delete kuberay-logging and kuberay-operator module

Change-Id: I2b8eda653bcf4b1d1cd402111e7bd79d18eaf1ac

applications/rag/main.tf

@@ -64,25 +64,25 @@ module "infra" {
   source = "../../infrastructure"
   count  = var.create_cluster ? 1 : 0
 
-  project_id         = var.project_id
-  cluster_name       = local.cluster_name
-  cluster_location   = var.cluster_location
-  region             = local.cluster_location_region
-  autopilot_cluster  = var.autopilot_cluster
-  private_cluster    = var.private_cluster
-  create_network     = var.create_network
-  network_name       = local.network_name
-  subnetwork_name    = local.network_name
-  subnetwork_cidr    = var.subnetwork_cidr
-  subnetwork_region  = local.cluster_location_region
-  cpu_pools          = var.cpu_pools
-  enable_gpu         = true
-  gpu_pools          = var.gpu_pools
-  ray_addon_enabled  = true
+  project_id        = var.project_id
+  cluster_name      = local.cluster_name
+  cluster_location  = var.cluster_location
+  region            = local.cluster_location_region
+  autopilot_cluster = var.autopilot_cluster
+  private_cluster   = var.private_cluster
+  create_network    = var.create_network
+  network_name      = local.network_name
+  subnetwork_name   = local.network_name
+  subnetwork_cidr   = var.subnetwork_cidr
+  subnetwork_region = local.cluster_location_region
+  cpu_pools         = var.cpu_pools
+  enable_gpu        = true
+  gpu_pools         = var.gpu_pools
+  ray_addon_enabled = true
   # TODO(genlu): remove channel and k8s_version after ray addon is in REGULAR channel
-  release_channel = "RAPID"
+  release_channel    = "RAPID"
   kubernetes_version = "1.30.3-gke.1969000"
-  depends_on      = [module.project-services]
+  depends_on         = [module.project-services]
 }
 
 data "google_container_cluster" "default" {

cloudbuild.yaml

@@ -100,10 +100,12 @@ steps:
         -auto-approve -no-color 
         echo "pass" > /workspace/user_result.txt
 
-        # Make sure pods are running
+        chmod +x /workspace/scripts/ci/wait_for_pods.sh
+        /workspace/scripts/ci/wait_for_pods.sh ml-$SHORT_SHA-$_BUILD_ID-ray 3000
+      
         kubectl wait --all pods -n ml-$SHORT_SHA-$_BUILD_ID-ray --for=condition=Ready --timeout=1200s
-        # Wait for pods to be stable
-        sleep 5s
+        # Ray head's readinessProbe is not probing the head service today. Therefore the wait for ready above is not reliable.
+        sleep 60s
         kubectl port-forward -n ml-$SHORT_SHA-$_BUILD_ID-ray service/ray-cluster-kuberay-head-svc 8265:8265 &
         # Wait port-forwarding to take its place
         sleep 10s

infrastructure/tfvars_tests/standard-gke-public.platform.tfvars

@@ -36,6 +36,10 @@ autopilot_cluster   = false # false = standard cluster, true = autopilot cluster
 cluster_name        = "test-cluster"
 cluster_location    = "us-east4"
 gcs_fuse_csi_driver = true
+ray_addon_enabled = true
+# TODO(genlu): remove release_channel and kubernetes_version after 1.30.3-gke.1969000 is in REGULAR channel
+release_channel    = "RAPID"
+kubernetes_version = "1.30.3-gke.1969000"
 
 cpu_pools = [{
   name         = "cpu-pool"