googleapis
Version:
Google APIs Client Library for Node.js
936 lines • 401 kB
TypeScript
/// <reference types="node" />
import { OAuth2Client, JWT, Compute, UserRefreshClient, BaseExternalAccountClient, GaxiosPromise, GoogleConfigurable, MethodOptions, StreamMethodOptions, GlobalOptions, GoogleAuth, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { Readable } from 'stream';
export declare namespace dataproc_v1beta2 {
export interface Options extends GlobalOptions {
version: 'v1beta2';
}
interface StandardParameters {
/**
* Auth client or API Key for the request
*/
auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient | BaseExternalAccountClient | GoogleAuth;
/**
* V1 error format.
*/
'$.xgafv'?: string;
/**
* OAuth access token.
*/
access_token?: string;
/**
* Data format for response.
*/
alt?: string;
/**
* JSONP
*/
callback?: string;
/**
* Selector specifying which fields to include in a partial response.
*/
fields?: string;
/**
* API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
*/
key?: string;
/**
* OAuth 2.0 token for the current user.
*/
oauth_token?: string;
/**
* Returns response with indentations and line breaks.
*/
prettyPrint?: boolean;
/**
* Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
*/
quotaUser?: string;
/**
* Legacy upload protocol for media (e.g. "media", "multipart").
*/
uploadType?: string;
/**
* Upload protocol for media (e.g. "raw", "multipart").
*/
upload_protocol?: string;
}
/**
* Cloud Dataproc API
*
* Manages Hadoop-based clusters and jobs on Google Cloud Platform.
*
* @example
* ```js
* const {google} = require('googleapis');
* const dataproc = google.dataproc('v1beta2');
* ```
*/
export class Dataproc {
context: APIRequestContext;
projects: Resource$Projects;
constructor(options: GlobalOptions, google?: GoogleConfigurable);
}
/**
* Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/)).
*/
export interface Schema$AcceleratorConfig {
/**
* The number of the accelerator cards of this type exposed to this instance.
*/
acceleratorCount?: number | null;
/**
* Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See Compute Engine AcceleratorTypes (https://cloud.google.com/compute/docs/reference/beta/acceleratorTypes)Examples * https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * nvidia-tesla-k80Auto Zone Exception: If you are using the Dataproc Auto Zone Placement (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the accelerator type resource, for example, nvidia-tesla-k80.
*/
acceleratorTypeUri?: string | null;
}
/**
* Autoscaling Policy config associated with the cluster.
*/
export interface Schema$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.
*/
policyUri?: string | null;
}
/**
* Describes an autoscaling policy for Dataproc cluster autoscaler.
*/
export interface Schema$AutoscalingPolicy {
basicAlgorithm?: Schema$BasicAutoscalingAlgorithm;
/**
* Required. The policy id.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 between 3 and 50 characters.
*/
id?: string | null;
/**
* Output only. The "resource name" of the autoscaling policy, as described in https://cloud.google.com/apis/design/resource_names. For projects.regions.autoscalingPolicies, the resource name of the policy has the following format: projects/{project_id\}/regions/{region\}/autoscalingPolicies/{policy_id\} For projects.locations.autoscalingPolicies, the resource name of the policy has the following format: projects/{project_id\}/locations/{location\}/autoscalingPolicies/{policy_id\}
*/
name?: string | null;
/**
* Optional. Describes how the autoscaler will operate for secondary workers.
*/
secondaryWorkerConfig?: Schema$InstanceGroupAutoscalingPolicyConfig;
/**
* Required. Describes how the autoscaler will operate for primary workers.
*/
workerConfig?: Schema$InstanceGroupAutoscalingPolicyConfig;
}
/**
* Basic algorithm for autoscaling.
*/
export interface Schema$BasicAutoscalingAlgorithm {
/**
* Optional. Duration between scaling events. A scaling period starts after the update operation from the previous event has completed.Bounds: 2m, 1d. Default: 2m.
*/
cooldownPeriod?: string | null;
/**
* Optional. YARN autoscaling configuration.
*/
yarnConfig?: Schema$BasicYarnAutoscalingConfig;
}
/**
* Basic autoscaling configurations for YARN.
*/
export interface Schema$BasicYarnAutoscalingConfig {
/**
* Required. Timeout for YARN graceful decommissioning of Node Managers. Specifies the duration to wait for jobs to complete before forcefully removing workers (and potentially interrupting jobs). Only applicable to downscaling operations.Bounds: 0s, 1d.
*/
gracefulDecommissionTimeout?: string | null;
/**
* Required. Fraction of average YARN pending memory in the last cooldown period for which to remove workers. A scale-down factor of 1 will result in scaling down so that there is no available memory remaining after the update (more aggressive scaling). A scale-down factor of 0 disables removing workers, which can be beneficial for autoscaling a single job. See How autoscaling works for more information.Bounds: 0.0, 1.0.
*/
scaleDownFactor?: number | null;
/**
* Optional. Minimum scale-down threshold as a fraction of total cluster size before scaling occurs. For example, in a 20-worker cluster, a threshold of 0.1 means the autoscaler must recommend at least a 2 worker scale-down for the cluster to scale. A threshold of 0 means the autoscaler will scale down on any recommended change.Bounds: 0.0, 1.0. Default: 0.0.
*/
scaleDownMinWorkerFraction?: number | null;
/**
* Required. Fraction of average YARN pending memory in the last cooldown period for which to add workers. A scale-up factor of 1.0 will result in scaling up so that there is no pending memory remaining after the update (more aggressive scaling). A scale-up factor closer to 0 will result in a smaller magnitude of scaling up (less aggressive scaling). See How autoscaling works for more information.Bounds: 0.0, 1.0.
*/
scaleUpFactor?: number | null;
/**
* Optional. Minimum scale-up threshold as a fraction of total cluster size before scaling occurs. For example, in a 20-worker cluster, a threshold of 0.1 means the autoscaler must recommend at least a 2-worker scale-up for the cluster to scale. A threshold of 0 means the autoscaler will scale up on any recommended change.Bounds: 0.0, 1.0. Default: 0.0.
*/
scaleUpMinWorkerFraction?: number | null;
}
/**
* Associates members with a role.
*/
export interface Schema$Binding {
/**
* The condition that is associated with this binding.If the condition evaluates to true, then this binding applies to the current request.If the condition evaluates to false, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the members in this binding.To learn which resources support conditions in their IAM policies, see the IAM documentation (https://cloud.google.com/iam/help/conditions/resource-policies).
*/
condition?: Schema$Expr;
/**
* Specifies the identities requesting access for a Cloud Platform resource. members can have the following values: allUsers: A special identifier that represents anyone who is on the internet; with or without a Google account. allAuthenticatedUsers: A special identifier that represents anyone who is authenticated with a Google account or a service account. user:{emailid\}: An email address that represents a specific Google account. For example, alice@example.com . serviceAccount:{emailid\}: An email address that represents a service account. For example, my-other-app@appspot.gserviceaccount.com. group:{emailid\}: An email address that represents a Google group. For example, admins@example.com. deleted:user:{emailid\}?uid={uniqueid\}: An email address (plus unique identifier) representing a user that has been recently deleted. For example, alice@example.com?uid=123456789012345678901. If the user is recovered, this value reverts to user:{emailid\} and the recovered user retains the role in the binding. deleted:serviceAccount:{emailid\}?uid={uniqueid\}: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901. If the service account is undeleted, this value reverts to serviceAccount:{emailid\} and the undeleted service account retains the role in the binding. deleted:group:{emailid\}?uid={uniqueid\}: An email address (plus unique identifier) representing a Google group that has been recently deleted. For example, admins@example.com?uid=123456789012345678901. If the group is recovered, this value reverts to group:{emailid\} and the recovered group retains the role in the binding. domain:{domain\}: The G Suite domain (primary) that represents all the users of that domain. For example, google.com or example.com.
*/
members?: string[] | null;
/**
* Role that is assigned to members. For example, roles/viewer, roles/editor, or roles/owner.
*/
role?: string | null;
}
/**
* A request to cancel a job.
*/
export interface Schema$CancelJobRequest {
}
/**
* Describes the identifying information, config, and status of a cluster of Compute Engine instances.
*/
export interface Schema$Cluster {
/**
* Required. The cluster name. Cluster names within a project must be unique. Names of deleted clusters can be reused.
*/
clusterName?: string | null;
/**
* Output only. A cluster UUID (Unique Universal Identifier). Dataproc generates this value when it creates the cluster.
*/
clusterUuid?: string | null;
/**
* Required. The cluster config. Note that Dataproc may set default values, and values may change when clusters are updated.
*/
config?: Schema$ClusterConfig;
/**
* 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.
*/
labels?: {
[key: string]: string;
} | null;
/**
* 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.
*/
metrics?: Schema$ClusterMetrics;
/**
* Required. The Google Cloud Platform project ID that the cluster belongs to.
*/
projectId?: string | null;
/**
* Output only. Cluster status.
*/
status?: Schema$ClusterStatus;
/**
* Output only. The previous cluster status.
*/
statusHistory?: Schema$ClusterStatus[];
}
/**
* The cluster config.
*/
export interface Schema$ClusterConfig {
/**
* Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
*/
autoscalingConfig?: Schema$AutoscalingConfig;
/**
* Optional. A Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, Cloud Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see Dataproc staging bucket (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.
*/
configBucket?: string | null;
/**
* Optional. Encryption settings for the cluster.
*/
encryptionConfig?: Schema$EncryptionConfig;
/**
* Optional. Port/endpoint configuration for this cluster
*/
endpointConfig?: Schema$EndpointConfig;
/**
* Optional. The shared Compute Engine config settings for all instances in a cluster.
*/
gceClusterConfig?: Schema$GceClusterConfig;
/**
* Optional. 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?: Schema$GkeClusterConfig;
/**
* Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's role metadata to run an executable on a master or worker node, as shown below using curl (you can also use wget): ROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1beta2/instance/attributes/dataproc-role) if [[ "${ROLE\}" == 'Master' ]]; then ... master specific actions ... else ... worker specific actions ... fi
*/
initializationActions?: Schema$NodeInitializationAction[];
/**
* Optional. The config setting for auto delete cluster schedule.
*/
lifecycleConfig?: Schema$LifecycleConfig;
/**
* Optional. The Compute Engine config settings for the master instance in a cluster.
*/
masterConfig?: Schema$InstanceGroupConfig;
/**
* Optional. Metastore configuration.
*/
metastoreConfig?: Schema$MetastoreConfig;
/**
* Optional. The Compute Engine config settings for additional worker instances in a cluster.
*/
secondaryWorkerConfig?: Schema$InstanceGroupConfig;
/**
* Optional. Security related configuration.
*/
securityConfig?: Schema$SecurityConfig;
/**
* Optional. The config settings for software inside the cluster.
*/
softwareConfig?: Schema$SoftwareConfig;
/**
* 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.
*/
tempBucket?: string | null;
/**
* Optional. The Compute Engine config settings for worker instances in a cluster.
*/
workerConfig?: Schema$InstanceGroupConfig;
}
/**
* Contains cluster daemon metrics, such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
*/
export interface Schema$ClusterMetrics {
/**
* The HDFS metrics.
*/
hdfsMetrics?: {
[key: string]: string;
} | null;
/**
* The YARN metrics.
*/
yarnMetrics?: {
[key: string]: string;
} | null;
}
/**
* The cluster operation triggered by a workflow.
*/
export interface Schema$ClusterOperation {
/**
* Output only. Indicates the operation is done.
*/
done?: boolean | null;
/**
* Output only. Error, if operation failed.
*/
error?: string | null;
/**
* Output only. The id of the cluster operation.
*/
operationId?: string | null;
}
/**
* Metadata describing the operation.
*/
export interface Schema$ClusterOperationMetadata {
/**
* Output only. Name of the cluster for the operation.
*/
clusterName?: string | null;
/**
* Output only. Cluster UUID for the operation.
*/
clusterUuid?: string | null;
/**
* Output only. Short description of operation.
*/
description?: string | null;
/**
* Output only. Labels associated with the operation
*/
labels?: {
[key: string]: string;
} | null;
/**
* Output only. The operation type.
*/
operationType?: string | null;
/**
* Output only. Current operation status.
*/
status?: Schema$ClusterOperationStatus;
/**
* Output only. The previous operation status.
*/
statusHistory?: Schema$ClusterOperationStatus[];
/**
* Output only. Errors encountered during operation execution.
*/
warnings?: string[] | null;
}
/**
* The status of the operation.
*/
export interface Schema$ClusterOperationStatus {
/**
* Output only. A message containing any operation metadata details.
*/
details?: string | null;
/**
* Output only. A message containing the detailed operation state.
*/
innerState?: string | null;
/**
* Output only. A message containing the operation state.
*/
state?: string | null;
/**
* Output only. The time this state was entered.
*/
stateStartTime?: string | null;
}
/**
* A selector that chooses target cluster for jobs based on metadata.
*/
export interface Schema$ClusterSelector {
/**
* Required. The cluster labels. Cluster must have all labels to match.
*/
clusterLabels?: {
[key: string]: string;
} | null;
/**
* Optional. The zone where workflow process executes. This parameter does not affect the selection of the cluster.If unspecified, the zone of the first cluster matching the selector is used.
*/
zone?: string | null;
}
/**
* The status of a cluster and its instances.
*/
export interface Schema$ClusterStatus {
/**
* Output only. Optional details of cluster's state.
*/
detail?: string | null;
/**
* Output only. The cluster's state.
*/
state?: string | null;
/**
* Output only. Time when this state was entered (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).
*/
stateStartTime?: string | null;
/**
* Output only. Additional state information that includes status reported by the agent.
*/
substate?: string | null;
}
/**
* A request to collect cluster diagnostic information.
*/
export interface Schema$DiagnoseClusterRequest {
}
/**
* The location of diagnostic output.
*/
export interface Schema$DiagnoseClusterResults {
/**
* Output only. The Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics.
*/
outputUri?: string | null;
}
/**
* Specifies the config of disk options for a group of VM instances.
*/
export interface Schema$DiskConfig {
/**
* Optional. Size in GB of the boot disk (default is 500GB).
*/
bootDiskSizeGb?: number | null;
/**
* 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).
*/
bootDiskType?: string | null;
/**
* 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.
*/
numLocalSsds?: number | null;
}
/**
* A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); \} The JSON representation for Empty is empty JSON object {\}.
*/
export interface Schema$Empty {
}
/**
* Encryption settings for the cluster.
*/
export interface Schema$EncryptionConfig {
/**
* Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
*/
gcePdKmsKeyName?: string | null;
}
/**
* Endpoint config for this cluster
*/
export interface Schema$EndpointConfig {
/**
* Optional. If true, enable http access to specific ports on the cluster from external sources. Defaults to false.
*/
enableHttpPortAccess?: boolean | null;
/**
* Output only. The map of port descriptions to URLs. Will only be populated if enable_http_port_access is true.
*/
httpPorts?: {
[key: string]: string;
} | null;
}
/**
* Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec.Example (Comparison): title: "Summary size limit" description: "Determines if a summary is less than 100 chars" expression: "document.summary.size() < 100" Example (Equality): title: "Requestor is owner" description: "Determines if requestor is the document owner" expression: "document.owner == request.auth.claims.email" Example (Logic): title: "Public documents" description: "Determine whether the document should be publicly visible" expression: "document.type != 'private' && document.type != 'internal'" Example (Data Manipulation): title: "Notification string" description: "Create a notification string with a timestamp." expression: "'New message received at ' + string(document.create_time)" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information.
*/
export interface Schema$Expr {
/**
* Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
*/
description?: string | null;
/**
* Textual representation of an expression in Common Expression Language syntax.
*/
expression?: string | null;
/**
* Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
*/
location?: string | null;
/**
* Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.
*/
title?: string | null;
}
/**
* Common config settings for resources of Compute Engine cluster instances, applicable to all instances in the cluster.
*/
export interface Schema$GceClusterConfig {
/**
* Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This internal_ip_only restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.
*/
internalIpOnly?: boolean | null;
/**
* The Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).
*/
metadata?: {
[key: string]: string;
} | null;
/**
* Optional. The Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither network_uri nor subnetwork_uri is specified, the "default" network of the project is used, if it exists. Cannot be a "Custom Subnet Network" (see Using Subnetworks (https://cloud.google.com/compute/docs/subnetworks) for more information).A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default projects/[project_id]/regions/global/default default
*/
networkUri?: string | null;
/**
* Optional. Node Group Affinity for sole-tenant clusters.
*/
nodeGroupAffinity?: Schema$NodeGroupAffinity;
/**
* Optional. The type of IPv6 access for a cluster.
*/
privateIpv6GoogleAccess?: string | null;
/**
* Optional. Reservation Affinity for consuming Zonal reservation.
*/
reservationAffinity?: Schema$ReservationAffinity;
/**
* Optional. The Dataproc service account (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc) (also see VM Data Plane identity (https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity)) used by Dataproc cluster VM instances to access Google Cloud Platform services.If not specified, the Compute Engine default service account (https://cloud.google.com/compute/docs/access/service-accounts#default_service_account) is used.
*/
serviceAccount?: string | null;
/**
* Optional. The URIs of service account scopes to be included in Compute Engine instances. The following base set of scopes is always included: https://www.googleapis.com/auth/cloud.useraccounts.readonly https://www.googleapis.com/auth/devstorage.read_write https://www.googleapis.com/auth/logging.writeIf no scopes are specified, the following defaults are also provided: https://www.googleapis.com/auth/bigquery https://www.googleapis.com/auth/bigtable.admin.table https://www.googleapis.com/auth/bigtable.data https://www.googleapis.com/auth/devstorage.full_control
*/
serviceAccountScopes?: string[] | null;
/**
* Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).
*/
shieldedInstanceConfig?: Schema$ShieldedInstanceConfig;
/**
* 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
*/
subnetworkUri?: string | null;
/**
* The Compute Engine tags to add to all instances (see Tagging instances (https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
*/
tags?: string[] | null;
/**
* 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
*/
zoneUri?: string | null;
}
/**
* Request message for GetIamPolicy method.
*/
export interface Schema$GetIamPolicyRequest {
/**
* OPTIONAL: A GetPolicyOptions object for specifying options to GetIamPolicy.
*/
options?: Schema$GetPolicyOptions;
}
/**
* Encapsulates settings provided to GetIamPolicy.
*/
export interface Schema$GetPolicyOptions {
/**
* Optional. The policy format version to be returned.Valid values are 0, 1, and 3. Requests specifying an invalid value will be rejected.Requests for policies with any conditional bindings must specify version 3. Policies without any conditional bindings may specify any valid value or leave the field unset.To learn which resources support conditions in their IAM policies, see the IAM documentation (https://cloud.google.com/iam/help/conditions/resource-policies).
*/
requestedPolicyVersion?: number | null;
}
/**
* The GKE config for this cluster.
*/
export interface Schema$GkeClusterConfig {
/**
* Optional. A target for the deployment.
*/
namespacedGkeDeploymentTarget?: Schema$NamespacedGkeDeploymentTarget;
}
/**
* A Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html).
*/
export interface Schema$HadoopJob {
/**
* Optional. HCFS URIs of archives to be extracted in the working directory of Hadoop drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, or .zip.
*/
archiveUris?: string[] | null;
/**
* Optional. The arguments to pass to the driver. Do not include arguments, such as -libjars or -Dfoo=bar, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
*/
args?: string[] | null;
/**
* Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
*/
fileUris?: string[] | null;
/**
* Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
*/
jarFileUris?: string[] | null;
/**
* Optional. The runtime log config for job execution.
*/
loggingConfig?: Schema$LoggingConfig;
/**
* The name of the driver's main class. The jar file containing the class must be in the default CLASSPATH or specified in jar_file_uris.
*/
mainClass?: string | null;
/**
* The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
*/
mainJarFileUri?: string | null;
/**
* Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/x-site and classes in user code.
*/
properties?: {
[key: string]: string;
} | null;
}
/**
* A Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN.
*/
export interface Schema$HiveJob {
/**
* Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.
*/
continueOnFailure?: boolean | null;
/**
* Optional. HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
*/
jarFileUris?: string[] | null;
/**
* Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/x-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
*/
properties?: {
[key: string]: string;
} | null;
/**
* The HCFS URI of the script that contains Hive queries.
*/
queryFileUri?: string | null;
/**
* A list of queries.
*/
queryList?: Schema$QueryList;
/**
* Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
*/
scriptVariables?: {
[key: string]: string;
} | null;
}
/**
* A request to inject credentials into a cluster.
*/
export interface Schema$InjectCredentialsRequest {
/**
* Required. The cluster UUID.
*/
clusterUuid?: string | null;
/**
* Required. The encrypted credentials being injected in to the cluster.The client is responsible for encrypting the credentials in a way that is supported by the cluster.A wrapped value is used here so that the actual contents of the encrypted credentials are not written to audit logs.
*/
credentialsCiphertext?: string | null;
}
/**
* Configuration for the size bounds of an instance group, including its proportional size to other groups.
*/
export interface Schema$InstanceGroupAutoscalingPolicyConfig {
/**
* Optional. Maximum number of instances for this group. Required for primary workers. Note that by default, clusters will not use secondary workers. Required for secondary workers if the minimum secondary instances is set.Primary workers - Bounds: [min_instances, ). Required. Secondary workers - Bounds: [min_instances, ). Default: 0.
*/
maxInstances?: number | null;
/**
* Optional. Minimum number of instances for this group.Primary workers - Bounds: 2, max_instances. Default: 2. Secondary workers - Bounds: 0, max_instances. Default: 0.
*/
minInstances?: number | null;
/**
* Optional. Weight for the instance group, which is used to determine the fraction of total workers in the cluster from this instance group. For example, if primary workers have weight 2, and secondary workers have weight 1, the cluster will have approximately 2 primary workers for each secondary worker.The cluster may not reach the specified balance if constrained by min/max bounds or other autoscaling settings. For example, if max_instances for secondary workers is 0, then only primary workers will be added. The cluster can also be out of balance when created.If weight is not set on any instance group, the cluster will default to equal weight for all groups: the cluster will attempt to maintain an equal number of workers in each group within the configured size bounds for each group. If weight is set for one group only, the cluster will default to zero weight on the unset group. For example if weight is set only on primary workers, the cluster will use primary workers only and no secondary workers.
*/
weight?: number | null;
}
/**
* The config settings for Compute Engine resources in an instance group, such as a master or worker group.
*/
export interface Schema$InstanceGroupConfig {
/**
* Optional. The Compute Engine accelerator configuration for these instances.
*/
accelerators?: Schema$AcceleratorConfig[];
/**
* Optional. Disk option config settings.
*/
diskConfig?: Schema$DiskConfig;
/**
* 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-idImage 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.
*/
imageUri?: string | null;
/**
* Output only. The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group.
*/
instanceNames?: string[] | null;
/**
* Output only. List of references to Compute Engine instances.
*/
instanceReferences?: Schema$InstanceReference[];
/**
* Output only. Specifies that this instance group contains preemptible instances.
*/
isPreemptible?: boolean | null;
/**
* Optional. The Compute Engine machine type used for cluster instances.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2 projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2 n1-standard-2Auto Zone Exception: If you are using the Dataproc Auto Zone Placement (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the machine type resource, for example, n1-standard-2.
*/
machineTypeUri?: string | null;
/**
* Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups.
*/
managedGroupConfig?: Schema$ManagedGroupConfig;
/**
* 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).
*/
minCpuPlatform?: string | null;
/**
* Optional. The number of VM instances in the instance group. For HA cluster master_config groups, must be set to 3. For standard cluster master_config groups, must be set to 1.
*/
numInstances?: number | null;
/**
* 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?: string | null;
}
/**
* A reference to a Compute Engine instance.
*/
export interface Schema$InstanceReference {
/**
* The unique identifier of the Compute Engine instance.
*/
instanceId?: string | null;
/**
* The user-friendly name of the Compute Engine instance.
*/
instanceName?: string | null;
/**
* The public key used for sharing data with this instance.
*/
publicKey?: string | null;
}
/**
* A request to instantiate a workflow template.
*/
export interface Schema$InstantiateWorkflowTemplateRequest {
/**
* Deprecated. Please use request_id field instead.
*/
instanceId?: string | null;
/**
* Optional. Map from parameter names to values that should be used for those parameters. Values may not exceed 1000 characters.
*/
parameters?: {
[key: string]: string;
} | null;
/**
* Optional. A tag that prevents multiple concurrent workflow instances with the same tag from running. This mitigates risk of concurrent instances started due to retries.It is recommended to always set this value to a UUID (https://en.wikipedia.org/wiki/Universally_unique_identifier).The tag must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.
*/
requestId?: string | null;
/**
* Optional. The version of workflow template to instantiate. If specified, the workflow will be instantiated only if the current version of the workflow template has the supplied version.This option cannot be used to instantiate a previous version of workflow template.
*/
version?: number | null;
}
/**
* A Dataproc job resource.
*/
export interface Schema$Job {
/**
* Output only. Indicates whether the job is completed. If the value is false, the job is still in progress. If true, the job is completed, and status.state field will indicate if it was successful, failed, or cancelled.
*/
done?: boolean | null;
/**
* Output only. If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.
*/
driverControlFilesUri?: string | null;
/**
* Output only. A URI pointing to the location of the stdout of the job's driver program.
*/
driverOutputResourceUri?: string | null;
/**
* Optional. Job is a Hadoop job.
*/
hadoopJob?: Schema$HadoopJob;
/**
* Optional. Job is a Hive job.
*/
hiveJob?: Schema$HiveJob;
/**
* Output only. A UUID that uniquely identifies a job within the project over time. This is in contrast to a user-settable reference.job_id that may be reused over time.
*/
jobUuid?: string | null;
/**
* Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
*/
labels?: {
[key: string]: string;
} | null;
/**
* Optional. Job is a Pig job.
*/
pigJob?: Schema$PigJob;
/**
* Required. Job information, including how, when, and where to run the job.
*/
placement?: Schema$JobPlacement;
/**
* Optional. Job is a Presto job.
*/
prestoJob?: Schema$PrestoJob;
/**
* Optional. Job is a PySpark job.
*/
pysparkJob?: Schema$PySparkJob;
/**
* Optional. The fully qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a job_id.
*/
reference?: Schema$JobReference;
/**
* Optional. Job scheduling configuration.
*/
scheduling?: Schema$JobScheduling;
/**
* Optional. Job is a Spark job.
*/
sparkJob?: Schema$SparkJob;
/**
* Optional. Job is a SparkR job.
*/
sparkRJob?: Schema$SparkRJob;
/**
* Optional. Job is a SparkSql job.
*/
sparkSqlJob?: Schema$SparkSqlJob;
/**
* Output only. The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
*/
status?: Schema$JobStatus;
/**
* Output only. The previous job status.
*/
statusHistory?: Schema$JobStatus[];
/**
* Output only. The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
*/
submittedBy?: string | null;
/**
* 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.
*/
yarnApplications?: Schema$YarnApplication[];
}
/**
* Job Operation metadata.
*/
export interface Schema$JobMetadata {
/**
* Output only. The job id.
*/
jobId?: string | null;
/**
* Output only. Operation type.
*/
operationType?: string | null;
/**
* Output only. Job submission time.
*/
startTime?: string | null;
/**
* Output only. Most recent job status.
*/
status?: Schema$JobStatus;
}
/**
* Dataproc job config.
*/
export interface Schema$JobPlacement {
/**
* Optional. Cluster labels to identify a cluster where the job will be submitted.
*/
clusterLabels?: {
[key: string]: string;
} | null;
/**
* Required. The name of the cluster where the job will be submitted.
*/
clusterName?: string | null;
/**
* Output only. A cluster UUID generated by the Dataproc service when the job is submitted.
*/
clusterUuid?: string | null;
}
/**
* Encapsulates the full scoping used to reference a job.
*/
export interface Schema$JobReference {
/**
* Optional. The job ID, which must be unique within the project. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or hyphens (-). The maximum length is 100 characters.If not specified by the caller, the job ID will be provided by the server.
*/
jobId?: string | null;
/**
* Optional. The ID of the Google Cloud Platform project that the job belongs to. If specified, must match the request project ID.
*/
projectId?: string | null;
}
/**
* Job scheduling options.
*/
export interface Schema$JobScheduling {
/**
* Optional. Maximum number of times per hour a driver may be restarted as a result of driver terminating 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.Maximum value is 10.
*/
maxFailuresPerHour?: number | null;
/**
* 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. Maximum value is 240.
*/
maxFailuresTotal?: number | null;
}
/**
* Dataproc job status.
*/
export interface Schema$JobStatus {
/**
* Output only. Optional Job state details, such as an error description if the state is ERROR.
*/
details?: string | null;
/**
* Output only. A state message specifying the overall job state.
*/
state?: string | null;
/**
* Output only. The time when this state was entered.
*/
stateStartTime?: string | null;
/**
* Output only. Additional state information, which includes status reported by th