Migrate long-running test to new cluster to enable monitoring (#7357)

.github/scripts/cleanup-cluster.sh

@@ -21,22 +21,26 @@ set -e
 echo "cleaning up cluster"
 
 # Delete all test resources in queuemessages.
-echo "delete all resources in queuemessages.ucp.dev"
-kubectl delete queuemessages.ucp.dev -n radius-system --all
+if kubectl get crd queuemessages.ucp.dev > /dev/null 2>&1; then
+    echo "delete all resources in queuemessages.ucp.dev"
+    kubectl delete queuemessages.ucp.dev -n radius-system --all
+fi
 
 # Testing deletion of deployment.apps.
 
 # Delete all test resources in resources without proxy resource.
-echo "delete all resources in resources.ucp.dev"
-resources=$(kubectl get resources.ucp.dev -n radius-system --no-headers -o custom-columns=":metadata.name")
-for r in $resources; do
-    if [[ $r == scope.local.* || $r == scope.aws.* || -z "$r" ]]; then
-        echo "skip deletion: $r"
-    else
-        echo "delete resource: $r"
-        kubectl delete resources.ucp.dev $r -n radius-system --ignore-not-found=true
-    fi
-done
+if kubectl get crd resources.ucp.dev > /dev/null 2>&1; then
+    echo "delete all resources in resources.ucp.dev"
+    resources=$(kubectl get resources.ucp.dev -n radius-system --no-headers -o custom-columns=":metadata.name")
+    for r in $resources; do
+        if [[ $r == scope.local.* || $r == scope.aws.* || -z "$r" ]]; then
+            echo "skip deletion: $r"
+        else
+            echo "delete resource: $r"
+            kubectl delete resources.ucp.dev $r -n radius-system --ignore-not-found=true
+        fi
+    done
+fi
 
 # Delete all test namespaces.
 echo "delete all test namespaces"

.github/workflows/long-running-azure.yaml

@@ -34,7 +34,7 @@
 # the previous build is still valid. If valid, the workflow skips the build steps
 # and uses the cached 'rad cli' for testing.
 #
-# Grafana dashboard URL: https://radiuse2e00-dashboard-audycmffgberbghy.wus3.grafana.azure.com/
+# Grafana dashboard URL:  https://radlrtest00-dashboard-e4ffc0cwggchdhba.wus3.grafana.azure.com 
 
 name: Long-running test on Azure
 
@@ -44,6 +44,8 @@ permissions:
   packages: write # Required for uploading the package
 
 on:
+  # Enable manual trigger to deploy the latest changes from main.
+  workflow_dispatch:
   schedule:
     # Run every 2 hours
     - cron: "0 */2 * * *"
@@ -82,9 +84,9 @@ env:
   VALID_RADIUS_BUILD_WINDOW: 86400
 
   # The AKS cluster name
-  AKS_CLUSTER_NAME: "radiuse2e00-aks"
+  AKS_CLUSTER_NAME: "radlrtest00-aks"
   # The resource group for AKS_CLUSTER_NAME resource.
-  AKS_RESOURCE_GROUP: "radiuse2e00"
+  AKS_RESOURCE_GROUP: "radlrtest00"
 
   # Server where terraform test modules are deployed
   TF_RECIPE_MODULE_SERVER_URL: "http://tf-module-server.radius-test-tf-module-server.svc.cluster.local"
@@ -115,7 +117,7 @@ jobs:
           path: ./dist/cache
           key: radius-test-latest-
       - name: Skip build if build is still valid
-        if: github.event_name != 'pull_request'
+        if: github.event_name != 'pull_request' && github.event_name != 'workflow_dispatch'
         id: skip-build
         run: |
           # check if the last build time to see if we need to build again
@@ -499,7 +501,7 @@ jobs:
     name: Report test failure
     needs: [build, tests]
     runs-on: ubuntu-latest
-    if: failure() && github.repository == 'radius-project/radius'
+    if: failure() && github.repository == 'radius-project/radius' && github.event_name == 'schedule'
     steps:
       - name: Create failure issue for failing long running test run
         uses: actions/github-script@v6

test/infra/azure/bicepconfig.json

@@ -1,5 +1,5 @@
 {
-    "experimentalFeaturesEnabled": {
-      "extensibility": true
-    }
-  }
+  "experimentalFeaturesEnabled": {
+    "extensibility": true
+  }
+}

test/infra/azure/main.bicep

@@ -90,7 +90,7 @@ module aksCluster './modules/akscluster.bicep' = {
   params: {
     name: aksClusterName
     location: location
-    kubernetesVersion: '1.28.3'
+    kubernetesVersion: '1.28.5'
     logAnalyticsWorkspaceId: logAnalyticsWorkspace.outputs.id
     systemAgentPoolName: 'agentpool'
     systemAgentPoolVmSize: 'Standard_D4as_v5'

test/infra/azure/modules/akscluster.bicep

@@ -307,9 +307,6 @@ param autoScalerProfileMaxGracefulTerminationSec string = '600'
 @description('Specifies the resource id of the Log Analytics workspace.')
 param logAnalyticsWorkspaceId string
 
-@description('Specifies the workspace data retention in days.')
-param retentionInDays int = 30
-
 @description('Specifies the location.')
 param location string = resourceGroup().location
 
@@ -340,42 +337,8 @@ param imageCleanerIntervalHours int = 24
 @description('Specifies whether to enable Workload Identity. The default value is false.')
 param workloadIdentityEnabled bool = false
 
-// Variables
-var diagnosticSettingsName = 'diagnosticSettings'
-var logCategories = [
-  'kube-apiserver'
-  'kube-audit'
-  'kube-audit-admin'
-  'kube-controller-manager'
-  'kube-scheduler'
-  'cluster-autoscaler'
-  'cloud-controller-manager'
-  'guard'
-  'csi-azuredisk-controller'
-  'csi-azurefile-controller'
-  'csi-snapshot-controller'
-]
-var metricCategories = [
-  'AllMetrics'
-]
-var logs = [for category in logCategories: {
-  category: category
-  enabled: true
-  retentionPolicy: {
-    enabled: true
-    days: retentionInDays
-  }
-}]
-var metrics = [for category in metricCategories: {
-  category: category
-  enabled: true
-  retentionPolicy: {
-    enabled: true
-    days: retentionInDays
-  }
-}]
 
-resource aksCluster 'Microsoft.ContainerService/managedClusters@2023-05-01' = {
+resource aksCluster 'Microsoft.ContainerService/managedClusters@2023-10-01' = {
   name: name
   location: location
   tags: tags
@@ -515,7 +478,7 @@ resource aksCluster 'Microsoft.ContainerService/managedClusters@2023-05-01' = {
 }
 
 // Dapr Extension
-resource daprExtension 'Microsoft.KubernetesConfiguration/extensions@2022-04-02-preview' = if (daprEnabled) {
+resource daprExtension 'Microsoft.KubernetesConfiguration/extensions@2022-07-01' = if (daprEnabled) {
   name: 'dapr'
   scope: aksCluster
   properties: {
@@ -534,17 +497,6 @@ resource daprExtension 'Microsoft.KubernetesConfiguration/extensions@2022-04-02-
   }
 }
 
-// Diagnostic Settings
-resource diagnosticSettings 'Microsoft.Insights/diagnosticSettings@2021-05-01-preview' = {
-  name: diagnosticSettingsName
-  scope: aksCluster
-  properties: {
-    workspaceId: logAnalyticsWorkspaceId
-    logs: logs
-    metrics: metrics
-  }
-}
-
 // Output
 output id string = aksCluster.id
 output name string = aksCluster.name