-
Notifications
You must be signed in to change notification settings - Fork 2.2k
/
clusters.proto
1588 lines (1363 loc) · 65.7 KB
/
clusters.proto
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// Copyright 2023 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
syntax = "proto3";
package google.cloud.dataproc.v1;
import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/cloud/dataproc/v1/shared.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/duration.proto";
import "google/protobuf/field_mask.proto";
import "google/protobuf/timestamp.proto";
import "google/protobuf/wrappers.proto";
import "google/type/interval.proto";
option go_package = "cloud.google.com/go/dataproc/v2/apiv1/dataprocpb;dataprocpb";
option java_multiple_files = true;
option java_outer_classname = "ClustersProto";
option java_package = "com.google.cloud.dataproc.v1";
// The ClusterControllerService provides methods to manage clusters
// of Compute Engine instances.
service ClusterController {
option (google.api.default_host) = "dataproc.googleapis.com";
option (google.api.oauth_scopes) =
"https://www.googleapis.com/auth/cloud-platform";
// Creates a cluster in a project. The returned
// [Operation.metadata][google.longrunning.Operation.metadata] will be
// [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
rpc CreateCluster(CreateClusterRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1/projects/{project_id}/regions/{region}/clusters"
body: "cluster"
};
option (google.api.method_signature) = "project_id,region,cluster";
option (google.longrunning.operation_info) = {
response_type: "Cluster"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
// Updates a cluster in a project. The returned
// [Operation.metadata][google.longrunning.Operation.metadata] will be
// [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
// The cluster must be in a
// [`RUNNING`][google.cloud.dataproc.v1.ClusterStatus.State] state or an error
// is returned.
rpc UpdateCluster(UpdateClusterRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
patch: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}"
body: "cluster"
};
option (google.api.method_signature) =
"project_id,region,cluster_name,cluster,update_mask";
option (google.longrunning.operation_info) = {
response_type: "Cluster"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
// Stops a cluster in a project.
rpc StopCluster(StopClusterRequest) returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:stop"
body: "*"
};
option (google.longrunning.operation_info) = {
response_type: "Cluster"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
// Starts a cluster in a project.
rpc StartCluster(StartClusterRequest) returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:start"
body: "*"
};
option (google.longrunning.operation_info) = {
response_type: "Cluster"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
// Deletes a cluster in a project. The returned
// [Operation.metadata][google.longrunning.Operation.metadata] will be
// [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
rpc DeleteCluster(DeleteClusterRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
delete: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}"
};
option (google.api.method_signature) = "project_id,region,cluster_name";
option (google.longrunning.operation_info) = {
response_type: "google.protobuf.Empty"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
// Gets the resource representation for a cluster in a project.
rpc GetCluster(GetClusterRequest) returns (Cluster) {
option (google.api.http) = {
get: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}"
};
option (google.api.method_signature) = "project_id,region,cluster_name";
}
// Lists all regions/{region}/clusters in a project alphabetically.
rpc ListClusters(ListClustersRequest) returns (ListClustersResponse) {
option (google.api.http) = {
get: "/v1/projects/{project_id}/regions/{region}/clusters"
};
option (google.api.method_signature) = "project_id,region";
option (google.api.method_signature) = "project_id,region,filter";
}
// Gets cluster diagnostic information. The returned
// [Operation.metadata][google.longrunning.Operation.metadata] will be
// [ClusterOperationMetadata](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#clusteroperationmetadata).
// After the operation completes,
// [Operation.response][google.longrunning.Operation.response]
// contains
// [DiagnoseClusterResults](https://cloud.google.com/dataproc/docs/reference/rpc/google.cloud.dataproc.v1#diagnoseclusterresults).
rpc DiagnoseCluster(DiagnoseClusterRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1/projects/{project_id}/regions/{region}/clusters/{cluster_name}:diagnose"
body: "*"
};
option (google.api.method_signature) = "project_id,region,cluster_name";
option (google.longrunning.operation_info) = {
response_type: "DiagnoseClusterResults"
metadata_type: "google.cloud.dataproc.v1.ClusterOperationMetadata"
};
}
}
// Describes the identifying information, config, and status of
// a Dataproc cluster
message Cluster {
// Required. The Google Cloud Platform project ID that the cluster belongs to.
string project_id = 1 [(google.api.field_behavior) = REQUIRED];
// Required. The cluster name, which must be unique within a project.
// The name must start with a lowercase letter, and can contain
// up to 51 lowercase letters, numbers, and hyphens. It cannot end
// with a hyphen. The name of a deleted cluster can be reused.
string cluster_name = 2 [(google.api.field_behavior) = REQUIRED];
// Optional. The cluster config for a cluster of Compute Engine Instances.
// Note that Dataproc may set default values, and values may change
// when clusters are updated.
//
// Exactly one of ClusterConfig or VirtualClusterConfig must be specified.
ClusterConfig config = 3 [(google.api.field_behavior) = OPTIONAL];
// Optional. The virtual cluster config is used when creating a Dataproc
// cluster that does not directly control the underlying compute resources,
// for example, when creating a [Dataproc-on-GKE
// cluster](https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke-overview).
// Dataproc may set default values, and values may change when
// clusters are updated. Exactly one of
// [config][google.cloud.dataproc.v1.Cluster.config] or
// [virtual_cluster_config][google.cloud.dataproc.v1.Cluster.virtual_cluster_config]
// must be specified.
VirtualClusterConfig virtual_cluster_config = 10
[(google.api.field_behavior) = OPTIONAL];
// Optional. The labels to associate with this cluster.
// Label **keys** must contain 1 to 63 characters, and must conform to
// [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt).
// Label **values** may be empty, but, if present, must contain 1 to 63
// characters, and must conform to [RFC
// 1035](https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be
// associated with a cluster.
map<string, string> labels = 8 [(google.api.field_behavior) = OPTIONAL];
// Output only. Cluster status.
ClusterStatus status = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. The previous cluster status.
repeated ClusterStatus status_history = 7
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. A cluster UUID (Unique Universal Identifier). Dataproc
// generates this value when it creates the cluster.
string cluster_uuid = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Contains cluster daemon metrics such as HDFS and YARN stats.
//
// **Beta Feature**: This report is available for testing purposes only. It
// may be changed before final release.
ClusterMetrics metrics = 9 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// The cluster config.
message ClusterConfig {
// Optional. A Cloud Storage bucket used to stage job
// dependencies, config files, and job driver console output.
// If you do not specify a staging bucket, Cloud
// Dataproc will determine a Cloud Storage location (US,
// ASIA, or EU) for your cluster's staging bucket according to the
// Compute Engine zone where your cluster is deployed, and then create
// and manage this project-level, per-location bucket (see
// [Dataproc staging and temp
// buckets](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
// **This field requires a Cloud Storage bucket name, not a `gs://...` URI to
// a Cloud Storage bucket.**
string config_bucket = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs
// data, such as Spark and MapReduce history files. If you do not specify a
// temp bucket, Dataproc will determine a Cloud Storage location (US, ASIA, or
// EU) for your cluster's temp bucket according to the Compute Engine zone
// where your cluster is deployed, and then create and manage this
// project-level, per-location bucket. The default bucket has a TTL of 90
// days, but you can use any TTL (or none) if you specify a bucket (see
// [Dataproc staging and temp
// buckets](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
// **This field requires a Cloud Storage bucket name, not a `gs://...` URI to
// a Cloud Storage bucket.**
string temp_bucket = 2 [(google.api.field_behavior) = OPTIONAL];
// Optional. The shared Compute Engine config settings for
// all instances in a cluster.
GceClusterConfig gce_cluster_config = 8
[(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine config settings for
// the cluster's master instance.
InstanceGroupConfig master_config = 9
[(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine config settings for
// the cluster's worker instances.
InstanceGroupConfig worker_config = 10
[(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine config settings for
// a cluster's secondary worker instances
InstanceGroupConfig secondary_worker_config = 12
[(google.api.field_behavior) = OPTIONAL];
// Optional. The config settings for cluster software.
SoftwareConfig software_config = 13 [(google.api.field_behavior) = OPTIONAL];
// Optional. Commands to execute on each node after config is
// completed. By default, executables are run on master and all worker nodes.
// You can test a node's `role` metadata to run an executable on
// a master or worker node, as shown below using `curl` (you can also use
// `wget`):
//
// ROLE=$(curl -H Metadata-Flavor:Google
// http://metadata/computeMetadata/v1/instance/attributes/dataproc-role)
// if [[ "${ROLE}" == 'Master' ]]; then
// ... master specific actions ...
// else
// ... worker specific actions ...
// fi
repeated NodeInitializationAction initialization_actions = 11
[(google.api.field_behavior) = OPTIONAL];
// Optional. Encryption settings for the cluster.
EncryptionConfig encryption_config = 15
[(google.api.field_behavior) = OPTIONAL];
// Optional. Autoscaling config for the policy associated with the cluster.
// Cluster does not autoscale if this field is unset.
AutoscalingConfig autoscaling_config = 18
[(google.api.field_behavior) = OPTIONAL];
// Optional. Security settings for the cluster.
SecurityConfig security_config = 16 [(google.api.field_behavior) = OPTIONAL];
// Optional. Lifecycle setting for the cluster.
LifecycleConfig lifecycle_config = 17
[(google.api.field_behavior) = OPTIONAL];
// Optional. Port/endpoint configuration for this cluster
EndpointConfig endpoint_config = 19 [(google.api.field_behavior) = OPTIONAL];
// Optional. Metastore configuration.
MetastoreConfig metastore_config = 20
[(google.api.field_behavior) = OPTIONAL];
// Optional. The config for Dataproc metrics.
DataprocMetricConfig dataproc_metric_config = 23
[(google.api.field_behavior) = OPTIONAL];
// Optional. The node group settings.
repeated AuxiliaryNodeGroup auxiliary_node_groups = 25
[(google.api.field_behavior) = OPTIONAL];
}
// The Dataproc cluster config for a cluster that does not directly control the
// underlying compute resources, such as a [Dataproc-on-GKE
// cluster](https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke-overview).
message VirtualClusterConfig {
// Optional. A Cloud Storage bucket used to stage job
// dependencies, config files, and job driver console output.
// If you do not specify a staging bucket, Cloud
// Dataproc will determine a Cloud Storage location (US,
// ASIA, or EU) for your cluster's staging bucket according to the
// Compute Engine zone where your cluster is deployed, and then create
// and manage this project-level, per-location bucket (see
// [Dataproc staging and temp
// buckets](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)).
// **This field requires a Cloud Storage bucket name, not a `gs://...` URI to
// a Cloud Storage bucket.**
string staging_bucket = 1 [(google.api.field_behavior) = OPTIONAL];
oneof infrastructure_config {
// Required. The configuration for running the Dataproc cluster on
// Kubernetes.
KubernetesClusterConfig kubernetes_cluster_config = 6
[(google.api.field_behavior) = REQUIRED];
}
// Optional. Configuration of auxiliary services used by this cluster.
AuxiliaryServicesConfig auxiliary_services_config = 7
[(google.api.field_behavior) = OPTIONAL];
}
// Auxiliary services configuration for a Cluster.
message AuxiliaryServicesConfig {
// Optional. The Hive Metastore configuration for this workload.
MetastoreConfig metastore_config = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Spark History Server configuration for the workload.
SparkHistoryServerConfig spark_history_server_config = 2
[(google.api.field_behavior) = OPTIONAL];
}
// Endpoint config for this cluster
message EndpointConfig {
// Output only. The map of port descriptions to URLs. Will only be populated
// if enable_http_port_access is true.
map<string, string> http_ports = 1
[(google.api.field_behavior) = OUTPUT_ONLY];
// Optional. If true, enable http access to specific ports on the cluster
// from external sources. Defaults to false.
bool enable_http_port_access = 2 [(google.api.field_behavior) = OPTIONAL];
}
// Autoscaling Policy config associated with the cluster.
message AutoscalingConfig {
// Optional. The autoscaling policy used by the cluster.
//
// Only resource names including projectid and location (region) are valid.
// Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]`
// * `projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]`
//
// Note that the policy must be in the same project and Dataproc region.
string policy_uri = 1 [(google.api.field_behavior) = OPTIONAL];
}
// Encryption settings for the cluster.
message EncryptionConfig {
// Optional. The Cloud KMS key name to use for PD disk encryption for all
// instances in the cluster.
string gce_pd_kms_key_name = 1 [(google.api.field_behavior) = OPTIONAL];
}
// Common config settings for resources of Compute Engine cluster
// instances, applicable to all instances in the cluster.
message GceClusterConfig {
// `PrivateIpv6GoogleAccess` controls whether and how Dataproc cluster nodes
// can communicate with Google Services through gRPC over IPv6.
// These values are directly mapped to corresponding values in the
// [Compute Engine Instance
// fields](https://cloud.google.com/compute/docs/reference/rest/v1/instances).
enum PrivateIpv6GoogleAccess {
// If unspecified, Compute Engine default behavior will apply, which
// is the same as
// [INHERIT_FROM_SUBNETWORK][google.cloud.dataproc.v1.GceClusterConfig.PrivateIpv6GoogleAccess.INHERIT_FROM_SUBNETWORK].
PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED = 0;
// Private access to and from Google Services configuration
// inherited from the subnetwork configuration. This is the
// default Compute Engine behavior.
INHERIT_FROM_SUBNETWORK = 1;
// Enables outbound private IPv6 access to Google Services from the Dataproc
// cluster.
OUTBOUND = 2;
// Enables bidirectional private IPv6 access between Google Services and the
// Dataproc cluster.
BIDIRECTIONAL = 3;
}
// Optional. The Compute Engine zone where the Dataproc cluster will be
// located. If omitted, the service will pick a zone in the cluster's Compute
// Engine region. On a get request, zone will always be present.
//
// A full URL, partial URI, or short name are valid. Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]`
// * `projects/[project_id]/zones/[zone]`
// * `[zone]`
string zone_uri = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine network to be used for machine
// communications. Cannot be specified with subnetwork_uri. If neither
// `network_uri` nor `subnetwork_uri` is specified, the "default" network of
// the project is used, if it exists. Cannot be a "Custom Subnet Network" (see
// [Using Subnetworks](https://cloud.google.com/compute/docs/subnetworks) for
// more information).
//
// A full URL, partial URI, or short name are valid. Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/networks/default`
// * `projects/[project_id]/global/networks/default`
// * `default`
string network_uri = 2 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine subnetwork to be used for machine
// communications. Cannot be specified with network_uri.
//
// A full URL, partial URI, or short name are valid. Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/[region]/subnetworks/sub0`
// * `projects/[project_id]/regions/[region]/subnetworks/sub0`
// * `sub0`
string subnetwork_uri = 6 [(google.api.field_behavior) = OPTIONAL];
// Optional. If true, all instances in the cluster will only have internal IP
// addresses. By default, clusters are not restricted to internal IP
// addresses, and will have ephemeral external IP addresses assigned to each
// instance. This `internal_ip_only` restriction can only be enabled for
// subnetwork enabled networks, and all off-cluster dependencies must be
// configured to be accessible without external IP addresses.
optional bool internal_ip_only = 7 [(google.api.field_behavior) = OPTIONAL];
// Optional. The type of IPv6 access for a cluster.
PrivateIpv6GoogleAccess private_ipv6_google_access = 12
[(google.api.field_behavior) = OPTIONAL];
// Optional. The [Dataproc service
// account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc)
// (also see [VM Data Plane
// identity](https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity))
// used by Dataproc cluster VM instances to access Google Cloud Platform
// services.
//
// If not specified, the
// [Compute Engine default service
// account](https://cloud.google.com/compute/docs/access/service-accounts#default_service_account)
// is used.
string service_account = 8 [(google.api.field_behavior) = OPTIONAL];
// Optional. The URIs of service account scopes to be included in
// Compute Engine instances. The following base set of scopes is always
// included:
//
// * https://www.googleapis.com/auth/cloud.useraccounts.readonly
// * https://www.googleapis.com/auth/devstorage.read_write
// * https://www.googleapis.com/auth/logging.write
//
// If no scopes are specified, the following defaults are also provided:
//
// * https://www.googleapis.com/auth/bigquery
// * https://www.googleapis.com/auth/bigtable.admin.table
// * https://www.googleapis.com/auth/bigtable.data
// * https://www.googleapis.com/auth/devstorage.full_control
repeated string service_account_scopes = 3
[(google.api.field_behavior) = OPTIONAL];
// The Compute Engine tags to add to all instances (see [Tagging
// instances](https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).
repeated string tags = 4;
// Optional. The Compute Engine metadata entries to add to all instances (see
// [Project and instance
// metadata](https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).
map<string, string> metadata = 5 [(google.api.field_behavior) = OPTIONAL];
// Optional. Reservation Affinity for consuming Zonal reservation.
ReservationAffinity reservation_affinity = 11
[(google.api.field_behavior) = OPTIONAL];
// Optional. Node Group Affinity for sole-tenant clusters.
NodeGroupAffinity node_group_affinity = 13
[(google.api.field_behavior) = OPTIONAL];
// Optional. Shielded Instance Config for clusters using [Compute Engine
// Shielded
// VMs](https://cloud.google.com/security/shielded-cloud/shielded-vm).
ShieldedInstanceConfig shielded_instance_config = 14
[(google.api.field_behavior) = OPTIONAL];
// Optional. Confidential Instance Config for clusters using [Confidential
// VMs](https://cloud.google.com/compute/confidential-vm/docs).
ConfidentialInstanceConfig confidential_instance_config = 15
[(google.api.field_behavior) = OPTIONAL];
}
// Node Group Affinity for clusters using sole-tenant node groups.
// **The Dataproc `NodeGroupAffinity` resource is not related to the
// Dataproc [NodeGroup][google.cloud.dataproc.v1.NodeGroup] resource.**
message NodeGroupAffinity {
// Required. The URI of a
// sole-tenant [node group
// resource](https://cloud.google.com/compute/docs/reference/rest/v1/nodeGroups)
// that the cluster will be created on.
//
// A full URL, partial URI, or node group name are valid. Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/nodeGroups/node-group-1`
// * `projects/[project_id]/zones/[zone]/nodeGroups/node-group-1`
// * `node-group-1`
string node_group_uri = 1 [(google.api.field_behavior) = REQUIRED];
}
// Shielded Instance Config for clusters using [Compute Engine Shielded
// VMs](https://cloud.google.com/security/shielded-cloud/shielded-vm).
message ShieldedInstanceConfig {
// Optional. Defines whether instances have Secure Boot enabled.
optional bool enable_secure_boot = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. Defines whether instances have the vTPM enabled.
optional bool enable_vtpm = 2 [(google.api.field_behavior) = OPTIONAL];
// Optional. Defines whether instances have integrity monitoring enabled.
optional bool enable_integrity_monitoring = 3
[(google.api.field_behavior) = OPTIONAL];
}
// Confidential Instance Config for clusters using [Confidential
// VMs](https://cloud.google.com/compute/confidential-vm/docs)
message ConfidentialInstanceConfig {
// Optional. Defines whether the instance should have confidential compute
// enabled.
bool enable_confidential_compute = 1 [(google.api.field_behavior) = OPTIONAL];
}
// The config settings for Compute Engine resources in
// an instance group, such as a master or worker group.
message InstanceGroupConfig {
// Controls the use of preemptible instances within the group.
enum Preemptibility {
// Preemptibility is unspecified, the system will choose the
// appropriate setting for each instance group.
PREEMPTIBILITY_UNSPECIFIED = 0;
// Instances are non-preemptible.
//
// This option is allowed for all instance groups and is the only valid
// value for Master and Worker instance groups.
NON_PREEMPTIBLE = 1;
// Instances are [preemptible]
// (https://cloud.google.com/compute/docs/instances/preemptible).
//
// This option is allowed only for [secondary worker]
// (https://cloud.google.com/dataproc/docs/concepts/compute/secondary-vms)
// groups.
PREEMPTIBLE = 2;
// Instances are [Spot VMs]
// (https://cloud.google.com/compute/docs/instances/spot).
//
// This option is allowed only for [secondary worker]
// (https://cloud.google.com/dataproc/docs/concepts/compute/secondary-vms)
// groups. Spot VMs are the latest version of [preemptible VMs]
// (https://cloud.google.com/compute/docs/instances/preemptible), and
// provide additional features.
SPOT = 3;
}
// Optional. The number of VM instances in the instance group.
// For [HA
// cluster](/dataproc/docs/concepts/configuring-clusters/high-availability)
// [master_config](#FIELDS.master_config) groups, **must be set to 3**.
// For standard cluster [master_config](#FIELDS.master_config) groups,
// **must be set to 1**.
int32 num_instances = 1 [(google.api.field_behavior) = OPTIONAL];
// Output only. The list of instance names. Dataproc derives the names
// from `cluster_name`, `num_instances`, and the instance group.
repeated string instance_names = 2
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. List of references to Compute Engine instances.
repeated InstanceReference instance_references = 11
[(google.api.field_behavior) = OUTPUT_ONLY];
// Optional. The Compute Engine image resource used for cluster instances.
//
// The URI can represent an image or image family.
//
// Image examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/[image-id]`
// * `projects/[project_id]/global/images/[image-id]`
// * `image-id`
//
// Image family examples. Dataproc will use the most recent
// image from the family:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/family/[custom-image-family-name]`
// * `projects/[project_id]/global/images/family/[custom-image-family-name]`
//
// If the URI is unspecified, it will be inferred from
// `SoftwareConfig.image_version` or the system default.
string image_uri = 3 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Compute Engine machine type used for cluster instances.
//
// A full URL, partial URI, or short name are valid. Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2`
// * `projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2`
// * `n1-standard-2`
//
// **Auto Zone Exception**: If you are using the Dataproc
// [Auto Zone
// Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement)
// feature, you must use the short name of the machine type
// resource, for example, `n1-standard-2`.
string machine_type_uri = 4 [(google.api.field_behavior) = OPTIONAL];
// Optional. Disk option config settings.
DiskConfig disk_config = 5 [(google.api.field_behavior) = OPTIONAL];
// Output only. Specifies that this instance group contains preemptible
// instances.
bool is_preemptible = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
// Optional. Specifies the preemptibility of the instance group.
//
// The default value for master and worker groups is
// `NON_PREEMPTIBLE`. This default cannot be changed.
//
// The default value for secondary instances is
// `PREEMPTIBLE`.
Preemptibility preemptibility = 10 [(google.api.field_behavior) = OPTIONAL];
// Output only. The config for Compute Engine Instance Group
// Manager that manages this group.
// This is only used for preemptible instance groups.
ManagedGroupConfig managed_group_config = 7
[(google.api.field_behavior) = OUTPUT_ONLY];
// Optional. The Compute Engine accelerator configuration for these
// instances.
repeated AcceleratorConfig accelerators = 8
[(google.api.field_behavior) = OPTIONAL];
// Optional. Specifies the minimum cpu platform for the Instance Group.
// See [Dataproc -> Minimum CPU
// Platform](https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu).
string min_cpu_platform = 9 [(google.api.field_behavior) = OPTIONAL];
// Optional. The minimum number of primary worker instances to create.
// If `min_num_instances` is set, cluster creation will succeed if
// the number of primary workers created is at least equal to the
// `min_num_instances` number.
//
// Example: Cluster creation request with `num_instances` = `5` and
// `min_num_instances` = `3`:
//
// * If 4 VMs are created and 1 instance fails,
// the failed VM is deleted. The cluster is
// resized to 4 instances and placed in a `RUNNING` state.
// * If 2 instances are created and 3 instances fail,
// the cluster in placed in an `ERROR` state. The failed VMs
// are not deleted.
int32 min_num_instances = 12 [(google.api.field_behavior) = OPTIONAL];
// Optional. Instance flexibility Policy allowing a mixture of VM shapes and
// provisioning models.
InstanceFlexibilityPolicy instance_flexibility_policy = 13
[(google.api.field_behavior) = OPTIONAL];
}
// A reference to a Compute Engine instance.
message InstanceReference {
// The user-friendly name of the Compute Engine instance.
string instance_name = 1;
// The unique identifier of the Compute Engine instance.
string instance_id = 2;
// The public RSA key used for sharing data with this instance.
string public_key = 3;
// The public ECIES key used for sharing data with this instance.
string public_ecies_key = 4;
}
// Specifies the resources used to actively manage an instance group.
message ManagedGroupConfig {
// Output only. The name of the Instance Template used for the Managed
// Instance Group.
string instance_template_name = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. The name of the Instance Group Manager for this group.
string instance_group_manager_name = 2
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. The partial URI to the instance group manager for this group.
// E.g. projects/my-project/regions/us-central1/instanceGroupManagers/my-igm.
string instance_group_manager_uri = 3
[(google.api.field_behavior) = OUTPUT_ONLY];
}
// Instance flexibility Policy allowing a mixture of VM shapes and provisioning
// models.
message InstanceFlexibilityPolicy {
// Defines machines types and a rank to which the machines types belong.
message InstanceSelection {
// Optional. Full machine-type names, e.g. "n1-standard-16".
repeated string machine_types = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. Preference of this instance selection. Lower number means
// higher preference. Dataproc will first try to create a VM based on the
// machine-type with priority rank and fallback to next rank based on
// availability. Machine types and instance selections with the same
// priority have the same preference.
int32 rank = 2 [(google.api.field_behavior) = OPTIONAL];
}
// Defines a mapping from machine types to the number of VMs that are created
// with each machine type.
message InstanceSelectionResult {
// Output only. Full machine-type names, e.g. "n1-standard-16".
optional string machine_type = 1
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Number of VM provisioned with the machine_type.
optional int32 vm_count = 2 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Optional. List of instance selection options that the group will use when
// creating new VMs.
repeated InstanceSelection instance_selection_list = 2
[(google.api.field_behavior) = OPTIONAL];
// Output only. A list of instance selection results in the group.
repeated InstanceSelectionResult instance_selection_results = 3
[(google.api.field_behavior) = OUTPUT_ONLY];
}
// Specifies the type and number of accelerator cards attached to the instances
// of an instance. See [GPUs on Compute
// Engine](https://cloud.google.com/compute/docs/gpus/).
message AcceleratorConfig {
// Full URL, partial URI, or short name of the accelerator type resource to
// expose to this instance. See
// [Compute Engine
// AcceleratorTypes](https://cloud.google.com/compute/docs/reference/v1/acceleratorTypes).
//
// Examples:
//
// * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-k80`
// * `projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-k80`
// * `nvidia-tesla-k80`
//
// **Auto Zone Exception**: If you are using the Dataproc
// [Auto Zone
// Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement)
// feature, you must use the short name of the accelerator type
// resource, for example, `nvidia-tesla-k80`.
string accelerator_type_uri = 1;
// The number of the accelerator cards of this type exposed to this instance.
int32 accelerator_count = 2;
}
// Specifies the config of disk options for a group of VM instances.
message DiskConfig {
// Optional. Type of the boot disk (default is "pd-standard").
// Valid values: "pd-balanced" (Persistent Disk Balanced Solid State Drive),
// "pd-ssd" (Persistent Disk Solid State Drive),
// or "pd-standard" (Persistent Disk Hard Disk Drive).
// See [Disk types](https://cloud.google.com/compute/docs/disks#disk-types).
string boot_disk_type = 3 [(google.api.field_behavior) = OPTIONAL];
// Optional. Size in GB of the boot disk (default is 500GB).
int32 boot_disk_size_gb = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. Number of attached SSDs, from 0 to 8 (default is 0).
// If SSDs are not attached, the boot disk is used to store runtime logs and
// [HDFS](https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data.
// If one or more SSDs are attached, this runtime bulk
// data is spread across them, and the boot disk contains only basic
// config and installed binaries.
//
// Note: Local SSD options may vary by machine type and number of vCPUs
// selected.
int32 num_local_ssds = 2 [(google.api.field_behavior) = OPTIONAL];
// Optional. Interface type of local SSDs (default is "scsi").
// Valid values: "scsi" (Small Computer System Interface),
// "nvme" (Non-Volatile Memory Express).
// See [local SSD
// performance](https://cloud.google.com/compute/docs/disks/local-ssd#performance).
string local_ssd_interface = 4 [(google.api.field_behavior) = OPTIONAL];
}
// Node group identification and configuration information.
message AuxiliaryNodeGroup {
// Required. Node group configuration.
NodeGroup node_group = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. A node group ID. Generated if not specified.
//
// The ID must contain only letters (a-z, A-Z), numbers (0-9),
// underscores (_), and hyphens (-). Cannot begin or end with underscore
// or hyphen. Must consist of from 3 to 33 characters.
string node_group_id = 2 [(google.api.field_behavior) = OPTIONAL];
}
// Dataproc Node Group.
// **The Dataproc `NodeGroup` resource is not related to the
// Dataproc [NodeGroupAffinity][google.cloud.dataproc.v1.NodeGroupAffinity]
// resource.**
message NodeGroup {
option (google.api.resource) = {
type: "dataproc.googleapis.com/NodeGroup"
pattern: "projects/{project}/regions/{region}/clusters/{cluster}/nodeGroups/{node_group}"
};
// Node pool roles.
enum Role {
// Required unspecified role.
ROLE_UNSPECIFIED = 0;
// Job drivers run on the node pool.
DRIVER = 1;
}
// The Node group [resource name](https://aip.dev/122).
string name = 1;
// Required. Node group roles.
repeated Role roles = 2 [(google.api.field_behavior) = REQUIRED];
// Optional. The node group instance group configuration.
InstanceGroupConfig node_group_config = 3
[(google.api.field_behavior) = OPTIONAL];
// Optional. Node group labels.
//
// * Label **keys** must consist of from 1 to 63 characters and conform to
// [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt).
// * Label **values** can be empty. If specified, they must consist of from
// 1 to 63 characters and conform to [RFC 1035]
// (https://www.ietf.org/rfc/rfc1035.txt).
// * The node group must have no more than 32 labels.
map<string, string> labels = 4 [(google.api.field_behavior) = OPTIONAL];
}
// Specifies an executable to run on a fully configured node and a
// timeout period for executable completion.
message NodeInitializationAction {
// Required. Cloud Storage URI of executable file.
string executable_file = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. Amount of time executable has to complete. Default is
// 10 minutes (see JSON representation of
// [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).
//
// Cluster creation fails with an explanatory error message (the
// name of the executable that caused the error and the exceeded timeout
// period) if the executable is not completed at end of the timeout period.
google.protobuf.Duration execution_timeout = 2
[(google.api.field_behavior) = OPTIONAL];
}
// The status of a cluster and its instances.
message ClusterStatus {
// The cluster state.
enum State {
// The cluster state is unknown.
UNKNOWN = 0;
// The cluster is being created and set up. It is not ready for use.
CREATING = 1;
// The cluster is currently running and healthy. It is ready for use.
//
// **Note:** The cluster state changes from "creating" to "running" status
// after the master node(s), first two primary worker nodes (and the last
// primary worker node if primary workers > 2) are running.
RUNNING = 2;
// The cluster encountered an error. It is not ready for use.
ERROR = 3;
// The cluster has encountered an error while being updated. Jobs can
// be submitted to the cluster, but the cluster cannot be updated.
ERROR_DUE_TO_UPDATE = 9;
// The cluster is being deleted. It cannot be used.
DELETING = 4;
// The cluster is being updated. It continues to accept and process jobs.
UPDATING = 5;
// The cluster is being stopped. It cannot be used.
STOPPING = 6;
// The cluster is currently stopped. It is not ready for use.
STOPPED = 7;
// The cluster is being started. It is not ready for use.
STARTING = 8;
// The cluster is being repaired. It is not ready for use.
REPAIRING = 10;
}
// The cluster substate.
enum Substate {
// The cluster substate is unknown.
UNSPECIFIED = 0;
// The cluster is known to be in an unhealthy state
// (for example, critical daemons are not running or HDFS capacity is
// exhausted).
//
// Applies to RUNNING state.
UNHEALTHY = 1;
// The agent-reported status is out of date (may occur if
// Dataproc loses communication with Agent).
//
// Applies to RUNNING state.
STALE_STATUS = 2;
}
// Output only. The cluster's state.
State state = 1 [(google.api.field_behavior) = OUTPUT_ONLY];
// Optional. Output only. Details of cluster's state.
string detail = 2 [
(google.api.field_behavior) = OUTPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
];
// Output only. Time when this state was entered (see JSON representation of
// [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).
google.protobuf.Timestamp state_start_time = 3
[(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. Additional state information that includes
// status reported by the agent.
Substate substate = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Security related configuration, including encryption, Kerberos, etc.
message SecurityConfig {
// Optional. Kerberos related configuration.
KerberosConfig kerberos_config = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. Identity related configuration, including service account based
// secure multi-tenancy user mappings.
IdentityConfig identity_config = 2 [(google.api.field_behavior) = OPTIONAL];
}
// Specifies Kerberos related configuration.
message KerberosConfig {
// Optional. Flag to indicate whether to Kerberize the cluster (default:
// false). Set this field to true to enable Kerberos on a cluster.
bool enable_kerberos = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Cloud Storage URI of a KMS encrypted file containing the root
// principal password.
string root_principal_password_uri = 2
[(google.api.field_behavior) = OPTIONAL];
// Optional. The uri of the KMS key used to encrypt various sensitive
// files.
string kms_key_uri = 3 [(google.api.field_behavior) = OPTIONAL];
// Optional. The Cloud Storage URI of the keystore file used for SSL
// encryption. If not provided, Dataproc will provide a self-signed