forked from acryldata/datahub-helm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
values.yaml
826 lines (780 loc) · 26.7 KB
/
values.yaml
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
# Values to start up datahub after starting up the datahub-prerequisites chart with "prerequisites" release name
# Copy this chart and change configuration as needed.
datahub-gms:
enabled: true
image:
repository: acryldata/datahub-gms
# tag: "v0.11.0 # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
memory: 2Gi
requests:
cpu: 100m
memory: 1Gi
livenessProbe:
initialDelaySeconds: 60
periodSeconds: 30
failureThreshold: 8
readinessProbe:
initialDelaySeconds: 120
periodSeconds: 30
failureThreshold: 8
# Optionaly specify service type for datahub-gms: LoadBalancer, ClusterIP or NodePort, by default: LoadBalancer
# service:
# type: ClusterIP
# Optionally set a GMS specific SQL login (defaults to global login)
# sql:
# datasource:
# username: "gms-login"
# password:
# secretRef: gms-secret
# secretKey: gms-password
datahub-frontend:
enabled: true
image:
repository: acryldata/datahub-frontend-react
# tag: "v0.11.0" # # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
memory: 1400Mi
requests:
cpu: 100m
memory: 512Mi
# Set up ingress to expose react front-end
ingress:
enabled: false
defaultUserCredentials: {}
service:
extraLabels: {}
# randomAdminPassword: true
# You can also set specific passwords for default users
# manualValues: |
# datahub:manualPassword
# initialViewer:manualPassword
# Optionaly specify service type for datahub-frontend: LoadBalancer, ClusterIP or NodePort, by default: LoadBalancer
# service:
# type: ClusterIP
acryl-datahub-actions:
enabled: true
image:
repository: acryldata/datahub-actions
tag: "v0.1.1"
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
# mount the k8s secret as a volume in the container, each key name is mounted as a file on the mount path /etc/datahub/ingestion-secret-files
# ingestionSecretFiles:
# name: ${K8S_SECRET_NAME}
# defaultMode: "0444"
resources:
limits:
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
datahub-mae-consumer:
image:
repository: acryldata/datahub-mae-consumer
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
memory: 1536Mi
requests:
cpu: 100m
memory: 256Mi
datahub-mce-consumer:
image:
repository: acryldata/datahub-mce-consumer
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
memory: 1536Mi
requests:
cpu: 100m
memory: 256Mi
datahub-ingestion-cron:
enabled: false
image:
repository: acryldata/datahub-ingestion
# tag: "v0.11.0" # defaults to .global.datahub.version
elasticsearchSetupJob:
enabled: true
image:
repository: acryldata/datahub-elasticsearch-setup
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
extraInitContainers: []
podSecurityContext:
fsGroup: 1000
securityContext:
runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: pre-install,pre-upgrade
helm.sh/hook-weight: "-5"
helm.sh/hook-delete-policy: before-hook-creation
podAnnotations: {}
# If you want to use OpenSearch instead of ElasticSearch add the USE_AWS_ELASTICSEARCH environment variable below
# extraEnvs:
# - name: USE_AWS_ELASTICSEARCH
# value: "true"
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
kafkaSetupJob:
enabled: true
image:
repository: acryldata/datahub-kafka-setup
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
cpu: 500m
memory: 1024Mi
requests:
cpu: 300m
memory: 768Mi
extraInitContainers: []
podSecurityContext:
fsGroup: 1000
securityContext:
runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: pre-install,pre-upgrade
helm.sh/hook-weight: "-5"
helm.sh/hook-delete-policy: before-hook-creation
podAnnotations: {}
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
mysqlSetupJob:
enabled: true
image:
repository: acryldata/datahub-mysql-setup
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
extraInitContainers: []
podSecurityContext:
fsGroup: 1000
securityContext:
runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: pre-install,pre-upgrade
helm.sh/hook-weight: "-5"
helm.sh/hook-delete-policy: before-hook-creation
podAnnotations: {}
# Optionally set a set-up job specific login (defaults to global login)
# username: "mysqlSetupJob-login"
# password:
# secretRef: mysqlSetupJob-secret
# secretKey: mysqlSetupJob-password
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
postgresqlSetupJob:
enabled: false
image:
repository: acryldata/datahub-postgres-setup
# tag: "v0.11.0" # defaults to .global.datahub.version
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
extraInitContainers: []
podSecurityContext:
fsGroup: 1000
securityContext:
runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: pre-install,pre-upgrade
helm.sh/hook-weight: "-5"
helm.sh/hook-delete-policy: before-hook-creation
podAnnotations: {}
# Optionally set a set-up job specific login (defaults to global login)
# username: "postgresqlSetupJob-login"
# password:
# secretRef: postgresqlSetupJob-secret
# secretKey: postgresqlSetupJob-password
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
# Optionally set a specific database using extraEnvs
# extraEnvs: []
# - name: "DATAHUB_DB_NAME"
# value: "dh"
## No code data migration
datahubUpgrade:
enabled: true
image:
repository: acryldata/datahub-upgrade
# tag: "v0.11.0" # defaults to .global.datahub.version
batchSize: 1000
batchDelayMs: 100
noCodeDataMigration:
image:
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
command:
args: []
sqlDbType: "MYSQL"
# sqlDbType: "POSTGRES"
podSecurityContext: {}
# fsGroup: 1000
securityContext: {}
# runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: post-install,post-upgrade
helm.sh/hook-weight: "-2"
helm.sh/hook-delete-policy: before-hook-creation
podAnnotations: {}
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
cleanupJob:
image:
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
command:
args: []
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
# Add the concurrency Policy flexibility via values
concurrencyPolicy: Allow
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
restoreIndices:
image:
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
command:
args: []
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
# Schedule of CronJob when enabled
schedule: "0 0 * * 0"
# Add the concurrency Policy flexibility via values
concurrencyPolicy: Allow
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
# Optionally set a specific PostgreSQL database name using extraEnvs
# extraEnvs:
# - name: "DATAHUB_DB_NAME"
# value: "dh"
extraInitContainers: []
## Runs system update processes
## Includes: Elasticsearch Indices Creation/Reindex (See global.elasticsearch.index for additional configuration)
datahubSystemUpdate:
image:
repository: acryldata/datahub-upgrade
# tag:
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
podSecurityContext: {}
# fsGroup: 1000
securityContext: {}
# runAsUser: 1000
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: pre-install,pre-upgrade
helm.sh/hook-weight: "-4"
helm.sh/hook-delete-policy: before-hook-creation
# !! Requires version v0.13.0 or greater
# Split the system update into 2 jobs, one that is blocking the rest of
# the deployment and the other which is non-blocking. Once the blocking
# steps are completed, the non-blocking job runs while the rest of the
# system is starting.
nonblocking:
enabled: false
# When mode = 'nonblocking' the nonblocking job should not include the above helm.sh/hook annotations
annotations:
# This is what defines this resource as a hook. Without this line, the
# job is considered part of the release.
helm.sh/hook: post-install,post-upgrade
helm.sh/hook-delete-policy: before-hook-creation
image:
args:
# Add custom command / arguments to this job. Useful if you need a custom startup or shutdown script
# to run
# command: customCommand
# args: []
podAnnotations: {}
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 300m
memory: 256Mi
# Add extra sidecar containers to job pod
extraSidecars: []
# - name: my-image-name
# image: my-image
# imagePullPolicy: Always
extraInitContainers: []
global:
strict_mode: true
graph_service_impl: elasticsearch
datahub_analytics_enabled: true
datahub_standalone_consumers_enabled: false
imageRegistry: "docker.io"
elasticsearch:
host: "elasticsearch-master"
# If you want to use OpenSearch instead of ElasticSearch use different hostname below
# host: "opensearch-cluster-master"
port: "9200"
skipcheck: "false"
insecure: "false"
useSSL: "false"
# If you want to specify index prefixes use indexPrefix
# indexPrefix: "dh"
## The following section controls when and how reindexing of elasticsearch indices are performed
index:
## Enable reindexing when mappings change based on the data model annotations
enableMappingsReindex: true
## Enable reindexing when static index settings change.
## Dynamic settings which do not require reindexing are not affected
## Primarily this should be enabled when re-sharding is necessary for scaling/performance.
enableSettingsReindex: true
## Index settings can be overridden for entity indices or other indices on an index by index basis
## Some index settings, such as # of shards, requires reindexing while others, i.e. replicas, do not
## The index settings options can be specified as a string or a map (which is converted to a string
## representation)
##
## Non-Entity indices do not require the prefix
# settingsOverrides: '{"graph_service_v1":{"number_of_shards":"5"},"system_metadata_service_v1":{"number_of_shards":"5"}}'
## or
# settingsOverrides:
# graph_service_v1:
# number_of_shards: '5'
# system_metadata_service_v1:
# number_of_shards: '6'
#
## Entity indices do not require the prefix or suffix
# entitySettingsOverrides: '{"dataset":{"number_of_shards":"10"}}'
## The amount of delay between indexing a document and having it returned in queries
## Increasing this value can improve performance when ingesting large amounts of data
# refreshIntervalSeconds: 1
## The following options control settings for datahub-upgrade job when creating or reindexing indices
upgrade:
## When reindexing is required, this option will clone the existing index as a backup
## The clone indices are not currently managed.
cloneIndices: true
## Typically when reindexing the document counts between the original and destination indices should match.
## In some cases reindexing might not be able to proceed due to incompatibilities between a document in the
## orignal index and the new index's mappings. This document could be dropped and re-ingested or restored from
## the SQL database.
##
## This setting allows continuing if and only if the cloneIndices setting is also enabled which
## ensures a complete backup of the original index is preserved.
allowDocCountMismatch: false
## Search related configuration
search:
## Maximum terms in aggregations
maxTermBucketSize: 20
## Configuration around exact matching for search
exactMatch:
## if false will only apply weights, if true will exclude non-exact
exclusive: false
## include prefix exact matches
withPrefix: true
## boost multiplier when exact with case
exactFactor: 2.0
## boost multiplier when exact prefix
prefixFactor: 1.6
## stacked boost multiplier when case mismatch
caseSensitivityFactor: 0.7
## enable exact match on structured search
enableStructured: true
## Configuration for graph service dao
graph:
## graph dao timeout seconds
timeoutSeconds: 50
## graph dao batch size
batchSize: 1000
## graph dao max result size
maxResult: 10000
custom:
enabled: false
# See documentation: https://datahubproject.io/docs/how/search/#customizing-search
config:
# Notes:
#
# First match wins
#
# queryRegex = Java regex syntax
#
# functionScores - See the following for function score syntax
# https://www.elastic.co/guide/en/elasticsearch/reference/7.17/query-dsl-function-score-query.html
queryConfigurations:
# Select *
- queryRegex: '[*]|'
simpleQuery: false
prefixMatchQuery: false
exactMatchQuery: false
boolQuery:
must_not:
term:
deprecated:
value: true
functionScore:
functions:
- filter:
term:
materialized:
value: true
weight: 0.8
score_mode: multiply
boost_mode: multiply
# Criteria for exact-match only
# Contains quoted or contains underscore then use exact match query
- queryRegex: >-
["'].+["']|\S+_\S+
simpleQuery: false
prefixMatchQuery: true
exactMatchQuery: true
functionScore:
functions:
- filter:
term:
materialized:
value: true
weight: 0.8
- filter:
term:
deprecated:
value: true
weight: 0
score_mode: multiply
boost_mode: multiply
# default
- queryRegex: .*
simpleQuery: true
prefixMatchQuery: true
exactMatchQuery: true
boolQuery:
must_not:
term:
deprecated:
value: true
functionScore:
functions:
- filter:
term:
materialized:
value: true
weight: 0.8
score_mode: multiply
boost_mode: multiply
kafka:
bootstrap:
server: "prerequisites-kafka:9092"
zookeeper:
server: "prerequisites-zookeeper:2181"
# This section defines the names for the kafka topics that DataHub depends on, at a global level. Do not override this config
# at a sub-chart level.
topics:
metadata_change_event_name: "MetadataChangeEvent_v4"
failed_metadata_change_event_name: "FailedMetadataChangeEvent_v4"
metadata_audit_event_name: "MetadataAuditEvent_v4"
datahub_usage_event_name: "DataHubUsageEvent_v1"
metadata_change_proposal_topic_name: "MetadataChangeProposal_v1"
failed_metadata_change_proposal_topic_name: "FailedMetadataChangeProposal_v1"
metadata_change_log_versioned_topic_name: "MetadataChangeLog_Versioned_v1"
metadata_change_log_timeseries_topic_name: "MetadataChangeLog_Timeseries_v1"
platform_event_topic_name: "PlatformEvent_v1"
datahub_upgrade_history_topic_name: "DataHubUpgradeHistory_v1"
metadataChangeLog:
hooks:
siblings:
enabled: true
consumerGroupSuffix: ''
updateIndices:
enabled: true
consumerGroupSuffix: ''
ingestionScheduler:
enabled: true
consumerGroupSuffix: ''
incidents:
enabled: true
consumerGroupSuffix: ''
entityChangeEvents:
enabled: true
consumerGroupSuffix: ''
forms:
enabled: true
consumerGroupSuffix: ''
maxMessageBytes: "5242880" # 5MB
producer:
compressionType: none
maxRequestSize: "5242880" # 5MB
consumer:
maxPartitionFetchBytes: "5242880" # 5MB
stopContainerOnDeserializationError: true
## For AWS MSK set this to a number larger than 1
# partitions: 3
# replicationFactor: 3
schemaregistry:
# GMS Implementation - `url` configured based on component context
type: INTERNAL
# Confluent Kafka Implementation
# type: KAFKA
# url: "http://prerequisites-cp-schema-registry:8081"
# Glue Implementation - `url` not applicable
# type: AWS_GLUE
# glue:
# region: us-east-1
# registry: datahub
neo4j:
host: "prerequisites-neo4j:7474"
uri: "bolt://prerequisites-neo4j"
username: "neo4j"
password:
secretRef: neo4j-secrets
secretKey: neo4j-password
# --------------OR----------------
# value: password
sql:
datasource:
host: "prerequisites-mysql:3306"
hostForMysqlClient: "prerequisites-mysql"
port: "3306"
url: "jdbc:mysql://prerequisites-mysql:3306/datahub?verifyServerCertificate=false&useSSL=true&useUnicode=yes&characterEncoding=UTF-8&enabledTLSProtocols=TLSv1.2"
driver: "com.mysql.cj.jdbc.Driver"
username: "root"
password:
secretRef: mysql-secrets
secretKey: mysql-root-password
# --------------OR----------------
# value: password
## Use below for usage of PostgreSQL instead of MySQL
# host: "prerequisites-postgresql:5432"
# hostForpostgresqlClient: "prerequisites-postgresql"
# port: "5432"
# url: "jdbc:postgresql://prerequisites-postgresql:5432/datahub"
# driver: "org.postgresql.Driver"
# username: "postgres"
# password:
# secretRef: postgresql-secrets
# secretKey: postgres-password
# --------------OR----------------
# value: password
# If you want to use specific PostgreSQL database use extraEnvs
# extraEnvs:
# - name: "DATAHUB_DB_NAME"
# value: "dh"
## Use below for usage of Google Cloud SQL MySQL instance instead of the self hosted MySQL,
## make sure you have deployed gcloud-sqlproxy as prerequisite
# host: "prerequisites-gcloud-sqlproxy:3306"
# hostForMysqlClient: "prerequisites-gcloud-sqlproxy"
# port: "3306"
# url: "jdbc:mysql://prerequisites-gcloud-sqlproxy:3306/datahub?verifyServerCertificate=false&useSSL=true&useUnicode=yes&characterEncoding=UTF-8&enabledTLSProtocols=TLSv1.2"
# driver: "com.mysql.cj.jdbc.Driver"
# username: "root"
# password:
# secretRef: mysql-secrets
# secretKey: mysql-root-password
# --------------OR----------------
# value: password
datahub:
version: v0.14.1
gms:
protocol: "http"
port: "8080"
nodePort: "30001"
frontend:
validateSignUpEmail: true
monitoring:
enablePrometheus: true
# Set a custom name for the monitoring port
portName: jmx
mae_consumer:
port: "9091"
nodePort: "30002"
appVersion: "1.0"
systemUpdate:
## The following options control settings for datahub-upgrade job which will
## managed ES indices and other update related work
enabled: true
encryptionKey:
secretRef: "datahub-encryption-secrets"
secretKey: "encryption_key_secret"
# Set to false if you'd like to provide your own secret.
provisionSecret:
enabled: true
autoGenerate: true
annotations: {}
# Only specify if autoGenerate set to false
# secretValues:
# encryptionKey: <encryption key value>
managed_ingestion:
enabled: true
defaultCliVersion: "0.14.0.5"
metadata_service_authentication:
enabled: true
systemClientId: "__datahub_system"
systemClientSecret:
secretRef: "datahub-auth-secrets"
secretKey: "system_client_secret"
tokenService:
signingKey:
secretRef: "datahub-auth-secrets"
secretKey: "token_service_signing_key"
salt:
secretRef: "datahub-auth-secrets"
secretKey: "token_service_salt"
# Set to false if you'd like to provide your own auth secrets
provisionSecrets:
enabled: true
autoGenerate: true
annotations: {}
# Only specify if autoGenerate set to false
# secretValues:
# secret: <secret value>
# signingKey: <signing key value>
# salt: <salt value>
## Enables always emitting a MCL even when no changes are detected. Used for Time Based Lineage when no changes occur.
alwaysEmitChangeLog: false
## Enables diff mode for graph writes, uses a different code path that produces a diff from previous to next to write relationships instead of wholesale deleting edges and reading
enableGraphDiffMode: true
## Values specific to the unified search and browse feature.
search_and_browse:
show_search_v2: true # If on, show the new search filters experience as of v0.10.5
show_browse_v2: true # If on, show the new browse experience as of v0.10.5
backfill_browse_v2: true # If on, run the backfill upgrade job that generates default browse paths for relevant entities
## v0.13.4+
mcp:
throttle:
# updateIntervalMs: 60000
## Versioned MCL topic
versioned:
## Whether to throttle MCP processing based on MCL backlog
enabled: true
# threshold: 4000
# maxAttempts: 1000
# initialIntervalMs: 100
# multiplier: 10
# maxIntervalMs: 30000
# Timeseries MCL topic
timeseries:
## Whether to throttle MCP processing based on MCL backlog
enabled: false
# threshold: 4000
# maxAttempts: 1000
# initialIntervalMs: 100
# multiplier: 10
# maxIntervalMs: 30000
# hostAliases:
# - ip: "192.168.0.104"
# hostnames:
# - "broker"
# - "mysql"
# - "postgresql"
# - "elasticsearch"
# - "neo4j"
## Add below to enable SSL for kafka
# credentialsAndCertsSecrets:
# name: datahub-certs
# path: /mnt/datahub/certs
# secureEnv:
# ssl.key.password: datahub.linkedin.com.KeyPass
# ssl.keystore.password: datahub.linkedin.com.KeyStorePass
# ssl.truststore.password: datahub.linkedin.com.TrustStorePass
# kafkastore.ssl.truststore.password: datahub.linkedin.com.TrustStorePass
#
# springKafkaConfigurationOverrides:
# ssl.keystore.location: /mnt/datahub/certs/datahub.linkedin.com.keystore.jks
# ssl.truststore.location: /mnt/datahub/certs/datahub.linkedin.com.truststore.jks
# kafkastore.ssl.truststore.location: /mnt/datahub/certs/datahub.linkedin.com.truststore.jks
# security.protocol: SSL
# kafkastore.security.protocol: SSL
# ssl.keystore.type: JKS
# ssl.truststore.type: JKS
# ssl.protocol: TLS
# ssl.endpoint.identification.algorithm:
# basic.auth.credentials.source: USER_INFO
# basic.auth.user.info: