Add future reservation support

community/modules/compute/schedmd-slurm-gcp-v6-nodeset/README.md

@@ -179,6 +179,7 @@ No modules.
 | <a name="input_enable_shielded_vm"></a> [enable\_shielded\_vm](#input\_enable\_shielded\_vm) | Enable the Shielded VM configuration. Note: the instance image must support option. | `bool` | `false` | no |
 | <a name="input_enable_smt"></a> [enable\_smt](#input\_enable\_smt) | Enables Simultaneous Multi-Threading (SMT) on instance. | `bool` | `false` | no |
 | <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_future_reservation"></a> [future\_reservation](#input\_future\_reservation) | If set, will make use of the future reservation for the nodeset. Input can be either the future reservation name or its selfLink in the format 'projects/PROJECT\_ID/zones/ZONE/futureReservations/FUTURE\_RESERVATION\_NAME'.<br/>See https://cloud.google.com/compute/docs/instances/future-reservations-overview | `string` | `""` | 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-6-8-hpc-rocky-linux-8",<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 |

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

@@ -95,6 +95,7 @@ locals {
     spot                     = var.enable_spot_vm
     termination_action       = try(var.spot_instance_config.termination_action, null)
     reservation_name         = local.reservation_name
+    future_reservation       = local.future_reservation
     maintenance_interval     = var.maintenance_interval
     instance_properties_json = jsonencode(var.instance_properties)
 
@@ -141,6 +142,17 @@ locals {
   reservation_name = local.res_match.whole == null ? "" : "${local.res_prefix}${local.res_short_name}${local.res_suffix}"
 }
 
+locals {
+  fr_match = regex("^(?P<whole>projects/(?P<project>[a-z0-9-]+)/zones/(?P<zone>[a-z0-9-]+)/futureReservations/)?(?P<name>[a-z0-9-]+)?$", var.future_reservation)
+
+  fr_name    = local.fr_match.name
+  fr_project = coalesce(local.fr_match.project, var.project_id)
+  fr_zone    = coalesce(local.fr_match.zone, var.zone)
+
+  future_reservation = var.future_reservation == "" ? "" : "projects/${local.fr_project}/zones/${local.fr_zone}/futureReservations/${local.fr_name}"
+}
+
+
 # tflint-ignore: terraform_unused_declarations
 data "google_compute_reservation" "reservation" {
   count = length(local.reservation_name) > 0 ? 1 : 0

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

@@ -54,4 +54,28 @@ output "nodeset" {
     condition     = !var.enable_placement || !var.dws_flex.enabled
     error_message = "Cannot use DWS Flex with `enable_placement`."
   }
+
+  precondition {
+    condition     = var.reservation_name == "" || var.future_reservation == ""
+    error_message = "Cannot use reservations and future reservations in the same nodeset"
+  }
+
+  precondition {
+    condition     = !var.enable_placement || var.future_reservation == ""
+    error_message = "Cannot use `enable_placement` with future reservations."
+  }
+
+  precondition {
+    condition     = var.future_reservation == "" || length(var.zones) == 0
+    error_message = <<-EOD
+      If a future reservation is specified, `var.zones` should be empty.
+    EOD
+  }
+
+  precondition {
+    condition     = var.future_reservation == "" || local.fr_zone == var.zone
+    error_message = <<-EOD
+      The zone of the deployment must match that of the future reservation"
+    EOD
+  }
 }

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

@@ -463,6 +463,21 @@ variable "reservation_name" {
   }
 }
 
+variable "future_reservation" {
+  description = <<-EOD
+  If set, will make use of the future reservation for the nodeset. Input can be either the future reservation name or its selfLink in the format 'projects/PROJECT_ID/zones/ZONE/futureReservations/FUTURE_RESERVATION_NAME'.
+  See https://cloud.google.com/compute/docs/instances/future-reservations-overview
+  EOD
+  type        = string
+  default     = ""
+  nullable    = false
+
+  validation {
+    condition     = length(regexall("^(projects/([a-z0-9-]+)/zones/([a-z0-9-]+)/futureReservations/([a-z0-9-]+))?$", var.future_reservation)) > 0 || length(regexall("^([a-z0-9-]+)$", var.future_reservation)) > 0
+    error_message = "Future reservation must be either the future reservation name or its selfLink in the format 'projects/PROJECT_ID/zone/ZONE/futureReservations/FUTURE_RESERVATION_NAME'."
+  }
+}
+
 variable "maintenance_interval" {
   description = <<-EOD
     Sets the maintenance interval for instances in this nodeset.

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

@@ -336,7 +336,7 @@ 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/>    enable_maintenance_reservation   = optional(bool, false)<br/>    enable_opportunistic_maintenance = optional(bool, false)<br/>    gpu = optional(object({<br/>      count = number<br/>      type  = string<br/>    }))<br/>    dws_flex = object({<br/>      enabled          = bool<br/>      max_run_duration = number<br/>      use_job_duration = bool<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"></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/>    enable_maintenance_reservation   = optional(bool, false)<br/>    enable_opportunistic_maintenance = optional(bool, false)<br/>    gpu = optional(object({<br/>      count = number<br/>      type  = string<br/>    }))<br/>    dws_flex = object({<br/>      enabled          = bool<br/>      max_run_duration = number<br/>      use_job_duration = bool<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/>    future_reservation = 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 |