// Copyright 2020 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/shared.proto"; import "google/longrunning/operations.proto"; import "google/protobuf/duration.proto"; import "google/protobuf/field_mask.proto"; import "google/protobuf/timestamp.proto"; option go_package = "google.golang.org/genproto/googleapis/cloud/dataproc/v1;dataproc"; option java_multiple_files = true; option java_outer_classname = "ClustersProto"; option java_package = "com.google.cloud.dataproc.v1"; option (google.api.resource_definition) = { type: "container.googleapis.com/Cluster" pattern: "projects/{project}/locations/{location}/clusters/{cluster}" }; option (google.api.resource_definition) = { type: "metastore.googleapis.com/Service" pattern: "projects/{project}/locations/{location}/services/{service}" }; // The ClusterControllerService provides methods to manage clusters // 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"; // 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) { option (google.api.http) = { post: "/v1/projects/{project_id}/regions/{region}/clusters" body: "cluster" }; option (google.api.method_signature) = "project_id,region,cluster"; option (google.longrunning.operation_info) = { response_type: "Cluster" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } // 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). 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.longrunning.operation_info) = { response_type: "Cluster" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } // Stops a cluster in a project. rpc StopCluster(StopClusterRequest) returns (google.longrunning.Operation) { option (google.api.http) = { post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:stop" body: "*" }; option (google.longrunning.operation_info) = { response_type: "Cluster" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } // Starts a cluster in a project. rpc StartCluster(StartClusterRequest) returns (google.longrunning.Operation) { option (google.api.http) = { post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:start" body: "*" }; option (google.longrunning.operation_info) = { response_type: "Cluster" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } // 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) { option (google.api.http) = { delete: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}" }; option (google.api.method_signature) = "project_id,region,cluster_name"; option (google.longrunning.operation_info) = { response_type: "google.protobuf.Empty" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } // Gets the resource representation for a cluster in a project. rpc GetCluster(GetClusterRequest) returns (Cluster) { option (google.api.http) = { get: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}" }; option (google.api.method_signature) = "project_id,region,cluster_name"; } // Lists all regions/{region}/clusters in a project alphabetically. rpc ListClusters(ListClustersRequest) returns (ListClustersResponse) { option (google.api.http) = { get: "/v1/projects/{project_id}/regions/{region}/clusters" }; option (google.api.method_signature) = "project_id,region"; option (google.api.method_signature) = "project_id,region,filter"; } // Gets cluster diagnostic information. The returned // [Operation.metadata][google.longrunning.Operation.metadata] will be // [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata). // After the operation completes, // [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) { option (google.api.http) = { post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:diagnose" body: "*" }; option (google.api.method_signature) = "project_id,region,cluster_name"; option (google.longrunning.operation_info) = { response_type: "DiagnoseClusterResults" metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata" }; } } // Describes the identifying information, config, and status of // a cluster of Compute Engine instances. 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. string cluster_name = 2 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster config. Note that Dataproc may set // default values, and values may change when clusters are updated. ClusterConfig config = 3 [(google.api.field_behavior) = REQUIRED]; // Optional. The labels to associate with this cluster. // Label **keys** must contain 1 to 63 characters, and must conform to // [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt). // Label **values** may be empty, but, if present, must contain 1 to 63 // characters, and must conform to [RFC // 1035](https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be // associated with a cluster. map labels = 8 [(google.api.field_behavior) = OPTIONAL]; // Output only. Cluster status. 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]; // Output only. A cluster UUID (Unique Universal Identifier). Dataproc // generates this value when it creates the cluster. string cluster_uuid = 6 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. Contains cluster daemon metrics such as HDFS and YARN stats. // // **Beta Feature**: This report is available for testing purposes only. It // may be changed before final release. ClusterMetrics metrics = 9 [(google.api.field_behavior) = OUTPUT_ONLY]; } // The cluster config. message ClusterConfig { // 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, // ASIA, or EU) for your cluster's staging bucket according to the // Compute Engine zone where your cluster is deployed, and then create // and manage this project-level, per-location bucket (see // [Dataproc staging // bucket](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). // **This field requires a Cloud Storage bucket name, not a URI to 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. // **This field requires a Cloud Storage bucket name, not a URI to a Cloud // Storage bucket.** string temp_bucket = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. The shared Compute Engine config settings for // all instances in a cluster. GceClusterConfig gce_cluster_config = 8 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine config settings for // the master instance in a cluster. InstanceGroupConfig master_config = 9 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine config settings for // worker instances in a cluster. InstanceGroupConfig worker_config = 10 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine config settings for // additional worker instances in a cluster. InstanceGroupConfig secondary_worker_config = 12 [(google.api.field_behavior) = OPTIONAL]; // Optional. The config settings for software inside the cluster. SoftwareConfig software_config = 13 [(google.api.field_behavior) = OPTIONAL]; // Optional. Commands to execute on each node after config is // completed. By default, executables are run on master and all worker nodes. // You can test a node's `role` metadata to run an executable on // a master or worker node, as shown below using `curl` (you can also use // `wget`): // // ROLE=$(curl -H Metadata-Flavor:Google // http://metadata/computeMetadata/v1/instance/attributes/dataproc-role) // if [[ "${ROLE}" == 'Master' ]]; then // ... master specific actions ... // else // ... worker specific actions ... // fi 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]; // 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]; // 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]; // 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]; // Optional. BETA. The Kubernetes Engine config for Dataproc clusters deployed to // Kubernetes. Setting this is considered mutually exclusive with Compute // Engine-based options such as `gce_cluster_config`, `master_config`, // `worker_config`, `secondary_worker_config`, and `autoscaling_config`. GkeClusterConfig gke_cluster_config = 21 [(google.api.field_behavior) = OPTIONAL]; } // The GKE config for this cluster. message GkeClusterConfig { // A full, namespace-isolated deployment target for an existing GKE cluster. message NamespacedGkeDeploymentTarget { // Optional. The target GKE cluster to deploy to. // Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}' string target_gke_cluster = 1 [ (google.api.field_behavior) = OPTIONAL, (google.api.resource_reference) = { type: "container.googleapis.com/Cluster" } ]; // Optional. A namespace within the GKE cluster to deploy into. string cluster_namespace = 2 [(google.api.field_behavior) = OPTIONAL]; } // Optional. A target for the deployment. NamespacedGkeDeploymentTarget namespaced_gke_deployment_target = 1 [(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 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. bool enable_http_port_access = 2 [(google.api.field_behavior) = OPTIONAL]; } // Autoscaling Policy config associated with the cluster. message AutoscalingConfig { // Optional. The autoscaling policy used by the cluster. // // Only resource names including projectid and location (region) are valid. // Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]` // * `projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]` // // Note that the policy must be in the same project and Dataproc region. string policy_uri = 1 [(google.api.field_behavior) = OPTIONAL]; } // Encryption settings for the cluster. message EncryptionConfig { // Optional. The Cloud KMS key name to use for PD disk encryption for all // instances in the cluster. string gce_pd_kms_key_name = 1 [(google.api.field_behavior) = OPTIONAL]; } // Common config settings for resources of Compute Engine cluster // instances, applicable to all instances in the cluster. message GceClusterConfig { // `PrivateIpv6GoogleAccess` controls whether and how Dataproc cluster nodes // can communicate with Google Services through gRPC over IPv6. // These values are directly mapped to corresponding values in the // [Compute Engine Instance // 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]. PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED = 0; // Private access to and from Google Services configuration // inherited from the subnetwork configuration. This is the // default Compute Engine behavior. INHERIT_FROM_SUBNETWORK = 1; // Enables outbound private IPv6 access to Google Services from the Dataproc // cluster. OUTBOUND = 2; // Enables bidirectional private IPv6 access between Google Services and the // Dataproc cluster. BIDIRECTIONAL = 3; } // Optional. The zone where the Compute Engine cluster will be located. // On a create request, it is required in the "global" region. If omitted // in a non-global Dataproc region, the service will pick a zone in the // corresponding Compute Engine region. On a get request, zone will // always be present. // // A full URL, partial URI, or short name are valid. Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]` // * `projects/[project_id]/zones/[zone]` // * `us-central1-f` string zone_uri = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine network to be used for machine // communications. Cannot be specified with subnetwork_uri. If neither // `network_uri` nor `subnetwork_uri` is specified, the "default" network of // the project is used, if it exists. Cannot be a "Custom Subnet Network" (see // [Using Subnetworks](https://cloud.google.com/compute/docs/subnetworks) for // more information). // // A full URL, partial URI, or short name are valid. Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default` // * `projects/[project_id]/regions/global/default` // * `default` string network_uri = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine subnetwork to be used for machine // communications. Cannot be specified with network_uri. // // A full URL, partial URI, or short name are valid. Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/subnetworks/sub0` // * `projects/[project_id]/regions/us-east1/subnetworks/sub0` // * `sub0` string subnetwork_uri = 6 [(google.api.field_behavior) = OPTIONAL]; // Optional. If true, all instances in the cluster will only have internal IP // addresses. By default, clusters are not restricted to internal IP // addresses, and will have ephemeral external IP addresses assigned to each // instance. This `internal_ip_only` restriction can only be enabled for // subnetwork enabled networks, and all off-cluster dependencies must be // configured to be accessible without external IP addresses. 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]; // Optional. The [Dataproc service // account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc) // (also see [VM Data Plane // identity](https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity)) // used by Dataproc cluster VM instances to access Google Cloud Platform // services. // // If not specified, the // [Compute Engine default service // account](https://cloud.google.com/compute/docs/access/service-accounts#default_service_account) // is used. string service_account = 8 [(google.api.field_behavior) = OPTIONAL]; // Optional. The URIs of service account scopes to be included in // Compute Engine instances. The following base set of scopes is always // included: // // * https://www.googleapis.com/auth/cloud.useraccounts.readonly // * https://www.googleapis.com/auth/devstorage.read_write // * https://www.googleapis.com/auth/logging.write // // If no scopes are specified, the following defaults are also provided: // // * https://www.googleapis.com/auth/bigquery // * 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]; // The Compute Engine tags to add to all instances (see [Tagging // instances](https://cloud.google.com/compute/docs/label-or-tag-resources#tags)). repeated string tags = 4; // The Compute Engine metadata entries to add to all instances (see // [Project and instance // metadata](https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)). map metadata = 5; // Optional. Reservation Affinity for consuming Zonal reservation. 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]; // 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]; } // Node Group Affinity for clusters using sole-tenant node groups. message NodeGroupAffinity { // Required. The URI of a // sole-tenant [node group // resource](https://cloud.google.com/compute/docs/reference/rest/v1/nodeGroups) // that the cluster will be created on. // // A full URL, partial URI, or node group name are valid. Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-central1-a/nodeGroups/node-group-1` // * `projects/[project_id]/zones/us-central1-a/nodeGroups/node-group-1` // * `node-group-1` string node_group_uri = 1 [(google.api.field_behavior) = REQUIRED]; } // Shielded Instance Config for clusters using [Compute Engine Shielded // VMs](https://cloud.google.com/security/shielded-cloud/shielded-vm). message ShieldedInstanceConfig { // Optional. Defines whether instances have Secure Boot enabled. bool enable_secure_boot = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. Defines whether instances have the vTPM enabled. bool enable_vtpm = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. Defines whether instances have integrity monitoring enabled. bool enable_integrity_monitoring = 3 [(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. enum Preemptibility { // Preemptibility is unspecified, the system will choose the // appropriate setting for each instance group. PREEMPTIBILITY_UNSPECIFIED = 0; // Instances are non-preemptible. // // This option is allowed for all instance groups and is the only valid // value for Master and Worker instance groups. NON_PREEMPTIBLE = 1; // Instances are preemptible. // // This option is allowed only for secondary worker groups. PREEMPTIBLE = 2; } // Optional. The number of VM instances in the instance group. // For [HA // cluster](/dataproc/docs/concepts/configuring-clusters/high-availability) // [master_config](#FIELDS.master_config) groups, **must be set to 3**. // For standard cluster [master_config](#FIELDS.master_config) groups, // **must be set to 1**. int32 num_instances = 1 [(google.api.field_behavior) = OPTIONAL]; // 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]; // Optional. The Compute Engine image resource used for cluster instances. // // The URI can represent an image or image family. // // Image examples: // // * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/[image-id]` // * `projects/[project_id]/global/images/[image-id]` // * `image-id` // // Image family examples. Dataproc will use the most recent // image from the family: // // * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/family/[custom-image-family-name]` // * `projects/[project_id]/global/images/family/[custom-image-family-name]` // // If the URI is unspecified, it will be inferred from // `SoftwareConfig.image_version` or the system default. string image_uri = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Compute Engine machine type used for cluster instances. // // A full URL, partial URI, or short name are valid. Examples: // // * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` // * `projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` // * `n1-standard-2` // // **Auto Zone Exception**: If you are using the Dataproc // [Auto Zone // Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) // feature, you must use the short name of the machine type // resource, for example, `n1-standard-2`. string machine_type_uri = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. Disk option config settings. DiskConfig disk_config = 5 [(google.api.field_behavior) = OPTIONAL]; // Output only. Specifies that this instance group contains preemptible // instances. bool is_preemptible = 6 [(google.api.field_behavior) = OUTPUT_ONLY]; // Optional. Specifies the preemptibility of the instance group. // // The default value for master and worker groups is // `NON_PREEMPTIBLE`. This default cannot be changed. // // The default value for secondary instances is // `PREEMPTIBLE`. Preemptibility preemptibility = 10 [(google.api.field_behavior) = OPTIONAL]; // 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]; // Optional. The Compute Engine accelerator configuration for these // instances. repeated AcceleratorConfig accelerators = 8 [(google.api.field_behavior) = OPTIONAL]; // Optional. Specifies the minimum cpu platform for the Instance Group. // See [Dataproc -> Minimum CPU // Platform](https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu). string min_cpu_platform = 9 [(google.api.field_behavior) = OPTIONAL]; } // Specifies the resources used to actively manage an instance group. message ManagedGroupConfig { // Output only. The name of the Instance Template used for the Managed // Instance Group. 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]; } // Specifies the type and number of accelerator cards attached to the instances // of an instance. See [GPUs on Compute // Engine](https://cloud.google.com/compute/docs/gpus/). message AcceleratorConfig { // Full URL, partial URI, or short name of the accelerator type resource to // expose to this instance. See // [Compute Engine // AcceleratorTypes](https://cloud.google.com/compute/docs/reference/beta/acceleratorTypes). // // Examples: // // * `https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` // * `projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` // * `nvidia-tesla-k80` // // **Auto Zone Exception**: If you are using the Dataproc // [Auto Zone // Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) // feature, you must use the short name of the accelerator type // resource, for example, `nvidia-tesla-k80`. string accelerator_type_uri = 1; // The number of the accelerator cards of this type exposed to this instance. int32 accelerator_count = 2; } // Specifies the config of disk options for a group of VM instances. message DiskConfig { // Optional. Type of the boot disk (default is "pd-standard"). // Valid values: "pd-balanced" (Persistent Disk Balanced Solid State Drive), // "pd-ssd" (Persistent Disk Solid State Drive), // or "pd-standard" (Persistent Disk Hard Disk Drive). // See [Disk types](https://cloud.google.com/compute/docs/disks#disk-types). string boot_disk_type = 3 [(google.api.field_behavior) = OPTIONAL]; // 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). // 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 // data is spread across them, and the boot disk contains only basic // config and installed binaries. int32 num_local_ssds = 2 [(google.api.field_behavior) = OPTIONAL]; } // Specifies an executable to run on a fully configured node and a // timeout period for executable completion. message NodeInitializationAction { // Required. Cloud Storage URI of executable file. string executable_file = 1 [(google.api.field_behavior) = REQUIRED]; // Optional. Amount of time executable has to complete. Default is // 10 minutes (see JSON representation of // [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)). // // 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]; } // The status of a cluster and its instances. message ClusterStatus { // The cluster state. enum State { // The cluster state is unknown. UNKNOWN = 0; // The cluster is being created and set up. It is not ready for use. CREATING = 1; // The cluster is currently running and healthy. It is ready for use. RUNNING = 2; // The cluster encountered an error. It is not ready for use. ERROR = 3; // The cluster is being deleted. It cannot be used. DELETING = 4; // The cluster is being updated. It continues to accept and process jobs. UPDATING = 5; // The cluster is being stopped. It cannot be used. STOPPING = 6; // The cluster is currently stopped. It is not ready for use. STOPPED = 7; // The cluster is being started. It is not ready for use. STARTING = 8; } // The cluster substate. enum Substate { // The cluster substate is unknown. UNSPECIFIED = 0; // The cluster is known to be in an unhealthy state // (for example, critical daemons are not running or HDFS capacity is // exhausted). // // Applies to RUNNING state. UNHEALTHY = 1; // The agent-reported status is out of date (may occur if // Dataproc loses communication with Agent). // // Applies to RUNNING state. STALE_STATUS = 2; } // Output only. The cluster's state. State state = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Optional. Output only. Details of cluster's state. string detail = 2 [ (google.api.field_behavior) = OUTPUT_ONLY, (google.api.field_behavior) = OPTIONAL ]; // 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]; // Output only. Additional state information that includes // status reported by the agent. Substate substate = 4 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Security related configuration, including encryption, Kerberos, etc. message SecurityConfig { // Optional. Kerberos related configuration. KerberosConfig kerberos_config = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. Identity related configuration, including service account based // secure multi-tenancy user mappings. IdentityConfig identity_config = 2 [(google.api.field_behavior) = OPTIONAL]; } // 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. 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]; // Optional. The uri of the KMS key used to encrypt various sensitive // files. string kms_key_uri = 3 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Cloud Storage URI of the keystore file used for SSL // encryption. If not provided, Dataproc will provide a self-signed // certificate. string keystore_uri = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Cloud Storage URI of the truststore file used for SSL // encryption. If not provided, Dataproc will provide a self-signed // certificate. string truststore_uri = 5 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Cloud Storage URI of a KMS encrypted file containing the // password to the user provided keystore. For the self-signed certificate, // this password is generated by Dataproc. string keystore_password_uri = 6 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Cloud Storage URI of a KMS encrypted file containing the // password to the user provided key. For the self-signed certificate, this // password is generated by Dataproc. string key_password_uri = 7 [(google.api.field_behavior) = OPTIONAL]; // Optional. The Cloud Storage URI of a KMS encrypted file containing the // password to the user provided truststore. For the self-signed certificate, // this password is generated by Dataproc. string truststore_password_uri = 8 [(google.api.field_behavior) = OPTIONAL]; // Optional. The remote realm the Dataproc on-cluster KDC will trust, should // the user enable cross realm trust. string cross_realm_trust_realm = 9 [(google.api.field_behavior) = OPTIONAL]; // Optional. The KDC (IP or hostname) for the remote trusted realm in a cross // realm trust relationship. string cross_realm_trust_kdc = 10 [(google.api.field_behavior) = OPTIONAL]; // 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]; // 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]; // Optional. The Cloud Storage URI of a KMS encrypted file containing the // master key of the KDC database. string kdc_db_key_uri = 13 [(google.api.field_behavior) = OPTIONAL]; // Optional. The lifetime of the ticket granting ticket, in hours. // If not specified, or user specifies 0, then default value 10 // will be used. int32 tgt_lifetime_hours = 14 [(google.api.field_behavior) = OPTIONAL]; // Optional. The name of the on-cluster Kerberos realm. // If not specified, the uppercased domain of hostnames will be the realm. string realm = 15 [(google.api.field_behavior) = OPTIONAL]; } // Identity related configuration, including service account based // secure multi-tenancy user mappings. message IdentityConfig { // Required. Map of user to service account. map user_service_account_mapping = 1 [(google.api.field_behavior) = REQUIRED]; } // Specifies the selection and config of software inside the cluster. message SoftwareConfig { // Optional. The version of software inside the cluster. It must be one of the // supported [Dataproc // Versions](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#supported_dataproc_versions), // such as "1.2" (including a subminor version, such as "1.2.29"), or the // ["preview" // version](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#other_versions). // If unspecified, it defaults to the latest Debian version. string image_version = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. The properties to set on daemon config files. // // Property keys are specified in `prefix:property` format, for example // `core:hadoop.tmp.dir`. The following are supported prefixes // and their mappings: // // * capacity-scheduler: `capacity-scheduler.xml` // * core: `core-site.xml` // * distcp: `distcp-default.xml` // * hdfs: `hdfs-site.xml` // * hive: `hive-site.xml` // * mapred: `mapred-site.xml` // * pig: `pig.properties` // * spark: `spark-defaults.conf` // * yarn: `yarn-site.xml` // // For more information, see [Cluster // properties](https://cloud.google.com/dataproc/docs/concepts/cluster-properties). map 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]; } // Specifies the cluster auto-delete schedule configuration. message LifecycleConfig { // Optional. The duration to keep the cluster alive while idling (when no jobs // are running). Passing this threshold will cause the cluster to be // 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]; // 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 // [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)). 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]; } // 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]; } // Specifies a Metastore configuration. message MetastoreConfig { // Required. Resource name of an existing Dataproc Metastore service. // // Example: // // * `projects/[project_id]/locations/[dataproc_region]/services/[service-name]` string dataproc_metastore_service = 1 [ (google.api.field_behavior) = REQUIRED, (google.api.resource_reference) = { type: "metastore.googleapis.com/Service" } ]; } // Contains cluster daemon metrics, such as HDFS and YARN stats. // // **Beta Feature**: This report is available for testing purposes only. It may // be changed before final release. message ClusterMetrics { // The HDFS metrics. map hdfs_metrics = 1; // The YARN metrics. map yarn_metrics = 2; } // A request to create a cluster. message CreateClusterRequest { // Required. The ID of the Google Cloud Platform project that the cluster // belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 3 [(google.api.field_behavior) = REQUIRED]; // 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 // [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. // // It is recommended to always 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 = 4 [(google.api.field_behavior) = OPTIONAL]; } // A request to update a cluster. message UpdateClusterRequest { // Required. The ID of the Google Cloud Platform project the // cluster belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 5 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 2 [(google.api.field_behavior) = REQUIRED]; // Required. The changes to the cluster. Cluster cluster = 3 [(google.api.field_behavior) = REQUIRED]; // Optional. Timeout for graceful YARN decomissioning. Graceful // decommissioning allows removing nodes from the cluster without // interrupting jobs in progress. 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 = 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 // in a cluster to 5, the `update_mask` parameter would be // specified as `config.worker_config.num_instances`, // and the `PATCH` request body would specify the new value, as follows: // // { // "config":{ // "workerConfig":{ // "numInstances":"5" // } // } // } // Similarly, to change the number of preemptible workers in a cluster to 5, // the `update_mask` parameter would be // `config.secondary_worker_config.num_instances`, and the `PATCH` request // body would be set as follows: // // { // "config":{ // "secondaryWorkerConfig":{ // "numInstances":"5" // } // } // } // Note: Currently, only the following fields can be updated: // // // // // // // // // // // // // // // // // // // // // // // //
MaskPurpose
labelsUpdate labels
config.worker_config.num_instancesResize primary worker group
config.secondary_worker_config.num_instancesResize secondary worker group
config.autoscaling_config.policy_uriUse, stop using, or // change autoscaling policies
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. // // It is recommended to always 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 = 7 [(google.api.field_behavior) = OPTIONAL]; } // A request to stop a cluster. message StopClusterRequest { // Required. The ID of the Google Cloud Platform project the // cluster belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 2 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 3 [(google.api.field_behavior) = REQUIRED]; // Optional. Specifying the `cluster_uuid` means the RPC will fail // (with error NOT_FOUND) if a cluster with the specified UUID does not exist. string cluster_uuid = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. A unique id used to identify the request. If the server // 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. // // 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 = 5 [(google.api.field_behavior) = OPTIONAL]; } // A request to start a cluster. message StartClusterRequest { // Required. The ID of the Google Cloud Platform project the // cluster belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 2 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 3 [(google.api.field_behavior) = REQUIRED]; // Optional. Specifying the `cluster_uuid` means the RPC will fail // (with error NOT_FOUND) if a cluster with the specified UUID does not exist. string cluster_uuid = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. A unique id used to identify the request. If the server // 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. // // 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 = 5 [(google.api.field_behavior) = OPTIONAL]; } // A request to delete a cluster. message DeleteClusterRequest { // Required. The ID of the Google Cloud Platform project that the cluster // belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 3 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 2 [(google.api.field_behavior) = REQUIRED]; // Optional. Specifying the `cluster_uuid` means the RPC should fail // (with error NOT_FOUND) if cluster with specified UUID does not exist. string cluster_uuid = 4 [(google.api.field_behavior) = OPTIONAL]; // Optional. A unique id used to identify the request. If the server // 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. // // It is recommended to always 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 = 5 [(google.api.field_behavior) = OPTIONAL]; } // Request to get the resource representation for a cluster in a project. message GetClusterRequest { // Required. The ID of the Google Cloud Platform project that the cluster // belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 3 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 2 [(google.api.field_behavior) = REQUIRED]; } // A request to list the clusters in a project. message ListClustersRequest { // Required. The ID of the Google Cloud Platform project that the cluster // belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 4 [(google.api.field_behavior) = REQUIRED]; // Optional. A filter constraining the clusters to list. Filters are // case-sensitive and have the following syntax: // // field = value [AND [field = value]] ... // // where **field** is one of `status.state`, `clusterName`, or `labels.[KEY]`, // and `[KEY]` is a label key. **value** can be `*` to match all values. // `status.state` can be one of the following: `ACTIVE`, `INACTIVE`, // `CREATING`, `RUNNING`, `ERROR`, `DELETING`, or `UPDATING`. `ACTIVE` // contains the `CREATING`, `UPDATING`, and `RUNNING` states. `INACTIVE` // contains the `DELETING` and `ERROR` states. // `clusterName` is the name of the cluster provided at creation time. // Only the logical `AND` operator is supported; space-separated items are // treated as having an implicit `AND` operator. // // Example filter: // // status.state = ACTIVE AND clusterName = mycluster // AND labels.env = staging AND labels.starred = * string filter = 5 [(google.api.field_behavior) = OPTIONAL]; // Optional. The standard List page size. int32 page_size = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. The standard List page token. string page_token = 3 [(google.api.field_behavior) = OPTIONAL]; } // The list of all clusters in a project. message ListClustersResponse { // Output only. The clusters in the project. repeated Cluster clusters = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; // Output only. This token is included in the response if there are more // results to fetch. To fetch additional results, provide this value as the // `page_token` in a subsequent `ListClustersRequest`. string next_page_token = 2 [(google.api.field_behavior) = OUTPUT_ONLY]; } // A request to collect cluster diagnostic information. message DiagnoseClusterRequest { // Required. The ID of the Google Cloud Platform project that the cluster // belongs to. string project_id = 1 [(google.api.field_behavior) = REQUIRED]; // Required. The Dataproc region in which to handle the request. string region = 3 [(google.api.field_behavior) = REQUIRED]; // Required. The cluster name. string cluster_name = 2 [(google.api.field_behavior) = REQUIRED]; } // The location of diagnostic output. message DiagnoseClusterResults { // Output only. The Cloud Storage URI of the diagnostic output. // The output report is a plain text file with a summary of collected // diagnostics. string output_uri = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; } // Reservation Affinity for consuming Zonal reservation. message ReservationAffinity { // Indicates whether to consume capacity from an reservation or not. enum Type { TYPE_UNSPECIFIED = 0; // Do not consume from any allocated capacity. NO_RESERVATION = 1; // Consume any reservation available. ANY_RESERVATION = 2; // Must consume from a specific reservation. Must specify key value fields // for specifying the reservations. SPECIFIC_RESERVATION = 3; } // Optional. Type of reservation to consume Type consume_reservation_type = 1 [(google.api.field_behavior) = OPTIONAL]; // Optional. Corresponds to the label key of reservation resource. string key = 2 [(google.api.field_behavior) = OPTIONAL]; // Optional. Corresponds to the label values of reservation resource. repeated string values = 3 [(google.api.field_behavior) = OPTIONAL]; }