Move examples/hpc-slurm to V6 (#2097)

pick f88a30f Unify usage and rendering of `HintError`

* Move `examples/hpc-slurm` to V6;
* Updated `examples/README`;
* Remove `slurm-v5-hpc-centos7` test.

community/modules/scheduler/schedmd-slurm-gcp-v5-login/README.md

@@ -28,9 +28,6 @@ This creates a Slurm login node which is:
   `use`
 * of VM machine type `n2-standard-4`
 
-For a complete example using this module, see
-[hpc-slurm.yaml](../../../../examples/hpc-slurm.yaml).
-
 ## Custom Images
 
 For more information on creating valid custom images for the login node VM

examples/README.md

@@ -13,7 +13,6 @@ md_toc github examples/README.md | sed -e "s/\s-\s/ * /"
 * [Blueprint Descriptions](#blueprint-descriptions)
   * [hpc-slurm.yaml](#hpc-slurmyaml-) ![core-badge]
   * [hpc-enterprise-slurm.yaml](#hpc-enterprise-slurmyaml-) ![core-badge]
-  * [hpc-slurm6.yaml](#hpc-slurm6yaml--) ![community-badge] ![experimental-badge]
   * [hpc-slurm6-tpu.yaml](#hpc-slurm6-tpuyaml--) ![community-badge] ![experimental-badge]
   * [ml-slurm.yaml](#ml-slurmyaml-) ![core-badge]
   * [image-builder.yaml](#image-builderyaml-) ![core-badge]
@@ -118,13 +117,11 @@ the experimental badge (![experimental-badge]).
 
 ### [hpc-slurm.yaml] ![core-badge]
 
-> **Warning**: The variables `enable_reconfigure`,
-> `enable_cleanup_compute`, and `enable_cleanup_subscriptions`, if set to
-> `true`, require additional dependencies **to be installed on the system deploying the infrastructure**.
+> **Warning**: Requires additional dependencies **to be installed on the system deploying the infrastructure**.
 >
 > ```shell
 > # Install Python3 and run
-> pip3 install -r https://raw.githubusercontent.com/SchedMD/slurm-gcp/5.9.1/scripts/requirements.txt
+> pip3 install -r https://raw.githubusercontent.com/GoogleCloudPlatform/slurm-gcp/6.2.1/scripts/requirements.txt
 > ```
 
 Creates a basic auto-scaling Slurm cluster with mostly default settings. The
@@ -265,35 +262,6 @@ to 256
 
 [hpc-enterprise-slurm.yaml]: ./hpc-enterprise-slurm.yaml
 
-### [hpc-slurm6.yaml] ![community-badge] ![experimental-badge]
-
-> **Warning**: Requires additional dependencies **to be installed on the system deploying the infrastructure**.
->
-> ```shell
-> # Install Python3 and run
-> pip3 install -r https://raw.githubusercontent.com/GoogleCloudPlatform/slurm-gcp/6.2.1/scripts/requirements.txt
-> ```
-
-Creates a basic auto-scaling Slurm cluster with mostly default settings. The
-blueprint also creates a new VPC network, and a filestore instance mounted to
-`/home`.
-
-There are 2 partitions in this example: `debug`, and `compute`. The `debug`
-partition uses `n2-standard-2` VMs, which should work out of the box without
-needing to request additional quota. The purpose of the `debug` partition is to
-make sure that first time users are not immediately blocked by quota
-limitations.
-
-[hpc-slurm6.yaml]: ../community/examples/hpc-slurm6.yaml
-
-#### Compute Partition
-
-There is a `compute` partition that achieves higher performance. Any
-performance analysis should be done on the `compute` partition. By default it
-uses `c2-standard-60` VMs with placement groups enabled. You may need to request
-additional quota for `C2 CPUs` in the region you are deploying in. You can
-select the compute partition using the `-p compute` argument when running `srun`.
-
 ### [hpc-slurm6-tpu.yaml] ![community-badge] ![experimental-badge]
 
 > **Warning**: Requires additional dependencies **to be installed on the system deploying the infrastructure**.

examples/hpc-slurm.yaml

@@ -18,7 +18,7 @@ blueprint_name: hpc-slurm
 
 vars:
   project_id:  ## Set GCP Project ID Here ##
-  deployment_name: hpc-small
+  deployment_name: hpc-slurm
   region: us-central1
   zone: us-central1-a
 
@@ -28,53 +28,54 @@ vars:
 deployment_groups:
 - group: primary
   modules:
-  # Source is an embedded resource, denoted by "resources/*" without ./, ../, /
-  # as a prefix. To refer to a local resource, prefix with ./, ../ or /
-  # Example - ./resources/network/vpc
-  - id: network1
+  # Source is an embedded module, denoted by "modules/*" without ./, ../, /
+  # as a prefix. To refer to a local module, prefix with ./, ../ or /
+  # Example - ./modules/network/vpc
+  - id: network
     source: modules/network/vpc
 
   - id: homefs
     source: modules/file-system/filestore
-    use: [network1]
+    use: [network]
     settings:
       local_mount: /home
 
-  - id: debug_node_group
-    source: community/modules/compute/schedmd-slurm-gcp-v5-node-group
+  - id: debug_nodeset
+    source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
+    use: [network]
     settings:
       node_count_dynamic_max: 4
       machine_type: n2-standard-2
+      enable_placement: false # the default is: true
 
   - id: debug_partition
-    source: community/modules/compute/schedmd-slurm-gcp-v5-partition
+    source: community/modules/compute/schedmd-slurm-gcp-v6-partition
     use:
-    - network1
     - homefs
-    - debug_node_group
+    - debug_nodeset
     settings:
       partition_name: debug
       exclusive: false # allows nodes to stay up after jobs are done
-      enable_placement: false # the default is: true
       is_default: true
 
-  - id: compute_node_group
-    source: community/modules/compute/schedmd-slurm-gcp-v5-node-group
+  - id: compute_nodeset
+    source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
+    use: [network]
     settings:
       node_count_dynamic_max: 20
       bandwidth_tier: gvnic_enabled
 
   - id: compute_partition
-    source: community/modules/compute/schedmd-slurm-gcp-v5-partition
+    source: community/modules/compute/schedmd-slurm-gcp-v6-partition
     use:
-    - network1
     - homefs
-    - compute_node_group
+    - compute_nodeset
     settings:
       partition_name: compute
 
-  - id: h3_node_group
-    source: community/modules/compute/schedmd-slurm-gcp-v5-node-group
+  - id: h3_nodeset
+    source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
+    use: [network]
     settings:
       node_count_dynamic_max: 20
       machine_type: h3-standard-88
@@ -84,30 +85,29 @@ deployment_groups:
       bandwidth_tier: gvnic_enabled
 
   - id: h3_partition
-    source: community/modules/compute/schedmd-slurm-gcp-v5-partition
+    source: community/modules/compute/schedmd-slurm-gcp-v6-partition
     use:
-    - network1
     - homefs
-    - h3_node_group
+    - h3_nodeset
     settings:
       partition_name: h3
 
+  - id: slurm_login
+    source: community/modules/scheduler/schedmd-slurm-gcp-v6-login
+    use: [network]
+    settings:
+      name_prefix: login
+      machine_type: n2-standard-4
+      disable_login_public_ips: false
+
   - id: slurm_controller
-    source: community/modules/scheduler/schedmd-slurm-gcp-v5-controller
+    source: community/modules/scheduler/schedmd-slurm-gcp-v6-controller
     use:
-    - network1
+    - network
     - debug_partition
     - compute_partition
     - h3_partition
     - homefs
+    - slurm_login
     settings:
       disable_controller_public_ips: false
-
-  - id: slurm_login
-    source: community/modules/scheduler/schedmd-slurm-gcp-v5-login
-    use:
-    - network1
-    - slurm_controller
-    settings:
-      machine_type: n2-standard-4
-      disable_login_public_ips: false

tools/cloud-build/daily-tests/tests/slurm-v6-rocky8.yml

@@ -26,13 +26,14 @@ cli_deployment_vars:
 
 zone: us-west4-c
 workspace: /workspace
-blueprint_yaml: "{{ workspace }}/community/examples/hpc-slurm6.yaml"
+blueprint_yaml: "{{ workspace }}/examples/hpc-slurm.yaml"
 network: "{{ deployment_name }}-net"
 max_nodes: 5
 # Note: Pattern matching in gcloud only supports 1 wildcard, a*-login-* won't work.
 login_node: "{{ slurm_cluster_name }}-login-*"
 controller_node: "{{ slurm_cluster_name }}-controller"
 post_deploy_tests:
+- test-validation/test-mounts.yml
 - test-validation/test-partitions.yml
 custom_vars:
    partitions: