Merge pull request #2189 from GoogleCloudPlatform/slurm_5_10_2

Update Slurm-GCP release to 5.10.2

community/examples/AMD/hpc-amd-slurm.yaml

@@ -171,7 +171,7 @@ deployment_groups:
         # these images must match the images used by Slurm modules below because
         # we are building OpenMPI with PMI support in libraries contained in
         # Slurm installation
-        family: slurm-gcp-5-9-hpc-centos-7
+        family: slurm-gcp-5-10-hpc-centos-7
         project: schedmd-slurm-public
 
   - id: low_cost_node_group

community/examples/hpc-slurm-chromedesktop.yaml

@@ -17,15 +17,16 @@
 blueprint_name: slurm-crd
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: slurm-crd-01
   region: us-central1
   zone: us-central1-c
   instance_image_crd:
-    family: slurm-gcp-5-9-debian-11
+    family: slurm-gcp-5-10-debian-11
     project: schedmd-slurm-public
   instance_image:
-    family: slurm-gcp-5-9-hpc-centos-7
+    family: slurm-gcp-5-10-hpc-centos-7
     project: schedmd-slurm-public
 
 # Documentation for each of the modules used below can be found at

community/examples/hpc-slurm-local-ssd.yaml

@@ -17,6 +17,7 @@
 blueprint_name: hpc-slurm-local-ssd
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: hpc-localssd
   region: us-central1

community/examples/hpc-slurm-ramble-gromacs.yaml

@@ -17,6 +17,7 @@
 blueprint_name: hpc-slurm-ramble-gromacs
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: hpc-slurm-ramble-gromacs
   region: us-central1

community/examples/hpc-slurm-ubuntu2004.yaml

@@ -17,14 +17,15 @@
 blueprint_name: hpc-slurm-ubuntu2004
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: slurm-gcp-v5
   region: us-west4
   zone: us-west4-c
   instance_image:
     # Please refer to the following link for the latest images:
-    # https://github.com/SchedMD/slurm-gcp/blob/master/docs/images.md#supported-operating-systems
-    family: slurm-gcp-5-9-ubuntu-2004-lts
+    # https://github.com/GoogleCloudPlatform/slurm-gcp/blob/master/docs/images.md#supported-operating-systems
+    family: slurm-gcp-5-10-ubuntu-2004-lts
     project: schedmd-slurm-public
   instance_image_custom: true
 

community/examples/htc-slurm.yaml

@@ -17,12 +17,13 @@
 
 # This blueprint provisions a cluster using the Slurm scheduler configured to
 # efficiently run many short duration, loosely-coupled (non-MPI) jobs. See also:
-# https://github.com/SchedMD/slurm-gcp/blob/master/docs/htc.md
+# https://github.com/GoogleCloudPlatform/slurm-gcp/blob/master/docs/htc.md
 # https://slurm.schedmd.com/high_throughput.html
 
 blueprint_name: htc-slurm
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: htc-slurm
   region: us-west4

community/examples/tutorial-starccm-slurm.yaml

@@ -17,6 +17,7 @@
 blueprint_name: starccm-on-slurm
 
 vars:
+  enable_devel: true
   project_id:  ## Set GCP Project ID Here ##
   deployment_name: starccm-slurm
   region: us-central1

community/modules/compute/schedmd-slurm-gcp-v5-node-group/README.md

@@ -72,8 +72,8 @@ The HPC Toolkit team maintains the wrapper around the [slurm-on-gcp] terraform
 modules. For support with the underlying modules, see the instructions in the
 [slurm-gcp README][slurm-gcp-readme].
 
-[slurm-on-gcp]: https://github.com/SchedMD/slurm-gcp
-[slurm-gcp-readme]: https://github.com/SchedMD/slurm-gcp#slurm-on-google-cloud-platform
+[slurm-on-gcp]: https://github.com/GoogleCloudPlatform/slurm-gcp
+[slurm-gcp-readme]: https://github.com/GoogleCloudPlatform/slurm-gcp#slurm-on-google-cloud-platform
 
 ## License
 <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->
@@ -136,11 +136,12 @@ No modules.
 | <a name="input_enable_spot_vm"></a> [enable\_spot\_vm](#input\_enable\_spot\_vm) | Enable the partition to use spot VMs (https://cloud.google.com/spot-vms). | `bool` | `false` | no |
 | <a name="input_gpu"></a> [gpu](#input\_gpu) | DEPRECATED: use var.guest\_accelerator | <pre>object({<br>    type  = string<br>    count = number<br>  })</pre> | `null` | 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_instance_image"></a> [instance\_image](#input\_instance\_image) | Defines the image that will be used in the Slurm node group VM instances.<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.<br><br>For more information on creating custom images that comply with Slurm on GCP<br>see the "Slurm on GCP Custom Images" section in docs/vm-images.md. | `map(string)` | <pre>{<br>  "family": "slurm-gcp-5-9-hpc-centos-7",<br>  "project": "schedmd-slurm-public"<br>}</pre> | no |
+| <a name="input_instance_image"></a> [instance\_image](#input\_instance\_image) | Defines the image that will be used in the Slurm node group VM instances.<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.<br><br>For more information on creating custom images that comply with Slurm on GCP<br>see the "Slurm on GCP Custom Images" section in docs/vm-images.md. | `map(string)` | <pre>{<br>  "family": "slurm-gcp-5-10-hpc-centos-7",<br>  "project": "schedmd-slurm-public"<br>}</pre> | no |
 | <a name="input_instance_image_custom"></a> [instance\_image\_custom](#input\_instance\_image\_custom) | A flag that designates that the user is aware that they are requesting<br>to use a custom and potentially incompatible image for this Slurm on<br>GCP module.<br><br>If the field is set to false, only the compatible families and project<br>names will be accepted.  The deployment will fail with any other image<br>family or name.  If set to true, no checks will be done.<br><br>See: https://goo.gle/hpc-slurm-images | `bool` | `false` | no |
 | <a name="input_instance_template"></a> [instance\_template](#input\_instance\_template) | Self link to a custom instance template. If set, other VM definition<br>variables such as machine\_type and instance\_image will be ignored in favor<br>of the provided instance template.<br><br>For more information on creating custom images for the instance template<br>that comply with Slurm on GCP see the "Slurm on GCP Custom Images" section<br>in docs/vm-images.md. | `string` | `null` | no |
 | <a name="input_labels"></a> [labels](#input\_labels) | Labels to add to partition compute instances. Key-value pairs. | `map(string)` | `{}` | no |
 | <a name="input_machine_type"></a> [machine\_type](#input\_machine\_type) | Compute Platform machine type to use for this partition compute nodes. | `string` | `"c2-standard-60"` | no |
+| <a name="input_maintenance_interval"></a> [maintenance\_interval](#input\_maintenance\_interval) | Specifies the frequency of planned maintenance events. Must be unset (null) or "PERIODIC". | `string` | `null` | no |
 | <a name="input_metadata"></a> [metadata](#input\_metadata) | Metadata, provided as a map. | `map(string)` | `{}` | no |
 | <a name="input_min_cpu_platform"></a> [min\_cpu\_platform](#input\_min\_cpu\_platform) | The name of the minimum CPU platform that you want the instance to use. | `string` | `null` | no |
 | <a name="input_name"></a> [name](#input\_name) | Name of the node group. | `string` | `"ghpc"` | no |

community/modules/compute/schedmd-slurm-gcp-v5-node-group/main.tf

@@ -58,6 +58,7 @@ locals {
     gpu                      = one(local.guest_accelerator)
     labels                   = local.labels
     machine_type             = var.machine_type
+    maintenance_interval     = var.maintenance_interval
     metadata                 = var.metadata
     min_cpu_platform         = var.min_cpu_platform
     on_host_maintenance      = var.on_host_maintenance

community/modules/compute/schedmd-slurm-gcp-v5-node-group/source_image_logic.tf

@@ -18,12 +18,12 @@ locals {
   # Currently supported images and projects
   known_project_families = {
     schedmd-slurm-public = [
-      "slurm-gcp-5-9-debian-11",
-      "slurm-gcp-5-9-hpc-rocky-linux-8",
-      "slurm-gcp-5-9-ubuntu-2004-lts",
-      "slurm-gcp-5-9-ubuntu-2204-lts-arm64",
-      "slurm-gcp-5-9-hpc-centos-7-k80",
-      "slurm-gcp-5-9-hpc-centos-7"
+      "slurm-gcp-5-10-debian-11",
+      "slurm-gcp-5-10-hpc-rocky-linux-8",
+      "slurm-gcp-5-10-ubuntu-2004-lts",
+      "slurm-gcp-5-10-ubuntu-2204-lts-arm64",
+      "slurm-gcp-5-10-hpc-centos-7-k80",
+      "slurm-gcp-5-10-hpc-centos-7"
     ]
   }
 

community/modules/compute/schedmd-slurm-gcp-v5-node-group/variables.tf

@@ -15,7 +15,7 @@
  */
 
 # Most variables have been sourced and modified from the SchedMD/slurm-gcp
-# github repository: https://github.com/SchedMD/slurm-gcp/tree/5.9.1
+# github repository: https://github.com/GoogleCloudPlatform/slurm-gcp/tree/5.10.2
 
 variable "project_id" {
   description = "Project in which the HPC deployment will be created."
@@ -96,7 +96,7 @@ variable "instance_image" {
   type        = map(string)
   default = {
     project = "schedmd-slurm-public"
-    family  = "slurm-gcp-5-9-hpc-centos-7"
+    family  = "slurm-gcp-5-10-hpc-centos-7"
   }
 
   validation {
@@ -413,6 +413,18 @@ variable "additional_networks" {
   }))
 }
 
+variable "maintenance_interval" {
+  description = "Specifies the frequency of planned maintenance events. Must be unset (null) or \"PERIODIC\"."
+  default     = null
+  type        = string
+  nullable    = true
+
+  validation {
+    condition     = var.maintenance_interval == null || var.maintenance_interval == "PERIODIC"
+    error_message = "var.maintenance_interval must be unset (null) or set to \"PERIODIC\""
+  }
+}
+
 variable "disable_public_ips" {
   description = "If set to false. The node group VMs will have a random public IP assigned to it. Ignored if access_config is set."
   type        = bool

community/modules/compute/schedmd-slurm-gcp-v5-partition-dynamic/README.md

@@ -35,8 +35,8 @@ The HPC Toolkit team maintains the wrapper around the [slurm-on-gcp] terraform
 modules. For support with the underlying modules, see the instructions in the
 [slurm-gcp README][slurm-gcp-readme].
 
-[slurm-on-gcp]: https://github.com/SchedMD/slurm-gcp
-[slurm-gcp-readme]: https://github.com/SchedMD/slurm-gcp#slurm-on-google-cloud-platform
+[slurm-on-gcp]: https://github.com/GoogleCloudPlatform/slurm-gcp
+[slurm-gcp-readme]: https://github.com/GoogleCloudPlatform/slurm-gcp#slurm-on-google-cloud-platform
 
 ## License
 <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->
@@ -69,7 +69,7 @@ No providers.
 
 | Name | Source | Version |
 |------|--------|---------|
-| <a name="module_slurm_partition"></a> [slurm\_partition](#module\_slurm\_partition) | github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition | 5.9.1 |
+| <a name="module_slurm_partition"></a> [slurm\_partition](#module\_slurm\_partition) | github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition | 5.10.2 |
 
 ## Resources
 

community/modules/compute/schedmd-slurm-gcp-v5-partition-dynamic/main.tf

@@ -29,7 +29,7 @@ locals {
 }
 
 module "slurm_partition" {
-  source = "github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition?ref=5.9.1"
+  source = "github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition?ref=5.10.2"
 
   slurm_cluster_name   = local.slurm_cluster_name
   enable_job_exclusive = var.exclusive

community/modules/compute/schedmd-slurm-gcp-v5-partition-dynamic/variables.tf

@@ -15,7 +15,7 @@
  */
 
 # Most variables have been sourced and modified from the SchedMD/slurm-gcp
-# github repository: https://github.com/SchedMD/slurm-gcp/tree/5.9.1
+# github repository: https://github.com/GoogleCloudPlatform/slurm-gcp/tree/5.10.2
 
 variable "deployment_name" {
   description = "Name of the deployment."

community/modules/compute/schedmd-slurm-gcp-v5-partition/README.md

@@ -110,8 +110,8 @@ The HPC Toolkit team maintains the wrapper around the [slurm-on-gcp] terraform
 modules. For support with the underlying modules, see the instructions in the
 [slurm-gcp README][slurm-gcp-readme].
 
-[slurm-on-gcp]: https://github.com/SchedMD/slurm-gcp
-[slurm-gcp-readme]: https://github.com/SchedMD/slurm-gcp#slurm-on-google-cloud-platform
+[slurm-on-gcp]: https://github.com/GoogleCloudPlatform/slurm-gcp
+[slurm-gcp-readme]: https://github.com/GoogleCloudPlatform/slurm-gcp#slurm-on-google-cloud-platform
 
 ## License
 <!-- BEGINNING OF PRE-COMMIT-TERRAFORM DOCS HOOK -->
@@ -146,7 +146,7 @@ limitations under the License.
 
 | Name | Source | Version |
 |------|--------|---------|
-| <a name="module_slurm_partition"></a> [slurm\_partition](#module\_slurm\_partition) | github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition | 5.9.1 |
+| <a name="module_slurm_partition"></a> [slurm\_partition](#module\_slurm\_partition) | github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition | 5.10.2 |
 
 ## Resources
 
@@ -164,7 +164,7 @@ limitations under the License.
 | <a name="input_exclusive"></a> [exclusive](#input\_exclusive) | Exclusive job access to nodes. | `bool` | `true` | no |
 | <a name="input_is_default"></a> [is\_default](#input\_is\_default) | Sets this partition as the default partition by updating the partition\_conf.<br>If "Default" is already set in partition\_conf, this variable will have no effect. | `bool` | `false` | no |
 | <a name="input_network_storage"></a> [network\_storage](#input\_network\_storage) | An array of network attached storage mounts to be configured on the partition compute nodes. | <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_node_groups"></a> [node\_groups](#input\_node\_groups) | A list of node groups associated with this partition. See<br>schedmd-slurm-gcp-v5-node-group for more information on defining a node<br>group in a blueprint. | <pre>list(object({<br>    node_count_static      = number<br>    node_count_dynamic_max = number<br>    group_name             = string<br>    node_conf              = map(string)<br>    access_config = list(object({<br>      nat_ip       = string<br>      network_tier = string<br>    }))<br>    additional_disks = list(object({<br>      disk_name    = string<br>      device_name  = string<br>      disk_size_gb = number<br>      disk_type    = string<br>      disk_labels  = map(string)<br>      auto_delete  = bool<br>      boot         = bool<br>    }))<br>    additional_networks = list(object({<br>      network            = string<br>      subnetwork         = string<br>      subnetwork_project = string<br>      network_ip         = string<br>      nic_type           = string<br>      stack_type         = string<br>      queue_count        = number<br>      access_config = list(object({<br>        nat_ip       = string<br>        network_tier = string<br>      }))<br>      ipv6_access_config = list(object({<br>        network_tier = string<br>      }))<br>      alias_ip_range = list(object({<br>        ip_cidr_range         = string<br>        subnetwork_range_name = string<br>      }))<br>    }))<br>    bandwidth_tier         = string<br>    can_ip_forward         = bool<br>    disable_smt            = bool<br>    disk_auto_delete       = bool<br>    disk_labels            = map(string)<br>    disk_size_gb           = number<br>    disk_type              = string<br>    enable_confidential_vm = bool<br>    enable_oslogin         = bool<br>    enable_shielded_vm     = bool<br>    enable_spot_vm         = bool<br>    gpu = object({<br>      count = number<br>      type  = string<br>    })<br>    instance_template   = string<br>    labels              = map(string)<br>    machine_type        = string<br>    metadata            = map(string)<br>    min_cpu_platform    = string<br>    on_host_maintenance = string<br>    preemptible         = bool<br>    reservation_name    = string<br>    service_account = object({<br>      email  = string<br>      scopes = list(string)<br>    })<br>    shielded_instance_config = object({<br>      enable_integrity_monitoring = bool<br>      enable_secure_boot          = bool<br>      enable_vtpm                 = bool<br>    })<br>    spot_instance_config = object({<br>      termination_action = string<br>    })<br>    source_image_family  = string<br>    source_image_project = string<br>    source_image         = string<br>    tags                 = list(string)<br>  }))</pre> | `[]` | no |
+| <a name="input_node_groups"></a> [node\_groups](#input\_node\_groups) | A list of node groups associated with this partition. See<br>schedmd-slurm-gcp-v5-node-group for more information on defining a node<br>group in a blueprint. | <pre>list(object({<br>    node_count_static      = number<br>    node_count_dynamic_max = number<br>    group_name             = string<br>    node_conf              = map(string)<br>    access_config = list(object({<br>      nat_ip       = string<br>      network_tier = string<br>    }))<br>    additional_disks = list(object({<br>      disk_name    = string<br>      device_name  = string<br>      disk_size_gb = number<br>      disk_type    = string<br>      disk_labels  = map(string)<br>      auto_delete  = bool<br>      boot         = bool<br>    }))<br>    additional_networks = list(object({<br>      network            = string<br>      subnetwork         = string<br>      subnetwork_project = string<br>      network_ip         = string<br>      nic_type           = string<br>      stack_type         = string<br>      queue_count        = number<br>      access_config = list(object({<br>        nat_ip       = string<br>        network_tier = string<br>      }))<br>      ipv6_access_config = list(object({<br>        network_tier = string<br>      }))<br>      alias_ip_range = list(object({<br>        ip_cidr_range         = string<br>        subnetwork_range_name = string<br>      }))<br>    }))<br>    bandwidth_tier         = string<br>    can_ip_forward         = bool<br>    disable_smt            = bool<br>    disk_auto_delete       = bool<br>    disk_labels            = map(string)<br>    disk_size_gb           = number<br>    disk_type              = string<br>    enable_confidential_vm = bool<br>    enable_oslogin         = bool<br>    enable_shielded_vm     = bool<br>    enable_spot_vm         = bool<br>    gpu = object({<br>      count = number<br>      type  = string<br>    })<br>    instance_template    = string<br>    labels               = map(string)<br>    machine_type         = string<br>    maintenance_interval = string<br>    metadata             = map(string)<br>    min_cpu_platform     = string<br>    on_host_maintenance  = string<br>    preemptible          = bool<br>    reservation_name     = string<br>    service_account = object({<br>      email  = string<br>      scopes = list(string)<br>    })<br>    shielded_instance_config = object({<br>      enable_integrity_monitoring = bool<br>      enable_secure_boot          = bool<br>      enable_vtpm                 = bool<br>    })<br>    spot_instance_config = object({<br>      termination_action = string<br>    })<br>    source_image_family  = string<br>    source_image_project = string<br>    source_image         = string<br>    tags                 = list(string)<br>  }))</pre> | `[]` | no |
 | <a name="input_partition_conf"></a> [partition\_conf](#input\_partition\_conf) | Slurm partition configuration as a map.<br>See https://slurm.schedmd.com/slurm.conf.html#SECTION_PARTITION-CONFIGURATION | `map(string)` | `{}` | no |
 | <a name="input_partition_name"></a> [partition\_name](#input\_partition\_name) | The name of the slurm partition. | `string` | n/a | yes |
 | <a name="input_partition_startup_scripts_timeout"></a> [partition\_startup\_scripts\_timeout](#input\_partition\_startup\_scripts\_timeout) | The timeout (seconds) applied to the partition startup script. If<br>any script exceeds this timeout, then the instance setup process is considered<br>failed and handled accordingly.<br><br>NOTE: When set to 0, the timeout is considered infinite and thus disabled. | `number` | `300` | no |

community/modules/compute/schedmd-slurm-gcp-v5-partition/main.tf

@@ -38,7 +38,7 @@ data "google_compute_zones" "available" {
 }
 
 module "slurm_partition" {
-  source = "github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition?ref=5.9.1"
+  source = "github.com/GoogleCloudPlatform/slurm-gcp.git//terraform/slurm_cluster/modules/slurm_partition?ref=5.10.2"
 
   slurm_cluster_name                = local.slurm_cluster_name
   partition_nodes                   = var.node_groups