Zane/configmap testing pipeline

.pipelines/azure-pipeline-config-tests.yaml

@@ -1,21 +1,229 @@
-# ConfigMap Testing Pipeline for ama-logs (stub - full implementation in zane/configmap-testing-pipeline)
+# ConfigMap Testing Pipeline for ama-logs
+# Applies different ConfigMap variants, restarts pods, and runs scenario-specific Ginkgo tests via TestKube.
+# Manual trigger only.
+
 trigger: none
 pr: none
 
 parameters:
   - name: clusterName
     displayName: 'AKS Cluster Name'
     type: string
+    default: 'ci-logs-dev-aks-std-prof-config-test1'
   - name: clusterResourceGroup
     displayName: 'AKS Cluster Resource Group'
     type: string
+    default: 'ci-logs-dev-aks-configmap-test'
+  - name: branch
+    displayName: 'Git branch for TestKube workflows'
+    type: string
+    default: 'zane/configmap-testing-pipeline'
+  # Case names must match the 'name' field in test/testkube/configmap-test-matrix.yaml
+  - name: cases
+    displayName: 'Test cases to run'
+    type: object
+    default:
+      - process-metrics-enabled
+      - process-metrics-default
 
 stages:
 - stage: ConfigMapTests
   jobs:
-  - job: Placeholder
+  - job: RunConfigMapTests
+    timeoutInMinutes: 120
+    displayName: "ConfigMap Processing Tests"
     pool:
       name: Azure-Pipelines-CI-Test-EO
+    variables:
+      skipComponentGovernanceDetection: true
     steps:
-    - script: echo "Pipeline created. Point to branch zane/configmap-testing-pipeline for full implementation."
-      displayName: 'Placeholder'
+    - checkout: self
+      persistCredentials: true
+
+    # === Setup ===
+
+    - script: |
+        curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash
+      displayName: 'Install Azure CLI'
+
+    - script: |
+        set -euo pipefail
+        echo "Ensuring kubectl & helm are installed"
+        if ! command -v az >/dev/null 2>&1; then
+          echo "Azure CLI not found; aborting" >&2
+          exit 1
+        fi
+        if ! command -v kubectl >/dev/null 2>&1; then
+          echo "kubectl not found. Installing via 'az aks install-cli' with sudo"
+          sudo az aks install-cli
+        else
+          echo "kubectl already installed: $(kubectl version --client --short || true)"
+        fi
+        if ! command -v helm >/dev/null 2>&1; then
+          echo "Helm not found. Installing Helm 3"
+          curl -fsSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
+        else
+          echo "Helm already installed: $(helm version --short || true)"
+        fi
+      displayName: 'Install kubectl and Helm'
+
+    - task: AzureCLI@2
+      displayName: Get kubeconfig
+      inputs:
+        azureSubscription: 'ContainerInsights_Build_Subscription_CI'
+        scriptLocation: 'inlineScript'
+        scriptType: 'bash'
+        inlineScript: 'az aks get-credentials -g ${{ parameters.clusterResourceGroup }} -n ${{ parameters.clusterName }}'
+
+    - script: |
+        echo "Install testkube CLI"
+        wget -qO - https://repo.testkube.io/key.pub | sudo apt-key add -
+        echo "deb https://repo.testkube.io/linux linux main" | sudo tee -a /etc/apt/sources.list
+        sudo apt-get update
+        sudo apt-get install -y testkube
+      displayName: 'Install Testkube CLI'
+
+    - bash: |
+        set -euo pipefail
+
+        # Remove stale CRDs that block Helm ownership
+        stale_crds=(
+            "testworkflowexecutions.testworkflows.testkube.io"
+            "testworkflows.testkube.io"
+            "testworkflows.testworkflows.testkube.io"
+            "testworkflowtemplates.testworkflows.testkube.io"
+        )
+        echo "Checking for stale Testkube CRDs"
+        for crd in "${stale_crds[@]}"; do
+            if kubectl get crd "$crd" >/dev/null 2>&1; then
+                owner=$(kubectl get crd "$crd" -o jsonpath='{.metadata.labels.app\.kubernetes\.io/managed-by}')
+                if [[ "$owner" != "Helm" ]]; then
+                    echo "Deleting CRD $crd with unmanaged owner: ${owner:-none}"
+                    kubectl delete crd "$crd" --wait=true || true
+                fi
+            fi
+        done
+
+        # Clean up existing TestKube installation if present
+        if helm list -n testkube 2>/dev/null | grep -q testkube; then
+            echo "Found existing Testkube installation. Cleaning up..."
+            helm uninstall testkube -n testkube || true
+            kubectl delete namespace testkube --wait=true --timeout=120s || true
+            sleep 30
+        fi
+
+        # Add Helm repo
+        helm repo add kubeshop https://kubeshop.github.io/helm-charts
+        helm repo update
+
+        # Pre-install CRDs from the chart so post-install hooks can create
+        # TestWorkflowTemplate resources. The operator is disabled in values
+        # (existing CI clusters already have CRDs from prior installs).
+        echo "Pre-installing TestKube CRDs from chart..."
+        helm template testkube kubeshop/testkube -n testkube \
+          -f ./helm-testkube-values.yaml \
+          --set testkube-operator.enabled=true \
+          --set testkube-operator.installCRD=true \
+          --show-only charts/testkube-operator/templates/crds.yaml \
+          | kubectl apply --server-side -f -
+
+        # Label/annotate CRDs so Helm adopts them as part of the "testkube" release
+        echo "Labeling CRDs for Helm ownership..."
+        for crd in $(kubectl get crds -o name | grep testkube); do
+          kubectl label "$crd" app.kubernetes.io/managed-by=Helm --overwrite
+          kubectl annotate "$crd" meta.helm.sh/release-name=testkube --overwrite
+          kubectl annotate "$crd" meta.helm.sh/release-namespace=testkube --overwrite
+        done
+
+        echo "Waiting for CRDs to be established..."
+        for crd in testworkflows.testworkflows.testkube.io testworkflowtemplates.testworkflows.testkube.io testworkflowexecutions.testworkflows.testkube.io; do
+          kubectl wait --for=condition=Established crd/"$crd" --timeout=60s || echo "Warning: CRD $crd not yet established"
+        done
+
+        # Install TestKube (operator stays DISABLED — CRDs already in place)
+        helm upgrade --install --create-namespace testkube kubeshop/testkube -n testkube \
+          -f ./helm-testkube-values.yaml
+
+        # Apply RBAC
+        kubectl apply -f ./api-server-permissions.yaml
+
+        echo "Waiting for TestKube API server to be ready..."
+        kubectl rollout status deployment/testkube-api-server -n testkube --timeout=300s
+        # Give the API server a moment to finish initialization after pod is ready
+        sleep 15
+      workingDirectory: $(Build.SourcesDirectory)/test/testkube
+      displayName: 'Install TestKube on cluster'
+
+    # Apply TestWorkflow CRs (includes countprocess and others)
+    - bash: |
+        kubectl apply -f ./testkube-test-crs.yaml
+        echo "Waiting for TestWorkflows to be registered..."
+        sleep 10
+      workingDirectory: $(Build.SourcesDirectory)/test/testkube
+      displayName: 'Apply TestWorkflow CRs'
+
+    # === Validate cases match matrix ===
+    - bash: |
+        set -euo pipefail
+
+        # Install yq if not present
+        if ! command -v yq &> /dev/null; then
+          curl -sL https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 -o /tmp/yq
+          chmod +x /tmp/yq
+          yq="/tmp/yq"
+        else
+          yq="yq"
+        fi
+
+        # Cases from pipeline parameter
+        echo "$PIPELINE_CASES" | tr ',' '\n' | sed 's/^ *//;s/ *$//' | sort > /tmp/pipeline.txt
+
+        # Cases from matrix YAML
+        $yq '.cases[].name' ./configmap-test-matrix.yaml | sort > /tmp/matrix.txt
+
+        echo "Pipeline cases:"
+        cat /tmp/pipeline.txt
+        echo ""
+        echo "Matrix cases:"
+        cat /tmp/matrix.txt
+        echo ""
+
+        if ! diff /tmp/pipeline.txt /tmp/matrix.txt; then
+          echo "##[error]Pipeline cases and matrix cases are out of sync!"
+          echo "Update the 'cases' parameter in azure-pipeline-config-tests.yaml to match configmap-test-matrix.yaml"
+          exit 1
+        fi
+
+        echo "Pipeline cases match matrix cases."
+      workingDirectory: $(Build.SourcesDirectory)/test/testkube
+      displayName: 'Validate cases match matrix'
+      env:
+        PIPELINE_CASES: ${{ join(',', parameters.cases) }}
+
+    # === Run test cases (one step per case) ===
+    - ${{ each caseName in parameters.cases }}:
+      - bash: |
+          chmod +x ./run-configmap-test-case.sh
+          ./run-configmap-test-case.sh \
+            --case "${{ caseName }}" \
+            --repo-root "$(Build.SourcesDirectory)"
+        workingDirectory: $(Build.SourcesDirectory)/test/testkube
+        displayName: "ConfigTest: ${{ caseName }}"
+        continueOnError: true
+        env:
+          AZURE_TENANT_ID: $(AZURE_TENANT_ID)
+          AZURE_CLIENT_ID: $(AZURE_CLIENT_ID)
+          GENEVA_INTEGRATION: false
+
+    # === Cleanup ===
+    - bash: |
+        echo "Restoring original configmap..."
+        kubectl apply -f $(Build.SourcesDirectory)/kubernetes/container-azm-ms-agentconfig.yaml || true
+
+        echo "Cleaning up Testkube installation..."
+        helm uninstall testkube -n testkube || true
+        kubectl delete namespace testkube --wait=true --timeout=120s || true
+        echo "Cleanup complete."
+      workingDirectory: $(Build.SourcesDirectory)/test/testkube
+      displayName: 'Cleanup'
+      condition: always()