Merge pull request #33572 from Jont828/capz-pr-100-nodes

Add CAPZ PR job to run 100 node azure custom k8s build test

Author: k8s-ci-robot

config/jobs/kubernetes-sigs/cluster-api-provider-azure/cluster-api-provider-azure-presubmits-main.yaml

@@ -748,3 +748,108 @@ presubmits:
     annotations:
       testgrid-dashboards: sig-cluster-lifecycle-cluster-api-provider-azure
       testgrid-tab-name: capz-pr-windows-containerd-upstream-custom-k8s-main
+  - name: pull-cluster-api-provider-azure-load-test-custom-builds
+    cluster: eks-prow-build-cluster
+    decorate: true
+    decoration_config:
+      timeout: 8h
+    path_alias: "sigs.k8s.io/cluster-api-provider-azure"
+    always_run: false
+    optional: true
+    run_if_changed: 'test\/e2e\/conformance_test.go|templates\/test|^scripts\/|conformance.mk'
+    labels:
+      preset-dind-enabled: "true"
+      preset-kind-volume-mounts: "true"
+      preset-azure-community: "true"
+    branches:
+    - ^main$
+    extra_refs:
+    - org: kubernetes
+      repo: kubernetes
+      base_ref: master
+      path_alias: k8s.io/kubernetes
+    - org: kubernetes
+      repo: perf-tests
+      base_ref: "master"
+      path_alias: "k8s.io/perf-tests"
+    spec:
+      serviceAccountName: azure
+      containers:
+      - image: gcr.io/k8s-staging-test-infra/kubekins-e2e:v20240803-cf1183f2db-master
+        command:
+        - runner.sh
+        - ./scripts/ci-entrypoint.sh
+        args:
+        - bash
+        - -c
+        - >-
+          cd ${GOPATH}/src/k8s.io/perf-tests/ &&
+          ./run-e2e.sh cluster-loader2
+          --nodes=100 \
+          --prometheus-scrape-kubelets=true \
+          --prometheus-scrape-node-exporter \
+          --provider=aks \
+          --testconfig=testing/load/config.yaml \
+          --testconfig=testing/huge-service/config.yaml \
+          --testconfig=testing/access-tokens/config.yaml \
+          --testoverrides=./testing/experiments/enable_restart_count_check.yaml \
+          --testoverrides=./testing/experiments/use_simple_latency_query.yaml \
+          --testoverrides=./testing/overrides/load_throughput.yaml \
+          --v=2
+        securityContext:
+          privileged: true
+        env:
+          # CAPZ variables
+        - name: TEST_K8S
+          value: "true"
+        - name: CLUSTER_TEMPLATE
+          value: "templates/test/ci/cluster-template-prow-load.yaml"
+        - name: NODE_MACHINE_TYPE
+          value: "Standard_D8s_v3"
+        - name: TEST_WINDOWS
+          value: "false"
+        - name: "CONTROL_PLANE_MACHINE_COUNT"
+          value: "3"
+        - name: WINDOWS_WORKER_MACHINE_COUNT
+          value: "0" # Don't create windows workers
+        - name: WORKER_MACHINE_COUNT
+          value: "100"
+        # clusterloader2 variables
+        - name: ENABLE_PROMETHEUS_SERVER
+          value: "true"
+        - name: PROMETHEUS_SCRAPE_APISERVER_ONLY
+          value: "true"
+        - name: PROMETHEUS_APISERVER_SCRAPE_PORT
+          value: "6443"
+        - name: PROMETHEUS_SCRAPE_WINDOWS_NODE_EXPORTER
+          value: "true"
+        - name: CL2_PROMETHEUS_TOLERATE_MASTER
+          value: "true"
+        # from google cl2
+        - name: CL2_ENABLE_DNS_PROGRAMMING
+          value: "true"
+        - name: CL2_SCHEDULER_THROUGHPUT_THRESHOLD
+          value: "0"
+        - name: CL2_ENABLE_API_AVAILABILITY_MEASUREMENT
+          value: "true"
+        - name: CL2_API_AVAILABILITY_PERCENTAGE_THRESHOLD
+          value: "99.5"
+        # azuredisk variables - required for Prometheus PVC
+        - name: DEPLOY_AZURE_CSI_DRIVER
+          value: "true"
+        - name: AZUREDISK_CSI_DRIVER_VERSION
+          value: "master"
+        - name: PROMETHEUS_STORAGE_CLASS_PROVISIONER
+          value: "kubernetes.io/azure-disk"
+        - name: PROMETHEUS_STORAGE_CLASS_VOLUME_TYPE
+          value: "StandardSSD_LRS"
+        resources:
+          requests:
+            cpu: "4"
+            memory: "9Gi"
+          limits:
+            cpu: "4"
+            memory: "9Gi"
+    annotations:
+      testgrid-dashboards: sig-cluster-lifecycle-cluster-api-provider-azure
+      testgrid-tab-name: capz-pr-scalability-100-node-k8s-main