feat: added node groups API protos

PiperOrigin-RevId: 494840237
2 years ago · 28449ecb37
parent e8356fefc5
commit 28449ecb37
6 changed files with 503 additions and 131 deletions
--- a/google/cloud/dataproc/v1/BUILD.bazel
+++ b/google/cloud/dataproc/v1/BUILD.bazel
@ -19,6 +19,7 @@ proto_library(
        "operations.proto",
        "shared.proto",
        "workflow_templates.proto",
+        "node_groups.proto",
    ],
    deps = [
        "//google/api:annotations_proto",
@ -91,6 +92,8 @@ java_gapic_test(
        "com.google.cloud.dataproc.v1.JobControllerClientTest",
        "com.google.cloud.dataproc.v1.WorkflowTemplateServiceClientHttpJsonTest",
        "com.google.cloud.dataproc.v1.WorkflowTemplateServiceClientTest",
+        "com.google.cloud.dataproc.v1.NodeGroupControllerClientHttpJsonTest",
+        "com.google.cloud.dataproc.v1.NodeGroupControllerClientTest",
    ],
    runtime_deps = [":dataproc_java_gapic_test"],
 )
--- a/google/cloud/dataproc/v1/clusters.proto
+++ b/google/cloud/dataproc/v1/clusters.proto
@ -43,12 +43,14 @@ option (google.api.resource_definition) = {
 // of Compute Engine instances.
 service ClusterController {
  option (google.api.default_host) = "dataproc.googleapis.com";
-  option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";

  // Creates a cluster in a project. The returned
  // [Operation.metadata][google.longrunning.Operation.metadata] will be
  // [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
-  rpc CreateCluster(CreateClusterRequest) returns (google.longrunning.Operation) {
+  rpc CreateCluster(CreateClusterRequest)
+      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/projects/{project_id}/regions/{region}/clusters"
      body: "cluster"
@ -63,14 +65,17 @@ service ClusterController {
  // Updates a cluster in a project. The returned
  // [Operation.metadata][google.longrunning.Operation.metadata] will be
  // [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
-  // The cluster must be in a [`RUNNING`][google.cloud.dataproc.v1.ClusterStatus.State] state or an error
+  // The cluster must be in a
+  // [`RUNNING`][google.cloud.dataproc.v1.ClusterStatus.State] state or an error
  // is returned.
-  rpc UpdateCluster(UpdateClusterRequest) returns (google.longrunning.Operation) {
+  rpc UpdateCluster(UpdateClusterRequest)
+      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      patch: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}"
      body: "cluster"
    };
-    option (google.api.method_signature) = "project_id,region,cluster_name,cluster,update_mask";
+    option (google.api.method_signature) =
+        "project_id,region,cluster_name,cluster,update_mask";
    option (google.longrunning.operation_info) = {
      response_type: "Cluster"
      metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
@ -104,7 +109,8 @@ service ClusterController {
  // Deletes a cluster in a project. The returned
  // [Operation.metadata][google.longrunning.Operation.metadata] will be
  // [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
-  rpc DeleteCluster(DeleteClusterRequest) returns (google.longrunning.Operation) {
+  rpc DeleteCluster(DeleteClusterRequest)
+      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      delete: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}"
    };
@ -139,7 +145,8 @@ service ClusterController {
  // [Operation.response][google.longrunning.Operation.response]
  // contains
  // [DiagnoseClusterResults](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#diagnoseclusterresults).
-  rpc DiagnoseCluster(DiagnoseClusterRequest) returns (google.longrunning.Operation) {
+  rpc DiagnoseCluster(DiagnoseClusterRequest)
+      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:diagnose"
      body: "*"
@ -158,8 +165,10 @@ message Cluster {
  // Required. The Google Cloud Platform project ID that the cluster belongs to.
  string project_id = 1 [(google.api.field_behavior) = REQUIRED];

-  // Required. The cluster name. Cluster names within a project must be
-  // unique. Names of deleted clusters can be reused.
+  // Required. The cluster name, which must be unique within a project.
+  // The name must start with a lowercase letter, and can contain
+  // up to 51 lowercase letters, numbers, and hyphens. It cannot end
+  // with a hyphen. The name of a deleted cluster can be reused.
  string cluster_name = 2 [(google.api.field_behavior) = REQUIRED];

  // Optional. The cluster config for a cluster of Compute Engine Instances.
@ -167,14 +176,17 @@ message Cluster {
  // when clusters are updated.
  ClusterConfig config = 3 [(google.api.field_behavior) = OPTIONAL];

-  // Optional. The virtual cluster config, used when creating a Dataproc cluster that
-  // does not directly control the underlying compute resources, for example,
-  // when creating a [Dataproc-on-GKE
-  // cluster](https://cloud.google.com/dataproc/docs/concepts/jobs/dataproc-gke#create-a-dataproc-on-gke-cluster).
-  // Note that Dataproc may set default values, and values may change when
-  // clusters are updated. Exactly one of config or virtualClusterConfig must be
-  // specified.
-  VirtualClusterConfig virtual_cluster_config = 10 [(google.api.field_behavior) = OPTIONAL];
+  // Optional. The virtual cluster config is used when creating a Dataproc
+  // cluster that does not directly control the underlying compute resources,
+  // for example, when creating a [Dataproc-on-GKE
+  // cluster](https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke).
+  // Dataproc may set default values, and values may change when
+  // clusters are updated. Exactly one of
+  // [config][google.cloud.dataproc.v1.Cluster.config] or
+  // [virtual_cluster_config][google.cloud.dataproc.v1.Cluster.virtual_cluster_config]
+  // must be specified.
+  VirtualClusterConfig virtual_cluster_config = 10
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The labels to associate with this cluster.
  // Label **keys** must contain 1 to 63 characters, and must conform to
@ -189,7 +201,8 @@ message Cluster {
  ClusterStatus status = 4 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The previous cluster status.
-  repeated ClusterStatus status_history = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+  repeated ClusterStatus status_history = 7
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. A cluster UUID (Unique Universal Identifier). Dataproc
  // generates this value when it creates the cluster.
@ -217,15 +230,13 @@ message ClusterConfig {
  // a Cloud Storage bucket.**
  string config_bucket = 1 [(google.api.field_behavior) = OPTIONAL];

-  // Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs data,
-  // such as Spark and MapReduce history files.
-  // If you do not specify a temp bucket,
-  // Dataproc will determine a Cloud Storage location (US,
-  // ASIA, or EU) for your cluster's temp bucket according to the
-  // Compute Engine zone where your cluster is deployed, and then create
-  // and manage this project-level, per-location bucket. The default bucket has
-  // a TTL of 90 days, but you can use any TTL (or none) if you specify a
-  // bucket (see
+  // Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs
+  // data, such as Spark and MapReduce history files. If you do not specify a
+  // temp bucket, Dataproc will determine a Cloud Storage location (US, ASIA, or
+  // EU) for your cluster's temp bucket according to the Compute Engine zone
+  // where your cluster is deployed, and then create and manage this
+  // project-level, per-location bucket. The default bucket has a TTL of 90
+  // days, but you can use any TTL (or none) if you specify a bucket (see
  // [Dataproc staging and temp
  // buckets](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
  // **This field requires a Cloud Storage bucket name, not a `gs://...` URI to
@ -234,19 +245,23 @@ message ClusterConfig {

  // Optional. The shared Compute Engine config settings for
  // all instances in a cluster.
-  GceClusterConfig gce_cluster_config = 8 [(google.api.field_behavior) = OPTIONAL];
+  GceClusterConfig gce_cluster_config = 8
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Compute Engine config settings for
  // the cluster's master instance.
-  InstanceGroupConfig master_config = 9 [(google.api.field_behavior) = OPTIONAL];
+  InstanceGroupConfig master_config = 9
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Compute Engine config settings for
  // the cluster's worker instances.
-  InstanceGroupConfig worker_config = 10 [(google.api.field_behavior) = OPTIONAL];
+  InstanceGroupConfig worker_config = 10
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Compute Engine config settings for
  // a cluster's secondary worker instances
-  InstanceGroupConfig secondary_worker_config = 12 [(google.api.field_behavior) = OPTIONAL];
+  InstanceGroupConfig secondary_worker_config = 12
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The config settings for cluster software.
  SoftwareConfig software_config = 13 [(google.api.field_behavior) = OPTIONAL];
@ -264,36 +279,46 @@ message ClusterConfig {
  //     else
  //       ... worker specific actions ...
  //     fi
-  repeated NodeInitializationAction initialization_actions = 11 [(google.api.field_behavior) = OPTIONAL];
+  repeated NodeInitializationAction initialization_actions = 11
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Encryption settings for the cluster.
-  EncryptionConfig encryption_config = 15 [(google.api.field_behavior) = OPTIONAL];
+  EncryptionConfig encryption_config = 15
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Autoscaling config for the policy associated with the cluster.
  // Cluster does not autoscale if this field is unset.
-  AutoscalingConfig autoscaling_config = 18 [(google.api.field_behavior) = OPTIONAL];
+  AutoscalingConfig autoscaling_config = 18
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Security settings for the cluster.
  SecurityConfig security_config = 16 [(google.api.field_behavior) = OPTIONAL];

  // Optional. Lifecycle setting for the cluster.
-  LifecycleConfig lifecycle_config = 17 [(google.api.field_behavior) = OPTIONAL];
+  LifecycleConfig lifecycle_config = 17
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Port/endpoint configuration for this cluster
  EndpointConfig endpoint_config = 19 [(google.api.field_behavior) = OPTIONAL];

  // Optional. Metastore configuration.
-  MetastoreConfig metastore_config = 20 [(google.api.field_behavior) = OPTIONAL];
+  MetastoreConfig metastore_config = 20
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The config for Dataproc metrics.
-  DataprocMetricConfig dataproc_metric_config = 23 [(google.api.field_behavior) = OPTIONAL];
+  DataprocMetricConfig dataproc_metric_config = 23
+      [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. The node group settings.
+  repeated AuxiliaryNodeGroup auxiliary_node_groups = 25
+      [(google.api.field_behavior) = OPTIONAL];
 }

-// Dataproc cluster config for a cluster that does not directly control the
+// The Dataproc cluster config for a cluster that does not directly control the
 // underlying compute resources, such as a [Dataproc-on-GKE
-// cluster](https://cloud.google.com/dataproc/docs/concepts/jobs/dataproc-gke#create-a-dataproc-on-gke-cluster).
+// cluster](https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke).
 message VirtualClusterConfig {
-  // Optional. A Storage bucket used to stage job
+  // Optional. A Cloud Storage bucket used to stage job
  // dependencies, config files, and job driver console output.
  // If you do not specify a staging bucket, Cloud
  // Dataproc will determine a Cloud Storage location (US,
@ -307,12 +332,15 @@ message VirtualClusterConfig {
  string staging_bucket = 1 [(google.api.field_behavior) = OPTIONAL];

  oneof infrastructure_config {
-    // Required. The configuration for running the Dataproc cluster on Kubernetes.
-    KubernetesClusterConfig kubernetes_cluster_config = 6 [(google.api.field_behavior) = REQUIRED];
+    // Required. The configuration for running the Dataproc cluster on
+    // Kubernetes.
+    KubernetesClusterConfig kubernetes_cluster_config = 6
+        [(google.api.field_behavior) = REQUIRED];
  }

  // Optional. Configuration of auxiliary services used by this cluster.
-  AuxiliaryServicesConfig auxiliary_services_config = 7 [(google.api.field_behavior) = OPTIONAL];
+  AuxiliaryServicesConfig auxiliary_services_config = 7
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // Auxiliary services configuration for a Cluster.
@ -321,14 +349,16 @@ message AuxiliaryServicesConfig {
  MetastoreConfig metastore_config = 1 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Spark History Server configuration for the workload.
-  SparkHistoryServerConfig spark_history_server_config = 2 [(google.api.field_behavior) = OPTIONAL];
+  SparkHistoryServerConfig spark_history_server_config = 2
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // Endpoint config for this cluster
 message EndpointConfig {
  // Output only. The map of port descriptions to URLs. Will only be populated
  // if enable_http_port_access is true.
-  map<string, string> http_ports = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
+  map<string, string> http_ports = 1
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Optional. If true, enable http access to specific ports on the cluster
  // from external sources. Defaults to false.
@ -366,7 +396,8 @@ message GceClusterConfig {
  // fields](https://cloud.google.com/compute/docs/reference/rest/v1/instances).
  enum PrivateIpv6GoogleAccess {
    // If unspecified, Compute Engine default behavior will apply, which
-    // is the same as [INHERIT_FROM_SUBNETWORK][google.cloud.dataproc.v1.GceClusterConfig.PrivateIpv6GoogleAccess.INHERIT_FROM_SUBNETWORK].
+    // is the same as
+    // [INHERIT_FROM_SUBNETWORK][google.cloud.dataproc.v1.GceClusterConfig.PrivateIpv6GoogleAccess.INHERIT_FROM_SUBNETWORK].
    PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED = 0;

    // Private access to and from Google Services configuration
@ -429,7 +460,8 @@ message GceClusterConfig {
  bool internal_ip_only = 7 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The type of IPv6 access for a cluster.
-  PrivateIpv6GoogleAccess private_ipv6_google_access = 12 [(google.api.field_behavior) = OPTIONAL];
+  PrivateIpv6GoogleAccess private_ipv6_google_access = 12
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The [Dataproc service
  // account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc)
@ -458,7 +490,8 @@ message GceClusterConfig {
  // * https://www.googleapis.com/auth/bigtable.admin.table
  // * https://www.googleapis.com/auth/bigtable.data
  // * https://www.googleapis.com/auth/devstorage.full_control
-  repeated string service_account_scopes = 3 [(google.api.field_behavior) = OPTIONAL];
+  repeated string service_account_scopes = 3
+      [(google.api.field_behavior) = OPTIONAL];

  // The Compute Engine tags to add to all instances (see [Tagging
  // instances](https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
@ -470,21 +503,28 @@ message GceClusterConfig {
  map<string, string> metadata = 5;

  // Optional. Reservation Affinity for consuming Zonal reservation.
-  ReservationAffinity reservation_affinity = 11 [(google.api.field_behavior) = OPTIONAL];
+  ReservationAffinity reservation_affinity = 11
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Node Group Affinity for sole-tenant clusters.
-  NodeGroupAffinity node_group_affinity = 13 [(google.api.field_behavior) = OPTIONAL];
+  NodeGroupAffinity node_group_affinity = 13
+      [(google.api.field_behavior) = OPTIONAL];

-  // Optional. Shielded Instance Config for clusters using [Compute Engine Shielded
+  // Optional. Shielded Instance Config for clusters using [Compute Engine
+  // Shielded
  // VMs](https://cloud.google.com/security/shielded-cloud/shielded-vm).
-  ShieldedInstanceConfig shielded_instance_config = 14 [(google.api.field_behavior) = OPTIONAL];
+  ShieldedInstanceConfig shielded_instance_config = 14
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Confidential Instance Config for clusters using [Confidential
  // VMs](https://cloud.google.com/compute/confidential-vm/docs).
-  ConfidentialInstanceConfig confidential_instance_config = 15 [(google.api.field_behavior) = OPTIONAL];
+  ConfidentialInstanceConfig confidential_instance_config = 15
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // Node Group Affinity for clusters using sole-tenant node groups.
+// **The Dataproc `NodeGroupAffinity` resource is not related to the
+// Dataproc [NodeGroup][google.cloud.dataproc.v1.NodeGroup] resource.**
 message NodeGroupAffinity {
  // Required. The URI of a
  // sole-tenant [node group
@ -515,17 +555,15 @@ message ShieldedInstanceConfig {
 // Confidential Instance Config for clusters using [Confidential
 // VMs](https://cloud.google.com/compute/confidential-vm/docs)
 message ConfidentialInstanceConfig {
-  // Optional. Defines whether the instance should have confidential compute enabled.
+  // Optional. Defines whether the instance should have confidential compute
+  // enabled.
  bool enable_confidential_compute = 1 [(google.api.field_behavior) = OPTIONAL];
 }

 // The config settings for Compute Engine resources in
 // an instance group, such as a master or worker group.
 message InstanceGroupConfig {
-  // Controls the use of
-  // [preemptible instances]
-  // (https://cloud.google.com/compute/docs/instances/preemptible)
-  // within the group.
+  // Controls the use of preemptible instances within the group.
  enum Preemptibility {
    // Preemptibility is unspecified, the system will choose the
    // appropriate setting for each instance group.
@ -537,9 +575,12 @@ message InstanceGroupConfig {
    // value for Master and Worker instance groups.
    NON_PREEMPTIBLE = 1;

-    // Instances are preemptible.
+    // Instances are [preemptible]
+    // (https://cloud.google.com/compute/docs/instances/preemptible).
    //
-    // This option is allowed only for secondary worker groups.
+    // This option is allowed only for [secondary worker]
+    // (https://cloud.google.com/dataproc/docs/concepts/compute/secondary-vms)
+    // groups.
    PREEMPTIBLE = 2;
  }

@ -553,7 +594,8 @@ message InstanceGroupConfig {

  // Output only. The list of instance names. Dataproc derives the names
  // from `cluster_name`, `num_instances`, and the instance group.
-  repeated string instance_names = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
+  repeated string instance_names = 2
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Optional. The Compute Engine image resource used for cluster instances.
  //
@ -609,11 +651,13 @@ message InstanceGroupConfig {
  // Output only. The config for Compute Engine Instance Group
  // Manager that manages this group.
  // This is only used for preemptible instance groups.
-  ManagedGroupConfig managed_group_config = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+  ManagedGroupConfig managed_group_config = 7
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Optional. The Compute Engine accelerator configuration for these
  // instances.
-  repeated AcceleratorConfig accelerators = 8 [(google.api.field_behavior) = OPTIONAL];
+  repeated AcceleratorConfig accelerators = 8
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. Specifies the minimum cpu platform for the Instance Group.
  // See [Dataproc -> Minimum CPU
@ -628,7 +672,8 @@ message ManagedGroupConfig {
  string instance_template_name = 1 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The name of the Instance Group Manager for this group.
-  string instance_group_manager_name = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
+  string instance_group_manager_name = 2
+      [(google.api.field_behavior) = OUTPUT_ONLY];
 }

 // Specifies the type and number of accelerator cards attached to the instances
@ -669,7 +714,7 @@ message DiskConfig {
  // Optional. Size in GB of the boot disk (default is 500GB).
  int32 boot_disk_size_gb = 1 [(google.api.field_behavior) = OPTIONAL];

-  // Optional. Number of attached SSDs, from 0 to 4 (default is 0).
+  // Optional. Number of attached SSDs, from 0 to 8 (default is 0).
  // If SSDs are not attached, the boot disk is used to store runtime logs and
  // [HDFS](https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data.
  // If one or more SSDs are attached, this runtime bulk
@ -685,6 +730,59 @@ message DiskConfig {
  string local_ssd_interface = 4 [(google.api.field_behavior) = OPTIONAL];
 }

+// Node group identification and configuration information.
+message AuxiliaryNodeGroup {
+  // Required. Node group configuration.
+  NodeGroup node_group = 1 [(google.api.field_behavior) = REQUIRED];
+
+  // Optional. A node group ID. Generated if not specified.
+  //
+  // The ID must contain only letters (a-z, A-Z), numbers (0-9),
+  // underscores (_), and hyphens (-). Cannot begin or end with underscore
+  // or hyphen. Must consist of from 3 to 33 characters.
+  string node_group_id = 2 [(google.api.field_behavior) = OPTIONAL];
+}
+
+// Dataproc Node Group.
+// **The Dataproc `NodeGroup` resource is not related to the
+// Dataproc [NodeGroupAffinity][google.cloud.dataproc.v1.NodeGroupAffinity]
+// resource.**
+message NodeGroup {
+  option (google.api.resource) = {
+    type: "dataproc.googleapis.com/NodeGroup"
+    pattern: "projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{node_group}"
+  };
+
+  // Node group roles.
+  enum Role {
+    // Required unspecified role.
+    ROLE_UNSPECIFIED = 0;
+
+    // Job drivers run on the node group.
+    DRIVER = 1;
+  }
+
+  // The Node group [resource name](https://aip.dev/122).
+  string name = 1;
+
+  // Required. Node group roles.
+  repeated Role roles = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Optional. The node group instance group configuration.
+  InstanceGroupConfig node_group_config = 3
+      [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Node group labels.
+  //
+  // * Label **keys** must consist of from 1 to 63 characters and conform to
+  //   [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt).
+  // * Label **values** can be empty. If specified, they must consist of from
+  //   1 to 63 characters and conform to [RFC 1035]
+  //   (https://www.ietf.org/rfc/rfc1035.txt).
+  // * The node group must have no more than 32 labels.
+  map<string, string> labels = 4 [(google.api.field_behavior) = OPTIONAL];
+}
+
 // Specifies an executable to run on a fully configured node and a
 // timeout period for executable completion.
 message NodeInitializationAction {
@ -698,7 +796,8 @@ message NodeInitializationAction {
  // Cluster creation fails with an explanatory error message (the
  // name of the executable that caused the error and the exceeded timeout
  // period) if the executable is not completed at end of the timeout period.
-  google.protobuf.Duration execution_timeout = 2 [(google.api.field_behavior) = OPTIONAL];
+  google.protobuf.Duration execution_timeout = 2
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // The status of a cluster and its instances.
@ -771,7 +870,8 @@ message ClusterStatus {

  // Output only. Time when this state was entered (see JSON representation of
  // [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).
-  google.protobuf.Timestamp state_start_time = 3 [(google.api.field_behavior) = OUTPUT_ONLY];
+  google.protobuf.Timestamp state_start_time = 3
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Additional state information that includes
  // status reported by the agent.
@ -790,13 +890,14 @@ message SecurityConfig {

 // Specifies Kerberos related configuration.
 message KerberosConfig {
-  // Optional. Flag to indicate whether to Kerberize the cluster (default: false). Set
-  // this field to true to enable Kerberos on a cluster.
+  // Optional. Flag to indicate whether to Kerberize the cluster (default:
+  // false). Set this field to true to enable Kerberos on a cluster.
  bool enable_kerberos = 1 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Cloud Storage URI of a KMS encrypted file containing the root
  // principal password.
-  string root_principal_password_uri = 2 [(google.api.field_behavior) = OPTIONAL];
+  string root_principal_password_uri = 2
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The uri of the KMS key used to encrypt various sensitive
  // files.
@ -837,12 +938,14 @@ message KerberosConfig {

  // Optional. The admin server (IP or hostname) for the remote trusted realm in
  // a cross realm trust relationship.
-  string cross_realm_trust_admin_server = 11 [(google.api.field_behavior) = OPTIONAL];
+  string cross_realm_trust_admin_server = 11
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Cloud Storage URI of a KMS encrypted file containing the
  // shared password between the on-cluster Kerberos realm and the remote
  // trusted realm, in a cross realm trust relationship.
-  string cross_realm_trust_shared_password_uri = 12 [(google.api.field_behavior) = OPTIONAL];
+  string cross_realm_trust_shared_password_uri = 12
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. The Cloud Storage URI of a KMS encrypted file containing the
  // master key of the KDC database.
@ -862,7 +965,8 @@ message KerberosConfig {
 // secure multi-tenancy user mappings.
 message IdentityConfig {
  // Required. Map of user to service account.
-  map<string, string> user_service_account_mapping = 1 [(google.api.field_behavior) = REQUIRED];
+  map<string, string> user_service_account_mapping = 1
+      [(google.api.field_behavior) = REQUIRED];
 }

 // Specifies the selection and config of software inside the cluster.
@ -897,7 +1001,8 @@ message SoftwareConfig {
  map<string, string> properties = 2 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The set of components to activate on the cluster.
-  repeated Component optional_components = 3 [(google.api.field_behavior) = OPTIONAL];
+  repeated Component optional_components = 3
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // Specifies the cluster auto-delete schedule configuration.
@ -907,27 +1012,32 @@ message LifecycleConfig {
  // deleted. Minimum value is 5 minutes; maximum value is 14 days (see JSON
  // representation of
  // [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).
-  google.protobuf.Duration idle_delete_ttl = 1 [(google.api.field_behavior) = OPTIONAL];
+  google.protobuf.Duration idle_delete_ttl = 1
+      [(google.api.field_behavior) = OPTIONAL];

  // Either the exact time the cluster should be deleted at or
  // the cluster maximum age.
  oneof ttl {
-    // Optional. The time when cluster will be auto-deleted (see JSON representation of
+    // Optional. The time when cluster will be auto-deleted (see JSON
+    // representation of
    // [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).
-    google.protobuf.Timestamp auto_delete_time = 2 [(google.api.field_behavior) = OPTIONAL];
+    google.protobuf.Timestamp auto_delete_time = 2
+        [(google.api.field_behavior) = OPTIONAL];

    // Optional. The lifetime duration of cluster. The cluster will be
    // auto-deleted at the end of this period. Minimum value is 10 minutes;
    // maximum value is 14 days (see JSON representation of
    // [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).
-    google.protobuf.Duration auto_delete_ttl = 3 [(google.api.field_behavior) = OPTIONAL];
+    google.protobuf.Duration auto_delete_ttl = 3
+        [(google.api.field_behavior) = OPTIONAL];
  }

  // Output only. The time when cluster became idle (most recent job finished)
  // and became eligible for deletion due to idleness (see JSON representation
  // of
  // [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).
-  google.protobuf.Timestamp idle_start_time = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
+  google.protobuf.Timestamp idle_start_time = 4
+      [(google.api.field_behavior) = OUTPUT_ONLY];
 }

 // Specifies a Metastore configuration.
@ -945,7 +1055,6 @@ message MetastoreConfig {
  ];
 }

-
 // Dataproc metric config.
 message DataprocMetricConfig {
  // A source for the collection of Dataproc OSS metrics (see [available OSS
@ -1014,7 +1123,8 @@ message DataprocMetricConfig {
    //   sources is unaffected. For example, if both `SPARK` andd `YARN` metric
    //   sources are enabled, and overrides are provided for Spark metrics only,
    //   all default YARN metrics will be collected.
-    repeated string metric_overrides = 2 [(google.api.field_behavior) = OPTIONAL];
+    repeated string metric_overrides = 2
+        [(google.api.field_behavior) = OPTIONAL];
  }

  // Required. Metrics sources to enable.
@ -1045,11 +1155,12 @@ message CreateClusterRequest {
  // Required. The cluster to create.
  Cluster cluster = 2 [(google.api.field_behavior) = REQUIRED];

-  // Optional. A unique ID used to identify the request. If the server receives two
+  // Optional. A unique ID used to identify the request. If the server receives
+  // two
  // [CreateClusterRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.CreateClusterRequest)s
  // with the same id, then the second request will be ignored and the
-  // first [google.longrunning.Operation][google.longrunning.Operation] created and stored in the backend
-  // is returned.
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
  //
  // It is recommended to always set this value to a
  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
@ -1059,7 +1170,8 @@ message CreateClusterRequest {
  string request_id = 4 [(google.api.field_behavior) = OPTIONAL];

  // Optional. Failure action when primary worker creation fails.
-  FailureAction action_on_failed_primary_workers = 5 [(google.api.field_behavior) = OPTIONAL];
+  FailureAction action_on_failed_primary_workers = 5
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // A request to update a cluster.
@ -1086,7 +1198,8 @@ message UpdateClusterRequest {
  // [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).
  //
  // Only supported on Dataproc image versions 1.2 and higher.
-  google.protobuf.Duration graceful_decommission_timeout = 6 [(google.api.field_behavior) = OPTIONAL];
+  google.protobuf.Duration graceful_decommission_timeout = 6
+      [(google.api.field_behavior) = OPTIONAL];

  // Required. Specifies the path, relative to `Cluster`, of
  // the field to update. For example, to change the number of workers
@ -1139,14 +1252,15 @@ message UpdateClusterRequest {
  //  </tr>
  //  </tbody>
  //  </table>
-  google.protobuf.FieldMask update_mask = 4 [(google.api.field_behavior) = REQUIRED];
+  google.protobuf.FieldMask update_mask = 4
+      [(google.api.field_behavior) = REQUIRED];

  // Optional. A unique ID used to identify the request. If the server
  // receives two
  // [UpdateClusterRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.UpdateClusterRequest)s
  // with the same id, then the second request will be ignored and the
-  // first [google.longrunning.Operation][google.longrunning.Operation] created and stored in the
-  // backend is returned.
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
  //
  // It is recommended to always set this value to a
  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
@ -1176,8 +1290,8 @@ message StopClusterRequest {
  // receives two
  // [StopClusterRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.StopClusterRequest)s
  // with the same id, then the second request will be ignored and the
-  // first [google.longrunning.Operation][google.longrunning.Operation] created and stored in the
-  // backend is returned.
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
  //
  // Recommendation: Set this value to a
  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
@ -1207,8 +1321,8 @@ message StartClusterRequest {
  // receives two
  // [StartClusterRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.StartClusterRequest)s
  // with the same id, then the second request will be ignored and the
-  // first [google.longrunning.Operation][google.longrunning.Operation] created and stored in the
-  // backend is returned.
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
  //
  // Recommendation: Set this value to a
  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
@ -1238,8 +1352,8 @@ message DeleteClusterRequest {
  // receives two
  // [DeleteClusterRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.DeleteClusterRequest)s
  // with the same id, then the second request will be ignored and the
-  // first [google.longrunning.Operation][google.longrunning.Operation] created and stored in the
-  // backend is returned.
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
  //
  // It is recommended to always set this value to a
  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
--- a/google/cloud/dataproc/v1/dataproc_v1.yaml
+++ b/google/cloud/dataproc/v1/dataproc_v1.yaml
@ -8,6 +8,7 @@ apis:
 - name: google.cloud.dataproc.v1.BatchController
 - name: google.cloud.dataproc.v1.ClusterController
 - name: google.cloud.dataproc.v1.JobController
+- name: google.cloud.dataproc.v1.NodeGroupController
 - name: google.cloud.dataproc.v1.WorkflowTemplateService

 types:
@ -15,6 +16,7 @@ types:
 - name: google.cloud.dataproc.v1.ClusterOperationMetadata
 - name: google.cloud.dataproc.v1.DiagnoseClusterResults
 - name: google.cloud.dataproc.v1.JobMetadata
+- name: google.cloud.dataproc.v1.NodeGroupOperationMetadata
 - name: google.cloud.dataproc.v1.WorkflowMetadata

 documentation:
@ -120,6 +122,10 @@ authentication:
    oauth:
      canonical_scopes: |-
        https://www.googleapis.com/auth/cloud-platform
+  - selector: 'google.cloud.dataproc.v1.NodeGroupController.*'
+    oauth:
+      canonical_scopes: |-
+        https://www.googleapis.com/auth/cloud-platform
  - selector: 'google.cloud.dataproc.v1.WorkflowTemplateService.*'
    oauth:
      canonical_scopes: |-
--- a/google/cloud/dataproc/v1/jobs.proto
+++ b/google/cloud/dataproc/v1/jobs.proto
@ -1,4 +1,4 @@
-// Copyright 2021 Google LLC
+// Copyright 2022 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@ -32,7 +32,8 @@ option java_package = "com.google.cloud.dataproc.v1";
 // The JobController provides methods to manage jobs.
 service JobController {
  option (google.api.default_host) = "dataproc.googleapis.com";
-  option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";

  // Submits a job to a cluster.
  rpc SubmitJob(SubmitJobRequest) returns (Job) {
@ -44,7 +45,8 @@ service JobController {
  }

  // Submits job to a cluster.
-  rpc SubmitJobAsOperation(SubmitJobRequest) returns (google.longrunning.Operation) {
+  rpc SubmitJobAsOperation(SubmitJobRequest)
+      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/projects/{project_id}/regions/{region}/jobs:submitAsOperation"
      body: "*"
@ -198,7 +200,7 @@ message HadoopJob {
  LoggingConfig logging_config = 8 [(google.api.field_behavior) = OPTIONAL];
 }

-// A Dataproc job for running [Apache Spark](http://spark.apache.org/)
+// A Dataproc job for running [Apache Spark](https://spark.apache.org/)
 // applications on YARN.
 message SparkJob {
  // Required. The specification of the main method to call to drive the job.
@ -323,7 +325,8 @@ message HiveJob {

  // Optional. Mapping of query variable names to values (equivalent to the
  // Hive command: `SET name="value";`).
-  map<string, string> script_variables = 4 [(google.api.field_behavior) = OPTIONAL];
+  map<string, string> script_variables = 4
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. A mapping of property names and values, used to configure Hive.
  // Properties that conflict with values set by the Dataproc API may be
@ -338,7 +341,7 @@ message HiveJob {
 }

 // A Dataproc job for running [Apache Spark
-// SQL](http://spark.apache.org/sql/) queries.
+// SQL](https://spark.apache.org/sql/) queries.
 message SparkSqlJob {
  // Required. The sequence of Spark SQL queries to execute, specified as
  // either an HCFS file URI or as a list of queries.
@ -352,7 +355,8 @@ message SparkSqlJob {

  // Optional. Mapping of query variable names to values (equivalent to the
  // Spark SQL command: SET `name="value";`).
-  map<string, string> script_variables = 3 [(google.api.field_behavior) = OPTIONAL];
+  map<string, string> script_variables = 3
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. A mapping of property names to values, used to configure
  // Spark SQL's SparkConf. Properties that conflict with values set by the
@ -386,7 +390,8 @@ message PigJob {

  // Optional. Mapping of query variable names to values (equivalent to the Pig
  // command: `name=[value]`).
-  map<string, string> script_variables = 4 [(google.api.field_behavior) = OPTIONAL];
+  map<string, string> script_variables = 4
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. A mapping of property names to values, used to configure Pig.
  // Properties that conflict with values set by the Dataproc API may be
@ -480,8 +485,10 @@ message JobPlacement {
  // the job is submitted.
  string cluster_uuid = 2 [(google.api.field_behavior) = OUTPUT_ONLY];

-  // Optional. Cluster labels to identify a cluster where the job will be submitted.
-  map<string, string> cluster_labels = 3 [(google.api.field_behavior) = OPTIONAL];
+  // Optional. Cluster labels to identify a cluster where the job will be
+  // submitted.
+  map<string, string> cluster_labels = 3
+      [(google.api.field_behavior) = OPTIONAL];
 }

 // Dataproc job status.
@ -560,7 +567,8 @@ message JobStatus {
  ];

  // Output only. The time when this state was entered.
-  google.protobuf.Timestamp state_start_time = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
+  google.protobuf.Timestamp state_start_time = 6
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Additional state information, which includes
  // status reported by the agent.
@ -569,8 +577,8 @@ message JobStatus {

 // Encapsulates the full scoping used to reference a job.
 message JobReference {
-  // Optional. The ID of the Google Cloud Platform project that the job belongs to. If
-  // specified, must match the request project ID.
+  // Optional. The ID of the Google Cloud Platform project that the job belongs
+  // to. If specified, must match the request project ID.
  string project_id = 1 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The job ID, which must be unique within the project.
@ -680,22 +688,26 @@ message Job {
  JobStatus status = 8 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The previous job status.
-  repeated JobStatus status_history = 13 [(google.api.field_behavior) = OUTPUT_ONLY];
+  repeated JobStatus status_history = 13
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The collection of YARN applications spun up by this job.
  //
  // **Beta** Feature: This report is available for testing purposes only. It
  // may be changed before final release.
-  repeated YarnApplication yarn_applications = 9 [(google.api.field_behavior) = OUTPUT_ONLY];
+  repeated YarnApplication yarn_applications = 9
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. A URI pointing to the location of the stdout of the job's
  // driver program.
-  string driver_output_resource_uri = 17 [(google.api.field_behavior) = OUTPUT_ONLY];
+  string driver_output_resource_uri = 17
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. If present, the location of miscellaneous control files
  // which may be used as part of job setup and handling. If not present,
  // control files may be placed in the same location as `driver_output_uri`.
-  string driver_control_files_uri = 15 [(google.api.field_behavior) = OUTPUT_ONLY];
+  string driver_control_files_uri = 15
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Optional. The labels to associate with this job.
  // Label **keys** must contain 1 to 63 characters, and must conform to
@ -714,11 +726,24 @@ message Job {
  // may be reused over time.
  string job_uuid = 22 [(google.api.field_behavior) = OUTPUT_ONLY];

-  // Output only. Indicates whether the job is completed. If the value is `false`,
-  // the job is still in progress. If `true`, the job is completed, and
+  // Output only. Indicates whether the job is completed. If the value is
+  // `false`, the job is still in progress. If `true`, the job is completed, and
  // `status.state` field will indicate if it was successful, failed,
  // or cancelled.
  bool done = 24 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Optional. Driver scheduling configuration.
+  DriverSchedulingConfig driver_scheduling_config = 27
+      [(google.api.field_behavior) = OPTIONAL];
+}
+
+// Driver scheduling configuration.
+message DriverSchedulingConfig {
+  // Required. The amount of memory in MB the driver is requesting.
+  int32 memory_mb = 1 [(google.api.field_behavior) = REQUIRED];
+
+  // Required. The number of vCPUs the driver is requesting.
+  int32 vcores = 2 [(google.api.field_behavior) = REQUIRED];
 }

 // Job scheduling options.
@ -727,27 +752,26 @@ message JobScheduling {
  // a result of driver exiting with non-zero code before job is
  // reported failed.
  //
-  // A job may be reported as thrashing if driver exits with non-zero code
-  // 4 times within 10 minute window.
+  // A job may be reported as thrashing if the driver exits with a non-zero code
+  // four times within a 10-minute window.
  //
  // Maximum value is 10.
  //
-  // **Note:** Currently, this restartable job option is
-  // not supported in Dataproc
-  // [workflow
-  // template](https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template)
-  // jobs.
+  // **Note:** This restartable job option is not supported in Dataproc
+  // [workflow templates]
+  // (https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).
  int32 max_failures_per_hour = 1 [(google.api.field_behavior) = OPTIONAL];

-  // Optional. Maximum number of times in total a driver may be restarted as a result of
-  // driver exiting with non-zero code before job is reported failed.
+  // Optional. Maximum total number of times a driver may be restarted as a
+  // result of the driver exiting with a non-zero code. After the maximum number
+  // is reached, the job will be reported as failed.
+  //
  // Maximum value is 240.
  //
  // **Note:** Currently, this restartable job option is
  // not supported in Dataproc
  // [workflow
-  // template](https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template)
-  // jobs.
+  // templates](https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).
  int32 max_failures_total = 2 [(google.api.field_behavior) = OPTIONAL];
 }

@ -790,7 +814,8 @@ message JobMetadata {
  string operation_type = 3 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Job submission time.
-  google.protobuf.Timestamp start_time = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
+  google.protobuf.Timestamp start_time = 4
+      [(google.api.field_behavior) = OUTPUT_ONLY];
 }

 // A request to get the resource representation for a job in a project.
@ -843,7 +868,8 @@ message ListJobsRequest {
  // (default = match ALL jobs).
  //
  // If `filter` is provided, `jobStateMatcher` will be ignored.
-  JobStateMatcher job_state_matcher = 5 [(google.api.field_behavior) = OPTIONAL];
+  JobStateMatcher job_state_matcher = 5
+      [(google.api.field_behavior) = OPTIONAL];

  // Optional. A filter constraining the jobs to list. Filters are
  // case-sensitive and have the following syntax:
@ -883,7 +909,8 @@ message UpdateJobRequest {
  // <code>labels</code>, and the `PATCH` request body would specify the new
  // value. <strong>Note:</strong> Currently, <code>labels</code> is the only
  // field that can be updated.
-  google.protobuf.FieldMask update_mask = 5 [(google.api.field_behavior) = REQUIRED];
+  google.protobuf.FieldMask update_mask = 5
+      [(google.api.field_behavior) = REQUIRED];
 }

 // A list of jobs in a project.
--- a/google/cloud/dataproc/v1/node_groups.proto
+++ b/google/cloud/dataproc/v1/node_groups.proto
@ -0,0 +1,174 @@
+// Copyright 2022 Google LLC
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+syntax = "proto3";
+
+package google.cloud.dataproc.v1;
+
+import "google/api/annotations.proto";
+import "google/api/client.proto";
+import "google/api/field_behavior.proto";
+import "google/api/resource.proto";
+import "google/cloud/dataproc/v1/clusters.proto";
+import "google/longrunning/operations.proto";
+import "google/protobuf/duration.proto";
+
+option go_package = "google.golang.org/genproto/googleapis/cloud/dataproc/v1;dataproc";
+option java_multiple_files = true;
+option java_outer_classname = "NodeGroupsProto";
+option java_package = "com.google.cloud.dataproc.v1";
+option (google.api.resource_definition) = {
+  type: "dataproc.googleapis.com/ClusterRegion"
+  pattern: "projects/{project}/regions/{region}/clusters/{cluster}"
+};
+
+// The `NodeGroupControllerService` provides methods to manage node groups
+// of Compute Engine managed instances.
+service NodeGroupController {
+  option (google.api.default_host) = "dataproc.googleapis.com";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";
+
+  // Creates a node group in a cluster. The returned
+  // [Operation.metadata][google.longrunning.Operation.metadata] is
+  // [NodeGroupOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#nodegroupoperationmetadata).
+  rpc CreateNodeGroup(CreateNodeGroupRequest)
+      returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1/{parent=projects/*/regions/*/clusters/*}/nodeGroups"
+      body: "node_group"
+    };
+    option (google.api.method_signature) = "parent,node_group,node_group_id";
+    option (google.longrunning.operation_info) = {
+      response_type: "NodeGroup"
+      metadata_type: "google.cloud.dataproc.v1.NodeGroupOperationMetadata"
+    };
+  }
+
+  // Resizes a node group in a cluster. The returned
+  // [Operation.metadata][google.longrunning.Operation.metadata] is
+  // [NodeGroupOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#nodegroupoperationmetadata).
+  rpc ResizeNodeGroup(ResizeNodeGroupRequest)
+      returns (google.longrunning.Operation) {
+    option (google.api.http) = {
+      post: "/v1/{name=projects/*/regions/*/clusters/*/nodeGroups/*}:resize"
+      body: "*"
+    };
+    option (google.api.method_signature) = "name,size";
+    option (google.longrunning.operation_info) = {
+      response_type: "NodeGroup"
+      metadata_type: "google.cloud.dataproc.v1.NodeGroupOperationMetadata"
+    };
+  }
+
+  // Gets the resource representation for a node group in a
+  // cluster.
+  rpc GetNodeGroup(GetNodeGroupRequest) returns (NodeGroup) {
+    option (google.api.http) = {
+      get: "/v1/{name=projects/*/regions/*/clusters/*/nodeGroups/*}"
+    };
+    option (google.api.method_signature) = "name";
+  }
+}
+
+// A request to create a node group.
+message CreateNodeGroupRequest {
+  // Required. The parent resource where this node group will be created.
+  // Format: `projects/{project}/regions/{region}/clusters/{cluster}`
+  string parent = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      child_type: "dataproc.googleapis.com/NodeGroup"
+    }
+  ];
+
+  // Required. The node group to create.
+  NodeGroup node_group = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Optional. An optional node group ID. Generated if not specified.
+  //
+  // The ID must contain only letters (a-z, A-Z), numbers (0-9),
+  // underscores (_), and hyphens (-). Cannot begin or end with underscore
+  // or hyphen. Must consist of from 3 to 33 characters.
+  string node_group_id = 4 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. A unique ID used to identify the request. If the server receives
+  // two
+  // [CreateNodeGroupRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.CreateNodeGroupRequests)
+  // with the same ID, the second request is ignored and the
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
+  //
+  // Recommendation: Set this value to a
+  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
+  //
+  // The ID must contain only letters (a-z, A-Z), numbers (0-9),
+  // underscores (_), and hyphens (-). The maximum length is 40 characters.
+  string request_id = 3 [(google.api.field_behavior) = OPTIONAL];
+}
+
+// A request to resize a node group.
+message ResizeNodeGroupRequest {
+  // Required. The name of the node group to resize.
+  // Format:
+  // `projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{nodeGroup}`
+  string name = 1 [(google.api.field_behavior) = REQUIRED];
+
+  // Required. The number of running instances for the node group to maintain.
+  // The group adds or removes instances to maintain the number of instances
+  // specified by this parameter.
+  int32 size = 2 [(google.api.field_behavior) = REQUIRED];
+
+  // Optional. A unique ID used to identify the request. If the server receives
+  // two
+  // [ResizeNodeGroupRequest](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#google.cloud.dataproc.v1.ResizeNodeGroupRequests)
+  // with the same ID, the second request is ignored and the
+  // first [google.longrunning.Operation][google.longrunning.Operation] created
+  // and stored in the backend is returned.
+  //
+  // Recommendation: Set this value to a
+  // [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
+  //
+  // The ID must contain only letters (a-z, A-Z), numbers (0-9),
+  // underscores (_), and hyphens (-). The maximum length is 40 characters.
+  string request_id = 3 [(google.api.field_behavior) = OPTIONAL];
+
+  // Optional. Timeout for graceful YARN decommissioning. [Graceful
+  // decommissioning]
+  // (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/scaling-clusters#graceful_decommissioning)
+  // allows the removal of nodes from the Compute Engine node group
+  // without interrupting jobs in progress. This timeout specifies how long to
+  // wait for jobs in progress to finish before forcefully removing nodes (and
+  // potentially interrupting jobs). Default timeout is 0 (for forceful
+  // decommission), and the maximum allowed timeout is 1 day. (see JSON
+  // representation of
+  // [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).
+  //
+  // Only supported on Dataproc image versions 1.2 and higher.
+  google.protobuf.Duration graceful_decommission_timeout = 4
+      [(google.api.field_behavior) = OPTIONAL];
+}
+
+// A request to get a node group .
+message GetNodeGroupRequest {
+  // Required. The name of the node group to retrieve.
+  // Format:
+  // `projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{nodeGroup}`
+  string name = 1 [
+    (google.api.field_behavior) = REQUIRED,
+    (google.api.resource_reference) = {
+      type: "dataproc.googleapis.com/NodeGroup"
+    }
+  ];
+}
--- a/google/cloud/dataproc/v1/operations.proto
+++ b/google/cloud/dataproc/v1/operations.proto
@ -1,4 +1,4 @@
-// Copyright 2021 Google LLC
+// Copyright 2022 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@ -87,7 +87,8 @@ message ClusterOperationStatus {
  string details = 3 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The time this state was entered.
-  google.protobuf.Timestamp state_start_time = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
+  google.protobuf.Timestamp state_start_time = 4
+      [(google.api.field_behavior) = OUTPUT_ONLY];
 }

 // Metadata describing the operation.
@ -102,7 +103,8 @@ message ClusterOperationMetadata {
  ClusterOperationStatus status = 9 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The previous operation status.
-  repeated ClusterOperationStatus status_history = 10 [(google.api.field_behavior) = OUTPUT_ONLY];
+  repeated ClusterOperationStatus status_history = 10
+      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The operation type.
  string operation_type = 11 [(google.api.field_behavior) = OUTPUT_ONLY];
@ -116,3 +118,49 @@ message ClusterOperationMetadata {
  // Output only. Errors encountered during operation execution.
  repeated string warnings = 14 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
+
+// Metadata describing the node group operation.
+message NodeGroupOperationMetadata {
+  // Operation type for node group resources.
+  enum NodeGroupOperationType {
+    // Node group operation type is unknown.
+    NODE_GROUP_OPERATION_TYPE_UNSPECIFIED = 0;
+
+    // Create node group operation type.
+    CREATE = 1;
+
+    // Update node group operation type.
+    UPDATE = 2;
+
+    // Delete node group operation type.
+    DELETE = 3;
+
+    // Resize node group operation type.
+    RESIZE = 4;
+  }
+
+  // Output only. Node group ID for the operation.
+  string node_group_id = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Cluster UUID associated with the node group operation.
+  string cluster_uuid = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Current operation status.
+  ClusterOperationStatus status = 3 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. The previous operation status.
+  repeated ClusterOperationStatus status_history = 4
+      [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // The operation type.
+  NodeGroupOperationType operation_type = 5;
+
+  // Output only. Short description of operation.
+  string description = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Labels associated with the operation.
+  map<string, string> labels = 7 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Errors encountered during operation execution.
+  repeated string warnings = 8 [(google.api.field_behavior) = OUTPUT_ONLY];
+}