1<html><body> 2<style> 3 4body, h1, h2, h3, div, span, p, pre, a { 5 margin: 0; 6 padding: 0; 7 border: 0; 8 font-weight: inherit; 9 font-style: inherit; 10 font-size: 100%; 11 font-family: inherit; 12 vertical-align: baseline; 13} 14 15body { 16 font-size: 13px; 17 padding: 1em; 18} 19 20h1 { 21 font-size: 26px; 22 margin-bottom: 1em; 23} 24 25h2 { 26 font-size: 24px; 27 margin-bottom: 1em; 28} 29 30h3 { 31 font-size: 20px; 32 margin-bottom: 1em; 33 margin-top: 1em; 34} 35 36pre, code { 37 line-height: 1.5; 38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace; 39} 40 41pre { 42 margin-top: 0.5em; 43} 44 45h1, h2, h3, p { 46 font-family: Arial, sans serif; 47} 48 49h1, h2, h3 { 50 border-bottom: solid #CCC 1px; 51} 52 53.toc_element { 54 margin-top: 0.5em; 55} 56 57.firstline { 58 margin-left: 2 em; 59} 60 61.method { 62 margin-top: 1em; 63 border: solid 1px #CCC; 64 padding: 1em; 65 background: #EEE; 66} 67 68.details { 69 font-weight: bold; 70 font-size: 14px; 71} 72 73</style> 74 75<h1><a href="dataproc_v1alpha1.html">Google Cloud Dataproc API</a> . <a href="dataproc_v1alpha1.projects.html">projects</a> . <a href="dataproc_v1alpha1.projects.regions.html">regions</a> . <a href="dataproc_v1alpha1.projects.regions.clusters.html">clusters</a></h1> 76<h2>Instance Methods</h2> 77<p class="toc_element"> 78 <code><a href="#create">create(projectId, region, body, x__xgafv=None)</a></code></p> 79<p class="firstline">Request to create a cluster in a project.</p> 80<p class="toc_element"> 81 <code><a href="#delete">delete(projectId, region, clusterName, x__xgafv=None)</a></code></p> 82<p class="firstline">Request to delete a cluster in a project.</p> 83<p class="toc_element"> 84 <code><a href="#get">get(projectId, region, clusterName, x__xgafv=None)</a></code></p> 85<p class="firstline">Request to get the resource representation for a cluster in a project.</p> 86<p class="toc_element"> 87 <code><a href="#list">list(projectId, region, pageSize=None, filter=None, pageToken=None, x__xgafv=None)</a></code></p> 88<p class="firstline">Request a list of all regions/{region}/clusters in a project.</p> 89<p class="toc_element"> 90 <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p> 91<p class="firstline">Retrieves the next page of results.</p> 92<p class="toc_element"> 93 <code><a href="#patch">patch(projectId, region, clusterName, body, updateMask=None, x__xgafv=None)</a></code></p> 94<p class="firstline">Request to update a cluster in a project.</p> 95<h3>Method Details</h3> 96<div class="method"> 97 <code class="details" id="create">create(projectId, region, body, x__xgafv=None)</code> 98 <pre>Request to create a cluster in a project. 99 100Args: 101 projectId: string, Required The ID of the Google Cloud Platform project that the cluster belongs to. (required) 102 region: string, Required The Dataproc region in which to handle the request. (required) 103 body: object, The request body. (required) 104 The object takes the form of: 105 106{ # Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances. 107 "status": { # The status of a cluster and its instances. # Output-only Cluster status. 108 "state": "A String", # The cluster's state. 109 "stateStartTime": "A String", # Time when this state was entered. 110 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 111 "detail": "A String", # Optional details of cluster's state. 112 }, 113 "configuration": { # The cluster configuration. # Required The cluster configuration. It may differ from a user's initial configuration due to Cloud Dataproc setting of default values and updating clusters. 114 "workerDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of worker node disk options. 115 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 116 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 117 }, 118 "softwareConfiguration": { # Specifies the selection and configuration of software inside the cluster. # Optional The configuration settings for software inside the cluster. 119 "imageVersion": "A String", # Optional The version of software inside the cluster. It must match the regular expression 0-9+.0-9+. If unspecified it will default to latest version. 120 "properties": { # Optional The properties to set on daemon configuration files.Property keys are specified in "prefix:property" format, such as "core:fs.defaultFS". The following are supported prefixes and their mappings: core - core-site.xml hdfs - hdfs-site.xml mapred - mapred-site.xml yarn - yarn-site.xml hive - hive-site.xml pig - pig.properties spark - spark-defaults.conf 121 "a_key": "A String", 122 }, 123 }, 124 "workers": [ # Deprecated The list of worker node names. Dataproc derives the names from cluster_name and num_workers if not set by user (recommended practice is to let Dataproc derive the name). Derived worker node name example: hadoop-w-0. 125 "A String", 126 ], 127 "masterConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for the master instance in a cluster. 128 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 129 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 130 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 131 "A String", 132 ], 133 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 134 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 135 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 136 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 137 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 138 }, 139 ], 140 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 141 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 142 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 143 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 144 }, 145 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 146 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 147 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 148 }, 149 }, 150 "gceClusterConfiguration": { # Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Optional The shared Google Compute Engine configuration settings for all instances in a cluster. 151 "internalIpOnly": True or False, # If true, all instances in the cluser 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 restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses. 152 "networkUri": "A String", # The Google 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 https://cloud.google.com/compute/docs/subnetworks for more information). Example: compute.googleapis.com/projects/[project_id]/regions/global/default. 153 "tags": [ # The Google Compute Engine tags to add to all instances. 154 "A String", 155 ], 156 "serviceAccount": "A String", # Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles: 157 # roles/logging.logWriter 158 # 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 159 "zoneUri": "A String", # Required The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 160 "subnetworkUri": "A String", # The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: compute.googleapis.com/projects/[project_id]/regions/us-east1/sub0. 161 "serviceAccountScopes": [ # The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 162 "A String", 163 ], 164 "metadata": { # The Google Compute Engine metadata entries to add to all instances. 165 "a_key": "A String", 166 }, 167 }, 168 "masterName": "A String", # Deprecated The Master's hostname. Dataproc derives the name from cluster_name if not set by user (recommended practice is to let Dataproc derive the name). Derived master name example: hadoop-m. 169 "configurationBucket": "A String", # Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate 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, then it will create and manage this project-level, per-location bucket for you. 170 "gceConfiguration": { # Deprecated Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Deprecated The Google Compute Engine configuration settings for cluster resources. 171 "machineTypeUri": "A String", # Deprecated The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 172 "networkUri": "A String", # Deprecated The Google Compute Engine network to be used for machine communications. Inbound SSH connections are necessary to complete cluster configuration. Example "compute.googleapis.com/projects/project_id /zones/us-east1-a/default". 173 "zoneUri": "A String", # Deprecated The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 174 "serviceAccountScopes": [ # Deprecated The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 175 "A String", 176 ], 177 "imageUri": "A String", # Deprecated The Google Compute Engine image resource used for cluster instances. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 178 }, 179 "masterDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of master node disk options. 180 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 181 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 182 }, 183 "numWorkers": 42, # Deprecated The number of worker nodes in the cluster. 184 "initializationActions": [ # Optional Commands to execute on each node after configuration 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: 185 # ROLE=$(/usr/share/google/get_metadata_value attributes/role) 186 # if [[ "${ROLE}" == 'Master' ]]; then 187 # ... master specific actions ... 188 # else 189 # ... worker specific actions ... 190 # fi 191 { # Specifies an executable to run on a fully configured node and a timeout period for executable completion. 192 "executionTimeout": "A 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. 193 "executableFile": "A String", # Required Google Cloud Storage URI of executable file. 194 }, 195 ], 196 "secondaryWorkerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for additional worker instances in a cluster. 197 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 198 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 199 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 200 "A String", 201 ], 202 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 203 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 204 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 205 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 206 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 207 }, 208 ], 209 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 210 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 211 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 212 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 213 }, 214 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 215 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 216 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 217 }, 218 }, 219 "workerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for worker instances in a cluster. 220 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 221 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 222 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 223 "A String", 224 ], 225 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 226 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 227 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 228 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 229 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 230 }, 231 ], 232 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 233 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 234 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 235 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 236 }, 237 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 238 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 239 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 240 }, 241 }, 242 }, 243 "clusterUuid": "A String", # Output-only A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster. 244 "clusterName": "A String", # Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused. 245 "projectId": "A String", # Required The Google Cloud Platform project ID that the cluster belongs to. 246 "labels": { # 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 64 labels can be associated with a given cluster. 247 "a_key": "A String", 248 }, 249 "metrics": { # Contains cluster daemon metrics, such as HDFS and YARN stats. # Contains cluster daemon metrics such as HDFS and YARN stats. 250 "yarnMetrics": { # The YARN metrics. 251 "a_key": "A String", 252 }, 253 "hdfsMetrics": { # The HDFS metrics. 254 "a_key": "A String", 255 }, 256 }, 257 "statusHistory": [ # Output-only Previous cluster statuses. 258 { # The status of a cluster and its instances. 259 "state": "A String", # The cluster's state. 260 "stateStartTime": "A String", # Time when this state was entered. 261 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 262 "detail": "A String", # Optional details of cluster's state. 263 }, 264 ], 265 "createTime": "A String", # Output-only The timestamp of cluster creation. 266} 267 268 x__xgafv: string, V1 error format. 269 Allowed values 270 1 - v1 error format 271 2 - v2 error format 272 273Returns: 274 An object of the form: 275 276 { # An asynchronous operation in a project that runs over a given cluster. Used to track the progress of a user request that is running asynchronously. Examples include creating a cluster, updating a cluster, and deleting a cluster. 277 "metadata": { # Service-specific metadata associated with the operation. 278 "a_key": "", # Properties of the object. Contains field @type with type URL. 279 }, 280 "error": { # The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be: # The error result of the operation in case of failure. 281 # Simple to use and understand for most users 282 # Flexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc that can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include: 283 # Partial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors. 284 # Workflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting. 285 # Batch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response. 286 # Asynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message. 287 # Logging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons. 288 "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. 289 "code": 42, # The status code, which should be an enum value of google.rpc.Code. 290 "details": [ # A list of messages that carry the error details. There will be a common set of message types for APIs to use. 291 { 292 "a_key": "", # Properties of the object. Contains field @type with type URL. 293 }, 294 ], 295 }, 296 "done": True or False, # Indicates if the operation is done. If true, the operation is complete and the result is available. If false, the operation is still in progress. 297 "response": { # The operation response. If the called method returns no data on success, the response is google.protobuf.Empty. If the called method is Get,Create or Update, the response is the resource. For all other methods, the response type is a concatenation of the method name and "Response". For example, if the called method is TakeSnapshot(), the response type is TakeSnapshotResponse. 298 "a_key": "", # Properties of the object. Contains field @type with type URL. 299 }, 300 "name": "A String", # The name of the operation resource, in the format projects/project_id/operations/operation_id 301 }</pre> 302</div> 303 304<div class="method"> 305 <code class="details" id="delete">delete(projectId, region, clusterName, x__xgafv=None)</code> 306 <pre>Request to delete a cluster in a project. 307 308Args: 309 projectId: string, Required The ID of the Google Cloud Platform project that the cluster belongs to. (required) 310 region: string, Required The Dataproc region in which to handle the request. (required) 311 clusterName: string, Required The cluster name. (required) 312 x__xgafv: string, V1 error format. 313 Allowed values 314 1 - v1 error format 315 2 - v2 error format 316 317Returns: 318 An object of the form: 319 320 { # An asynchronous operation in a project that runs over a given cluster. Used to track the progress of a user request that is running asynchronously. Examples include creating a cluster, updating a cluster, and deleting a cluster. 321 "metadata": { # Service-specific metadata associated with the operation. 322 "a_key": "", # Properties of the object. Contains field @type with type URL. 323 }, 324 "error": { # The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be: # The error result of the operation in case of failure. 325 # Simple to use and understand for most users 326 # Flexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc that can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include: 327 # Partial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors. 328 # Workflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting. 329 # Batch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response. 330 # Asynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message. 331 # Logging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons. 332 "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. 333 "code": 42, # The status code, which should be an enum value of google.rpc.Code. 334 "details": [ # A list of messages that carry the error details. There will be a common set of message types for APIs to use. 335 { 336 "a_key": "", # Properties of the object. Contains field @type with type URL. 337 }, 338 ], 339 }, 340 "done": True or False, # Indicates if the operation is done. If true, the operation is complete and the result is available. If false, the operation is still in progress. 341 "response": { # The operation response. If the called method returns no data on success, the response is google.protobuf.Empty. If the called method is Get,Create or Update, the response is the resource. For all other methods, the response type is a concatenation of the method name and "Response". For example, if the called method is TakeSnapshot(), the response type is TakeSnapshotResponse. 342 "a_key": "", # Properties of the object. Contains field @type with type URL. 343 }, 344 "name": "A String", # The name of the operation resource, in the format projects/project_id/operations/operation_id 345 }</pre> 346</div> 347 348<div class="method"> 349 <code class="details" id="get">get(projectId, region, clusterName, x__xgafv=None)</code> 350 <pre>Request to get the resource representation for a cluster in a project. 351 352Args: 353 projectId: string, Required The ID of the Google Cloud Platform project that the cluster belongs to. (required) 354 region: string, Required The Dataproc region in which to handle the request. (required) 355 clusterName: string, Required The cluster name. (required) 356 x__xgafv: string, V1 error format. 357 Allowed values 358 1 - v1 error format 359 2 - v2 error format 360 361Returns: 362 An object of the form: 363 364 { # Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances. 365 "status": { # The status of a cluster and its instances. # Output-only Cluster status. 366 "state": "A String", # The cluster's state. 367 "stateStartTime": "A String", # Time when this state was entered. 368 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 369 "detail": "A String", # Optional details of cluster's state. 370 }, 371 "configuration": { # The cluster configuration. # Required The cluster configuration. It may differ from a user's initial configuration due to Cloud Dataproc setting of default values and updating clusters. 372 "workerDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of worker node disk options. 373 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 374 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 375 }, 376 "softwareConfiguration": { # Specifies the selection and configuration of software inside the cluster. # Optional The configuration settings for software inside the cluster. 377 "imageVersion": "A String", # Optional The version of software inside the cluster. It must match the regular expression 0-9+.0-9+. If unspecified it will default to latest version. 378 "properties": { # Optional The properties to set on daemon configuration files.Property keys are specified in "prefix:property" format, such as "core:fs.defaultFS". The following are supported prefixes and their mappings: core - core-site.xml hdfs - hdfs-site.xml mapred - mapred-site.xml yarn - yarn-site.xml hive - hive-site.xml pig - pig.properties spark - spark-defaults.conf 379 "a_key": "A String", 380 }, 381 }, 382 "workers": [ # Deprecated The list of worker node names. Dataproc derives the names from cluster_name and num_workers if not set by user (recommended practice is to let Dataproc derive the name). Derived worker node name example: hadoop-w-0. 383 "A String", 384 ], 385 "masterConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for the master instance in a cluster. 386 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 387 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 388 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 389 "A String", 390 ], 391 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 392 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 393 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 394 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 395 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 396 }, 397 ], 398 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 399 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 400 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 401 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 402 }, 403 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 404 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 405 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 406 }, 407 }, 408 "gceClusterConfiguration": { # Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Optional The shared Google Compute Engine configuration settings for all instances in a cluster. 409 "internalIpOnly": True or False, # If true, all instances in the cluser 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 restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses. 410 "networkUri": "A String", # The Google 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 https://cloud.google.com/compute/docs/subnetworks for more information). Example: compute.googleapis.com/projects/[project_id]/regions/global/default. 411 "tags": [ # The Google Compute Engine tags to add to all instances. 412 "A String", 413 ], 414 "serviceAccount": "A String", # Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles: 415 # roles/logging.logWriter 416 # 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 417 "zoneUri": "A String", # Required The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 418 "subnetworkUri": "A String", # The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: compute.googleapis.com/projects/[project_id]/regions/us-east1/sub0. 419 "serviceAccountScopes": [ # The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 420 "A String", 421 ], 422 "metadata": { # The Google Compute Engine metadata entries to add to all instances. 423 "a_key": "A String", 424 }, 425 }, 426 "masterName": "A String", # Deprecated The Master's hostname. Dataproc derives the name from cluster_name if not set by user (recommended practice is to let Dataproc derive the name). Derived master name example: hadoop-m. 427 "configurationBucket": "A String", # Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate 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, then it will create and manage this project-level, per-location bucket for you. 428 "gceConfiguration": { # Deprecated Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Deprecated The Google Compute Engine configuration settings for cluster resources. 429 "machineTypeUri": "A String", # Deprecated The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 430 "networkUri": "A String", # Deprecated The Google Compute Engine network to be used for machine communications. Inbound SSH connections are necessary to complete cluster configuration. Example "compute.googleapis.com/projects/project_id /zones/us-east1-a/default". 431 "zoneUri": "A String", # Deprecated The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 432 "serviceAccountScopes": [ # Deprecated The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 433 "A String", 434 ], 435 "imageUri": "A String", # Deprecated The Google Compute Engine image resource used for cluster instances. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 436 }, 437 "masterDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of master node disk options. 438 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 439 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 440 }, 441 "numWorkers": 42, # Deprecated The number of worker nodes in the cluster. 442 "initializationActions": [ # Optional Commands to execute on each node after configuration 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: 443 # ROLE=$(/usr/share/google/get_metadata_value attributes/role) 444 # if [[ "${ROLE}" == 'Master' ]]; then 445 # ... master specific actions ... 446 # else 447 # ... worker specific actions ... 448 # fi 449 { # Specifies an executable to run on a fully configured node and a timeout period for executable completion. 450 "executionTimeout": "A 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. 451 "executableFile": "A String", # Required Google Cloud Storage URI of executable file. 452 }, 453 ], 454 "secondaryWorkerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for additional worker instances in a cluster. 455 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 456 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 457 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 458 "A String", 459 ], 460 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 461 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 462 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 463 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 464 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 465 }, 466 ], 467 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 468 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 469 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 470 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 471 }, 472 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 473 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 474 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 475 }, 476 }, 477 "workerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for worker instances in a cluster. 478 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 479 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 480 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 481 "A String", 482 ], 483 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 484 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 485 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 486 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 487 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 488 }, 489 ], 490 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 491 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 492 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 493 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 494 }, 495 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 496 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 497 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 498 }, 499 }, 500 }, 501 "clusterUuid": "A String", # Output-only A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster. 502 "clusterName": "A String", # Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused. 503 "projectId": "A String", # Required The Google Cloud Platform project ID that the cluster belongs to. 504 "labels": { # 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 64 labels can be associated with a given cluster. 505 "a_key": "A String", 506 }, 507 "metrics": { # Contains cluster daemon metrics, such as HDFS and YARN stats. # Contains cluster daemon metrics such as HDFS and YARN stats. 508 "yarnMetrics": { # The YARN metrics. 509 "a_key": "A String", 510 }, 511 "hdfsMetrics": { # The HDFS metrics. 512 "a_key": "A String", 513 }, 514 }, 515 "statusHistory": [ # Output-only Previous cluster statuses. 516 { # The status of a cluster and its instances. 517 "state": "A String", # The cluster's state. 518 "stateStartTime": "A String", # Time when this state was entered. 519 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 520 "detail": "A String", # Optional details of cluster's state. 521 }, 522 ], 523 "createTime": "A String", # Output-only The timestamp of cluster creation. 524 }</pre> 525</div> 526 527<div class="method"> 528 <code class="details" id="list">list(projectId, region, pageSize=None, filter=None, pageToken=None, x__xgafv=None)</code> 529 <pre>Request a list of all regions/{region}/clusters in a project. 530 531Args: 532 projectId: string, Required The ID of the Google Cloud Platform project that the cluster belongs to. (required) 533 region: string, Required The Dataproc region in which to handle the request. (required) 534 pageSize: integer, The standard List page size. 535 filter: string, Optional A filter constraining which clusters to list. Valid filters contain label terms such as: labels.key1 = val1 AND (-labels.k2 = val2 OR labels.k3 = val3) 536 pageToken: string, The standard List page token. 537 x__xgafv: string, V1 error format. 538 Allowed values 539 1 - v1 error format 540 2 - v2 error format 541 542Returns: 543 An object of the form: 544 545 { # The list of all clusters in a project. 546 "nextPageToken": "A String", # The standard List next-page token. 547 "clusters": [ # Output-only The clusters in the project. 548 { # Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances. 549 "status": { # The status of a cluster and its instances. # Output-only Cluster status. 550 "state": "A String", # The cluster's state. 551 "stateStartTime": "A String", # Time when this state was entered. 552 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 553 "detail": "A String", # Optional details of cluster's state. 554 }, 555 "configuration": { # The cluster configuration. # Required The cluster configuration. It may differ from a user's initial configuration due to Cloud Dataproc setting of default values and updating clusters. 556 "workerDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of worker node disk options. 557 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 558 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 559 }, 560 "softwareConfiguration": { # Specifies the selection and configuration of software inside the cluster. # Optional The configuration settings for software inside the cluster. 561 "imageVersion": "A String", # Optional The version of software inside the cluster. It must match the regular expression 0-9+.0-9+. If unspecified it will default to latest version. 562 "properties": { # Optional The properties to set on daemon configuration files.Property keys are specified in "prefix:property" format, such as "core:fs.defaultFS". The following are supported prefixes and their mappings: core - core-site.xml hdfs - hdfs-site.xml mapred - mapred-site.xml yarn - yarn-site.xml hive - hive-site.xml pig - pig.properties spark - spark-defaults.conf 563 "a_key": "A String", 564 }, 565 }, 566 "workers": [ # Deprecated The list of worker node names. Dataproc derives the names from cluster_name and num_workers if not set by user (recommended practice is to let Dataproc derive the name). Derived worker node name example: hadoop-w-0. 567 "A String", 568 ], 569 "masterConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for the master instance in a cluster. 570 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 571 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 572 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 573 "A String", 574 ], 575 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 576 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 577 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 578 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 579 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 580 }, 581 ], 582 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 583 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 584 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 585 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 586 }, 587 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 588 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 589 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 590 }, 591 }, 592 "gceClusterConfiguration": { # Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Optional The shared Google Compute Engine configuration settings for all instances in a cluster. 593 "internalIpOnly": True or False, # If true, all instances in the cluser 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 restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses. 594 "networkUri": "A String", # The Google 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 https://cloud.google.com/compute/docs/subnetworks for more information). Example: compute.googleapis.com/projects/[project_id]/regions/global/default. 595 "tags": [ # The Google Compute Engine tags to add to all instances. 596 "A String", 597 ], 598 "serviceAccount": "A String", # Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles: 599 # roles/logging.logWriter 600 # 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 601 "zoneUri": "A String", # Required The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 602 "subnetworkUri": "A String", # The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: compute.googleapis.com/projects/[project_id]/regions/us-east1/sub0. 603 "serviceAccountScopes": [ # The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 604 "A String", 605 ], 606 "metadata": { # The Google Compute Engine metadata entries to add to all instances. 607 "a_key": "A String", 608 }, 609 }, 610 "masterName": "A String", # Deprecated The Master's hostname. Dataproc derives the name from cluster_name if not set by user (recommended practice is to let Dataproc derive the name). Derived master name example: hadoop-m. 611 "configurationBucket": "A String", # Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate 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, then it will create and manage this project-level, per-location bucket for you. 612 "gceConfiguration": { # Deprecated Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Deprecated The Google Compute Engine configuration settings for cluster resources. 613 "machineTypeUri": "A String", # Deprecated The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 614 "networkUri": "A String", # Deprecated The Google Compute Engine network to be used for machine communications. Inbound SSH connections are necessary to complete cluster configuration. Example "compute.googleapis.com/projects/project_id /zones/us-east1-a/default". 615 "zoneUri": "A String", # Deprecated The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 616 "serviceAccountScopes": [ # Deprecated The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 617 "A String", 618 ], 619 "imageUri": "A String", # Deprecated The Google Compute Engine image resource used for cluster instances. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 620 }, 621 "masterDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of master node disk options. 622 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 623 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 624 }, 625 "numWorkers": 42, # Deprecated The number of worker nodes in the cluster. 626 "initializationActions": [ # Optional Commands to execute on each node after configuration 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: 627 # ROLE=$(/usr/share/google/get_metadata_value attributes/role) 628 # if [[ "${ROLE}" == 'Master' ]]; then 629 # ... master specific actions ... 630 # else 631 # ... worker specific actions ... 632 # fi 633 { # Specifies an executable to run on a fully configured node and a timeout period for executable completion. 634 "executionTimeout": "A 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. 635 "executableFile": "A String", # Required Google Cloud Storage URI of executable file. 636 }, 637 ], 638 "secondaryWorkerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for additional worker instances in a cluster. 639 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 640 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 641 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 642 "A String", 643 ], 644 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 645 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 646 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 647 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 648 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 649 }, 650 ], 651 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 652 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 653 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 654 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 655 }, 656 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 657 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 658 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 659 }, 660 }, 661 "workerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for worker instances in a cluster. 662 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 663 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 664 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 665 "A String", 666 ], 667 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 668 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 669 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 670 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 671 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 672 }, 673 ], 674 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 675 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 676 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 677 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 678 }, 679 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 680 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 681 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 682 }, 683 }, 684 }, 685 "clusterUuid": "A String", # Output-only A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster. 686 "clusterName": "A String", # Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused. 687 "projectId": "A String", # Required The Google Cloud Platform project ID that the cluster belongs to. 688 "labels": { # 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 64 labels can be associated with a given cluster. 689 "a_key": "A String", 690 }, 691 "metrics": { # Contains cluster daemon metrics, such as HDFS and YARN stats. # Contains cluster daemon metrics such as HDFS and YARN stats. 692 "yarnMetrics": { # The YARN metrics. 693 "a_key": "A String", 694 }, 695 "hdfsMetrics": { # The HDFS metrics. 696 "a_key": "A String", 697 }, 698 }, 699 "statusHistory": [ # Output-only Previous cluster statuses. 700 { # The status of a cluster and its instances. 701 "state": "A String", # The cluster's state. 702 "stateStartTime": "A String", # Time when this state was entered. 703 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 704 "detail": "A String", # Optional details of cluster's state. 705 }, 706 ], 707 "createTime": "A String", # Output-only The timestamp of cluster creation. 708 }, 709 ], 710 }</pre> 711</div> 712 713<div class="method"> 714 <code class="details" id="list_next">list_next(previous_request, previous_response)</code> 715 <pre>Retrieves the next page of results. 716 717Args: 718 previous_request: The request for the previous page. (required) 719 previous_response: The response from the request for the previous page. (required) 720 721Returns: 722 A request object that you can call 'execute()' on to request the next 723 page. Returns None if there are no more items in the collection. 724 </pre> 725</div> 726 727<div class="method"> 728 <code class="details" id="patch">patch(projectId, region, clusterName, body, updateMask=None, x__xgafv=None)</code> 729 <pre>Request to update a cluster in a project. 730 731Args: 732 projectId: string, Required The ID of the Google Cloud Platform project the cluster belongs to. (required) 733 region: string, Required The Dataproc region in which to handle the request. (required) 734 clusterName: string, Required The cluster name. (required) 735 body: object, The request body. (required) 736 The object takes the form of: 737 738{ # Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances. 739 "status": { # The status of a cluster and its instances. # Output-only Cluster status. 740 "state": "A String", # The cluster's state. 741 "stateStartTime": "A String", # Time when this state was entered. 742 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 743 "detail": "A String", # Optional details of cluster's state. 744 }, 745 "configuration": { # The cluster configuration. # Required The cluster configuration. It may differ from a user's initial configuration due to Cloud Dataproc setting of default values and updating clusters. 746 "workerDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of worker node disk options. 747 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 748 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 749 }, 750 "softwareConfiguration": { # Specifies the selection and configuration of software inside the cluster. # Optional The configuration settings for software inside the cluster. 751 "imageVersion": "A String", # Optional The version of software inside the cluster. It must match the regular expression 0-9+.0-9+. If unspecified it will default to latest version. 752 "properties": { # Optional The properties to set on daemon configuration files.Property keys are specified in "prefix:property" format, such as "core:fs.defaultFS". The following are supported prefixes and their mappings: core - core-site.xml hdfs - hdfs-site.xml mapred - mapred-site.xml yarn - yarn-site.xml hive - hive-site.xml pig - pig.properties spark - spark-defaults.conf 753 "a_key": "A String", 754 }, 755 }, 756 "workers": [ # Deprecated The list of worker node names. Dataproc derives the names from cluster_name and num_workers if not set by user (recommended practice is to let Dataproc derive the name). Derived worker node name example: hadoop-w-0. 757 "A String", 758 ], 759 "masterConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for the master instance in a cluster. 760 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 761 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 762 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 763 "A String", 764 ], 765 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 766 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 767 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 768 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 769 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 770 }, 771 ], 772 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 773 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 774 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 775 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 776 }, 777 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 778 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 779 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 780 }, 781 }, 782 "gceClusterConfiguration": { # Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Optional The shared Google Compute Engine configuration settings for all instances in a cluster. 783 "internalIpOnly": True or False, # If true, all instances in the cluser 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 restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses. 784 "networkUri": "A String", # The Google 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 https://cloud.google.com/compute/docs/subnetworks for more information). Example: compute.googleapis.com/projects/[project_id]/regions/global/default. 785 "tags": [ # The Google Compute Engine tags to add to all instances. 786 "A String", 787 ], 788 "serviceAccount": "A String", # Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles: 789 # roles/logging.logWriter 790 # 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 791 "zoneUri": "A String", # Required The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 792 "subnetworkUri": "A String", # The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: compute.googleapis.com/projects/[project_id]/regions/us-east1/sub0. 793 "serviceAccountScopes": [ # The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 794 "A String", 795 ], 796 "metadata": { # The Google Compute Engine metadata entries to add to all instances. 797 "a_key": "A String", 798 }, 799 }, 800 "masterName": "A String", # Deprecated The Master's hostname. Dataproc derives the name from cluster_name if not set by user (recommended practice is to let Dataproc derive the name). Derived master name example: hadoop-m. 801 "configurationBucket": "A String", # Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate 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, then it will create and manage this project-level, per-location bucket for you. 802 "gceConfiguration": { # Deprecated Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster. # Deprecated The Google Compute Engine configuration settings for cluster resources. 803 "machineTypeUri": "A String", # Deprecated The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 804 "networkUri": "A String", # Deprecated The Google Compute Engine network to be used for machine communications. Inbound SSH connections are necessary to complete cluster configuration. Example "compute.googleapis.com/projects/project_id /zones/us-east1-a/default". 805 "zoneUri": "A String", # Deprecated The zone where the Google Compute Engine cluster will be located. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a". 806 "serviceAccountScopes": [ # Deprecated The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example "auth.googleapis.com/compute" and "auth.googleapis.com/devstorage.full_control". 807 "A String", 808 ], 809 "imageUri": "A String", # Deprecated The Google Compute Engine image resource used for cluster instances. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 810 }, 811 "masterDiskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Deprecated The configuration settings of master node disk options. 812 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 813 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 814 }, 815 "numWorkers": 42, # Deprecated The number of worker nodes in the cluster. 816 "initializationActions": [ # Optional Commands to execute on each node after configuration 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: 817 # ROLE=$(/usr/share/google/get_metadata_value attributes/role) 818 # if [[ "${ROLE}" == 'Master' ]]; then 819 # ... master specific actions ... 820 # else 821 # ... worker specific actions ... 822 # fi 823 { # Specifies an executable to run on a fully configured node and a timeout period for executable completion. 824 "executionTimeout": "A 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. 825 "executableFile": "A String", # Required Google Cloud Storage URI of executable file. 826 }, 827 ], 828 "secondaryWorkerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for additional worker instances in a cluster. 829 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 830 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 831 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 832 "A String", 833 ], 834 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 835 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 836 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 837 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 838 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 839 }, 840 ], 841 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 842 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 843 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 844 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 845 }, 846 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 847 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 848 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 849 }, 850 }, 851 "workerConfiguration": { # The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group. # Optional The Google Compute Engine configuration settings for worker instances in a cluster. 852 "isPreemptible": True or False, # Specifies that this instance group contains Preemptible Instances. 853 "machineTypeUri": "A String", # The Google Compute Engine machine type used for cluster instances. Example: "compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2". 854 "instanceNames": [ # The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name). 855 "A String", 856 ], 857 "imageUri": "A String", # Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: "compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904". 858 "accelerators": [ # Optional The Google Compute Engine accelerator configuration for these instances. 859 { # Specifies the type and number of accelerator cards attached to the instances of an instance group (see GPUs on Compute Engine). 860 "acceleratorCount": 42, # The number of the accelerator cards of this type exposed to this instance. 861 "acceleratorTypeUri": "A String", # Full or partial URI of the accelerator type resource to expose to this instance. See Google Compute Engine AcceleratorTypes( /compute/docs/reference/beta/acceleratorTypes) 862 }, 863 ], 864 "numInstances": 42, # The number of VM instances in the instance group. For master instance groups, must be set to 1. 865 "diskConfiguration": { # Specifies the configuration of disk options for a group of VM instances. # Disk option configuration settings. 866 "numLocalSsds": 42, # 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 data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries. 867 "bootDiskSizeGb": 42, # Optional Size in GB of the boot disk (default is 500GB). 868 }, 869 "managedGroupConfiguration": { # Specifies the resources used to actively manage an instance group. # Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups. 870 "instanceTemplateName": "A String", # Output-only The name of Instance Template used for Managed Instance Group. 871 "instanceGroupManagerName": "A String", # Output-only The name of Instance Group Manager managing this group. 872 }, 873 }, 874 }, 875 "clusterUuid": "A String", # Output-only A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster. 876 "clusterName": "A String", # Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused. 877 "projectId": "A String", # Required The Google Cloud Platform project ID that the cluster belongs to. 878 "labels": { # 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 64 labels can be associated with a given cluster. 879 "a_key": "A String", 880 }, 881 "metrics": { # Contains cluster daemon metrics, such as HDFS and YARN stats. # Contains cluster daemon metrics such as HDFS and YARN stats. 882 "yarnMetrics": { # The YARN metrics. 883 "a_key": "A String", 884 }, 885 "hdfsMetrics": { # The HDFS metrics. 886 "a_key": "A String", 887 }, 888 }, 889 "statusHistory": [ # Output-only Previous cluster statuses. 890 { # The status of a cluster and its instances. 891 "state": "A String", # The cluster's state. 892 "stateStartTime": "A String", # Time when this state was entered. 893 "substate": "A String", # Output-only Additional state information that includes status reported by the agent. 894 "detail": "A String", # Optional details of cluster's state. 895 }, 896 ], 897 "createTime": "A String", # Output-only The timestamp of cluster creation. 898} 899 900 updateMask: string, Required Specifies the path, relative to <code>Cluster</code>, of the field to update. For example, to change the number of workers in a cluster to 5, the <code>update_mask</code> parameter would be specified as <code>"configuration.worker_configuration.num_instances,"</code> and the PATCH request body would specify the new value, as follows: 901{ 902 "configuration":{ 903 "workerConfiguration":{ 904 "numInstances":"5" 905 } 906 } 907} 908<strong>Note:</strong> Currently, <code>configuration.worker_configuration.num_instances</code> is the only field that can be updated. 909 x__xgafv: string, V1 error format. 910 Allowed values 911 1 - v1 error format 912 2 - v2 error format 913 914Returns: 915 An object of the form: 916 917 { # An asynchronous operation in a project that runs over a given cluster. Used to track the progress of a user request that is running asynchronously. Examples include creating a cluster, updating a cluster, and deleting a cluster. 918 "metadata": { # Service-specific metadata associated with the operation. 919 "a_key": "", # Properties of the object. Contains field @type with type URL. 920 }, 921 "error": { # The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be: # The error result of the operation in case of failure. 922 # Simple to use and understand for most users 923 # Flexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc that can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include: 924 # Partial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors. 925 # Workflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting. 926 # Batch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response. 927 # Asynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message. 928 # Logging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons. 929 "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. 930 "code": 42, # The status code, which should be an enum value of google.rpc.Code. 931 "details": [ # A list of messages that carry the error details. There will be a common set of message types for APIs to use. 932 { 933 "a_key": "", # Properties of the object. Contains field @type with type URL. 934 }, 935 ], 936 }, 937 "done": True or False, # Indicates if the operation is done. If true, the operation is complete and the result is available. If false, the operation is still in progress. 938 "response": { # The operation response. If the called method returns no data on success, the response is google.protobuf.Empty. If the called method is Get,Create or Update, the response is the resource. For all other methods, the response type is a concatenation of the method name and "Response". For example, if the called method is TakeSnapshot(), the response type is TakeSnapshotResponse. 939 "a_key": "", # Properties of the object. Contains field @type with type URL. 940 }, 941 "name": "A String", # The name of the operation resource, in the format projects/project_id/operations/operation_id 942 }</pre> 943</div> 944 945</body></html>