Create EKS cluster, deploy CKF and run bundle test #15
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Create EKS cluster, deploy CKF and run bundle test | |
| on: | |
| workflow_dispatch: # This event allows manual triggering from the Github UI | |
| secrets: | |
| BUNDLE_KUBEFLOW_EKS_AWS_ACCESS_KEY_ID: | |
| required: true | |
| BUNDLE_KUBEFLOW_EKS_AWS_SECRET_ACCESS_KEY: | |
| required: true | |
| schedule: | |
| - cron: "23 0 * * 2" | |
| jobs: | |
| deploy-ckf-to-eks: | |
| runs-on: ubuntu-22.04 | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v2 | |
| - name: Install tox | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install tox | |
| - name: Configure AWS Credentials | |
| env: | |
| AWS_ACCESS_KEY_ID: ${{ secrets.BUNDLE_KUBEFLOW_EKS_AWS_ACCESS_KEY_ID }} | |
| AWS_SECRET_ACCESS_KEY: ${{ secrets.BUNDLE_KUBEFLOW_EKS_AWS_SECRET_ACCESS_KEY }} | |
| run: | | |
| aws configure set aws_access_key_id $AWS_ACCESS_KEY_ID | |
| aws configure set aws_secret_access_key $AWS_SECRET_ACCESS_KEY | |
| aws configure set default.region eu-central-1 | |
| - name: Install kubectl | |
| run: | | |
| sudo snap install kubectl --classic --channel=1.24/stable | |
| mkdir ~/.kube | |
| kubectl version --client | |
| - name: Install eksctl | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y unzip | |
| curl --silent --location "https://github.com/weaveworks/eksctl/releases/latest/download/eksctl_$(uname -s)_amd64.tar.gz" | tar xz -C /tmp | |
| sudo mv /tmp/eksctl /usr/local/bin | |
| eksctl version | |
| - name: Install juju | |
| run: | | |
| sudo snap install juju --classic --channel=2.9/stable | |
| sudo snap install charmcraft --classic | |
| juju version | |
| - name: Create cluster | |
| run: | | |
| eksctl create cluster -f .github/cluster.yaml | |
| kubectl get nodes | |
| - name: Setup juju | |
| run: | | |
| juju add-k8s kubeflow --client | |
| juju bootstrap --no-gui kubeflow kubeflow-controller | |
| juju add-model kubeflow | |
| - name: Test bundle deployment | |
| run: | | |
| tox -vve test_bundle_deployment-1.7 -- --model kubeflow --keep-models -vv -s | |
| # On failure, capture debugging resources | |
| - name: Get juju status | |
| run: juju status | |
| if: failure() | |
| - name: Get juju debug logs | |
| run: juju debug-log --replay --no-tail | |
| if: failure() | |
| - name: Get all kubernetes resources | |
| run: kubectl get all -A | |
| if: failure() | |
| - name: Get logs from pods with status = Pending | |
| run: kubectl -n kubeflow get pods | tail -n +2 | grep Pending | awk '{print $1}' | xargs -n1 kubectl -n kubeflow logs --all-containers=true --tail 100 | |
| if: failure() | |
| - name: Get logs from pods with status = Failed | |
| run: kubectl -n kubeflow get pods | tail -n +2 | grep Failed | awk '{print $1}' | xargs -n1 kubectl -n kubeflow logs --all-containers=true --tail 100 | |
| if: failure() | |
| - name: Get logs from pods with status = CrashLoopBackOff | |
| run: kubectl -n kubeflow get pods | tail -n +2 | grep CrashLoopBackOff | awk '{print $1}' | xargs -n1 kubectl -n kubeflow logs --all-containers=true --tail 100 | |
| if: failure() | |
| - name: Delete EKS cluster | |
| if: always() | |
| run: | | |
| eksctl delete cluster --region eu-central-1 --name=kubeflow-test | |
| delete-unattached-volumes: | |
| if: always() | |
| uses: ./.github/workflows/delete-aws-volumes.yaml | |
| secrets: inherit | |
| with: | |
| region: eu-central-1 | |
| needs: [deploy-ckf-to-eks] |