delete kuberay-logging and kuberay-operator module

Change-Id: If63c090e99186df2fb5ed27c37d187cd75cbf663

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

@@ -29,22 +29,6 @@ steps:
     dir: 'applications/ray/'
     waitFor: ['validate platform']
 
-  - id: 'validate jupyterhub'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    script: |
-      terraform init -no-color
-      terraform validate -no-color
-    dir: 'applications/jupyter/'
-    waitFor: ['validate platform']
-
-  - id: 'validate rag'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    script: |
-      terraform init -no-color
-      terraform validate -no-color
-    dir: 'applications/rag/'
-    waitFor: ['validate platform']
-
   # Create cluster to test ray, jupyterhub, rag
   - id: 'create gke cluster'
     name: 'gcr.io/$PROJECT_ID/terraform'
@@ -71,7 +55,7 @@ steps:
         echo "pass" > /workspace/gke_cluster_result.txt
     dir: 'infrastructure/'
     allowFailure: true
-    waitFor: ['validate platform', 'validate ray', 'validate jupyterhub', validate rag]
+    waitFor: ['validate platform', 'validate ray']
 
   - id: 'test ray cluster'
     name: 'gcr.io/$PROJECT_ID/terraform'
@@ -114,216 +98,6 @@ steps:
     allowFailure: true
     waitFor: ['create gke cluster']
 
-  - id: 'cleanup ray cluster'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'bash'
-    args:
-      - '-c'
-      - |
-        set -e
-
-        cd /workspace/applications/ray/
-        terraform destroy \
-        -var-file=workloads.tfvars \
-        -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=cluster_location=$_REGION \
-        -var=kubernetes_namespace=ml-$SHORT_SHA-$_BUILD_ID-ray \
-        -var=workload_identity_service_account=ray-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=gcs_bucket=gke-aieco-ray-$SHORT_SHA-$_BUILD_ID \
-        -var=enable_gpu=true \
-        -auto-approve -no-color
-    allowFailure: true
-    waitFor: ['test ray cluster']
-
-  - id: 'test jupyterhub'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'bash'
-    args:
-      - '-c'
-      - |
-        set -e
-
-        cd /workspace/modules/jupyter/tests
-        python3 change_jupyter_config.py $_AUTOPILOT_CLUSTER
-
-        cd /workspace/applications/jupyter
-        terraform apply \
-        -var-file=workloads-without-iap.example.tfvars \
-        -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=cluster_location=$_REGION \
-        -var=kubernetes_namespace=ml-$SHORT_SHA-$_BUILD_ID-jupyter \
-        -var=workload_identity_service_account=jupyter-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=gcs_bucket=gke-aieco-jupyter-$SHORT_SHA-$_BUILD_ID \
-        -auto-approve -no-color 
-        echo "pass" > /workspace/jupyterhub_tf_result.txt
-
-        kubectl wait --for=condition=Ready pods -n ml-$SHORT_SHA-$_BUILD_ID-jupyter -l 'component!=continuous-image-puller' --timeout=1800s
-        kubectl get services -n ml-$SHORT_SHA-$_BUILD_ID-jupyter
-        kubectl port-forward -n ml-$SHORT_SHA-$_BUILD_ID-jupyter service/proxy-public 9442:80 &
-        # Wait port-forwarding to take its place
-        sleep 5s
-
-        cd /workspace/modules/jupyter/tests
-        python3 test_hub.py "127.0.0.1:9442" $_AUTOPILOT_CLUSTER
-        echo "pass" > /workspace/jupyterhub_test_result.txt
-    allowFailure: true
-    waitFor: ['create gke cluster']
-
-  - id: 'cleanup jupyterhub'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'bash'
-    args:
-      - '-c'
-      - |
-        set -e
-
-        cd /workspace/applications/jupyter/
-        terraform destroy \
-        -var-file=workloads-without-iap.example.tfvars \
-        -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=cluster_location=$_REGION \
-        -var=kubernetes_namespace=ml-$SHORT_SHA-$_BUILD_ID-jupyter \
-        -var=workload_identity_service_account=jupyter-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=gcs_bucket=gke-aieco-jupyter-$SHORT_SHA-$_BUILD_ID \
-        -auto-approve -no-color
-    allowFailure: true
-    waitFor: ['test jupyterhub']
-
-  - id: 'test rag'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'sh'
-    secretEnv: ['KAGGLE_USERNAME', 'KAGGLE_KEY']
-    args:
-      - '-c'
-      - |
-        set -e
-
-        # Get kube config
-        gcloud container clusters get-credentials \
-        ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        --location $_REGION \
-        --project $PROJECT_ID
-
-        cd /workspace/modules/jupyter/tests
-        python3 change_jupyter_config.py $_AUTOPILOT_CLUSTER
-
-        cd /workspace/applications/rag/
-        terraform apply \
-        -var-file=workloads.tfvars \
-        -var=network_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
-        -var=create_cluster=false \
-        -var=jupyter_add_auth=false \
-        -var=frontend_add_auth=false \
-        -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=cluster_location=$_REGION \
-        -var=kubernetes_namespace=rag-$SHORT_SHA-$_BUILD_ID \
-        -var=gcs_bucket=gke-aieco-rag-$SHORT_SHA-$_BUILD_ID \
-        -var=ray_service_account=ray-sa-4-rag-$SHORT_SHA-$_BUILD_ID \
-        -var=rag_service_account=rag-sa-4-rag-$SHORT_SHA-$_BUILD_ID \
-        -var=jupyter_service_account=jupyter-sa-4-rag-$SHORT_SHA-$_BUILD_ID \
-        -var=cloudsql_instance=pgvector-instance-$SHORT_SHA-$_BUILD_ID \
-        -auto-approve -no-color 
-        echo "pass" > /workspace/rag_tf_result.txt
-
-        # Validate Ray: Make sure pods are running
-        kubectl wait --for=condition=Ready pods -n rag-$SHORT_SHA-$_BUILD_ID -l 'component!=continuous-image-puller' --timeout=1200s
-        kubectl port-forward -n rag-$SHORT_SHA-$_BUILD_ID service/ray-cluster-kuberay-head-svc 8262:8265 &
-        # Wait port-forwarding to take its place
-        sleep 5s
-
-        # Validate Ray: Check dashboard
-        ray job submit --working-dir ./tests \
-        --address=http://127.0.0.1:8262 -- python -c "import ray; ray.init(); print(ray.cluster_resources())"
-        echo "pass" > /workspace/rag_ray_dashboard_result.txt
-
-        # Validate JupyterHub: Get hub url
-        kubectl get services -n rag-$SHORT_SHA-$_BUILD_ID
-        kubectl port-forward -n rag-$SHORT_SHA-$_BUILD_ID service/proxy-public 9443:80 &
-        # Wait port-forwarding to take its place
-        sleep 5s
-
-        # Validate JupyterHub: Test Hub
-        cd /workspace/modules/jupyter/tests
-        python3 test_hub.py "127.0.0.1:9443" $_AUTOPILOT_CLUSTER
-        echo "pass" > /workspace/rag_jupyterhub_test_result.txt
-
-        # Validate RAG: Test rag frontend
-        kubectl port-forward -n rag-$SHORT_SHA-$_BUILD_ID service/rag-frontend 8081:8080 &
-        # Wait port-forwarding to take its place
-        sleep 5s
-
-        cd /workspace/applications/rag/tests
-        python3 test_frontend.py "127.0.0.1:8081"
-        echo "pass" > /workspace/rag_frontend_result.txt
-
-        cd /workspace/
-        sed -i "s/<username>/$$KAGGLE_USERNAME/g" ./applications/rag/example_notebooks/rag-kaggle-ray-sql-interactive.ipynb
-        sed -i "s/<token>/$$KAGGLE_KEY/g" ./applications/rag/example_notebooks/rag-kaggle-ray-sql-interactive.ipynb
-        gsutil cp ./applications/rag/example_notebooks/rag-kaggle-ray-sql-interactive.ipynb gs://gke-aieco-rag-$SHORT_SHA-$_BUILD_ID/
-        kubectl exec -it -n rag-$SHORT_SHA-$_BUILD_ID $(kubectl get pod -l app=jupyterhub,component=hub -n rag-$SHORT_SHA-$_BUILD_ID -o jsonpath="{.items[0].metadata.name}") -- jupyterhub token admin --log-level=CRITICAL | xargs python3 ./applications/rag/notebook_starter.py
-        # Wait for jupyterhub to trigger notebook pod startup
-        sleep 5s
-        kubectl wait --for=condition=Ready pod/jupyter-admin -n rag-$SHORT_SHA-$_BUILD_ID --timeout=500s
-        kubectl exec -it -n rag-$SHORT_SHA-$_BUILD_ID jupyter-admin -c notebook -- jupyter nbconvert --to script /data/rag-kaggle-ray-sql-interactive.ipynb
-        kubectl exec -it -n rag-$SHORT_SHA-$_BUILD_ID jupyter-admin -c notebook -- ipython /data/rag-kaggle-ray-sql-interactive.py
-
-        python3 ./applications/rag/tests/test_rag.py "http://127.0.0.1:8081/prompt"
-        echo "pass" > /workspace/rag_prompt_result.txt
-
-    allowFailure: true
-    waitFor: ['create gke cluster']
-
-  - id: 'cleanup rag'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'bash'
-    args:
-      - '-c'
-      - |
-        set -e
-
-        cd /workspace/applications/rag/
-        terraform destroy \
-        -var-file=workloads.tfvars \
-        -var=network_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
-        -var=create_cluster=false \
-        -var=jupyter_add_auth=false \
-        -var=frontend_add_auth=false \
-        -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=cluster_location=$_REGION \
-        -var=kubernetes_namespace=rag-$SHORT_SHA-$_BUILD_ID \
-        -var=gcs_bucket=gke-aieco-rag-$SHORT_SHA-$_BUILD_ID \
-        -var=ray_service_account=ray-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=rag_service_account=rag-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=jupyter_service_account=jupyter-sa-$SHORT_SHA-$_BUILD_ID \
-        -var=cloudsql_instance=pgvector-instance-$SHORT_SHA-$_BUILD_ID \
-        -auto-approve -no-color
-    allowFailure: true
-    waitFor: ['test rag']
-
-  - id: 'cleanup gke cluster'
-    name: 'gcr.io/$PROJECT_ID/terraform'
-    entrypoint: 'bash'
-    args:
-      - '-c'
-      - |
-        set -e
-
-        cd /workspace/infrastructure
-        terraform destroy -var-file=tfvars_tests/standard-gke-public.platform.tfvars -var=project_id=$PROJECT_ID \
-        -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
-        -var=network_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
-        -var=subnetwork_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
-        -var=autopilot_cluster=$_AUTOPILOT_CLUSTER \
-        -var=cluster_location=$_REGION -auto-approve -no-color
-
-    allowFailure: true
-    waitFor: ['cleanup rag', 'cleanup jupyterhub', 'cleanup ray cluster']
-
   - id: 'check result'
     name: 'gcr.io/$PROJECT_ID/terraform'
     entrypoint: 'bash'
@@ -345,41 +119,7 @@ steps:
           exit 1
         fi
 
-        if [[ $(cat /workspace/jupyterhub_tf_result.txt) != "pass" ]]; then
-          echo "jupyterhub tf failed"
-          exit 1
-        fi
-
-        if [[ $(cat /workspace/jupyterhub_test_result.txt) != "pass" ]]; then
-          echo "jupyterhub test failed"
-          exit 1
-        fi
-
-        if [[ $(cat /workspace/rag_tf_result.txt) != "pass" ]]; then
-          echo "rag tf failed"
-          exit 1
-        fi
-
-        if [[ $(cat /workspace/rag_ray_dashboard_result.txt) != "pass" ]]; then
-          echo "rag ray dashboard test failed"
-          exit 1
-        fi
-        
-        if [[ $(cat /workspace/rag_jupyterhub_test_result.txt) != "pass" ]]; then
-          echo "rag jupyterhub test failed"
-          exit 1
-        fi
-
-        if [[ $(cat /workspace/rag_frontend_result.txt) != "pass" ]]; then
-          echo "rag frontend test failed"
-          exit 1
-        fi
-
-        if [[ $(cat /workspace/rag_prompt_result.txt) != "pass" ]]; then
-          echo "rag prompt test failed"
-          exit 1
-        fi
-    waitFor: ['cleanup gke cluster']
+    waitFor: ['test ray cluster']
 
 substitutions:
   _REGION: us-east4
@@ -389,11 +129,4 @@ substitutions:
 options:
   substitutionOption: 'ALLOW_LOOSE'
   machineType: 'E2_HIGHCPU_8'
-timeout: 5400s
-
-availableSecrets:
-  secretManager:
-  - versionName: projects/gke-ai-eco-dev/secrets/cloudbuild-kaggle-username/versions/latest
-    env: 'KAGGLE_USERNAME'
-  - versionName: projects/gke-ai-eco-dev/secrets/cloudbuild-kaggle-key/versions/latest
-    env: 'KAGGLE_KEY'
+timeout: 5400s