diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-partition/README.md b/community/modules/compute/schedmd-slurm-gcp-v6-partition/README.md index 54148697bf..00aa1198e8 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-partition/README.md +++ b/community/modules/compute/schedmd-slurm-gcp-v6-partition/README.md @@ -85,7 +85,7 @@ No resources. | [exclusive](#input\_exclusive) | Exclusive job access to nodes. When set to true nodes execute single job and are deleted
after job exits. If set to false, multiple jobs can be scheduled on one node. | `bool` | `true` | no | | [is\_default](#input\_is\_default) | Sets this partition as the default partition by updating the partition\_conf.
If "Default" is already set in partition\_conf, this variable will have no effect. | `bool` | `false` | no | | [network\_storage](#input\_network\_storage) | DEPRECATED | 
list(object({
    server_ip             = string,
    remote_mount          = string,
    local_mount           = string,
    fs_type               = string,
    mount_options         = string,
    client_install_runner = map(string)
    mount_runner          = map(string)
  }))
| `[]` | no | -| [nodeset](#input\_nodeset) | A list of nodesets.
For type definition see community/modules/scheduler/schedmd-slurm-gcp-v6-controller/variables.tf::nodeset | `list(any)` | `[]` | no | +| [nodeset](#input\_nodeset) | A list of nodesets.
For type definition see community/modules/scheduler/schedmd-slurm-gcp-v6-controller/variables.tf::nodeset | 
list(object({
    node_count_static      = optional(number, 0)
    node_count_dynamic_max = optional(number, 1)
    node_conf              = optional(map(string), {})
    nodeset_name           = string
    additional_disks = optional(list(object({
      disk_name    = optional(string)
      device_name  = optional(string)
      disk_size_gb = optional(number)
      disk_type    = optional(string)
      disk_labels  = optional(map(string), {})
      auto_delete  = optional(bool, true)
      boot         = optional(bool, false)
    })), [])
    bandwidth_tier                   = optional(string, "platform_default")
    can_ip_forward                   = optional(bool, false)
    disable_smt                      = optional(bool, false)
    disk_auto_delete                 = optional(bool, true)
    disk_labels                      = optional(map(string), {})
    disk_size_gb                     = optional(number)
    disk_type                        = optional(string)
    enable_confidential_vm           = optional(bool, false)
    enable_placement                 = optional(bool, false)
    enable_oslogin                   = optional(bool, true)
    enable_shielded_vm               = optional(bool, false)
    enable_maintenance_reservation   = optional(bool, false)
    enable_opportunistic_maintenance = optional(bool, false)
    gpu = optional(object({
      count = number
      type  = string
    }))
    dws_flex = object({
      enabled          = bool
      max_run_duration = number
      use_job_duration = bool
    })
    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
      local_mount           = string
      fs_type               = string
      mount_options         = string
      client_install_runner = optional(map(string))
      mount_runner          = optional(map(string))
    })), [])
    on_host_maintenance = optional(string)
    preemptible         = optional(bool, false)
    region              = optional(string)
    service_account = optional(object({
      email  = optional(string)
      scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"])
    }))
    shielded_instance_config = optional(object({
      enable_integrity_monitoring = optional(bool, true)
      enable_secure_boot          = optional(bool, true)
      enable_vtpm                 = optional(bool, true)
    }))
    source_image_family  = optional(string)
    source_image_project = optional(string)
    source_image         = optional(string)
    subnetwork_self_link = string
    additional_networks = optional(list(object({
      network            = string
      subnetwork         = string
      subnetwork_project = string
      network_ip         = string
      nic_type           = string
      stack_type         = string
      queue_count        = number
      access_config = list(object({
        nat_ip       = string
        network_tier = string
      }))
      ipv6_access_config = list(object({
        network_tier = string
      }))
      alias_ip_range = list(object({
        ip_cidr_range         = string
        subnetwork_range_name = string
      }))
    })))
    access_config = optional(list(object({
      nat_ip       = string
      network_tier = string
    })))
    spot               = optional(bool, false)
    tags               = optional(list(string), [])
    termination_action = optional(string)
    reservation_name   = optional(string)
    future_reservation = string
    startup_script = optional(list(object({
      filename = string
    content = string })), [])

    zone_target_shape = string
    zone_policy_allow = set(string)
    zone_policy_deny  = set(string)
  }))
| `[]` | no | | [nodeset\_dyn](#input\_nodeset\_dyn) | Defines dynamic nodesets, as a list. | 
list(object({
    nodeset_name    = string
    nodeset_feature = string
  }))
| `[]` | no | | [nodeset\_tpu](#input\_nodeset\_tpu) | Define TPU nodesets, as a list. | 
list(object({
    node_count_static      = optional(number, 0)
    node_count_dynamic_max = optional(number, 5)
    nodeset_name           = string
    enable_public_ip       = optional(bool, false)
    node_type              = string
    accelerator_config = optional(object({
      topology = string
      version  = string
      }), {
      topology = ""
      version  = ""
    })
    tf_version   = string
    preemptible  = optional(bool, false)
    preserve_tpu = optional(bool, false)
    zone         = string
    data_disks   = optional(list(string), [])
    docker_image = optional(string, "")
    network_storage = optional(list(object({
      server_ip     = string
      remote_mount  = string
      local_mount   = string
      fs_type       = string
      mount_options = string
    })), [])
    subnetwork = string
    service_account = optional(object({
      email  = optional(string)
      scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"])
    }))
    project_id = string
    reserved   = optional(string, false)
  }))
| `[]` | no | | [partition\_conf](#input\_partition\_conf) | Slurm partition configuration as a map.
See https://slurm.schedmd.com/slurm.conf.html#SECTION_PARTITION-CONFIGURATION | `map(string)` | `{}` | no | diff --git a/community/modules/compute/schedmd-slurm-gcp-v6-partition/variables.tf b/community/modules/compute/schedmd-slurm-gcp-v6-partition/variables.tf index e14e44b02a..5798e68878 100644 --- a/community/modules/compute/schedmd-slurm-gcp-v6-partition/variables.tf +++ b/community/modules/compute/schedmd-slurm-gcp-v6-partition/variables.tf @@ -54,8 +54,112 @@ variable "nodeset" { A list of nodesets. For type definition see community/modules/scheduler/schedmd-slurm-gcp-v6-controller/variables.tf::nodeset EOD - type = list(any) - default = [] + type = list(object({ + node_count_static = optional(number, 0) + node_count_dynamic_max = optional(number, 1) + node_conf = optional(map(string), {}) + nodeset_name = string + additional_disks = optional(list(object({ + disk_name = optional(string) + device_name = optional(string) + disk_size_gb = optional(number) + disk_type = optional(string) + disk_labels = optional(map(string), {}) + auto_delete = optional(bool, true) + boot = optional(bool, false) + })), []) + bandwidth_tier = optional(string, "platform_default") + can_ip_forward = optional(bool, false) + disable_smt = optional(bool, false) + disk_auto_delete = optional(bool, true) + disk_labels = optional(map(string), {}) + disk_size_gb = optional(number) + disk_type = optional(string) + enable_confidential_vm = optional(bool, false) + enable_placement = optional(bool, false) + enable_oslogin = optional(bool, true) + enable_shielded_vm = optional(bool, false) + enable_maintenance_reservation = optional(bool, false) + enable_opportunistic_maintenance = optional(bool, false) + gpu = optional(object({ + count = number + type = string + })) + dws_flex = object({ + enabled = bool + max_run_duration = number + use_job_duration = bool + }) + 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 + local_mount = string + fs_type = string + mount_options = string + client_install_runner = optional(map(string)) + mount_runner = optional(map(string)) + })), []) + on_host_maintenance = optional(string) + preemptible = optional(bool, false) + region = optional(string) + service_account = optional(object({ + email = optional(string) + scopes = optional(list(string), ["https://www.googleapis.com/auth/cloud-platform"]) + })) + shielded_instance_config = optional(object({ + enable_integrity_monitoring = optional(bool, true) + enable_secure_boot = optional(bool, true) + enable_vtpm = optional(bool, true) + })) + source_image_family = optional(string) + source_image_project = optional(string) + source_image = optional(string) + subnetwork_self_link = string + additional_networks = optional(list(object({ + network = string + subnetwork = string + subnetwork_project = string + network_ip = string + nic_type = string + stack_type = string + queue_count = number + access_config = list(object({ + nat_ip = string + network_tier = string + })) + ipv6_access_config = list(object({ + network_tier = string + })) + alias_ip_range = list(object({ + ip_cidr_range = string + subnetwork_range_name = string + })) + }))) + access_config = optional(list(object({ + nat_ip = string + network_tier = string + }))) + spot = optional(bool, false) + tags = optional(list(string), []) + termination_action = optional(string) + reservation_name = optional(string) + future_reservation = string + startup_script = optional(list(object({ + filename = string + content = string })), []) + + zone_target_shape = string + zone_policy_allow = set(string) + zone_policy_deny = set(string) + })) + default = [] validation { condition = length(distinct(var.nodeset[*].nodeset_name)) == length(var.nodeset) diff --git a/tools/validate_configs/test_configs/node-groups.yaml b/tools/validate_configs/test_configs/node-groups.yaml index 962d1e3130..ef512993c7 100644 --- a/tools/validate_configs/test_configs/node-groups.yaml +++ b/tools/validate_configs/test_configs/node-groups.yaml @@ -107,51 +107,6 @@ deployment_groups: settings: partition_name: multns - ## Explicitly set node partition with one nodeset - - id: single_nodeset_explicit_partition - source: community/modules/compute/schedmd-slurm-gcp-v6-partition - settings: - partition_name: explns - is_default: true - nodeset: - - nodeset_name: expl - node_count_static: 0 - node_count_dynamic_max: 4 - enable_placement: false - node_conf: {} - additional_disks: [] - additional_networks: [] - bandwidth_tier: null - can_ip_forward: false - enable_smt: true - disk_auto_delete: true - disk_labels: {} - disk_size_gb: 50 - disk_type: pd-standard - enable_confidential_vm: false - enable_oslogin: true - enable_shielded_vm: false - enable_spot_vm: false - gpu: null - instance_template: null - labels: $(vars.labels) - machine_type: n2-standard-16 - maintenance_interval: "" - metadata: {} - min_cpu_platform: null - on_host_maintenance: TERMINATE - preemptible: false - reservation_name: null # will be replaced by default value empty string - service_account_email: null - shielded_instance_config: null - subnetwork_self_link: $(network.subnetwork_self_link) - spot_instance_config: null - source_image_family: null - source_image_project: null - source_image: null - tags: [] - access_config: [] - - id: slurm_login source: community/modules/scheduler/schedmd-slurm-gcp-v6-login use: [network] @@ -165,7 +120,6 @@ deployment_groups: - network - single_nodeset_partition - multiple_nodesets - - single_nodeset_explicit_partition - homefs - slurm_login settings: