        run: |
          curl -LO "https://github.com/weaveworks/eksctl/releases/download/${{ env.eksctl_version }}/eksctl_$(uname -s)_amd64.tar.gz"
          sudo tar xzvfC eksctl_$(uname -s)_amd64.tar.gz /usr/bin
          rm eksctl_$(uname -s)_amd64.tar.gz

      - name: Set up AWS CLI credentials
        uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
        with:
          role-to-assume: ${{ secrets.AWS_PR_ASSUME_ROLE }}
          aws-region: ${{ env.region }}

      - name: Run aws configure
        run: |
          aws configure set aws_access_key_id ${{ env.AWS_ACCESS_KEY_ID }}
          aws configure set aws_secret_access_key ${{ env.AWS_SECRET_ACCESS_KEY }}
          aws configure set aws_session_token ${{ env.AWS_SESSION_TOKEN }}
          aws configure set default.region ${{ env.AWS_REGION }}

      - name: Set up job variables
        id: vars
        run: |
          env
          if [ ${{ github.event.issue.pull_request || github.event.pull_request }} ]; then
            PR_API_JSON=$(curl \
              -H "Accept: application/vnd.github.v3+json" \
              -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" \
              ${{ github.event.issue.pull_request.url || github.event.pull_request.url }})
            SHA=$(echo "$PR_API_JSON" | jq -r ".head.sha")
            OWNER=$(echo "$PR_API_JSON" | jq -r ".number")
          else
            SHA=${{ github.sha }}
            OWNER=${{ github.sha }}
          fi

          echo "sha=${SHA}" >> $GITHUB_OUTPUT
          echo "owner=${OWNER}" >> $GITHUB_OUTPUT

      - name: Create EKS cluster
        run: |
          cat <<EOF > eks-config.yaml
          apiVersion: eksctl.io/v1alpha5
          kind: ClusterConfig

          metadata:
            name: ${{ env.clusterName }}
            region: ${{ env.region }}
            tags:
             usage: "${{ github.repository_owner }}-${{ github.event.repository.name }}"
             owner: "${{ steps.vars.outputs.owner }}"

          managedNodeGroups:
          - name: ng-1
            instanceTypes:
             - t3.medium
             - t3a.medium
            desiredCapacity: 2
            spot: true
            privateNetworking: true
            volumeType: "gp3"
            volumeSize: 10
            taints:
             - key: "node.cilium.io/agent-not-ready"
               value: "true"
               effect: "NoExecute"
          EOF

          eksctl create cluster -f ./eks-config.yaml

      - name: Install Cilium CLI
        uses: ./
        with:
          skip-build: 'true'
          image-tag: ${{ steps.vars.outputs.sha }}

      - name: Install Cilium and run tests
        timeout-minutes: 30
        run: |
          # Install Cilium
          cilium install \
            --version "${{ env.cilium_version }}" \
            --set cluster.name="${{ env.clusterName }}" \
            --wait=false \
            --set loadBalancer.l7.backend=envoy \
            --set tls.secretsBackend=k8s \
            --set bpf.monitorAggregation=none

          # Enable Relay
          cilium hubble enable

          # Wait for cilium and hubble relay to be ready
          # NB: necessary to work against occasional flakes due to https://github.com/cilium/cilium-cli/issues/918
          cilium status --wait

          # Make sure the 'aws-node' DaemonSet exists but has no scheduled pods
          [[ $(kubectl -n kube-system get ds/aws-node -o jsonpath='{.status.currentNumberScheduled}') == 0 ]]

          # Port forward Relay
          cilium hubble port-forward&
          sleep 10s
          [[ $(pgrep -f "kubectl.*port-forward.*hubble-relay" | wc -l) == 1 ]]

          # Run connectivity test
          cilium connectivity test --test-concurrency=3 --all-flows --collect-sysdump-on-failure --external-target amazon.com.
          kubectl delete namespace -l "app.kubernetes.io/name=cilium-cli"

          # Run performance test
          cilium connectivity perf --duration 1s

      - name: Post-test information gathering
        if: ${{ !success() }}
        run: |
          echo "=== Retrieve cluster state ==="
          kubectl get pods --all-namespaces -o wide
          cilium status
          cilium sysdump --output-filename cilium-sysdump-out
        shell: bash {0} # Disable default fail-fast behaviour so that all commands run independently

      - name: Uninstall and make sure the 'aws-node' DaemonSet blocking nodeSelector was removed
        if: ${{ success() }}
        timeout-minutes: 5
        run: |
          cilium uninstall --wait

          # Make sure the 'aws-node' DaemonSet blocking nodeSelector was removed
          [[ ! $(kubectl -n kube-system get ds/aws-node -o jsonpath="{.spec.template.spec.nodeSelector['io\.cilium/aws-node-enabled']}") ]]

      - name: Clean up EKS
        if: ${{ always() }}
        run: |
          eksctl delete cluster --name ${{ env.clusterName }}
        shell: bash {0} # Disable default fail-fast behaviour so that all commands run independently

      - name: Upload artifacts
        if: ${{ !success() }}
        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874 # v4.4.0
        with:
          name: cilium-sysdump-out.zip
          path: cilium-sysdump-out.zip
          retention-days: 5