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"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 98 | <code><a href="#create">create(projectId, location, body=None, 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"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 113 | <code><a href="#snapshot">snapshot(projectId, location, jobId, body=None, x__xgafv=None)</a></code></p> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 114 | <p class="firstline">Snapshot the state of a streaming job.</p> |
| 115 | <p class="toc_element"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 116 | <code><a href="#update">update(projectId, location, jobId, body=None, 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"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 120 | <code class="details" id="create">create(projectId, location, body=None, 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) |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 134 | body: object, The request body. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 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} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 145 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 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. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 192 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 193 | "table": "A String", # Table accessed in the connection. |
| 194 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 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. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 213 | "key": "A String", # The key identifying the display data. |
| 214 | # This is intended to be used as a label for the display data |
| 215 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 216 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 217 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 218 | # will be stored with MyDoFn as the short_str_value and |
| 219 | # com.mypackage.MyDoFn as the java_class_name value. |
| 220 | # short_str_value can be displayed and java_class_name_value |
| 221 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 222 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 223 | "url": "A String", # An optional full URL. |
| 224 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 225 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 226 | # language namespace (i.e. python module) which defines the display data. |
| 227 | # This allows a dax monitoring system to specially handle the data |
| 228 | # and perform custom rendering. |
| 229 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 230 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 231 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 232 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 233 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 234 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 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. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 289 | "key": "A String", # The key identifying the display data. |
| 290 | # This is intended to be used as a label for the display data |
| 291 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 292 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 293 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 294 | # will be stored with MyDoFn as the short_str_value and |
| 295 | # com.mypackage.MyDoFn as the java_class_name value. |
| 296 | # short_str_value can be displayed and java_class_name_value |
| 297 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 298 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 299 | "url": "A String", # An optional full URL. |
| 300 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 301 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 302 | # language namespace (i.e. python module) which defines the display data. |
| 303 | # This allows a dax monitoring system to specially handle the data |
| 304 | # and perform custom rendering. |
| 305 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 306 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 307 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 308 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 309 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 310 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 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. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 334 | "workerRegion": "A String", # The Compute Engine region |
| 335 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 336 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 337 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 338 | # default to the control plane's region. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 339 | "version": { # A structure describing which components and their versions of the service |
| 340 | # are required in order to run the job. |
| 341 | "a_key": "", # Properties of the object. |
| 342 | }, |
| 343 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 344 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 345 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 346 | # |
| 347 | # Format: |
| 348 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 349 | "internalExperiments": { # Experimental settings. |
| 350 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 351 | }, |
| 352 | "dataset": "A String", # The dataset for the current project where various workflow |
| 353 | # related tables are stored. |
| 354 | # |
| 355 | # The supported resource type is: |
| 356 | # |
| 357 | # Google BigQuery: |
| 358 | # bigquery.googleapis.com/{dataset} |
| 359 | "experiments": [ # The list of experiments to enable. |
| 360 | "A String", |
| 361 | ], |
| 362 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 363 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 364 | # options are passed through the service and are used to recreate the |
| 365 | # SDK pipeline options on the worker in a language agnostic and platform |
| 366 | # independent way. |
| 367 | "a_key": "", # Properties of the object. |
| 368 | }, |
| 369 | "userAgent": { # A description of the process that generated the request. |
| 370 | "a_key": "", # Properties of the object. |
| 371 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 372 | "workerZone": "A String", # The Compute Engine zone |
| 373 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 374 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 375 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 376 | # a zone in the control plane's region is chosen based on available capacity. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 377 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 378 | # specified in order for the job to have workers. |
| 379 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 380 | # instantiated by the Cloud Dataflow service in order to perform the |
| 381 | # computations required by a job. Note that a workflow job may use |
| 382 | # multiple pools, in order to match the various computational |
| 383 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 384 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 385 | # harness, residing in Google Container Registry. |
| 386 | # |
| 387 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 388 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 389 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 390 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 391 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 392 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 393 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 394 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 395 | # the service will use the network "default". |
| 396 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 397 | # will attempt to choose a reasonable default. |
| 398 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 399 | "a_key": "A String", |
| 400 | }, |
| 401 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 402 | # service will attempt to choose a reasonable default. |
| 403 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 404 | # Compute Engine API. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 405 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 406 | # using the standard Dataflow task runner. Users should ignore |
| 407 | # this field. |
| 408 | "workflowFileName": "A String", # The file to store the workflow in. |
| 409 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 410 | # will not be uploaded. |
| 411 | # |
| 412 | # The supported resource type is: |
| 413 | # |
| 414 | # Google Cloud Storage: |
| 415 | # storage.googleapis.com/{bucket}/{object} |
| 416 | # bucket.storage.googleapis.com/{object} |
| 417 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 418 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 419 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 420 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 421 | "vmId": "A String", # The ID string of the VM. |
| 422 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 423 | # taskrunner; e.g. "wheel". |
| 424 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 425 | # taskrunner; e.g. "root". |
| 426 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 427 | # access the Cloud Dataflow API. |
| 428 | "A String", |
| 429 | ], |
| 430 | "languageHint": "A String", # The suggested backend language. |
| 431 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 432 | # console. |
| 433 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 434 | "logDir": "A String", # The directory on the VM to store logs. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 435 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 436 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 437 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 438 | # "shuffle/v1beta1". |
| 439 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 440 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 441 | # |
| 442 | # When workers access Google Cloud APIs, they logically do so via |
| 443 | # relative URLs. If this field is specified, it supplies the base |
| 444 | # URL to use for resolving these relative URLs. The normative |
| 445 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 446 | # Locators". |
| 447 | # |
| 448 | # If not specified, the default value is "http://www.googleapis.com/" |
| 449 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 450 | # "dataflow/v1b3/projects". |
| 451 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 452 | # storage. |
| 453 | # |
| 454 | # The supported resource type is: |
| 455 | # |
| 456 | # Google Cloud Storage: |
| 457 | # |
| 458 | # storage.googleapis.com/{bucket}/{object} |
| 459 | # bucket.storage.googleapis.com/{object} |
| 460 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 461 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 462 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 463 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 464 | # temporary storage. |
| 465 | # |
| 466 | # The supported resource type is: |
| 467 | # |
| 468 | # Google Cloud Storage: |
| 469 | # storage.googleapis.com/{bucket}/{object} |
| 470 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 471 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 472 | # |
| 473 | # When workers access Google Cloud APIs, they logically do so via |
| 474 | # relative URLs. If this field is specified, it supplies the base |
| 475 | # URL to use for resolving these relative URLs. The normative |
| 476 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 477 | # Locators". |
| 478 | # |
| 479 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 480 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 481 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 482 | # service will choose a number of threads (according to the number of cores |
| 483 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 484 | "poolArgs": { # Extra arguments for this worker pool. |
| 485 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 486 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 487 | "packages": [ # Packages to be installed on workers. |
| 488 | { # The packages that must be installed in order for a worker to run the |
| 489 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 490 | # pool. |
| 491 | # |
| 492 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 493 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 494 | # might use this to install jars containing the user's code and all of the |
| 495 | # various dependencies (libraries, data files, etc.) required in order |
| 496 | # for that code to run. |
| 497 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 498 | # |
| 499 | # Google Cloud Storage: |
| 500 | # |
| 501 | # storage.googleapis.com/{bucket} |
| 502 | # bucket.storage.googleapis.com/ |
| 503 | "name": "A String", # The name of the package. |
| 504 | }, |
| 505 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 506 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 507 | # select a default set of packages which are useful to worker |
| 508 | # harnesses written in a particular language. |
| 509 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 510 | # are supported. |
| 511 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 512 | # attempt to choose a reasonable default. |
| 513 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 514 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 515 | # `TEARDOWN_NEVER`. |
| 516 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 517 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 518 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 519 | # down. |
| 520 | # |
| 521 | # If the workers are not torn down by the service, they will |
| 522 | # continue to run and use Google Compute Engine VM resources in the |
| 523 | # user's project until they are explicitly terminated by the user. |
| 524 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 525 | # policy except for small, manually supervised test jobs. |
| 526 | # |
| 527 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 528 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 529 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 530 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 531 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 532 | # execute the job. If zero or unspecified, the service will |
| 533 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 534 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 535 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 536 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 537 | { # Describes the data disk used by a workflow job. |
| 538 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 539 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 540 | # attempt to choose a reasonable default. |
| 541 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 542 | # must be a disk type appropriate to the project and zone in which |
| 543 | # the workers will run. If unknown or unspecified, the service |
| 544 | # will attempt to choose a reasonable default. |
| 545 | # |
| 546 | # For example, the standard persistent disk type is a resource name |
| 547 | # typically ending in "pd-standard". If SSD persistent disks are |
| 548 | # available, the resource name typically ends with "pd-ssd". The |
| 549 | # actual valid values are defined the Google Compute Engine API, |
| 550 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 551 | # documentation for more information about determining the set of |
| 552 | # available disk types for a particular project and zone. |
| 553 | # |
| 554 | # Google Compute Engine Disk types are local to a particular |
| 555 | # project in a particular zone, and so the resource name will |
| 556 | # typically look something like this: |
| 557 | # |
| 558 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
| 559 | }, |
| 560 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 561 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 562 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 563 | # should have only one entry. Cross-language pipelines will have two or more |
| 564 | # entries. |
| 565 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 566 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 567 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 568 | # container instance with this image. If false (or unset) recommends using |
| 569 | # more than one core per SDK container instance with this image for |
| 570 | # efficiency. Note that Dataflow service may choose to override this property |
| 571 | # if needed. |
| 572 | }, |
| 573 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 574 | }, |
| 575 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 576 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 577 | # unspecified, the service will attempt to choose a reasonable |
| 578 | # default. This should be in the form of the API service name, |
| 579 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 580 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 581 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 582 | # this resource prefix, where {JOBNAME} is the value of the |
| 583 | # job_name field. The resulting bucket and object prefix is used |
| 584 | # as the prefix of the resources used to store temporary data |
| 585 | # needed during the job execution. NOTE: This will override the |
| 586 | # value in taskrunner_settings. |
| 587 | # The supported resource type is: |
| 588 | # |
| 589 | # Google Cloud Storage: |
| 590 | # |
| 591 | # storage.googleapis.com/{bucket}/{object} |
| 592 | # bucket.storage.googleapis.com/{object} |
| 593 | }, |
| 594 | "location": "A String", # The [regional endpoint] |
| 595 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 596 | # contains this job. |
| 597 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 598 | # for temporary storage. These temporary files will be |
| 599 | # removed on job completion. |
| 600 | # No duplicates are allowed. |
| 601 | # No file patterns are supported. |
| 602 | # |
| 603 | # The supported files are: |
| 604 | # |
| 605 | # Google Cloud Storage: |
| 606 | # |
| 607 | # storage.googleapis.com/{bucket}/{object} |
| 608 | # bucket.storage.googleapis.com/{object} |
| 609 | "A String", |
| 610 | ], |
| 611 | "type": "A String", # The type of Cloud Dataflow job. |
| 612 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 613 | # If this field is set, the service will ensure its uniqueness. |
| 614 | # The request to create a job will fail if the service has knowledge of a |
| 615 | # previously submitted job with the same client's ID and job name. |
| 616 | # The caller may use this field to ensure idempotence of job |
| 617 | # creation across retried attempts to create a job. |
| 618 | # By default, the field is empty and, in that case, the service ignores it. |
| 619 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 620 | # snapshot. |
| 621 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 622 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 623 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 624 | # Flexible resource scheduling jobs are started with some delay after job |
| 625 | # creation, so start_time is unset before start and is updated when the |
| 626 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 627 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 628 | # service. |
| 629 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 630 | # Cloud Dataflow service. |
| 631 | "requestedState": "A String", # The job's requested state. |
| 632 | # |
| 633 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 634 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 635 | # also be used to directly set a job's requested state to |
| 636 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 637 | # job if it has not already reached a terminal state. |
| 638 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 639 | # |
| 640 | # Only one Job with a given name may exist in a project at any |
| 641 | # given time. If a caller attempts to create a Job with the same |
| 642 | # name as an already-existing Job, the attempt returns the |
| 643 | # existing Job. |
| 644 | # |
| 645 | # The name must match the regular expression |
| 646 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 647 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 648 | # |
| 649 | # The top-level steps that constitute the entire job. |
| 650 | { # Defines a particular step within a Cloud Dataflow job. |
| 651 | # |
| 652 | # A job consists of multiple steps, each of which performs some |
| 653 | # specific operation as part of the overall job. Data is typically |
| 654 | # passed from one step to another as part of the job. |
| 655 | # |
| 656 | # Here's an example of a sequence of steps which together implement a |
| 657 | # Map-Reduce job: |
| 658 | # |
| 659 | # * Read a collection of data from some source, parsing the |
| 660 | # collection's elements. |
| 661 | # |
| 662 | # * Validate the elements. |
| 663 | # |
| 664 | # * Apply a user-defined function to map each element to some value |
| 665 | # and extract an element-specific key value. |
| 666 | # |
| 667 | # * Group elements with the same key into a single element with |
| 668 | # that key, transforming a multiply-keyed collection into a |
| 669 | # uniquely-keyed collection. |
| 670 | # |
| 671 | # * Write the elements out to some data sink. |
| 672 | # |
| 673 | # Note that the Cloud Dataflow service may be used to run many different |
| 674 | # types of jobs, not just Map-Reduce. |
| 675 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 676 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 677 | # step with respect to all other steps in the Cloud Dataflow job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 678 | "properties": { # Named properties associated with the step. Each kind of |
| 679 | # predefined step has its own required set of properties. |
| 680 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 681 | "a_key": "", # Properties of the object. |
| 682 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 683 | }, |
| 684 | ], |
| 685 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 686 | # of the job it replaced. |
| 687 | # |
| 688 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 689 | # here. The job named here is stopped, and its intermediate state is |
| 690 | # transferred to this job. |
| 691 | "currentState": "A String", # The current state of the job. |
| 692 | # |
| 693 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 694 | # specified. |
| 695 | # |
| 696 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 697 | # terminal state. After a job has reached a terminal state, no |
| 698 | # further state updates may be made. |
| 699 | # |
| 700 | # This field may be mutated by the Cloud Dataflow service; |
| 701 | # callers cannot mutate it. |
| 702 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 703 | # isn't contained in the submitted job. |
| 704 | "stages": { # A mapping from each stage to the information about that stage. |
| 705 | "a_key": { # Contains information about how a particular |
| 706 | # google.dataflow.v1beta3.Step will be executed. |
| 707 | "stepName": [ # The steps associated with the execution stage. |
| 708 | # Note that stages may have several steps, and that a given step |
| 709 | # might be run by more than one stage. |
| 710 | "A String", |
| 711 | ], |
| 712 | }, |
| 713 | }, |
| 714 | }, |
| 715 | } |
| 716 | |
| 717 | x__xgafv: string, V1 error format. |
| 718 | Allowed values |
| 719 | 1 - v1 error format |
| 720 | 2 - v2 error format |
| 721 | replaceJobId: string, Deprecated. This field is now in the Job message. |
| 722 | view: string, The level of information requested in response. |
| 723 | |
| 724 | Returns: |
| 725 | An object of the form: |
| 726 | |
| 727 | { # Defines a job to be run by the Cloud Dataflow service. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 728 | "labels": { # User-defined labels for this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 729 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 730 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 731 | # map are UTF8 strings that comply with the following restrictions: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 732 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 733 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 734 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 735 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 736 | # size. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 737 | "a_key": "A String", |
| 738 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 739 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 740 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 741 | # views SUMMARY and higher. |
| 742 | # ListJob response and Job SUMMARY view. |
| 743 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 744 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 745 | "version": "A String", # The version of the SDK used to run the job. |
| 746 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 747 | }, |
| 748 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 749 | { # Metadata for a PubSub connector used by the job. |
| 750 | "topic": "A String", # Topic accessed in the connection. |
| 751 | "subscription": "A String", # Subscription used in the connection. |
| 752 | }, |
| 753 | ], |
| 754 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 755 | { # Metadata for a Datastore connector used by the job. |
| 756 | "projectId": "A String", # ProjectId accessed in the connection. |
| 757 | "namespace": "A String", # Namespace used in the connection. |
| 758 | }, |
| 759 | ], |
| 760 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 761 | { # Metadata for a File connector used by the job. |
| 762 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 763 | }, |
| 764 | ], |
| 765 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 766 | { # Metadata for a Spanner connector used by the job. |
| 767 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 768 | "projectId": "A String", # ProjectId accessed in the connection. |
| 769 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 770 | }, |
| 771 | ], |
| 772 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 773 | { # Metadata for a BigTable connector used by the job. |
| 774 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 775 | "projectId": "A String", # ProjectId accessed in the connection. |
| 776 | "tableId": "A String", # TableId accessed in the connection. |
| 777 | }, |
| 778 | ], |
| 779 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 780 | { # Metadata for a BigQuery connector used by the job. |
| 781 | "projectId": "A String", # Project accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 782 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 783 | "table": "A String", # Table accessed in the connection. |
| 784 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 785 | }, |
| 786 | ], |
| 787 | }, |
| 788 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 789 | # A description of the user pipeline and stages through which it is executed. |
| 790 | # Created by Cloud Dataflow service. Only retrieved with |
| 791 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 792 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 793 | # the pipeline and interpreting Dataflow provided metrics. |
| 794 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 795 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 796 | "kind": "A String", # Type of transform. |
| 797 | "name": "A String", # User provided name for this transform instance. |
| 798 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 799 | "A String", |
| 800 | ], |
| 801 | "displayData": [ # Transform-specific display data. |
| 802 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 803 | "key": "A String", # The key identifying the display data. |
| 804 | # This is intended to be used as a label for the display data |
| 805 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 806 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 807 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 808 | # will be stored with MyDoFn as the short_str_value and |
| 809 | # com.mypackage.MyDoFn as the java_class_name value. |
| 810 | # short_str_value can be displayed and java_class_name_value |
| 811 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 812 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 813 | "url": "A String", # An optional full URL. |
| 814 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 815 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 816 | # language namespace (i.e. python module) which defines the display data. |
| 817 | # This allows a dax monitoring system to specially handle the data |
| 818 | # and perform custom rendering. |
| 819 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 820 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 821 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 822 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 823 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 824 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 825 | }, |
| 826 | ], |
| 827 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 828 | "A String", |
| 829 | ], |
| 830 | "id": "A String", # SDK generated id of this transform instance. |
| 831 | }, |
| 832 | ], |
| 833 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 834 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 835 | # stage of execution. Some composing transforms and sources may have been |
| 836 | # generated by the Dataflow service during execution planning. |
| 837 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 838 | { # Description of an interstitial value between transforms in an execution |
| 839 | # stage. |
| 840 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 841 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 842 | # source is most closely associated. |
| 843 | "name": "A String", # Dataflow service generated name for this source. |
| 844 | }, |
| 845 | ], |
| 846 | "kind": "A String", # Type of tranform this stage is executing. |
| 847 | "name": "A String", # Dataflow service generated name for this stage. |
| 848 | "outputSource": [ # Output sources for this stage. |
| 849 | { # Description of an input or output of an execution stage. |
| 850 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 851 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 852 | "name": "A String", # Dataflow service generated name for this source. |
| 853 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 854 | # source is most closely associated. |
| 855 | }, |
| 856 | ], |
| 857 | "inputSource": [ # Input sources for this stage. |
| 858 | { # Description of an input or output of an execution stage. |
| 859 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 860 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 861 | "name": "A String", # Dataflow service generated name for this source. |
| 862 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 863 | # source is most closely associated. |
| 864 | }, |
| 865 | ], |
| 866 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 867 | { # Description of a transform executed as part of an execution stage. |
| 868 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 869 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 870 | # most closely associated. |
| 871 | "name": "A String", # Dataflow service generated name for this source. |
| 872 | }, |
| 873 | ], |
| 874 | "id": "A String", # Dataflow service generated id for this stage. |
| 875 | }, |
| 876 | ], |
| 877 | "displayData": [ # Pipeline level display data. |
| 878 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 879 | "key": "A String", # The key identifying the display data. |
| 880 | # This is intended to be used as a label for the display data |
| 881 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 882 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 883 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 884 | # will be stored with MyDoFn as the short_str_value and |
| 885 | # com.mypackage.MyDoFn as the java_class_name value. |
| 886 | # short_str_value can be displayed and java_class_name_value |
| 887 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 888 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 889 | "url": "A String", # An optional full URL. |
| 890 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 891 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 892 | # language namespace (i.e. python module) which defines the display data. |
| 893 | # This allows a dax monitoring system to specially handle the data |
| 894 | # and perform custom rendering. |
| 895 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 896 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 897 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 898 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 899 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 900 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 901 | }, |
| 902 | ], |
| 903 | }, |
| 904 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 905 | # callers cannot mutate it. |
| 906 | { # A message describing the state of a particular execution stage. |
| 907 | "executionStageName": "A String", # The name of the execution stage. |
| 908 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 909 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 910 | }, |
| 911 | ], |
| 912 | "id": "A String", # The unique ID of this job. |
| 913 | # |
| 914 | # This field is set by the Cloud Dataflow service when the Job is |
| 915 | # created, and is immutable for the life of the job. |
| 916 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 917 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 918 | "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] | 919 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 920 | # corresponding name prefixes of the new job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 921 | "a_key": "A String", |
| 922 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 923 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 924 | "workerRegion": "A String", # The Compute Engine region |
| 925 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 926 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 927 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 928 | # default to the control plane's region. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 929 | "version": { # A structure describing which components and their versions of the service |
| 930 | # are required in order to run the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 931 | "a_key": "", # Properties of the object. |
| 932 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 933 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 934 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 935 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 936 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 937 | # Format: |
| 938 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 939 | "internalExperiments": { # Experimental settings. |
| 940 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 941 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 942 | "dataset": "A String", # The dataset for the current project where various workflow |
| 943 | # related tables are stored. |
| 944 | # |
| 945 | # The supported resource type is: |
| 946 | # |
| 947 | # Google BigQuery: |
| 948 | # bigquery.googleapis.com/{dataset} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 949 | "experiments": [ # The list of experiments to enable. |
| 950 | "A String", |
| 951 | ], |
| 952 | "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] | 953 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 954 | # options are passed through the service and are used to recreate the |
| 955 | # SDK pipeline options on the worker in a language agnostic and platform |
| 956 | # independent way. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 957 | "a_key": "", # Properties of the object. |
| 958 | }, |
| 959 | "userAgent": { # A description of the process that generated the request. |
| 960 | "a_key": "", # Properties of the object. |
| 961 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 962 | "workerZone": "A String", # The Compute Engine zone |
| 963 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 964 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 965 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 966 | # a zone in the control plane's region is chosen based on available capacity. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 967 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 968 | # specified in order for the job to have workers. |
| 969 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 970 | # instantiated by the Cloud Dataflow service in order to perform the |
| 971 | # computations required by a job. Note that a workflow job may use |
| 972 | # multiple pools, in order to match the various computational |
| 973 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 974 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 975 | # harness, residing in Google Container Registry. |
| 976 | # |
| 977 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 978 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 979 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 980 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 981 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 982 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 983 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 984 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 985 | # the service will use the network "default". |
| 986 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 987 | # will attempt to choose a reasonable default. |
| 988 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 989 | "a_key": "A String", |
| 990 | }, |
| 991 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 992 | # service will attempt to choose a reasonable default. |
| 993 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 994 | # Compute Engine API. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 995 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 996 | # using the standard Dataflow task runner. Users should ignore |
| 997 | # this field. |
| 998 | "workflowFileName": "A String", # The file to store the workflow in. |
| 999 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 1000 | # will not be uploaded. |
| 1001 | # |
| 1002 | # The supported resource type is: |
| 1003 | # |
| 1004 | # Google Cloud Storage: |
| 1005 | # storage.googleapis.com/{bucket}/{object} |
| 1006 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 1007 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1008 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 1009 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 1010 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 1011 | "vmId": "A String", # The ID string of the VM. |
| 1012 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 1013 | # taskrunner; e.g. "wheel". |
| 1014 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 1015 | # taskrunner; e.g. "root". |
| 1016 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 1017 | # access the Cloud Dataflow API. |
| 1018 | "A String", |
| 1019 | ], |
| 1020 | "languageHint": "A String", # The suggested backend language. |
| 1021 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 1022 | # console. |
| 1023 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 1024 | "logDir": "A String", # The directory on the VM to store logs. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1025 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 1026 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 1027 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 1028 | # "shuffle/v1beta1". |
| 1029 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 1030 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 1031 | # |
| 1032 | # When workers access Google Cloud APIs, they logically do so via |
| 1033 | # relative URLs. If this field is specified, it supplies the base |
| 1034 | # URL to use for resolving these relative URLs. The normative |
| 1035 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1036 | # Locators". |
| 1037 | # |
| 1038 | # If not specified, the default value is "http://www.googleapis.com/" |
| 1039 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 1040 | # "dataflow/v1b3/projects". |
| 1041 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1042 | # storage. |
| 1043 | # |
| 1044 | # The supported resource type is: |
| 1045 | # |
| 1046 | # Google Cloud Storage: |
| 1047 | # |
| 1048 | # storage.googleapis.com/{bucket}/{object} |
| 1049 | # bucket.storage.googleapis.com/{object} |
| 1050 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1051 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 1052 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 1053 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 1054 | # temporary storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1055 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 1056 | # The supported resource type is: |
| 1057 | # |
| 1058 | # Google Cloud Storage: |
| 1059 | # storage.googleapis.com/{bucket}/{object} |
| 1060 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1061 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 1062 | # |
| 1063 | # When workers access Google Cloud APIs, they logically do so via |
| 1064 | # relative URLs. If this field is specified, it supplies the base |
| 1065 | # URL to use for resolving these relative URLs. The normative |
| 1066 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1067 | # Locators". |
| 1068 | # |
| 1069 | # If not specified, the default value is "http://www.googleapis.com/" |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1070 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1071 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 1072 | # service will choose a number of threads (according to the number of cores |
| 1073 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 1074 | "poolArgs": { # Extra arguments for this worker pool. |
| 1075 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1076 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1077 | "packages": [ # Packages to be installed on workers. |
| 1078 | { # The packages that must be installed in order for a worker to run the |
| 1079 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 1080 | # pool. |
| 1081 | # |
| 1082 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 1083 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 1084 | # might use this to install jars containing the user's code and all of the |
| 1085 | # various dependencies (libraries, data files, etc.) required in order |
| 1086 | # for that code to run. |
| 1087 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 1088 | # |
| 1089 | # Google Cloud Storage: |
| 1090 | # |
| 1091 | # storage.googleapis.com/{bucket} |
| 1092 | # bucket.storage.googleapis.com/ |
| 1093 | "name": "A String", # The name of the package. |
| 1094 | }, |
| 1095 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1096 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 1097 | # select a default set of packages which are useful to worker |
| 1098 | # harnesses written in a particular language. |
| 1099 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 1100 | # are supported. |
| 1101 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1102 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1103 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 1104 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 1105 | # `TEARDOWN_NEVER`. |
| 1106 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 1107 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 1108 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 1109 | # down. |
| 1110 | # |
| 1111 | # If the workers are not torn down by the service, they will |
| 1112 | # continue to run and use Google Compute Engine VM resources in the |
| 1113 | # user's project until they are explicitly terminated by the user. |
| 1114 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 1115 | # policy except for small, manually supervised test jobs. |
| 1116 | # |
| 1117 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 1118 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1119 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 1120 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1121 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 1122 | # execute the job. If zero or unspecified, the service will |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1123 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1124 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 1125 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1126 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 1127 | { # Describes the data disk used by a workflow job. |
| 1128 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 1129 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 1130 | # attempt to choose a reasonable default. |
| 1131 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 1132 | # must be a disk type appropriate to the project and zone in which |
| 1133 | # the workers will run. If unknown or unspecified, the service |
| 1134 | # will attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1135 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1136 | # For example, the standard persistent disk type is a resource name |
| 1137 | # typically ending in "pd-standard". If SSD persistent disks are |
| 1138 | # available, the resource name typically ends with "pd-ssd". The |
| 1139 | # actual valid values are defined the Google Compute Engine API, |
| 1140 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 1141 | # documentation for more information about determining the set of |
| 1142 | # available disk types for a particular project and zone. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1143 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1144 | # Google Compute Engine Disk types are local to a particular |
| 1145 | # project in a particular zone, and so the resource name will |
| 1146 | # typically look something like this: |
| 1147 | # |
| 1148 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1149 | }, |
| 1150 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1151 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 1152 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 1153 | # should have only one entry. Cross-language pipelines will have two or more |
| 1154 | # entries. |
| 1155 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 1156 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 1157 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 1158 | # container instance with this image. If false (or unset) recommends using |
| 1159 | # more than one core per SDK container instance with this image for |
| 1160 | # efficiency. Note that Dataflow service may choose to override this property |
| 1161 | # if needed. |
| 1162 | }, |
| 1163 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1164 | }, |
| 1165 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1166 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 1167 | # unspecified, the service will attempt to choose a reasonable |
| 1168 | # default. This should be in the form of the API service name, |
| 1169 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1170 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1171 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 1172 | # this resource prefix, where {JOBNAME} is the value of the |
| 1173 | # job_name field. The resulting bucket and object prefix is used |
| 1174 | # as the prefix of the resources used to store temporary data |
| 1175 | # needed during the job execution. NOTE: This will override the |
| 1176 | # value in taskrunner_settings. |
| 1177 | # The supported resource type is: |
| 1178 | # |
| 1179 | # Google Cloud Storage: |
| 1180 | # |
| 1181 | # storage.googleapis.com/{bucket}/{object} |
| 1182 | # bucket.storage.googleapis.com/{object} |
| 1183 | }, |
| 1184 | "location": "A String", # The [regional endpoint] |
| 1185 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1186 | # contains this job. |
| 1187 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 1188 | # for temporary storage. These temporary files will be |
| 1189 | # removed on job completion. |
| 1190 | # No duplicates are allowed. |
| 1191 | # No file patterns are supported. |
| 1192 | # |
| 1193 | # The supported files are: |
| 1194 | # |
| 1195 | # Google Cloud Storage: |
| 1196 | # |
| 1197 | # storage.googleapis.com/{bucket}/{object} |
| 1198 | # bucket.storage.googleapis.com/{object} |
| 1199 | "A String", |
| 1200 | ], |
| 1201 | "type": "A String", # The type of Cloud Dataflow job. |
| 1202 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 1203 | # If this field is set, the service will ensure its uniqueness. |
| 1204 | # The request to create a job will fail if the service has knowledge of a |
| 1205 | # previously submitted job with the same client's ID and job name. |
| 1206 | # The caller may use this field to ensure idempotence of job |
| 1207 | # creation across retried attempts to create a job. |
| 1208 | # By default, the field is empty and, in that case, the service ignores it. |
| 1209 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 1210 | # snapshot. |
| 1211 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 1212 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 1213 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 1214 | # Flexible resource scheduling jobs are started with some delay after job |
| 1215 | # creation, so start_time is unset before start and is updated when the |
| 1216 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 1217 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 1218 | # service. |
| 1219 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 1220 | # Cloud Dataflow service. |
| 1221 | "requestedState": "A String", # The job's requested state. |
| 1222 | # |
| 1223 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 1224 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 1225 | # also be used to directly set a job's requested state to |
| 1226 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 1227 | # job if it has not already reached a terminal state. |
| 1228 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 1229 | # |
| 1230 | # Only one Job with a given name may exist in a project at any |
| 1231 | # given time. If a caller attempts to create a Job with the same |
| 1232 | # name as an already-existing Job, the attempt returns the |
| 1233 | # existing Job. |
| 1234 | # |
| 1235 | # The name must match the regular expression |
| 1236 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 1237 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 1238 | # |
| 1239 | # The top-level steps that constitute the entire job. |
| 1240 | { # Defines a particular step within a Cloud Dataflow job. |
| 1241 | # |
| 1242 | # A job consists of multiple steps, each of which performs some |
| 1243 | # specific operation as part of the overall job. Data is typically |
| 1244 | # passed from one step to another as part of the job. |
| 1245 | # |
| 1246 | # Here's an example of a sequence of steps which together implement a |
| 1247 | # Map-Reduce job: |
| 1248 | # |
| 1249 | # * Read a collection of data from some source, parsing the |
| 1250 | # collection's elements. |
| 1251 | # |
| 1252 | # * Validate the elements. |
| 1253 | # |
| 1254 | # * Apply a user-defined function to map each element to some value |
| 1255 | # and extract an element-specific key value. |
| 1256 | # |
| 1257 | # * Group elements with the same key into a single element with |
| 1258 | # that key, transforming a multiply-keyed collection into a |
| 1259 | # uniquely-keyed collection. |
| 1260 | # |
| 1261 | # * Write the elements out to some data sink. |
| 1262 | # |
| 1263 | # Note that the Cloud Dataflow service may be used to run many different |
| 1264 | # types of jobs, not just Map-Reduce. |
| 1265 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1266 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 1267 | # step with respect to all other steps in the Cloud Dataflow job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1268 | "properties": { # Named properties associated with the step. Each kind of |
| 1269 | # predefined step has its own required set of properties. |
| 1270 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 1271 | "a_key": "", # Properties of the object. |
| 1272 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1273 | }, |
| 1274 | ], |
| 1275 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 1276 | # of the job it replaced. |
| 1277 | # |
| 1278 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 1279 | # here. The job named here is stopped, and its intermediate state is |
| 1280 | # transferred to this job. |
| 1281 | "currentState": "A String", # The current state of the job. |
| 1282 | # |
| 1283 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 1284 | # specified. |
| 1285 | # |
| 1286 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 1287 | # terminal state. After a job has reached a terminal state, no |
| 1288 | # further state updates may be made. |
| 1289 | # |
| 1290 | # This field may be mutated by the Cloud Dataflow service; |
| 1291 | # callers cannot mutate it. |
| 1292 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 1293 | # isn't contained in the submitted job. |
| 1294 | "stages": { # A mapping from each stage to the information about that stage. |
| 1295 | "a_key": { # Contains information about how a particular |
| 1296 | # google.dataflow.v1beta3.Step will be executed. |
| 1297 | "stepName": [ # The steps associated with the execution stage. |
| 1298 | # Note that stages may have several steps, and that a given step |
| 1299 | # might be run by more than one stage. |
| 1300 | "A String", |
| 1301 | ], |
| 1302 | }, |
| 1303 | }, |
| 1304 | }, |
| 1305 | }</pre> |
| 1306 | </div> |
| 1307 | |
| 1308 | <div class="method"> |
| 1309 | <code class="details" id="get">get(projectId, location, jobId, x__xgafv=None, view=None)</code> |
| 1310 | <pre>Gets the state of the specified Cloud Dataflow job. |
| 1311 | |
| 1312 | To get the state of a job, we recommend using `projects.locations.jobs.get` |
| 1313 | with a [regional endpoint] |
| 1314 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 1315 | `projects.jobs.get` is not recommended, as you can only get the state of |
| 1316 | jobs that are running in `us-central1`. |
| 1317 | |
| 1318 | Args: |
| 1319 | projectId: string, The ID of the Cloud Platform project that the job belongs to. (required) |
| 1320 | location: string, The [regional endpoint] |
| 1321 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1322 | contains this job. (required) |
| 1323 | jobId: string, The job ID. (required) |
| 1324 | x__xgafv: string, V1 error format. |
| 1325 | Allowed values |
| 1326 | 1 - v1 error format |
| 1327 | 2 - v2 error format |
| 1328 | view: string, The level of information requested in response. |
| 1329 | |
| 1330 | Returns: |
| 1331 | An object of the form: |
| 1332 | |
| 1333 | { # Defines a job to be run by the Cloud Dataflow service. |
| 1334 | "labels": { # User-defined labels for this job. |
| 1335 | # |
| 1336 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 1337 | # map are UTF8 strings that comply with the following restrictions: |
| 1338 | # |
| 1339 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 1340 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1341 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1342 | # size. |
| 1343 | "a_key": "A String", |
| 1344 | }, |
| 1345 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 1346 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 1347 | # views SUMMARY and higher. |
| 1348 | # ListJob response and Job SUMMARY view. |
| 1349 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 1350 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 1351 | "version": "A String", # The version of the SDK used to run the job. |
| 1352 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 1353 | }, |
| 1354 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 1355 | { # Metadata for a PubSub connector used by the job. |
| 1356 | "topic": "A String", # Topic accessed in the connection. |
| 1357 | "subscription": "A String", # Subscription used in the connection. |
| 1358 | }, |
| 1359 | ], |
| 1360 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 1361 | { # Metadata for a Datastore connector used by the job. |
| 1362 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1363 | "namespace": "A String", # Namespace used in the connection. |
| 1364 | }, |
| 1365 | ], |
| 1366 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 1367 | { # Metadata for a File connector used by the job. |
| 1368 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 1369 | }, |
| 1370 | ], |
| 1371 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 1372 | { # Metadata for a Spanner connector used by the job. |
| 1373 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 1374 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1375 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 1376 | }, |
| 1377 | ], |
| 1378 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 1379 | { # Metadata for a BigTable connector used by the job. |
| 1380 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 1381 | "projectId": "A String", # ProjectId accessed in the connection. |
| 1382 | "tableId": "A String", # TableId accessed in the connection. |
| 1383 | }, |
| 1384 | ], |
| 1385 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 1386 | { # Metadata for a BigQuery connector used by the job. |
| 1387 | "projectId": "A String", # Project accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1388 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1389 | "table": "A String", # Table accessed in the connection. |
| 1390 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1391 | }, |
| 1392 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1393 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1394 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 1395 | # A description of the user pipeline and stages through which it is executed. |
| 1396 | # Created by Cloud Dataflow service. Only retrieved with |
| 1397 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 1398 | # 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] | 1399 | # the pipeline and interpreting Dataflow provided metrics. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1400 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 1401 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 1402 | "kind": "A String", # Type of transform. |
| 1403 | "name": "A String", # User provided name for this transform instance. |
| 1404 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 1405 | "A String", |
| 1406 | ], |
| 1407 | "displayData": [ # Transform-specific display data. |
| 1408 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1409 | "key": "A String", # The key identifying the display data. |
| 1410 | # This is intended to be used as a label for the display data |
| 1411 | # when viewed in a dax monitoring system. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1412 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 1413 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 1414 | # will be stored with MyDoFn as the short_str_value and |
| 1415 | # com.mypackage.MyDoFn as the java_class_name value. |
| 1416 | # short_str_value can be displayed and java_class_name_value |
| 1417 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1418 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1419 | "url": "A String", # An optional full URL. |
| 1420 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 1421 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 1422 | # language namespace (i.e. python module) which defines the display data. |
| 1423 | # This allows a dax monitoring system to specially handle the data |
| 1424 | # and perform custom rendering. |
| 1425 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 1426 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 1427 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 1428 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1429 | "durationValue": "A String", # Contains value if the data is of duration type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1430 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 1431 | }, |
| 1432 | ], |
| 1433 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 1434 | "A String", |
| 1435 | ], |
| 1436 | "id": "A String", # SDK generated id of this transform instance. |
| 1437 | }, |
| 1438 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1439 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 1440 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 1441 | # stage of execution. Some composing transforms and sources may have been |
| 1442 | # generated by the Dataflow service during execution planning. |
| 1443 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 1444 | { # Description of an interstitial value between transforms in an execution |
| 1445 | # stage. |
| 1446 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 1447 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1448 | # source is most closely associated. |
| 1449 | "name": "A String", # Dataflow service generated name for this source. |
| 1450 | }, |
| 1451 | ], |
| 1452 | "kind": "A String", # Type of tranform this stage is executing. |
| 1453 | "name": "A String", # Dataflow service generated name for this stage. |
| 1454 | "outputSource": [ # Output sources for this stage. |
| 1455 | { # Description of an input or output of an execution stage. |
| 1456 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 1457 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 1458 | "name": "A String", # Dataflow service generated name for this source. |
| 1459 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1460 | # source is most closely associated. |
| 1461 | }, |
| 1462 | ], |
| 1463 | "inputSource": [ # Input sources for this stage. |
| 1464 | { # Description of an input or output of an execution stage. |
| 1465 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 1466 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 1467 | "name": "A String", # Dataflow service generated name for this source. |
| 1468 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 1469 | # source is most closely associated. |
| 1470 | }, |
| 1471 | ], |
| 1472 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 1473 | { # Description of a transform executed as part of an execution stage. |
| 1474 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 1475 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 1476 | # most closely associated. |
| 1477 | "name": "A String", # Dataflow service generated name for this source. |
| 1478 | }, |
| 1479 | ], |
| 1480 | "id": "A String", # Dataflow service generated id for this stage. |
| 1481 | }, |
| 1482 | ], |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1483 | "displayData": [ # Pipeline level display data. |
| 1484 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1485 | "key": "A String", # The key identifying the display data. |
| 1486 | # This is intended to be used as a label for the display data |
| 1487 | # when viewed in a dax monitoring system. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1488 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 1489 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 1490 | # will be stored with MyDoFn as the short_str_value and |
| 1491 | # com.mypackage.MyDoFn as the java_class_name value. |
| 1492 | # short_str_value can be displayed and java_class_name_value |
| 1493 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1494 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1495 | "url": "A String", # An optional full URL. |
| 1496 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 1497 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 1498 | # language namespace (i.e. python module) which defines the display data. |
| 1499 | # This allows a dax monitoring system to specially handle the data |
| 1500 | # and perform custom rendering. |
| 1501 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 1502 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 1503 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 1504 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1505 | "durationValue": "A String", # Contains value if the data is of duration type. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1506 | "int64Value": "A String", # Contains value if the data is of int64 type. |
| 1507 | }, |
| 1508 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1509 | }, |
| 1510 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 1511 | # callers cannot mutate it. |
| 1512 | { # A message describing the state of a particular execution stage. |
| 1513 | "executionStageName": "A String", # The name of the execution stage. |
| 1514 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 1515 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 1516 | }, |
| 1517 | ], |
| 1518 | "id": "A String", # The unique ID of this job. |
| 1519 | # |
| 1520 | # This field is set by the Cloud Dataflow service when the Job is |
| 1521 | # created, and is immutable for the life of the job. |
| 1522 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 1523 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 1524 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 1525 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 1526 | # corresponding name prefixes of the new job. |
| 1527 | "a_key": "A String", |
| 1528 | }, |
| 1529 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1530 | "workerRegion": "A String", # The Compute Engine region |
| 1531 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 1532 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 1533 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 1534 | # default to the control plane's region. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1535 | "version": { # A structure describing which components and their versions of the service |
| 1536 | # are required in order to run the job. |
| 1537 | "a_key": "", # Properties of the object. |
| 1538 | }, |
| 1539 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 1540 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 1541 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 1542 | # |
| 1543 | # Format: |
| 1544 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 1545 | "internalExperiments": { # Experimental settings. |
| 1546 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1547 | }, |
| 1548 | "dataset": "A String", # The dataset for the current project where various workflow |
| 1549 | # related tables are stored. |
| 1550 | # |
| 1551 | # The supported resource type is: |
| 1552 | # |
| 1553 | # Google BigQuery: |
| 1554 | # bigquery.googleapis.com/{dataset} |
| 1555 | "experiments": [ # The list of experiments to enable. |
| 1556 | "A String", |
| 1557 | ], |
| 1558 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 1559 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 1560 | # options are passed through the service and are used to recreate the |
| 1561 | # SDK pipeline options on the worker in a language agnostic and platform |
| 1562 | # independent way. |
| 1563 | "a_key": "", # Properties of the object. |
| 1564 | }, |
| 1565 | "userAgent": { # A description of the process that generated the request. |
| 1566 | "a_key": "", # Properties of the object. |
| 1567 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1568 | "workerZone": "A String", # The Compute Engine zone |
| 1569 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 1570 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 1571 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 1572 | # a zone in the control plane's region is chosen based on available capacity. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1573 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 1574 | # specified in order for the job to have workers. |
| 1575 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 1576 | # instantiated by the Cloud Dataflow service in order to perform the |
| 1577 | # computations required by a job. Note that a workflow job may use |
| 1578 | # multiple pools, in order to match the various computational |
| 1579 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1580 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 1581 | # harness, residing in Google Container Registry. |
| 1582 | # |
| 1583 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 1584 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 1585 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 1586 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 1587 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 1588 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1589 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1590 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 1591 | # the service will use the network "default". |
| 1592 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 1593 | # will attempt to choose a reasonable default. |
| 1594 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 1595 | "a_key": "A String", |
| 1596 | }, |
| 1597 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 1598 | # service will attempt to choose a reasonable default. |
| 1599 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 1600 | # Compute Engine API. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1601 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 1602 | # using the standard Dataflow task runner. Users should ignore |
| 1603 | # this field. |
| 1604 | "workflowFileName": "A String", # The file to store the workflow in. |
| 1605 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 1606 | # will not be uploaded. |
| 1607 | # |
| 1608 | # The supported resource type is: |
| 1609 | # |
| 1610 | # Google Cloud Storage: |
| 1611 | # storage.googleapis.com/{bucket}/{object} |
| 1612 | # bucket.storage.googleapis.com/{object} |
| 1613 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1614 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 1615 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 1616 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 1617 | "vmId": "A String", # The ID string of the VM. |
| 1618 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 1619 | # taskrunner; e.g. "wheel". |
| 1620 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 1621 | # taskrunner; e.g. "root". |
| 1622 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 1623 | # access the Cloud Dataflow API. |
| 1624 | "A String", |
| 1625 | ], |
| 1626 | "languageHint": "A String", # The suggested backend language. |
| 1627 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 1628 | # console. |
| 1629 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 1630 | "logDir": "A String", # The directory on the VM to store logs. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1631 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 1632 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 1633 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 1634 | # "shuffle/v1beta1". |
| 1635 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 1636 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 1637 | # |
| 1638 | # When workers access Google Cloud APIs, they logically do so via |
| 1639 | # relative URLs. If this field is specified, it supplies the base |
| 1640 | # URL to use for resolving these relative URLs. The normative |
| 1641 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1642 | # Locators". |
| 1643 | # |
| 1644 | # If not specified, the default value is "http://www.googleapis.com/" |
| 1645 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 1646 | # "dataflow/v1b3/projects". |
| 1647 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1648 | # storage. |
| 1649 | # |
| 1650 | # The supported resource type is: |
| 1651 | # |
| 1652 | # Google Cloud Storage: |
| 1653 | # |
| 1654 | # storage.googleapis.com/{bucket}/{object} |
| 1655 | # bucket.storage.googleapis.com/{object} |
| 1656 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1657 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 1658 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 1659 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 1660 | # temporary storage. |
| 1661 | # |
| 1662 | # The supported resource type is: |
| 1663 | # |
| 1664 | # Google Cloud Storage: |
| 1665 | # storage.googleapis.com/{bucket}/{object} |
| 1666 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1667 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 1668 | # |
| 1669 | # When workers access Google Cloud APIs, they logically do so via |
| 1670 | # relative URLs. If this field is specified, it supplies the base |
| 1671 | # URL to use for resolving these relative URLs. The normative |
| 1672 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 1673 | # Locators". |
| 1674 | # |
| 1675 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1676 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1677 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 1678 | # service will choose a number of threads (according to the number of cores |
| 1679 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 1680 | "poolArgs": { # Extra arguments for this worker pool. |
| 1681 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 1682 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1683 | "packages": [ # Packages to be installed on workers. |
| 1684 | { # The packages that must be installed in order for a worker to run the |
| 1685 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 1686 | # pool. |
| 1687 | # |
| 1688 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 1689 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 1690 | # might use this to install jars containing the user's code and all of the |
| 1691 | # various dependencies (libraries, data files, etc.) required in order |
| 1692 | # for that code to run. |
| 1693 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 1694 | # |
| 1695 | # Google Cloud Storage: |
| 1696 | # |
| 1697 | # storage.googleapis.com/{bucket} |
| 1698 | # bucket.storage.googleapis.com/ |
| 1699 | "name": "A String", # The name of the package. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1700 | }, |
| 1701 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1702 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 1703 | # select a default set of packages which are useful to worker |
| 1704 | # harnesses written in a particular language. |
| 1705 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 1706 | # are supported. |
| 1707 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1708 | # attempt to choose a reasonable default. |
| 1709 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 1710 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 1711 | # `TEARDOWN_NEVER`. |
| 1712 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 1713 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 1714 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 1715 | # down. |
| 1716 | # |
| 1717 | # If the workers are not torn down by the service, they will |
| 1718 | # continue to run and use Google Compute Engine VM resources in the |
| 1719 | # user's project until they are explicitly terminated by the user. |
| 1720 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 1721 | # policy except for small, manually supervised test jobs. |
| 1722 | # |
| 1723 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 1724 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1725 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 1726 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1727 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 1728 | # execute the job. If zero or unspecified, the service will |
| 1729 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1730 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 1731 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 1732 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 1733 | { # Describes the data disk used by a workflow job. |
| 1734 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 1735 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 1736 | # attempt to choose a reasonable default. |
| 1737 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 1738 | # must be a disk type appropriate to the project and zone in which |
| 1739 | # the workers will run. If unknown or unspecified, the service |
| 1740 | # will attempt to choose a reasonable default. |
| 1741 | # |
| 1742 | # For example, the standard persistent disk type is a resource name |
| 1743 | # typically ending in "pd-standard". If SSD persistent disks are |
| 1744 | # available, the resource name typically ends with "pd-ssd". The |
| 1745 | # actual valid values are defined the Google Compute Engine API, |
| 1746 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 1747 | # documentation for more information about determining the set of |
| 1748 | # available disk types for a particular project and zone. |
| 1749 | # |
| 1750 | # Google Compute Engine Disk types are local to a particular |
| 1751 | # project in a particular zone, and so the resource name will |
| 1752 | # typically look something like this: |
| 1753 | # |
| 1754 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1755 | }, |
| 1756 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1757 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 1758 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 1759 | # should have only one entry. Cross-language pipelines will have two or more |
| 1760 | # entries. |
| 1761 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 1762 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 1763 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 1764 | # container instance with this image. If false (or unset) recommends using |
| 1765 | # more than one core per SDK container instance with this image for |
| 1766 | # efficiency. Note that Dataflow service may choose to override this property |
| 1767 | # if needed. |
| 1768 | }, |
| 1769 | ], |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1770 | }, |
| 1771 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1772 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 1773 | # unspecified, the service will attempt to choose a reasonable |
| 1774 | # default. This should be in the form of the API service name, |
| 1775 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1776 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 1777 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 1778 | # this resource prefix, where {JOBNAME} is the value of the |
| 1779 | # job_name field. The resulting bucket and object prefix is used |
| 1780 | # as the prefix of the resources used to store temporary data |
| 1781 | # needed during the job execution. NOTE: This will override the |
| 1782 | # value in taskrunner_settings. |
| 1783 | # The supported resource type is: |
| 1784 | # |
| 1785 | # Google Cloud Storage: |
| 1786 | # |
| 1787 | # storage.googleapis.com/{bucket}/{object} |
| 1788 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1789 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1790 | "location": "A String", # The [regional endpoint] |
| 1791 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1792 | # contains this job. |
| 1793 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 1794 | # for temporary storage. These temporary files will be |
| 1795 | # removed on job completion. |
| 1796 | # No duplicates are allowed. |
| 1797 | # No file patterns are supported. |
| 1798 | # |
| 1799 | # The supported files are: |
| 1800 | # |
| 1801 | # Google Cloud Storage: |
| 1802 | # |
| 1803 | # storage.googleapis.com/{bucket}/{object} |
| 1804 | # bucket.storage.googleapis.com/{object} |
| 1805 | "A String", |
| 1806 | ], |
| 1807 | "type": "A String", # The type of Cloud Dataflow job. |
| 1808 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 1809 | # If this field is set, the service will ensure its uniqueness. |
| 1810 | # The request to create a job will fail if the service has knowledge of a |
| 1811 | # previously submitted job with the same client's ID and job name. |
| 1812 | # The caller may use this field to ensure idempotence of job |
| 1813 | # creation across retried attempts to create a job. |
| 1814 | # By default, the field is empty and, in that case, the service ignores it. |
| 1815 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 1816 | # snapshot. |
| 1817 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 1818 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 1819 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 1820 | # Flexible resource scheduling jobs are started with some delay after job |
| 1821 | # creation, so start_time is unset before start and is updated when the |
| 1822 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 1823 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 1824 | # service. |
| 1825 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 1826 | # Cloud Dataflow service. |
| 1827 | "requestedState": "A String", # The job's requested state. |
| 1828 | # |
| 1829 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 1830 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 1831 | # also be used to directly set a job's requested state to |
| 1832 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 1833 | # job if it has not already reached a terminal state. |
| 1834 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 1835 | # |
| 1836 | # Only one Job with a given name may exist in a project at any |
| 1837 | # given time. If a caller attempts to create a Job with the same |
| 1838 | # name as an already-existing Job, the attempt returns the |
| 1839 | # existing Job. |
| 1840 | # |
| 1841 | # The name must match the regular expression |
| 1842 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 1843 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 1844 | # |
| 1845 | # The top-level steps that constitute the entire job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1846 | { # Defines a particular step within a Cloud Dataflow job. |
| 1847 | # |
| 1848 | # A job consists of multiple steps, each of which performs some |
| 1849 | # specific operation as part of the overall job. Data is typically |
| 1850 | # passed from one step to another as part of the job. |
| 1851 | # |
| 1852 | # Here's an example of a sequence of steps which together implement a |
| 1853 | # Map-Reduce job: |
| 1854 | # |
| 1855 | # * Read a collection of data from some source, parsing the |
| 1856 | # collection's elements. |
| 1857 | # |
| 1858 | # * Validate the elements. |
| 1859 | # |
| 1860 | # * Apply a user-defined function to map each element to some value |
| 1861 | # and extract an element-specific key value. |
| 1862 | # |
| 1863 | # * Group elements with the same key into a single element with |
| 1864 | # that key, transforming a multiply-keyed collection into a |
| 1865 | # uniquely-keyed collection. |
| 1866 | # |
| 1867 | # * Write the elements out to some data sink. |
| 1868 | # |
| 1869 | # Note that the Cloud Dataflow service may be used to run many different |
| 1870 | # types of jobs, not just Map-Reduce. |
| 1871 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1872 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 1873 | # step with respect to all other steps in the Cloud Dataflow job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1874 | "properties": { # Named properties associated with the step. Each kind of |
| 1875 | # predefined step has its own required set of properties. |
| 1876 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1877 | "a_key": "", # Properties of the object. |
| 1878 | }, |
| 1879 | }, |
| 1880 | ], |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 1881 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 1882 | # of the job it replaced. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1883 | # |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 1884 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 1885 | # here. The job named here is stopped, and its intermediate state is |
| 1886 | # transferred to this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1887 | "currentState": "A String", # The current state of the job. |
| 1888 | # |
| 1889 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 1890 | # specified. |
| 1891 | # |
| 1892 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 1893 | # terminal state. After a job has reached a terminal state, no |
| 1894 | # further state updates may be made. |
| 1895 | # |
| 1896 | # This field may be mutated by the Cloud Dataflow service; |
| 1897 | # callers cannot mutate it. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1898 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 1899 | # isn't contained in the submitted job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1900 | "stages": { # A mapping from each stage to the information about that stage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1901 | "a_key": { # Contains information about how a particular |
| 1902 | # google.dataflow.v1beta3.Step will be executed. |
| 1903 | "stepName": [ # The steps associated with the execution stage. |
| 1904 | # Note that stages may have several steps, and that a given step |
| 1905 | # might be run by more than one stage. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1906 | "A String", |
| 1907 | ], |
| 1908 | }, |
| 1909 | }, |
| 1910 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1911 | }</pre> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1912 | </div> |
| 1913 | |
| 1914 | <div class="method"> |
| 1915 | <code class="details" id="getMetrics">getMetrics(projectId, location, jobId, startTime=None, x__xgafv=None)</code> |
| 1916 | <pre>Request the job status. |
| 1917 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1918 | To request the status of a job, we recommend using |
| 1919 | `projects.locations.jobs.getMetrics` with a [regional endpoint] |
| 1920 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 1921 | `projects.jobs.getMetrics` is not recommended, as you can only request the |
| 1922 | status of jobs that are running in `us-central1`. |
| 1923 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1924 | Args: |
| 1925 | projectId: string, A project id. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1926 | location: string, The [regional endpoint] |
| 1927 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 1928 | contains the job specified by job_id. (required) |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1929 | jobId: string, The job to get messages for. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1930 | startTime: string, Return only metric data that has changed since this time. |
| 1931 | 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] | 1932 | x__xgafv: string, V1 error format. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1933 | Allowed values |
| 1934 | 1 - v1 error format |
| 1935 | 2 - v2 error format |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1936 | |
| 1937 | Returns: |
| 1938 | An object of the form: |
| 1939 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1940 | { # JobMetrics contains a collection of metrics describing the detailed progress |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1941 | # of a Dataflow job. Metrics correspond to user-defined and system-defined |
| 1942 | # metrics in the job. |
| 1943 | # |
| 1944 | # This resource captures only the most recent values of each metric; |
| 1945 | # time-series data can be queried for them (under the same metric names) |
| 1946 | # from Cloud Monitoring. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1947 | "metrics": [ # All metrics for this job. |
| 1948 | { # Describes the state of a metric. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1949 | "meanCount": "", # Worker-computed aggregate value for the "Mean" aggregation kind. |
| 1950 | # This holds the count of the aggregated values and is used in combination |
| 1951 | # with mean_sum above to obtain the actual mean aggregate value. |
| 1952 | # The only possible value type is Long. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1953 | "kind": "A String", # Metric aggregation kind. The possible metric aggregation kinds are |
| 1954 | # "Sum", "Max", "Min", "Mean", "Set", "And", "Or", and "Distribution". |
| 1955 | # The specified aggregation kind is case-insensitive. |
| 1956 | # |
| 1957 | # If omitted, this is not an aggregated value but instead |
| 1958 | # a single metric sample value. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1959 | "set": "", # Worker-computed aggregate value for the "Set" aggregation kind. The only |
| 1960 | # possible value type is a list of Values whose type can be Long, Double, |
| 1961 | # or String, according to the metric's type. All Values in the list must |
| 1962 | # be of the same type. |
| 1963 | "name": { # Identifies a metric, by describing the source which generated the # Name of the metric. |
| 1964 | # metric. |
| 1965 | "origin": "A String", # Origin (namespace) of metric name. May be blank for user-define metrics; |
| 1966 | # 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] | 1967 | "name": "A String", # Worker-defined metric name. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1968 | "context": { # Zero or more labeled fields which identify the part of the job this |
| 1969 | # metric is associated with, such as the name of a step or collection. |
| 1970 | # |
| 1971 | # For example, built-in counters associated with steps will have |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 1972 | # context['step'] = <step-name>. Counters associated with PCollections |
| 1973 | # in the SDK will have context['pcollection'] = <pcollection-name>. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 1974 | "a_key": "A String", |
| 1975 | }, |
| 1976 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 1977 | "meanSum": "", # Worker-computed aggregate value for the "Mean" aggregation kind. |
| 1978 | # This holds the sum of the aggregated values and is used in combination |
| 1979 | # with mean_count below to obtain the actual mean aggregate value. |
| 1980 | # The only possible value types are Long and Double. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1981 | "cumulative": True or False, # True if this metric is reported as the total cumulative aggregate |
| 1982 | # value accumulated since the worker started working on this WorkItem. |
| 1983 | # By default this is false, indicating that this metric is reported |
| 1984 | # as a delta that is not associated with any WorkItem. |
| 1985 | "updateTime": "A String", # Timestamp associated with the metric value. Optional when workers are |
| 1986 | # reporting work progress; it will be filled in responses from the |
| 1987 | # metrics API. |
| 1988 | "scalar": "", # Worker-computed aggregate value for aggregation kinds "Sum", "Max", "Min", |
| 1989 | # "And", and "Or". The possible value types are Long, Double, and Boolean. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 1990 | "internal": "", # Worker-computed aggregate value for internal use by the Dataflow |
| 1991 | # service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 1992 | "gauge": "", # A struct value describing properties of a Gauge. |
| 1993 | # Metrics of gauge type show the value of a metric across time, and is |
| 1994 | # aggregated based on the newest value. |
| 1995 | "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] | 1996 | }, |
| 1997 | ], |
| 1998 | "metricTime": "A String", # Timestamp as of which metric values are current. |
| 1999 | }</pre> |
| 2000 | </div> |
| 2001 | |
| 2002 | <div class="method"> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2003 | <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] | 2004 | <pre>List the jobs of a project. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2005 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2006 | To list the jobs of a project in a region, we recommend using |
| 2007 | `projects.locations.jobs.get` with a [regional endpoint] |
| 2008 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). To |
| 2009 | list the all jobs across all regions, use `projects.jobs.aggregated`. Using |
| 2010 | `projects.jobs.list` is not recommended, as you can only get the list of |
| 2011 | jobs that are running in `us-central1`. |
| 2012 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2013 | Args: |
| 2014 | projectId: string, The project which owns the jobs. (required) |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2015 | location: string, The [regional endpoint] |
| 2016 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2017 | contains this job. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2018 | pageSize: integer, If there are many jobs, limit response to at most this many. |
| 2019 | The actual number of jobs returned will be the lesser of max_responses |
| 2020 | and an unspecified server-defined limit. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2021 | pageToken: string, Set this to the 'next_page_token' field of a previous response |
| 2022 | to request additional results in a long list. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2023 | x__xgafv: string, V1 error format. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2024 | Allowed values |
| 2025 | 1 - v1 error format |
| 2026 | 2 - v2 error format |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2027 | filter: string, The kind of filter to use. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2028 | 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] | 2029 | |
| 2030 | Returns: |
| 2031 | An object of the form: |
| 2032 | |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2033 | { # Response to a request to list Cloud Dataflow jobs in a project. This might |
| 2034 | # be a partial response, depending on the page size in the ListJobsRequest. |
| 2035 | # However, if the project does not have any jobs, an instance of |
| 2036 | # ListJobsResponse is not returned and the requests's response |
| 2037 | # body is empty {}. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2038 | "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] | 2039 | "failedLocation": [ # Zero or more messages describing the [regional endpoints] |
| 2040 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2041 | # failed to respond. |
| 2042 | { # Indicates which [regional endpoint] |
| 2043 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) failed |
| 2044 | # to respond to a request for data. |
| 2045 | "name": "A String", # The name of the [regional endpoint] |
| 2046 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2047 | # failed to respond. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2048 | }, |
| 2049 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2050 | "jobs": [ # A subset of the requested job information. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2051 | { # Defines a job to be run by the Cloud Dataflow service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2052 | "labels": { # User-defined labels for this job. |
| 2053 | # |
| 2054 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 2055 | # map are UTF8 strings that comply with the following restrictions: |
| 2056 | # |
| 2057 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 2058 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2059 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2060 | # size. |
| 2061 | "a_key": "A String", |
| 2062 | }, |
| 2063 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 2064 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 2065 | # views SUMMARY and higher. |
| 2066 | # ListJob response and Job SUMMARY view. |
| 2067 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 2068 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 2069 | "version": "A String", # The version of the SDK used to run the job. |
| 2070 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2071 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2072 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 2073 | { # Metadata for a PubSub connector used by the job. |
| 2074 | "topic": "A String", # Topic accessed in the connection. |
| 2075 | "subscription": "A String", # Subscription used in the connection. |
| 2076 | }, |
| 2077 | ], |
| 2078 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 2079 | { # Metadata for a Datastore connector used by the job. |
| 2080 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2081 | "namespace": "A String", # Namespace used in the connection. |
| 2082 | }, |
| 2083 | ], |
| 2084 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 2085 | { # Metadata for a File connector used by the job. |
| 2086 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 2087 | }, |
| 2088 | ], |
| 2089 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 2090 | { # Metadata for a Spanner connector used by the job. |
| 2091 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2092 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2093 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 2094 | }, |
| 2095 | ], |
| 2096 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 2097 | { # Metadata for a BigTable connector used by the job. |
| 2098 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2099 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2100 | "tableId": "A String", # TableId accessed in the connection. |
| 2101 | }, |
| 2102 | ], |
| 2103 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 2104 | { # Metadata for a BigQuery connector used by the job. |
| 2105 | "projectId": "A String", # Project accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2106 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2107 | "table": "A String", # Table accessed in the connection. |
| 2108 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2109 | }, |
| 2110 | ], |
| 2111 | }, |
| 2112 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 2113 | # A description of the user pipeline and stages through which it is executed. |
| 2114 | # Created by Cloud Dataflow service. Only retrieved with |
| 2115 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 2116 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 2117 | # the pipeline and interpreting Dataflow provided metrics. |
| 2118 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 2119 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 2120 | "kind": "A String", # Type of transform. |
| 2121 | "name": "A String", # User provided name for this transform instance. |
| 2122 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 2123 | "A String", |
| 2124 | ], |
| 2125 | "displayData": [ # Transform-specific display data. |
| 2126 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2127 | "key": "A String", # The key identifying the display data. |
| 2128 | # This is intended to be used as a label for the display data |
| 2129 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2130 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2131 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2132 | # will be stored with MyDoFn as the short_str_value and |
| 2133 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2134 | # short_str_value can be displayed and java_class_name_value |
| 2135 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2136 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2137 | "url": "A String", # An optional full URL. |
| 2138 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2139 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2140 | # language namespace (i.e. python module) which defines the display data. |
| 2141 | # This allows a dax monitoring system to specially handle the data |
| 2142 | # and perform custom rendering. |
| 2143 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2144 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2145 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2146 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2147 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2148 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2149 | }, |
| 2150 | ], |
| 2151 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 2152 | "A String", |
| 2153 | ], |
| 2154 | "id": "A String", # SDK generated id of this transform instance. |
| 2155 | }, |
| 2156 | ], |
| 2157 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 2158 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 2159 | # stage of execution. Some composing transforms and sources may have been |
| 2160 | # generated by the Dataflow service during execution planning. |
| 2161 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 2162 | { # Description of an interstitial value between transforms in an execution |
| 2163 | # stage. |
| 2164 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2165 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2166 | # source is most closely associated. |
| 2167 | "name": "A String", # Dataflow service generated name for this source. |
| 2168 | }, |
| 2169 | ], |
| 2170 | "kind": "A String", # Type of tranform this stage is executing. |
| 2171 | "name": "A String", # Dataflow service generated name for this stage. |
| 2172 | "outputSource": [ # Output sources for this stage. |
| 2173 | { # Description of an input or output of an execution stage. |
| 2174 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2175 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2176 | "name": "A String", # Dataflow service generated name for this source. |
| 2177 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2178 | # source is most closely associated. |
| 2179 | }, |
| 2180 | ], |
| 2181 | "inputSource": [ # Input sources for this stage. |
| 2182 | { # Description of an input or output of an execution stage. |
| 2183 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2184 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2185 | "name": "A String", # Dataflow service generated name for this source. |
| 2186 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2187 | # source is most closely associated. |
| 2188 | }, |
| 2189 | ], |
| 2190 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 2191 | { # Description of a transform executed as part of an execution stage. |
| 2192 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2193 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 2194 | # most closely associated. |
| 2195 | "name": "A String", # Dataflow service generated name for this source. |
| 2196 | }, |
| 2197 | ], |
| 2198 | "id": "A String", # Dataflow service generated id for this stage. |
| 2199 | }, |
| 2200 | ], |
| 2201 | "displayData": [ # Pipeline level display data. |
| 2202 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2203 | "key": "A String", # The key identifying the display data. |
| 2204 | # This is intended to be used as a label for the display data |
| 2205 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2206 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2207 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2208 | # will be stored with MyDoFn as the short_str_value and |
| 2209 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2210 | # short_str_value can be displayed and java_class_name_value |
| 2211 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2212 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2213 | "url": "A String", # An optional full URL. |
| 2214 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2215 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2216 | # language namespace (i.e. python module) which defines the display data. |
| 2217 | # This allows a dax monitoring system to specially handle the data |
| 2218 | # and perform custom rendering. |
| 2219 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2220 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2221 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2222 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2223 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2224 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2225 | }, |
| 2226 | ], |
| 2227 | }, |
| 2228 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 2229 | # callers cannot mutate it. |
| 2230 | { # A message describing the state of a particular execution stage. |
| 2231 | "executionStageName": "A String", # The name of the execution stage. |
| 2232 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 2233 | "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] | 2234 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2235 | ], |
| 2236 | "id": "A String", # The unique ID of this job. |
| 2237 | # |
| 2238 | # This field is set by the Cloud Dataflow service when the Job is |
| 2239 | # created, and is immutable for the life of the job. |
| 2240 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 2241 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 2242 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 2243 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 2244 | # corresponding name prefixes of the new job. |
| 2245 | "a_key": "A String", |
| 2246 | }, |
| 2247 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2248 | "workerRegion": "A String", # The Compute Engine region |
| 2249 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 2250 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 2251 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 2252 | # default to the control plane's region. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2253 | "version": { # A structure describing which components and their versions of the service |
| 2254 | # are required in order to run the job. |
| 2255 | "a_key": "", # Properties of the object. |
| 2256 | }, |
| 2257 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 2258 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 2259 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2260 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2261 | # Format: |
| 2262 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 2263 | "internalExperiments": { # Experimental settings. |
| 2264 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2265 | }, |
| 2266 | "dataset": "A String", # The dataset for the current project where various workflow |
| 2267 | # related tables are stored. |
| 2268 | # |
| 2269 | # The supported resource type is: |
| 2270 | # |
| 2271 | # Google BigQuery: |
| 2272 | # bigquery.googleapis.com/{dataset} |
| 2273 | "experiments": [ # The list of experiments to enable. |
| 2274 | "A String", |
| 2275 | ], |
| 2276 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 2277 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 2278 | # options are passed through the service and are used to recreate the |
| 2279 | # SDK pipeline options on the worker in a language agnostic and platform |
| 2280 | # independent way. |
| 2281 | "a_key": "", # Properties of the object. |
| 2282 | }, |
| 2283 | "userAgent": { # A description of the process that generated the request. |
| 2284 | "a_key": "", # Properties of the object. |
| 2285 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2286 | "workerZone": "A String", # The Compute Engine zone |
| 2287 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 2288 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 2289 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 2290 | # a zone in the control plane's region is chosen based on available capacity. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2291 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 2292 | # specified in order for the job to have workers. |
| 2293 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 2294 | # instantiated by the Cloud Dataflow service in order to perform the |
| 2295 | # computations required by a job. Note that a workflow job may use |
| 2296 | # multiple pools, in order to match the various computational |
| 2297 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2298 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 2299 | # harness, residing in Google Container Registry. |
| 2300 | # |
| 2301 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 2302 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 2303 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 2304 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 2305 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 2306 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2307 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2308 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 2309 | # the service will use the network "default". |
| 2310 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 2311 | # will attempt to choose a reasonable default. |
| 2312 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 2313 | "a_key": "A String", |
| 2314 | }, |
| 2315 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 2316 | # service will attempt to choose a reasonable default. |
| 2317 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 2318 | # Compute Engine API. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2319 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 2320 | # using the standard Dataflow task runner. Users should ignore |
| 2321 | # this field. |
| 2322 | "workflowFileName": "A String", # The file to store the workflow in. |
| 2323 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 2324 | # will not be uploaded. |
| 2325 | # |
| 2326 | # The supported resource type is: |
| 2327 | # |
| 2328 | # Google Cloud Storage: |
| 2329 | # storage.googleapis.com/{bucket}/{object} |
| 2330 | # bucket.storage.googleapis.com/{object} |
| 2331 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2332 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 2333 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 2334 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 2335 | "vmId": "A String", # The ID string of the VM. |
| 2336 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 2337 | # taskrunner; e.g. "wheel". |
| 2338 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 2339 | # taskrunner; e.g. "root". |
| 2340 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 2341 | # access the Cloud Dataflow API. |
| 2342 | "A String", |
| 2343 | ], |
| 2344 | "languageHint": "A String", # The suggested backend language. |
| 2345 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 2346 | # console. |
| 2347 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 2348 | "logDir": "A String", # The directory on the VM to store logs. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2349 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 2350 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 2351 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 2352 | # "shuffle/v1beta1". |
| 2353 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 2354 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2355 | # |
| 2356 | # When workers access Google Cloud APIs, they logically do so via |
| 2357 | # relative URLs. If this field is specified, it supplies the base |
| 2358 | # URL to use for resolving these relative URLs. The normative |
| 2359 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2360 | # Locators". |
| 2361 | # |
| 2362 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2363 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 2364 | # "dataflow/v1b3/projects". |
| 2365 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 2366 | # storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2367 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 2368 | # The supported resource type is: |
| 2369 | # |
| 2370 | # Google Cloud Storage: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2371 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 2372 | # storage.googleapis.com/{bucket}/{object} |
| 2373 | # bucket.storage.googleapis.com/{object} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2374 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2375 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 2376 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 2377 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 2378 | # temporary storage. |
| 2379 | # |
| 2380 | # The supported resource type is: |
| 2381 | # |
| 2382 | # Google Cloud Storage: |
| 2383 | # storage.googleapis.com/{bucket}/{object} |
| 2384 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2385 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 2386 | # |
| 2387 | # When workers access Google Cloud APIs, they logically do so via |
| 2388 | # relative URLs. If this field is specified, it supplies the base |
| 2389 | # URL to use for resolving these relative URLs. The normative |
| 2390 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 2391 | # Locators". |
| 2392 | # |
| 2393 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2394 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2395 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 2396 | # service will choose a number of threads (according to the number of cores |
| 2397 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 2398 | "poolArgs": { # Extra arguments for this worker pool. |
| 2399 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2400 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2401 | "packages": [ # Packages to be installed on workers. |
| 2402 | { # The packages that must be installed in order for a worker to run the |
| 2403 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 2404 | # pool. |
| 2405 | # |
| 2406 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 2407 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 2408 | # might use this to install jars containing the user's code and all of the |
| 2409 | # various dependencies (libraries, data files, etc.) required in order |
| 2410 | # for that code to run. |
| 2411 | "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] | 2412 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2413 | # Google Cloud Storage: |
| 2414 | # |
| 2415 | # storage.googleapis.com/{bucket} |
| 2416 | # bucket.storage.googleapis.com/ |
| 2417 | "name": "A String", # The name of the package. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2418 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2419 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2420 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 2421 | # select a default set of packages which are useful to worker |
| 2422 | # harnesses written in a particular language. |
| 2423 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 2424 | # are supported. |
| 2425 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2426 | # attempt to choose a reasonable default. |
| 2427 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 2428 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 2429 | # `TEARDOWN_NEVER`. |
| 2430 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 2431 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 2432 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 2433 | # down. |
| 2434 | # |
| 2435 | # If the workers are not torn down by the service, they will |
| 2436 | # continue to run and use Google Compute Engine VM resources in the |
| 2437 | # user's project until they are explicitly terminated by the user. |
| 2438 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 2439 | # policy except for small, manually supervised test jobs. |
| 2440 | # |
| 2441 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 2442 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2443 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 2444 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2445 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 2446 | # execute the job. If zero or unspecified, the service will |
| 2447 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2448 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 2449 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 2450 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 2451 | { # Describes the data disk used by a workflow job. |
| 2452 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 2453 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 2454 | # attempt to choose a reasonable default. |
| 2455 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 2456 | # must be a disk type appropriate to the project and zone in which |
| 2457 | # the workers will run. If unknown or unspecified, the service |
| 2458 | # will attempt to choose a reasonable default. |
| 2459 | # |
| 2460 | # For example, the standard persistent disk type is a resource name |
| 2461 | # typically ending in "pd-standard". If SSD persistent disks are |
| 2462 | # available, the resource name typically ends with "pd-ssd". The |
| 2463 | # actual valid values are defined the Google Compute Engine API, |
| 2464 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 2465 | # documentation for more information about determining the set of |
| 2466 | # available disk types for a particular project and zone. |
| 2467 | # |
| 2468 | # Google Compute Engine Disk types are local to a particular |
| 2469 | # project in a particular zone, and so the resource name will |
| 2470 | # typically look something like this: |
| 2471 | # |
| 2472 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 2473 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2474 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2475 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 2476 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 2477 | # should have only one entry. Cross-language pipelines will have two or more |
| 2478 | # entries. |
| 2479 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 2480 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 2481 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 2482 | # container instance with this image. If false (or unset) recommends using |
| 2483 | # more than one core per SDK container instance with this image for |
| 2484 | # efficiency. Note that Dataflow service may choose to override this property |
| 2485 | # if needed. |
| 2486 | }, |
| 2487 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2488 | }, |
| 2489 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2490 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 2491 | # unspecified, the service will attempt to choose a reasonable |
| 2492 | # default. This should be in the form of the API service name, |
| 2493 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2494 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 2495 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 2496 | # this resource prefix, where {JOBNAME} is the value of the |
| 2497 | # job_name field. The resulting bucket and object prefix is used |
| 2498 | # as the prefix of the resources used to store temporary data |
| 2499 | # needed during the job execution. NOTE: This will override the |
| 2500 | # value in taskrunner_settings. |
| 2501 | # The supported resource type is: |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2502 | # |
| 2503 | # Google Cloud Storage: |
| 2504 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2505 | # storage.googleapis.com/{bucket}/{object} |
| 2506 | # bucket.storage.googleapis.com/{object} |
| 2507 | }, |
| 2508 | "location": "A String", # The [regional endpoint] |
| 2509 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2510 | # contains this job. |
| 2511 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 2512 | # for temporary storage. These temporary files will be |
| 2513 | # removed on job completion. |
| 2514 | # No duplicates are allowed. |
| 2515 | # No file patterns are supported. |
| 2516 | # |
| 2517 | # The supported files are: |
| 2518 | # |
| 2519 | # Google Cloud Storage: |
| 2520 | # |
| 2521 | # storage.googleapis.com/{bucket}/{object} |
| 2522 | # bucket.storage.googleapis.com/{object} |
| 2523 | "A String", |
| 2524 | ], |
| 2525 | "type": "A String", # The type of Cloud Dataflow job. |
| 2526 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 2527 | # If this field is set, the service will ensure its uniqueness. |
| 2528 | # The request to create a job will fail if the service has knowledge of a |
| 2529 | # previously submitted job with the same client's ID and job name. |
| 2530 | # The caller may use this field to ensure idempotence of job |
| 2531 | # creation across retried attempts to create a job. |
| 2532 | # By default, the field is empty and, in that case, the service ignores it. |
| 2533 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 2534 | # snapshot. |
| 2535 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 2536 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 2537 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 2538 | # Flexible resource scheduling jobs are started with some delay after job |
| 2539 | # creation, so start_time is unset before start and is updated when the |
| 2540 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 2541 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 2542 | # service. |
| 2543 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 2544 | # Cloud Dataflow service. |
| 2545 | "requestedState": "A String", # The job's requested state. |
| 2546 | # |
| 2547 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 2548 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 2549 | # also be used to directly set a job's requested state to |
| 2550 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 2551 | # job if it has not already reached a terminal state. |
| 2552 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 2553 | # |
| 2554 | # Only one Job with a given name may exist in a project at any |
| 2555 | # given time. If a caller attempts to create a Job with the same |
| 2556 | # name as an already-existing Job, the attempt returns the |
| 2557 | # existing Job. |
| 2558 | # |
| 2559 | # The name must match the regular expression |
| 2560 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 2561 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 2562 | # |
| 2563 | # The top-level steps that constitute the entire job. |
| 2564 | { # Defines a particular step within a Cloud Dataflow job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2565 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2566 | # A job consists of multiple steps, each of which performs some |
| 2567 | # specific operation as part of the overall job. Data is typically |
| 2568 | # passed from one step to another as part of the job. |
| 2569 | # |
| 2570 | # Here's an example of a sequence of steps which together implement a |
| 2571 | # Map-Reduce job: |
| 2572 | # |
| 2573 | # * Read a collection of data from some source, parsing the |
| 2574 | # collection's elements. |
| 2575 | # |
| 2576 | # * Validate the elements. |
| 2577 | # |
| 2578 | # * Apply a user-defined function to map each element to some value |
| 2579 | # and extract an element-specific key value. |
| 2580 | # |
| 2581 | # * Group elements with the same key into a single element with |
| 2582 | # that key, transforming a multiply-keyed collection into a |
| 2583 | # uniquely-keyed collection. |
| 2584 | # |
| 2585 | # * Write the elements out to some data sink. |
| 2586 | # |
| 2587 | # Note that the Cloud Dataflow service may be used to run many different |
| 2588 | # types of jobs, not just Map-Reduce. |
| 2589 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2590 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 2591 | # step with respect to all other steps in the Cloud Dataflow job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2592 | "properties": { # Named properties associated with the step. Each kind of |
| 2593 | # predefined step has its own required set of properties. |
| 2594 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 2595 | "a_key": "", # Properties of the object. |
| 2596 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2597 | }, |
| 2598 | ], |
| 2599 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 2600 | # of the job it replaced. |
| 2601 | # |
| 2602 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 2603 | # here. The job named here is stopped, and its intermediate state is |
| 2604 | # transferred to this job. |
| 2605 | "currentState": "A String", # The current state of the job. |
| 2606 | # |
| 2607 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 2608 | # specified. |
| 2609 | # |
| 2610 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 2611 | # terminal state. After a job has reached a terminal state, no |
| 2612 | # further state updates may be made. |
| 2613 | # |
| 2614 | # This field may be mutated by the Cloud Dataflow service; |
| 2615 | # callers cannot mutate it. |
| 2616 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 2617 | # isn't contained in the submitted job. |
| 2618 | "stages": { # A mapping from each stage to the information about that stage. |
| 2619 | "a_key": { # Contains information about how a particular |
| 2620 | # google.dataflow.v1beta3.Step will be executed. |
| 2621 | "stepName": [ # The steps associated with the execution stage. |
| 2622 | # Note that stages may have several steps, and that a given step |
| 2623 | # might be run by more than one stage. |
| 2624 | "A String", |
| 2625 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2626 | }, |
| 2627 | }, |
| 2628 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2629 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2630 | ], |
| 2631 | }</pre> |
| 2632 | </div> |
| 2633 | |
| 2634 | <div class="method"> |
| 2635 | <code class="details" id="list_next">list_next(previous_request, previous_response)</code> |
| 2636 | <pre>Retrieves the next page of results. |
| 2637 | |
| 2638 | Args: |
| 2639 | previous_request: The request for the previous page. (required) |
| 2640 | previous_response: The response from the request for the previous page. (required) |
| 2641 | |
| 2642 | Returns: |
| 2643 | A request object that you can call 'execute()' on to request the next |
| 2644 | page. Returns None if there are no more items in the collection. |
| 2645 | </pre> |
| 2646 | </div> |
| 2647 | |
| 2648 | <div class="method"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2649 | <code class="details" id="snapshot">snapshot(projectId, location, jobId, body=None, x__xgafv=None)</code> |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2650 | <pre>Snapshot the state of a streaming job. |
| 2651 | |
| 2652 | Args: |
| 2653 | projectId: string, The project which owns the job to be snapshotted. (required) |
| 2654 | location: string, The location that contains this job. (required) |
| 2655 | jobId: string, The job to be snapshotted. (required) |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2656 | body: object, The request body. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2657 | The object takes the form of: |
| 2658 | |
| 2659 | { # Request to create a snapshot of a job. |
| 2660 | "location": "A String", # The location that contains this job. |
| 2661 | "ttl": "A String", # TTL for the snapshot. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2662 | "description": "A String", # User specified description of the snapshot. Maybe empty. |
| 2663 | "snapshotSources": True or False, # If true, perform snapshots for sources which support this. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2664 | } |
| 2665 | |
| 2666 | x__xgafv: string, V1 error format. |
| 2667 | Allowed values |
| 2668 | 1 - v1 error format |
| 2669 | 2 - v2 error format |
| 2670 | |
| 2671 | Returns: |
| 2672 | An object of the form: |
| 2673 | |
| 2674 | { # Represents a snapshot of a job. |
| 2675 | "sourceJobId": "A String", # The job this snapshot was created from. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2676 | "diskSizeBytes": "A String", # The disk byte size of the snapshot. Only available for snapshots in READY |
| 2677 | # state. |
| 2678 | "description": "A String", # User specified description of the snapshot. Maybe empty. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2679 | "projectId": "A String", # The project this snapshot belongs to. |
| 2680 | "creationTime": "A String", # The time this snapshot was created. |
| 2681 | "state": "A String", # State of the snapshot. |
| 2682 | "ttl": "A String", # The time after which this snapshot will be automatically deleted. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2683 | "pubsubMetadata": [ # PubSub snapshot metadata. |
| 2684 | { # Represents a Pubsub snapshot. |
| 2685 | "expireTime": "A String", # The expire time of the Pubsub snapshot. |
| 2686 | "snapshotName": "A String", # The name of the Pubsub snapshot. |
| 2687 | "topicName": "A String", # The name of the Pubsub topic. |
| 2688 | }, |
| 2689 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2690 | "id": "A String", # The unique ID of this snapshot. |
| 2691 | }</pre> |
| 2692 | </div> |
| 2693 | |
| 2694 | <div class="method"> |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2695 | <code class="details" id="update">update(projectId, location, jobId, body=None, x__xgafv=None)</code> |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2696 | <pre>Updates the state of an existing Cloud Dataflow job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2697 | |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2698 | To update the state of an existing job, we recommend using |
| 2699 | `projects.locations.jobs.update` with a [regional endpoint] |
| 2700 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using |
| 2701 | `projects.jobs.update` is not recommended, as you can only update the state |
| 2702 | of jobs that are running in `us-central1`. |
| 2703 | |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2704 | Args: |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2705 | 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] | 2706 | location: string, The [regional endpoint] |
| 2707 | (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 2708 | contains this job. (required) |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2709 | jobId: string, The job ID. (required) |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2710 | body: object, The request body. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 2711 | The object takes the form of: |
| 2712 | |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 2713 | { # Defines a job to be run by the Cloud Dataflow service. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2714 | "labels": { # User-defined labels for this job. |
| 2715 | # |
| 2716 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 2717 | # map are UTF8 strings that comply with the following restrictions: |
| 2718 | # |
| 2719 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 2720 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2721 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2722 | # size. |
| 2723 | "a_key": "A String", |
| 2724 | }, |
| 2725 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 2726 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 2727 | # views SUMMARY and higher. |
| 2728 | # ListJob response and Job SUMMARY view. |
| 2729 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 2730 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 2731 | "version": "A String", # The version of the SDK used to run the job. |
| 2732 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 2733 | }, |
| 2734 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 2735 | { # Metadata for a PubSub connector used by the job. |
| 2736 | "topic": "A String", # Topic accessed in the connection. |
| 2737 | "subscription": "A String", # Subscription used in the connection. |
| 2738 | }, |
| 2739 | ], |
| 2740 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 2741 | { # Metadata for a Datastore connector used by the job. |
| 2742 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2743 | "namespace": "A String", # Namespace used in the connection. |
| 2744 | }, |
| 2745 | ], |
| 2746 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 2747 | { # Metadata for a File connector used by the job. |
| 2748 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 2749 | }, |
| 2750 | ], |
| 2751 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 2752 | { # Metadata for a Spanner connector used by the job. |
| 2753 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2754 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2755 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 2756 | }, |
| 2757 | ], |
| 2758 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 2759 | { # Metadata for a BigTable connector used by the job. |
| 2760 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 2761 | "projectId": "A String", # ProjectId accessed in the connection. |
| 2762 | "tableId": "A String", # TableId accessed in the connection. |
| 2763 | }, |
| 2764 | ], |
| 2765 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 2766 | { # Metadata for a BigQuery connector used by the job. |
| 2767 | "projectId": "A String", # Project accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2768 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2769 | "table": "A String", # Table accessed in the connection. |
| 2770 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2771 | }, |
| 2772 | ], |
| 2773 | }, |
| 2774 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 2775 | # A description of the user pipeline and stages through which it is executed. |
| 2776 | # Created by Cloud Dataflow service. Only retrieved with |
| 2777 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 2778 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 2779 | # the pipeline and interpreting Dataflow provided metrics. |
| 2780 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 2781 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 2782 | "kind": "A String", # Type of transform. |
| 2783 | "name": "A String", # User provided name for this transform instance. |
| 2784 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 2785 | "A String", |
| 2786 | ], |
| 2787 | "displayData": [ # Transform-specific display data. |
| 2788 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2789 | "key": "A String", # The key identifying the display data. |
| 2790 | # This is intended to be used as a label for the display data |
| 2791 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2792 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2793 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2794 | # will be stored with MyDoFn as the short_str_value and |
| 2795 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2796 | # short_str_value can be displayed and java_class_name_value |
| 2797 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2798 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2799 | "url": "A String", # An optional full URL. |
| 2800 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2801 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2802 | # language namespace (i.e. python module) which defines the display data. |
| 2803 | # This allows a dax monitoring system to specially handle the data |
| 2804 | # and perform custom rendering. |
| 2805 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2806 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2807 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2808 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2809 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2810 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2811 | }, |
| 2812 | ], |
| 2813 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 2814 | "A String", |
| 2815 | ], |
| 2816 | "id": "A String", # SDK generated id of this transform instance. |
| 2817 | }, |
| 2818 | ], |
| 2819 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 2820 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 2821 | # stage of execution. Some composing transforms and sources may have been |
| 2822 | # generated by the Dataflow service during execution planning. |
| 2823 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 2824 | { # Description of an interstitial value between transforms in an execution |
| 2825 | # stage. |
| 2826 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2827 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2828 | # source is most closely associated. |
| 2829 | "name": "A String", # Dataflow service generated name for this source. |
| 2830 | }, |
| 2831 | ], |
| 2832 | "kind": "A String", # Type of tranform this stage is executing. |
| 2833 | "name": "A String", # Dataflow service generated name for this stage. |
| 2834 | "outputSource": [ # Output sources for this stage. |
| 2835 | { # Description of an input or output of an execution stage. |
| 2836 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2837 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2838 | "name": "A String", # Dataflow service generated name for this source. |
| 2839 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2840 | # source is most closely associated. |
| 2841 | }, |
| 2842 | ], |
| 2843 | "inputSource": [ # Input sources for this stage. |
| 2844 | { # Description of an input or output of an execution stage. |
| 2845 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 2846 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 2847 | "name": "A String", # Dataflow service generated name for this source. |
| 2848 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 2849 | # source is most closely associated. |
| 2850 | }, |
| 2851 | ], |
| 2852 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 2853 | { # Description of a transform executed as part of an execution stage. |
| 2854 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 2855 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 2856 | # most closely associated. |
| 2857 | "name": "A String", # Dataflow service generated name for this source. |
| 2858 | }, |
| 2859 | ], |
| 2860 | "id": "A String", # Dataflow service generated id for this stage. |
| 2861 | }, |
| 2862 | ], |
| 2863 | "displayData": [ # Pipeline level display data. |
| 2864 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2865 | "key": "A String", # The key identifying the display data. |
| 2866 | # This is intended to be used as a label for the display data |
| 2867 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2868 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 2869 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 2870 | # will be stored with MyDoFn as the short_str_value and |
| 2871 | # com.mypackage.MyDoFn as the java_class_name value. |
| 2872 | # short_str_value can be displayed and java_class_name_value |
| 2873 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2874 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2875 | "url": "A String", # An optional full URL. |
| 2876 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 2877 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 2878 | # language namespace (i.e. python module) which defines the display data. |
| 2879 | # This allows a dax monitoring system to specially handle the data |
| 2880 | # and perform custom rendering. |
| 2881 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 2882 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 2883 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 2884 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2885 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2886 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2887 | }, |
| 2888 | ], |
| 2889 | }, |
| 2890 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 2891 | # callers cannot mutate it. |
| 2892 | { # A message describing the state of a particular execution stage. |
| 2893 | "executionStageName": "A String", # The name of the execution stage. |
| 2894 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 2895 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 2896 | }, |
| 2897 | ], |
| 2898 | "id": "A String", # The unique ID of this job. |
| 2899 | # |
| 2900 | # This field is set by the Cloud Dataflow service when the Job is |
| 2901 | # created, and is immutable for the life of the job. |
| 2902 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 2903 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 2904 | "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to. |
| 2905 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 2906 | # corresponding name prefixes of the new job. |
| 2907 | "a_key": "A String", |
| 2908 | }, |
| 2909 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2910 | "workerRegion": "A String", # The Compute Engine region |
| 2911 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 2912 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 2913 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 2914 | # default to the control plane's region. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2915 | "version": { # A structure describing which components and their versions of the service |
| 2916 | # are required in order to run the job. |
| 2917 | "a_key": "", # Properties of the object. |
| 2918 | }, |
| 2919 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 2920 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 2921 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
| 2922 | # |
| 2923 | # Format: |
| 2924 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
| 2925 | "internalExperiments": { # Experimental settings. |
| 2926 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 2927 | }, |
| 2928 | "dataset": "A String", # The dataset for the current project where various workflow |
| 2929 | # related tables are stored. |
| 2930 | # |
| 2931 | # The supported resource type is: |
| 2932 | # |
| 2933 | # Google BigQuery: |
| 2934 | # bigquery.googleapis.com/{dataset} |
| 2935 | "experiments": [ # The list of experiments to enable. |
| 2936 | "A String", |
| 2937 | ], |
| 2938 | "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account. |
| 2939 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 2940 | # options are passed through the service and are used to recreate the |
| 2941 | # SDK pipeline options on the worker in a language agnostic and platform |
| 2942 | # independent way. |
| 2943 | "a_key": "", # Properties of the object. |
| 2944 | }, |
| 2945 | "userAgent": { # A description of the process that generated the request. |
| 2946 | "a_key": "", # Properties of the object. |
| 2947 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2948 | "workerZone": "A String", # The Compute Engine zone |
| 2949 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 2950 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 2951 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 2952 | # a zone in the control plane's region is chosen based on available capacity. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2953 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 2954 | # specified in order for the job to have workers. |
| 2955 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 2956 | # instantiated by the Cloud Dataflow service in order to perform the |
| 2957 | # computations required by a job. Note that a workflow job may use |
| 2958 | # multiple pools, in order to match the various computational |
| 2959 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2960 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 2961 | # harness, residing in Google Container Registry. |
| 2962 | # |
| 2963 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 2964 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 2965 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 2966 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 2967 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 2968 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2969 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2970 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 2971 | # the service will use the network "default". |
| 2972 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 2973 | # will attempt to choose a reasonable default. |
| 2974 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 2975 | "a_key": "A String", |
| 2976 | }, |
| 2977 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 2978 | # service will attempt to choose a reasonable default. |
| 2979 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 2980 | # Compute Engine API. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 2981 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 2982 | # using the standard Dataflow task runner. Users should ignore |
| 2983 | # this field. |
| 2984 | "workflowFileName": "A String", # The file to store the workflow in. |
| 2985 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 2986 | # will not be uploaded. |
| 2987 | # |
| 2988 | # The supported resource type is: |
| 2989 | # |
| 2990 | # Google Cloud Storage: |
| 2991 | # storage.googleapis.com/{bucket}/{object} |
| 2992 | # bucket.storage.googleapis.com/{object} |
| 2993 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 2994 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 2995 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 2996 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 2997 | "vmId": "A String", # The ID string of the VM. |
| 2998 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 2999 | # taskrunner; e.g. "wheel". |
| 3000 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 3001 | # taskrunner; e.g. "root". |
| 3002 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 3003 | # access the Cloud Dataflow API. |
| 3004 | "A String", |
| 3005 | ], |
| 3006 | "languageHint": "A String", # The suggested backend language. |
| 3007 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 3008 | # console. |
| 3009 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 3010 | "logDir": "A String", # The directory on the VM to store logs. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3011 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 3012 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 3013 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 3014 | # "shuffle/v1beta1". |
| 3015 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 3016 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 3017 | # |
| 3018 | # When workers access Google Cloud APIs, they logically do so via |
| 3019 | # relative URLs. If this field is specified, it supplies the base |
| 3020 | # URL to use for resolving these relative URLs. The normative |
| 3021 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3022 | # Locators". |
| 3023 | # |
| 3024 | # If not specified, the default value is "http://www.googleapis.com/" |
| 3025 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 3026 | # "dataflow/v1b3/projects". |
| 3027 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3028 | # storage. |
| 3029 | # |
| 3030 | # The supported resource type is: |
| 3031 | # |
| 3032 | # Google Cloud Storage: |
| 3033 | # |
| 3034 | # storage.googleapis.com/{bucket}/{object} |
| 3035 | # bucket.storage.googleapis.com/{object} |
| 3036 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3037 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
| 3038 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 3039 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 3040 | # temporary storage. |
| 3041 | # |
| 3042 | # The supported resource type is: |
| 3043 | # |
| 3044 | # Google Cloud Storage: |
| 3045 | # storage.googleapis.com/{bucket}/{object} |
| 3046 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3047 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 3048 | # |
| 3049 | # When workers access Google Cloud APIs, they logically do so via |
| 3050 | # relative URLs. If this field is specified, it supplies the base |
| 3051 | # URL to use for resolving these relative URLs. The normative |
| 3052 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3053 | # Locators". |
| 3054 | # |
| 3055 | # If not specified, the default value is "http://www.googleapis.com/" |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3056 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3057 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 3058 | # service will choose a number of threads (according to the number of cores |
| 3059 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 3060 | "poolArgs": { # Extra arguments for this worker pool. |
| 3061 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 3062 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3063 | "packages": [ # Packages to be installed on workers. |
| 3064 | { # The packages that must be installed in order for a worker to run the |
| 3065 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 3066 | # pool. |
| 3067 | # |
| 3068 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 3069 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 3070 | # might use this to install jars containing the user's code and all of the |
| 3071 | # various dependencies (libraries, data files, etc.) required in order |
| 3072 | # for that code to run. |
| 3073 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 3074 | # |
| 3075 | # Google Cloud Storage: |
| 3076 | # |
| 3077 | # storage.googleapis.com/{bucket} |
| 3078 | # bucket.storage.googleapis.com/ |
| 3079 | "name": "A String", # The name of the package. |
| 3080 | }, |
| 3081 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3082 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 3083 | # select a default set of packages which are useful to worker |
| 3084 | # harnesses written in a particular language. |
| 3085 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 3086 | # are supported. |
| 3087 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3088 | # attempt to choose a reasonable default. |
| 3089 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 3090 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 3091 | # `TEARDOWN_NEVER`. |
| 3092 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 3093 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 3094 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 3095 | # down. |
| 3096 | # |
| 3097 | # If the workers are not torn down by the service, they will |
| 3098 | # continue to run and use Google Compute Engine VM resources in the |
| 3099 | # user's project until they are explicitly terminated by the user. |
| 3100 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 3101 | # policy except for small, manually supervised test jobs. |
| 3102 | # |
| 3103 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 3104 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3105 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 3106 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3107 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 3108 | # execute the job. If zero or unspecified, the service will |
| 3109 | # attempt to choose a reasonable default. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3110 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 3111 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
| 3112 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 3113 | { # Describes the data disk used by a workflow job. |
| 3114 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 3115 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 3116 | # attempt to choose a reasonable default. |
| 3117 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 3118 | # must be a disk type appropriate to the project and zone in which |
| 3119 | # the workers will run. If unknown or unspecified, the service |
| 3120 | # will attempt to choose a reasonable default. |
| 3121 | # |
| 3122 | # For example, the standard persistent disk type is a resource name |
| 3123 | # typically ending in "pd-standard". If SSD persistent disks are |
| 3124 | # available, the resource name typically ends with "pd-ssd". The |
| 3125 | # actual valid values are defined the Google Compute Engine API, |
| 3126 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 3127 | # documentation for more information about determining the set of |
| 3128 | # available disk types for a particular project and zone. |
| 3129 | # |
| 3130 | # Google Compute Engine Disk types are local to a particular |
| 3131 | # project in a particular zone, and so the resource name will |
| 3132 | # typically look something like this: |
| 3133 | # |
| 3134 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
| 3135 | }, |
| 3136 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3137 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 3138 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 3139 | # should have only one entry. Cross-language pipelines will have two or more |
| 3140 | # entries. |
| 3141 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 3142 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 3143 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 3144 | # container instance with this image. If false (or unset) recommends using |
| 3145 | # more than one core per SDK container instance with this image for |
| 3146 | # efficiency. Note that Dataflow service may choose to override this property |
| 3147 | # if needed. |
| 3148 | }, |
| 3149 | ], |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3150 | }, |
| 3151 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3152 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 3153 | # unspecified, the service will attempt to choose a reasonable |
| 3154 | # default. This should be in the form of the API service name, |
| 3155 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3156 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3157 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 3158 | # this resource prefix, where {JOBNAME} is the value of the |
| 3159 | # job_name field. The resulting bucket and object prefix is used |
| 3160 | # as the prefix of the resources used to store temporary data |
| 3161 | # needed during the job execution. NOTE: This will override the |
| 3162 | # value in taskrunner_settings. |
| 3163 | # The supported resource type is: |
| 3164 | # |
| 3165 | # Google Cloud Storage: |
| 3166 | # |
| 3167 | # storage.googleapis.com/{bucket}/{object} |
| 3168 | # bucket.storage.googleapis.com/{object} |
| 3169 | }, |
| 3170 | "location": "A String", # The [regional endpoint] |
| 3171 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 3172 | # contains this job. |
| 3173 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 3174 | # for temporary storage. These temporary files will be |
| 3175 | # removed on job completion. |
| 3176 | # No duplicates are allowed. |
| 3177 | # No file patterns are supported. |
| 3178 | # |
| 3179 | # The supported files are: |
| 3180 | # |
| 3181 | # Google Cloud Storage: |
| 3182 | # |
| 3183 | # storage.googleapis.com/{bucket}/{object} |
| 3184 | # bucket.storage.googleapis.com/{object} |
| 3185 | "A String", |
| 3186 | ], |
| 3187 | "type": "A String", # The type of Cloud Dataflow job. |
| 3188 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 3189 | # If this field is set, the service will ensure its uniqueness. |
| 3190 | # The request to create a job will fail if the service has knowledge of a |
| 3191 | # previously submitted job with the same client's ID and job name. |
| 3192 | # The caller may use this field to ensure idempotence of job |
| 3193 | # creation across retried attempts to create a job. |
| 3194 | # By default, the field is empty and, in that case, the service ignores it. |
| 3195 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 3196 | # snapshot. |
| 3197 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 3198 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 3199 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 3200 | # Flexible resource scheduling jobs are started with some delay after job |
| 3201 | # creation, so start_time is unset before start and is updated when the |
| 3202 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 3203 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 3204 | # service. |
| 3205 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 3206 | # Cloud Dataflow service. |
| 3207 | "requestedState": "A String", # The job's requested state. |
| 3208 | # |
| 3209 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 3210 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 3211 | # also be used to directly set a job's requested state to |
| 3212 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 3213 | # job if it has not already reached a terminal state. |
| 3214 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 3215 | # |
| 3216 | # Only one Job with a given name may exist in a project at any |
| 3217 | # given time. If a caller attempts to create a Job with the same |
| 3218 | # name as an already-existing Job, the attempt returns the |
| 3219 | # existing Job. |
| 3220 | # |
| 3221 | # The name must match the regular expression |
| 3222 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 3223 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 3224 | # |
| 3225 | # The top-level steps that constitute the entire job. |
| 3226 | { # Defines a particular step within a Cloud Dataflow job. |
| 3227 | # |
| 3228 | # A job consists of multiple steps, each of which performs some |
| 3229 | # specific operation as part of the overall job. Data is typically |
| 3230 | # passed from one step to another as part of the job. |
| 3231 | # |
| 3232 | # Here's an example of a sequence of steps which together implement a |
| 3233 | # Map-Reduce job: |
| 3234 | # |
| 3235 | # * Read a collection of data from some source, parsing the |
| 3236 | # collection's elements. |
| 3237 | # |
| 3238 | # * Validate the elements. |
| 3239 | # |
| 3240 | # * Apply a user-defined function to map each element to some value |
| 3241 | # and extract an element-specific key value. |
| 3242 | # |
| 3243 | # * Group elements with the same key into a single element with |
| 3244 | # that key, transforming a multiply-keyed collection into a |
| 3245 | # uniquely-keyed collection. |
| 3246 | # |
| 3247 | # * Write the elements out to some data sink. |
| 3248 | # |
| 3249 | # Note that the Cloud Dataflow service may be used to run many different |
| 3250 | # types of jobs, not just Map-Reduce. |
| 3251 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3252 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 3253 | # step with respect to all other steps in the Cloud Dataflow job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3254 | "properties": { # Named properties associated with the step. Each kind of |
| 3255 | # predefined step has its own required set of properties. |
| 3256 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
| 3257 | "a_key": "", # Properties of the object. |
| 3258 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3259 | }, |
| 3260 | ], |
| 3261 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 3262 | # of the job it replaced. |
| 3263 | # |
| 3264 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 3265 | # here. The job named here is stopped, and its intermediate state is |
| 3266 | # transferred to this job. |
| 3267 | "currentState": "A String", # The current state of the job. |
| 3268 | # |
| 3269 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 3270 | # specified. |
| 3271 | # |
| 3272 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 3273 | # terminal state. After a job has reached a terminal state, no |
| 3274 | # further state updates may be made. |
| 3275 | # |
| 3276 | # This field may be mutated by the Cloud Dataflow service; |
| 3277 | # callers cannot mutate it. |
| 3278 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 3279 | # isn't contained in the submitted job. |
| 3280 | "stages": { # A mapping from each stage to the information about that stage. |
| 3281 | "a_key": { # Contains information about how a particular |
| 3282 | # google.dataflow.v1beta3.Step will be executed. |
| 3283 | "stepName": [ # The steps associated with the execution stage. |
| 3284 | # Note that stages may have several steps, and that a given step |
| 3285 | # might be run by more than one stage. |
| 3286 | "A String", |
| 3287 | ], |
| 3288 | }, |
| 3289 | }, |
| 3290 | }, |
| 3291 | } |
| 3292 | |
| 3293 | x__xgafv: string, V1 error format. |
| 3294 | Allowed values |
| 3295 | 1 - v1 error format |
| 3296 | 2 - v2 error format |
| 3297 | |
| 3298 | Returns: |
| 3299 | An object of the form: |
| 3300 | |
| 3301 | { # Defines a job to be run by the Cloud Dataflow service. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3302 | "labels": { # User-defined labels for this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3303 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3304 | # The labels map can contain no more than 64 entries. Entries of the labels |
| 3305 | # map are UTF8 strings that comply with the following restrictions: |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3306 | # |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3307 | # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} |
| 3308 | # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3309 | # * Both keys and values are additionally constrained to be <= 128 bytes in |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3310 | # size. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3311 | "a_key": "A String", |
| 3312 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3313 | "jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs |
| 3314 | # by the metadata values provided here. Populated for ListJobs and all GetJob |
| 3315 | # views SUMMARY and higher. |
| 3316 | # ListJob response and Job SUMMARY view. |
| 3317 | "sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job. |
| 3318 | "versionDisplayName": "A String", # A readable string describing the version of the SDK. |
| 3319 | "version": "A String", # The version of the SDK used to run the job. |
| 3320 | "sdkSupportStatus": "A String", # The support status for this SDK version. |
| 3321 | }, |
| 3322 | "pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job. |
| 3323 | { # Metadata for a PubSub connector used by the job. |
| 3324 | "topic": "A String", # Topic accessed in the connection. |
| 3325 | "subscription": "A String", # Subscription used in the connection. |
| 3326 | }, |
| 3327 | ], |
| 3328 | "datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job. |
| 3329 | { # Metadata for a Datastore connector used by the job. |
| 3330 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3331 | "namespace": "A String", # Namespace used in the connection. |
| 3332 | }, |
| 3333 | ], |
| 3334 | "fileDetails": [ # Identification of a File source used in the Dataflow job. |
| 3335 | { # Metadata for a File connector used by the job. |
| 3336 | "filePattern": "A String", # File Pattern used to access files by the connector. |
| 3337 | }, |
| 3338 | ], |
| 3339 | "spannerDetails": [ # Identification of a Spanner source used in the Dataflow job. |
| 3340 | { # Metadata for a Spanner connector used by the job. |
| 3341 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 3342 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3343 | "databaseId": "A String", # DatabaseId accessed in the connection. |
| 3344 | }, |
| 3345 | ], |
| 3346 | "bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job. |
| 3347 | { # Metadata for a BigTable connector used by the job. |
| 3348 | "instanceId": "A String", # InstanceId accessed in the connection. |
| 3349 | "projectId": "A String", # ProjectId accessed in the connection. |
| 3350 | "tableId": "A String", # TableId accessed in the connection. |
| 3351 | }, |
| 3352 | ], |
| 3353 | "bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job. |
| 3354 | { # Metadata for a BigQuery connector used by the job. |
| 3355 | "projectId": "A String", # Project accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3356 | "query": "A String", # Query used to access data in the connection. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3357 | "table": "A String", # Table accessed in the connection. |
| 3358 | "dataset": "A String", # Dataset accessed in the connection. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3359 | }, |
| 3360 | ], |
| 3361 | }, |
| 3362 | "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time. |
| 3363 | # A description of the user pipeline and stages through which it is executed. |
| 3364 | # Created by Cloud Dataflow service. Only retrieved with |
| 3365 | # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. |
| 3366 | # form. This data is provided by the Dataflow service for ease of visualizing |
| 3367 | # the pipeline and interpreting Dataflow provided metrics. |
| 3368 | "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them. |
| 3369 | { # Description of the type, names/ids, and input/outputs for a transform. |
| 3370 | "kind": "A String", # Type of transform. |
| 3371 | "name": "A String", # User provided name for this transform instance. |
| 3372 | "inputCollectionName": [ # User names for all collection inputs to this transform. |
| 3373 | "A String", |
| 3374 | ], |
| 3375 | "displayData": [ # Transform-specific display data. |
| 3376 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3377 | "key": "A String", # The key identifying the display data. |
| 3378 | # This is intended to be used as a label for the display data |
| 3379 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3380 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 3381 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 3382 | # will be stored with MyDoFn as the short_str_value and |
| 3383 | # com.mypackage.MyDoFn as the java_class_name value. |
| 3384 | # short_str_value can be displayed and java_class_name_value |
| 3385 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3386 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3387 | "url": "A String", # An optional full URL. |
| 3388 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 3389 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 3390 | # language namespace (i.e. python module) which defines the display data. |
| 3391 | # This allows a dax monitoring system to specially handle the data |
| 3392 | # and perform custom rendering. |
| 3393 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 3394 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 3395 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 3396 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3397 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3398 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3399 | }, |
| 3400 | ], |
| 3401 | "outputCollectionName": [ # User names for all collection outputs to this transform. |
| 3402 | "A String", |
| 3403 | ], |
| 3404 | "id": "A String", # SDK generated id of this transform instance. |
| 3405 | }, |
| 3406 | ], |
| 3407 | "executionPipelineStage": [ # Description of each stage of execution of the pipeline. |
| 3408 | { # Description of the composing transforms, names/ids, and input/outputs of a |
| 3409 | # stage of execution. Some composing transforms and sources may have been |
| 3410 | # generated by the Dataflow service during execution planning. |
| 3411 | "componentSource": [ # Collections produced and consumed by component transforms of this stage. |
| 3412 | { # Description of an interstitial value between transforms in an execution |
| 3413 | # stage. |
| 3414 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 3415 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3416 | # source is most closely associated. |
| 3417 | "name": "A String", # Dataflow service generated name for this source. |
| 3418 | }, |
| 3419 | ], |
| 3420 | "kind": "A String", # Type of tranform this stage is executing. |
| 3421 | "name": "A String", # Dataflow service generated name for this stage. |
| 3422 | "outputSource": [ # Output sources for this stage. |
| 3423 | { # Description of an input or output of an execution stage. |
| 3424 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 3425 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 3426 | "name": "A String", # Dataflow service generated name for this source. |
| 3427 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3428 | # source is most closely associated. |
| 3429 | }, |
| 3430 | ], |
| 3431 | "inputSource": [ # Input sources for this stage. |
| 3432 | { # Description of an input or output of an execution stage. |
| 3433 | "userName": "A String", # Human-readable name for this source; may be user or system generated. |
| 3434 | "sizeBytes": "A String", # Size of the source, if measurable. |
| 3435 | "name": "A String", # Dataflow service generated name for this source. |
| 3436 | "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this |
| 3437 | # source is most closely associated. |
| 3438 | }, |
| 3439 | ], |
| 3440 | "componentTransform": [ # Transforms that comprise this execution stage. |
| 3441 | { # Description of a transform executed as part of an execution stage. |
| 3442 | "userName": "A String", # Human-readable name for this transform; may be user or system generated. |
| 3443 | "originalTransform": "A String", # User name for the original user transform with which this transform is |
| 3444 | # most closely associated. |
| 3445 | "name": "A String", # Dataflow service generated name for this source. |
| 3446 | }, |
| 3447 | ], |
| 3448 | "id": "A String", # Dataflow service generated id for this stage. |
| 3449 | }, |
| 3450 | ], |
| 3451 | "displayData": [ # Pipeline level display data. |
| 3452 | { # Data provided with a pipeline or transform to provide descriptive info. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3453 | "key": "A String", # The key identifying the display data. |
| 3454 | # This is intended to be used as a label for the display data |
| 3455 | # when viewed in a dax monitoring system. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3456 | "shortStrValue": "A String", # A possible additional shorter value to display. |
| 3457 | # For example a java_class_name_value of com.mypackage.MyDoFn |
| 3458 | # will be stored with MyDoFn as the short_str_value and |
| 3459 | # com.mypackage.MyDoFn as the java_class_name value. |
| 3460 | # short_str_value can be displayed and java_class_name_value |
| 3461 | # will be displayed as a tooltip. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3462 | "timestampValue": "A String", # Contains value if the data is of timestamp type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3463 | "url": "A String", # An optional full URL. |
| 3464 | "floatValue": 3.14, # Contains value if the data is of float type. |
| 3465 | "namespace": "A String", # The namespace for the key. This is usually a class name or programming |
| 3466 | # language namespace (i.e. python module) which defines the display data. |
| 3467 | # This allows a dax monitoring system to specially handle the data |
| 3468 | # and perform custom rendering. |
| 3469 | "javaClassValue": "A String", # Contains value if the data is of java class type. |
| 3470 | "label": "A String", # An optional label to display in a dax UI for the element. |
| 3471 | "boolValue": True or False, # Contains value if the data is of a boolean type. |
| 3472 | "strValue": "A String", # Contains value if the data is of string type. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3473 | "durationValue": "A String", # Contains value if the data is of duration type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3474 | "int64Value": "A String", # Contains value if the data is of int64 type. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3475 | }, |
| 3476 | ], |
| 3477 | }, |
| 3478 | "stageStates": [ # This field may be mutated by the Cloud Dataflow service; |
| 3479 | # callers cannot mutate it. |
| 3480 | { # A message describing the state of a particular execution stage. |
| 3481 | "executionStageName": "A String", # The name of the execution stage. |
| 3482 | "executionStageState": "A String", # Executions stage states allow the same set of values as JobState. |
| 3483 | "currentStateTime": "A String", # The time at which the stage transitioned to this state. |
| 3484 | }, |
| 3485 | ], |
| 3486 | "id": "A String", # The unique ID of this job. |
| 3487 | # |
| 3488 | # This field is set by the Cloud Dataflow service when the Job is |
| 3489 | # created, and is immutable for the life of the job. |
| 3490 | "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in |
| 3491 | # `JOB_STATE_UPDATED`), this field contains the ID of that job. |
| 3492 | "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] | 3493 | "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the |
| 3494 | # corresponding name prefixes of the new job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3495 | "a_key": "A String", |
| 3496 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3497 | "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3498 | "workerRegion": "A String", # The Compute Engine region |
| 3499 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 3500 | # which worker processing should occur, e.g. "us-west1". Mutually exclusive |
| 3501 | # with worker_zone. If neither worker_region nor worker_zone is specified, |
| 3502 | # default to the control plane's region. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3503 | "version": { # A structure describing which components and their versions of the service |
| 3504 | # are required in order to run the job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3505 | "a_key": "", # Properties of the object. |
| 3506 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3507 | "flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in. |
| 3508 | "serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data |
| 3509 | # at rest, AKA a Customer Managed Encryption Key (CMEK). |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3510 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3511 | # Format: |
| 3512 | # projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3513 | "internalExperiments": { # Experimental settings. |
| 3514 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 3515 | }, |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3516 | "dataset": "A String", # The dataset for the current project where various workflow |
| 3517 | # related tables are stored. |
| 3518 | # |
| 3519 | # The supported resource type is: |
| 3520 | # |
| 3521 | # Google BigQuery: |
| 3522 | # bigquery.googleapis.com/{dataset} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3523 | "experiments": [ # The list of experiments to enable. |
| 3524 | "A String", |
| 3525 | ], |
| 3526 | "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] | 3527 | "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These |
| 3528 | # options are passed through the service and are used to recreate the |
| 3529 | # SDK pipeline options on the worker in a language agnostic and platform |
| 3530 | # independent way. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3531 | "a_key": "", # Properties of the object. |
| 3532 | }, |
| 3533 | "userAgent": { # A description of the process that generated the request. |
| 3534 | "a_key": "", # Properties of the object. |
| 3535 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3536 | "workerZone": "A String", # The Compute Engine zone |
| 3537 | # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in |
| 3538 | # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive |
| 3539 | # with worker_region. If neither worker_region nor worker_zone is specified, |
| 3540 | # a zone in the control plane's region is chosen based on available capacity. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3541 | "workerPools": [ # The worker pools. At least one "harness" worker pool must be |
| 3542 | # specified in order for the job to have workers. |
| 3543 | { # Describes one particular pool of Cloud Dataflow workers to be |
| 3544 | # instantiated by the Cloud Dataflow service in order to perform the |
| 3545 | # computations required by a job. Note that a workflow job may use |
| 3546 | # multiple pools, in order to match the various computational |
| 3547 | # requirements of the various stages of the job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3548 | "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker |
| 3549 | # harness, residing in Google Container Registry. |
| 3550 | # |
| 3551 | # Deprecated for the Fn API path. Use sdk_harness_container_images instead. |
| 3552 | "ipConfiguration": "A String", # Configuration for VM IPs. |
| 3553 | "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool. |
| 3554 | "maxNumWorkers": 42, # The maximum number of workers to cap scaling at. |
| 3555 | "algorithm": "A String", # The algorithm to use for autoscaling. |
| 3556 | }, |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3557 | "diskSourceImage": "A String", # Fully qualified source image for disks. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3558 | "network": "A String", # Network to which VMs will be assigned. If empty or unspecified, |
| 3559 | # the service will use the network "default". |
| 3560 | "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service |
| 3561 | # will attempt to choose a reasonable default. |
| 3562 | "metadata": { # Metadata to set on the Google Compute Engine VMs. |
| 3563 | "a_key": "A String", |
| 3564 | }, |
| 3565 | "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the |
| 3566 | # service will attempt to choose a reasonable default. |
| 3567 | "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google |
| 3568 | # Compute Engine API. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3569 | "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when |
| 3570 | # using the standard Dataflow task runner. Users should ignore |
| 3571 | # this field. |
| 3572 | "workflowFileName": "A String", # The file to store the workflow in. |
| 3573 | "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs |
| 3574 | # will not be uploaded. |
| 3575 | # |
| 3576 | # The supported resource type is: |
| 3577 | # |
| 3578 | # Google Cloud Storage: |
| 3579 | # storage.googleapis.com/{bucket}/{object} |
| 3580 | # bucket.storage.googleapis.com/{object} |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3581 | "commandlinesFileName": "A String", # The file to store preprocessing commands in. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3582 | "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr. |
| 3583 | "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit. |
| 3584 | "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories. |
| 3585 | "vmId": "A String", # The ID string of the VM. |
| 3586 | "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by |
| 3587 | # taskrunner; e.g. "wheel". |
| 3588 | "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by |
| 3589 | # taskrunner; e.g. "root". |
| 3590 | "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to |
| 3591 | # access the Cloud Dataflow API. |
| 3592 | "A String", |
| 3593 | ], |
| 3594 | "languageHint": "A String", # The suggested backend language. |
| 3595 | "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial |
| 3596 | # console. |
| 3597 | "streamingWorkerMainClass": "A String", # The streaming worker main class name. |
| 3598 | "logDir": "A String", # The directory on the VM to store logs. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3599 | "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness. |
| 3600 | "reportingEnabled": True or False, # Whether to send work progress updates to the service. |
| 3601 | "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example, |
| 3602 | # "shuffle/v1beta1". |
| 3603 | "workerId": "A String", # The ID of the worker running this pipeline. |
| 3604 | "baseUrl": "A String", # The base URL for accessing Google Cloud APIs. |
| 3605 | # |
| 3606 | # When workers access Google Cloud APIs, they logically do so via |
| 3607 | # relative URLs. If this field is specified, it supplies the base |
| 3608 | # URL to use for resolving these relative URLs. The normative |
| 3609 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3610 | # Locators". |
| 3611 | # |
| 3612 | # If not specified, the default value is "http://www.googleapis.com/" |
| 3613 | "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example, |
| 3614 | # "dataflow/v1b3/projects". |
| 3615 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3616 | # storage. |
| 3617 | # |
| 3618 | # The supported resource type is: |
| 3619 | # |
| 3620 | # Google Cloud Storage: |
| 3621 | # |
| 3622 | # storage.googleapis.com/{bucket}/{object} |
| 3623 | # bucket.storage.googleapis.com/{object} |
| 3624 | }, |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3625 | "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3" |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3626 | "harnessCommand": "A String", # The command to launch the worker harness. |
| 3627 | "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for |
| 3628 | # temporary storage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3629 | # |
Sai Cheemalapati | e833b79 | 2017-03-24 15:06:46 -0700 | [diff] [blame] | 3630 | # The supported resource type is: |
| 3631 | # |
| 3632 | # Google Cloud Storage: |
| 3633 | # storage.googleapis.com/{bucket}/{object} |
| 3634 | # bucket.storage.googleapis.com/{object} |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3635 | "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs. |
| 3636 | # |
| 3637 | # When workers access Google Cloud APIs, they logically do so via |
| 3638 | # relative URLs. If this field is specified, it supplies the base |
| 3639 | # URL to use for resolving these relative URLs. The normative |
| 3640 | # algorithm used is defined by RFC 1808, "Relative Uniform Resource |
| 3641 | # Locators". |
| 3642 | # |
| 3643 | # If not specified, the default value is "http://www.googleapis.com/" |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3644 | }, |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3645 | "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the |
| 3646 | # service will choose a number of threads (according to the number of cores |
| 3647 | # on the selected machine type for batch, or 1 by convention for streaming). |
| 3648 | "poolArgs": { # Extra arguments for this worker pool. |
| 3649 | "a_key": "", # Properties of the object. Contains field @type with type URL. |
| 3650 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3651 | "packages": [ # Packages to be installed on workers. |
| 3652 | { # The packages that must be installed in order for a worker to run the |
| 3653 | # steps of the Cloud Dataflow job that will be assigned to its worker |
| 3654 | # pool. |
| 3655 | # |
| 3656 | # This is the mechanism by which the Cloud Dataflow SDK causes code to |
| 3657 | # be loaded onto the workers. For example, the Cloud Dataflow Java SDK |
| 3658 | # might use this to install jars containing the user's code and all of the |
| 3659 | # various dependencies (libraries, data files, etc.) required in order |
| 3660 | # for that code to run. |
| 3661 | "location": "A String", # The resource to read the package from. The supported resource type is: |
| 3662 | # |
| 3663 | # Google Cloud Storage: |
| 3664 | # |
| 3665 | # storage.googleapis.com/{bucket} |
| 3666 | # bucket.storage.googleapis.com/ |
| 3667 | "name": "A String", # The name of the package. |
| 3668 | }, |
| 3669 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3670 | "defaultPackageSet": "A String", # The default package set to install. This allows the service to |
| 3671 | # select a default set of packages which are useful to worker |
| 3672 | # harnesses written in a particular language. |
| 3673 | "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle` |
| 3674 | # are supported. |
| 3675 | "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3676 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3677 | "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool. |
| 3678 | # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and |
| 3679 | # `TEARDOWN_NEVER`. |
| 3680 | # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether |
| 3681 | # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down |
| 3682 | # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn |
| 3683 | # down. |
| 3684 | # |
| 3685 | # If the workers are not torn down by the service, they will |
| 3686 | # continue to run and use Google Compute Engine VM resources in the |
| 3687 | # user's project until they are explicitly terminated by the user. |
| 3688 | # Because of this, Google recommends using the `TEARDOWN_ALWAYS` |
| 3689 | # policy except for small, manually supervised test jobs. |
| 3690 | # |
| 3691 | # If unknown or unspecified, the service will attempt to choose a reasonable |
| 3692 | # default. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3693 | "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will |
| 3694 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3695 | "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to |
| 3696 | # execute the job. If zero or unspecified, the service will |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3697 | # attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3698 | "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of |
| 3699 | # the form "regions/REGION/subnetworks/SUBNETWORK". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3700 | "dataDisks": [ # Data disks that are used by a VM in this workflow. |
| 3701 | { # Describes the data disk used by a workflow job. |
| 3702 | "mountPoint": "A String", # Directory in a VM where disk is mounted. |
| 3703 | "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will |
| 3704 | # attempt to choose a reasonable default. |
| 3705 | "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This |
| 3706 | # must be a disk type appropriate to the project and zone in which |
| 3707 | # the workers will run. If unknown or unspecified, the service |
| 3708 | # will attempt to choose a reasonable default. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3709 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3710 | # For example, the standard persistent disk type is a resource name |
| 3711 | # typically ending in "pd-standard". If SSD persistent disks are |
| 3712 | # available, the resource name typically ends with "pd-ssd". The |
| 3713 | # actual valid values are defined the Google Compute Engine API, |
| 3714 | # not by the Cloud Dataflow API; consult the Google Compute Engine |
| 3715 | # documentation for more information about determining the set of |
| 3716 | # available disk types for a particular project and zone. |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3717 | # |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3718 | # Google Compute Engine Disk types are local to a particular |
| 3719 | # project in a particular zone, and so the resource name will |
| 3720 | # typically look something like this: |
| 3721 | # |
| 3722 | # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard |
Sai Cheemalapati | 4ba8c23 | 2017-06-06 18:46:08 -0400 | [diff] [blame] | 3723 | }, |
| 3724 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3725 | "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will |
| 3726 | # only be set in the Fn API path. For non-cross-language pipelines this |
| 3727 | # should have only one entry. Cross-language pipelines will have two or more |
| 3728 | # entries. |
| 3729 | { # Defines a SDK harness container for executing Dataflow pipelines. |
| 3730 | "containerImage": "A String", # A docker container image that resides in Google Container Registry. |
| 3731 | "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK |
| 3732 | # container instance with this image. If false (or unset) recommends using |
| 3733 | # more than one core per SDK container instance with this image for |
| 3734 | # efficiency. Note that Dataflow service may choose to override this property |
| 3735 | # if needed. |
| 3736 | }, |
| 3737 | ], |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3738 | }, |
| 3739 | ], |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3740 | "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or |
| 3741 | # unspecified, the service will attempt to choose a reasonable |
| 3742 | # default. This should be in the form of the API service name, |
| 3743 | # e.g. "compute.googleapis.com". |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3744 | "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary |
| 3745 | # storage. The system will append the suffix "/temp-{JOBNAME} to |
| 3746 | # this resource prefix, where {JOBNAME} is the value of the |
| 3747 | # job_name field. The resulting bucket and object prefix is used |
| 3748 | # as the prefix of the resources used to store temporary data |
| 3749 | # needed during the job execution. NOTE: This will override the |
| 3750 | # value in taskrunner_settings. |
| 3751 | # The supported resource type is: |
| 3752 | # |
| 3753 | # Google Cloud Storage: |
| 3754 | # |
| 3755 | # storage.googleapis.com/{bucket}/{object} |
| 3756 | # bucket.storage.googleapis.com/{object} |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3757 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3758 | "location": "A String", # The [regional endpoint] |
| 3759 | # (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that |
| 3760 | # contains this job. |
| 3761 | "tempFiles": [ # A set of files the system should be aware of that are used |
| 3762 | # for temporary storage. These temporary files will be |
| 3763 | # removed on job completion. |
| 3764 | # No duplicates are allowed. |
| 3765 | # No file patterns are supported. |
| 3766 | # |
| 3767 | # The supported files are: |
| 3768 | # |
| 3769 | # Google Cloud Storage: |
| 3770 | # |
| 3771 | # storage.googleapis.com/{bucket}/{object} |
| 3772 | # bucket.storage.googleapis.com/{object} |
| 3773 | "A String", |
| 3774 | ], |
| 3775 | "type": "A String", # The type of Cloud Dataflow job. |
| 3776 | "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts. |
| 3777 | # If this field is set, the service will ensure its uniqueness. |
| 3778 | # The request to create a job will fail if the service has knowledge of a |
| 3779 | # previously submitted job with the same client's ID and job name. |
| 3780 | # The caller may use this field to ensure idempotence of job |
| 3781 | # creation across retried attempts to create a job. |
| 3782 | # By default, the field is empty and, in that case, the service ignores it. |
| 3783 | "createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given |
| 3784 | # snapshot. |
| 3785 | "stepsLocation": "A String", # The GCS location where the steps are stored. |
| 3786 | "currentStateTime": "A String", # The timestamp associated with the current state. |
| 3787 | "startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING). |
| 3788 | # Flexible resource scheduling jobs are started with some delay after job |
| 3789 | # creation, so start_time is unset before start and is updated when the |
| 3790 | # job is started by the Cloud Dataflow service. For other jobs, start_time |
| 3791 | # always equals to create_time and is immutable and set by the Cloud Dataflow |
| 3792 | # service. |
| 3793 | "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the |
| 3794 | # Cloud Dataflow service. |
| 3795 | "requestedState": "A String", # The job's requested state. |
| 3796 | # |
| 3797 | # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and |
| 3798 | # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may |
| 3799 | # also be used to directly set a job's requested state to |
| 3800 | # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the |
| 3801 | # job if it has not already reached a terminal state. |
| 3802 | "name": "A String", # The user-specified Cloud Dataflow job name. |
| 3803 | # |
| 3804 | # Only one Job with a given name may exist in a project at any |
| 3805 | # given time. If a caller attempts to create a Job with the same |
| 3806 | # name as an already-existing Job, the attempt returns the |
| 3807 | # existing Job. |
| 3808 | # |
| 3809 | # The name must match the regular expression |
| 3810 | # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` |
| 3811 | "steps": [ # Exactly one of step or steps_location should be specified. |
| 3812 | # |
| 3813 | # The top-level steps that constitute the entire job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3814 | { # Defines a particular step within a Cloud Dataflow job. |
| 3815 | # |
| 3816 | # A job consists of multiple steps, each of which performs some |
| 3817 | # specific operation as part of the overall job. Data is typically |
| 3818 | # passed from one step to another as part of the job. |
| 3819 | # |
| 3820 | # Here's an example of a sequence of steps which together implement a |
| 3821 | # Map-Reduce job: |
| 3822 | # |
| 3823 | # * Read a collection of data from some source, parsing the |
| 3824 | # collection's elements. |
| 3825 | # |
| 3826 | # * Validate the elements. |
| 3827 | # |
| 3828 | # * Apply a user-defined function to map each element to some value |
| 3829 | # and extract an element-specific key value. |
| 3830 | # |
| 3831 | # * Group elements with the same key into a single element with |
| 3832 | # that key, transforming a multiply-keyed collection into a |
| 3833 | # uniquely-keyed collection. |
| 3834 | # |
| 3835 | # * Write the elements out to some data sink. |
| 3836 | # |
| 3837 | # Note that the Cloud Dataflow service may be used to run many different |
| 3838 | # types of jobs, not just Map-Reduce. |
| 3839 | "kind": "A String", # The kind of step in the Cloud Dataflow job. |
Dan O'Meara | dd49464 | 2020-05-01 07:42:23 -0700 | [diff] [blame] | 3840 | "name": "A String", # The name that identifies the step. This must be unique for each |
| 3841 | # step with respect to all other steps in the Cloud Dataflow job. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3842 | "properties": { # Named properties associated with the step. Each kind of |
| 3843 | # predefined step has its own required set of properties. |
| 3844 | # Must be provided on Create. Only retrieved with JOB_VIEW_ALL. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3845 | "a_key": "", # Properties of the object. |
| 3846 | }, |
| 3847 | }, |
| 3848 | ], |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 3849 | "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID |
| 3850 | # of the job it replaced. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3851 | # |
Thomas Coffee | 2f24537 | 2017-03-27 10:39:26 -0700 | [diff] [blame] | 3852 | # When sending a `CreateJobRequest`, you can update a job by specifying it |
| 3853 | # here. The job named here is stopped, and its intermediate state is |
| 3854 | # transferred to this job. |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3855 | "currentState": "A String", # The current state of the job. |
| 3856 | # |
| 3857 | # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise |
| 3858 | # specified. |
| 3859 | # |
| 3860 | # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a |
| 3861 | # terminal state. After a job has reached a terminal state, no |
| 3862 | # further state updates may be made. |
| 3863 | # |
| 3864 | # This field may be mutated by the Cloud Dataflow service; |
| 3865 | # callers cannot mutate it. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3866 | "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated. |
| 3867 | # isn't contained in the submitted job. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3868 | "stages": { # A mapping from each stage to the information about that stage. |
Sai Cheemalapati | c30d2b5 | 2017-03-13 12:12:03 -0400 | [diff] [blame] | 3869 | "a_key": { # Contains information about how a particular |
| 3870 | # google.dataflow.v1beta3.Step will be executed. |
| 3871 | "stepName": [ # The steps associated with the execution stage. |
| 3872 | # Note that stages may have several steps, and that a given step |
| 3873 | # might be run by more than one stage. |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3874 | "A String", |
| 3875 | ], |
| 3876 | }, |
| 3877 | }, |
| 3878 | }, |
Bu Sun Kim | 715bd7f | 2019-06-14 16:50:42 -0700 | [diff] [blame] | 3879 | }</pre> |
Jon Wayne Parrott | 692617a | 2017-01-06 09:58:29 -0800 | [diff] [blame] | 3880 | </div> |
| 3881 | |
| 3882 | </body></html> |