Merge pull request #2926 from mr0re1/cp_2893

Fix bug of suppliying different `instance_properties`

community/modules/compute/schedmd-slurm-gcp-v6-nodeset/main.tf

@@ -97,7 +97,7 @@ locals {
     termination_action       = try(var.spot_instance_config.termination_action, null)
     reservation_name         = local.reservation_name
     maintenance_interval     = var.maintenance_interval
-    instance_properties      = var.instance_properties
+    instance_properties_json = jsonencode(var.instance_properties)
 
     zone_target_shape = var.zone_target_shape
     zone_policy_allow = local.zones

community/modules/scheduler/schedmd-slurm-gcp-v6-controller/README.md

@@ -273,7 +273,7 @@ limitations under the License.
 | <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) | Specifies a minimum CPU platform. Applicable values are the friendly names of<br>CPU platforms, such as Intel Haswell or Intel Skylake. See the complete list:<br>https://cloud.google.com/compute/docs/instances/specify-min-cpu-platform | `string` | `null` | no |
 | <a name="input_network_storage"></a> [network\_storage](#input\_network\_storage) | An array of network attached storage mounts to be configured on all instances. | <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 = optional(map(string))<br>    mount_runner          = optional(map(string))<br>  }))</pre> | `[]` | no |
-| <a name="input_nodeset"></a> [nodeset](#input\_nodeset) | Define nodesets, as a list. | <pre>list(object({<br>    node_count_static      = optional(number, 0)<br>    node_count_dynamic_max = optional(number, 1)<br>    node_conf              = optional(map(string), {})<br>    nodeset_name           = string<br>    additional_disks = optional(list(object({<br>      disk_name    = optional(string)<br>      device_name  = optional(string)<br>      disk_size_gb = optional(number)<br>      disk_type    = optional(string)<br>      disk_labels  = optional(map(string), {})<br>      auto_delete  = optional(bool, true)<br>      boot         = optional(bool, false)<br>    })), [])<br>    bandwidth_tier         = optional(string, "platform_default")<br>    can_ip_forward         = optional(bool, false)<br>    disable_smt            = optional(bool, false)<br>    disk_auto_delete       = optional(bool, true)<br>    disk_labels            = optional(map(string), {})<br>    disk_size_gb           = optional(number)<br>    disk_type              = optional(string)<br>    enable_confidential_vm = optional(bool, false)<br>    enable_placement       = optional(bool, false)<br>    enable_oslogin         = optional(bool, true)<br>    enable_shielded_vm     = optional(bool, false)<br>    gpu = optional(object({<br>      count = number<br>      type  = string<br>    }))<br>    labels               = optional(map(string), {})<br>    machine_type         = optional(string)<br>    maintenance_interval = optional(string)<br>    instance_properties  = optional(any, null)<br>    metadata             = optional(map(string), {})<br>    min_cpu_platform     = optional(string)<br>    network_tier         = optional(string, "STANDARD")<br>    network_storage = optional(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 = optional(map(string))<br>      mount_runner          = optional(map(string))<br>    })), [])<br>    on_host_maintenance = optional(string)<br>    preemptible         = optional(bool, false)<br>    region              = optional(string)<br>    service_account = optional(object({<br>      email  = optional(string)<br>      scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"])<br>    }))<br>    shielded_instance_config = optional(object({<br>      enable_integrity_monitoring = optional(bool, true)<br>      enable_secure_boot          = optional(bool, true)<br>      enable_vtpm                 = optional(bool, true)<br>    }))<br>    source_image_family  = optional(string)<br>    source_image_project = optional(string)<br>    source_image         = optional(string)<br>    subnetwork_self_link = string<br>    additional_networks = optional(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>    access_config = optional(list(object({<br>      nat_ip       = string<br>      network_tier = string<br>    })))<br>    spot               = optional(bool, false)<br>    tags               = optional(list(string), [])<br>    termination_action = optional(string)<br>    reservation_name   = optional(string)<br>    startup_script = optional(list(object({<br>      filename = string<br>    content = string })), [])<br><br>    zone_target_shape = string<br>    zone_policy_allow = set(string)<br>    zone_policy_deny  = set(string)<br>  }))</pre> | `[]` | no |
+| <a name="input_nodeset"></a> [nodeset](#input\_nodeset) | Define nodesets, as a list. | <pre>list(object({<br>    node_count_static      = optional(number, 0)<br>    node_count_dynamic_max = optional(number, 1)<br>    node_conf              = optional(map(string), {})<br>    nodeset_name           = string<br>    additional_disks = optional(list(object({<br>      disk_name    = optional(string)<br>      device_name  = optional(string)<br>      disk_size_gb = optional(number)<br>      disk_type    = optional(string)<br>      disk_labels  = optional(map(string), {})<br>      auto_delete  = optional(bool, true)<br>      boot         = optional(bool, false)<br>    })), [])<br>    bandwidth_tier         = optional(string, "platform_default")<br>    can_ip_forward         = optional(bool, false)<br>    disable_smt            = optional(bool, false)<br>    disk_auto_delete       = optional(bool, true)<br>    disk_labels            = optional(map(string), {})<br>    disk_size_gb           = optional(number)<br>    disk_type              = optional(string)<br>    enable_confidential_vm = optional(bool, false)<br>    enable_placement       = optional(bool, false)<br>    enable_oslogin         = optional(bool, true)<br>    enable_shielded_vm     = optional(bool, false)<br>    gpu = optional(object({<br>      count = number<br>      type  = string<br>    }))<br>    labels                   = optional(map(string), {})<br>    machine_type             = optional(string)<br>    maintenance_interval     = optional(string)<br>    instance_properties_json = string<br>    metadata                 = optional(map(string), {})<br>    min_cpu_platform         = optional(string)<br>    network_tier             = optional(string, "STANDARD")<br>    network_storage = optional(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 = optional(map(string))<br>      mount_runner          = optional(map(string))<br>    })), [])<br>    on_host_maintenance = optional(string)<br>    preemptible         = optional(bool, false)<br>    region              = optional(string)<br>    service_account = optional(object({<br>      email  = optional(string)<br>      scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"])<br>    }))<br>    shielded_instance_config = optional(object({<br>      enable_integrity_monitoring = optional(bool, true)<br>      enable_secure_boot          = optional(bool, true)<br>      enable_vtpm                 = optional(bool, true)<br>    }))<br>    source_image_family  = optional(string)<br>    source_image_project = optional(string)<br>    source_image         = optional(string)<br>    subnetwork_self_link = string<br>    additional_networks = optional(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>    access_config = optional(list(object({<br>      nat_ip       = string<br>      network_tier = string<br>    })))<br>    spot               = optional(bool, false)<br>    tags               = optional(list(string), [])<br>    termination_action = optional(string)<br>    reservation_name   = optional(string)<br>    startup_script = optional(list(object({<br>      filename = string<br>    content = string })), [])<br><br>    zone_target_shape = string<br>    zone_policy_allow = set(string)<br>    zone_policy_deny  = set(string)<br>  }))</pre> | `[]` | no |
 | <a name="input_nodeset_dyn"></a> [nodeset\_dyn](#input\_nodeset\_dyn) | Defines dynamic nodesets, as a list. | <pre>list(object({<br>    nodeset_name    = string<br>    nodeset_feature = string<br>  }))</pre> | `[]` | no |
 | <a name="input_nodeset_tpu"></a> [nodeset\_tpu](#input\_nodeset\_tpu) | Define TPU nodesets, as a list. | <pre>list(object({<br>    node_count_static      = optional(number, 0)<br>    node_count_dynamic_max = optional(number, 5)<br>    nodeset_name           = string<br>    enable_public_ip       = optional(bool, false)<br>    node_type              = string<br>    accelerator_config = optional(object({<br>      topology = string<br>      version  = string<br>      }), {<br>      topology = ""<br>      version  = ""<br>    })<br>    tf_version   = string<br>    preemptible  = optional(bool, false)<br>    preserve_tpu = optional(bool, false)<br>    zone         = string<br>    data_disks   = optional(list(string), [])<br>    docker_image = optional(string, "")<br>    network_storage = optional(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 = optional(map(string))<br>      mount_runner          = optional(map(string))<br>    })), [])<br>    subnetwork = string<br>    service_account = optional(object({<br>      email  = optional(string)<br>      scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"])<br>    }))<br>    project_id = string<br>    reserved   = optional(string, false)<br>  }))</pre> | `[]` | no |
 | <a name="input_on_host_maintenance"></a> [on\_host\_maintenance](#input\_on\_host\_maintenance) | Instance availability Policy. | `string` | `"MIGRATE"` | no |

community/modules/scheduler/schedmd-slurm-gcp-v6-controller/modules/slurm_files/main.tf

@@ -67,8 +67,12 @@ locals {
     epilog_scripts   = [for k, v in google_storage_bucket_object.epilog_scripts : k]
     cloud_parameters = var.cloud_parameters
 
-    partitions  = { for p in var.partitions : p.partition_name => p }
-    nodeset     = { for n in var.nodeset : n.nodeset_name => n }
+    partitions = { for p in var.partitions : p.partition_name => p }
+    nodeset = {
+      for n in var.nodeset : n.nodeset_name => merge(n, {
+        instance_properties = jsondecode(n.instance_properties_json)
+      })
+    }
     nodeset_dyn = { for n in var.nodeset_dyn : n.nodeset_name => n }
     nodeset_tpu = { for n in var.nodeset_tpu[*].nodeset : n.nodeset_name => n }
 

community/modules/scheduler/schedmd-slurm-gcp-v6-controller/partition.tf

@@ -68,20 +68,20 @@ module "slurm_nodeset_template" {
 
 locals {
   nodesets = [for name, ns in local.nodeset_map : {
-    nodeset_name           = ns.nodeset_name
-    node_conf              = ns.node_conf
-    instance_template      = module.slurm_nodeset_template[ns.nodeset_name].self_link
-    node_count_dynamic_max = ns.node_count_dynamic_max
-    node_count_static      = ns.node_count_static
-    subnetwork             = ns.subnetwork_self_link
-    reservation_name       = ns.reservation_name
-    maintenance_interval   = ns.maintenance_interval
-    instance_properties    = ns.instance_properties
-    enable_placement       = ns.enable_placement
-    network_storage        = ns.network_storage
-    zone_target_shape      = ns.zone_target_shape
-    zone_policy_allow      = ns.zone_policy_allow
-    zone_policy_deny       = ns.zone_policy_deny
+    nodeset_name             = ns.nodeset_name
+    node_conf                = ns.node_conf
+    instance_template        = module.slurm_nodeset_template[ns.nodeset_name].self_link
+    node_count_dynamic_max   = ns.node_count_dynamic_max
+    node_count_static        = ns.node_count_static
+    subnetwork               = ns.subnetwork_self_link
+    reservation_name         = ns.reservation_name
+    maintenance_interval     = ns.maintenance_interval
+    instance_properties_json = ns.instance_properties_json
+    enable_placement         = ns.enable_placement
+    network_storage          = ns.network_storage
+    zone_target_shape        = ns.zone_target_shape
+    zone_policy_allow        = ns.zone_policy_allow
+    zone_policy_deny         = ns.zone_policy_deny
   }]
 }
 

community/modules/scheduler/schedmd-slurm-gcp-v6-controller/variables.tf

@@ -211,13 +211,13 @@ variable "nodeset" {
       count = number
       type  = string
     }))
-    labels               = optional(map(string), {})
-    machine_type         = optional(string)
-    maintenance_interval = optional(string)
-    instance_properties  = optional(any, null)
-    metadata             = optional(map(string), {})
-    min_cpu_platform     = optional(string)
-    network_tier         = optional(string, "STANDARD")
+    labels                   = optional(map(string), {})
+    machine_type             = optional(string)
+    maintenance_interval     = optional(string)
+    instance_properties_json = string
+    metadata                 = optional(map(string), {})
+    min_cpu_platform         = optional(string)
+    network_tier             = optional(string, "STANDARD")
     network_storage = optional(list(object({
       server_ip             = string
       remote_mount          = string