Fix project service dependency (#497)

* fix project service dependency * fix project service dependency
GoogleCloudPlatform · Apr 15, 2024 · 9296daa · 9296daa
1 parent 92394d3
commit 9296daa
Show file tree

Hide file tree

Showing 6 changed files with 24 additions and 13 deletions.
diff --git a/applications/jupyter/main.tf b/applications/jupyter/main.tf
@@ -69,12 +69,14 @@ module "infra" {
   subnetwork_name   = "default"
   cpu_pools         = var.cpu_pools
   enable_gpu        = false
+  depends_on        = [module.project-services]
 }
 
 data "google_container_cluster" "default" {
-  count    = var.create_cluster ? 0 : 1
-  name     = var.cluster_name
-  location = var.cluster_location
+  count      = var.create_cluster ? 0 : 1
+  name       = var.cluster_name
+  location   = var.cluster_location
+  depends_on = [module.project-services]
 }
 
 locals {

diff --git a/applications/rag/main.tf b/applications/rag/main.tf
@@ -79,12 +79,14 @@ module "infra" {
   enable_gpu         = true
   gpu_pools          = var.gpu_pools
   kubernetes_version = var.kubernetes_version
+  depends_on         = [module.project-services]
 }
 
 data "google_container_cluster" "default" {
-  count    = var.create_cluster ? 0 : 1
-  name     = var.cluster_name
-  location = var.cluster_location
+  count      = var.create_cluster ? 0 : 1
+  name       = var.cluster_name
+  location   = var.cluster_location
+  depends_on = [module.project-services]
 }
 
 locals {

diff --git a/applications/ray/main.tf b/applications/ray/main.tf
@@ -73,12 +73,14 @@ module "infra" {
   cpu_pools         = var.cpu_pools
   enable_gpu        = var.enable_gpu
   gpu_pools         = var.gpu_pools
+  depends_on        = [module.project-services]
 }
 
 data "google_container_cluster" "default" {
-  count    = var.create_cluster ? 0 : 1
-  name     = var.cluster_name
-  location = var.cluster_location
+  count      = var.create_cluster ? 0 : 1
+  name       = var.cluster_name
+  location   = var.cluster_location
+  depends_on = [module.project-services]
 }
 
 locals {

diff --git a/cloudbuild.yaml b/cloudbuild.yaml
@@ -59,6 +59,8 @@ steps:
         terraform apply \
         -var-file=tfvars_tests/standard-gke-public.platform.tfvars \
         -var=project_id=$PROJECT_ID \
+        -var=network_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
+        -var=subnetwork_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-$_AUTOPILOT_CLUSTER  \
         -var=cluster_name=ml-$SHORT_SHA-$_PR_NUMBER-$_BUILD_ID-cluster \
         -var=autopilot_cluster=$_AUTOPILOT_CLUSTER \
         -var=cluster_location=$_REGION \
@@ -202,7 +204,7 @@ steps:
         cd /workspace/applications/rag/
         terraform apply \
         -var-file=workloads.tfvars \
-        -var=network_name=default \
+        -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 \
@@ -261,7 +263,7 @@ steps:
         cd /workspace/applications/rag/
         terraform destroy \
         -var-file=workloads.tfvars \
-        -var=network_name=default \
+        -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 \
@@ -289,6 +291,8 @@ steps:
         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
 

diff --git a/infrastructure/tfvars_tests/standard-gke-public.platform.tfvars b/infrastructure/tfvars_tests/standard-gke-public.platform.tfvars
@@ -25,7 +25,7 @@ project_id = "<project-id>"
 # subnetwork_cidr   = "10.100.0.0/16"
 # subnetwork_region = "us-central1"
 
-create_network    = false
+create_network    = true
 network_name      = "default"
 subnetwork_name   = "default"
 subnetwork_region = "us-central1"

diff --git a/modules/kuberay-monitoring/main.tf b/modules/kuberay-monitoring/main.tf
@@ -14,7 +14,8 @@
 
 # Temporary workaround to ensure the GMP webhook is installed before applying PodMonitorings.
 resource "time_sleep" "wait_for_gmp_operator" {
-  count           = var.autopilot_cluster ? 1 : 0
+  ## Temporary workaroud, This is impacting for the standard cluster dependency graph
+  #count           = var.autopilot_cluster ? 1 : 0
   create_duration = "30s"
 }