Merge pull request #3437 from mohitchaurasia91/release-branch

[Cherry Pick] Update README and related test setup for GKE managed parallelstore blueprint

examples/README.md

@@ -1518,6 +1518,30 @@ cleaned up when the job is deleted.
 
 [storage-gke.yaml]: ../examples/storage-gke.yaml
 
+### [gke-managed-parallelstore.yaml] ![core-badge] ![experimental-badge]
+
+This blueprint shows how to use managed parallelstore storage options with GKE in the toolkit.
+
+The blueprint contains the following:
+
+* A K8s Job that uses a managed parallelstore storage volume option.
+* A K8s Job that demonstrates ML training workload with managed parallelstore storage disk operation.
+
+> **Warning**: In this example blueprint, when storage type `Parallelstore` is specified in `gke-storage` module.
+> The lifecycle of the parallelstore is managed by the blueprint.
+> On glcuster destroy operation, the Parallelstore storage created will also be destroyed.
+>
+> [!Note]
+> The Kubernetes API server will only allow requests from authorized networks.
+> The `gke-cluster` module needs access to the Kubernetes API server
+> to create a Persistent Volume and a Persistent Volume Claim. **You must use
+> the `authorized_cidr` variable to supply an authorized network which contains
+> the IP address of the machine deploying the blueprint, for example
+> `--vars authorized_cidr=<your-ip-address>/32`.** You can use a service like
+> [whatismyip.com](https://whatismyip.com) to determine your IP address.
+
+[gke-managed-parallelstore.yaml]: ../examples/gke-managed-parallelstore.yaml
+
 ### [gke-a3-megagpu.yaml] ![core-badge] ![experimental-badge]
 
 This blueprint shows how to provision a GKE cluster with A3 Mega machines in the toolkit.

examples/gke-storage-parallelstore.yaml → examples/gke-managed-parallelstore.yaml

@@ -12,10 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 ---
-blueprint_name: gke-storage-parallelstore
+blueprint_name: gke-managed-parallelstore
 vars:
   project_id:  ## Set GCP Project ID Here ##
-  deployment_name: gke-storage-ps
+  deployment_name: gke-storage-managed-ps
   region: us-central1
   zone: us-central1-c
   # Cidr block containing the IP of the machine calling terraform.

modules/file-system/gke-storage/README.md

@@ -39,7 +39,7 @@ then use them in a `gke-job-template` to dynamically provision the resource.
 ```
 
 See example
-[gke-storage-parallelstore.yaml](../../../examples/README.md#gke-storage-parallelstoreyaml--) blueprint
+[gke-managed-parallelstore.yaml](../../../examples/README.md#gke-managed-parallelstoreyaml--) blueprint
 for a complete example.
 
 ### Authorized Network

tools/cloud-build/daily-tests/builds/gke-storage-parallelstore.yaml → tools/cloud-build/daily-tests/builds/gke-managed-parallelstore.yaml

@@ -27,7 +27,7 @@ timeout: 14400s  # 4hr
 
 steps:
 ## Test GKE
-- id: gke-storage-parallelstore
+- id: gke-managed-parallelstore
   name: us-central1-docker.pkg.dev/$PROJECT_ID/hpc-toolkit-repo/test-runner
   entrypoint: /bin/bash
   env:
@@ -40,7 +40,7 @@ steps:
     cd /workspace && make
     BUILD_ID_FULL=$BUILD_ID
     BUILD_ID_SHORT=$${BUILD_ID_FULL:0:6}
-    SG_EXAMPLE=examples/gke-storage-parallelstore.yaml
+    SG_EXAMPLE=examples/gke-managed-parallelstore.yaml
 
     # adding vm to act as remote node
     echo '  - id: remote-node'                     >> $${SG_EXAMPLE}
@@ -58,4 +58,4 @@ steps:
 
     ansible-playbook tools/cloud-build/daily-tests/ansible_playbooks/base-integration-test.yml \
       --user=sa_106486320838376751393 --extra-vars="project=${PROJECT_ID} build=$${BUILD_ID_SHORT}" \
-      --extra-vars="@tools/cloud-build/daily-tests/tests/gke-storage-parallelstore.yml"
+      --extra-vars="@tools/cloud-build/daily-tests/tests/gke-managed-parallelstore.yml"

tools/cloud-build/daily-tests/tests/gke-storage-parallelstore.yml → tools/cloud-build/daily-tests/tests/gke-managed-parallelstore.yml

@@ -12,16 +12,16 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 ---
-test_name: gke-storage-parallelstore
-deployment_name: gke-storage-parallelstore-{{ build }}
+test_name: gke-managed-parallelstore
+deployment_name: gke-managed-parallelstore-{{ build }}
 zone: us-central1-a  # for remote node
 region: us-central1
 workspace: /workspace
-blueprint_yaml: "{{ workspace }}/examples/gke-storage-parallelstore.yaml"
+blueprint_yaml: "{{ workspace }}/examples/gke-managed-parallelstore.yaml"
 network: "{{ deployment_name }}-net"
 remote_node: "{{ deployment_name }}-0"
 post_deploy_tests:
-- test-validation/test-gke-storage-parallelstore.yml
+- test-validation/test-gke-managed-parallelstore.yml
 custom_vars:
   project: "{{ project }}"
 cli_deployment_vars: