googleapis
Version:
Google APIs Client Library for Node.js
1,054 lines • 226 kB
TypeScript
/**
* Copyright 2019 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.
*/
import { OAuth2Client, JWT, Compute, UserRefreshClient } from 'google-auth-library';
import { GoogleConfigurable, MethodOptions, GlobalOptions, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { GaxiosPromise } from 'gaxios';
export declare namespace dataproc_v1beta2 {
interface Options extends GlobalOptions {
version: 'v1beta2';
}
interface StandardParameters {
/**
* V1 error format.
*/
'$.xgafv'?: string;
/**
* OAuth access token.
*/
access_token?: string;
/**
* Data format for response.
*/
alt?: string;
/**
* JSONP
*/
callback?: string;
/**
* Selector specifying which fields to include in a partial response.
*/
fields?: string;
/**
* API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
*/
key?: string;
/**
* OAuth 2.0 token for the current user.
*/
oauth_token?: string;
/**
* Returns response with indentations and line breaks.
*/
prettyPrint?: boolean;
/**
* Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
*/
quotaUser?: string;
/**
* Legacy upload protocol for media (e.g. "media", "multipart").
*/
uploadType?: string;
/**
* Upload protocol for media (e.g. "raw", "multipart").
*/
upload_protocol?: string;
}
/**
* Cloud Dataproc API
*
* Manages Hadoop-based clusters and jobs on Google Cloud Platform.
*
* @example
* const {google} = require('googleapis');
* const dataproc = google.dataproc('v1beta2');
*
* @namespace dataproc
* @type {Function}
* @version v1beta2
* @variation v1beta2
* @param {object=} options Options for Dataproc
*/
class Dataproc {
context: APIRequestContext;
projects: Resource$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).
*/
interface Schema$AcceleratorConfig {
/**
* The number of the accelerator cards of this type exposed to this instance.
*/
acceleratorCount?: number;
/**
* Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See Compute Engine AcceleratorTypesExamples * https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80 * nvidia-tesla-k80Auto Zone Exception: If you are using the Cloud Dataproc Auto Zone Placement feature, you must use the short name of the accelerator type resource, for example, nvidia-tesla-k80.
*/
acceleratorTypeUri?: string;
}
/**
* Autoscaling Policy config associated with the cluster.
*/
interface Schema$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 Cloud Dataproc region.
*/
policyUri?: string;
}
/**
* Describes an autoscaling policy for Dataproc cluster autoscaler.
*/
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;
/**
* Output only. The "resource name" of the policy, as described in https://cloud.google.com/apis/design/resource_names of the form projects/{project_id}/regions/{region}/autoscalingPolicies/{policy_id}.
*/
name?: string;
/**
* 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.
*/
interface Schema$BasicAutoscalingAlgorithm {
/**
* Optional. Duration between scaling events. A scaling period starts after the update operation from the previous event has completed.Bounds: 2m, 1d. Default: 2m.
*/
cooldownPeriod?: string;
/**
* Required. YARN autoscaling configuration.
*/
yarnConfig?: Schema$BasicYarnAutoscalingConfig;
}
/**
* Basic autoscaling configurations for YARN.
*/
interface Schema$BasicYarnAutoscalingConfig {
/**
* Required. Timeout for YARN graceful decommissioning of Node Managers. Specifies the duration to wait for jobs to complete before forcefully removing workers (and potentially interrupting jobs). Only applicable to downscaling operations.Bounds: 0s, 1d.
*/
gracefulDecommissionTimeout?: string;
/**
* Required. Fraction of average pending memory in the last cooldown period for which to remove workers. A scale-down factor of 1 will result in scaling down so that there is no available memory remaining after the update (more aggressive scaling). A scale-down factor of 0 disables removing workers, which can be beneficial for autoscaling a single job.Bounds: 0.0, 1.0.
*/
scaleDownFactor?: number;
/**
* Optional. Minimum scale-down threshold as a fraction of total cluster size before scaling occurs. For example, in a 20-worker cluster, a threshold of 0.1 means the autoscaler must recommend at least a 2 worker scale-down for the cluster to scale. A threshold of 0 means the autoscaler will scale down on any recommended change.Bounds: 0.0, 1.0. Default: 0.0.
*/
scaleDownMinWorkerFraction?: number;
/**
* Required. Fraction of average pending memory in the last cooldown period for which to add workers. A scale-up factor of 1.0 will result in scaling up so that there is no pending memory remaining after the update (more aggressive scaling). A scale-up factor closer to 0 will result in a smaller magnitude of scaling up (less aggressive scaling).Bounds: 0.0, 1.0.
*/
scaleUpFactor?: number;
/**
* Optional. Minimum scale-up threshold as a fraction of total cluster size before scaling occurs. For example, in a 20-worker cluster, a threshold of 0.1 means the autoscaler must recommend at least a 2-worker scale-up for the cluster to scale. A threshold of 0 means the autoscaler will scale up on any recommended change.Bounds: 0.0, 1.0. Default: 0.0.
*/
scaleUpMinWorkerFraction?: number;
}
/**
* Associates members with a role.
*/
interface Schema$Binding {
/**
* The condition that is associated with this binding. NOTE: An unsatisfied condition will not allow user access via current binding. Different bindings, including their conditions, are examined independently.
*/
condition?: Schema$Expr;
/**
* Specifies the identities requesting access for a Cloud Platform resource. members can have the following values: allUsers: A special identifier that represents anyone who is on the internet; with or without a Google account. allAuthenticatedUsers: A special identifier that represents anyone who is authenticated with a Google account or a service account. user:{emailid}: An email address that represents a specific Google account. For example, alice@gmail.com . serviceAccount:{emailid}: An email address that represents a service account. For example, my-other-app@appspot.gserviceaccount.com. group:{emailid}: An email address that represents a Google group. For example, admins@example.com. domain:{domain}: The G Suite domain (primary) that represents all the users of that domain. For example, google.com or example.com.
*/
members?: string[];
/**
* Role that is assigned to members. For example, roles/viewer, roles/editor, or roles/owner.
*/
role?: string;
}
/**
* A request to cancel a job.
*/
interface Schema$CancelJobRequest {
}
/**
* Describes the identifying information, config, and status of a cluster of Compute Engine instances.
*/
interface Schema$Cluster {
/**
* Required. The cluster name. Cluster names within a project must be unique. Names of deleted clusters can be reused.
*/
clusterName?: string;
/**
* Output only. A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster.
*/
clusterUuid?: string;
/**
* Required. The cluster config. Note that Cloud Dataproc may set default values, and values may change when clusters are updated.
*/
config?: Schema$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;
};
/**
* 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$ClusterMetrics;
/**
* Required. The Google Cloud Platform project ID that the cluster belongs to.
*/
projectId?: string;
/**
* Output only. Cluster status.
*/
status?: Schema$ClusterStatus;
/**
* Output only. The previous cluster status.
*/
statusHistory?: Schema$ClusterStatus[];
}
/**
* The cluster config.
*/
interface Schema$ClusterConfig {
/**
* Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.
*/
autoscalingConfig?: Schema$AutoscalingConfig;
/**
* Optional. A Google Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, Cloud Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see Cloud Dataproc staging bucket).
*/
configBucket?: string;
/**
* Optional. Encryption settings for the cluster.
*/
encryptionConfig?: Schema$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. 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 <code>role</code> 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$InstanceGroupConfig;
/**
* Optional. The Compute Engine config settings for additional worker instances in a cluster.
*/
secondaryWorkerConfig?: Schema$InstanceGroupConfig;
/**
* Optional. Security related configuration.
*/
securityConfig?: Schema$SecurityConfig;
/**
* Optional. The config settings for software inside the cluster.
*/
softwareConfig?: Schema$SoftwareConfig;
/**
* Optional. The Compute Engine config settings for worker instances in a cluster.
*/
workerConfig?: Schema$InstanceGroupConfig;
}
/**
* Contains cluster daemon metrics, such as HDFS and YARN stats.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
*/
interface Schema$ClusterMetrics {
/**
* The HDFS metrics.
*/
hdfsMetrics?: {
[key: string]: string;
};
/**
* The YARN metrics.
*/
yarnMetrics?: {
[key: string]: string;
};
}
/**
* The cluster operation triggered by a workflow.
*/
interface Schema$ClusterOperation {
/**
* Output only. Indicates the operation is done.
*/
done?: boolean;
/**
* Output only. Error, if operation failed.
*/
error?: string;
/**
* Output only. The id of the cluster operation.
*/
operationId?: string;
}
/**
* Metadata describing the operation.
*/
interface Schema$ClusterOperationMetadata {
/**
* Output only. Name of the cluster for the operation.
*/
clusterName?: string;
/**
* Output only. Cluster UUID for the operation.
*/
clusterUuid?: string;
/**
* Output only. Short description of operation.
*/
description?: string;
/**
* Output only. Labels associated with the operation
*/
labels?: {
[key: string]: string;
};
/**
* Output only. The operation type.
*/
operationType?: string;
/**
* 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[];
}
/**
* The status of the operation.
*/
interface Schema$ClusterOperationStatus {
/**
* Output only. A message containing any operation metadata details.
*/
details?: string;
/**
* Output only. A message containing the detailed operation state.
*/
innerState?: string;
/**
* Output only. A message containing the operation state.
*/
state?: string;
/**
* Output only. The time this state was entered.
*/
stateStartTime?: string;
}
/**
* A selector that chooses target cluster for jobs based on metadata.
*/
interface Schema$ClusterSelector {
/**
* Required. The cluster labels. Cluster must have all labels to match.
*/
clusterLabels?: {
[key: string]: string;
};
/**
* 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;
}
/**
* The status of a cluster and its instances.
*/
interface Schema$ClusterStatus {
/**
* Output only. Optional details of cluster's state.
*/
detail?: string;
/**
* Output only. The cluster's state.
*/
state?: string;
/**
* Output only. Time when this state was entered.
*/
stateStartTime?: string;
/**
* Output only. Additional state information that includes status reported by the agent.
*/
substate?: string;
}
/**
* A request to collect cluster diagnostic information.
*/
interface Schema$DiagnoseClusterRequest {
}
/**
* The location of diagnostic output.
*/
interface Schema$DiagnoseClusterResults {
/**
* Output only. The Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics.
*/
outputUri?: string;
}
/**
* Specifies the config of disk options for a group of VM instances.
*/
interface Schema$DiskConfig {
/**
* Optional. Size in GB of the boot disk (default is 500GB).
*/
bootDiskSizeGb?: number;
/**
* Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-ssd" (Persistent Disk Solid State Drive) or "pd-standard" (Persistent Disk Hard Disk Drive).
*/
bootDiskType?: string;
/**
* 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.
*/
numLocalSsds?: number;
}
/**
* 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 {}.
*/
interface Schema$Empty {
}
/**
* Encryption settings for the cluster.
*/
interface Schema$EncryptionConfig {
/**
* Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster.
*/
gcePdKmsKeyName?: string;
}
/**
* Endpoint config for this cluster
*/
interface Schema$EndpointConfig {
/**
* Optional. If true, enable http access to specific ports on the cluster from external sources. Defaults to false.
*/
enableHttpPortAccess?: boolean;
/**
* Output only. The map of port descriptions to URLs. Will only be populated if enable_http_port_access is true.
*/
httpPorts?: {
[key: string]: string;
};
}
/**
* Represents an expression text. Example: title: "User account presence" description: "Determines whether the request has a user account" expression: "size(request.user) > 0"
*/
interface Schema$Expr {
/**
* An 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;
/**
* Textual representation of an expression in Common Expression Language syntax.The application context of the containing message determines which well-known feature set of CEL is supported.
*/
expression?: string;
/**
* An optional string indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
*/
location?: string;
/**
* An 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;
}
/**
* Common config settings for resources of Compute Engine cluster instances, applicable to all instances in the cluster.
*/
interface Schema$GceClusterConfig {
/**
* Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This internal_ip_only restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.
*/
internalIpOnly?: boolean;
/**
* The Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).
*/
metadata?: {
[key: string]: string;
};
/**
* Optional. The Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither network_uri nor subnetwork_uri is specified, the "default" network of the project is used, if it exists. Cannot be a "Custom Subnet Network" (see Using Subnetworks for more information).A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default projects/[project_id]/regions/global/default default
*/
networkUri?: string;
/**
* Optional. Reservation Affinity for consuming Zonal reservation.
*/
reservationAffinity?: Schema$ReservationAffinity;
/**
* Optional. The service account of the instances. Defaults to the default Compute Engine service account. Custom service accounts need permissions equivalent to the following IAM roles: roles/logging.logWriter roles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com
*/
serviceAccount?: string;
/**
* 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[];
/**
* 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;
/**
* The Compute Engine tags to add to all instances (see Tagging instances).
*/
tags?: string[];
/**
* 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 Cloud 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;
}
/**
* Request message for GetIamPolicy method.
*/
interface Schema$GetIamPolicyRequest {
}
/**
* A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html).
*/
interface Schema$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[];
/**
* 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[];
/**
* 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[];
/**
* Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
*/
jarFileUris?: string[];
/**
* Optional. The runtime log config for job execution.
*/
loggingConfig?: Schema$LoggingConfig;
/**
* The name of the driver's main class. The jar file containing the class must be in the default CLASSPATH or specified in jar_file_uris.
*/
mainClass?: string;
/**
* The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
*/
mainJarFileUri?: string;
/**
* Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
*/
properties?: {
[key: string]: string;
};
}
/**
* A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN.
*/
interface Schema$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;
/**
* 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[];
/**
* Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
*/
properties?: {
[key: string]: string;
};
/**
* The HCFS URI of the script that contains Hive queries.
*/
queryFileUri?: string;
/**
* A list of queries.
*/
queryList?: Schema$QueryList;
/**
* Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
*/
scriptVariables?: {
[key: string]: string;
};
}
/**
* Configuration for the size bounds of an instance group, including its proportional size to other groups.
*/
interface Schema$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;
/**
* 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;
/**
* 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;
}
/**
* Optional. The config settings for Compute Engine resources in an instance group, such as a master or worker group.
*/
interface Schema$InstanceGroupConfig {
/**
* Optional. The Compute Engine accelerator configuration for these instances.Beta Feature: This feature is still under development. It may be changed before final release.
*/
accelerators?: Schema$AcceleratorConfig[];
/**
* Optional. Disk option config settings.
*/
diskConfig?: Schema$DiskConfig;
/**
* Optional. The Compute Engine image resource used for cluster instances. It can be specified or may be inferred from SoftwareConfig.image_version.
*/
imageUri?: string;
/**
* Output only. The list of instance names. Cloud Dataproc derives the names from cluster_name, num_instances, and the instance group.
*/
instanceNames?: string[];
/**
* Optional. Specifies that this instance group contains preemptible instances.
*/
isPreemptible?: boolean;
/**
* Optional. The Compute Engine machine type used for cluster instances.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2 projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2 n1-standard-2Auto Zone Exception: If you are using the Cloud Dataproc Auto Zone Placement feature, you must use the short name of the machine type resource, for example, n1-standard-2.
*/
machineTypeUri?: string;
/**
* Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups.
*/
managedGroupConfig?: Schema$ManagedGroupConfig;
/**
* Optional. Specifies the minimum cpu platform for the Instance Group. See Cloud Dataproc&rarr;Minimum CPU Platform.
*/
minCpuPlatform?: string;
/**
* Optional. The number of VM instances in the instance group. For master instance groups, must be set to 1.
*/
numInstances?: number;
}
/**
* A request to instantiate a workflow template.
*/
interface Schema$InstantiateWorkflowTemplateRequest {
/**
* Deprecated. Please use request_id field instead.
*/
instanceId?: string;
/**
* Optional. Map from parameter names to values that should be used for those parameters. Values may not exceed 100 characters.
*/
parameters?: {
[key: string]: string;
};
/**
* Optional. A tag that prevents multiple concurrent workflow instances with the same tag from running. This mitigates risk of concurrent instances started due to retries.It is recommended to always set this value to a UUID (https://en.wikipedia.org/wiki/Universally_unique_identifier).The tag must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). The maximum length is 40 characters.
*/
requestId?: string;
/**
* Optional. The version of workflow template to instantiate. If specified, the workflow will be instantiated only if the current version of the workflow template has the supplied version.This option cannot be used to instantiate a previous version of workflow template.
*/
version?: number;
}
/**
* A Cloud Dataproc job resource.
*/
interface Schema$Job {
/**
* 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;
/**
* Output only. A URI pointing to the location of the stdout of the job's driver program.
*/
driverOutputResourceUri?: string;
/**
* Job is a Hadoop job.
*/
hadoopJob?: Schema$HadoopJob;
/**
* Job is a Hive job.
*/
hiveJob?: Schema$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;
/**
* 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;
};
/**
* Job is a Pig job.
*/
pigJob?: Schema$PigJob;
/**
* Required. Job information, including how, when, and where to run the job.
*/
placement?: Schema$JobPlacement;
/**
* Job is a Presto job
*/
prestoJob?: Schema$PrestoJob;
/**
* Job is a Pyspark job.
*/
pysparkJob?: Schema$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 <code>job_id</code>.
*/
reference?: Schema$JobReference;
/**
* Optional. Job scheduling configuration.
*/
scheduling?: Schema$JobScheduling;
/**
* Job is a Spark job.
*/
sparkJob?: Schema$SparkJob;
/**
* Job is a SparkR job.
*/
sparkRJob?: Schema$SparkRJob;
/**
* Job is a SparkSql job.
*/
sparkSqlJob?: Schema$SparkSqlJob;
/**
* Output only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
*/
status?: Schema$JobStatus;
/**
* Output only. The previous job status.
*/
statusHistory?: Schema$JobStatus[];
/**
* Output only. The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
*/
submittedBy?: string;
/**
* Output only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
*/
yarnApplications?: Schema$YarnApplication[];
}
/**
* Cloud Dataproc job config.
*/
interface Schema$JobPlacement {
/**
* Required. The name of the cluster where the job will be submitted.
*/
clusterName?: string;
/**
* Output only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
*/
clusterUuid?: string;
}
/**
* Encapsulates the full scoping used to reference a job.
*/
interface Schema$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;
/**
* Required. The ID of the Google Cloud Platform project that the job belongs to.
*/
projectId?: string;
}
/**
* Job scheduling options.
*/
interface Schema$JobScheduling {
/**
* Optional. Maximum number of times per hour a driver may be restarted as a result of driver terminating with non-zero code before job is reported failed.A job may be reported as thrashing if driver exits with non-zero code 4 times within 10 minute window.Maximum value is 10.
*/
maxFailuresPerHour?: number;
}
/**
* Cloud Dataproc job status.
*/
interface Schema$JobStatus {
/**
* Output only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
*/
details?: string;
/**
* Output only. A state message specifying the overall job state.
*/
state?: string;
/**
* Output only. The time when this state was entered.
*/
stateStartTime?: string;
/**
* Output only. Additional state information, which includes status reported by the agent.
*/
substate?: string;
}
/**
* Specifies Kerberos related configuration.
*/
interface Schema$KerberosConfig {
/**
* Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
*/
crossRealmTrustAdminServer?: string;
/**
* Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.
*/
crossRealmTrustKdc?: string;
/**
* Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.
*/
crossRealmTrustRealm?: string;
/**
* 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.
*/
crossRealmTrustSharedPasswordUri?: string;
/**
* Optional. Flag to indicate whether to Kerberize the cluster.
*/
enableKerberos?: boolean;
/**
* Optional. The Cloud Storage URI of a KMS encrypted file containing the master key of the KDC database.
*/
kdcDbKeyUri?: string;
/**
* 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.
*/
keyPasswordUri?: string;
/**
* 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.
*/
keystorePasswordUri?: string;
/**
* Optional. The Cloud Storage URI of the keystore file used for SSL encryption. If not provided, Dataproc will provide a self-signed certificate.
*/
keystoreUri?: string;
/**
* Required. The uri of the KMS key used to encrypt various sensitive files.
*/
kmsKeyUri?: string;
/**
* Required. The Cloud Storage URI of a KMS encrypted file containing the root principal password.
*/
rootPrincipalPasswordUri?: string;
/**
* Optional. The lifetime of the ticket granting ticket, in hours. If not specified, or user specifies 0, then default value 10 will be used.
*/
tgtLifetimeHours?: number;
/**
* 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.
*/
truststorePasswordUri?: string;
/**
* Optional. The Cloud Storage URI of the truststore file used for SSL encryption. If not provided, Dataproc will provide a self-signed certificate.
*/
truststoreUri?: string;
}
/**
* Specifies the cluster auto-delete schedule configuration.
*/
interface Schema$LifecycleConfig {
/**
* Optional. The time when cluster will be auto-deleted.
*/
autoDeleteTime?: string;
/**
* Optional. The lifetime duration of cluster. The cluster will be auto-deleted at the end of this period. Valid range: 10m, 14d.Example: "1d", to delete the cluster 1 day after its creation..
*/
autoDeleteTtl?: string;
/**
* Optional. The duration to keep the cluster alive while idling. Passing this threshold will cause the cluster to be deleted. Valid range: 10m, 14d.Example: "10m", the minimum value, to delete the cluster when it has had no jobs running for 10 minutes.
*/
idleDeleteTtl?: string;
}
/**
* A response to a request to list autoscaling policies in a project.
*/
interface Schema$ListAutoscalingPoliciesResponse {
/**
* Output only. This token is included in the response if there are more results to fetch.
*/
nextPageToken?: string;
/**
* Output only. Autoscaling policies list.
*/
policies?: Schema$AutoscalingPolicy[];
}
/**
* The list of all clusters in a project.
*/
interface Schema$ListClustersResponse {
/**
* Output only. The clusters in the project.
*/
clusters?: Schema$Cluster[];
/**
* 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 <code>ListClustersRequest</code>.
*/
nextPageToken?: string;
}
/**
* A list of jobs in a project.
*/
interface Schema$ListJobsResponse {
/**
* Output only. Jobs list.
*/
jobs?: Schema$Job[];
/**
* Optional. 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 <code>ListJobsRequest</code>.
*/
nextPageToken?: string;
}
/**
* The response message for Operations.ListOperations.
*/
interface Schema$ListOperationsResponse {
/**
* The standard List next-page token.
*/
nextPageToken?: string;
/**
* A list of operations that matches the specified filter in the request.
*/
operations?: Schema$Operation[];
}
/**
* A response to a request to list workflow templates in a project.
*/
interface Schema$ListWorkflowTemplatesResponse {
/**
* Output only. This token is included in the response if there are more results to fetch. To fetch additional results, provide this value as the page_token in a subsequent <code>ListWorkflowTemplatesRequest</code>.
*/
nextPageToken?: string;
/**
* Output only. WorkflowTemplates list.
*/
templates?: Schema$WorkflowTemplate[];
}
/**
* The runtime logging config of the job.
*/
interface Schema$LoggingConfig {
/**
* The per-package log levels for the driver. This may include "root" package name to configure rootLogger. Examples: 'com.google = FATAL', 'root = INFO', 'org.apache = DEBUG'
*/
driverLogLevels?: {
[key: string]: string;
};
}
/**
* Cluster that is managed by the workflow.
*/
interface Schema$ManagedCluster {
/**
* Required. The cluster name prefix. A unique cluster name will be formed by appending a random suffix.The name must contain only lower-case letters (a-z), numbers (0-9), and hyphens (-). Must begin with a letter. Cannot begin or end with hyphen. Must consist of between 2 and 35 characters.
*/
clusterName?: string;
/**
* Required. The cluster configuration.
*/
config?: Schema$ClusterConfig;
/**
* Optional. The labels to associate with this cluster.Label keys must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 32 labels can be associated with a given cluster.
*/
labels?: {
[key: string]: string;
};
}
/**
* Specifies the resources used to actively manage an instance group.
*/
interface Schema$ManagedGroupConfig {
/**
* Output only. The name of the Instance Group Manager for this group.
*/
instanceGroupManagerName?: string;
/**
* Output only. The name of the Instance Template used for the Managed Instance Group.
*/
instanceTemplateName?: string;
}
/**
* Specifies an executable to run on a fully configured node and a timeout period for executable completion.
*/
interface Schema$NodeInitializationAction {
/**
* Required. Cloud Storage URI of executable file.
*/
executableFile?: string;
/**
* Optional. Amount of time executable has to complete. Default is 10 minutes. Cluster creation fails with an explanatory error message (the name of the executable that caused the error and the exceeded timeout period) if the executable is not completed at end of the timeout period.
*/
executionTimeout?: string;
}
/**
* This resource represents a long-running operation that is the result of a network API call.
*/
interface Schema$Operation {
/**
* If the value is false, it means the operation is still in progress. If true, the operation is completed, and either error or response is available.
*/
done?: boolean;
/**
* The error result of the operation in case of failure or cancellation.
*/
error?: Schema$Status;
/**
* Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
*/
metadata?: {
[key: string]: any;
};
/**
* The server-assig