forked from datahub-project/datahub
-
Notifications
You must be signed in to change notification settings - Fork 0
/
application.yml
374 lines (335 loc) · 19.2 KB
/
application.yml
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
# App Layer
authentication:
# Enable if you want all requests to the Metadata Service to be authenticated. Disabled by default.
enabled: ${METADATA_SERVICE_AUTH_ENABLED:false}
# Required if enabled is true! A configurable chain of Authenticators
authenticators:
# Required for authenticating requests with DataHub-issued Access Tokens - best not to remove.
- type: com.datahub.authentication.authenticator.DataHubTokenAuthenticator
configs:
# Key used to validate incoming tokens. Should typically be the same as authentication.tokenService.signingKey
signingKey: ${DATAHUB_TOKEN_SERVICE_SIGNING_KEY:WnEdIeTG/VVCLQqGwC/BAkqyY0k+H8NEAtWGejrBI94=}
salt: ${DATAHUB_TOKEN_SERVICE_SALT:ohDVbJBvHHVJh9S/UA4BYF9COuNnqqVhr9MLKEGXk1O=}
# Required for unauthenticated health check endpoints - best not to remove.
- type: com.datahub.authentication.authenticator.HealthStatusAuthenticator
# Normally failures are only warnings, enable this to throw them.
logAuthenticatorExceptions: ${METADATA_SERVICE_AUTHENTICATOR_EXCEPTIONS_ENABLED:false}
# Required separately from the DataHubTokenAuthenticator as this is used by the AuthServiceController to authorize token generation
# at user login time.
systemClientId: ${DATAHUB_SYSTEM_CLIENT_ID:__datahub_system}
systemClientSecret: ${DATAHUB_SYSTEM_CLIENT_SECRET:JohnSnowKnowsNothing}
# Configurations for DataHub token service
tokenService:
# Key used to sign new tokens.
signingKey: ${DATAHUB_TOKEN_SERVICE_SIGNING_KEY:WnEdIeTG/VVCLQqGwC/BAkqyY0k+H8NEAtWGejrBI94=}
salt: ${DATAHUB_TOKEN_SERVICE_SALT:ohDVbJBvHHVJh9S/UA4BYF9COuNnqqVhr9MLKEGXk1O=}
issuer: ${DATAHUB_TOKEN_SERVICE_ISSUER:datahub-metadata-service}
signingAlgorithm: ${DATAHUB_TOKEN_SERVICE_SIGNING_ALGORITHM:HS256}
# The max duration of a UI session in milliseconds. Defaults to 1 day.
sessionTokenDurationMs: ${SESSION_TOKEN_DURATION_MS:86400000}
# Authorization-related configurations.
authorization:
# Configurations for the default DataHub policies-based authorizer.
defaultAuthorizer:
enabled: ${AUTH_POLICIES_ENABLED:true}
cacheRefreshIntervalSecs: ${POLICY_CACHE_REFRESH_INTERVAL_SECONDS:120}
cachePolicyFetchSize: ${POLICY_CACHE_FETCH_SIZE:1000}
# Enables authorization of reads, writes, and deletes on REST APIs. Defaults to false for backwards compatibility, but should become true down the road
restApiAuthorization: ${REST_API_AUTHORIZATION_ENABLED:false}
ingestion:
# The value of cliMajorVersion is substituted in by the processResources Gradle task.
enabled: ${UI_INGESTION_ENABLED:true}
defaultCliVersion: "${UI_INGESTION_DEFAULT_CLI_VERSION:@cliMajorVersion@}"
maxSerializedStringLength: "${INGESTION_MAX_SERIALIZED_STRING_LENGTH:16000000}" # Indicates the maximum allowed JSON String length Jackson will handle, impacts the maximum size of ingested aspects
telemetry:
enabledCli: ${CLI_TELEMETRY_ENABLED:true}
enabledIngestion: ${INGESTION_REPORTING_ENABLED:false}
enableThirdPartyLogging: ${ENABLE_THIRD_PARTY_LOGGING:false}
enabledServer: ${DATAHUB_TELEMETRY_ENABLED:true}
secretService:
encryptionKey: "#{systemEnvironment['SECRET_SERVICE_ENCRYPTION_KEY'] ?: 'ENCRYPTION_KEY'}"
datahub:
serverType: ${DATAHUB_SERVER_TYPE:prod}
gms:
host: ${DATAHUB_GMS_HOST:localhost}
port: ${DATAHUB_GMS_PORT:8080}
useSSL: ${DATAHUB_GMS_USE_SSL:${GMS_USE_SSL:false}}
# URI instead of above host/port/ssl
# Priority is given to the URI setting over separate host/port/useSSL parameters
uri: ${DATAHUB_GMS_URI:#{null}}
sslContext:
protocol: ${DATAHUB_GMS_SSL_PROTOCOL:${GMS_SSL_PROTOCOL:#{null}}}
plugin:
pluginSecurityMode: ${PLUGIN_SECURITY_MODE:RESTRICTED} # Possible value RESTRICTED or LENIENT, default to RESTRICTED
entityRegistry:
path: ${ENTITY_REGISTRY_PLUGIN_PATH:/etc/datahub/plugins/models}
retention:
path: ${RETENTION_PLUGIN_PATH:/etc/datahub/plugins/retention}
auth:
path: ${AUTH_PLUGIN_PATH:/etc/datahub/plugins/auth}
entityService:
impl: ${ENTITY_SERVICE_IMPL:ebean}
retention:
enabled: ${ENTITY_SERVICE_ENABLE_RETENTION:true}
applyOnBootstrap: ${ENTITY_SERVICE_APPLY_RETENTION_BOOTSTRAP:false}
graphService:
type: ${GRAPH_SERVICE_IMPL:elasticsearch}
searchService:
resultBatchSize: ${SEARCH_SERVICE_BATCH_SIZE:100}
enableCache: ${SEARCH_SERVICE_ENABLE_CACHE:false}
cacheImplementation: ${SEARCH_SERVICE_CACHE_IMPLEMENTATION:caffeine}
cache:
hazelcast:
serviceName: ${SEARCH_SERVICE_HAZELCAST_SERVICE_NAME:hazelcast-service}
configEntityRegistry:
path: ${ENTITY_REGISTRY_CONFIG_PATH:../../metadata-models/src/main/resources/entity-registry.yml}
# Priority is given to the `path` setting above (outside jar)
resource: ${ENTITY_REGISTRY_CONFIG_CLASSPATH:classpath:/entity-registry.yml}
platformAnalytics:
enabled: ${DATAHUB_ANALYTICS_ENABLED:true}
visualConfig:
queriesTab:
# Experimental! This env var is subject to change and may be deprecated in the future. The Queries tab has a larger
# overhaul coming.
queriesTabResultSize: ${REACT_APP_QUERIES_TAB_RESULT_SIZE:5}
assets:
logoUrl: ${REACT_APP_LOGO_URL:/assets/platforms/datahublogo.png}
faviconUrl: ${REACT_APP_FAVICON_URL:/assets/favicon.ico}
entityProfile:
# we only support default tab for domains right now. In order to implement for other entities, update React code
domainDefaultTab: ${DOMAIN_DEFAULT_TAB:} # set to DOCUMENTATION_TAB to show documentation tab first
searchResult:
enableNameHighlight: ${SEARCH_RESULT_NAME_HIGHLIGHT_ENABLED:true} # Enables visual highlighting on search result names/descriptions.
# Storage Layer
# Only required if entityService.impl is ebean
ebean:
username: ${EBEAN_DATASOURCE_USERNAME:datahub}
password: ${EBEAN_DATASOURCE_PASSWORD:datahub}
url: ${EBEAN_DATASOURCE_URL:jdbc:mysql://localhost:3306/datahub} # JDBC URL
driver: ${EBEAN_DATASOURCE_DRIVER:com.mysql.jdbc.Driver} # JDBC Driver
minConnections: ${EBEAN_MIN_CONNECTIONS:2}
maxConnections: ${EBEAN_MAX_CONNECTIONS:50}
maxInactiveTimeSeconds: ${EBEAN_MAX_INACTIVE_TIME_IN_SECS:120}
maxAgeMinutes: ${EBEAN_MAX_AGE_MINUTES:120}
leakTimeMinutes: ${EBEAN_LEAK_TIME_MINUTES:15}
waitTimeoutMillis: ${EBEAN_WAIT_TIMEOUT_MILLIS:1000}
autoCreateDdl: ${EBEAN_AUTOCREATE:false}
postgresUseIamAuth: ${EBEAN_POSTGRES_USE_AWS_IAM_AUTH:false}
# Only required if entityService.impl is cassandra
cassandra:
datasourceUsername: ${CASSANDRA_DATASOURCE_USERNAME:cassandra}
datasourcePassword: ${CASSANDRA_DATASOURCE_PASSWORD:cassandra}
hosts: ${CASSANDRA_HOSTS:cassandra}
port: ${CASSANDRA_PORT:9042}
datacenter: ${CASSANDRA_DATACENTER:datacenter1}
keyspace: ${CASSANDRA_KEYSPACE:datahub}
useSsl: ${CASSANDRA_USE_SSL:false}
elasticsearch:
host: ${ELASTICSEARCH_HOST:localhost}
port: ${ELASTICSEARCH_PORT:9200}
threadCount: ${ELASTICSEARCH_THREAD_COUNT:1}
connectionRequestTimeout: ${ELASTICSEARCH_CONNECTION_REQUEST_TIMEOUT:0}
username: ${ELASTICSEARCH_USERNAME:#{null}}
password: ${ELASTICSEARCH_PASSWORD:#{null}}
pathPrefix: ${ELASTICSEARCH_PATH_PREFIX:#{null}}
useSSL: ${ELASTICSEARCH_USE_SSL:false}
opensearchUseAwsIamAuth: ${OPENSEARCH_USE_AWS_IAM_AUTH:false}
region: ${AWS_REGION:#{null}}
implementation: ${ELASTICSEARCH_IMPLEMENTATION:elasticsearch} # elasticsearch or opensearch, for handling divergent cases
sslContext: # Required if useSSL is true
protocol: ${ELASTICSEARCH_SSL_PROTOCOL:#{null}}
secureRandomImplementation: ${ELASTICSEARCH_SSL_SECURE_RANDOM_IMPL:#{null}}
trustStoreFile: ${ELASTICSEARCH_SSL_TRUSTSTORE_FILE:#{null}}
trustStoreType: ${ELASTICSEARCH_SSL_TRUSTSTORE_TYPE:#{null}}
trustStorePassword: ${ELASTICSEARCH_SSL_TRUSTSTORE_PASSWORD:#{null}}
keyStoreFile: ${ELASTICSEARCH_SSL_KEYSTORE_FILE:#{null}}
keyStoreType: ${ELASTICSEARCH_SSL_KEYSTORE_TYPE:#{null}}
keyStorePassword: ${ELASTICSEARCH_SSL_KEYSTORE_PASSWORD:#{null}}
keyPassword: ${ELASTICSEARCH_SSL_KEY_PASSWORD:#{null}}
bulkProcessor:
async: ${ES_BULK_ASYNC:true}
requestsLimit: ${ES_BULK_REQUESTS_LIMIT:1000}
flushPeriod: ${ES_BULK_FLUSH_PERIOD:1}
numRetries: ${ES_BULK_NUM_RETRIES:3}
retryInterval: ${ES_BULK_RETRY_INTERVAL:1}
refreshPolicy: ${ES_BULK_REFRESH_POLICY:NONE}
enableBatchDelete: ${ES_BULK_ENABLE_BATCH_DELETE:false}
index:
prefix: ${INDEX_PREFIX:}
numShards: ${ELASTICSEARCH_NUM_SHARDS_PER_INDEX:1}
numReplicas: ${ELASTICSEARCH_NUM_REPLICAS_PER_INDEX:1}
numRetries: ${ELASTICSEARCH_INDEX_BUILDER_NUM_RETRIES:3}
refreshIntervalSeconds: ${ELASTICSEARCH_INDEX_BUILDER_REFRESH_INTERVAL_SECONDS:1} # increase to 30 if expected indexing rates to be greater than 100/s
maxArrayLength: ${SEARCH_DOCUMENT_MAX_ARRAY_LENGTH:1000}
maxObjectKeys: ${SEARCH_DOCUMENT_MAX_OBJECT_KEYS:1000}
maxValueLength: ${SEARCH_DOCUMENT_MAX_VALUE_LENGTH:4096} # i.e. customProperty values
mainTokenizer: ${ELASTICSEARCH_MAIN_TOKENIZER:#{null}}
enableMappingsReindex: ${ELASTICSEARCH_INDEX_BUILDER_MAPPINGS_REINDEX:false}
enableSettingsReindex: ${ELASTICSEARCH_INDEX_BUILDER_SETTINGS_REINDEX:false}
settingsOverrides: ${ELASTICSEARCH_INDEX_BUILDER_SETTINGS_OVERRIDES:#{null}}
entitySettingsOverrides: ${ELASTICSEARCH_INDEX_BUILDER_ENTITY_SETTINGS_OVERRIDES:#{null}}
buildIndices:
allowDocCountMismatch: ${ELASTICSEARCH_BUILD_INDICES_ALLOW_DOC_COUNT_MISMATCH:false} # when cloneIndices is also enabled
cloneIndices: ${ELASTICSEARCH_BUILD_INDICES_CLONE_INDICES:true}
retentionUnit: ${ELASTICSEARCH_BUILD_INDICES_RETENTION_UNIT:DAYS}
retentionValue: ${ELASTICSEARCH_BUILD_INDICES_RETENTION_VALUE:60}
search:
maxTermBucketSize: ${ELASTICSEARCH_QUERY_MAX_TERM_BUCKET_SIZE:20}
# Defines the behavior of quoted searches, do they apply weights or exclude results
exactMatch:
exclusive: ${ELASTICSEARCH_QUERY_EXACT_MATCH_EXCLUSIVE:false} # if false will only apply weights, if true will exclude non-exact
withPrefix: ${ELASTICSEARCH_QUERY_EXACT_MATCH_WITH_PREFIX:true} # include prefix exact matches
exactFactor: ${ELASTICSEARCH_QUERY_EXACT_MATCH_FACTOR:10.0} # boost multiplier when exact with case
prefixFactor: ${ELASTICSEARCH_QUERY_EXACT_MATCH_PREFIX_FACTOR:1.6} # boost multiplier when exact prefix
caseSensitivityFactor: ${ELASTICSEARCH_QUERY_EXACT_MATCH_CASE_FACTOR:0.7} # stacked boost multiplier when case mismatch
enableStructured: ${ELASTICSEARCH_QUERY_EXACT_MATCH_ENABLE_STRUCTURED:true} # enable exact match on structured search
wordGram:
twoGramFactor: ${ELASTICSEARCH_QUERY_TWO_GRAM_FACTOR:1.2} # boost multiplier when match on 2-gram tokens
threeGramFactor: ${ELASTICSEARCH_QUERY_THREE_GRAM_FACTOR:1.5} # boost multiplier when match on 3-gram tokens
fourGramFactor: ${ELASTICSEARCH_QUERY_FOUR_GRAM_FACTOR:1.8} # boost multiplier when match on 4-gram tokens
# Field weight annotations are typically calibrated for exact match, if partial match is possible on the field use these adjustments
partial:
urnFactor: ${ELASTICSEARCH_QUERY_PARTIAL_URN_FACTOR:0.5} # multiplier on Urn token match, a partial match on Urn > non-Urn is assumed
factor: ${ELASTICSEARCH_QUERY_PARTIAL_FACTOR:0.4} # multiplier on possible non-Urn token match
custom:
enabled: ${ELASTICSEARCH_QUERY_CUSTOM_CONFIG_ENABLED:false}
file: ${ELASTICSEARCH_QUERY_CUSTOM_CONFIG_FILE:search_config.yml}
graph:
timeoutSeconds: ${ELASTICSEARCH_SEARCH_GRAPH_TIMEOUT_SECONDS:50} # graph dao timeout seconds
batchSize: ${ELASTICSEARCH_SEARCH_GRAPH_BATCH_SIZE:1000} # graph dao batch size
maxResult: ${ELASTICSEARCH_SEARCH_GRAPH_MAX_RESULT:10000} # graph dao max result size
# TODO: Kafka topic convention
kafka:
listener:
concurrency: ${KAFKA_LISTENER_CONCURRENCY:1}
bootstrapServers: ${KAFKA_BOOTSTRAP_SERVER:http://localhost:9092}
producer:
retryCount: ${KAFKA_PRODUCER_RETRY_COUNT:3}
deliveryTimeout: ${KAFKA_PRODUCER_DELIVERY_TIMEOUT:30000}
requestTimeout: ${KAFKA_PRODUCER_REQUEST_TIMEOUT:3000}
backoffTimeout: ${KAFKA_PRODUCER_BACKOFF_TIMEOUT:500}
compressionType: ${KAFKA_PRODUCER_COMPRESSION_TYPE:snappy} # producer's compression algorithm
maxRequestSize: ${KAFKA_PRODUCER_MAX_REQUEST_SIZE:5242880} # the max bytes sent by the producer, also see kafka-setup MAX_MESSAGE_BYTES for matching value
consumer:
maxPartitionFetchBytes: ${KAFKA_CONSUMER_MAX_PARTITION_FETCH_BYTES:5242880} # the max bytes consumed per partition
schemaRegistry:
type: ${SCHEMA_REGISTRY_TYPE:KAFKA} # INTERNAL or KAFKA or AWS_GLUE
url: ${KAFKA_SCHEMAREGISTRY_URL:http://localhost:8081}
awsGlue:
region: ${AWS_GLUE_SCHEMA_REGISTRY_REGION:us-east-1}
registryName: ${AWS_GLUE_SCHEMA_REGISTRY_NAME:#{null}}
schema:
registry:
security:
protocol: ${KAFKA_PROPERTIES_SECURITY_PROTOCOL:PLAINTEXT}
# Only required if GraphService type is neo4j
neo4j:
username: ${NEO4J_USERNAME:neo4j}
password: ${NEO4J_PASSWORD:datahub}
uri: ${NEO4J_URI:bolt://localhost}
database: ${NEO4J_DATABASE:graph.db}
maxConnectionPoolSize: ${NEO4J_MAX_CONNECTION_POOL_SIZE:100}
maxConnectionAcquisitionTimeout: ${NEO4J_MAX_CONNECTION_ACQUISITION_TIMEOUT_IN_SECONDS:60}
maxConnectionLifetimeInSeconds: ${NEO4j_MAX_CONNECTION_LIFETIME_IN_SECONDS:3600}
maxTransactionRetryTime: ${NEO4J_MAX_TRANSACTION_RETRY_TIME_IN_SECONDS:30}
connectionLivenessCheckTimeout: ${NEO4J_CONNECTION_LIVENESS_CHECK_TIMEOUT_IN_SECONDS:-1}
spring:
mvc:
servlet:
path: /openapi
kafka:
security:
protocol: ${KAFKA_PROPERTIES_SECURITY_PROTOCOL:PLAINTEXT}
springdoc:
cache:
disabled: true
metadataTests:
enabled: ${METADATA_TESTS_ENABLED:false}
siblings:
enabled: ${ENABLE_SIBLING_HOOK:true} # enable to turn on automatic sibling associations for dbt
updateIndices:
enabled: ${ENABLE_UPDATE_INDICES_HOOK:true}
ingestionScheduler:
enabled: ${ENABLE_INGESTION_SCHEDULER_HOOK:true} # enable to execute ingestion scheduling
bootstrap:
upgradeDefaultBrowsePaths:
enabled: ${UPGRADE_DEFAULT_BROWSE_PATHS_ENABLED:false} # enable to run the upgrade to migrate legacy default browse paths to new ones
backfillBrowsePathsV2:
enabled: ${BACKFILL_BROWSE_PATHS_V2:false} # Enables running the backfill of browsePathsV2 upgrade step. There are concerns about the load of this step so hiding it behind a flag. Deprecating in favor of running through SystemUpdate
reprocessDefaultBrowsePathsV2:
enabled: ${REPROCESS_DEFAULT_BROWSE_PATHS_V2:false} # reprocess V2 browse paths which were set to the default: {"path":[{"id":"Default"}]}
policies:
file: ${BOOTSTRAP_POLICIES_FILE:classpath:boot/policies.json}
# eg for local file
# file: "file:///datahub/datahub-gms/resources/custom-policies.json"
servlets:
waitTimeout: ${BOOTSTRAP_SERVLETS_WAITTIMEOUT:60} # Total waiting time in seconds for servlets to initialize
systemUpdate:
initialBackOffMs: ${BOOTSTRAP_SYSTEM_UPDATE_INITIAL_BACK_OFF_MILLIS:5000}
maxBackOffs: ${BOOTSTRAP_SYSTEM_UPDATE_MAX_BACK_OFFS:50}
backOffFactor: ${BOOTSTRAP_SYSTEM_UPDATE_BACK_OFF_FACTOR:2} # Multiplicative factor for back off, default values will result in waiting 5min 15s
waitForSystemUpdate: ${BOOTSTRAP_SYSTEM_UPDATE_WAIT_FOR_SYSTEM_UPDATE:true}
healthCheck:
cacheDurationSeconds: ${HEALTH_CHECK_CACHE_DURATION_SECONDS:5}
featureFlags:
showSimplifiedHomepageByDefault: ${SHOW_SIMPLIFIED_HOMEPAGE_BY_DEFAULT:false} # shows a simplified homepage with just datasets, charts and dashboards by default to users. this can be configured in user settings
lineageSearchCacheEnabled: ${LINEAGE_SEARCH_CACHE_ENABLED:true} # Enables in-memory cache for searchAcrossLineage query
graphServiceDiffModeEnabled: ${GRAPH_SERVICE_DIFF_MODE_ENABLED:true} # 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
pointInTimeCreationEnabled: ${POINT_IN_TIME_CREATION_ENABLED:false} # Enables creation of point in time snapshots for the scroll API, only works with main line ElasticSearch releases after 7.10. OpenSearch is unsupported, plans to eventually target OpenSearch 2.4+ with a divergent client
alwaysEmitChangeLog: ${ALWAYS_EMIT_CHANGE_LOG:false} # Enables always emitting a MCL even when no changes are detected. Used for Time Based Lineage when no changes occur.
searchServiceDiffModeEnabled: ${SEARCH_SERVICE_DIFF_MODE_ENABLED:true} # Enables diff mode for search document writes, reduces amount of writes to ElasticSearch documents for no-ops
readOnlyModeEnabled: ${READ_ONLY_MODE_ENABLED:false} # Enables read only mode for an instance. Right now this only affects ability to edit user profile image URL but can be extended
showAccessManagement: ${SHOW_ACCESS_MANAGEMENT:false} #Whether we should show AccessManagement tab in the datahub UI.
showSearchFiltersV2: ${SHOW_SEARCH_FILTERS_V2:true} # Enables showing the search filters V2 experience.
showBrowseV2: ${SHOW_BROWSE_V2:true} # Enables showing the browse v2 sidebar experience.
preProcessHooks:
uiEnabled: ${PRE_PROCESS_HOOKS_UI_ENABLED:true} # Circumvents Kafka for processing index updates for UI changes sourced from GraphQL to avoid processing delays
showAcrylInfo: ${SHOW_ACRYL_INFO:false} # Show different CTAs within DataHub around moving to Managed DataHub. Set to true for the demo site.
nestedDomainsEnabled: ${NESTED_DOMAINS_ENABLED:true} # Enables the nested Domains feature that allows users to have sub-Domains. If this is off, Domains appear "flat" again
entityChangeEvents:
enabled: ${ENABLE_ENTITY_CHANGE_EVENTS_HOOK:true}
views:
enabled: ${VIEWS_ENABLED:true}
entityClient:
retryInterval: ${ENTITY_CLIENT_RETRY_INTERVAL:2}
numRetries: ${ENTITY_CLIENT_NUM_RETRIES:3}
usageClient:
retryInterval: ${USAGE_CLIENT_RETRY_INTERVAL:2}
numRetries: ${USAGE_CLIENT_NUM_RETRIES:0}
timeoutMs: ${USAGE_CLIENT_TIMEOUT_MS:3000}
cache:
primary:
ttlSeconds: ${CACHE_TTL_SECONDS:600}
maxSize: ${CACHE_MAX_SIZE:10000}
homepage:
entityCounts:
ttlSeconds: ${CACHE_ENTITY_COUNTS_TTL_SECONDS:600}
search:
lineage:
ttlSeconds: ${CACHE_SEARCH_LINEAGE_TTL_SECONDS:86400} # 1 day
lightningThreshold: ${CACHE_SEARCH_LINEAGE_LIGHTNING_THRESHOLD:300}
client:
usageClient:
enabled: ${CACHE_CLIENT_USAGE_CLIENT_ENABLED:true}
statsEnabled: ${CACHE_CLIENT_USAGE_CLIENT_STATS_ENABLED:true}
statsIntervalSeconds: ${CACHE_CLIENT_USAGE_CLIENT_STATS_INTERVAL_SECONDS:120}
defaultTTLSeconds: ${CACHE_CLIENT_USAGE_CLIENT_TTL_SECONDS:86400} # 1 day
maxBytes: ${CACHE_CLIENT_USAGE_CLIENT_MAX_BYTES:52428800} # 50MB
entityClient:
enabled: ${CACHE_CLIENT_ENTITY_CLIENT_ENABLED:true}
statsEnabled: ${CACHE_CLIENT_ENTITY_CLIENT_STATS_ENABLED:true}
statsIntervalSeconds: ${CACHE_CLIENT_ENTITY_CLIENT_STATS_INTERVAL_SECONDS:120}
defaultTTLSeconds: ${CACHE_CLIENT_ENTITY_CLIENT_TTL_SECONDS:0} # do not cache entity/aspects by default
maxBytes: ${CACHE_CLIENT_ENTITY_CLIENT_MAX_BYTES:104857600} # 100MB
entityAspectTTLSeconds:
# cache user aspects for 20s
corpuser:
corpUserKey: 20
corpUserInfo: 20
corpUserEditableInfo: 20
corpUserStatus: 20
globalTags: 20
status: 20
corpUserCredentials: 20
corpUserSettings: 20
springdoc.api-docs.groups.enabled: true