-
Notifications
You must be signed in to change notification settings - Fork 216
Expand file tree
/
Copy pathbundle_descriptions.json
More file actions
4879 lines (4879 loc) · 343 KB
/
Copy pathbundle_descriptions.json
File metadata and controls
4879 lines (4879 loc) · 343 KB
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
{
"description": "Root of the bundle config",
"properties": {
"artifacts": {
"description": "A description of all code artifacts in this bundle.",
"additionalproperties": {
"description": "",
"properties": {
"build": {
"description": ""
},
"files": {
"description": "",
"items": {
"description": "",
"properties": {
"source": {
"description": ""
}
}
}
},
"path": {
"description": ""
},
"type": {
"description": ""
}
}
}
},
"bundle": {
"description": "The details for this bundle.",
"properties": {
"compute_id": {
"description": ""
},
"git": {
"description": "",
"properties": {
"branch": {
"description": ""
},
"origin_url": {
"description": ""
}
}
},
"name": {
"description": "The name of the bundle."
}
}
},
"experimental": {
"description": "",
"properties": {
"python_wheel_wrapper": {
"description": ""
},
"scripts": {
"description": "",
"additionalproperties": {
"description": ""
}
}
}
},
"include": {
"description": "A list of glob patterns of files to load and merge into the this configuration. Defaults to no files being included.",
"items": {
"description": ""
}
},
"permissions": {
"description": "",
"items": {
"description": "",
"properties": {
"group_name": {
"description": ""
},
"level": {
"description": ""
},
"service_principal_name": {
"description": ""
},
"user_name": {
"description": ""
}
}
}
},
"resources": {
"description": "Collection of Databricks resources to deploy.",
"properties": {
"experiments": {
"description": "List of MLflow experiments",
"additionalproperties": {
"description": "",
"properties": {
"artifact_location": {
"description": "Location where artifacts for the experiment are stored."
},
"creation_time": {
"description": "Creation time"
},
"experiment_id": {
"description": "Unique identifier for the experiment."
},
"last_update_time": {
"description": "Last update time"
},
"lifecycle_stage": {
"description": "Current life cycle stage of the experiment: \"active\" or \"deleted\".\nDeleted experiments are not returned by APIs."
},
"name": {
"description": "Human readable name that identifies the experiment."
},
"permissions": {
"description": "",
"items": {
"description": "",
"properties": {
"group_name": {
"description": ""
},
"level": {
"description": ""
},
"service_principal_name": {
"description": ""
},
"user_name": {
"description": ""
}
}
}
},
"tags": {
"description": "Tags: Additional metadata key-value pairs.",
"items": {
"description": "",
"properties": {
"key": {
"description": "The tag key."
},
"value": {
"description": "The tag value."
}
}
}
}
}
}
},
"jobs": {
"description": "List of Databricks jobs",
"additionalproperties": {
"description": "",
"properties": {
"compute": {
"description": "A list of compute requirements that can be referenced by tasks of this job.",
"items": {
"description": "",
"properties": {
"compute_key": {
"description": "A unique name for the compute requirement. This field is required and must be unique within the job.\n`JobTaskSettings` may refer to this field to determine the compute requirements for the task execution."
},
"spec": {
"description": "",
"properties": {
"kind": {
"description": "The kind of compute described by this compute specification."
}
}
}
}
}
},
"continuous": {
"description": "An optional continuous property for this job. The continuous property will ensure that there is always one run executing. Only one of `schedule` and `continuous` can be used.",
"properties": {
"pause_status": {
"description": "Indicate whether the continuous execution of the job is paused or not. Defaults to UNPAUSED."
}
}
},
"deployment": {
"description": "Deployment information for jobs managed by external sources.",
"properties": {
"kind": {
"description": "The kind of deployment that manages the job.\n\n* `BUNDLE`: The job is managed by Databricks Asset Bundle.\n"
},
"metadata_file_path": {
"description": "Path of the file that contains deployment metadata."
}
}
},
"description": {
"description": "An optional description for the job. The maximum length is 1024 characters in UTF-8 encoding."
},
"edit_mode": {
"description": "Edit mode of the job.\n\n* `UI_LOCKED`: The job is in a locked UI state and cannot be modified.\n* `EDITABLE`: The job is in an editable state and can be modified.\n"
},
"email_notifications": {
"description": "An optional set of email addresses that is notified when runs of this job begin or complete as well as when this job is deleted.",
"properties": {
"no_alert_for_skipped_runs": {
"description": "If true, do not send email to recipients specified in `on_failure` if the run is skipped."
},
"on_duration_warning_threshold_exceeded": {
"description": "A list of email addresses to be notified when the duration of a run exceeds the threshold specified for the `RUN_DURATION_SECONDS` metric in the `health` field. If no rule for the `RUN_DURATION_SECONDS` metric is specified in the `health` field for the job, notifications are not sent.",
"items": {
"description": ""
}
},
"on_failure": {
"description": "A list of email addresses to be notified when a run unsuccessfully completes. A run is considered to have completed unsuccessfully if it ends with an `INTERNAL_ERROR` `life_cycle_state` or a `FAILED`, or `TIMED_OUT` result_state. If this is not specified on job creation, reset, or update the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
},
"on_start": {
"description": "A list of email addresses to be notified when a run begins. If not specified on job creation, reset, or update, the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
},
"on_success": {
"description": "A list of email addresses to be notified when a run successfully completes. A run is considered to have completed successfully if it ends with a `TERMINATED` `life_cycle_state` and a `SUCCESS` result_state. If not specified on job creation, reset, or update, the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
}
}
},
"format": {
"description": "Used to tell what is the format of the job. This field is ignored in Create/Update/Reset calls. When using the Jobs API 2.1 this value is always set to `\"MULTI_TASK\"`."
},
"git_source": {
"description": "An optional specification for a remote Git repository containing the source code used by tasks. Version-controlled source code is supported by notebook, dbt, Python script, and SQL File tasks.\n\nIf `git_source` is set, these tasks retrieve the file from the remote repository by default. However, this behavior can be overridden by setting `source` to `WORKSPACE` on the task.\n\nNote: dbt and SQL File tasks support only version-controlled sources. If dbt or SQL File tasks are used, `git_source` must be defined on the job.",
"properties": {
"git_branch": {
"description": "Name of the branch to be checked out and used by this job. This field cannot be specified in conjunction with git_tag or git_commit."
},
"git_commit": {
"description": "Commit to be checked out and used by this job. This field cannot be specified in conjunction with git_branch or git_tag."
},
"git_provider": {
"description": "Unique identifier of the service used to host the Git repository. The value is case insensitive."
},
"git_snapshot": {
"description": "",
"properties": {
"used_commit": {
"description": "Commit that was used to execute the run. If git_branch was specified, this points to the HEAD of the branch at the time of the run; if git_tag was specified, this points to the commit the tag points to."
}
}
},
"git_tag": {
"description": "Name of the tag to be checked out and used by this job. This field cannot be specified in conjunction with git_branch or git_commit."
},
"git_url": {
"description": "URL of the repository to be cloned by this job."
},
"job_source": {
"description": "The source of the job specification in the remote repository when the job is source controlled.",
"properties": {
"dirty_state": {
"description": "Dirty state indicates the job is not fully synced with the job specification in the remote repository.\n\nPossible values are:\n* `NOT_SYNCED`: The job is not yet synced with the remote job specification. Import the remote job specification from UI to make the job fully synced.\n* `DISCONNECTED`: The job is temporary disconnected from the remote job specification and is allowed for live edit. Import the remote job specification again from UI to make the job fully synced.\n"
},
"import_from_git_branch": {
"description": "Name of the branch which the job is imported from."
},
"job_config_path": {
"description": "Path of the job YAML file that contains the job specification."
}
}
}
}
},
"health": {
"description": "",
"properties": {
"rules": {
"description": "",
"items": {
"description": "",
"properties": {
"metric": {
"description": ""
},
"op": {
"description": ""
},
"value": {
"description": "Specifies the threshold value that the health metric should obey to satisfy the health rule."
}
}
}
}
}
},
"job_clusters": {
"description": "A list of job cluster specifications that can be shared and reused by tasks of this job. Libraries cannot be declared in a shared job cluster. You must declare dependent libraries in task settings.",
"items": {
"description": "",
"properties": {
"job_cluster_key": {
"description": "A unique name for the job cluster. This field is required and must be unique within the job.\n`JobTaskSettings` may refer to this field to determine which cluster to launch for the task execution."
},
"new_cluster": {
"description": "If new_cluster, a description of a cluster that is created for only for this task.",
"properties": {
"apply_policy_default_values": {
"description": ""
},
"autoscale": {
"description": "Parameters needed in order to automatically scale clusters up and down based on load.\nNote: autoscaling works best with DB runtime versions 3.0 or later.",
"properties": {
"max_workers": {
"description": "The maximum number of workers to which the cluster can scale up when overloaded.\nNote that `max_workers` must be strictly greater than `min_workers`."
},
"min_workers": {
"description": "The minimum number of workers to which the cluster can scale down when underutilized.\nIt is also the initial number of workers the cluster will have after creation."
}
}
},
"autotermination_minutes": {
"description": "Automatically terminates the cluster after it is inactive for this time in minutes. If not set,\nthis cluster will not be automatically terminated. If specified, the threshold must be between\n10 and 10000 minutes.\nUsers can also set this value to 0 to explicitly disable automatic termination."
},
"aws_attributes": {
"description": "Attributes related to clusters running on Amazon Web Services.\nIf not specified at cluster creation, a set of default values will be used.",
"properties": {
"availability": {
"description": ""
},
"ebs_volume_count": {
"description": "The number of volumes launched for each instance. Users can choose up to 10 volumes.\nThis feature is only enabled for supported node types. Legacy node types cannot specify\ncustom EBS volumes.\nFor node types with no instance store, at least one EBS volume needs to be specified;\notherwise, cluster creation will fail.\n\nThese EBS volumes will be mounted at `/ebs0`, `/ebs1`, and etc.\nInstance store volumes will be mounted at `/local_disk0`, `/local_disk1`, and etc.\n\nIf EBS volumes are attached, Databricks will configure Spark to use only the EBS volumes for\nscratch storage because heterogenously sized scratch devices can lead to inefficient disk\nutilization. If no EBS volumes are attached, Databricks will configure Spark to use instance\nstore volumes.\n\nPlease note that if EBS volumes are specified, then the Spark configuration `spark.local.dir`\nwill be overridden."
},
"ebs_volume_iops": {
"description": "\u003cneeds content added\u003e"
},
"ebs_volume_size": {
"description": "The size of each EBS volume (in GiB) launched for each instance. For general purpose\nSSD, this value must be within the range 100 - 4096. For throughput optimized HDD,\nthis value must be within the range 500 - 4096."
},
"ebs_volume_throughput": {
"description": "\u003cneeds content added\u003e"
},
"ebs_volume_type": {
"description": ""
},
"first_on_demand": {
"description": "The first `first_on_demand` nodes of the cluster will be placed on on-demand instances.\nIf this value is greater than 0, the cluster driver node in particular will be placed on an\non-demand instance. If this value is greater than or equal to the current cluster size, all\nnodes will be placed on on-demand instances. If this value is less than the current cluster\nsize, `first_on_demand` nodes will be placed on on-demand instances and the remainder will\nbe placed on `availability` instances. Note that this value does not affect\ncluster size and cannot currently be mutated over the lifetime of a cluster."
},
"instance_profile_arn": {
"description": "Nodes for this cluster will only be placed on AWS instances with this instance profile. If\nommitted, nodes will be placed on instances without an IAM instance profile. The instance\nprofile must have previously been added to the Databricks environment by an account\nadministrator.\n\nThis feature may only be available to certain customer plans.\n\nIf this field is ommitted, we will pull in the default from the conf if it exists."
},
"spot_bid_price_percent": {
"description": "The bid price for AWS spot instances, as a percentage of the corresponding instance type's\non-demand price.\nFor example, if this field is set to 50, and the cluster needs a new `r3.xlarge` spot\ninstance, then the bid price is half of the price of\non-demand `r3.xlarge` instances. Similarly, if this field is set to 200, the bid price is twice\nthe price of on-demand `r3.xlarge` instances. If not specified, the default value is 100.\nWhen spot instances are requested for this cluster, only spot instances whose bid price\npercentage matches this field will be considered.\nNote that, for safety, we enforce this field to be no more than 10000.\n\nThe default value and documentation here should be kept consistent with\nCommonConf.defaultSpotBidPricePercent and CommonConf.maxSpotBidPricePercent."
},
"zone_id": {
"description": "Identifier for the availability zone/datacenter in which the cluster resides.\nThis string will be of a form like \"us-west-2a\". The provided availability\nzone must be in the same region as the Databricks deployment. For example, \"us-west-2a\"\nis not a valid zone id if the Databricks deployment resides in the \"us-east-1\" region.\nThis is an optional field at cluster creation, and if not specified, a default zone will be used.\nIf the zone specified is \"auto\", will try to place cluster in a zone with high availability,\nand will retry placement in a different AZ if there is not enough capacity.\nThe list of available zones as well as the default value can be found by using the\n`List Zones` method."
}
}
},
"azure_attributes": {
"description": "Attributes related to clusters running on Microsoft Azure.\nIf not specified at cluster creation, a set of default values will be used.",
"properties": {
"availability": {
"description": ""
},
"first_on_demand": {
"description": "The first `first_on_demand` nodes of the cluster will be placed on on-demand instances.\nThis value should be greater than 0, to make sure the cluster driver node is placed on an\non-demand instance. If this value is greater than or equal to the current cluster size, all\nnodes will be placed on on-demand instances. If this value is less than the current cluster\nsize, `first_on_demand` nodes will be placed on on-demand instances and the remainder will\nbe placed on `availability` instances. Note that this value does not affect\ncluster size and cannot currently be mutated over the lifetime of a cluster."
},
"log_analytics_info": {
"description": "Defines values necessary to configure and run Azure Log Analytics agent",
"properties": {
"log_analytics_primary_key": {
"description": "\u003cneeds content added\u003e"
},
"log_analytics_workspace_id": {
"description": "\u003cneeds content added\u003e"
}
}
},
"spot_bid_max_price": {
"description": "The max bid price to be used for Azure spot instances.\nThe Max price for the bid cannot be higher than the on-demand price of the instance.\nIf not specified, the default value is -1, which specifies that the instance cannot be evicted\non the basis of price, and only on the basis of availability. Further, the value should \u003e 0 or -1."
}
}
},
"cluster_log_conf": {
"description": "The configuration for delivering spark logs to a long-term storage destination.\nTwo kinds of destinations (dbfs and s3) are supported. Only one destination can be specified\nfor one cluster. If the conf is given, the logs will be delivered to the destination every\n`5 mins`. The destination of driver logs is `$destination/$clusterId/driver`, while\nthe destination of executor logs is `$destination/$clusterId/executor`.",
"properties": {
"dbfs": {
"description": "destination needs to be provided. e.g.\n`{ \"dbfs\" : { \"destination\" : \"dbfs:/home/cluster_log\" } }`",
"properties": {
"destination": {
"description": "dbfs destination, e.g. `dbfs:/my/path`"
}
}
},
"s3": {
"description": "destination and either the region or endpoint need to be provided. e.g.\n`{ \"s3\": { \"destination\" : \"s3://cluster_log_bucket/prefix\", \"region\" : \"us-west-2\" } }`\nCluster iam role is used to access s3, please make sure the cluster iam role in\n`instance_profile_arn` has permission to write data to the s3 destination.",
"properties": {
"canned_acl": {
"description": "(Optional) Set canned access control list for the logs, e.g. `bucket-owner-full-control`.\nIf `canned_cal` is set, please make sure the cluster iam role has `s3:PutObjectAcl` permission on\nthe destination bucket and prefix. The full list of possible canned acl can be found at\nhttp://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl.\nPlease also note that by default only the object owner gets full controls. If you are using cross account\nrole for writing data, you may want to set `bucket-owner-full-control` to make bucket owner able to\nread the logs."
},
"destination": {
"description": "S3 destination, e.g. `s3://my-bucket/some-prefix` Note that logs will be delivered using\ncluster iam role, please make sure you set cluster iam role and the role has write access to the\ndestination. Please also note that you cannot use AWS keys to deliver logs."
},
"enable_encryption": {
"description": "(Optional) Flag to enable server side encryption, `false` by default."
},
"encryption_type": {
"description": "(Optional) The encryption type, it could be `sse-s3` or `sse-kms`. It will be used only when\nencryption is enabled and the default type is `sse-s3`."
},
"endpoint": {
"description": "S3 endpoint, e.g. `https://s3-us-west-2.amazonaws.com`. Either region or endpoint needs to be set.\nIf both are set, endpoint will be used."
},
"kms_key": {
"description": "(Optional) Kms key which will be used if encryption is enabled and encryption type is set to `sse-kms`."
},
"region": {
"description": "S3 region, e.g. `us-west-2`. Either region or endpoint needs to be set. If both are set,\nendpoint will be used."
}
}
}
}
},
"cluster_name": {
"description": "Cluster name requested by the user. This doesn't have to be unique.\nIf not specified at creation, the cluster name will be an empty string.\n"
},
"cluster_source": {
"description": ""
},
"custom_tags": {
"description": "Additional tags for cluster resources. Databricks will tag all cluster resources (e.g., AWS\ninstances and EBS volumes) with these tags in addition to `default_tags`. Notes:\n\n- Currently, Databricks allows at most 45 custom tags\n\n- Clusters can only reuse cloud resources if the resources' tags are a subset of the cluster tags",
"additionalproperties": {
"description": ""
}
},
"data_security_mode": {
"description": ""
},
"docker_image": {
"description": "",
"properties": {
"basic_auth": {
"description": "",
"properties": {
"password": {
"description": "Password of the user"
},
"username": {
"description": "Name of the user"
}
}
},
"url": {
"description": "URL of the docker image."
}
}
},
"driver_instance_pool_id": {
"description": "The optional ID of the instance pool for the driver of the cluster belongs.\nThe pool cluster uses the instance pool with id (instance_pool_id) if the driver pool is not\nassigned."
},
"driver_node_type_id": {
"description": "The node type of the Spark driver. Note that this field is optional;\nif unset, the driver node type will be set as the same value\nas `node_type_id` defined above.\n"
},
"enable_elastic_disk": {
"description": "Autoscaling Local Storage: when enabled, this cluster will dynamically acquire additional disk\nspace when its Spark workers are running low on disk space. This feature requires specific AWS\npermissions to function correctly - refer to the User Guide for more details."
},
"enable_local_disk_encryption": {
"description": "Whether to enable LUKS on cluster VMs' local disks"
},
"gcp_attributes": {
"description": "Attributes related to clusters running on Google Cloud Platform.\nIf not specified at cluster creation, a set of default values will be used.",
"properties": {
"availability": {
"description": ""
},
"boot_disk_size": {
"description": "boot disk size in GB"
},
"google_service_account": {
"description": "If provided, the cluster will impersonate the google service account when accessing\ngcloud services (like GCS). The google service account\nmust have previously been added to the Databricks environment by an account\nadministrator."
},
"local_ssd_count": {
"description": "If provided, each node (workers and driver) in the cluster will have this number of local SSDs attached. Each local SSD is 375GB in size. Refer to [GCP documentation](https://cloud.google.com/compute/docs/disks/local-ssd#choose_number_local_ssds) for the supported number of local SSDs for each instance type."
}
}
},
"init_scripts": {
"description": "The configuration for storing init scripts. Any number of destinations can be specified. The scripts are executed sequentially in the order provided. If `cluster_log_conf` is specified, init script logs are sent to `\u003cdestination\u003e/\u003ccluster-ID\u003e/init_scripts`.",
"items": {
"description": "",
"properties": {
"dbfs": {
"description": "destination needs to be provided. e.g.\n`{ \"dbfs\" : { \"destination\" : \"dbfs:/home/cluster_log\" } }`",
"properties": {
"destination": {
"description": "dbfs destination, e.g. `dbfs:/my/path`"
}
}
},
"file": {
"description": "destination needs to be provided. e.g.\n`{ \"file\" : { \"destination\" : \"file:/my/local/file.sh\" } }`",
"properties": {
"destination": {
"description": "local file destination, e.g. `file:/my/local/file.sh`"
}
}
},
"s3": {
"description": "destination and either the region or endpoint need to be provided. e.g.\n`{ \"s3\": { \"destination\" : \"s3://cluster_log_bucket/prefix\", \"region\" : \"us-west-2\" } }`\nCluster iam role is used to access s3, please make sure the cluster iam role in\n`instance_profile_arn` has permission to write data to the s3 destination.",
"properties": {
"canned_acl": {
"description": "(Optional) Set canned access control list for the logs, e.g. `bucket-owner-full-control`.\nIf `canned_cal` is set, please make sure the cluster iam role has `s3:PutObjectAcl` permission on\nthe destination bucket and prefix. The full list of possible canned acl can be found at\nhttp://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl.\nPlease also note that by default only the object owner gets full controls. If you are using cross account\nrole for writing data, you may want to set `bucket-owner-full-control` to make bucket owner able to\nread the logs."
},
"destination": {
"description": "S3 destination, e.g. `s3://my-bucket/some-prefix` Note that logs will be delivered using\ncluster iam role, please make sure you set cluster iam role and the role has write access to the\ndestination. Please also note that you cannot use AWS keys to deliver logs."
},
"enable_encryption": {
"description": "(Optional) Flag to enable server side encryption, `false` by default."
},
"encryption_type": {
"description": "(Optional) The encryption type, it could be `sse-s3` or `sse-kms`. It will be used only when\nencryption is enabled and the default type is `sse-s3`."
},
"endpoint": {
"description": "S3 endpoint, e.g. `https://s3-us-west-2.amazonaws.com`. Either region or endpoint needs to be set.\nIf both are set, endpoint will be used."
},
"kms_key": {
"description": "(Optional) Kms key which will be used if encryption is enabled and encryption type is set to `sse-kms`."
},
"region": {
"description": "S3 region, e.g. `us-west-2`. Either region or endpoint needs to be set. If both are set,\nendpoint will be used."
}
}
},
"volumes": {
"description": "destination needs to be provided. e.g.\n`{ \"volumes\" : { \"destination\" : \"/Volumes/my-init.sh\" } }`",
"properties": {
"destination": {
"description": "Unity Catalog Volumes file destination, e.g. `/Volumes/my-init.sh`"
}
}
},
"workspace": {
"description": "destination needs to be provided. e.g.\n`{ \"workspace\" : { \"destination\" : \"/Users/user1@databricks.com/my-init.sh\" } }`",
"properties": {
"destination": {
"description": "workspace files destination, e.g. `/Users/user1@databricks.com/my-init.sh`"
}
}
}
}
}
},
"instance_pool_id": {
"description": "The optional ID of the instance pool to which the cluster belongs."
},
"node_type_id": {
"description": "This field encodes, through a single value, the resources available to each of\nthe Spark nodes in this cluster. For example, the Spark nodes can be provisioned\nand optimized for memory or compute intensive workloads. A list of available node\ntypes can be retrieved by using the :method:clusters/listNodeTypes API call.\n"
},
"num_workers": {
"description": "Number of worker nodes that this cluster should have. A cluster has one Spark Driver\nand `num_workers` Executors for a total of `num_workers` + 1 Spark nodes.\n\nNote: When reading the properties of a cluster, this field reflects the desired number\nof workers rather than the actual current number of workers. For instance, if a cluster\nis resized from 5 to 10 workers, this field will immediately be updated to reflect\nthe target size of 10 workers, whereas the workers listed in `spark_info` will gradually\nincrease from 5 to 10 as the new nodes are provisioned."
},
"policy_id": {
"description": "The ID of the cluster policy used to create the cluster if applicable."
},
"runtime_engine": {
"description": ""
},
"single_user_name": {
"description": "Single user name if data_security_mode is `SINGLE_USER`"
},
"spark_conf": {
"description": "An object containing a set of optional, user-specified Spark configuration key-value pairs.\nUsers can also pass in a string of extra JVM options to the driver and the executors via\n`spark.driver.extraJavaOptions` and `spark.executor.extraJavaOptions` respectively.\n",
"additionalproperties": {
"description": ""
}
},
"spark_env_vars": {
"description": "An object containing a set of optional, user-specified environment variable key-value pairs.\nPlease note that key-value pair of the form (X,Y) will be exported as is (i.e.,\n`export X='Y'`) while launching the driver and workers.\n\nIn order to specify an additional set of `SPARK_DAEMON_JAVA_OPTS`, we recommend appending\nthem to `$SPARK_DAEMON_JAVA_OPTS` as shown in the example below. This ensures that all\ndefault databricks managed environmental variables are included as well.\n\nExample Spark environment variables:\n`{\"SPARK_WORKER_MEMORY\": \"28000m\", \"SPARK_LOCAL_DIRS\": \"/local_disk0\"}` or\n`{\"SPARK_DAEMON_JAVA_OPTS\": \"$SPARK_DAEMON_JAVA_OPTS -Dspark.shuffle.service.enabled=true\"}`",
"additionalproperties": {
"description": ""
}
},
"spark_version": {
"description": "The Spark version of the cluster, e.g. `3.3.x-scala2.11`.\nA list of available Spark versions can be retrieved by using\nthe :method:clusters/sparkVersions API call.\n"
},
"ssh_public_keys": {
"description": "SSH public key contents that will be added to each Spark node in this cluster. The\ncorresponding private keys can be used to login with the user name `ubuntu` on port `2200`.\nUp to 10 keys can be specified.",
"items": {
"description": ""
}
},
"workload_type": {
"description": "",
"properties": {
"clients": {
"description": " defined what type of clients can use the cluster. E.g. Notebooks, Jobs",
"properties": {
"jobs": {
"description": "With jobs set, the cluster can be used for jobs"
},
"notebooks": {
"description": "With notebooks set, this cluster can be used for notebooks"
}
}
}
}
}
}
}
}
}
},
"max_concurrent_runs": {
"description": "An optional maximum allowed number of concurrent runs of the job.\n\nSet this value if you want to be able to execute multiple runs of the same job concurrently. This is useful for example if you trigger your job on a frequent schedule and want to allow consecutive runs to overlap with each other, or if you want to trigger multiple runs which differ by their input parameters.\n\nThis setting affects only new runs. For example, suppose the job’s concurrency is 4 and there are 4 concurrent active runs. Then setting the concurrency to 3 won’t kill any of the active runs. However, from then on, new runs are skipped unless there are fewer than 3 active runs.\n\nThis value cannot exceed 1000. Setting this value to `0` causes all new runs to be skipped."
},
"name": {
"description": "An optional name for the job. The maximum length is 4096 bytes in UTF-8 encoding."
},
"notification_settings": {
"description": "Optional notification settings that are used when sending notifications to each of the `email_notifications` and `webhook_notifications` for this job.",
"properties": {
"no_alert_for_canceled_runs": {
"description": "If true, do not send notifications to recipients specified in `on_failure` if the run is canceled."
},
"no_alert_for_skipped_runs": {
"description": "If true, do not send notifications to recipients specified in `on_failure` if the run is skipped."
}
}
},
"parameters": {
"description": "Job-level parameter definitions",
"items": {
"description": "",
"properties": {
"default": {
"description": "Default value of the parameter."
},
"name": {
"description": "The name of the defined parameter. May only contain alphanumeric characters, `_`, `-`, and `.`"
}
}
}
},
"permissions": {
"description": "",
"items": {
"description": "",
"properties": {
"group_name": {
"description": ""
},
"level": {
"description": ""
},
"service_principal_name": {
"description": ""
},
"user_name": {
"description": ""
}
}
}
},
"queue": {
"description": "The queue settings of the job.",
"properties": {
"enabled": {
"description": "If true, enable queueing for the job. This is a required field."
}
}
},
"run_as": {
"description": "",
"properties": {
"service_principal_name": {
"description": "Application ID of an active service principal. Setting this field requires the `servicePrincipal/user` role."
},
"user_name": {
"description": "The email of an active workspace user. Non-admin users can only set this field to their own email."
}
}
},
"schedule": {
"description": "An optional periodic schedule for this job. The default behavior is that the job only runs when triggered by clicking “Run Now” in the Jobs UI or sending an API request to `runNow`.",
"properties": {
"pause_status": {
"description": "Indicate whether the continuous execution of the job is paused or not. Defaults to UNPAUSED."
},
"quartz_cron_expression": {
"description": "A Cron expression using Quartz syntax that describes the schedule for a job.\nSee [Cron Trigger](http://www.quartz-scheduler.org/documentation/quartz-2.3.0/tutorials/crontrigger.html)\nfor details. This field is required.\"\n"
},
"timezone_id": {
"description": "A Java timezone ID. The schedule for a job is resolved with respect to this timezone.\nSee [Java TimeZone](https://docs.oracle.com/javase/7/docs/api/java/util/TimeZone.html) for details.\nThis field is required.\n"
}
}
},
"tags": {
"description": "A map of tags associated with the job. These are forwarded to the cluster as cluster tags for jobs clusters, and are subject to the same limitations as cluster tags. A maximum of 25 tags can be added to the job.",
"additionalproperties": {
"description": ""
}
},
"tasks": {
"description": "A list of task specifications to be executed by this job.",
"items": {
"description": "",
"properties": {
"compute_key": {
"description": "The key of the compute requirement, specified in `job.settings.compute`, to use for execution of this task."
},
"condition_task": {
"description": "If condition_task, specifies a condition with an outcome that can be used to control the execution of other tasks. Does not require a cluster to execute and does not support retries or notifications.",
"properties": {
"left": {
"description": "The left operand of the condition task. Can be either a string value or a job state or parameter reference."
},
"op": {
"description": "* `EQUAL_TO`, `NOT_EQUAL` operators perform string comparison of their operands. This means that `“12.0” == “12”` will evaluate to `false`.\n* `GREATER_THAN`, `GREATER_THAN_OR_EQUAL`, `LESS_THAN`, `LESS_THAN_OR_EQUAL` operators perform numeric comparison of their operands. `“12.0” \u003e= “12”` will evaluate to `true`, `“10.0” \u003e= “12”` will evaluate to `false`.\n\nThe boolean comparison to task values can be implemented with operators `EQUAL_TO`, `NOT_EQUAL`. If a task value was set to a boolean value, it will be serialized to `“true”` or `“false”` for the comparison.\n"
},
"right": {
"description": "The right operand of the condition task. Can be either a string value or a job state or parameter reference."
}
}
},
"dbt_task": {
"description": "If dbt_task, indicates that this must execute a dbt task. It requires both Databricks SQL and the ability to use a serverless or a pro SQL warehouse.",
"properties": {
"catalog": {
"description": "Optional name of the catalog to use. The value is the top level in the 3-level namespace of Unity Catalog (catalog / schema / relation). The catalog value can only be specified if a warehouse_id is specified. Requires dbt-databricks \u003e= 1.1.1."
},
"commands": {
"description": "A list of dbt commands to execute. All commands must start with `dbt`. This parameter must not be empty. A maximum of up to 10 commands can be provided.",
"items": {
"description": ""
}
},
"profiles_directory": {
"description": "Optional (relative) path to the profiles directory. Can only be specified if no warehouse_id is specified. If no warehouse_id is specified and this folder is unset, the root directory is used."
},
"project_directory": {
"description": "Optional (relative) path to the project directory, if no value is provided, the root of the git repository is used."
},
"schema": {
"description": "Optional schema to write to. This parameter is only used when a warehouse_id is also provided. If not provided, the `default` schema is used."
},
"warehouse_id": {
"description": "ID of the SQL warehouse to connect to. If provided, we automatically generate and provide the profile and connection details to dbt. It can be overridden on a per-command basis by using the `--profiles-dir` command line argument."
}
}
},
"depends_on": {
"description": "An optional array of objects specifying the dependency graph of the task. All tasks specified in this field must complete before executing this task. The task will run only if the `run_if` condition is true.\nThe key is `task_key`, and the value is the name assigned to the dependent task.\n",
"items": {
"description": "",
"properties": {
"outcome": {
"description": "Can only be specified on condition task dependencies. The outcome of the dependent task that must be met for this task to run."
},
"task_key": {
"description": "The name of the task this task depends on."
}
}
}
},
"description": {
"description": "An optional description for this task."
},
"email_notifications": {
"description": "An optional set of email addresses that is notified when runs of this task begin or complete as well as when this task is deleted. The default behavior is to not send any emails.",
"properties": {
"on_duration_warning_threshold_exceeded": {
"description": "A list of email addresses to be notified when the duration of a run exceeds the threshold specified for the `RUN_DURATION_SECONDS` metric in the `health` field. If no rule for the `RUN_DURATION_SECONDS` metric is specified in the `health` field for the job, notifications are not sent.",
"items": {
"description": ""
}
},
"on_failure": {
"description": "A list of email addresses to be notified when a run unsuccessfully completes. A run is considered to have completed unsuccessfully if it ends with an `INTERNAL_ERROR` `life_cycle_state` or a `FAILED`, or `TIMED_OUT` result_state. If this is not specified on job creation, reset, or update the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
},
"on_start": {
"description": "A list of email addresses to be notified when a run begins. If not specified on job creation, reset, or update, the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
},
"on_success": {
"description": "A list of email addresses to be notified when a run successfully completes. A run is considered to have completed successfully if it ends with a `TERMINATED` `life_cycle_state` and a `SUCCESS` result_state. If not specified on job creation, reset, or update, the list is empty, and notifications are not sent.",
"items": {
"description": ""
}
}
}
},
"existing_cluster_id": {
"description": "If existing_cluster_id, the ID of an existing cluster that is used for all runs of this task. When running tasks on an existing cluster, you may need to manually restart the cluster if it stops responding. We suggest running jobs on new clusters for greater reliability."
},
"health": {
"description": "",
"properties": {
"rules": {
"description": "",
"items": {
"description": "",
"properties": {
"metric": {
"description": ""
},
"op": {
"description": ""
},
"value": {
"description": "Specifies the threshold value that the health metric should obey to satisfy the health rule."
}
}
}
}
}
},
"job_cluster_key": {
"description": "If job_cluster_key, this task is executed reusing the cluster specified in `job.settings.job_clusters`."
},
"libraries": {
"description": "An optional list of libraries to be installed on the cluster that executes the task. The default value is an empty list.",
"items": {
"description": "",
"properties": {
"cran": {
"description": "Specification of a CRAN library to be installed as part of the library",
"properties": {
"package": {
"description": "The name of the CRAN package to install."
},
"repo": {
"description": "The repository where the package can be found. If not specified, the default CRAN repo is used."
}
}
},
"egg": {
"description": "URI of the egg to be installed. Currently only DBFS and S3 URIs are supported.\nFor example: `{ \"egg\": \"dbfs:/my/egg\" }` or\n`{ \"egg\": \"s3://my-bucket/egg\" }`.\nIf S3 is used, please make sure the cluster has read access on the library. You may need to\nlaunch the cluster with an IAM role to access the S3 URI."
},
"jar": {
"description": "URI of the jar to be installed. Currently only DBFS and S3 URIs are supported.\nFor example: `{ \"jar\": \"dbfs:/mnt/databricks/library.jar\" }` or\n`{ \"jar\": \"s3://my-bucket/library.jar\" }`.\nIf S3 is used, please make sure the cluster has read access on the library. You may need to\nlaunch the cluster with an IAM role to access the S3 URI."
},
"maven": {
"description": "Specification of a maven library to be installed. For example:\n`{ \"coordinates\": \"org.jsoup:jsoup:1.7.2\" }`",
"properties": {
"coordinates": {
"description": "Gradle-style maven coordinates. For example: \"org.jsoup:jsoup:1.7.2\"."
},
"exclusions": {
"description": "List of dependences to exclude. For example: `[\"slf4j:slf4j\", \"*:hadoop-client\"]`.\n\nMaven dependency exclusions:\nhttps://maven.apache.org/guides/introduction/introduction-to-optional-and-excludes-dependencies.html.",
"items": {
"description": ""
}
},
"repo": {
"description": "Maven repo to install the Maven package from. If omitted, both Maven Central Repository\nand Spark Packages are searched."
}
}
},
"pypi": {
"description": "Specification of a PyPi library to be installed. For example:\n`{ \"package\": \"simplejson\" }`",
"properties": {
"package": {
"description": "The name of the pypi package to install. An optional exact version specification is also\nsupported. Examples: \"simplejson\" and \"simplejson==3.8.0\"."
},
"repo": {
"description": "The repository where the package can be found. If not specified, the default pip index is\nused."
}
}
},
"whl": {
"description": "URI of the wheel to be installed.\nFor example: `{ \"whl\": \"dbfs:/my/whl\" }` or `{ \"whl\": \"s3://my-bucket/whl\" }`.\nIf S3 is used, please make sure the cluster has read access on the library. You may need to\nlaunch the cluster with an IAM role to access the S3 URI."
}
}
}
},
"max_retries": {
"description": "An optional maximum number of times to retry an unsuccessful run. A run is considered to be unsuccessful if it completes with the `FAILED` result_state or `INTERNAL_ERROR` `life_cycle_state`. The value `-1` means to retry indefinitely and the value `0` means to never retry."
},
"min_retry_interval_millis": {
"description": "An optional minimal interval in milliseconds between the start of the failed run and the subsequent retry run. The default behavior is that unsuccessful runs are immediately retried."
},
"new_cluster": {
"description": "If new_cluster, a description of a cluster that is created for only for this task.",
"properties": {
"apply_policy_default_values": {
"description": ""
},
"autoscale": {
"description": "Parameters needed in order to automatically scale clusters up and down based on load.\nNote: autoscaling works best with DB runtime versions 3.0 or later.",
"properties": {
"max_workers": {
"description": "The maximum number of workers to which the cluster can scale up when overloaded.\nNote that `max_workers` must be strictly greater than `min_workers`."
},
"min_workers": {
"description": "The minimum number of workers to which the cluster can scale down when underutilized.\nIt is also the initial number of workers the cluster will have after creation."
}
}
},
"autotermination_minutes": {
"description": "Automatically terminates the cluster after it is inactive for this time in minutes. If not set,\nthis cluster will not be automatically terminated. If specified, the threshold must be between\n10 and 10000 minutes.\nUsers can also set this value to 0 to explicitly disable automatic termination."
},
"aws_attributes": {
"description": "Attributes related to clusters running on Amazon Web Services.\nIf not specified at cluster creation, a set of default values will be used.",
"properties": {
"availability": {
"description": ""
},
"ebs_volume_count": {
"description": "The number of volumes launched for each instance. Users can choose up to 10 volumes.\nThis feature is only enabled for supported node types. Legacy node types cannot specify\ncustom EBS volumes.\nFor node types with no instance store, at least one EBS volume needs to be specified;\notherwise, cluster creation will fail.\n\nThese EBS volumes will be mounted at `/ebs0`, `/ebs1`, and etc.\nInstance store volumes will be mounted at `/local_disk0`, `/local_disk1`, and etc.\n\nIf EBS volumes are attached, Databricks will configure Spark to use only the EBS volumes for\nscratch storage because heterogenously sized scratch devices can lead to inefficient disk\nutilization. If no EBS volumes are attached, Databricks will configure Spark to use instance\nstore volumes.\n\nPlease note that if EBS volumes are specified, then the Spark configuration `spark.local.dir`\nwill be overridden."
},
"ebs_volume_iops": {
"description": "\u003cneeds content added\u003e"
},
"ebs_volume_size": {
"description": "The size of each EBS volume (in GiB) launched for each instance. For general purpose\nSSD, this value must be within the range 100 - 4096. For throughput optimized HDD,\nthis value must be within the range 500 - 4096."
},
"ebs_volume_throughput": {
"description": "\u003cneeds content added\u003e"
},
"ebs_volume_type": {
"description": ""
},
"first_on_demand": {
"description": "The first `first_on_demand` nodes of the cluster will be placed on on-demand instances.\nIf this value is greater than 0, the cluster driver node in particular will be placed on an\non-demand instance. If this value is greater than or equal to the current cluster size, all\nnodes will be placed on on-demand instances. If this value is less than the current cluster\nsize, `first_on_demand` nodes will be placed on on-demand instances and the remainder will\nbe placed on `availability` instances. Note that this value does not affect\ncluster size and cannot currently be mutated over the lifetime of a cluster."
},
"instance_profile_arn": {
"description": "Nodes for this cluster will only be placed on AWS instances with this instance profile. If\nommitted, nodes will be placed on instances without an IAM instance profile. The instance\nprofile must have previously been added to the Databricks environment by an account\nadministrator.\n\nThis feature may only be available to certain customer plans.\n\nIf this field is ommitted, we will pull in the default from the conf if it exists."
},
"spot_bid_price_percent": {
"description": "The bid price for AWS spot instances, as a percentage of the corresponding instance type's\non-demand price.\nFor example, if this field is set to 50, and the cluster needs a new `r3.xlarge` spot\ninstance, then the bid price is half of the price of\non-demand `r3.xlarge` instances. Similarly, if this field is set to 200, the bid price is twice\nthe price of on-demand `r3.xlarge` instances. If not specified, the default value is 100.\nWhen spot instances are requested for this cluster, only spot instances whose bid price\npercentage matches this field will be considered.\nNote that, for safety, we enforce this field to be no more than 10000.\n\nThe default value and documentation here should be kept consistent with\nCommonConf.defaultSpotBidPricePercent and CommonConf.maxSpotBidPricePercent."
},
"zone_id": {
"description": "Identifier for the availability zone/datacenter in which the cluster resides.\nThis string will be of a form like \"us-west-2a\". The provided availability\nzone must be in the same region as the Databricks deployment. For example, \"us-west-2a\"\nis not a valid zone id if the Databricks deployment resides in the \"us-east-1\" region.\nThis is an optional field at cluster creation, and if not specified, a default zone will be used.\nIf the zone specified is \"auto\", will try to place cluster in a zone with high availability,\nand will retry placement in a different AZ if there is not enough capacity.\nThe list of available zones as well as the default value can be found by using the\n`List Zones` method."
}
}
},
"azure_attributes": {
"description": "Attributes related to clusters running on Microsoft Azure.\nIf not specified at cluster creation, a set of default values will be used.",
"properties": {
"availability": {
"description": ""
},
"first_on_demand": {
"description": "The first `first_on_demand` nodes of the cluster will be placed on on-demand instances.\nThis value should be greater than 0, to make sure the cluster driver node is placed on an\non-demand instance. If this value is greater than or equal to the current cluster size, all\nnodes will be placed on on-demand instances. If this value is less than the current cluster\nsize, `first_on_demand` nodes will be placed on on-demand instances and the remainder will\nbe placed on `availability` instances. Note that this value does not affect\ncluster size and cannot currently be mutated over the lifetime of a cluster."
},
"log_analytics_info": {
"description": "Defines values necessary to configure and run Azure Log Analytics agent",
"properties": {
"log_analytics_primary_key": {
"description": "\u003cneeds content added\u003e"
},
"log_analytics_workspace_id": {
"description": "\u003cneeds content added\u003e"
}
}
},
"spot_bid_max_price": {
"description": "The max bid price to be used for Azure spot instances.\nThe Max price for the bid cannot be higher than the on-demand price of the instance.\nIf not specified, the default value is -1, which specifies that the instance cannot be evicted\non the basis of price, and only on the basis of availability. Further, the value should \u003e 0 or -1."
}
}
},
"cluster_log_conf": {
"description": "The configuration for delivering spark logs to a long-term storage destination.\nTwo kinds of destinations (dbfs and s3) are supported. Only one destination can be specified\nfor one cluster. If the conf is given, the logs will be delivered to the destination every\n`5 mins`. The destination of driver logs is `$destination/$clusterId/driver`, while\nthe destination of executor logs is `$destination/$clusterId/executor`.",
"properties": {
"dbfs": {
"description": "destination needs to be provided. e.g.\n`{ \"dbfs\" : { \"destination\" : \"dbfs:/home/cluster_log\" } }`",
"properties": {
"destination": {
"description": "dbfs destination, e.g. `dbfs:/my/path`"
}
}
},
"s3": {
"description": "destination and either the region or endpoint need to be provided. e.g.\n`{ \"s3\": { \"destination\" : \"s3://cluster_log_bucket/prefix\", \"region\" : \"us-west-2\" } }`\nCluster iam role is used to access s3, please make sure the cluster iam role in\n`instance_profile_arn` has permission to write data to the s3 destination.",
"properties": {
"canned_acl": {
"description": "(Optional) Set canned access control list for the logs, e.g. `bucket-owner-full-control`.\nIf `canned_cal` is set, please make sure the cluster iam role has `s3:PutObjectAcl` permission on\nthe destination bucket and prefix. The full list of possible canned acl can be found at\nhttp://docs.aws.amazon.com/AmazonS3/latest/dev/acl-overview.html#canned-acl.\nPlease also note that by default only the object owner gets full controls. If you are using cross account\nrole for writing data, you may want to set `bucket-owner-full-control` to make bucket owner able to\nread the logs."
},
"destination": {
"description": "S3 destination, e.g. `s3://my-bucket/some-prefix` Note that logs will be delivered using\ncluster iam role, please make sure you set cluster iam role and the role has write access to the\ndestination. Please also note that you cannot use AWS keys to deliver logs."
},
"enable_encryption": {
"description": "(Optional) Flag to enable server side encryption, `false` by default."
},
"encryption_type": {
"description": "(Optional) The encryption type, it could be `sse-s3` or `sse-kms`. It will be used only when\nencryption is enabled and the default type is `sse-s3`."
},