Merge pull request #1 from project-codeflare/RHOAIENG-24150

RHOAIENG-24150: e2e kuberay upgrade

Author: pawelpaszki

.github/workflows/kuberay-upgrade.yml

@@ -10,8 +10,78 @@ jobs:
     permissions:
       contents: read
     steps:
-      - name: dummy test
+      - name: Clone KubeRay repository
         run: |
-          sleep 60 # test success
-      #     # sleep 300 # test failure
-      #     # exit 1 # test failure
+          git clone --depth=1 --branch dev https://github.com/opendatahub-io/kuberay.git
+      
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          cache: false
+          go-version: '1.24'
+
+      - name: Install go dependencies
+        run: |
+          ls
+          cd ${{ github.workspace }}/kuberay/ray-operator
+          go mod download
+
+      - name: Install helm
+        run: |
+          curl -Lo helm.tar.gz https://get.helm.sh/helm-v3.12.2-linux-amd64.tar.gz
+          tar -zxvf helm.tar.gz
+          mv linux-amd64/helm /usr/local/bin/helm
+          helm repo add kuberay https://ray-project.github.io/kuberay-helm/
+          helm repo update
+
+      - name: Install kind
+        run: go install sigs.k8s.io/kind@latest
+
+      - name: Create Kind Cluster
+        run: kind create cluster
+
+      - name: Set kubectl context
+        run: kubectl cluster-info --context kind-kind
+
+      - name: Install Older KubeRay Operator (v1.3.2)
+        run: |
+          helm repo add kuberay https://ray-project.github.io/kuberay-helm/
+          helm install kuberay-operator kuberay/kuberay-operator --version 1.3.2
+
+      - name: Wait for Kuberay Operator to be available
+        run: kubectl wait --timeout=90s --for=condition=Available=true deployment -n default kuberay-operator
+
+      - name: Prepare and Run Upgrade Tests
+        run: |
+          cd kuberay/ray-operator
+          echo "--- START:Running e2e Operator upgrade (v1.3.2 to v1.4.0 operator) tests"
+          KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m KUBERAY_TEST_UPGRADE_IMAGE=v1.4.0 \
+          go test -timeout 30m -v ./test/e2eupgrade
+          echo "--- END:e2e Operator upgrade (v1.3.2 to v1.4.0 operator) tests finished"
+
+      - name: Debug Kubernetes Cluster on Failure
+        if: failure()
+        run: |
+          echo "--- DEBUG OUTPUT ---"
+          echo "Checking GitHub Runner resources..."
+          lscpu
+          free -h
+          echo "Checking Kubernetes cluster state..."
+          kubectl cluster-info
+          kubectl get nodes
+          
+          echo "Describing all nodes..."
+          kubectl describe nodes
+          echo "Printing all Kubernetes events..."
+          kubectl get events -A
+          echo "Getting logs of Kind control plane container..."
+          docker logs kind-control-plane
+          echo "--- END OF DEBUG OUTPUT ---"
+      - name: Display all pods on kind cluster
+        if: failure()
+        run: kubectl get pods -A
+
+      - name: Cleanup
+        if: always()
+        run: kind delete clusters --all || true
+