Release v1.40.0

cmd/root.go

@@ -53,7 +53,7 @@ HPC deployments on the Google Cloud Platform.`,
 				logging.Fatal("cmd.Help function failed: %s", err)
 			}
 		},
-		Version:     "v1.39.0",
+		Version:     "v1.40.0",
 		Annotations: annotation,
 	}
 )

community/examples/hpc-build-slurm-image.yaml

@@ -23,7 +23,7 @@ vars:
   image_build_machine_type: n2d-standard-16
   build_from_image_family: hpc-rocky-linux-8
   build_from_image_project: cloud-hpc-image-public
-  build_from_git_ref: 6.5.9
+  build_from_git_ref: 6.7.0
   built_image_family: my-custom-slurm
   built_instance_image:
     family: $(vars.built_image_family)

community/examples/hpc-slurm6-tpu.yaml

@@ -49,6 +49,7 @@ deployment_groups:
     use: [tpu_nodeset]
     settings:
       partition_name: tpu
+      resume_timeout: 600
 
   - id: slurm_login
     source: community/modules/scheduler/schedmd-slurm-gcp-v6-login

community/front-end/ofe/infrastructure_files/workbench_tf/google/README.md

@@ -71,12 +71,12 @@ limitations under the License.
 | <a name="input_folder_id"></a> [folder\_id](#input\_folder\_id) | Folder ID where the project should be created. It can be skipped if already setting organization\_id. Leave blank if the project should be created directly underneath the Organization node. | `string` | `""` | no |
 | <a name="input_image_family"></a> [image\_family](#input\_image\_family) | DEPRECATED: Image of the AI notebook. | `string` | `null` | no |
 | <a name="input_image_project"></a> [image\_project](#input\_image\_project) | DEPRECATED: Google Cloud project where the image is hosted. | `string` | `null` | no |
-| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | Image of the AI notebook.<br><br>Expected Fields:<br>name: The name of the image. Mutually exclusive with family.<br>family: The image family to use. Mutually exclusive with name.<br>project: The project where the image is hosted. | `map(string)` | <pre>{<br>  "family": "tf-latest-cpu",<br>  "project": "deeplearning-platform-release"<br>}</pre> | no |
+| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | Image of the AI notebook.<br/><br/>Expected Fields:<br/>name: The name of the image. Mutually exclusive with family.<br/>family: The image family to use. Mutually exclusive with name.<br/>project: The project where the image is hosted. | `map(string)` | <pre>{<br/>  "family": "tf-latest-cpu",<br/>  "project": "deeplearning-platform-release"<br/>}</pre> | no |
 | <a name="input_ip_cidr_range"></a> [ip\_cidr\_range](#input\_ip\_cidr\_range) | Unique IP CIDR Range for AI Notebooks subnet | `string` | `"10.142.190.0/24"` | no |
 | <a name="input_machine_type"></a> [machine\_type](#input\_machine\_type) | Type of VM you would like to spin up | `string` | `"n1-standard-1"` | no |
 | <a name="input_network_name"></a> [network\_name](#input\_network\_name) | Name of the network to be created. | `string` | `"ai-notebook"` | no |
 | <a name="input_organization_id"></a> [organization\_id](#input\_organization\_id) | Organization ID where GCP Resources need to get spin up. It can be skipped if already setting folder\_id | `string` | `""` | no |
-| <a name="input_owner_id"></a> [owner\_id](#input\_owner\_id) | Billing Account associated to the GCP Resources | `list(any)` | <pre>[<br>  ""<br>]</pre> | no |
+| <a name="input_owner_id"></a> [owner\_id](#input\_owner\_id) | Billing Account associated to the GCP Resources | `list(any)` | <pre>[<br/>  ""<br/>]</pre> | no |
 | <a name="input_project"></a> [project](#input\_project) | Project in which to launch the AI Notebooks. | `string` | `""` | no |
 | <a name="input_project_name"></a> [project\_name](#input\_project\_name) | Project name or ID, if it's an existing project. | `string` | `"gcluster-discovery"` | no |
 | <a name="input_random_id"></a> [random\_id](#input\_random\_id) | Adds a suffix of 4 random characters to the `project_id` | `string` | `null` | no |

community/modules/compute/htcondor-execute-point/README.md

@@ -212,7 +212,7 @@ limitations under the License.
 |------|--------|---------|
 | <a name="module_execute_point_instance_template"></a> [execute\_point\_instance\_template](#module\_execute\_point\_instance\_template) | terraform-google-modules/vm/google//modules/instance_template | 10.1.1 |
 | <a name="module_mig"></a> [mig](#module\_mig) | terraform-google-modules/vm/google//modules/mig | 10.1.1 |
-| <a name="module_startup_script"></a> [startup\_script](#module\_startup\_script) | github.com/GoogleCloudPlatform/hpc-toolkit//modules/scripts/startup-script | v1.36.0&depth=1 |
+| <a name="module_startup_script"></a> [startup\_script](#module\_startup\_script) | github.com/GoogleCloudPlatform/hpc-toolkit//modules/scripts/startup-script | v1.39.0&depth=1 |
 
 ## Resources
 
@@ -226,7 +226,7 @@ limitations under the License.
 
 | Name | Description | Type | Default | Required |
 |------|-------------|------|---------|:--------:|
-| <a name="input_allow_automatic_updates"></a> [allow\_automatic\_updates](#input\_allow\_automatic\_updates) | If false, disables automatic system package updates on the created instances.  This feature is<br>only available on supported images (or images derived from them).  For more details, see<br>https://cloud.google.com/compute/docs/instances/create-hpc-vm#disable_automatic_updates | `bool` | `true` | no |
+| <a name="input_allow_automatic_updates"></a> [allow\_automatic\_updates](#input\_allow\_automatic\_updates) | If false, disables automatic system package updates on the created instances.  This feature is<br/>only available on supported images (or images derived from them).  For more details, see<br/>https://cloud.google.com/compute/docs/instances/create-hpc-vm#disable_automatic_updates | `bool` | `true` | no |
 | <a name="input_central_manager_ips"></a> [central\_manager\_ips](#input\_central\_manager\_ips) | List of IP addresses of HTCondor Central Managers | `list(string)` | n/a | yes |
 | <a name="input_deployment_name"></a> [deployment\_name](#input\_deployment\_name) | Cluster Toolkit deployment name. HTCondor cloud resource names will include this value. | `string` | n/a | yes |
 | <a name="input_disk_size_gb"></a> [disk\_size\_gb](#input\_disk\_size\_gb) | Boot disk size in GB | `number` | `100` | no |
@@ -236,21 +236,21 @@ limitations under the License.
 | <a name="input_enable_shielded_vm"></a> [enable\_shielded\_vm](#input\_enable\_shielded\_vm) | Enable the Shielded VM configuration (var.shielded\_instance\_config). | `bool` | `false` | no |
 | <a name="input_execute_point_runner"></a> [execute\_point\_runner](#input\_execute\_point\_runner) | A list of Toolkit runners for configuring an HTCondor execute point | `list(map(string))` | `[]` | no |
 | <a name="input_execute_point_service_account_email"></a> [execute\_point\_service\_account\_email](#input\_execute\_point\_service\_account\_email) | Service account for HTCondor execute point (e-mail format) | `string` | n/a | yes |
-| <a name="input_guest_accelerator"></a> [guest\_accelerator](#input\_guest\_accelerator) | List of the type and count of accelerator cards attached to the instance. | <pre>list(object({<br>    type  = string,<br>    count = number<br>  }))</pre> | `[]` | no |
+| <a name="input_guest_accelerator"></a> [guest\_accelerator](#input\_guest\_accelerator) | List of the type and count of accelerator cards attached to the instance. | <pre>list(object({<br/>    type  = string,<br/>    count = number<br/>  }))</pre> | `[]` | no |
 | <a name="input_htcondor_bucket_name"></a> [htcondor\_bucket\_name](#input\_htcondor\_bucket\_name) | Name of HTCondor configuration bucket | `string` | n/a | yes |
-| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | HTCondor execute point VM image<br><br>Expected Fields:<br>name: The name of the image. Mutually exclusive with family.<br>family: The image family to use. Mutually exclusive with name.<br>project: The project where the image is hosted. | `map(string)` | <pre>{<br>  "family": "hpc-rocky-linux-8",<br>  "project": "cloud-hpc-image-public"<br>}</pre> | no |
+| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | HTCondor execute point VM image<br/><br/>Expected Fields:<br/>name: The name of the image. Mutually exclusive with family.<br/>family: The image family to use. Mutually exclusive with name.<br/>project: The project where the image is hosted. | `map(string)` | <pre>{<br/>  "family": "hpc-rocky-linux-8",<br/>  "project": "cloud-hpc-image-public"<br/>}</pre> | no |
 | <a name="input_labels"></a> [labels](#input\_labels) | Labels to add to HTConodr execute points | `map(string)` | n/a | yes |
 | <a name="input_machine_type"></a> [machine\_type](#input\_machine\_type) | Machine type to use for HTCondor execute points | `string` | `"n2-standard-4"` | no |
 | <a name="input_max_size"></a> [max\_size](#input\_max\_size) | Maximum size of the HTCondor execute point pool. | `number` | `5` | no |
 | <a name="input_metadata"></a> [metadata](#input\_metadata) | Metadata to add to HTCondor execute points | `map(string)` | `{}` | no |
 | <a name="input_min_idle"></a> [min\_idle](#input\_min\_idle) | Minimum number of idle VMs in the HTCondor pool (if pool reaches var.max\_size, this minimum is not guaranteed); set to ensure jobs beginning run more quickly. | `number` | `0` | no |
 | <a name="input_name_prefix"></a> [name\_prefix](#input\_name\_prefix) | Name prefix given to hostnames in this group of execute points; must be unique across all instances of this module | `string` | n/a | yes |
 | <a name="input_network_self_link"></a> [network\_self\_link](#input\_network\_self\_link) | The self link of the network HTCondor execute points will join | `string` | `"default"` | no |
-| <a name="input_network_storage"></a> [network\_storage](#input\_network\_storage) | An array of network attached storage mounts to be configured | <pre>list(object({<br>    server_ip             = string,<br>    remote_mount          = string,<br>    local_mount           = string,<br>    fs_type               = string,<br>    mount_options         = string,<br>    client_install_runner = map(string)<br>    mount_runner          = map(string)<br>  }))</pre> | `[]` | no |
+| <a name="input_network_storage"></a> [network\_storage](#input\_network\_storage) | An array of network attached storage mounts to be configured | <pre>list(object({<br/>    server_ip             = string,<br/>    remote_mount          = string,<br/>    local_mount           = string,<br/>    fs_type               = string,<br/>    mount_options         = string,<br/>    client_install_runner = map(string)<br/>    mount_runner          = map(string)<br/>  }))</pre> | `[]` | no |
 | <a name="input_project_id"></a> [project\_id](#input\_project\_id) | Project in which the HTCondor execute points will be created | `string` | n/a | yes |
 | <a name="input_region"></a> [region](#input\_region) | The region in which HTCondor execute points will be created | `string` | n/a | yes |
-| <a name="input_service_account_scopes"></a> [service\_account\_scopes](#input\_service\_account\_scopes) | Scopes by which to limit service account attached to central manager. | `set(string)` | <pre>[<br>  "https://www.googleapis.com/auth/cloud-platform"<br>]</pre> | no |
-| <a name="input_shielded_instance_config"></a> [shielded\_instance\_config](#input\_shielded\_instance\_config) | Shielded VM configuration for the instance (must set var.enabled\_shielded\_vm) | <pre>object({<br>    enable_secure_boot          = bool<br>    enable_vtpm                 = bool<br>    enable_integrity_monitoring = bool<br>  })</pre> | <pre>{<br>  "enable_integrity_monitoring": true,<br>  "enable_secure_boot": true,<br>  "enable_vtpm": true<br>}</pre> | no |
+| <a name="input_service_account_scopes"></a> [service\_account\_scopes](#input\_service\_account\_scopes) | Scopes by which to limit service account attached to central manager. | `set(string)` | <pre>[<br/>  "https://www.googleapis.com/auth/cloud-platform"<br/>]</pre> | no |
+| <a name="input_shielded_instance_config"></a> [shielded\_instance\_config](#input\_shielded\_instance\_config) | Shielded VM configuration for the instance (must set var.enabled\_shielded\_vm) | <pre>object({<br/>    enable_secure_boot          = bool<br/>    enable_vtpm                 = bool<br/>    enable_integrity_monitoring = bool<br/>  })</pre> | <pre>{<br/>  "enable_integrity_monitoring": true,<br/>  "enable_secure_boot": true,<br/>  "enable_vtpm": true<br/>}</pre> | no |
 | <a name="input_spot"></a> [spot](#input\_spot) | Provision VMs using discounted Spot pricing, allowing for preemption | `bool` | `false` | no |
 | <a name="input_subnetwork_self_link"></a> [subnetwork\_self\_link](#input\_subnetwork\_self\_link) | The self link of the subnetwork HTCondor execute points will join | `string` | `null` | no |
 | <a name="input_target_size"></a> [target\_size](#input\_target\_size) | Initial size of the HTCondor execute point pool; set to null (default) to avoid Terraform management of size. | `number` | `null` | no |

community/modules/compute/htcondor-execute-point/main.tf

@@ -120,7 +120,7 @@ resource "google_storage_bucket_object" "execute_config" {
 }
 
 module "startup_script" {
-  source = "github.com/GoogleCloudPlatform/hpc-toolkit//modules/scripts/startup-script?ref=v1.36.0&depth=1"
+  source = "github.com/GoogleCloudPlatform/hpc-toolkit//modules/scripts/startup-script?ref=v1.39.0&depth=1"
 
   project_id      = var.project_id
   region          = var.region

community/modules/compute/htcondor-execute-point/versions.tf

@@ -25,6 +25,6 @@ terraform {
   }
 
   provider_meta "google" {
-    module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.39.0"
+    module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.40.0"
   }
 }

community/modules/compute/mig/README.md

@@ -33,7 +33,7 @@ No modules.
 | <a name="input_name"></a> [name](#input\_name) | Name of the MIG. If not provided, will be generated from `var.deployment_name` | `string` | `null` | no |
 | <a name="input_project_id"></a> [project\_id](#input\_project\_id) | Project in which the MIG will be created | `string` | n/a | yes |
 | <a name="input_target_size"></a> [target\_size](#input\_target\_size) | Target number of instances in the MIG | `number` | `0` | no |
-| <a name="input_versions"></a> [versions](#input\_versions) | Application versions managed by this instance group. Each version deals with a specific instance template | <pre>list(object({<br>    name              = string<br>    instance_template = string<br>    target_size = optional(object({<br>      fixed   = optional(number)<br>      percent = optional(number)<br>    }))<br>  }))</pre> | n/a | yes |
+| <a name="input_versions"></a> [versions](#input\_versions) | Application versions managed by this instance group. Each version deals with a specific instance template | <pre>list(object({<br/>    name              = string<br/>    instance_template = string<br/>    target_size = optional(object({<br/>      fixed   = optional(number)<br/>      percent = optional(number)<br/>    }))<br/>  }))</pre> | n/a | yes |
 | <a name="input_wait_for_instances"></a> [wait\_for\_instances](#input\_wait\_for\_instances) | Whether to wait for all instances to be created/updated before returning | `bool` | `false` | no |
 | <a name="input_zone"></a> [zone](#input\_zone) | Compute Platform zone. Required, currently only zonal MIGs are supported | `string` | n/a | yes |
 

community/modules/compute/mig/versions.tf

@@ -22,6 +22,6 @@ terraform {
     }
   }
   provider_meta "google" {
-    module_name = "blueprints/terraform/hpc-toolkit:mig/v1.39.0"
+    module_name = "blueprints/terraform/hpc-toolkit:mig/v1.40.0"
   }
 }

community/modules/compute/notebook/README.md

@@ -76,7 +76,7 @@ No modules.
 |------|-------------|------|---------|:--------:|
 | <a name="input_deployment_name"></a> [deployment\_name](#input\_deployment\_name) | Name of the HPC deployment; used as part of name of the notebook. | `string` | n/a | yes |
 | <a name="input_gcs_bucket_path"></a> [gcs\_bucket\_path](#input\_gcs\_bucket\_path) | Bucket name, can be provided from the google-cloud-storage module | `string` | `null` | no |
-| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | Instance Image | `map(string)` | <pre>{<br>  "family": "tf-latest-cpu",<br>  "name": null,<br>  "project": "deeplearning-platform-release"<br>}</pre> | no |
+| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | Instance Image | `map(string)` | <pre>{<br/>  "family": "tf-latest-cpu",<br/>  "name": null,<br/>  "project": "deeplearning-platform-release"<br/>}</pre> | no |
 | <a name="input_labels"></a> [labels](#input\_labels) | Labels to add to the resource Key-value pairs. | `map(string)` | n/a | yes |
 | <a name="input_machine_type"></a> [machine\_type](#input\_machine\_type) | The machine type to employ | `string` | n/a | yes |
 | <a name="input_mount_runner"></a> [mount\_runner](#input\_mount\_runner) | mount content from the google-cloud-storage module | `map(string)` | n/a | yes |