Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1 | <html><body> |
| 2 | <style> |
| 3 | |
| 4 | body, 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 | |
| 15 | body { |
| 16 | font-size: 13px; |
| 17 | padding: 1em; |
| 18 | } |
| 19 | |
| 20 | h1 { |
| 21 | font-size: 26px; |
| 22 | margin-bottom: 1em; |
| 23 | } |
| 24 | |
| 25 | h2 { |
| 26 | font-size: 24px; |
| 27 | margin-bottom: 1em; |
| 28 | } |
| 29 | |
| 30 | h3 { |
| 31 | font-size: 20px; |
| 32 | margin-bottom: 1em; |
| 33 | margin-top: 1em; |
| 34 | } |
| 35 | |
| 36 | pre, code { |
| 37 | line-height: 1.5; |
| 38 | font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace; |
| 39 | } |
| 40 | |
| 41 | pre { |
| 42 | margin-top: 0.5em; |
| 43 | } |
| 44 | |
| 45 | h1, h2, h3, p { |
| 46 | font-family: Arial, sans serif; |
| 47 | } |
| 48 | |
| 49 | h1, 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 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 75 | <h1><a href="dataflow_v1b3.html">Dataflow API</a> . <a href="dataflow_v1b3.projects.html">projects</a> . <a href="dataflow_v1b3.projects.locations.html">locations</a> . <a href="dataflow_v1b3.projects.locations.jobs.html">jobs</a></h1> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 76 | <h2>Instance Methods</h2> |
| 77 | <p class="toc_element"> |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 78 | <code><a href="dataflow_v1b3.projects.locations.jobs.debug.html">debug()</a></code> |
| 79 | </p> |
| 80 | <p class="firstline">Returns the debug Resource.</p> |
| 81 | |
| 82 | <p class="toc_element"> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 83 | <code><a href="dataflow_v1b3.projects.locations.jobs.messages.html">messages()</a></code> |
| 84 | </p> |
| 85 | <p class="firstline">Returns the messages Resource.</p> |
| 86 | |
| 87 | <p class="toc_element"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 88 | <code><a href="dataflow_v1b3.projects.locations.jobs.snapshots.html">snapshots()</a></code> |
| 89 | </p> |
| 90 | <p class="firstline">Returns the snapshots Resource.</p> |
| 91 | |
| 92 | <p class="toc_element"> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 93 | <code><a href="dataflow_v1b3.projects.locations.jobs.workItems.html">workItems()</a></code> |
| 94 | </p> |
| 95 | <p class="firstline">Returns the workItems Resource.</p> |
| 96 | |
| 97 | <p class="toc_element"> |
| 98 | <code><a href="#create">create(projectId, location, body, x__xgafv=None, replaceJobId=None, view=None)</a></code></p> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 99 | <p class="firstline">Creates a Cloud Dataflow job.</p> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 100 | <p class="toc_element"> |
| 101 | <code><a href="#get">get(projectId, location, jobId, x__xgafv=None, view=None)</a></code></p> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 102 | <p class="firstline">Gets the state of the specified Cloud Dataflow job.</p> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 103 | <p class="toc_element"> |
| 104 | <code><a href="#getMetrics">getMetrics(projectId, location, jobId, startTime=None, x__xgafv=None)</a></code></p> |
| 105 | <p class="firstline">Request the job status.</p> |
| 106 | <p class="toc_element"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 107 | <code><a href="#list">list(projectId, location, pageSize=None, pageToken=None, x__xgafv=None, filter=None, view=None)</a></code></p> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 108 | <p class="firstline">List the jobs of a project.</p> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 109 | <p class="toc_element"> |
| 110 | <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p> |
| 111 | <p class="firstline">Retrieves the next page of results.</p> |
| 112 | <p class="toc_element"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 113 | <code><a href="#snapshot">snapshot(projectId, location, jobId, body, x__xgafv=None)</a></code></p> |
| 114 | <p class="firstline">Snapshot the state of a streaming job.</p> |
| 115 | <p class="toc_element"> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 116 | <code><a href="#update">update(projectId, location, jobId, body, x__xgafv=None)</a></code></p> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 117 | <p class="firstline">Updates the state of an existing Cloud Dataflow job.</p> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 118 | <h3>Method Details</h3> |
| 119 | <div class="method"> |
| 120 | <code class="details" id="create">create(projectId, location, body, x__xgafv=None, replaceJobId=None, view=None)</code> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 121 | <pre>Creates a Cloud Dataflow job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 122 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 123 | To create a job, we recommend using `projects.locations.jobs.create` with a |
| 124 | [regional endpoint] |
| 125 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 126 | `projects.jobs.create` is not recommended, as your job will always start |
| 127 | in `us-central1`. |
| 128 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 129 | Args: |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 130 | projectId: string, The ID of the Cloud Platform project that the job belongs to. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 131 | location: string, The [regional endpoint] |
| 132 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 133 | contains this job. (required) |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 134 | body: object, The request body. (required) |
| 135 | The object takes the form of: |
| 136 | |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 137 | { # Defines a job to be run by the Cloud Dataflow service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 138 | "labels": { # User-defined labels for this job. |
| 139 | # |
| 140 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 141 | # map are UTF8 strings that comply with the following restrictions: |
| 142 | # |
| 143 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 144 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 145 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 146 | # size. |
| 147 | "a_key": "A String", |
| 148 | }, |
| 149 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 150 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 151 | # views SUMMARY and higher. |
| 152 | # ListJob response and Job SUMMARY view. |
| 153 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 154 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 155 | "version": "A String", # The version of the SDK used to run the job. |
| 156 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 157 | }, |
| 158 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 159 | { # Metadata for a PubSub connector used by the job. |
| 160 | "topic": "A String", # Topic accessed in the connection. |
| 161 | "subscription": "A String", # Subscription used in the connection. |
| 162 | }, |
| 163 | ], |
| 164 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 165 | { # Metadata for a Datastore connector used by the job. |
| 166 | "projectId": "A String", # ProjectId accessed in the connection. |
| 167 | "namespace": "A String", # Namespace used in the connection. |
| 168 | }, |
| 169 | ], |
| 170 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 171 | { # Metadata for a File connector used by the job. |
| 172 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 173 | }, |
| 174 | ], |
| 175 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 176 | { # Metadata for a Spanner connector used by the job. |
| 177 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 178 | "projectId": "A String", # ProjectId accessed in the connection. |
| 179 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 180 | }, |
| 181 | ], |
| 182 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 183 | { # Metadata for a BigTable connector used by the job. |
| 184 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 185 | "projectId": "A String", # ProjectId accessed in the connection. |
| 186 | "tableId": "A String", # TableId accessed in the connection. |
| 187 | }, |
| 188 | ], |
| 189 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 190 | { # Metadata for a BigQuery connector used by the job. |
| 191 | "projectId": "A String", # Project accessed in the connection. |
| 192 | "dataset": "A String", # Dataset accessed in the connection. |
| 193 | "table": "A String", # Table accessed in the connection. |
| 194 | "query": "A String", # Query used to access data in the connection. |
| 195 | }, |
| 196 | ], |
| 197 | }, |
| 198 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 199 | # A description of the user pipeline and stages through which it is executed. |
| 200 | # Created by Cloud Dataflow service. Only retrieved with |
| 201 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 202 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 203 | # the pipeline and interpreting Dataflow provided metrics. |
| 204 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 205 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 206 | "kind": "A String", # Type of transform. |
| 207 | "name": "A String", # User provided name for this transform instance. |
| 208 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 209 | "A String", |
| 210 | ], |
| 211 | "displayData": [ # Transform-specific display data. |
| 212 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 213 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 214 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 215 | # will be stored with MyDoFn as the short_str_value and |
| 216 | # com.mypackage.MyDoFn as the java_class_name value. |
| 217 | # short_str_value can be displayed and java_class_name_value |
| 218 | # will be displayed as a tooltip. |
| 219 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 220 | "url": "A String", # An optional full URL. |
| 221 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 222 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 223 | # language namespace (i.e. python module) which defines the display data. |
| 224 | # This allows a dax monitoring system to specially handle the data |
| 225 | # and perform custom rendering. |
| 226 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 227 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 228 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 229 | "strValue": "A String", # Contains value if the data is of string type. |
| 230 | "key": "A String", # The key identifying the display data. |
| 231 | # This is intended to be used as a label for the display data |
| 232 | # when viewed in a dax monitoring system. |
| 233 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 234 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 235 | }, |
| 236 | ], |
| 237 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 238 | "A String", |
| 239 | ], |
| 240 | "id": "A String", # SDK generated id of this transform instance. |
| 241 | }, |
| 242 | ], |
| 243 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 244 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 245 | # stage of execution. Some composing transforms and sources may have been |
| 246 | # generated by the Dataflow service during execution planning. |
| 247 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 248 | { # Description of an interstitial value between transforms in an execution |
| 249 | # stage. |
| 250 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 251 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 252 | # source is most closely associated. |
| 253 | "name": "A String", # Dataflow service generated name for this source. |
| 254 | }, |
| 255 | ], |
| 256 | "kind": "A String", # Type of tranform this stage is executing. |
| 257 | "name": "A String", # Dataflow service generated name for this stage. |
| 258 | "outputSource": [ # Output sources for this stage. |
| 259 | { # Description of an input or output of an execution stage. |
| 260 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 261 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 262 | "name": "A String", # Dataflow service generated name for this source. |
| 263 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 264 | # source is most closely associated. |
| 265 | }, |
| 266 | ], |
| 267 | "inputSource": [ # Input sources for this stage. |
| 268 | { # Description of an input or output of an execution stage. |
| 269 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 270 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 271 | "name": "A String", # Dataflow service generated name for this source. |
| 272 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 273 | # source is most closely associated. |
| 274 | }, |
| 275 | ], |
| 276 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 277 | { # Description of a transform executed as part of an execution stage. |
| 278 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 279 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 280 | # most closely associated. |
| 281 | "name": "A String", # Dataflow service generated name for this source. |
| 282 | }, |
| 283 | ], |
| 284 | "id": "A String", # Dataflow service generated id for this stage. |
| 285 | }, |
| 286 | ], |
| 287 | "displayData": [ # Pipeline level display data. |
| 288 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 289 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 290 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 291 | # will be stored with MyDoFn as the short_str_value and |
| 292 | # com.mypackage.MyDoFn as the java_class_name value. |
| 293 | # short_str_value can be displayed and java_class_name_value |
| 294 | # will be displayed as a tooltip. |
| 295 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 296 | "url": "A String", # An optional full URL. |
| 297 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 298 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 299 | # language namespace (i.e. python module) which defines the display data. |
| 300 | # This allows a dax monitoring system to specially handle the data |
| 301 | # and perform custom rendering. |
| 302 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 303 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 304 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 305 | "strValue": "A String", # Contains value if the data is of string type. |
| 306 | "key": "A String", # The key identifying the display data. |
| 307 | # This is intended to be used as a label for the display data |
| 308 | # when viewed in a dax monitoring system. |
| 309 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 310 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 311 | }, |
| 312 | ], |
| 313 | }, |
| 314 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 315 | # callers cannot mutate it. |
| 316 | { # A message describing the state of a particular execution stage. |
| 317 | "executionStageName": "A String", # The name of the execution stage. |
| 318 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 319 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 320 | }, |
| 321 | ], |
| 322 | "id": "A String", # The unique ID of this job. |
| 323 | # |
| 324 | # This field is set by the Cloud Dataflow service when the Job is |
| 325 | # created, and is immutable for the life of the job. |
| 326 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 327 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 328 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 329 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 330 | # corresponding name prefixes of the new job. |
| 331 | "a_key": "A String", |
| 332 | }, |
| 333 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 334 | "version": { # A structure describing which components and their versions of the service |
| 335 | # are required in order to run the job. |
| 336 | "a_key": "", # Properties of the object. |
| 337 | }, |
| 338 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 339 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 340 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 341 | # |
| 342 | # Format: |
| 343 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 344 | "internalExperiments": { # Experimental settings. |
| 345 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 346 | }, |
| 347 | "dataset": "A String", # The dataset for the current project where various workflow |
| 348 | # related tables are stored. |
| 349 | # |
| 350 | # The supported resource type is: |
| 351 | # |
| 352 | # Google BigQuery: |
| 353 | # bigquery.googleapis.com/{dataset} |
| 354 | "experiments": [ # The list of experiments to enable. |
| 355 | "A String", |
| 356 | ], |
| 357 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 358 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 359 | # options are passed through the service and are used to recreate the |
| 360 | # SDK pipeline options on the worker in a language agnostic and platform |
| 361 | # independent way. |
| 362 | "a_key": "", # Properties of the object. |
| 363 | }, |
| 364 | "userAgent": { # A description of the process that generated the request. |
| 365 | "a_key": "", # Properties of the object. |
| 366 | }, |
| 367 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 368 | # unspecified, the service will attempt to choose a reasonable |
| 369 | # default. This should be in the form of the API service name, |
| 370 | # e.g. "compute.googleapis.com". |
| 371 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 372 | # specified in order for the job to have workers. |
| 373 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 374 | # instantiated by the Cloud Dataflow service in order to perform the |
| 375 | # computations required by a job. Note that a workflow job may use |
| 376 | # multiple pools, in order to match the various computational |
| 377 | # requirements of the various stages of the job. |
| 378 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
| 379 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 380 | # using the standard Dataflow task runner. Users should ignore |
| 381 | # this field. |
| 382 | "workflowFileName": "A String", # The file to store the workflow in. |
| 383 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 384 | # will not be uploaded. |
| 385 | # |
| 386 | # The supported resource type is: |
| 387 | # |
| 388 | # Google Cloud Storage: |
| 389 | # storage.googleapis.com/{bucket}/{object} |
| 390 | # bucket.storage.googleapis.com/{object} |
| 391 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
| 392 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 393 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 394 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 395 | # "shuffle/v1beta1". |
| 396 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 397 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 398 | # |
| 399 | # When workers access Google Cloud APIs, they logically do so via |
| 400 | # relative URLs. If this field is specified, it supplies the base |
| 401 | # URL to use for resolving these relative URLs. The normative |
| 402 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 403 | # Locators". |
| 404 | # |
| 405 | # If not specified, the default value is "http://www.googleapis.com/" |
| 406 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 407 | # "dataflow/v1b3/projects". |
| 408 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 409 | # storage. |
| 410 | # |
| 411 | # The supported resource type is: |
| 412 | # |
| 413 | # Google Cloud Storage: |
| 414 | # |
| 415 | # storage.googleapis.com/{bucket}/{object} |
| 416 | # bucket.storage.googleapis.com/{object} |
| 417 | }, |
| 418 | "vmId": "A String", # The ID string of the VM. |
| 419 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 420 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 421 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 422 | # access the Cloud Dataflow API. |
| 423 | "A String", |
| 424 | ], |
| 425 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 426 | # taskrunner; e.g. "root". |
| 427 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 428 | # |
| 429 | # When workers access Google Cloud APIs, they logically do so via |
| 430 | # relative URLs. If this field is specified, it supplies the base |
| 431 | # URL to use for resolving these relative URLs. The normative |
| 432 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 433 | # Locators". |
| 434 | # |
| 435 | # If not specified, the default value is "http://www.googleapis.com/" |
| 436 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 437 | # taskrunner; e.g. "wheel". |
| 438 | "languageHint": "A String", # The suggested backend language. |
| 439 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 440 | # console. |
| 441 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 442 | "logDir": "A String", # The directory on the VM to store logs. |
| 443 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 444 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 445 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 446 | # temporary storage. |
| 447 | # |
| 448 | # The supported resource type is: |
| 449 | # |
| 450 | # Google Cloud Storage: |
| 451 | # storage.googleapis.com/{bucket}/{object} |
| 452 | # bucket.storage.googleapis.com/{object} |
| 453 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 454 | }, |
| 455 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 456 | # are supported. |
| 457 | "packages": [ # Packages to be installed on workers. |
| 458 | { # The packages that must be installed in order for a worker to run the |
| 459 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 460 | # pool. |
| 461 | # |
| 462 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 463 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 464 | # might use this to install jars containing the user's code and all of the |
| 465 | # various dependencies (libraries, data files, etc.) required in order |
| 466 | # for that code to run. |
| 467 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 468 | # |
| 469 | # Google Cloud Storage: |
| 470 | # |
| 471 | # storage.googleapis.com/{bucket} |
| 472 | # bucket.storage.googleapis.com/ |
| 473 | "name": "A String", # The name of the package. |
| 474 | }, |
| 475 | ], |
| 476 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 477 | # service will attempt to choose a reasonable default. |
| 478 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 479 | # the service will use the network "default". |
| 480 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 481 | # will attempt to choose a reasonable default. |
| 482 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 483 | # attempt to choose a reasonable default. |
| 484 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 485 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 486 | # `TEARDOWN_NEVER`. |
| 487 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 488 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 489 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 490 | # down. |
| 491 | # |
| 492 | # If the workers are not torn down by the service, they will |
| 493 | # continue to run and use Google Compute Engine VM resources in the |
| 494 | # user's project until they are explicitly terminated by the user. |
| 495 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 496 | # policy except for small, manually supervised test jobs. |
| 497 | # |
| 498 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 499 | # default. |
| 500 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 501 | # Compute Engine API. |
| 502 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 503 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 504 | # service will choose a number of threads (according to the number of cores |
| 505 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 506 | "poolArgs": { # Extra arguments for this worker pool. |
| 507 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 508 | }, |
| 509 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 510 | # execute the job. If zero or unspecified, the service will |
| 511 | # attempt to choose a reasonable default. |
| 512 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 513 | # harness, residing in Google Container Registry. |
| 514 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 515 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 516 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 517 | { # Describes the data disk used by a workflow job. |
| 518 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 519 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 520 | # attempt to choose a reasonable default. |
| 521 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 522 | # must be a disk type appropriate to the project and zone in which |
| 523 | # the workers will run. If unknown or unspecified, the service |
| 524 | # will attempt to choose a reasonable default. |
| 525 | # |
| 526 | # For example, the standard persistent disk type is a resource name |
| 527 | # typically ending in "pd-standard". If SSD persistent disks are |
| 528 | # available, the resource name typically ends with "pd-ssd". The |
| 529 | # actual valid values are defined the Google Compute Engine API, |
| 530 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 531 | # documentation for more information about determining the set of |
| 532 | # available disk types for a particular project and zone. |
| 533 | # |
| 534 | # Google Compute Engine Disk types are local to a particular |
| 535 | # project in a particular zone, and so the resource name will |
| 536 | # typically look something like this: |
| 537 | # |
| 538 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
| 539 | }, |
| 540 | ], |
| 541 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 542 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 543 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 544 | }, |
| 545 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 546 | # select a default set of packages which are useful to worker |
| 547 | # harnesses written in a particular language. |
| 548 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 549 | # attempt to choose a reasonable default. |
| 550 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 551 | "a_key": "A String", |
| 552 | }, |
| 553 | }, |
| 554 | ], |
| 555 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 556 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 557 | # this resource prefix, where {JOBNAME} is the value of the |
| 558 | # job_name field. The resulting bucket and object prefix is used |
| 559 | # as the prefix of the resources used to store temporary data |
| 560 | # needed during the job execution. NOTE: This will override the |
| 561 | # value in taskrunner_settings. |
| 562 | # The supported resource type is: |
| 563 | # |
| 564 | # Google Cloud Storage: |
| 565 | # |
| 566 | # storage.googleapis.com/{bucket}/{object} |
| 567 | # bucket.storage.googleapis.com/{object} |
| 568 | }, |
| 569 | "location": "A String", # The [regional endpoint] |
| 570 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 571 | # contains this job. |
| 572 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 573 | # for temporary storage. These temporary files will be |
| 574 | # removed on job completion. |
| 575 | # No duplicates are allowed. |
| 576 | # No file patterns are supported. |
| 577 | # |
| 578 | # The supported files are: |
| 579 | # |
| 580 | # Google Cloud Storage: |
| 581 | # |
| 582 | # storage.googleapis.com/{bucket}/{object} |
| 583 | # bucket.storage.googleapis.com/{object} |
| 584 | "A String", |
| 585 | ], |
| 586 | "type": "A String", # The type of Cloud Dataflow job. |
| 587 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 588 | # If this field is set, the service will ensure its uniqueness. |
| 589 | # The request to create a job will fail if the service has knowledge of a |
| 590 | # previously submitted job with the same client's ID and job name. |
| 591 | # The caller may use this field to ensure idempotence of job |
| 592 | # creation across retried attempts to create a job. |
| 593 | # By default, the field is empty and, in that case, the service ignores it. |
| 594 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 595 | # snapshot. |
| 596 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 597 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 598 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 599 | # Flexible resource scheduling jobs are started with some delay after job |
| 600 | # creation, so start_time is unset before start and is updated when the |
| 601 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 602 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 603 | # service. |
| 604 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 605 | # Cloud Dataflow service. |
| 606 | "requestedState": "A String", # The job's requested state. |
| 607 | # |
| 608 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 609 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 610 | # also be used to directly set a job's requested state to |
| 611 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 612 | # job if it has not already reached a terminal state. |
| 613 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 614 | # |
| 615 | # Only one Job with a given name may exist in a project at any |
| 616 | # given time. If a caller attempts to create a Job with the same |
| 617 | # name as an already-existing Job, the attempt returns the |
| 618 | # existing Job. |
| 619 | # |
| 620 | # The name must match the regular expression |
| 621 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 622 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 623 | # |
| 624 | # The top-level steps that constitute the entire job. |
| 625 | { # Defines a particular step within a Cloud Dataflow job. |
| 626 | # |
| 627 | # A job consists of multiple steps, each of which performs some |
| 628 | # specific operation as part of the overall job. Data is typically |
| 629 | # passed from one step to another as part of the job. |
| 630 | # |
| 631 | # Here's an example of a sequence of steps which together implement a |
| 632 | # Map-Reduce job: |
| 633 | # |
| 634 | # * Read a collection of data from some source, parsing the |
| 635 | # collection's elements. |
| 636 | # |
| 637 | # * Validate the elements. |
| 638 | # |
| 639 | # * Apply a user-defined function to map each element to some value |
| 640 | # and extract an element-specific key value. |
| 641 | # |
| 642 | # * Group elements with the same key into a single element with |
| 643 | # that key, transforming a multiply-keyed collection into a |
| 644 | # uniquely-keyed collection. |
| 645 | # |
| 646 | # * Write the elements out to some data sink. |
| 647 | # |
| 648 | # Note that the Cloud Dataflow service may be used to run many different |
| 649 | # types of jobs, not just Map-Reduce. |
| 650 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 651 | "properties": { # Named properties associated with the step. Each kind of |
| 652 | # predefined step has its own required set of properties. |
| 653 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 654 | "a_key": "", # Properties of the object. |
| 655 | }, |
| 656 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 657 | # step with respect to all other steps in the Cloud Dataflow job. |
| 658 | }, |
| 659 | ], |
| 660 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 661 | # of the job it replaced. |
| 662 | # |
| 663 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 664 | # here. The job named here is stopped, and its intermediate state is |
| 665 | # transferred to this job. |
| 666 | "currentState": "A String", # The current state of the job. |
| 667 | # |
| 668 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 669 | # specified. |
| 670 | # |
| 671 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 672 | # terminal state. After a job has reached a terminal state, no |
| 673 | # further state updates may be made. |
| 674 | # |
| 675 | # This field may be mutated by the Cloud Dataflow service; |
| 676 | # callers cannot mutate it. |
| 677 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 678 | # isn't contained in the submitted job. |
| 679 | "stages": { # A mapping from each stage to the information about that stage. |
| 680 | "a_key": { # Contains information about how a particular |
| 681 | # google.dataflow.v1beta3.Step will be executed. |
| 682 | "stepName": [ # The steps associated with the execution stage. |
| 683 | # Note that stages may have several steps, and that a given step |
| 684 | # might be run by more than one stage. |
| 685 | "A String", |
| 686 | ], |
| 687 | }, |
| 688 | }, |
| 689 | }, |
| 690 | } |
| 691 | |
| 692 | x__xgafv: string, V1 error format. |
| 693 | Allowed values |
| 694 | 1 - v1 error format |
| 695 | 2 - v2 error format |
| 696 | replaceJobId: string, Deprecated. This field is now in the Job message. |
| 697 | view: string, The level of information requested in response. |
| 698 | |
| 699 | Returns: |
| 700 | An object of the form: |
| 701 | |
| 702 | { # Defines a job to be run by the Cloud Dataflow service. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 703 | "labels": { # User-defined labels for this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 704 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 705 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 706 | # map are UTF8 strings that comply with the following restrictions: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 707 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 708 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 709 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 710 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 711 | # size. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 712 | "a_key": "A String", |
| 713 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 714 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 715 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 716 | # views SUMMARY and higher. |
| 717 | # ListJob response and Job SUMMARY view. |
| 718 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 719 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 720 | "version": "A String", # The version of the SDK used to run the job. |
| 721 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 722 | }, |
| 723 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 724 | { # Metadata for a PubSub connector used by the job. |
| 725 | "topic": "A String", # Topic accessed in the connection. |
| 726 | "subscription": "A String", # Subscription used in the connection. |
| 727 | }, |
| 728 | ], |
| 729 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 730 | { # Metadata for a Datastore connector used by the job. |
| 731 | "projectId": "A String", # ProjectId accessed in the connection. |
| 732 | "namespace": "A String", # Namespace used in the connection. |
| 733 | }, |
| 734 | ], |
| 735 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 736 | { # Metadata for a File connector used by the job. |
| 737 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 738 | }, |
| 739 | ], |
| 740 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 741 | { # Metadata for a Spanner connector used by the job. |
| 742 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 743 | "projectId": "A String", # ProjectId accessed in the connection. |
| 744 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 745 | }, |
| 746 | ], |
| 747 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 748 | { # Metadata for a BigTable connector used by the job. |
| 749 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 750 | "projectId": "A String", # ProjectId accessed in the connection. |
| 751 | "tableId": "A String", # TableId accessed in the connection. |
| 752 | }, |
| 753 | ], |
| 754 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 755 | { # Metadata for a BigQuery connector used by the job. |
| 756 | "projectId": "A String", # Project accessed in the connection. |
| 757 | "dataset": "A String", # Dataset accessed in the connection. |
| 758 | "table": "A String", # Table accessed in the connection. |
| 759 | "query": "A String", # Query used to access data in the connection. |
| 760 | }, |
| 761 | ], |
| 762 | }, |
| 763 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 764 | # A description of the user pipeline and stages through which it is executed. |
| 765 | # Created by Cloud Dataflow service. Only retrieved with |
| 766 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 767 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 768 | # the pipeline and interpreting Dataflow provided metrics. |
| 769 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 770 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 771 | "kind": "A String", # Type of transform. |
| 772 | "name": "A String", # User provided name for this transform instance. |
| 773 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 774 | "A String", |
| 775 | ], |
| 776 | "displayData": [ # Transform-specific display data. |
| 777 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 778 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 779 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 780 | # will be stored with MyDoFn as the short_str_value and |
| 781 | # com.mypackage.MyDoFn as the java_class_name value. |
| 782 | # short_str_value can be displayed and java_class_name_value |
| 783 | # will be displayed as a tooltip. |
| 784 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 785 | "url": "A String", # An optional full URL. |
| 786 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 787 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 788 | # language namespace (i.e. python module) which defines the display data. |
| 789 | # This allows a dax monitoring system to specially handle the data |
| 790 | # and perform custom rendering. |
| 791 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 792 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 793 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 794 | "strValue": "A String", # Contains value if the data is of string type. |
| 795 | "key": "A String", # The key identifying the display data. |
| 796 | # This is intended to be used as a label for the display data |
| 797 | # when viewed in a dax monitoring system. |
| 798 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 799 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 800 | }, |
| 801 | ], |
| 802 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 803 | "A String", |
| 804 | ], |
| 805 | "id": "A String", # SDK generated id of this transform instance. |
| 806 | }, |
| 807 | ], |
| 808 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 809 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 810 | # stage of execution. Some composing transforms and sources may have been |
| 811 | # generated by the Dataflow service during execution planning. |
| 812 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 813 | { # Description of an interstitial value between transforms in an execution |
| 814 | # stage. |
| 815 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 816 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 817 | # source is most closely associated. |
| 818 | "name": "A String", # Dataflow service generated name for this source. |
| 819 | }, |
| 820 | ], |
| 821 | "kind": "A String", # Type of tranform this stage is executing. |
| 822 | "name": "A String", # Dataflow service generated name for this stage. |
| 823 | "outputSource": [ # Output sources for this stage. |
| 824 | { # Description of an input or output of an execution stage. |
| 825 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 826 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 827 | "name": "A String", # Dataflow service generated name for this source. |
| 828 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 829 | # source is most closely associated. |
| 830 | }, |
| 831 | ], |
| 832 | "inputSource": [ # Input sources for this stage. |
| 833 | { # Description of an input or output of an execution stage. |
| 834 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 835 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 836 | "name": "A String", # Dataflow service generated name for this source. |
| 837 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 838 | # source is most closely associated. |
| 839 | }, |
| 840 | ], |
| 841 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 842 | { # Description of a transform executed as part of an execution stage. |
| 843 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 844 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 845 | # most closely associated. |
| 846 | "name": "A String", # Dataflow service generated name for this source. |
| 847 | }, |
| 848 | ], |
| 849 | "id": "A String", # Dataflow service generated id for this stage. |
| 850 | }, |
| 851 | ], |
| 852 | "displayData": [ # Pipeline level display data. |
| 853 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 854 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 855 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 856 | # will be stored with MyDoFn as the short_str_value and |
| 857 | # com.mypackage.MyDoFn as the java_class_name value. |
| 858 | # short_str_value can be displayed and java_class_name_value |
| 859 | # will be displayed as a tooltip. |
| 860 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 861 | "url": "A String", # An optional full URL. |
| 862 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 863 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 864 | # language namespace (i.e. python module) which defines the display data. |
| 865 | # This allows a dax monitoring system to specially handle the data |
| 866 | # and perform custom rendering. |
| 867 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 868 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 869 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 870 | "strValue": "A String", # Contains value if the data is of string type. |
| 871 | "key": "A String", # The key identifying the display data. |
| 872 | # This is intended to be used as a label for the display data |
| 873 | # when viewed in a dax monitoring system. |
| 874 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 875 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 876 | }, |
| 877 | ], |
| 878 | }, |
| 879 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 880 | # callers cannot mutate it. |
| 881 | { # A message describing the state of a particular execution stage. |
| 882 | "executionStageName": "A String", # The name of the execution stage. |
| 883 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 884 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 885 | }, |
| 886 | ], |
| 887 | "id": "A String", # The unique ID of this job. |
| 888 | # |
| 889 | # This field is set by the Cloud Dataflow service when the Job is |
| 890 | # created, and is immutable for the life of the job. |
| 891 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 892 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 893 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 894 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 895 | # corresponding name prefixes of the new job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 896 | "a_key": "A String", |
| 897 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 898 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 899 | "version": { # A structure describing which components and their versions of the service |
| 900 | # are required in order to run the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 901 | "a_key": "", # Properties of the object. |
| 902 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 903 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 904 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 905 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 906 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 907 | # Format: |
| 908 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 909 | "internalExperiments": { # Experimental settings. |
| 910 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 911 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 912 | "dataset": "A String", # The dataset for the current project where various workflow |
| 913 | # related tables are stored. |
| 914 | # |
| 915 | # The supported resource type is: |
| 916 | # |
| 917 | # Google BigQuery: |
| 918 | # bigquery.googleapis.com/{dataset} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 919 | "experiments": [ # The list of experiments to enable. |
| 920 | "A String", |
| 921 | ], |
| 922 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 923 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 924 | # options are passed through the service and are used to recreate the |
| 925 | # SDK pipeline options on the worker in a language agnostic and platform |
| 926 | # independent way. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 927 | "a_key": "", # Properties of the object. |
| 928 | }, |
| 929 | "userAgent": { # A description of the process that generated the request. |
| 930 | "a_key": "", # Properties of the object. |
| 931 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 932 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 933 | # unspecified, the service will attempt to choose a reasonable |
| 934 | # default. This should be in the form of the API service name, |
| 935 | # e.g. "compute.googleapis.com". |
| 936 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 937 | # specified in order for the job to have workers. |
| 938 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 939 | # instantiated by the Cloud Dataflow service in order to perform the |
| 940 | # computations required by a job. Note that a workflow job may use |
| 941 | # multiple pools, in order to match the various computational |
| 942 | # requirements of the various stages of the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 943 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 944 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 945 | # using the standard Dataflow task runner. Users should ignore |
| 946 | # this field. |
| 947 | "workflowFileName": "A String", # The file to store the workflow in. |
| 948 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 949 | # will not be uploaded. |
| 950 | # |
| 951 | # The supported resource type is: |
| 952 | # |
| 953 | # Google Cloud Storage: |
| 954 | # storage.googleapis.com/{bucket}/{object} |
| 955 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 956 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 957 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 958 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 959 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 960 | # "shuffle/v1beta1". |
| 961 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 962 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 963 | # |
| 964 | # When workers access Google Cloud APIs, they logically do so via |
| 965 | # relative URLs. If this field is specified, it supplies the base |
| 966 | # URL to use for resolving these relative URLs. The normative |
| 967 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 968 | # Locators". |
| 969 | # |
| 970 | # If not specified, the default value is "http://www.googleapis.com/" |
| 971 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 972 | # "dataflow/v1b3/projects". |
| 973 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 974 | # storage. |
| 975 | # |
| 976 | # The supported resource type is: |
| 977 | # |
| 978 | # Google Cloud Storage: |
| 979 | # |
| 980 | # storage.googleapis.com/{bucket}/{object} |
| 981 | # bucket.storage.googleapis.com/{object} |
| 982 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 983 | "vmId": "A String", # The ID string of the VM. |
| 984 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 985 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 986 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 987 | # access the Cloud Dataflow API. |
| 988 | "A String", |
| 989 | ], |
| 990 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 991 | # taskrunner; e.g. "root". |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 992 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 993 | # |
| 994 | # When workers access Google Cloud APIs, they logically do so via |
| 995 | # relative URLs. If this field is specified, it supplies the base |
| 996 | # URL to use for resolving these relative URLs. The normative |
| 997 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 998 | # Locators". |
| 999 | # |
| 1000 | # If not specified, the default value is "http://www.googleapis.com/" |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1001 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 1002 | # taskrunner; e.g. "wheel". |
| 1003 | "languageHint": "A String", # The suggested backend language. |
| 1004 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 1005 | # console. |
| 1006 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 1007 | "logDir": "A String", # The directory on the VM to store logs. |
| 1008 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 1009 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 1010 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 1011 | # temporary storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1012 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 1013 | # The supported resource type is: |
| 1014 | # |
| 1015 | # Google Cloud Storage: |
| 1016 | # storage.googleapis.com/{bucket}/{object} |
| 1017 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1018 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1019 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1020 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 1021 | # are supported. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1022 | "packages": [ # Packages to be installed on workers. |
| 1023 | { # The packages that must be installed in order for a worker to run the |
| 1024 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 1025 | # pool. |
| 1026 | # |
| 1027 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 1028 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 1029 | # might use this to install jars containing the user's code and all of the |
| 1030 | # various dependencies (libraries, data files, etc.) required in order |
| 1031 | # for that code to run. |
| 1032 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 1033 | # |
| 1034 | # Google Cloud Storage: |
| 1035 | # |
| 1036 | # storage.googleapis.com/{bucket} |
| 1037 | # bucket.storage.googleapis.com/ |
| 1038 | "name": "A String", # The name of the package. |
| 1039 | }, |
| 1040 | ], |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1041 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 1042 | # service will attempt to choose a reasonable default. |
| 1043 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 1044 | # the service will use the network "default". |
| 1045 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 1046 | # will attempt to choose a reasonable default. |
| 1047 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 1048 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1049 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 1050 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 1051 | # `TEARDOWN_NEVER`. |
| 1052 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 1053 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 1054 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 1055 | # down. |
| 1056 | # |
| 1057 | # If the workers are not torn down by the service, they will |
| 1058 | # continue to run and use Google Compute Engine VM resources in the |
| 1059 | # user's project until they are explicitly terminated by the user. |
| 1060 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 1061 | # policy except for small, manually supervised test jobs. |
| 1062 | # |
| 1063 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 1064 | # default. |
| 1065 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 1066 | # Compute Engine API. |
| 1067 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 1068 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 1069 | # service will choose a number of threads (according to the number of cores |
| 1070 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 1071 | "poolArgs": { # Extra arguments for this worker pool. |
| 1072 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1073 | }, |
| 1074 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 1075 | # execute the job. If zero or unspecified, the service will |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1076 | # attempt to choose a reasonable default. |
| 1077 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 1078 | # harness, residing in Google Container Registry. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1079 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 1080 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1081 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 1082 | { # Describes the data disk used by a workflow job. |
| 1083 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 1084 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 1085 | # attempt to choose a reasonable default. |
| 1086 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 1087 | # must be a disk type appropriate to the project and zone in which |
| 1088 | # the workers will run. If unknown or unspecified, the service |
| 1089 | # will attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1090 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1091 | # For example, the standard persistent disk type is a resource name |
| 1092 | # typically ending in "pd-standard". If SSD persistent disks are |
| 1093 | # available, the resource name typically ends with "pd-ssd". The |
| 1094 | # actual valid values are defined the Google Compute Engine API, |
| 1095 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 1096 | # documentation for more information about determining the set of |
| 1097 | # available disk types for a particular project and zone. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1098 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1099 | # Google Compute Engine Disk types are local to a particular |
| 1100 | # project in a particular zone, and so the resource name will |
| 1101 | # typically look something like this: |
| 1102 | # |
| 1103 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1104 | }, |
| 1105 | ], |
| 1106 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 1107 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 1108 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 1109 | }, |
| 1110 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 1111 | # select a default set of packages which are useful to worker |
| 1112 | # harnesses written in a particular language. |
| 1113 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 1114 | # attempt to choose a reasonable default. |
| 1115 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 1116 | "a_key": "A String", |
| 1117 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1118 | }, |
| 1119 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1120 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1121 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 1122 | # this resource prefix, where {JOBNAME} is the value of the |
| 1123 | # job_name field. The resulting bucket and object prefix is used |
| 1124 | # as the prefix of the resources used to store temporary data |
| 1125 | # needed during the job execution. NOTE: This will override the |
| 1126 | # value in taskrunner_settings. |
| 1127 | # The supported resource type is: |
| 1128 | # |
| 1129 | # Google Cloud Storage: |
| 1130 | # |
| 1131 | # storage.googleapis.com/{bucket}/{object} |
| 1132 | # bucket.storage.googleapis.com/{object} |
| 1133 | }, |
| 1134 | "location": "A String", # The [regional endpoint] |
| 1135 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1136 | # contains this job. |
| 1137 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 1138 | # for temporary storage. These temporary files will be |
| 1139 | # removed on job completion. |
| 1140 | # No duplicates are allowed. |
| 1141 | # No file patterns are supported. |
| 1142 | # |
| 1143 | # The supported files are: |
| 1144 | # |
| 1145 | # Google Cloud Storage: |
| 1146 | # |
| 1147 | # storage.googleapis.com/{bucket}/{object} |
| 1148 | # bucket.storage.googleapis.com/{object} |
| 1149 | "A String", |
| 1150 | ], |
| 1151 | "type": "A String", # The type of Cloud Dataflow job. |
| 1152 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 1153 | # If this field is set, the service will ensure its uniqueness. |
| 1154 | # The request to create a job will fail if the service has knowledge of a |
| 1155 | # previously submitted job with the same client's ID and job name. |
| 1156 | # The caller may use this field to ensure idempotence of job |
| 1157 | # creation across retried attempts to create a job. |
| 1158 | # By default, the field is empty and, in that case, the service ignores it. |
| 1159 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 1160 | # snapshot. |
| 1161 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 1162 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 1163 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 1164 | # Flexible resource scheduling jobs are started with some delay after job |
| 1165 | # creation, so start_time is unset before start and is updated when the |
| 1166 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 1167 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 1168 | # service. |
| 1169 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 1170 | # Cloud Dataflow service. |
| 1171 | "requestedState": "A String", # The job's requested state. |
| 1172 | # |
| 1173 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 1174 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 1175 | # also be used to directly set a job's requested state to |
| 1176 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 1177 | # job if it has not already reached a terminal state. |
| 1178 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 1179 | # |
| 1180 | # Only one Job with a given name may exist in a project at any |
| 1181 | # given time. If a caller attempts to create a Job with the same |
| 1182 | # name as an already-existing Job, the attempt returns the |
| 1183 | # existing Job. |
| 1184 | # |
| 1185 | # The name must match the regular expression |
| 1186 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 1187 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 1188 | # |
| 1189 | # The top-level steps that constitute the entire job. |
| 1190 | { # Defines a particular step within a Cloud Dataflow job. |
| 1191 | # |
| 1192 | # A job consists of multiple steps, each of which performs some |
| 1193 | # specific operation as part of the overall job. Data is typically |
| 1194 | # passed from one step to another as part of the job. |
| 1195 | # |
| 1196 | # Here's an example of a sequence of steps which together implement a |
| 1197 | # Map-Reduce job: |
| 1198 | # |
| 1199 | # * Read a collection of data from some source, parsing the |
| 1200 | # collection's elements. |
| 1201 | # |
| 1202 | # * Validate the elements. |
| 1203 | # |
| 1204 | # * Apply a user-defined function to map each element to some value |
| 1205 | # and extract an element-specific key value. |
| 1206 | # |
| 1207 | # * Group elements with the same key into a single element with |
| 1208 | # that key, transforming a multiply-keyed collection into a |
| 1209 | # uniquely-keyed collection. |
| 1210 | # |
| 1211 | # * Write the elements out to some data sink. |
| 1212 | # |
| 1213 | # Note that the Cloud Dataflow service may be used to run many different |
| 1214 | # types of jobs, not just Map-Reduce. |
| 1215 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 1216 | "properties": { # Named properties associated with the step. Each kind of |
| 1217 | # predefined step has its own required set of properties. |
| 1218 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 1219 | "a_key": "", # Properties of the object. |
| 1220 | }, |
| 1221 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 1222 | # step with respect to all other steps in the Cloud Dataflow job. |
| 1223 | }, |
| 1224 | ], |
| 1225 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 1226 | # of the job it replaced. |
| 1227 | # |
| 1228 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 1229 | # here. The job named here is stopped, and its intermediate state is |
| 1230 | # transferred to this job. |
| 1231 | "currentState": "A String", # The current state of the job. |
| 1232 | # |
| 1233 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 1234 | # specified. |
| 1235 | # |
| 1236 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 1237 | # terminal state. After a job has reached a terminal state, no |
| 1238 | # further state updates may be made. |
| 1239 | # |
| 1240 | # This field may be mutated by the Cloud Dataflow service; |
| 1241 | # callers cannot mutate it. |
| 1242 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 1243 | # isn't contained in the submitted job. |
| 1244 | "stages": { # A mapping from each stage to the information about that stage. |
| 1245 | "a_key": { # Contains information about how a particular |
| 1246 | # google.dataflow.v1beta3.Step will be executed. |
| 1247 | "stepName": [ # The steps associated with the execution stage. |
| 1248 | # Note that stages may have several steps, and that a given step |
| 1249 | # might be run by more than one stage. |
| 1250 | "A String", |
| 1251 | ], |
| 1252 | }, |
| 1253 | }, |
| 1254 | }, |
| 1255 | }</pre> |
| 1256 | </div> |
| 1257 | |
| 1258 | <div class="method"> |
| 1259 | <code class="details" id="get">get(projectId, location, jobId, x__xgafv=None, view=None)</code> |
| 1260 | <pre>Gets the state of the specified Cloud Dataflow job. |
| 1261 | |
| 1262 | To get the state of a job, we recommend using `projects.locations.jobs.get` |
| 1263 | with a [regional endpoint] |
| 1264 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 1265 | `projects.jobs.get` is not recommended, as you can only get the state of |
| 1266 | jobs that are running in `us-central1`. |
| 1267 | |
| 1268 | Args: |
| 1269 | projectId: string, The ID of the Cloud Platform project that the job belongs to. (required) |
| 1270 | location: string, The [regional endpoint] |
| 1271 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1272 | contains this job. (required) |
| 1273 | jobId: string, The job ID. (required) |
| 1274 | x__xgafv: string, V1 error format. |
| 1275 | Allowed values |
| 1276 | 1 - v1 error format |
| 1277 | 2 - v2 error format |
| 1278 | view: string, The level of information requested in response. |
| 1279 | |
| 1280 | Returns: |
| 1281 | An object of the form: |
| 1282 | |
| 1283 | { # Defines a job to be run by the Cloud Dataflow service. |
| 1284 | "labels": { # User-defined labels for this job. |
| 1285 | # |
| 1286 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 1287 | # map are UTF8 strings that comply with the following restrictions: |
| 1288 | # |
| 1289 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 1290 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 1291 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 1292 | # size. |
| 1293 | "a_key": "A String", |
| 1294 | }, |
| 1295 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 1296 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 1297 | # views SUMMARY and higher. |
| 1298 | # ListJob response and Job SUMMARY view. |
| 1299 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 1300 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 1301 | "version": "A String", # The version of the SDK used to run the job. |
| 1302 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 1303 | }, |
| 1304 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 1305 | { # Metadata for a PubSub connector used by the job. |
| 1306 | "topic": "A String", # Topic accessed in the connection. |
| 1307 | "subscription": "A String", # Subscription used in the connection. |
| 1308 | }, |
| 1309 | ], |
| 1310 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 1311 | { # Metadata for a Datastore connector used by the job. |
| 1312 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1313 | "namespace": "A String", # Namespace used in the connection. |
| 1314 | }, |
| 1315 | ], |
| 1316 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 1317 | { # Metadata for a File connector used by the job. |
| 1318 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 1319 | }, |
| 1320 | ], |
| 1321 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 1322 | { # Metadata for a Spanner connector used by the job. |
| 1323 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 1324 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1325 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 1326 | }, |
| 1327 | ], |
| 1328 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 1329 | { # Metadata for a BigTable connector used by the job. |
| 1330 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 1331 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1332 | "tableId": "A String", # TableId accessed in the connection. |
| 1333 | }, |
| 1334 | ], |
| 1335 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 1336 | { # Metadata for a BigQuery connector used by the job. |
| 1337 | "projectId": "A String", # Project accessed in the connection. |
| 1338 | "dataset": "A String", # Dataset accessed in the connection. |
| 1339 | "table": "A String", # Table accessed in the connection. |
| 1340 | "query": "A String", # Query used to access data in the connection. |
| 1341 | }, |
| 1342 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1343 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1344 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 1345 | # A description of the user pipeline and stages through which it is executed. |
| 1346 | # Created by Cloud Dataflow service. Only retrieved with |
| 1347 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 1348 | # form. This data is provided by the Dataflow service for ease of visualizing |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1349 | # the pipeline and interpreting Dataflow provided metrics. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1350 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 1351 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 1352 | "kind": "A String", # Type of transform. |
| 1353 | "name": "A String", # User provided name for this transform instance. |
| 1354 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 1355 | "A String", |
| 1356 | ], |
| 1357 | "displayData": [ # Transform-specific display data. |
| 1358 | { # Data provided with a pipeline or transform to provide descriptive info. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1359 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 1360 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 1361 | # will be stored with MyDoFn as the short_str_value and |
| 1362 | # com.mypackage.MyDoFn as the java_class_name value. |
| 1363 | # short_str_value can be displayed and java_class_name_value |
| 1364 | # will be displayed as a tooltip. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1365 | "durationValue": "A String", # Contains value if the data is of duration type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1366 | "url": "A String", # An optional full URL. |
| 1367 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 1368 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 1369 | # language namespace (i.e. python module) which defines the display data. |
| 1370 | # This allows a dax monitoring system to specially handle the data |
| 1371 | # and perform custom rendering. |
| 1372 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 1373 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 1374 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 1375 | "strValue": "A String", # Contains value if the data is of string type. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1376 | "key": "A String", # The key identifying the display data. |
| 1377 | # This is intended to be used as a label for the display data |
| 1378 | # when viewed in a dax monitoring system. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1379 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1380 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1381 | }, |
| 1382 | ], |
| 1383 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 1384 | "A String", |
| 1385 | ], |
| 1386 | "id": "A String", # SDK generated id of this transform instance. |
| 1387 | }, |
| 1388 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1389 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 1390 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 1391 | # stage of execution. Some composing transforms and sources may have been |
| 1392 | # generated by the Dataflow service during execution planning. |
| 1393 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 1394 | { # Description of an interstitial value between transforms in an execution |
| 1395 | # stage. |
| 1396 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 1397 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1398 | # source is most closely associated. |
| 1399 | "name": "A String", # Dataflow service generated name for this source. |
| 1400 | }, |
| 1401 | ], |
| 1402 | "kind": "A String", # Type of tranform this stage is executing. |
| 1403 | "name": "A String", # Dataflow service generated name for this stage. |
| 1404 | "outputSource": [ # Output sources for this stage. |
| 1405 | { # Description of an input or output of an execution stage. |
| 1406 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 1407 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 1408 | "name": "A String", # Dataflow service generated name for this source. |
| 1409 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1410 | # source is most closely associated. |
| 1411 | }, |
| 1412 | ], |
| 1413 | "inputSource": [ # Input sources for this stage. |
| 1414 | { # Description of an input or output of an execution stage. |
| 1415 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 1416 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 1417 | "name": "A String", # Dataflow service generated name for this source. |
| 1418 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1419 | # source is most closely associated. |
| 1420 | }, |
| 1421 | ], |
| 1422 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 1423 | { # Description of a transform executed as part of an execution stage. |
| 1424 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 1425 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 1426 | # most closely associated. |
| 1427 | "name": "A String", # Dataflow service generated name for this source. |
| 1428 | }, |
| 1429 | ], |
| 1430 | "id": "A String", # Dataflow service generated id for this stage. |
| 1431 | }, |
| 1432 | ], |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1433 | "displayData": [ # Pipeline level display data. |
| 1434 | { # Data provided with a pipeline or transform to provide descriptive info. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1435 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 1436 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 1437 | # will be stored with MyDoFn as the short_str_value and |
| 1438 | # com.mypackage.MyDoFn as the java_class_name value. |
| 1439 | # short_str_value can be displayed and java_class_name_value |
| 1440 | # will be displayed as a tooltip. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1441 | "durationValue": "A String", # Contains value if the data is of duration type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1442 | "url": "A String", # An optional full URL. |
| 1443 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 1444 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 1445 | # language namespace (i.e. python module) which defines the display data. |
| 1446 | # This allows a dax monitoring system to specially handle the data |
| 1447 | # and perform custom rendering. |
| 1448 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 1449 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 1450 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 1451 | "strValue": "A String", # Contains value if the data is of string type. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1452 | "key": "A String", # The key identifying the display data. |
| 1453 | # This is intended to be used as a label for the display data |
| 1454 | # when viewed in a dax monitoring system. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1455 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1456 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1457 | }, |
| 1458 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1459 | }, |
| 1460 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 1461 | # callers cannot mutate it. |
| 1462 | { # A message describing the state of a particular execution stage. |
| 1463 | "executionStageName": "A String", # The name of the execution stage. |
| 1464 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 1465 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 1466 | }, |
| 1467 | ], |
| 1468 | "id": "A String", # The unique ID of this job. |
| 1469 | # |
| 1470 | # This field is set by the Cloud Dataflow service when the Job is |
| 1471 | # created, and is immutable for the life of the job. |
| 1472 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 1473 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 1474 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 1475 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 1476 | # corresponding name prefixes of the new job. |
| 1477 | "a_key": "A String", |
| 1478 | }, |
| 1479 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 1480 | "version": { # A structure describing which components and their versions of the service |
| 1481 | # are required in order to run the job. |
| 1482 | "a_key": "", # Properties of the object. |
| 1483 | }, |
| 1484 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 1485 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 1486 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 1487 | # |
| 1488 | # Format: |
| 1489 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 1490 | "internalExperiments": { # Experimental settings. |
| 1491 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1492 | }, |
| 1493 | "dataset": "A String", # The dataset for the current project where various workflow |
| 1494 | # related tables are stored. |
| 1495 | # |
| 1496 | # The supported resource type is: |
| 1497 | # |
| 1498 | # Google BigQuery: |
| 1499 | # bigquery.googleapis.com/{dataset} |
| 1500 | "experiments": [ # The list of experiments to enable. |
| 1501 | "A String", |
| 1502 | ], |
| 1503 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 1504 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 1505 | # options are passed through the service and are used to recreate the |
| 1506 | # SDK pipeline options on the worker in a language agnostic and platform |
| 1507 | # independent way. |
| 1508 | "a_key": "", # Properties of the object. |
| 1509 | }, |
| 1510 | "userAgent": { # A description of the process that generated the request. |
| 1511 | "a_key": "", # Properties of the object. |
| 1512 | }, |
| 1513 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 1514 | # unspecified, the service will attempt to choose a reasonable |
| 1515 | # default. This should be in the form of the API service name, |
| 1516 | # e.g. "compute.googleapis.com". |
| 1517 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 1518 | # specified in order for the job to have workers. |
| 1519 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 1520 | # instantiated by the Cloud Dataflow service in order to perform the |
| 1521 | # computations required by a job. Note that a workflow job may use |
| 1522 | # multiple pools, in order to match the various computational |
| 1523 | # requirements of the various stages of the job. |
| 1524 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
| 1525 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 1526 | # using the standard Dataflow task runner. Users should ignore |
| 1527 | # this field. |
| 1528 | "workflowFileName": "A String", # The file to store the workflow in. |
| 1529 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 1530 | # will not be uploaded. |
| 1531 | # |
| 1532 | # The supported resource type is: |
| 1533 | # |
| 1534 | # Google Cloud Storage: |
| 1535 | # storage.googleapis.com/{bucket}/{object} |
| 1536 | # bucket.storage.googleapis.com/{object} |
| 1537 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
| 1538 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 1539 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 1540 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 1541 | # "shuffle/v1beta1". |
| 1542 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 1543 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 1544 | # |
| 1545 | # When workers access Google Cloud APIs, they logically do so via |
| 1546 | # relative URLs. If this field is specified, it supplies the base |
| 1547 | # URL to use for resolving these relative URLs. The normative |
| 1548 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1549 | # Locators". |
| 1550 | # |
| 1551 | # If not specified, the default value is "http://www.googleapis.com/" |
| 1552 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 1553 | # "dataflow/v1b3/projects". |
| 1554 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1555 | # storage. |
| 1556 | # |
| 1557 | # The supported resource type is: |
| 1558 | # |
| 1559 | # Google Cloud Storage: |
| 1560 | # |
| 1561 | # storage.googleapis.com/{bucket}/{object} |
| 1562 | # bucket.storage.googleapis.com/{object} |
| 1563 | }, |
| 1564 | "vmId": "A String", # The ID string of the VM. |
| 1565 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 1566 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 1567 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 1568 | # access the Cloud Dataflow API. |
| 1569 | "A String", |
| 1570 | ], |
| 1571 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 1572 | # taskrunner; e.g. "root". |
| 1573 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 1574 | # |
| 1575 | # When workers access Google Cloud APIs, they logically do so via |
| 1576 | # relative URLs. If this field is specified, it supplies the base |
| 1577 | # URL to use for resolving these relative URLs. The normative |
| 1578 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1579 | # Locators". |
| 1580 | # |
| 1581 | # If not specified, the default value is "http://www.googleapis.com/" |
| 1582 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 1583 | # taskrunner; e.g. "wheel". |
| 1584 | "languageHint": "A String", # The suggested backend language. |
| 1585 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 1586 | # console. |
| 1587 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 1588 | "logDir": "A String", # The directory on the VM to store logs. |
| 1589 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 1590 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 1591 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 1592 | # temporary storage. |
| 1593 | # |
| 1594 | # The supported resource type is: |
| 1595 | # |
| 1596 | # Google Cloud Storage: |
| 1597 | # storage.googleapis.com/{bucket}/{object} |
| 1598 | # bucket.storage.googleapis.com/{object} |
| 1599 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 1600 | }, |
| 1601 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 1602 | # are supported. |
| 1603 | "packages": [ # Packages to be installed on workers. |
| 1604 | { # The packages that must be installed in order for a worker to run the |
| 1605 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 1606 | # pool. |
| 1607 | # |
| 1608 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 1609 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 1610 | # might use this to install jars containing the user's code and all of the |
| 1611 | # various dependencies (libraries, data files, etc.) required in order |
| 1612 | # for that code to run. |
| 1613 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 1614 | # |
| 1615 | # Google Cloud Storage: |
| 1616 | # |
| 1617 | # storage.googleapis.com/{bucket} |
| 1618 | # bucket.storage.googleapis.com/ |
| 1619 | "name": "A String", # The name of the package. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1620 | }, |
| 1621 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1622 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 1623 | # service will attempt to choose a reasonable default. |
| 1624 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 1625 | # the service will use the network "default". |
| 1626 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 1627 | # will attempt to choose a reasonable default. |
| 1628 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 1629 | # attempt to choose a reasonable default. |
| 1630 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 1631 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 1632 | # `TEARDOWN_NEVER`. |
| 1633 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 1634 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 1635 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 1636 | # down. |
| 1637 | # |
| 1638 | # If the workers are not torn down by the service, they will |
| 1639 | # continue to run and use Google Compute Engine VM resources in the |
| 1640 | # user's project until they are explicitly terminated by the user. |
| 1641 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 1642 | # policy except for small, manually supervised test jobs. |
| 1643 | # |
| 1644 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 1645 | # default. |
| 1646 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 1647 | # Compute Engine API. |
| 1648 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 1649 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 1650 | # service will choose a number of threads (according to the number of cores |
| 1651 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 1652 | "poolArgs": { # Extra arguments for this worker pool. |
| 1653 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1654 | }, |
| 1655 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 1656 | # execute the job. If zero or unspecified, the service will |
| 1657 | # attempt to choose a reasonable default. |
| 1658 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 1659 | # harness, residing in Google Container Registry. |
| 1660 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 1661 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 1662 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 1663 | { # Describes the data disk used by a workflow job. |
| 1664 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 1665 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 1666 | # attempt to choose a reasonable default. |
| 1667 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 1668 | # must be a disk type appropriate to the project and zone in which |
| 1669 | # the workers will run. If unknown or unspecified, the service |
| 1670 | # will attempt to choose a reasonable default. |
| 1671 | # |
| 1672 | # For example, the standard persistent disk type is a resource name |
| 1673 | # typically ending in "pd-standard". If SSD persistent disks are |
| 1674 | # available, the resource name typically ends with "pd-ssd". The |
| 1675 | # actual valid values are defined the Google Compute Engine API, |
| 1676 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 1677 | # documentation for more information about determining the set of |
| 1678 | # available disk types for a particular project and zone. |
| 1679 | # |
| 1680 | # Google Compute Engine Disk types are local to a particular |
| 1681 | # project in a particular zone, and so the resource name will |
| 1682 | # typically look something like this: |
| 1683 | # |
| 1684 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1685 | }, |
| 1686 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1687 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 1688 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 1689 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 1690 | }, |
| 1691 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 1692 | # select a default set of packages which are useful to worker |
| 1693 | # harnesses written in a particular language. |
| 1694 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 1695 | # attempt to choose a reasonable default. |
| 1696 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 1697 | "a_key": "A String", |
| 1698 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1699 | }, |
| 1700 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1701 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1702 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 1703 | # this resource prefix, where {JOBNAME} is the value of the |
| 1704 | # job_name field. The resulting bucket and object prefix is used |
| 1705 | # as the prefix of the resources used to store temporary data |
| 1706 | # needed during the job execution. NOTE: This will override the |
| 1707 | # value in taskrunner_settings. |
| 1708 | # The supported resource type is: |
| 1709 | # |
| 1710 | # Google Cloud Storage: |
| 1711 | # |
| 1712 | # storage.googleapis.com/{bucket}/{object} |
| 1713 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1714 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1715 | "location": "A String", # The [regional endpoint] |
| 1716 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1717 | # contains this job. |
| 1718 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 1719 | # for temporary storage. These temporary files will be |
| 1720 | # removed on job completion. |
| 1721 | # No duplicates are allowed. |
| 1722 | # No file patterns are supported. |
| 1723 | # |
| 1724 | # The supported files are: |
| 1725 | # |
| 1726 | # Google Cloud Storage: |
| 1727 | # |
| 1728 | # storage.googleapis.com/{bucket}/{object} |
| 1729 | # bucket.storage.googleapis.com/{object} |
| 1730 | "A String", |
| 1731 | ], |
| 1732 | "type": "A String", # The type of Cloud Dataflow job. |
| 1733 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 1734 | # If this field is set, the service will ensure its uniqueness. |
| 1735 | # The request to create a job will fail if the service has knowledge of a |
| 1736 | # previously submitted job with the same client's ID and job name. |
| 1737 | # The caller may use this field to ensure idempotence of job |
| 1738 | # creation across retried attempts to create a job. |
| 1739 | # By default, the field is empty and, in that case, the service ignores it. |
| 1740 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 1741 | # snapshot. |
| 1742 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 1743 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 1744 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 1745 | # Flexible resource scheduling jobs are started with some delay after job |
| 1746 | # creation, so start_time is unset before start and is updated when the |
| 1747 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 1748 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 1749 | # service. |
| 1750 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 1751 | # Cloud Dataflow service. |
| 1752 | "requestedState": "A String", # The job's requested state. |
| 1753 | # |
| 1754 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 1755 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 1756 | # also be used to directly set a job's requested state to |
| 1757 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 1758 | # job if it has not already reached a terminal state. |
| 1759 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 1760 | # |
| 1761 | # Only one Job with a given name may exist in a project at any |
| 1762 | # given time. If a caller attempts to create a Job with the same |
| 1763 | # name as an already-existing Job, the attempt returns the |
| 1764 | # existing Job. |
| 1765 | # |
| 1766 | # The name must match the regular expression |
| 1767 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 1768 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 1769 | # |
| 1770 | # The top-level steps that constitute the entire job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1771 | { # Defines a particular step within a Cloud Dataflow job. |
| 1772 | # |
| 1773 | # A job consists of multiple steps, each of which performs some |
| 1774 | # specific operation as part of the overall job. Data is typically |
| 1775 | # passed from one step to another as part of the job. |
| 1776 | # |
| 1777 | # Here's an example of a sequence of steps which together implement a |
| 1778 | # Map-Reduce job: |
| 1779 | # |
| 1780 | # * Read a collection of data from some source, parsing the |
| 1781 | # collection's elements. |
| 1782 | # |
| 1783 | # * Validate the elements. |
| 1784 | # |
| 1785 | # * Apply a user-defined function to map each element to some value |
| 1786 | # and extract an element-specific key value. |
| 1787 | # |
| 1788 | # * Group elements with the same key into a single element with |
| 1789 | # that key, transforming a multiply-keyed collection into a |
| 1790 | # uniquely-keyed collection. |
| 1791 | # |
| 1792 | # * Write the elements out to some data sink. |
| 1793 | # |
| 1794 | # Note that the Cloud Dataflow service may be used to run many different |
| 1795 | # types of jobs, not just Map-Reduce. |
| 1796 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 1797 | "properties": { # Named properties associated with the step. Each kind of |
| 1798 | # predefined step has its own required set of properties. |
| 1799 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1800 | "a_key": "", # Properties of the object. |
| 1801 | }, |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 1802 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 1803 | # step with respect to all other steps in the Cloud Dataflow job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1804 | }, |
| 1805 | ], |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 1806 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 1807 | # of the job it replaced. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1808 | # |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 1809 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 1810 | # here. The job named here is stopped, and its intermediate state is |
| 1811 | # transferred to this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1812 | "currentState": "A String", # The current state of the job. |
| 1813 | # |
| 1814 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 1815 | # specified. |
| 1816 | # |
| 1817 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 1818 | # terminal state. After a job has reached a terminal state, no |
| 1819 | # further state updates may be made. |
| 1820 | # |
| 1821 | # This field may be mutated by the Cloud Dataflow service; |
| 1822 | # callers cannot mutate it. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1823 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 1824 | # isn't contained in the submitted job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1825 | "stages": { # A mapping from each stage to the information about that stage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1826 | "a_key": { # Contains information about how a particular |
| 1827 | # google.dataflow.v1beta3.Step will be executed. |
| 1828 | "stepName": [ # The steps associated with the execution stage. |
| 1829 | # Note that stages may have several steps, and that a given step |
| 1830 | # might be run by more than one stage. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1831 | "A String", |
| 1832 | ], |
| 1833 | }, |
| 1834 | }, |
| 1835 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1836 | }</pre> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1837 | </div> |
| 1838 | |
| 1839 | <div class="method"> |
| 1840 | <code class="details" id="getMetrics">getMetrics(projectId, location, jobId, startTime=None, x__xgafv=None)</code> |
| 1841 | <pre>Request the job status. |
| 1842 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1843 | To request the status of a job, we recommend using |
| 1844 | `projects.locations.jobs.getMetrics` with a [regional endpoint] |
| 1845 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 1846 | `projects.jobs.getMetrics` is not recommended, as you can only request the |
| 1847 | status of jobs that are running in `us-central1`. |
| 1848 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1849 | Args: |
| 1850 | projectId: string, A project id. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1851 | location: string, The [regional endpoint] |
| 1852 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1853 | contains the job specified by job_id. (required) |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1854 | jobId: string, The job to get messages for. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1855 | startTime: string, Return only metric data that has changed since this time. |
| 1856 | Default is to return all information about all metrics for the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1857 | x__xgafv: string, V1 error format. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1858 | Allowed values |
| 1859 | 1 - v1 error format |
| 1860 | 2 - v2 error format |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1861 | |
| 1862 | Returns: |
| 1863 | An object of the form: |
| 1864 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1865 | { # JobMetrics contains a collection of metrics describing the detailed progress |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1866 | # of a Dataflow job. Metrics correspond to user-defined and system-defined |
| 1867 | # metrics in the job. |
| 1868 | # |
| 1869 | # This resource captures only the most recent values of each metric; |
| 1870 | # time-series data can be queried for them (under the same metric names) |
| 1871 | # from Cloud Monitoring. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1872 | "metrics": [ # All metrics for this job. |
| 1873 | { # Describes the state of a metric. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1874 | "meanCount": "", # Worker-computed aggregate value for the "Mean" aggregation kind. |
| 1875 | # This holds the count of the aggregated values and is used in combination |
| 1876 | # with mean_sum above to obtain the actual mean aggregate value. |
| 1877 | # The only possible value type is Long. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1878 | "kind": "A String", # Metric aggregation kind. The possible metric aggregation kinds are |
| 1879 | # "Sum", "Max", "Min", "Mean", "Set", "And", "Or", and "Distribution". |
| 1880 | # The specified aggregation kind is case-insensitive. |
| 1881 | # |
| 1882 | # If omitted, this is not an aggregated value but instead |
| 1883 | # a single metric sample value. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1884 | "set": "", # Worker-computed aggregate value for the "Set" aggregation kind. The only |
| 1885 | # possible value type is a list of Values whose type can be Long, Double, |
| 1886 | # or String, according to the metric's type. All Values in the list must |
| 1887 | # be of the same type. |
| 1888 | "name": { # Identifies a metric, by describing the source which generated the # Name of the metric. |
| 1889 | # metric. |
| 1890 | "origin": "A String", # Origin (namespace) of metric name. May be blank for user-define metrics; |
| 1891 | # will be "dataflow" for metrics defined by the Dataflow service or SDK. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1892 | "name": "A String", # Worker-defined metric name. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1893 | "context": { # Zero or more labeled fields which identify the part of the job this |
| 1894 | # metric is associated with, such as the name of a step or collection. |
| 1895 | # |
| 1896 | # For example, built-in counters associated with steps will have |
| 1897 | # context['step'] = <step-name>. Counters associated with PCollections |
| 1898 | # in the SDK will have context['pcollection'] = <pcollection-name>. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1899 | "a_key": "A String", |
| 1900 | }, |
| 1901 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1902 | "meanSum": "", # Worker-computed aggregate value for the "Mean" aggregation kind. |
| 1903 | # This holds the sum of the aggregated values and is used in combination |
| 1904 | # with mean_count below to obtain the actual mean aggregate value. |
| 1905 | # The only possible value types are Long and Double. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1906 | "cumulative": True or False, # True if this metric is reported as the total cumulative aggregate |
| 1907 | # value accumulated since the worker started working on this WorkItem. |
| 1908 | # By default this is false, indicating that this metric is reported |
| 1909 | # as a delta that is not associated with any WorkItem. |
| 1910 | "updateTime": "A String", # Timestamp associated with the metric value. Optional when workers are |
| 1911 | # reporting work progress; it will be filled in responses from the |
| 1912 | # metrics API. |
| 1913 | "scalar": "", # Worker-computed aggregate value for aggregation kinds "Sum", "Max", "Min", |
| 1914 | # "And", and "Or". The possible value types are Long, Double, and Boolean. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1915 | "internal": "", # Worker-computed aggregate value for internal use by the Dataflow |
| 1916 | # service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1917 | "gauge": "", # A struct value describing properties of a Gauge. |
| 1918 | # Metrics of gauge type show the value of a metric across time, and is |
| 1919 | # aggregated based on the newest value. |
| 1920 | "distribution": "", # A struct value describing properties of a distribution of numeric values. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1921 | }, |
| 1922 | ], |
| 1923 | "metricTime": "A String", # Timestamp as of which metric values are current. |
| 1924 | }</pre> |
| 1925 | </div> |
| 1926 | |
| 1927 | <div class="method"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1928 | <code class="details" id="list">list(projectId, location, pageSize=None, pageToken=None, x__xgafv=None, filter=None, view=None)</code> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1929 | <pre>List the jobs of a project. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1930 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1931 | To list the jobs of a project in a region, we recommend using |
| 1932 | `projects.locations.jobs.get` with a [regional endpoint] |
| 1933 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). To |
| 1934 | list the all jobs across all regions, use `projects.jobs.aggregated`. Using |
| 1935 | `projects.jobs.list` is not recommended, as you can only get the list of |
| 1936 | jobs that are running in `us-central1`. |
| 1937 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1938 | Args: |
| 1939 | projectId: string, The project which owns the jobs. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1940 | location: string, The [regional endpoint] |
| 1941 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1942 | contains this job. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1943 | pageSize: integer, If there are many jobs, limit response to at most this many. |
| 1944 | The actual number of jobs returned will be the lesser of max_responses |
| 1945 | and an unspecified server-defined limit. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1946 | pageToken: string, Set this to the 'next_page_token' field of a previous response |
| 1947 | to request additional results in a long list. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1948 | x__xgafv: string, V1 error format. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1949 | Allowed values |
| 1950 | 1 - v1 error format |
| 1951 | 2 - v2 error format |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1952 | filter: string, The kind of filter to use. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1953 | view: string, Level of information requested in response. Default is `JOB_VIEW_SUMMARY`. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1954 | |
| 1955 | Returns: |
| 1956 | An object of the form: |
| 1957 | |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1958 | { # Response to a request to list Cloud Dataflow jobs. This may be a partial |
| 1959 | # response, depending on the page size in the ListJobsRequest. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1960 | "nextPageToken": "A String", # Set if there may be more results than fit in this response. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1961 | "failedLocation": [ # Zero or more messages describing the [regional endpoints] |
| 1962 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1963 | # failed to respond. |
| 1964 | { # Indicates which [regional endpoint] |
| 1965 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) failed |
| 1966 | # to respond to a request for data. |
| 1967 | "name": "A String", # The name of the [regional endpoint] |
| 1968 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1969 | # failed to respond. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1970 | }, |
| 1971 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1972 | "jobs": [ # A subset of the requested job information. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1973 | { # Defines a job to be run by the Cloud Dataflow service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1974 | "labels": { # User-defined labels for this job. |
| 1975 | # |
| 1976 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 1977 | # map are UTF8 strings that comply with the following restrictions: |
| 1978 | # |
| 1979 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 1980 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 1981 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 1982 | # size. |
| 1983 | "a_key": "A String", |
| 1984 | }, |
| 1985 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 1986 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 1987 | # views SUMMARY and higher. |
| 1988 | # ListJob response and Job SUMMARY view. |
| 1989 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 1990 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 1991 | "version": "A String", # The version of the SDK used to run the job. |
| 1992 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1993 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 1994 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 1995 | { # Metadata for a PubSub connector used by the job. |
| 1996 | "topic": "A String", # Topic accessed in the connection. |
| 1997 | "subscription": "A String", # Subscription used in the connection. |
| 1998 | }, |
| 1999 | ], |
| 2000 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 2001 | { # Metadata for a Datastore connector used by the job. |
| 2002 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2003 | "namespace": "A String", # Namespace used in the connection. |
| 2004 | }, |
| 2005 | ], |
| 2006 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 2007 | { # Metadata for a File connector used by the job. |
| 2008 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 2009 | }, |
| 2010 | ], |
| 2011 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 2012 | { # Metadata for a Spanner connector used by the job. |
| 2013 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2014 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2015 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 2016 | }, |
| 2017 | ], |
| 2018 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 2019 | { # Metadata for a BigTable connector used by the job. |
| 2020 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2021 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2022 | "tableId": "A String", # TableId accessed in the connection. |
| 2023 | }, |
| 2024 | ], |
| 2025 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 2026 | { # Metadata for a BigQuery connector used by the job. |
| 2027 | "projectId": "A String", # Project accessed in the connection. |
| 2028 | "dataset": "A String", # Dataset accessed in the connection. |
| 2029 | "table": "A String", # Table accessed in the connection. |
| 2030 | "query": "A String", # Query used to access data in the connection. |
| 2031 | }, |
| 2032 | ], |
| 2033 | }, |
| 2034 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 2035 | # A description of the user pipeline and stages through which it is executed. |
| 2036 | # Created by Cloud Dataflow service. Only retrieved with |
| 2037 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 2038 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 2039 | # the pipeline and interpreting Dataflow provided metrics. |
| 2040 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 2041 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 2042 | "kind": "A String", # Type of transform. |
| 2043 | "name": "A String", # User provided name for this transform instance. |
| 2044 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 2045 | "A String", |
| 2046 | ], |
| 2047 | "displayData": [ # Transform-specific display data. |
| 2048 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 2049 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2050 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2051 | # will be stored with MyDoFn as the short_str_value and |
| 2052 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2053 | # short_str_value can be displayed and java_class_name_value |
| 2054 | # will be displayed as a tooltip. |
| 2055 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 2056 | "url": "A String", # An optional full URL. |
| 2057 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2058 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2059 | # language namespace (i.e. python module) which defines the display data. |
| 2060 | # This allows a dax monitoring system to specially handle the data |
| 2061 | # and perform custom rendering. |
| 2062 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2063 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2064 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2065 | "strValue": "A String", # Contains value if the data is of string type. |
| 2066 | "key": "A String", # The key identifying the display data. |
| 2067 | # This is intended to be used as a label for the display data |
| 2068 | # when viewed in a dax monitoring system. |
| 2069 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 2070 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 2071 | }, |
| 2072 | ], |
| 2073 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 2074 | "A String", |
| 2075 | ], |
| 2076 | "id": "A String", # SDK generated id of this transform instance. |
| 2077 | }, |
| 2078 | ], |
| 2079 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 2080 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 2081 | # stage of execution. Some composing transforms and sources may have been |
| 2082 | # generated by the Dataflow service during execution planning. |
| 2083 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 2084 | { # Description of an interstitial value between transforms in an execution |
| 2085 | # stage. |
| 2086 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2087 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2088 | # source is most closely associated. |
| 2089 | "name": "A String", # Dataflow service generated name for this source. |
| 2090 | }, |
| 2091 | ], |
| 2092 | "kind": "A String", # Type of tranform this stage is executing. |
| 2093 | "name": "A String", # Dataflow service generated name for this stage. |
| 2094 | "outputSource": [ # Output sources for this stage. |
| 2095 | { # Description of an input or output of an execution stage. |
| 2096 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2097 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2098 | "name": "A String", # Dataflow service generated name for this source. |
| 2099 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2100 | # source is most closely associated. |
| 2101 | }, |
| 2102 | ], |
| 2103 | "inputSource": [ # Input sources for this stage. |
| 2104 | { # Description of an input or output of an execution stage. |
| 2105 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2106 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2107 | "name": "A String", # Dataflow service generated name for this source. |
| 2108 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2109 | # source is most closely associated. |
| 2110 | }, |
| 2111 | ], |
| 2112 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 2113 | { # Description of a transform executed as part of an execution stage. |
| 2114 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2115 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 2116 | # most closely associated. |
| 2117 | "name": "A String", # Dataflow service generated name for this source. |
| 2118 | }, |
| 2119 | ], |
| 2120 | "id": "A String", # Dataflow service generated id for this stage. |
| 2121 | }, |
| 2122 | ], |
| 2123 | "displayData": [ # Pipeline level display data. |
| 2124 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 2125 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2126 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2127 | # will be stored with MyDoFn as the short_str_value and |
| 2128 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2129 | # short_str_value can be displayed and java_class_name_value |
| 2130 | # will be displayed as a tooltip. |
| 2131 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 2132 | "url": "A String", # An optional full URL. |
| 2133 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2134 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2135 | # language namespace (i.e. python module) which defines the display data. |
| 2136 | # This allows a dax monitoring system to specially handle the data |
| 2137 | # and perform custom rendering. |
| 2138 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2139 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2140 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2141 | "strValue": "A String", # Contains value if the data is of string type. |
| 2142 | "key": "A String", # The key identifying the display data. |
| 2143 | # This is intended to be used as a label for the display data |
| 2144 | # when viewed in a dax monitoring system. |
| 2145 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 2146 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 2147 | }, |
| 2148 | ], |
| 2149 | }, |
| 2150 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 2151 | # callers cannot mutate it. |
| 2152 | { # A message describing the state of a particular execution stage. |
| 2153 | "executionStageName": "A String", # The name of the execution stage. |
| 2154 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 2155 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2156 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2157 | ], |
| 2158 | "id": "A String", # The unique ID of this job. |
| 2159 | # |
| 2160 | # This field is set by the Cloud Dataflow service when the Job is |
| 2161 | # created, and is immutable for the life of the job. |
| 2162 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 2163 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 2164 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 2165 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 2166 | # corresponding name prefixes of the new job. |
| 2167 | "a_key": "A String", |
| 2168 | }, |
| 2169 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 2170 | "version": { # A structure describing which components and their versions of the service |
| 2171 | # are required in order to run the job. |
| 2172 | "a_key": "", # Properties of the object. |
| 2173 | }, |
| 2174 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 2175 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 2176 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2177 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2178 | # Format: |
| 2179 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 2180 | "internalExperiments": { # Experimental settings. |
| 2181 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2182 | }, |
| 2183 | "dataset": "A String", # The dataset for the current project where various workflow |
| 2184 | # related tables are stored. |
| 2185 | # |
| 2186 | # The supported resource type is: |
| 2187 | # |
| 2188 | # Google BigQuery: |
| 2189 | # bigquery.googleapis.com/{dataset} |
| 2190 | "experiments": [ # The list of experiments to enable. |
| 2191 | "A String", |
| 2192 | ], |
| 2193 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 2194 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 2195 | # options are passed through the service and are used to recreate the |
| 2196 | # SDK pipeline options on the worker in a language agnostic and platform |
| 2197 | # independent way. |
| 2198 | "a_key": "", # Properties of the object. |
| 2199 | }, |
| 2200 | "userAgent": { # A description of the process that generated the request. |
| 2201 | "a_key": "", # Properties of the object. |
| 2202 | }, |
| 2203 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 2204 | # unspecified, the service will attempt to choose a reasonable |
| 2205 | # default. This should be in the form of the API service name, |
| 2206 | # e.g. "compute.googleapis.com". |
| 2207 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 2208 | # specified in order for the job to have workers. |
| 2209 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 2210 | # instantiated by the Cloud Dataflow service in order to perform the |
| 2211 | # computations required by a job. Note that a workflow job may use |
| 2212 | # multiple pools, in order to match the various computational |
| 2213 | # requirements of the various stages of the job. |
| 2214 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
| 2215 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 2216 | # using the standard Dataflow task runner. Users should ignore |
| 2217 | # this field. |
| 2218 | "workflowFileName": "A String", # The file to store the workflow in. |
| 2219 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 2220 | # will not be uploaded. |
| 2221 | # |
| 2222 | # The supported resource type is: |
| 2223 | # |
| 2224 | # Google Cloud Storage: |
| 2225 | # storage.googleapis.com/{bucket}/{object} |
| 2226 | # bucket.storage.googleapis.com/{object} |
| 2227 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
| 2228 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 2229 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 2230 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 2231 | # "shuffle/v1beta1". |
| 2232 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 2233 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2234 | # |
| 2235 | # When workers access Google Cloud APIs, they logically do so via |
| 2236 | # relative URLs. If this field is specified, it supplies the base |
| 2237 | # URL to use for resolving these relative URLs. The normative |
| 2238 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2239 | # Locators". |
| 2240 | # |
| 2241 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2242 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 2243 | # "dataflow/v1b3/projects". |
| 2244 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 2245 | # storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2246 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 2247 | # The supported resource type is: |
| 2248 | # |
| 2249 | # Google Cloud Storage: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2250 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 2251 | # storage.googleapis.com/{bucket}/{object} |
| 2252 | # bucket.storage.googleapis.com/{object} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2253 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2254 | "vmId": "A String", # The ID string of the VM. |
| 2255 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 2256 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 2257 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 2258 | # access the Cloud Dataflow API. |
| 2259 | "A String", |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2260 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2261 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 2262 | # taskrunner; e.g. "root". |
| 2263 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2264 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2265 | # When workers access Google Cloud APIs, they logically do so via |
| 2266 | # relative URLs. If this field is specified, it supplies the base |
| 2267 | # URL to use for resolving these relative URLs. The normative |
| 2268 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2269 | # Locators". |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2270 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2271 | # If not specified, the default value is "http://www.googleapis.com/" |
| 2272 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 2273 | # taskrunner; e.g. "wheel". |
| 2274 | "languageHint": "A String", # The suggested backend language. |
| 2275 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 2276 | # console. |
| 2277 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 2278 | "logDir": "A String", # The directory on the VM to store logs. |
| 2279 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 2280 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 2281 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 2282 | # temporary storage. |
| 2283 | # |
| 2284 | # The supported resource type is: |
| 2285 | # |
| 2286 | # Google Cloud Storage: |
| 2287 | # storage.googleapis.com/{bucket}/{object} |
| 2288 | # bucket.storage.googleapis.com/{object} |
| 2289 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 2290 | }, |
| 2291 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 2292 | # are supported. |
| 2293 | "packages": [ # Packages to be installed on workers. |
| 2294 | { # The packages that must be installed in order for a worker to run the |
| 2295 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 2296 | # pool. |
| 2297 | # |
| 2298 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 2299 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 2300 | # might use this to install jars containing the user's code and all of the |
| 2301 | # various dependencies (libraries, data files, etc.) required in order |
| 2302 | # for that code to run. |
| 2303 | "location": "A String", # The resource to read the package from. The supported resource type is: |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2304 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2305 | # Google Cloud Storage: |
| 2306 | # |
| 2307 | # storage.googleapis.com/{bucket} |
| 2308 | # bucket.storage.googleapis.com/ |
| 2309 | "name": "A String", # The name of the package. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2310 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2311 | ], |
| 2312 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 2313 | # service will attempt to choose a reasonable default. |
| 2314 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 2315 | # the service will use the network "default". |
| 2316 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 2317 | # will attempt to choose a reasonable default. |
| 2318 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 2319 | # attempt to choose a reasonable default. |
| 2320 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 2321 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 2322 | # `TEARDOWN_NEVER`. |
| 2323 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 2324 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 2325 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 2326 | # down. |
| 2327 | # |
| 2328 | # If the workers are not torn down by the service, they will |
| 2329 | # continue to run and use Google Compute Engine VM resources in the |
| 2330 | # user's project until they are explicitly terminated by the user. |
| 2331 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 2332 | # policy except for small, manually supervised test jobs. |
| 2333 | # |
| 2334 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 2335 | # default. |
| 2336 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 2337 | # Compute Engine API. |
| 2338 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 2339 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 2340 | # service will choose a number of threads (according to the number of cores |
| 2341 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 2342 | "poolArgs": { # Extra arguments for this worker pool. |
| 2343 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2344 | }, |
| 2345 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 2346 | # execute the job. If zero or unspecified, the service will |
| 2347 | # attempt to choose a reasonable default. |
| 2348 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 2349 | # harness, residing in Google Container Registry. |
| 2350 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 2351 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 2352 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 2353 | { # Describes the data disk used by a workflow job. |
| 2354 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 2355 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 2356 | # attempt to choose a reasonable default. |
| 2357 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 2358 | # must be a disk type appropriate to the project and zone in which |
| 2359 | # the workers will run. If unknown or unspecified, the service |
| 2360 | # will attempt to choose a reasonable default. |
| 2361 | # |
| 2362 | # For example, the standard persistent disk type is a resource name |
| 2363 | # typically ending in "pd-standard". If SSD persistent disks are |
| 2364 | # available, the resource name typically ends with "pd-ssd". The |
| 2365 | # actual valid values are defined the Google Compute Engine API, |
| 2366 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 2367 | # documentation for more information about determining the set of |
| 2368 | # available disk types for a particular project and zone. |
| 2369 | # |
| 2370 | # Google Compute Engine Disk types are local to a particular |
| 2371 | # project in a particular zone, and so the resource name will |
| 2372 | # typically look something like this: |
| 2373 | # |
| 2374 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2375 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2376 | ], |
| 2377 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 2378 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 2379 | "algorithm": "A String", # The algorithm to use for autoscaling. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2380 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2381 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 2382 | # select a default set of packages which are useful to worker |
| 2383 | # harnesses written in a particular language. |
| 2384 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 2385 | # attempt to choose a reasonable default. |
| 2386 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 2387 | "a_key": "A String", |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2388 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2389 | }, |
| 2390 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2391 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 2392 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 2393 | # this resource prefix, where {JOBNAME} is the value of the |
| 2394 | # job_name field. The resulting bucket and object prefix is used |
| 2395 | # as the prefix of the resources used to store temporary data |
| 2396 | # needed during the job execution. NOTE: This will override the |
| 2397 | # value in taskrunner_settings. |
| 2398 | # The supported resource type is: |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2399 | # |
| 2400 | # Google Cloud Storage: |
| 2401 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2402 | # storage.googleapis.com/{bucket}/{object} |
| 2403 | # bucket.storage.googleapis.com/{object} |
| 2404 | }, |
| 2405 | "location": "A String", # The [regional endpoint] |
| 2406 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2407 | # contains this job. |
| 2408 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 2409 | # for temporary storage. These temporary files will be |
| 2410 | # removed on job completion. |
| 2411 | # No duplicates are allowed. |
| 2412 | # No file patterns are supported. |
| 2413 | # |
| 2414 | # The supported files are: |
| 2415 | # |
| 2416 | # Google Cloud Storage: |
| 2417 | # |
| 2418 | # storage.googleapis.com/{bucket}/{object} |
| 2419 | # bucket.storage.googleapis.com/{object} |
| 2420 | "A String", |
| 2421 | ], |
| 2422 | "type": "A String", # The type of Cloud Dataflow job. |
| 2423 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 2424 | # If this field is set, the service will ensure its uniqueness. |
| 2425 | # The request to create a job will fail if the service has knowledge of a |
| 2426 | # previously submitted job with the same client's ID and job name. |
| 2427 | # The caller may use this field to ensure idempotence of job |
| 2428 | # creation across retried attempts to create a job. |
| 2429 | # By default, the field is empty and, in that case, the service ignores it. |
| 2430 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 2431 | # snapshot. |
| 2432 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 2433 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 2434 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 2435 | # Flexible resource scheduling jobs are started with some delay after job |
| 2436 | # creation, so start_time is unset before start and is updated when the |
| 2437 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 2438 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 2439 | # service. |
| 2440 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 2441 | # Cloud Dataflow service. |
| 2442 | "requestedState": "A String", # The job's requested state. |
| 2443 | # |
| 2444 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 2445 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 2446 | # also be used to directly set a job's requested state to |
| 2447 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 2448 | # job if it has not already reached a terminal state. |
| 2449 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 2450 | # |
| 2451 | # Only one Job with a given name may exist in a project at any |
| 2452 | # given time. If a caller attempts to create a Job with the same |
| 2453 | # name as an already-existing Job, the attempt returns the |
| 2454 | # existing Job. |
| 2455 | # |
| 2456 | # The name must match the regular expression |
| 2457 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 2458 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 2459 | # |
| 2460 | # The top-level steps that constitute the entire job. |
| 2461 | { # Defines a particular step within a Cloud Dataflow job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2462 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2463 | # A job consists of multiple steps, each of which performs some |
| 2464 | # specific operation as part of the overall job. Data is typically |
| 2465 | # passed from one step to another as part of the job. |
| 2466 | # |
| 2467 | # Here's an example of a sequence of steps which together implement a |
| 2468 | # Map-Reduce job: |
| 2469 | # |
| 2470 | # * Read a collection of data from some source, parsing the |
| 2471 | # collection's elements. |
| 2472 | # |
| 2473 | # * Validate the elements. |
| 2474 | # |
| 2475 | # * Apply a user-defined function to map each element to some value |
| 2476 | # and extract an element-specific key value. |
| 2477 | # |
| 2478 | # * Group elements with the same key into a single element with |
| 2479 | # that key, transforming a multiply-keyed collection into a |
| 2480 | # uniquely-keyed collection. |
| 2481 | # |
| 2482 | # * Write the elements out to some data sink. |
| 2483 | # |
| 2484 | # Note that the Cloud Dataflow service may be used to run many different |
| 2485 | # types of jobs, not just Map-Reduce. |
| 2486 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 2487 | "properties": { # Named properties associated with the step. Each kind of |
| 2488 | # predefined step has its own required set of properties. |
| 2489 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 2490 | "a_key": "", # Properties of the object. |
| 2491 | }, |
| 2492 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 2493 | # step with respect to all other steps in the Cloud Dataflow job. |
| 2494 | }, |
| 2495 | ], |
| 2496 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 2497 | # of the job it replaced. |
| 2498 | # |
| 2499 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 2500 | # here. The job named here is stopped, and its intermediate state is |
| 2501 | # transferred to this job. |
| 2502 | "currentState": "A String", # The current state of the job. |
| 2503 | # |
| 2504 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 2505 | # specified. |
| 2506 | # |
| 2507 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 2508 | # terminal state. After a job has reached a terminal state, no |
| 2509 | # further state updates may be made. |
| 2510 | # |
| 2511 | # This field may be mutated by the Cloud Dataflow service; |
| 2512 | # callers cannot mutate it. |
| 2513 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 2514 | # isn't contained in the submitted job. |
| 2515 | "stages": { # A mapping from each stage to the information about that stage. |
| 2516 | "a_key": { # Contains information about how a particular |
| 2517 | # google.dataflow.v1beta3.Step will be executed. |
| 2518 | "stepName": [ # The steps associated with the execution stage. |
| 2519 | # Note that stages may have several steps, and that a given step |
| 2520 | # might be run by more than one stage. |
| 2521 | "A String", |
| 2522 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2523 | }, |
| 2524 | }, |
| 2525 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2526 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2527 | ], |
| 2528 | }</pre> |
| 2529 | </div> |
| 2530 | |
| 2531 | <div class="method"> |
| 2532 | <code class="details" id="list_next">list_next(previous_request, previous_response)</code> |
| 2533 | <pre>Retrieves the next page of results. |
| 2534 | |
| 2535 | Args: |
| 2536 | previous_request: The request for the previous page. (required) |
| 2537 | previous_response: The response from the request for the previous page. (required) |
| 2538 | |
| 2539 | Returns: |
| 2540 | A request object that you can call 'execute()' on to request the next |
| 2541 | page. Returns None if there are no more items in the collection. |
| 2542 | </pre> |
| 2543 | </div> |
| 2544 | |
| 2545 | <div class="method"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2546 | <code class="details" id="snapshot">snapshot(projectId, location, jobId, body, x__xgafv=None)</code> |
| 2547 | <pre>Snapshot the state of a streaming job. |
| 2548 | |
| 2549 | Args: |
| 2550 | projectId: string, The project which owns the job to be snapshotted. (required) |
| 2551 | location: string, The location that contains this job. (required) |
| 2552 | jobId: string, The job to be snapshotted. (required) |
| 2553 | body: object, The request body. (required) |
| 2554 | The object takes the form of: |
| 2555 | |
| 2556 | { # Request to create a snapshot of a job. |
| 2557 | "location": "A String", # The location that contains this job. |
| 2558 | "ttl": "A String", # TTL for the snapshot. |
| 2559 | } |
| 2560 | |
| 2561 | x__xgafv: string, V1 error format. |
| 2562 | Allowed values |
| 2563 | 1 - v1 error format |
| 2564 | 2 - v2 error format |
| 2565 | |
| 2566 | Returns: |
| 2567 | An object of the form: |
| 2568 | |
| 2569 | { # Represents a snapshot of a job. |
| 2570 | "sourceJobId": "A String", # The job this snapshot was created from. |
| 2571 | "projectId": "A String", # The project this snapshot belongs to. |
| 2572 | "creationTime": "A String", # The time this snapshot was created. |
| 2573 | "state": "A String", # State of the snapshot. |
| 2574 | "ttl": "A String", # The time after which this snapshot will be automatically deleted. |
| 2575 | "id": "A String", # The unique ID of this snapshot. |
| 2576 | }</pre> |
| 2577 | </div> |
| 2578 | |
| 2579 | <div class="method"> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2580 | <code class="details" id="update">update(projectId, location, jobId, body, x__xgafv=None)</code> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2581 | <pre>Updates the state of an existing Cloud Dataflow job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2582 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2583 | To update the state of an existing job, we recommend using |
| 2584 | `projects.locations.jobs.update` with a [regional endpoint] |
| 2585 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 2586 | `projects.jobs.update` is not recommended, as you can only update the state |
| 2587 | of jobs that are running in `us-central1`. |
| 2588 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2589 | Args: |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2590 | projectId: string, The ID of the Cloud Platform project that the job belongs to. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2591 | location: string, The [regional endpoint] |
| 2592 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2593 | contains this job. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2594 | jobId: string, The job ID. (required) |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2595 | body: object, The request body. (required) |
| 2596 | The object takes the form of: |
| 2597 | |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2598 | { # Defines a job to be run by the Cloud Dataflow service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 2599 | "labels": { # User-defined labels for this job. |
| 2600 | # |
| 2601 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 2602 | # map are UTF8 strings that comply with the following restrictions: |
| 2603 | # |
| 2604 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 2605 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 2606 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 2607 | # size. |
| 2608 | "a_key": "A String", |
| 2609 | }, |
| 2610 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 2611 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 2612 | # views SUMMARY and higher. |
| 2613 | # ListJob response and Job SUMMARY view. |
| 2614 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 2615 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 2616 | "version": "A String", # The version of the SDK used to run the job. |
| 2617 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 2618 | }, |
| 2619 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 2620 | { # Metadata for a PubSub connector used by the job. |
| 2621 | "topic": "A String", # Topic accessed in the connection. |
| 2622 | "subscription": "A String", # Subscription used in the connection. |
| 2623 | }, |
| 2624 | ], |
| 2625 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 2626 | { # Metadata for a Datastore connector used by the job. |
| 2627 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2628 | "namespace": "A String", # Namespace used in the connection. |
| 2629 | }, |
| 2630 | ], |
| 2631 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 2632 | { # Metadata for a File connector used by the job. |
| 2633 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 2634 | }, |
| 2635 | ], |
| 2636 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 2637 | { # Metadata for a Spanner connector used by the job. |
| 2638 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2639 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2640 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 2641 | }, |
| 2642 | ], |
| 2643 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 2644 | { # Metadata for a BigTable connector used by the job. |
| 2645 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2646 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2647 | "tableId": "A String", # TableId accessed in the connection. |
| 2648 | }, |
| 2649 | ], |
| 2650 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 2651 | { # Metadata for a BigQuery connector used by the job. |
| 2652 | "projectId": "A String", # Project accessed in the connection. |
| 2653 | "dataset": "A String", # Dataset accessed in the connection. |
| 2654 | "table": "A String", # Table accessed in the connection. |
| 2655 | "query": "A String", # Query used to access data in the connection. |
| 2656 | }, |
| 2657 | ], |
| 2658 | }, |
| 2659 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 2660 | # A description of the user pipeline and stages through which it is executed. |
| 2661 | # Created by Cloud Dataflow service. Only retrieved with |
| 2662 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 2663 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 2664 | # the pipeline and interpreting Dataflow provided metrics. |
| 2665 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 2666 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 2667 | "kind": "A String", # Type of transform. |
| 2668 | "name": "A String", # User provided name for this transform instance. |
| 2669 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 2670 | "A String", |
| 2671 | ], |
| 2672 | "displayData": [ # Transform-specific display data. |
| 2673 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 2674 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2675 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2676 | # will be stored with MyDoFn as the short_str_value and |
| 2677 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2678 | # short_str_value can be displayed and java_class_name_value |
| 2679 | # will be displayed as a tooltip. |
| 2680 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 2681 | "url": "A String", # An optional full URL. |
| 2682 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2683 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2684 | # language namespace (i.e. python module) which defines the display data. |
| 2685 | # This allows a dax monitoring system to specially handle the data |
| 2686 | # and perform custom rendering. |
| 2687 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2688 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2689 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2690 | "strValue": "A String", # Contains value if the data is of string type. |
| 2691 | "key": "A String", # The key identifying the display data. |
| 2692 | # This is intended to be used as a label for the display data |
| 2693 | # when viewed in a dax monitoring system. |
| 2694 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 2695 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 2696 | }, |
| 2697 | ], |
| 2698 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 2699 | "A String", |
| 2700 | ], |
| 2701 | "id": "A String", # SDK generated id of this transform instance. |
| 2702 | }, |
| 2703 | ], |
| 2704 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 2705 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 2706 | # stage of execution. Some composing transforms and sources may have been |
| 2707 | # generated by the Dataflow service during execution planning. |
| 2708 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 2709 | { # Description of an interstitial value between transforms in an execution |
| 2710 | # stage. |
| 2711 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2712 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2713 | # source is most closely associated. |
| 2714 | "name": "A String", # Dataflow service generated name for this source. |
| 2715 | }, |
| 2716 | ], |
| 2717 | "kind": "A String", # Type of tranform this stage is executing. |
| 2718 | "name": "A String", # Dataflow service generated name for this stage. |
| 2719 | "outputSource": [ # Output sources for this stage. |
| 2720 | { # Description of an input or output of an execution stage. |
| 2721 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2722 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2723 | "name": "A String", # Dataflow service generated name for this source. |
| 2724 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2725 | # source is most closely associated. |
| 2726 | }, |
| 2727 | ], |
| 2728 | "inputSource": [ # Input sources for this stage. |
| 2729 | { # Description of an input or output of an execution stage. |
| 2730 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2731 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2732 | "name": "A String", # Dataflow service generated name for this source. |
| 2733 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2734 | # source is most closely associated. |
| 2735 | }, |
| 2736 | ], |
| 2737 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 2738 | { # Description of a transform executed as part of an execution stage. |
| 2739 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2740 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 2741 | # most closely associated. |
| 2742 | "name": "A String", # Dataflow service generated name for this source. |
| 2743 | }, |
| 2744 | ], |
| 2745 | "id": "A String", # Dataflow service generated id for this stage. |
| 2746 | }, |
| 2747 | ], |
| 2748 | "displayData": [ # Pipeline level display data. |
| 2749 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 2750 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2751 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2752 | # will be stored with MyDoFn as the short_str_value and |
| 2753 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2754 | # short_str_value can be displayed and java_class_name_value |
| 2755 | # will be displayed as a tooltip. |
| 2756 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 2757 | "url": "A String", # An optional full URL. |
| 2758 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2759 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2760 | # language namespace (i.e. python module) which defines the display data. |
| 2761 | # This allows a dax monitoring system to specially handle the data |
| 2762 | # and perform custom rendering. |
| 2763 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2764 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2765 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2766 | "strValue": "A String", # Contains value if the data is of string type. |
| 2767 | "key": "A String", # The key identifying the display data. |
| 2768 | # This is intended to be used as a label for the display data |
| 2769 | # when viewed in a dax monitoring system. |
| 2770 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 2771 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 2772 | }, |
| 2773 | ], |
| 2774 | }, |
| 2775 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 2776 | # callers cannot mutate it. |
| 2777 | { # A message describing the state of a particular execution stage. |
| 2778 | "executionStageName": "A String", # The name of the execution stage. |
| 2779 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 2780 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 2781 | }, |
| 2782 | ], |
| 2783 | "id": "A String", # The unique ID of this job. |
| 2784 | # |
| 2785 | # This field is set by the Cloud Dataflow service when the Job is |
| 2786 | # created, and is immutable for the life of the job. |
| 2787 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 2788 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 2789 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 2790 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 2791 | # corresponding name prefixes of the new job. |
| 2792 | "a_key": "A String", |
| 2793 | }, |
| 2794 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 2795 | "version": { # A structure describing which components and their versions of the service |
| 2796 | # are required in order to run the job. |
| 2797 | "a_key": "", # Properties of the object. |
| 2798 | }, |
| 2799 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 2800 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 2801 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 2802 | # |
| 2803 | # Format: |
| 2804 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 2805 | "internalExperiments": { # Experimental settings. |
| 2806 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2807 | }, |
| 2808 | "dataset": "A String", # The dataset for the current project where various workflow |
| 2809 | # related tables are stored. |
| 2810 | # |
| 2811 | # The supported resource type is: |
| 2812 | # |
| 2813 | # Google BigQuery: |
| 2814 | # bigquery.googleapis.com/{dataset} |
| 2815 | "experiments": [ # The list of experiments to enable. |
| 2816 | "A String", |
| 2817 | ], |
| 2818 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 2819 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 2820 | # options are passed through the service and are used to recreate the |
| 2821 | # SDK pipeline options on the worker in a language agnostic and platform |
| 2822 | # independent way. |
| 2823 | "a_key": "", # Properties of the object. |
| 2824 | }, |
| 2825 | "userAgent": { # A description of the process that generated the request. |
| 2826 | "a_key": "", # Properties of the object. |
| 2827 | }, |
| 2828 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 2829 | # unspecified, the service will attempt to choose a reasonable |
| 2830 | # default. This should be in the form of the API service name, |
| 2831 | # e.g. "compute.googleapis.com". |
| 2832 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 2833 | # specified in order for the job to have workers. |
| 2834 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 2835 | # instantiated by the Cloud Dataflow service in order to perform the |
| 2836 | # computations required by a job. Note that a workflow job may use |
| 2837 | # multiple pools, in order to match the various computational |
| 2838 | # requirements of the various stages of the job. |
| 2839 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
| 2840 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 2841 | # using the standard Dataflow task runner. Users should ignore |
| 2842 | # this field. |
| 2843 | "workflowFileName": "A String", # The file to store the workflow in. |
| 2844 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 2845 | # will not be uploaded. |
| 2846 | # |
| 2847 | # The supported resource type is: |
| 2848 | # |
| 2849 | # Google Cloud Storage: |
| 2850 | # storage.googleapis.com/{bucket}/{object} |
| 2851 | # bucket.storage.googleapis.com/{object} |
| 2852 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
| 2853 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 2854 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 2855 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 2856 | # "shuffle/v1beta1". |
| 2857 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 2858 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 2859 | # |
| 2860 | # When workers access Google Cloud APIs, they logically do so via |
| 2861 | # relative URLs. If this field is specified, it supplies the base |
| 2862 | # URL to use for resolving these relative URLs. The normative |
| 2863 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2864 | # Locators". |
| 2865 | # |
| 2866 | # If not specified, the default value is "http://www.googleapis.com/" |
| 2867 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 2868 | # "dataflow/v1b3/projects". |
| 2869 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 2870 | # storage. |
| 2871 | # |
| 2872 | # The supported resource type is: |
| 2873 | # |
| 2874 | # Google Cloud Storage: |
| 2875 | # |
| 2876 | # storage.googleapis.com/{bucket}/{object} |
| 2877 | # bucket.storage.googleapis.com/{object} |
| 2878 | }, |
| 2879 | "vmId": "A String", # The ID string of the VM. |
| 2880 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 2881 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 2882 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 2883 | # access the Cloud Dataflow API. |
| 2884 | "A String", |
| 2885 | ], |
| 2886 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 2887 | # taskrunner; e.g. "root". |
| 2888 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 2889 | # |
| 2890 | # When workers access Google Cloud APIs, they logically do so via |
| 2891 | # relative URLs. If this field is specified, it supplies the base |
| 2892 | # URL to use for resolving these relative URLs. The normative |
| 2893 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2894 | # Locators". |
| 2895 | # |
| 2896 | # If not specified, the default value is "http://www.googleapis.com/" |
| 2897 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 2898 | # taskrunner; e.g. "wheel". |
| 2899 | "languageHint": "A String", # The suggested backend language. |
| 2900 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 2901 | # console. |
| 2902 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 2903 | "logDir": "A String", # The directory on the VM to store logs. |
| 2904 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 2905 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 2906 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 2907 | # temporary storage. |
| 2908 | # |
| 2909 | # The supported resource type is: |
| 2910 | # |
| 2911 | # Google Cloud Storage: |
| 2912 | # storage.googleapis.com/{bucket}/{object} |
| 2913 | # bucket.storage.googleapis.com/{object} |
| 2914 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 2915 | }, |
| 2916 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 2917 | # are supported. |
| 2918 | "packages": [ # Packages to be installed on workers. |
| 2919 | { # The packages that must be installed in order for a worker to run the |
| 2920 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 2921 | # pool. |
| 2922 | # |
| 2923 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 2924 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 2925 | # might use this to install jars containing the user's code and all of the |
| 2926 | # various dependencies (libraries, data files, etc.) required in order |
| 2927 | # for that code to run. |
| 2928 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 2929 | # |
| 2930 | # Google Cloud Storage: |
| 2931 | # |
| 2932 | # storage.googleapis.com/{bucket} |
| 2933 | # bucket.storage.googleapis.com/ |
| 2934 | "name": "A String", # The name of the package. |
| 2935 | }, |
| 2936 | ], |
| 2937 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 2938 | # service will attempt to choose a reasonable default. |
| 2939 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 2940 | # the service will use the network "default". |
| 2941 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 2942 | # will attempt to choose a reasonable default. |
| 2943 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 2944 | # attempt to choose a reasonable default. |
| 2945 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 2946 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 2947 | # `TEARDOWN_NEVER`. |
| 2948 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 2949 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 2950 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 2951 | # down. |
| 2952 | # |
| 2953 | # If the workers are not torn down by the service, they will |
| 2954 | # continue to run and use Google Compute Engine VM resources in the |
| 2955 | # user's project until they are explicitly terminated by the user. |
| 2956 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 2957 | # policy except for small, manually supervised test jobs. |
| 2958 | # |
| 2959 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 2960 | # default. |
| 2961 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 2962 | # Compute Engine API. |
| 2963 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 2964 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 2965 | # service will choose a number of threads (according to the number of cores |
| 2966 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 2967 | "poolArgs": { # Extra arguments for this worker pool. |
| 2968 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2969 | }, |
| 2970 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 2971 | # execute the job. If zero or unspecified, the service will |
| 2972 | # attempt to choose a reasonable default. |
| 2973 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 2974 | # harness, residing in Google Container Registry. |
| 2975 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 2976 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 2977 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 2978 | { # Describes the data disk used by a workflow job. |
| 2979 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 2980 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 2981 | # attempt to choose a reasonable default. |
| 2982 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 2983 | # must be a disk type appropriate to the project and zone in which |
| 2984 | # the workers will run. If unknown or unspecified, the service |
| 2985 | # will attempt to choose a reasonable default. |
| 2986 | # |
| 2987 | # For example, the standard persistent disk type is a resource name |
| 2988 | # typically ending in "pd-standard". If SSD persistent disks are |
| 2989 | # available, the resource name typically ends with "pd-ssd". The |
| 2990 | # actual valid values are defined the Google Compute Engine API, |
| 2991 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 2992 | # documentation for more information about determining the set of |
| 2993 | # available disk types for a particular project and zone. |
| 2994 | # |
| 2995 | # Google Compute Engine Disk types are local to a particular |
| 2996 | # project in a particular zone, and so the resource name will |
| 2997 | # typically look something like this: |
| 2998 | # |
| 2999 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
| 3000 | }, |
| 3001 | ], |
| 3002 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 3003 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 3004 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 3005 | }, |
| 3006 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 3007 | # select a default set of packages which are useful to worker |
| 3008 | # harnesses written in a particular language. |
| 3009 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 3010 | # attempt to choose a reasonable default. |
| 3011 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 3012 | "a_key": "A String", |
| 3013 | }, |
| 3014 | }, |
| 3015 | ], |
| 3016 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3017 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 3018 | # this resource prefix, where {JOBNAME} is the value of the |
| 3019 | # job_name field. The resulting bucket and object prefix is used |
| 3020 | # as the prefix of the resources used to store temporary data |
| 3021 | # needed during the job execution. NOTE: This will override the |
| 3022 | # value in taskrunner_settings. |
| 3023 | # The supported resource type is: |
| 3024 | # |
| 3025 | # Google Cloud Storage: |
| 3026 | # |
| 3027 | # storage.googleapis.com/{bucket}/{object} |
| 3028 | # bucket.storage.googleapis.com/{object} |
| 3029 | }, |
| 3030 | "location": "A String", # The [regional endpoint] |
| 3031 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 3032 | # contains this job. |
| 3033 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 3034 | # for temporary storage. These temporary files will be |
| 3035 | # removed on job completion. |
| 3036 | # No duplicates are allowed. |
| 3037 | # No file patterns are supported. |
| 3038 | # |
| 3039 | # The supported files are: |
| 3040 | # |
| 3041 | # Google Cloud Storage: |
| 3042 | # |
| 3043 | # storage.googleapis.com/{bucket}/{object} |
| 3044 | # bucket.storage.googleapis.com/{object} |
| 3045 | "A String", |
| 3046 | ], |
| 3047 | "type": "A String", # The type of Cloud Dataflow job. |
| 3048 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 3049 | # If this field is set, the service will ensure its uniqueness. |
| 3050 | # The request to create a job will fail if the service has knowledge of a |
| 3051 | # previously submitted job with the same client's ID and job name. |
| 3052 | # The caller may use this field to ensure idempotence of job |
| 3053 | # creation across retried attempts to create a job. |
| 3054 | # By default, the field is empty and, in that case, the service ignores it. |
| 3055 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 3056 | # snapshot. |
| 3057 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 3058 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 3059 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 3060 | # Flexible resource scheduling jobs are started with some delay after job |
| 3061 | # creation, so start_time is unset before start and is updated when the |
| 3062 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 3063 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 3064 | # service. |
| 3065 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 3066 | # Cloud Dataflow service. |
| 3067 | "requestedState": "A String", # The job's requested state. |
| 3068 | # |
| 3069 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 3070 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 3071 | # also be used to directly set a job's requested state to |
| 3072 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 3073 | # job if it has not already reached a terminal state. |
| 3074 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 3075 | # |
| 3076 | # Only one Job with a given name may exist in a project at any |
| 3077 | # given time. If a caller attempts to create a Job with the same |
| 3078 | # name as an already-existing Job, the attempt returns the |
| 3079 | # existing Job. |
| 3080 | # |
| 3081 | # The name must match the regular expression |
| 3082 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 3083 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 3084 | # |
| 3085 | # The top-level steps that constitute the entire job. |
| 3086 | { # Defines a particular step within a Cloud Dataflow job. |
| 3087 | # |
| 3088 | # A job consists of multiple steps, each of which performs some |
| 3089 | # specific operation as part of the overall job. Data is typically |
| 3090 | # passed from one step to another as part of the job. |
| 3091 | # |
| 3092 | # Here's an example of a sequence of steps which together implement a |
| 3093 | # Map-Reduce job: |
| 3094 | # |
| 3095 | # * Read a collection of data from some source, parsing the |
| 3096 | # collection's elements. |
| 3097 | # |
| 3098 | # * Validate the elements. |
| 3099 | # |
| 3100 | # * Apply a user-defined function to map each element to some value |
| 3101 | # and extract an element-specific key value. |
| 3102 | # |
| 3103 | # * Group elements with the same key into a single element with |
| 3104 | # that key, transforming a multiply-keyed collection into a |
| 3105 | # uniquely-keyed collection. |
| 3106 | # |
| 3107 | # * Write the elements out to some data sink. |
| 3108 | # |
| 3109 | # Note that the Cloud Dataflow service may be used to run many different |
| 3110 | # types of jobs, not just Map-Reduce. |
| 3111 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 3112 | "properties": { # Named properties associated with the step. Each kind of |
| 3113 | # predefined step has its own required set of properties. |
| 3114 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 3115 | "a_key": "", # Properties of the object. |
| 3116 | }, |
| 3117 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 3118 | # step with respect to all other steps in the Cloud Dataflow job. |
| 3119 | }, |
| 3120 | ], |
| 3121 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 3122 | # of the job it replaced. |
| 3123 | # |
| 3124 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 3125 | # here. The job named here is stopped, and its intermediate state is |
| 3126 | # transferred to this job. |
| 3127 | "currentState": "A String", # The current state of the job. |
| 3128 | # |
| 3129 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 3130 | # specified. |
| 3131 | # |
| 3132 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 3133 | # terminal state. After a job has reached a terminal state, no |
| 3134 | # further state updates may be made. |
| 3135 | # |
| 3136 | # This field may be mutated by the Cloud Dataflow service; |
| 3137 | # callers cannot mutate it. |
| 3138 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 3139 | # isn't contained in the submitted job. |
| 3140 | "stages": { # A mapping from each stage to the information about that stage. |
| 3141 | "a_key": { # Contains information about how a particular |
| 3142 | # google.dataflow.v1beta3.Step will be executed. |
| 3143 | "stepName": [ # The steps associated with the execution stage. |
| 3144 | # Note that stages may have several steps, and that a given step |
| 3145 | # might be run by more than one stage. |
| 3146 | "A String", |
| 3147 | ], |
| 3148 | }, |
| 3149 | }, |
| 3150 | }, |
| 3151 | } |
| 3152 | |
| 3153 | x__xgafv: string, V1 error format. |
| 3154 | Allowed values |
| 3155 | 1 - v1 error format |
| 3156 | 2 - v2 error format |
| 3157 | |
| 3158 | Returns: |
| 3159 | An object of the form: |
| 3160 | |
| 3161 | { # Defines a job to be run by the Cloud Dataflow service. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3162 | "labels": { # User-defined labels for this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3163 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3164 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 3165 | # map are UTF8 strings that comply with the following restrictions: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3166 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3167 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 3168 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
| 3169 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
| 3170 | # size. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3171 | "a_key": "A String", |
| 3172 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3173 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 3174 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 3175 | # views SUMMARY and higher. |
| 3176 | # ListJob response and Job SUMMARY view. |
| 3177 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 3178 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 3179 | "version": "A String", # The version of the SDK used to run the job. |
| 3180 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 3181 | }, |
| 3182 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 3183 | { # Metadata for a PubSub connector used by the job. |
| 3184 | "topic": "A String", # Topic accessed in the connection. |
| 3185 | "subscription": "A String", # Subscription used in the connection. |
| 3186 | }, |
| 3187 | ], |
| 3188 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 3189 | { # Metadata for a Datastore connector used by the job. |
| 3190 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3191 | "namespace": "A String", # Namespace used in the connection. |
| 3192 | }, |
| 3193 | ], |
| 3194 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 3195 | { # Metadata for a File connector used by the job. |
| 3196 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 3197 | }, |
| 3198 | ], |
| 3199 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 3200 | { # Metadata for a Spanner connector used by the job. |
| 3201 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 3202 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3203 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 3204 | }, |
| 3205 | ], |
| 3206 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 3207 | { # Metadata for a BigTable connector used by the job. |
| 3208 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 3209 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3210 | "tableId": "A String", # TableId accessed in the connection. |
| 3211 | }, |
| 3212 | ], |
| 3213 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 3214 | { # Metadata for a BigQuery connector used by the job. |
| 3215 | "projectId": "A String", # Project accessed in the connection. |
| 3216 | "dataset": "A String", # Dataset accessed in the connection. |
| 3217 | "table": "A String", # Table accessed in the connection. |
| 3218 | "query": "A String", # Query used to access data in the connection. |
| 3219 | }, |
| 3220 | ], |
| 3221 | }, |
| 3222 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 3223 | # A description of the user pipeline and stages through which it is executed. |
| 3224 | # Created by Cloud Dataflow service. Only retrieved with |
| 3225 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 3226 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 3227 | # the pipeline and interpreting Dataflow provided metrics. |
| 3228 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 3229 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 3230 | "kind": "A String", # Type of transform. |
| 3231 | "name": "A String", # User provided name for this transform instance. |
| 3232 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 3233 | "A String", |
| 3234 | ], |
| 3235 | "displayData": [ # Transform-specific display data. |
| 3236 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 3237 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 3238 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 3239 | # will be stored with MyDoFn as the short_str_value and |
| 3240 | # com.mypackage.MyDoFn as the java_class_name value. |
| 3241 | # short_str_value can be displayed and java_class_name_value |
| 3242 | # will be displayed as a tooltip. |
| 3243 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 3244 | "url": "A String", # An optional full URL. |
| 3245 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 3246 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 3247 | # language namespace (i.e. python module) which defines the display data. |
| 3248 | # This allows a dax monitoring system to specially handle the data |
| 3249 | # and perform custom rendering. |
| 3250 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 3251 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 3252 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 3253 | "strValue": "A String", # Contains value if the data is of string type. |
| 3254 | "key": "A String", # The key identifying the display data. |
| 3255 | # This is intended to be used as a label for the display data |
| 3256 | # when viewed in a dax monitoring system. |
| 3257 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 3258 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 3259 | }, |
| 3260 | ], |
| 3261 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 3262 | "A String", |
| 3263 | ], |
| 3264 | "id": "A String", # SDK generated id of this transform instance. |
| 3265 | }, |
| 3266 | ], |
| 3267 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 3268 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 3269 | # stage of execution. Some composing transforms and sources may have been |
| 3270 | # generated by the Dataflow service during execution planning. |
| 3271 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 3272 | { # Description of an interstitial value between transforms in an execution |
| 3273 | # stage. |
| 3274 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 3275 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3276 | # source is most closely associated. |
| 3277 | "name": "A String", # Dataflow service generated name for this source. |
| 3278 | }, |
| 3279 | ], |
| 3280 | "kind": "A String", # Type of tranform this stage is executing. |
| 3281 | "name": "A String", # Dataflow service generated name for this stage. |
| 3282 | "outputSource": [ # Output sources for this stage. |
| 3283 | { # Description of an input or output of an execution stage. |
| 3284 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 3285 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 3286 | "name": "A String", # Dataflow service generated name for this source. |
| 3287 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3288 | # source is most closely associated. |
| 3289 | }, |
| 3290 | ], |
| 3291 | "inputSource": [ # Input sources for this stage. |
| 3292 | { # Description of an input or output of an execution stage. |
| 3293 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 3294 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 3295 | "name": "A String", # Dataflow service generated name for this source. |
| 3296 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3297 | # source is most closely associated. |
| 3298 | }, |
| 3299 | ], |
| 3300 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 3301 | { # Description of a transform executed as part of an execution stage. |
| 3302 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 3303 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 3304 | # most closely associated. |
| 3305 | "name": "A String", # Dataflow service generated name for this source. |
| 3306 | }, |
| 3307 | ], |
| 3308 | "id": "A String", # Dataflow service generated id for this stage. |
| 3309 | }, |
| 3310 | ], |
| 3311 | "displayData": [ # Pipeline level display data. |
| 3312 | { # Data provided with a pipeline or transform to provide descriptive info. |
| 3313 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 3314 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 3315 | # will be stored with MyDoFn as the short_str_value and |
| 3316 | # com.mypackage.MyDoFn as the java_class_name value. |
| 3317 | # short_str_value can be displayed and java_class_name_value |
| 3318 | # will be displayed as a tooltip. |
| 3319 | "durationValue": "A String", # Contains value if the data is of duration type. |
| 3320 | "url": "A String", # An optional full URL. |
| 3321 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 3322 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 3323 | # language namespace (i.e. python module) which defines the display data. |
| 3324 | # This allows a dax monitoring system to specially handle the data |
| 3325 | # and perform custom rendering. |
| 3326 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 3327 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 3328 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 3329 | "strValue": "A String", # Contains value if the data is of string type. |
| 3330 | "key": "A String", # The key identifying the display data. |
| 3331 | # This is intended to be used as a label for the display data |
| 3332 | # when viewed in a dax monitoring system. |
| 3333 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 3334 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
| 3335 | }, |
| 3336 | ], |
| 3337 | }, |
| 3338 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 3339 | # callers cannot mutate it. |
| 3340 | { # A message describing the state of a particular execution stage. |
| 3341 | "executionStageName": "A String", # The name of the execution stage. |
| 3342 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 3343 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 3344 | }, |
| 3345 | ], |
| 3346 | "id": "A String", # The unique ID of this job. |
| 3347 | # |
| 3348 | # This field is set by the Cloud Dataflow service when the Job is |
| 3349 | # created, and is immutable for the life of the job. |
| 3350 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 3351 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 3352 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3353 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 3354 | # corresponding name prefixes of the new job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3355 | "a_key": "A String", |
| 3356 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3357 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
| 3358 | "version": { # A structure describing which components and their versions of the service |
| 3359 | # are required in order to run the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3360 | "a_key": "", # Properties of the object. |
| 3361 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3362 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 3363 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 3364 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3365 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3366 | # Format: |
| 3367 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3368 | "internalExperiments": { # Experimental settings. |
| 3369 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 3370 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3371 | "dataset": "A String", # The dataset for the current project where various workflow |
| 3372 | # related tables are stored. |
| 3373 | # |
| 3374 | # The supported resource type is: |
| 3375 | # |
| 3376 | # Google BigQuery: |
| 3377 | # bigquery.googleapis.com/{dataset} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3378 | "experiments": [ # The list of experiments to enable. |
| 3379 | "A String", |
| 3380 | ], |
| 3381 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3382 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 3383 | # options are passed through the service and are used to recreate the |
| 3384 | # SDK pipeline options on the worker in a language agnostic and platform |
| 3385 | # independent way. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3386 | "a_key": "", # Properties of the object. |
| 3387 | }, |
| 3388 | "userAgent": { # A description of the process that generated the request. |
| 3389 | "a_key": "", # Properties of the object. |
| 3390 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3391 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 3392 | # unspecified, the service will attempt to choose a reasonable |
| 3393 | # default. This should be in the form of the API service name, |
| 3394 | # e.g. "compute.googleapis.com". |
| 3395 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 3396 | # specified in order for the job to have workers. |
| 3397 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 3398 | # instantiated by the Cloud Dataflow service in order to perform the |
| 3399 | # computations required by a job. Note that a workflow job may use |
| 3400 | # multiple pools, in order to match the various computational |
| 3401 | # requirements of the various stages of the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3402 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3403 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 3404 | # using the standard Dataflow task runner. Users should ignore |
| 3405 | # this field. |
| 3406 | "workflowFileName": "A String", # The file to store the workflow in. |
| 3407 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 3408 | # will not be uploaded. |
| 3409 | # |
| 3410 | # The supported resource type is: |
| 3411 | # |
| 3412 | # Google Cloud Storage: |
| 3413 | # storage.googleapis.com/{bucket}/{object} |
| 3414 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3415 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3416 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 3417 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 3418 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 3419 | # "shuffle/v1beta1". |
| 3420 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 3421 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 3422 | # |
| 3423 | # When workers access Google Cloud APIs, they logically do so via |
| 3424 | # relative URLs. If this field is specified, it supplies the base |
| 3425 | # URL to use for resolving these relative URLs. The normative |
| 3426 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3427 | # Locators". |
| 3428 | # |
| 3429 | # If not specified, the default value is "http://www.googleapis.com/" |
| 3430 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 3431 | # "dataflow/v1b3/projects". |
| 3432 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3433 | # storage. |
| 3434 | # |
| 3435 | # The supported resource type is: |
| 3436 | # |
| 3437 | # Google Cloud Storage: |
| 3438 | # |
| 3439 | # storage.googleapis.com/{bucket}/{object} |
| 3440 | # bucket.storage.googleapis.com/{object} |
| 3441 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3442 | "vmId": "A String", # The ID string of the VM. |
| 3443 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 3444 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 3445 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 3446 | # access the Cloud Dataflow API. |
| 3447 | "A String", |
| 3448 | ], |
| 3449 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 3450 | # taskrunner; e.g. "root". |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3451 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 3452 | # |
| 3453 | # When workers access Google Cloud APIs, they logically do so via |
| 3454 | # relative URLs. If this field is specified, it supplies the base |
| 3455 | # URL to use for resolving these relative URLs. The normative |
| 3456 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3457 | # Locators". |
| 3458 | # |
| 3459 | # If not specified, the default value is "http://www.googleapis.com/" |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3460 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 3461 | # taskrunner; e.g. "wheel". |
| 3462 | "languageHint": "A String", # The suggested backend language. |
| 3463 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 3464 | # console. |
| 3465 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 3466 | "logDir": "A String", # The directory on the VM to store logs. |
| 3467 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3468 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 3469 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 3470 | # temporary storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3471 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3472 | # The supported resource type is: |
| 3473 | # |
| 3474 | # Google Cloud Storage: |
| 3475 | # storage.googleapis.com/{bucket}/{object} |
| 3476 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3477 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3478 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3479 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 3480 | # are supported. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3481 | "packages": [ # Packages to be installed on workers. |
| 3482 | { # The packages that must be installed in order for a worker to run the |
| 3483 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 3484 | # pool. |
| 3485 | # |
| 3486 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 3487 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 3488 | # might use this to install jars containing the user's code and all of the |
| 3489 | # various dependencies (libraries, data files, etc.) required in order |
| 3490 | # for that code to run. |
| 3491 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 3492 | # |
| 3493 | # Google Cloud Storage: |
| 3494 | # |
| 3495 | # storage.googleapis.com/{bucket} |
| 3496 | # bucket.storage.googleapis.com/ |
| 3497 | "name": "A String", # The name of the package. |
| 3498 | }, |
| 3499 | ], |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3500 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 3501 | # service will attempt to choose a reasonable default. |
| 3502 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 3503 | # the service will use the network "default". |
| 3504 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 3505 | # will attempt to choose a reasonable default. |
| 3506 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 3507 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3508 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 3509 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 3510 | # `TEARDOWN_NEVER`. |
| 3511 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 3512 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 3513 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 3514 | # down. |
| 3515 | # |
| 3516 | # If the workers are not torn down by the service, they will |
| 3517 | # continue to run and use Google Compute Engine VM resources in the |
| 3518 | # user's project until they are explicitly terminated by the user. |
| 3519 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 3520 | # policy except for small, manually supervised test jobs. |
| 3521 | # |
| 3522 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 3523 | # default. |
| 3524 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 3525 | # Compute Engine API. |
| 3526 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 3527 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 3528 | # service will choose a number of threads (according to the number of cores |
| 3529 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 3530 | "poolArgs": { # Extra arguments for this worker pool. |
| 3531 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 3532 | }, |
| 3533 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 3534 | # execute the job. If zero or unspecified, the service will |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3535 | # attempt to choose a reasonable default. |
| 3536 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 3537 | # harness, residing in Google Container Registry. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3538 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 3539 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3540 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 3541 | { # Describes the data disk used by a workflow job. |
| 3542 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 3543 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 3544 | # attempt to choose a reasonable default. |
| 3545 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 3546 | # must be a disk type appropriate to the project and zone in which |
| 3547 | # the workers will run. If unknown or unspecified, the service |
| 3548 | # will attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3549 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3550 | # For example, the standard persistent disk type is a resource name |
| 3551 | # typically ending in "pd-standard". If SSD persistent disks are |
| 3552 | # available, the resource name typically ends with "pd-ssd". The |
| 3553 | # actual valid values are defined the Google Compute Engine API, |
| 3554 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 3555 | # documentation for more information about determining the set of |
| 3556 | # available disk types for a particular project and zone. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3557 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3558 | # Google Compute Engine Disk types are local to a particular |
| 3559 | # project in a particular zone, and so the resource name will |
| 3560 | # typically look something like this: |
| 3561 | # |
| 3562 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3563 | }, |
| 3564 | ], |
| 3565 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 3566 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 3567 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 3568 | }, |
| 3569 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 3570 | # select a default set of packages which are useful to worker |
| 3571 | # harnesses written in a particular language. |
| 3572 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
| 3573 | # attempt to choose a reasonable default. |
| 3574 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 3575 | "a_key": "A String", |
| 3576 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3577 | }, |
| 3578 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3579 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3580 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 3581 | # this resource prefix, where {JOBNAME} is the value of the |
| 3582 | # job_name field. The resulting bucket and object prefix is used |
| 3583 | # as the prefix of the resources used to store temporary data |
| 3584 | # needed during the job execution. NOTE: This will override the |
| 3585 | # value in taskrunner_settings. |
| 3586 | # The supported resource type is: |
| 3587 | # |
| 3588 | # Google Cloud Storage: |
| 3589 | # |
| 3590 | # storage.googleapis.com/{bucket}/{object} |
| 3591 | # bucket.storage.googleapis.com/{object} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3592 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3593 | "location": "A String", # The [regional endpoint] |
| 3594 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 3595 | # contains this job. |
| 3596 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 3597 | # for temporary storage. These temporary files will be |
| 3598 | # removed on job completion. |
| 3599 | # No duplicates are allowed. |
| 3600 | # No file patterns are supported. |
| 3601 | # |
| 3602 | # The supported files are: |
| 3603 | # |
| 3604 | # Google Cloud Storage: |
| 3605 | # |
| 3606 | # storage.googleapis.com/{bucket}/{object} |
| 3607 | # bucket.storage.googleapis.com/{object} |
| 3608 | "A String", |
| 3609 | ], |
| 3610 | "type": "A String", # The type of Cloud Dataflow job. |
| 3611 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 3612 | # If this field is set, the service will ensure its uniqueness. |
| 3613 | # The request to create a job will fail if the service has knowledge of a |
| 3614 | # previously submitted job with the same client's ID and job name. |
| 3615 | # The caller may use this field to ensure idempotence of job |
| 3616 | # creation across retried attempts to create a job. |
| 3617 | # By default, the field is empty and, in that case, the service ignores it. |
| 3618 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 3619 | # snapshot. |
| 3620 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 3621 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 3622 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 3623 | # Flexible resource scheduling jobs are started with some delay after job |
| 3624 | # creation, so start_time is unset before start and is updated when the |
| 3625 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 3626 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 3627 | # service. |
| 3628 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 3629 | # Cloud Dataflow service. |
| 3630 | "requestedState": "A String", # The job's requested state. |
| 3631 | # |
| 3632 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 3633 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 3634 | # also be used to directly set a job's requested state to |
| 3635 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 3636 | # job if it has not already reached a terminal state. |
| 3637 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 3638 | # |
| 3639 | # Only one Job with a given name may exist in a project at any |
| 3640 | # given time. If a caller attempts to create a Job with the same |
| 3641 | # name as an already-existing Job, the attempt returns the |
| 3642 | # existing Job. |
| 3643 | # |
| 3644 | # The name must match the regular expression |
| 3645 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 3646 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 3647 | # |
| 3648 | # The top-level steps that constitute the entire job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3649 | { # Defines a particular step within a Cloud Dataflow job. |
| 3650 | # |
| 3651 | # A job consists of multiple steps, each of which performs some |
| 3652 | # specific operation as part of the overall job. Data is typically |
| 3653 | # passed from one step to another as part of the job. |
| 3654 | # |
| 3655 | # Here's an example of a sequence of steps which together implement a |
| 3656 | # Map-Reduce job: |
| 3657 | # |
| 3658 | # * Read a collection of data from some source, parsing the |
| 3659 | # collection's elements. |
| 3660 | # |
| 3661 | # * Validate the elements. |
| 3662 | # |
| 3663 | # * Apply a user-defined function to map each element to some value |
| 3664 | # and extract an element-specific key value. |
| 3665 | # |
| 3666 | # * Group elements with the same key into a single element with |
| 3667 | # that key, transforming a multiply-keyed collection into a |
| 3668 | # uniquely-keyed collection. |
| 3669 | # |
| 3670 | # * Write the elements out to some data sink. |
| 3671 | # |
| 3672 | # Note that the Cloud Dataflow service may be used to run many different |
| 3673 | # types of jobs, not just Map-Reduce. |
| 3674 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
| 3675 | "properties": { # Named properties associated with the step. Each kind of |
| 3676 | # predefined step has its own required set of properties. |
| 3677 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3678 | "a_key": "", # Properties of the object. |
| 3679 | }, |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 3680 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 3681 | # step with respect to all other steps in the Cloud Dataflow job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3682 | }, |
| 3683 | ], |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 3684 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 3685 | # of the job it replaced. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3686 | # |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 3687 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 3688 | # here. The job named here is stopped, and its intermediate state is |
| 3689 | # transferred to this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3690 | "currentState": "A String", # The current state of the job. |
| 3691 | # |
| 3692 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 3693 | # specified. |
| 3694 | # |
| 3695 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 3696 | # terminal state. After a job has reached a terminal state, no |
| 3697 | # further state updates may be made. |
| 3698 | # |
| 3699 | # This field may be mutated by the Cloud Dataflow service; |
| 3700 | # callers cannot mutate it. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3701 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 3702 | # isn't contained in the submitted job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3703 | "stages": { # A mapping from each stage to the information about that stage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3704 | "a_key": { # Contains information about how a particular |
| 3705 | # google.dataflow.v1beta3.Step will be executed. |
| 3706 | "stepName": [ # The steps associated with the execution stage. |
| 3707 | # Note that stages may have several steps, and that a given step |
| 3708 | # might be run by more than one stage. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3709 | "A String", |
| 3710 | ], |
| 3711 | }, |
| 3712 | }, |
| 3713 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame^] | 3714 | }</pre> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3715 | </div> |
| 3716 | |
| 3717 | </body></html> |