google-apis-dataproc_v1 0.17.0 → 0.21.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +18 -0
- data/OVERVIEW.md +1 -1
- data/lib/google/apis/dataproc_v1/classes.rb +627 -8
- data/lib/google/apis/dataproc_v1/gem_version.rb +3 -3
- data/lib/google/apis/dataproc_v1/representations.rb +256 -0
- data/lib/google/apis/dataproc_v1/service.rb +151 -2
- metadata +4 -4
@@ -245,6 +245,131 @@ module Google
|
|
245
245
|
end
|
246
246
|
end
|
247
247
|
|
248
|
+
# A representation of a batch workload in the service.
|
249
|
+
class Batch
|
250
|
+
include Google::Apis::Core::Hashable
|
251
|
+
|
252
|
+
# Output only. The time when the batch was created.
|
253
|
+
# Corresponds to the JSON property `createTime`
|
254
|
+
# @return [String]
|
255
|
+
attr_accessor :create_time
|
256
|
+
|
257
|
+
# Output only. The email address of the user who created the batch.
|
258
|
+
# Corresponds to the JSON property `creator`
|
259
|
+
# @return [String]
|
260
|
+
attr_accessor :creator
|
261
|
+
|
262
|
+
# Environment configuration for a workload.
|
263
|
+
# Corresponds to the JSON property `environmentConfig`
|
264
|
+
# @return [Google::Apis::DataprocV1::EnvironmentConfig]
|
265
|
+
attr_accessor :environment_config
|
266
|
+
|
267
|
+
# Optional. The labels to associate with this batch. Label keys must contain 1
|
268
|
+
# to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/
|
269
|
+
# rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63
|
270
|
+
# characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt)
|
271
|
+
# . No more than 32 labels can be associated with a batch.
|
272
|
+
# Corresponds to the JSON property `labels`
|
273
|
+
# @return [Hash<String,String>]
|
274
|
+
attr_accessor :labels
|
275
|
+
|
276
|
+
# Output only. The resource name of the batch.
|
277
|
+
# Corresponds to the JSON property `name`
|
278
|
+
# @return [String]
|
279
|
+
attr_accessor :name
|
280
|
+
|
281
|
+
# Output only. The resource name of the operation associated with this batch.
|
282
|
+
# Corresponds to the JSON property `operation`
|
283
|
+
# @return [String]
|
284
|
+
attr_accessor :operation
|
285
|
+
|
286
|
+
# A configuration for running an Apache PySpark (https://spark.apache.org/docs/
|
287
|
+
# latest/api/python/getting_started/quickstart.html) batch workload.
|
288
|
+
# Corresponds to the JSON property `pysparkBatch`
|
289
|
+
# @return [Google::Apis::DataprocV1::PySparkBatch]
|
290
|
+
attr_accessor :pyspark_batch
|
291
|
+
|
292
|
+
# Runtime configuration for a workload.
|
293
|
+
# Corresponds to the JSON property `runtimeConfig`
|
294
|
+
# @return [Google::Apis::DataprocV1::RuntimeConfig]
|
295
|
+
attr_accessor :runtime_config
|
296
|
+
|
297
|
+
# Runtime information about workload execution.
|
298
|
+
# Corresponds to the JSON property `runtimeInfo`
|
299
|
+
# @return [Google::Apis::DataprocV1::RuntimeInfo]
|
300
|
+
attr_accessor :runtime_info
|
301
|
+
|
302
|
+
# A configuration for running an Apache Spark (https://spark.apache.org/) batch
|
303
|
+
# workload.
|
304
|
+
# Corresponds to the JSON property `sparkBatch`
|
305
|
+
# @return [Google::Apis::DataprocV1::SparkBatch]
|
306
|
+
attr_accessor :spark_batch
|
307
|
+
|
308
|
+
# A configuration for running an Apache SparkR (https://spark.apache.org/docs/
|
309
|
+
# latest/sparkr.html) batch workload.
|
310
|
+
# Corresponds to the JSON property `sparkRBatch`
|
311
|
+
# @return [Google::Apis::DataprocV1::SparkRBatch]
|
312
|
+
attr_accessor :spark_r_batch
|
313
|
+
|
314
|
+
# A configuration for running Apache Spark SQL (https://spark.apache.org/sql/)
|
315
|
+
# queries as a batch workload.
|
316
|
+
# Corresponds to the JSON property `sparkSqlBatch`
|
317
|
+
# @return [Google::Apis::DataprocV1::SparkSqlBatch]
|
318
|
+
attr_accessor :spark_sql_batch
|
319
|
+
|
320
|
+
# Output only. The state of the batch.
|
321
|
+
# Corresponds to the JSON property `state`
|
322
|
+
# @return [String]
|
323
|
+
attr_accessor :state
|
324
|
+
|
325
|
+
# Output only. Historical state information for the batch.
|
326
|
+
# Corresponds to the JSON property `stateHistory`
|
327
|
+
# @return [Array<Google::Apis::DataprocV1::StateHistory>]
|
328
|
+
attr_accessor :state_history
|
329
|
+
|
330
|
+
# Output only. Batch state details, such as a failure description if the state
|
331
|
+
# is FAILED.
|
332
|
+
# Corresponds to the JSON property `stateMessage`
|
333
|
+
# @return [String]
|
334
|
+
attr_accessor :state_message
|
335
|
+
|
336
|
+
# Output only. The time when the batch entered a current state.
|
337
|
+
# Corresponds to the JSON property `stateTime`
|
338
|
+
# @return [String]
|
339
|
+
attr_accessor :state_time
|
340
|
+
|
341
|
+
# Output only. A batch UUID (Unique Universal Identifier). The service generates
|
342
|
+
# this value when it creates the batch.
|
343
|
+
# Corresponds to the JSON property `uuid`
|
344
|
+
# @return [String]
|
345
|
+
attr_accessor :uuid
|
346
|
+
|
347
|
+
def initialize(**args)
|
348
|
+
update!(**args)
|
349
|
+
end
|
350
|
+
|
351
|
+
# Update properties of this object
|
352
|
+
def update!(**args)
|
353
|
+
@create_time = args[:create_time] if args.key?(:create_time)
|
354
|
+
@creator = args[:creator] if args.key?(:creator)
|
355
|
+
@environment_config = args[:environment_config] if args.key?(:environment_config)
|
356
|
+
@labels = args[:labels] if args.key?(:labels)
|
357
|
+
@name = args[:name] if args.key?(:name)
|
358
|
+
@operation = args[:operation] if args.key?(:operation)
|
359
|
+
@pyspark_batch = args[:pyspark_batch] if args.key?(:pyspark_batch)
|
360
|
+
@runtime_config = args[:runtime_config] if args.key?(:runtime_config)
|
361
|
+
@runtime_info = args[:runtime_info] if args.key?(:runtime_info)
|
362
|
+
@spark_batch = args[:spark_batch] if args.key?(:spark_batch)
|
363
|
+
@spark_r_batch = args[:spark_r_batch] if args.key?(:spark_r_batch)
|
364
|
+
@spark_sql_batch = args[:spark_sql_batch] if args.key?(:spark_sql_batch)
|
365
|
+
@state = args[:state] if args.key?(:state)
|
366
|
+
@state_history = args[:state_history] if args.key?(:state_history)
|
367
|
+
@state_message = args[:state_message] if args.key?(:state_message)
|
368
|
+
@state_time = args[:state_time] if args.key?(:state_time)
|
369
|
+
@uuid = args[:uuid] if args.key?(:uuid)
|
370
|
+
end
|
371
|
+
end
|
372
|
+
|
248
373
|
# Metadata describing the Batch operation.
|
249
374
|
class BatchOperationMetadata
|
250
375
|
include Google::Apis::Core::Hashable
|
@@ -481,6 +606,11 @@ module Google
|
|
481
606
|
# @return [String]
|
482
607
|
attr_accessor :config_bucket
|
483
608
|
|
609
|
+
# Contains dataproc metric config.
|
610
|
+
# Corresponds to the JSON property `dataprocMetricConfig`
|
611
|
+
# @return [Google::Apis::DataprocV1::DataprocMetricConfig]
|
612
|
+
attr_accessor :dataproc_metric_config
|
613
|
+
|
484
614
|
# Encryption settings for the cluster.
|
485
615
|
# Corresponds to the JSON property `encryptionConfig`
|
486
616
|
# @return [Google::Apis::DataprocV1::EncryptionConfig]
|
@@ -573,6 +703,7 @@ module Google
|
|
573
703
|
def update!(**args)
|
574
704
|
@autoscaling_config = args[:autoscaling_config] if args.key?(:autoscaling_config)
|
575
705
|
@config_bucket = args[:config_bucket] if args.key?(:config_bucket)
|
706
|
+
@dataproc_metric_config = args[:dataproc_metric_config] if args.key?(:dataproc_metric_config)
|
576
707
|
@encryption_config = args[:encryption_config] if args.key?(:encryption_config)
|
577
708
|
@endpoint_config = args[:endpoint_config] if args.key?(:endpoint_config)
|
578
709
|
@gce_cluster_config = args[:gce_cluster_config] if args.key?(:gce_cluster_config)
|
@@ -834,6 +965,25 @@ module Google
|
|
834
965
|
end
|
835
966
|
end
|
836
967
|
|
968
|
+
# Contains dataproc metric config.
|
969
|
+
class DataprocMetricConfig
|
970
|
+
include Google::Apis::Core::Hashable
|
971
|
+
|
972
|
+
# Required. Metrics to be enabled.
|
973
|
+
# Corresponds to the JSON property `metrics`
|
974
|
+
# @return [Array<Google::Apis::DataprocV1::Metric>]
|
975
|
+
attr_accessor :metrics
|
976
|
+
|
977
|
+
def initialize(**args)
|
978
|
+
update!(**args)
|
979
|
+
end
|
980
|
+
|
981
|
+
# Update properties of this object
|
982
|
+
def update!(**args)
|
983
|
+
@metrics = args[:metrics] if args.key?(:metrics)
|
984
|
+
end
|
985
|
+
end
|
986
|
+
|
837
987
|
# A request to collect cluster diagnostic information.
|
838
988
|
class DiagnoseClusterRequest
|
839
989
|
include Google::Apis::Core::Hashable
|
@@ -884,6 +1034,14 @@ module Google
|
|
884
1034
|
# @return [String]
|
885
1035
|
attr_accessor :boot_disk_type
|
886
1036
|
|
1037
|
+
# Optional. Interface type of local SSDs (default is "scsi"). Valid values: "
|
1038
|
+
# scsi" (Small Computer System Interface), "nvme" (Non-Volatile Memory Express).
|
1039
|
+
# See local SSD performance (https://cloud.google.com/compute/docs/disks/local-
|
1040
|
+
# ssd#performance).
|
1041
|
+
# Corresponds to the JSON property `localSsdInterface`
|
1042
|
+
# @return [String]
|
1043
|
+
attr_accessor :local_ssd_interface
|
1044
|
+
|
887
1045
|
# Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not
|
888
1046
|
# attached, the boot disk is used to store runtime logs and HDFS (https://hadoop.
|
889
1047
|
# apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are
|
@@ -901,6 +1059,7 @@ module Google
|
|
901
1059
|
def update!(**args)
|
902
1060
|
@boot_disk_size_gb = args[:boot_disk_size_gb] if args.key?(:boot_disk_size_gb)
|
903
1061
|
@boot_disk_type = args[:boot_disk_type] if args.key?(:boot_disk_type)
|
1062
|
+
@local_ssd_interface = args[:local_ssd_interface] if args.key?(:local_ssd_interface)
|
904
1063
|
@num_local_ssds = args[:num_local_ssds] if args.key?(:num_local_ssds)
|
905
1064
|
end
|
906
1065
|
end
|
@@ -970,6 +1129,74 @@ module Google
|
|
970
1129
|
end
|
971
1130
|
end
|
972
1131
|
|
1132
|
+
# Environment configuration for a workload.
|
1133
|
+
class EnvironmentConfig
|
1134
|
+
include Google::Apis::Core::Hashable
|
1135
|
+
|
1136
|
+
# Execution configuration for a workload.
|
1137
|
+
# Corresponds to the JSON property `executionConfig`
|
1138
|
+
# @return [Google::Apis::DataprocV1::ExecutionConfig]
|
1139
|
+
attr_accessor :execution_config
|
1140
|
+
|
1141
|
+
# Auxiliary services configuration for a workload.
|
1142
|
+
# Corresponds to the JSON property `peripheralsConfig`
|
1143
|
+
# @return [Google::Apis::DataprocV1::PeripheralsConfig]
|
1144
|
+
attr_accessor :peripherals_config
|
1145
|
+
|
1146
|
+
def initialize(**args)
|
1147
|
+
update!(**args)
|
1148
|
+
end
|
1149
|
+
|
1150
|
+
# Update properties of this object
|
1151
|
+
def update!(**args)
|
1152
|
+
@execution_config = args[:execution_config] if args.key?(:execution_config)
|
1153
|
+
@peripherals_config = args[:peripherals_config] if args.key?(:peripherals_config)
|
1154
|
+
end
|
1155
|
+
end
|
1156
|
+
|
1157
|
+
# Execution configuration for a workload.
|
1158
|
+
class ExecutionConfig
|
1159
|
+
include Google::Apis::Core::Hashable
|
1160
|
+
|
1161
|
+
# Optional. The Cloud KMS key to use for encryption.
|
1162
|
+
# Corresponds to the JSON property `kmsKey`
|
1163
|
+
# @return [String]
|
1164
|
+
attr_accessor :kms_key
|
1165
|
+
|
1166
|
+
# Optional. Tags used for network traffic control.
|
1167
|
+
# Corresponds to the JSON property `networkTags`
|
1168
|
+
# @return [Array<String>]
|
1169
|
+
attr_accessor :network_tags
|
1170
|
+
|
1171
|
+
# Optional. Network URI to connect workload to.
|
1172
|
+
# Corresponds to the JSON property `networkUri`
|
1173
|
+
# @return [String]
|
1174
|
+
attr_accessor :network_uri
|
1175
|
+
|
1176
|
+
# Optional. Service account that used to execute workload.
|
1177
|
+
# Corresponds to the JSON property `serviceAccount`
|
1178
|
+
# @return [String]
|
1179
|
+
attr_accessor :service_account
|
1180
|
+
|
1181
|
+
# Optional. Subnetwork URI to connect workload to.
|
1182
|
+
# Corresponds to the JSON property `subnetworkUri`
|
1183
|
+
# @return [String]
|
1184
|
+
attr_accessor :subnetwork_uri
|
1185
|
+
|
1186
|
+
def initialize(**args)
|
1187
|
+
update!(**args)
|
1188
|
+
end
|
1189
|
+
|
1190
|
+
# Update properties of this object
|
1191
|
+
def update!(**args)
|
1192
|
+
@kms_key = args[:kms_key] if args.key?(:kms_key)
|
1193
|
+
@network_tags = args[:network_tags] if args.key?(:network_tags)
|
1194
|
+
@network_uri = args[:network_uri] if args.key?(:network_uri)
|
1195
|
+
@service_account = args[:service_account] if args.key?(:service_account)
|
1196
|
+
@subnetwork_uri = args[:subnetwork_uri] if args.key?(:subnetwork_uri)
|
1197
|
+
end
|
1198
|
+
end
|
1199
|
+
|
973
1200
|
# Represents a textual expression in the Common Expression Language (CEL) syntax.
|
974
1201
|
# CEL is a C-like expression language. The syntax and semantics of CEL are
|
975
1202
|
# documented at https://github.com/google/cel-spec.Example (Comparison): title: "
|
@@ -1729,7 +1956,7 @@ module Google
|
|
1729
1956
|
# @return [Google::Apis::DataprocV1::JobScheduling]
|
1730
1957
|
attr_accessor :scheduling
|
1731
1958
|
|
1732
|
-
# A Dataproc job for running Apache Spark (
|
1959
|
+
# A Dataproc job for running Apache Spark (https://spark.apache.org/)
|
1733
1960
|
# applications on YARN.
|
1734
1961
|
# Corresponds to the JSON property `sparkJob`
|
1735
1962
|
# @return [Google::Apis::DataprocV1::SparkJob]
|
@@ -1741,7 +1968,7 @@ module Google
|
|
1741
1968
|
# @return [Google::Apis::DataprocV1::SparkRJob]
|
1742
1969
|
attr_accessor :spark_r_job
|
1743
1970
|
|
1744
|
-
# A Dataproc job for running Apache Spark SQL (
|
1971
|
+
# A Dataproc job for running Apache Spark SQL (https://spark.apache.org/sql/)
|
1745
1972
|
# queries.
|
1746
1973
|
# Corresponds to the JSON property `sparkSqlJob`
|
1747
1974
|
# @return [Google::Apis::DataprocV1::SparkSqlJob]
|
@@ -1897,14 +2124,19 @@ module Google
|
|
1897
2124
|
# Optional. Maximum number of times per hour a driver may be restarted as a
|
1898
2125
|
# result of driver exiting with non-zero code before job is reported failed.A
|
1899
2126
|
# job may be reported as thrashing if driver exits with non-zero code 4 times
|
1900
|
-
# within 10 minute window.Maximum value is 10.
|
2127
|
+
# within 10 minute window.Maximum value is 10.Note: Currently, this restartable
|
2128
|
+
# job option is not supported in Dataproc workflow template (https://cloud.
|
2129
|
+
# google.com/dataproc/docs/concepts/workflows/using-workflows#
|
2130
|
+
# adding_jobs_to_a_template) jobs.
|
1901
2131
|
# Corresponds to the JSON property `maxFailuresPerHour`
|
1902
2132
|
# @return [Fixnum]
|
1903
2133
|
attr_accessor :max_failures_per_hour
|
1904
2134
|
|
1905
2135
|
# Optional. Maximum number of times in total a driver may be restarted as a
|
1906
2136
|
# result of driver exiting with non-zero code before job is reported failed.
|
1907
|
-
# Maximum value is 240.
|
2137
|
+
# Maximum value is 240.Note: Currently, this restartable job option is not
|
2138
|
+
# supported in Dataproc workflow template (https://cloud.google.com/dataproc/
|
2139
|
+
# docs/concepts/workflows/using-workflows#adding_jobs_to_a_template) jobs.
|
1908
2140
|
# Corresponds to the JSON property `maxFailuresTotal`
|
1909
2141
|
# @return [Fixnum]
|
1910
2142
|
attr_accessor :max_failures_total
|
@@ -2154,6 +2386,32 @@ module Google
|
|
2154
2386
|
end
|
2155
2387
|
end
|
2156
2388
|
|
2389
|
+
# A list of batch workloads.
|
2390
|
+
class ListBatchesResponse
|
2391
|
+
include Google::Apis::Core::Hashable
|
2392
|
+
|
2393
|
+
# The batches from the specified collection.
|
2394
|
+
# Corresponds to the JSON property `batches`
|
2395
|
+
# @return [Array<Google::Apis::DataprocV1::Batch>]
|
2396
|
+
attr_accessor :batches
|
2397
|
+
|
2398
|
+
# A token, which can be sent as page_token to retrieve the next page. If this
|
2399
|
+
# field is omitted, there are no subsequent pages.
|
2400
|
+
# Corresponds to the JSON property `nextPageToken`
|
2401
|
+
# @return [String]
|
2402
|
+
attr_accessor :next_page_token
|
2403
|
+
|
2404
|
+
def initialize(**args)
|
2405
|
+
update!(**args)
|
2406
|
+
end
|
2407
|
+
|
2408
|
+
# Update properties of this object
|
2409
|
+
def update!(**args)
|
2410
|
+
@batches = args[:batches] if args.key?(:batches)
|
2411
|
+
@next_page_token = args[:next_page_token] if args.key?(:next_page_token)
|
2412
|
+
end
|
2413
|
+
end
|
2414
|
+
|
2157
2415
|
# The list of all clusters in a project.
|
2158
2416
|
class ListClustersResponse
|
2159
2417
|
include Google::Apis::Core::Hashable
|
@@ -2365,6 +2623,33 @@ module Google
|
|
2365
2623
|
end
|
2366
2624
|
end
|
2367
2625
|
|
2626
|
+
# Metric source to enable along with any optional metrics for this source that
|
2627
|
+
# override the dataproc defaults
|
2628
|
+
class Metric
|
2629
|
+
include Google::Apis::Core::Hashable
|
2630
|
+
|
2631
|
+
# Optional. Optional Metrics to override the dataproc default metrics configured
|
2632
|
+
# for the metric source
|
2633
|
+
# Corresponds to the JSON property `metricOverrides`
|
2634
|
+
# @return [Array<String>]
|
2635
|
+
attr_accessor :metric_overrides
|
2636
|
+
|
2637
|
+
# Required. MetricSource that should be enabled
|
2638
|
+
# Corresponds to the JSON property `metricSource`
|
2639
|
+
# @return [String]
|
2640
|
+
attr_accessor :metric_source
|
2641
|
+
|
2642
|
+
def initialize(**args)
|
2643
|
+
update!(**args)
|
2644
|
+
end
|
2645
|
+
|
2646
|
+
# Update properties of this object
|
2647
|
+
def update!(**args)
|
2648
|
+
@metric_overrides = args[:metric_overrides] if args.key?(:metric_overrides)
|
2649
|
+
@metric_source = args[:metric_source] if args.key?(:metric_source)
|
2650
|
+
end
|
2651
|
+
end
|
2652
|
+
|
2368
2653
|
# A full, namespace-isolated deployment target for an existing GKE cluster.
|
2369
2654
|
class NamespacedGkeDeploymentTarget
|
2370
2655
|
include Google::Apis::Core::Hashable
|
@@ -2566,7 +2851,7 @@ module Google
|
|
2566
2851
|
# @return [Google::Apis::DataprocV1::JobScheduling]
|
2567
2852
|
attr_accessor :scheduling
|
2568
2853
|
|
2569
|
-
# A Dataproc job for running Apache Spark (
|
2854
|
+
# A Dataproc job for running Apache Spark (https://spark.apache.org/)
|
2570
2855
|
# applications on YARN.
|
2571
2856
|
# Corresponds to the JSON property `sparkJob`
|
2572
2857
|
# @return [Google::Apis::DataprocV1::SparkJob]
|
@@ -2578,7 +2863,7 @@ module Google
|
|
2578
2863
|
# @return [Google::Apis::DataprocV1::SparkRJob]
|
2579
2864
|
attr_accessor :spark_r_job
|
2580
2865
|
|
2581
|
-
# A Dataproc job for running Apache Spark SQL (
|
2866
|
+
# A Dataproc job for running Apache Spark SQL (https://spark.apache.org/sql/)
|
2582
2867
|
# queries.
|
2583
2868
|
# Corresponds to the JSON property `sparkSqlJob`
|
2584
2869
|
# @return [Google::Apis::DataprocV1::SparkSqlJob]
|
@@ -2640,6 +2925,32 @@ module Google
|
|
2640
2925
|
end
|
2641
2926
|
end
|
2642
2927
|
|
2928
|
+
# Auxiliary services configuration for a workload.
|
2929
|
+
class PeripheralsConfig
|
2930
|
+
include Google::Apis::Core::Hashable
|
2931
|
+
|
2932
|
+
# Optional. Resource name of an existing Dataproc Metastore service.Example:
|
2933
|
+
# projects/[project_id]/locations/[region]/services/[service_id]
|
2934
|
+
# Corresponds to the JSON property `metastoreService`
|
2935
|
+
# @return [String]
|
2936
|
+
attr_accessor :metastore_service
|
2937
|
+
|
2938
|
+
# Spark History Server configuration for the workload.
|
2939
|
+
# Corresponds to the JSON property `sparkHistoryServerConfig`
|
2940
|
+
# @return [Google::Apis::DataprocV1::SparkHistoryServerConfig]
|
2941
|
+
attr_accessor :spark_history_server_config
|
2942
|
+
|
2943
|
+
def initialize(**args)
|
2944
|
+
update!(**args)
|
2945
|
+
end
|
2946
|
+
|
2947
|
+
# Update properties of this object
|
2948
|
+
def update!(**args)
|
2949
|
+
@metastore_service = args[:metastore_service] if args.key?(:metastore_service)
|
2950
|
+
@spark_history_server_config = args[:spark_history_server_config] if args.key?(:spark_history_server_config)
|
2951
|
+
end
|
2952
|
+
end
|
2953
|
+
|
2643
2954
|
# A Dataproc job for running Apache Pig (https://pig.apache.org/) queries on
|
2644
2955
|
# YARN.
|
2645
2956
|
class PigJob
|
@@ -2855,6 +3166,63 @@ module Google
|
|
2855
3166
|
end
|
2856
3167
|
end
|
2857
3168
|
|
3169
|
+
# A configuration for running an Apache PySpark (https://spark.apache.org/docs/
|
3170
|
+
# latest/api/python/getting_started/quickstart.html) batch workload.
|
3171
|
+
class PySparkBatch
|
3172
|
+
include Google::Apis::Core::Hashable
|
3173
|
+
|
3174
|
+
# Optional. HCFS URIs of archives to be extracted into the working directory of
|
3175
|
+
# each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
|
3176
|
+
# Corresponds to the JSON property `archiveUris`
|
3177
|
+
# @return [Array<String>]
|
3178
|
+
attr_accessor :archive_uris
|
3179
|
+
|
3180
|
+
# Optional. The arguments to pass to the driver. Do not include arguments that
|
3181
|
+
# can be set as batch properties, such as --conf, since a collision can occur
|
3182
|
+
# that causes an incorrect batch submission.
|
3183
|
+
# Corresponds to the JSON property `args`
|
3184
|
+
# @return [Array<String>]
|
3185
|
+
attr_accessor :args
|
3186
|
+
|
3187
|
+
# Optional. HCFS URIs of files to be placed in the working directory of each
|
3188
|
+
# executor.
|
3189
|
+
# Corresponds to the JSON property `fileUris`
|
3190
|
+
# @return [Array<String>]
|
3191
|
+
attr_accessor :file_uris
|
3192
|
+
|
3193
|
+
# Optional. HCFS URIs of jar files to add to the classpath of the Spark driver
|
3194
|
+
# and tasks.
|
3195
|
+
# Corresponds to the JSON property `jarFileUris`
|
3196
|
+
# @return [Array<String>]
|
3197
|
+
attr_accessor :jar_file_uris
|
3198
|
+
|
3199
|
+
# Required. The HCFS URI of the main Python file to use as the Spark driver.
|
3200
|
+
# Must be a .py file.
|
3201
|
+
# Corresponds to the JSON property `mainPythonFileUri`
|
3202
|
+
# @return [String]
|
3203
|
+
attr_accessor :main_python_file_uri
|
3204
|
+
|
3205
|
+
# Optional. HCFS file URIs of Python files to pass to the PySpark framework.
|
3206
|
+
# Supported file types: .py, .egg, and .zip.
|
3207
|
+
# Corresponds to the JSON property `pythonFileUris`
|
3208
|
+
# @return [Array<String>]
|
3209
|
+
attr_accessor :python_file_uris
|
3210
|
+
|
3211
|
+
def initialize(**args)
|
3212
|
+
update!(**args)
|
3213
|
+
end
|
3214
|
+
|
3215
|
+
# Update properties of this object
|
3216
|
+
def update!(**args)
|
3217
|
+
@archive_uris = args[:archive_uris] if args.key?(:archive_uris)
|
3218
|
+
@args = args[:args] if args.key?(:args)
|
3219
|
+
@file_uris = args[:file_uris] if args.key?(:file_uris)
|
3220
|
+
@jar_file_uris = args[:jar_file_uris] if args.key?(:jar_file_uris)
|
3221
|
+
@main_python_file_uri = args[:main_python_file_uri] if args.key?(:main_python_file_uri)
|
3222
|
+
@python_file_uris = args[:python_file_uris] if args.key?(:python_file_uris)
|
3223
|
+
end
|
3224
|
+
end
|
3225
|
+
|
2858
3226
|
# A Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/
|
2859
3227
|
# python-programming-guide.html) applications on YARN.
|
2860
3228
|
class PySparkJob
|
@@ -3034,6 +3402,72 @@ module Google
|
|
3034
3402
|
end
|
3035
3403
|
end
|
3036
3404
|
|
3405
|
+
# Runtime configuration for a workload.
|
3406
|
+
class RuntimeConfig
|
3407
|
+
include Google::Apis::Core::Hashable
|
3408
|
+
|
3409
|
+
# Optional. Optional custom container image for the job runtime environment. If
|
3410
|
+
# not specified, a default container image will be used.
|
3411
|
+
# Corresponds to the JSON property `containerImage`
|
3412
|
+
# @return [String]
|
3413
|
+
attr_accessor :container_image
|
3414
|
+
|
3415
|
+
# Optional. A mapping of property names to values, which are used to configure
|
3416
|
+
# workload execution.
|
3417
|
+
# Corresponds to the JSON property `properties`
|
3418
|
+
# @return [Hash<String,String>]
|
3419
|
+
attr_accessor :properties
|
3420
|
+
|
3421
|
+
# Optional. Version of the batch runtime.
|
3422
|
+
# Corresponds to the JSON property `version`
|
3423
|
+
# @return [String]
|
3424
|
+
attr_accessor :version
|
3425
|
+
|
3426
|
+
def initialize(**args)
|
3427
|
+
update!(**args)
|
3428
|
+
end
|
3429
|
+
|
3430
|
+
# Update properties of this object
|
3431
|
+
def update!(**args)
|
3432
|
+
@container_image = args[:container_image] if args.key?(:container_image)
|
3433
|
+
@properties = args[:properties] if args.key?(:properties)
|
3434
|
+
@version = args[:version] if args.key?(:version)
|
3435
|
+
end
|
3436
|
+
end
|
3437
|
+
|
3438
|
+
# Runtime information about workload execution.
|
3439
|
+
class RuntimeInfo
|
3440
|
+
include Google::Apis::Core::Hashable
|
3441
|
+
|
3442
|
+
# Output only. A URI pointing to the location of the diagnostics tarball.
|
3443
|
+
# Corresponds to the JSON property `diagnosticOutputUri`
|
3444
|
+
# @return [String]
|
3445
|
+
attr_accessor :diagnostic_output_uri
|
3446
|
+
|
3447
|
+
# Output only. Map of remote access endpoints (such as web interfaces and APIs)
|
3448
|
+
# to their URIs.
|
3449
|
+
# Corresponds to the JSON property `endpoints`
|
3450
|
+
# @return [Hash<String,String>]
|
3451
|
+
attr_accessor :endpoints
|
3452
|
+
|
3453
|
+
# Output only. A URI pointing to the location of the stdout and stderr of the
|
3454
|
+
# workload.
|
3455
|
+
# Corresponds to the JSON property `outputUri`
|
3456
|
+
# @return [String]
|
3457
|
+
attr_accessor :output_uri
|
3458
|
+
|
3459
|
+
def initialize(**args)
|
3460
|
+
update!(**args)
|
3461
|
+
end
|
3462
|
+
|
3463
|
+
# Update properties of this object
|
3464
|
+
def update!(**args)
|
3465
|
+
@diagnostic_output_uri = args[:diagnostic_output_uri] if args.key?(:diagnostic_output_uri)
|
3466
|
+
@endpoints = args[:endpoints] if args.key?(:endpoints)
|
3467
|
+
@output_uri = args[:output_uri] if args.key?(:output_uri)
|
3468
|
+
end
|
3469
|
+
end
|
3470
|
+
|
3037
3471
|
# Security related configuration, including encryption, Kerberos, etc.
|
3038
3472
|
class SecurityConfig
|
3039
3473
|
include Google::Apis::Core::Hashable
|
@@ -3244,7 +3678,84 @@ module Google
|
|
3244
3678
|
end
|
3245
3679
|
end
|
3246
3680
|
|
3247
|
-
# A
|
3681
|
+
# A configuration for running an Apache Spark (https://spark.apache.org/) batch
|
3682
|
+
# workload.
|
3683
|
+
class SparkBatch
|
3684
|
+
include Google::Apis::Core::Hashable
|
3685
|
+
|
3686
|
+
# Optional. HCFS URIs of archives to be extracted into the working directory of
|
3687
|
+
# each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
|
3688
|
+
# Corresponds to the JSON property `archiveUris`
|
3689
|
+
# @return [Array<String>]
|
3690
|
+
attr_accessor :archive_uris
|
3691
|
+
|
3692
|
+
# Optional. The arguments to pass to the driver. Do not include arguments that
|
3693
|
+
# can be set as batch properties, such as --conf, since a collision can occur
|
3694
|
+
# that causes an incorrect batch submission.
|
3695
|
+
# Corresponds to the JSON property `args`
|
3696
|
+
# @return [Array<String>]
|
3697
|
+
attr_accessor :args
|
3698
|
+
|
3699
|
+
# Optional. HCFS URIs of files to be placed in the working directory of each
|
3700
|
+
# executor.
|
3701
|
+
# Corresponds to the JSON property `fileUris`
|
3702
|
+
# @return [Array<String>]
|
3703
|
+
attr_accessor :file_uris
|
3704
|
+
|
3705
|
+
# Optional. HCFS URIs of jar files to add to the classpath of the Spark driver
|
3706
|
+
# and tasks.
|
3707
|
+
# Corresponds to the JSON property `jarFileUris`
|
3708
|
+
# @return [Array<String>]
|
3709
|
+
attr_accessor :jar_file_uris
|
3710
|
+
|
3711
|
+
# Optional. The name of the driver main class. The jar file that contains the
|
3712
|
+
# class must be in the classpath or specified in jar_file_uris.
|
3713
|
+
# Corresponds to the JSON property `mainClass`
|
3714
|
+
# @return [String]
|
3715
|
+
attr_accessor :main_class
|
3716
|
+
|
3717
|
+
# Optional. The HCFS URI of the jar file that contains the main class.
|
3718
|
+
# Corresponds to the JSON property `mainJarFileUri`
|
3719
|
+
# @return [String]
|
3720
|
+
attr_accessor :main_jar_file_uri
|
3721
|
+
|
3722
|
+
def initialize(**args)
|
3723
|
+
update!(**args)
|
3724
|
+
end
|
3725
|
+
|
3726
|
+
# Update properties of this object
|
3727
|
+
def update!(**args)
|
3728
|
+
@archive_uris = args[:archive_uris] if args.key?(:archive_uris)
|
3729
|
+
@args = args[:args] if args.key?(:args)
|
3730
|
+
@file_uris = args[:file_uris] if args.key?(:file_uris)
|
3731
|
+
@jar_file_uris = args[:jar_file_uris] if args.key?(:jar_file_uris)
|
3732
|
+
@main_class = args[:main_class] if args.key?(:main_class)
|
3733
|
+
@main_jar_file_uri = args[:main_jar_file_uri] if args.key?(:main_jar_file_uri)
|
3734
|
+
end
|
3735
|
+
end
|
3736
|
+
|
3737
|
+
# Spark History Server configuration for the workload.
|
3738
|
+
class SparkHistoryServerConfig
|
3739
|
+
include Google::Apis::Core::Hashable
|
3740
|
+
|
3741
|
+
# Optional. Resource name of an existing Dataproc Cluster to act as a Spark
|
3742
|
+
# History Server for the workload.Example: projects/[project_id]/regions/[region]
|
3743
|
+
# /clusters/[cluster_name]
|
3744
|
+
# Corresponds to the JSON property `dataprocCluster`
|
3745
|
+
# @return [String]
|
3746
|
+
attr_accessor :dataproc_cluster
|
3747
|
+
|
3748
|
+
def initialize(**args)
|
3749
|
+
update!(**args)
|
3750
|
+
end
|
3751
|
+
|
3752
|
+
# Update properties of this object
|
3753
|
+
def update!(**args)
|
3754
|
+
@dataproc_cluster = args[:dataproc_cluster] if args.key?(:dataproc_cluster)
|
3755
|
+
end
|
3756
|
+
end
|
3757
|
+
|
3758
|
+
# A Dataproc job for running Apache Spark (https://spark.apache.org/)
|
3248
3759
|
# applications on YARN.
|
3249
3760
|
class SparkJob
|
3250
3761
|
include Google::Apis::Core::Hashable
|
@@ -3315,6 +3826,49 @@ module Google
|
|
3315
3826
|
end
|
3316
3827
|
end
|
3317
3828
|
|
3829
|
+
# A configuration for running an Apache SparkR (https://spark.apache.org/docs/
|
3830
|
+
# latest/sparkr.html) batch workload.
|
3831
|
+
class SparkRBatch
|
3832
|
+
include Google::Apis::Core::Hashable
|
3833
|
+
|
3834
|
+
# Optional. HCFS URIs of archives to be extracted into the working directory of
|
3835
|
+
# each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
|
3836
|
+
# Corresponds to the JSON property `archiveUris`
|
3837
|
+
# @return [Array<String>]
|
3838
|
+
attr_accessor :archive_uris
|
3839
|
+
|
3840
|
+
# Optional. The arguments to pass to the Spark driver. Do not include arguments
|
3841
|
+
# that can be set as batch properties, such as --conf, since a collision can
|
3842
|
+
# occur that causes an incorrect batch submission.
|
3843
|
+
# Corresponds to the JSON property `args`
|
3844
|
+
# @return [Array<String>]
|
3845
|
+
attr_accessor :args
|
3846
|
+
|
3847
|
+
# Optional. HCFS URIs of files to be placed in the working directory of each
|
3848
|
+
# executor.
|
3849
|
+
# Corresponds to the JSON property `fileUris`
|
3850
|
+
# @return [Array<String>]
|
3851
|
+
attr_accessor :file_uris
|
3852
|
+
|
3853
|
+
# Required. The HCFS URI of the main R file to use as the driver. Must be a .R
|
3854
|
+
# or .r file.
|
3855
|
+
# Corresponds to the JSON property `mainRFileUri`
|
3856
|
+
# @return [String]
|
3857
|
+
attr_accessor :main_r_file_uri
|
3858
|
+
|
3859
|
+
def initialize(**args)
|
3860
|
+
update!(**args)
|
3861
|
+
end
|
3862
|
+
|
3863
|
+
# Update properties of this object
|
3864
|
+
def update!(**args)
|
3865
|
+
@archive_uris = args[:archive_uris] if args.key?(:archive_uris)
|
3866
|
+
@args = args[:args] if args.key?(:args)
|
3867
|
+
@file_uris = args[:file_uris] if args.key?(:file_uris)
|
3868
|
+
@main_r_file_uri = args[:main_r_file_uri] if args.key?(:main_r_file_uri)
|
3869
|
+
end
|
3870
|
+
end
|
3871
|
+
|
3318
3872
|
# A Dataproc job for running Apache SparkR (https://spark.apache.org/docs/latest/
|
3319
3873
|
# sparkr.html) applications on YARN.
|
3320
3874
|
class SparkRJob
|
@@ -3373,7 +3927,41 @@ module Google
|
|
3373
3927
|
end
|
3374
3928
|
end
|
3375
3929
|
|
3376
|
-
# A
|
3930
|
+
# A configuration for running Apache Spark SQL (https://spark.apache.org/sql/)
|
3931
|
+
# queries as a batch workload.
|
3932
|
+
class SparkSqlBatch
|
3933
|
+
include Google::Apis::Core::Hashable
|
3934
|
+
|
3935
|
+
# Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
|
3936
|
+
# Corresponds to the JSON property `jarFileUris`
|
3937
|
+
# @return [Array<String>]
|
3938
|
+
attr_accessor :jar_file_uris
|
3939
|
+
|
3940
|
+
# Required. The HCFS URI of the script that contains Spark SQL queries to
|
3941
|
+
# execute.
|
3942
|
+
# Corresponds to the JSON property `queryFileUri`
|
3943
|
+
# @return [String]
|
3944
|
+
attr_accessor :query_file_uri
|
3945
|
+
|
3946
|
+
# Optional. Mapping of query variable names to values (equivalent to the Spark
|
3947
|
+
# SQL command: SET name="value";).
|
3948
|
+
# Corresponds to the JSON property `queryVariables`
|
3949
|
+
# @return [Hash<String,String>]
|
3950
|
+
attr_accessor :query_variables
|
3951
|
+
|
3952
|
+
def initialize(**args)
|
3953
|
+
update!(**args)
|
3954
|
+
end
|
3955
|
+
|
3956
|
+
# Update properties of this object
|
3957
|
+
def update!(**args)
|
3958
|
+
@jar_file_uris = args[:jar_file_uris] if args.key?(:jar_file_uris)
|
3959
|
+
@query_file_uri = args[:query_file_uri] if args.key?(:query_file_uri)
|
3960
|
+
@query_variables = args[:query_variables] if args.key?(:query_variables)
|
3961
|
+
end
|
3962
|
+
end
|
3963
|
+
|
3964
|
+
# A Dataproc job for running Apache Spark SQL (https://spark.apache.org/sql/)
|
3377
3965
|
# queries.
|
3378
3966
|
class SparkSqlJob
|
3379
3967
|
include Google::Apis::Core::Hashable
|
@@ -3522,6 +4110,37 @@ module Google
|
|
3522
4110
|
end
|
3523
4111
|
end
|
3524
4112
|
|
4113
|
+
# Historical state information.
|
4114
|
+
class StateHistory
|
4115
|
+
include Google::Apis::Core::Hashable
|
4116
|
+
|
4117
|
+
# Output only. The state of the batch at this point in history.
|
4118
|
+
# Corresponds to the JSON property `state`
|
4119
|
+
# @return [String]
|
4120
|
+
attr_accessor :state
|
4121
|
+
|
4122
|
+
# Output only. Details about the state at this point in history.
|
4123
|
+
# Corresponds to the JSON property `stateMessage`
|
4124
|
+
# @return [String]
|
4125
|
+
attr_accessor :state_message
|
4126
|
+
|
4127
|
+
# Output only. The time when the batch entered the historical state.
|
4128
|
+
# Corresponds to the JSON property `stateStartTime`
|
4129
|
+
# @return [String]
|
4130
|
+
attr_accessor :state_start_time
|
4131
|
+
|
4132
|
+
def initialize(**args)
|
4133
|
+
update!(**args)
|
4134
|
+
end
|
4135
|
+
|
4136
|
+
# Update properties of this object
|
4137
|
+
def update!(**args)
|
4138
|
+
@state = args[:state] if args.key?(:state)
|
4139
|
+
@state_message = args[:state_message] if args.key?(:state_message)
|
4140
|
+
@state_start_time = args[:state_start_time] if args.key?(:state_start_time)
|
4141
|
+
end
|
4142
|
+
end
|
4143
|
+
|
3525
4144
|
# The Status type defines a logical error model that is suitable for different
|
3526
4145
|
# programming environments, including REST APIs and RPC APIs. It is used by gRPC
|
3527
4146
|
# (https://github.com/grpc). Each Status message contains three pieces of data:
|