feat: add configuration options for Kafka consumer groups

charts/datahub/Chart.yaml

@@ -4,33 +4,33 @@ description: A Helm chart for DataHub
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.4.33
+version: 0.4.34
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: 0.14.1
 dependencies:
   - name: datahub-gms
-    version: 0.2.174
+    version: 0.2.175
     repository: file://./subcharts/datahub-gms
     condition: datahub-gms.enabled
   - name: datahub-frontend
-    version: 0.2.160
+    version: 0.2.161
     repository: file://./subcharts/datahub-frontend
     condition: datahub-frontend.enabled
   - name: datahub-mae-consumer
-    version: 0.2.162
+    version: 0.2.163
     repository: file://./subcharts/datahub-mae-consumer
     condition: global.datahub_standalone_consumers_enabled
   - name: datahub-mce-consumer
-    version: 0.2.165
+    version: 0.2.166
     repository: file://./subcharts/datahub-mce-consumer
     condition: global.datahub_standalone_consumers_enabled
   - name: datahub-ingestion-cron
     version: 0.2.146
     repository: file://./subcharts/datahub-ingestion-cron
     condition: datahub-ingestion-cron.enabled
   - name: acryl-datahub-actions
-    version: 0.2.148
+    version: 0.2.149
     repository: file://./subcharts/acryl-datahub-actions
     condition: acryl-datahub-actions.enabled
 maintainers:

charts/datahub/README.md

@@ -116,6 +116,17 @@ helm install datahub datahub/datahub --values <<path-to-values-file>>
 | global.kafka.bootstrap.server                                  | string  | `"prerequisites-broker:9092"`                                                                    | Kafka bootstrap servers (with port)                                                                                                                     |
 | global.kafka.zookeeper.server                                  | string  | `"prerequisites-zookeeper:2181"`                                                                 | Kafka zookeeper servers (with port)                                                                                                                     |
 | global.kafka.consumer.stopContainerOnDeserializationError      | boolean | `true`                                                                                           | Determines whether or not to halt progress when encountering a deserialization error, halting prevents data loss but prevents progress until fixed      |
+| global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id.gms | string  | `"<<release-name>>-duhe-consumer-job-client-gms"`                              | Consumer group id for consuming DataHub Upgrade history events by the GMS                                                                                |
+| global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id.mae-consumer | string  | `"<<release-name>>-duhe-consumer-job-client-mcl"`                     | Consumer group id for consuming DataHub Upgrade history events by the MAE consumer          
+| global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id.mce-consumer | string  | `"<<release-name>>-duhe-consumer-job-client-mcp"`                     | Consumer group id for consuming DataHub Upgrade history events by the MCE consumer                                                                       |
+| global.kafka.consumer_groups.datahub_actions_ingestion_executor_consumer_group_id | string  | `"ingestion_executor"`                                                        | Consumer group id for consuming events by DataHub Actions ingestion executor pipeline                                                                    |
+| global.kafka.consumer_groups.datahub_actions_slack_consumer_group_id | string  | `"datahub_slack_action"`                                                                   | Consumer group id for consuming events by DataHub Actions slack action pipeline                                                                          |
+| global.kafka.consumer_groups.datahub_actions_teams_consumer_group_id | string  | `"datahub_teams_action"`                                                                   | Consumer group id for consuming events by DataHub Actions teams action pipeline                                                                          |
+| global.kafka.consumer_groups.datahub_usage_event_kafka_consumer_group_id | string  | `"datahub-usage-event-consumer-job-client"`                                            | Consumer group id for consuming DataHub Usage events by the GMS or MAE consumer                                                                          |
+| global.kafka.consumer_groups.metadata_change_log_kafka_consumer_group_id | string  | `"generic-mae-consumer-job-client"`                                                    | Consumer group id for consuming Metadata Change Log events by the GMS or MAE consumer                                                                    |
+| global.kafka.consumer_groups.platform_event_kafka_consumer_group_id | string  | `"generic-platform-event-job-client"`                                                       | Consumer group id for consuming Platform events by the GMS or MAE consumer                                                                               |
+| global.kafka.consumer_groups.metadata_change_event_kafka_consumer_group_id | string  | `"mce-consumer-job-client"`                                                          | Consumer group id for consuming Metadata Change events by the GMS or MCE consumer                                                                        |
+| global.kafka.consumer_groups.metadata_change_proposal_kafka_consumer_group_id | string  | `"generic-mce-consumer-job-client"`                                               | Consumer group id for consuming Metadata Change Proposal events by the GMS or MCE consumer                                                               |
 | global.kafka.topics.metadata_change_event_name                 | string  | `"MetadataChangeEvent_v4"`                                                                       | Kafka topic name for Metadata Change Events (deprecated)                                                                                                |
 | global.kafka.topics.failed_metadata_change_event_name          | string  | `"FailedMetadataChangeEvent_v4"`                                                                 | Kafka topic name for Failed Metadata Change events (deprecated)                                                                                         |
 | global.kafka.topics.metadata_audit_event_name                  | string  | `"MetadataAuditEvent_v4"`                                                                        | Kafka topic name for Metadata Audit events (deprecated)                                                                                                 |
@@ -125,6 +136,7 @@ helm install datahub datahub/datahub --values <<path-to-values-file>>
 | global.kafka.topics.metadata_change_log_versioned_topic_name   | string  | `"MetadataChangeLog_Versioned_v1"`                                                               | Kafka topic name for Versioned Metadata Change Log events                                                                                               |
 | global.kafka.topics.metadata_change_log_timeseries_topic_name  | string  | `"MetadataChangeLog_Timeseries_v1"`                                                              | Kafka topic name for Timeseries Metadata Change Log events                                                                                              |
 | global.kafka.topics.platform_event_topic_name                  | string  | `"PlatformEvent_v1"`                                                                             | Kafka topic name for Platform events                                                                                                                    |
+| global.kafka.topics.datahub_upgrade_history_topic_name         | string  | `"DataHubUpgradeHistory_v1"`                                                                     | Kafka topic name for DataHub Upgrade History events                                                                                                     |
 | global.kafka.schemaregistry.url                                | string  | ``                                                                                               | URL to kafka schema registry if using `KAFKA` type                                                                                                      |
 | global.neo4j.host                                              | string  | `"prerequisites-neo4j:7474"`                                                                     | Neo4j host address (with port)                                                                                                                          |
 | global.neo4j.uri                                               | string  | `"bolt://prerequisites-neo4j"`                                                                   | Neo4j URI                                                                                                                                               |

charts/datahub/subcharts/acryl-datahub-actions/Chart.yaml

@@ -12,7 +12,7 @@ description: A Helm chart for Kubernetes
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.2.148
+version: 0.2.149
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: 0.1.1

charts/datahub/subcharts/acryl-datahub-actions/templates/deployment.yaml

@@ -142,6 +142,14 @@ spec:
             - name: PLATFORM_EVENT_TOPIC_NAME
               value: {{ .platform_event_topic_name }}
             {{- end }}
+            {{- with .Values.global.kafka.consumer_groups }}
+            - name: DATAHUB_ACTIONS_INGESTION_EXECUTOR_CONSUMER_GROUP_ID
+              value: {{ .datahub_actions_ingestion_executor_consumer_group_id }}
+            - name: DATAHUB_ACTIONS_SLACK_CONSUMER_GROUP_ID
+              value: {{ .datahub_actions_slack_consumer_group_id }}
+            - name: DATAHUB_ACTIONS_TEAMS_CONSUMER_GROUP_ID
+              value: {{ .datahub_actions_teams_consumer_group_id }}
+            {{- end }}
             {{- if .Values.global.datahub.metadata_service_authentication.enabled }}
             - name: DATAHUB_SYSTEM_CLIENT_ID
               value: {{ .Values.global.datahub.metadata_service_authentication.systemClientId }}

charts/datahub/subcharts/datahub-frontend/Chart.yaml

@@ -12,7 +12,7 @@ description: A Helm chart for Kubernetes
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.2.160
+version: 0.2.161
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: v0.13.1
+appVersion: v0.14.1

charts/datahub/subcharts/datahub-gms/Chart.yaml

@@ -12,7 +12,7 @@ description: A Helm chart for DataHub's datahub-gms component
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.2.174
+version: 0.2.175
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: v0.14.1

charts/datahub/subcharts/datahub-gms/templates/deployment.yaml

@@ -129,8 +129,6 @@ spec:
               value: {{ printf "%s-%s-%s" .Release.Name (regexReplaceAll "[^-a-z0-9]+" .Values.global.datahub.version "-") "hazelcast-svc" | trunc 63 | trimSuffix "-" }}
             {{- end }}
             {{- if .Values.global.datahub.systemUpdate.enabled }}
-            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
-              value: {{ printf "%s-%s" .Release.Name "duhe-consumer-job-client-gms" }}
             - name: DATAHUB_REVISION
               value: {{ .Release.Revision | quote }}
             {{- end }}
@@ -294,6 +292,24 @@ spec:
             - name: DATAHUB_UPGRADE_HISTORY_TOPIC_NAME
               value: {{ .datahub_upgrade_history_topic_name }}
             {{- end }}
+            {{- if .Values.global.datahub.systemUpdate.enabled }}
+            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .Values.global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id.gms | default (printf "%s-%s" .Release.Name "duhe-consumer-job-client-gms") }}
+            {{- end }}
+            {{- if not .Values.global.datahub_standalone_consumers_enabled }}
+            {{- with .Values.global.kafka.consumer_groups }}
+            - name: DATAHUB_USAGE_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .datahub_usage_event_kafka_consumer_group_id }}
+            - name: METADATA_CHANGE_LOG_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_log_kafka_consumer_group_id }}
+            - name: PLATFORM_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .platform_event_kafka_consumer_group_id }}
+            - name: METADATA_CHANGE_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_event_kafka_consumer_group_id }}
+            - name: METADATA_CHANGE_PROPOSAL_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_proposal_kafka_consumer_group_id }}
+            {{- end }}
+            {{- end }}
             {{- if .Values.global.datahub.metadata_service_authentication.enabled }}
             - name: METADATA_SERVICE_AUTH_ENABLED
               value: "true"

charts/datahub/subcharts/datahub-mae-consumer/Chart.yaml

@@ -12,7 +12,7 @@ description: A Helm chart for Kubernetes
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.2.162
+version: 0.2.163
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: v0.14.1

charts/datahub/subcharts/datahub-mae-consumer/templates/deployment.yaml

@@ -100,8 +100,6 @@ spec:
             - name: BACKFILL_BROWSE_PATHS_V2
               value: {{ .Values.global.datahub.search_and_browse.backfill_browse_v2 | quote }}
             {{- if .Values.global.datahub.systemUpdate.enabled }}
-            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
-              value: {{ printf "%s-%s" .Release.Name "duhe-consumer-job-client-mcl" }}
             - name: DATAHUB_REVISION
               value: {{ .Release.Revision | quote }}
             {{- end }}
@@ -256,6 +254,18 @@ spec:
             - name: DATAHUB_UPGRADE_HISTORY_TOPIC_NAME
               value: {{ .datahub_upgrade_history_topic_name }}
             {{- end }}
+            {{- if .Values.global.datahub.systemUpdate.enabled }}
+            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
+              value: {{ index .Values.global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id "mae-consumer" | default (printf "%s-%s" .Release.Name "duhe-consumer-job-client-mcl")  }}
+            {{- end }}
+            {{- with .Values.global.kafka.consumer_groups }}
+            - name: DATAHUB_USAGE_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .datahub_usage_event_kafka_consumer_group_id }}
+            - name: METADATA_CHANGE_LOG_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_log_kafka_consumer_group_id }}
+            - name: PLATFORM_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .platform_event_kafka_consumer_group_id }}
+            {{- end }}
             - name: ALWAYS_EMIT_CHANGE_LOG
               value: {{ .Values.global.datahub.alwaysEmitChangeLog | quote }}
             - name: GRAPH_SERVICE_DIFF_MODE_ENABLED

charts/datahub/subcharts/datahub-mce-consumer/Chart.yaml

@@ -12,7 +12,7 @@ description: A Helm chart for Kubernetes
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.2.165
+version: 0.2.166
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: v0.14.1

charts/datahub/subcharts/datahub-mce-consumer/templates/deployment.yaml

@@ -104,8 +104,6 @@ spec:
             - name: BACKFILL_BROWSE_PATHS_V2
               value: {{ .Values.global.datahub.search_and_browse.backfill_browse_v2 | quote }}
             {{- if .Values.global.datahub.systemUpdate.enabled }}
-            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
-              value: {{ printf "%s-%s" .Release.Name "duhe-consumer-job-client-mcp" }}
             - name: DATAHUB_REVISION
               value: {{ .Release.Revision | quote }}
             {{- end }}
@@ -269,6 +267,16 @@ spec:
             - name: DATAHUB_UPGRADE_HISTORY_TOPIC_NAME
               value: {{ .datahub_upgrade_history_topic_name }}
             {{- end }}
+            {{- if .Values.global.datahub.systemUpdate.enabled }}
+            - name: DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID
+              value: {{ index .Values.global.kafka.consumer_groups.datahub_upgrade_history_kafka_consumer_group_id "mce-consumer" | default (printf "%s-%s" .Release.Name "duhe-consumer-job-client-mcp")  }}
+            {{- end }}
+            {{- with .Values.global.kafka.consumer_groups }}
+            - name: METADATA_CHANGE_EVENT_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_event_kafka_consumer_group_id }}
+            - name: METADATA_CHANGE_PROPOSAL_KAFKA_CONSUMER_GROUP_ID
+              value: {{ .metadata_change_proposal_kafka_consumer_group_id }}
+            {{- end }}
             - name: ALWAYS_EMIT_CHANGE_LOG
               value: {{ .Values.global.datahub.alwaysEmitChangeLog | quote }}
             - name: GRAPH_SERVICE_DIFF_MODE_ENABLED

charts/datahub/values.yaml

@@ -628,6 +628,19 @@ global:
       metadata_change_log_timeseries_topic_name: "MetadataChangeLog_Timeseries_v1"
       platform_event_topic_name: "PlatformEvent_v1"
       datahub_upgrade_history_topic_name: "DataHubUpgradeHistory_v1"
+    consumer_groups:
+      datahub_upgrade_history_kafka_consumer_group_id: {}
+      #   gms: "<<release-name>>-duhe-consumer-job-client-gms"
+      #   mae-consumer: "<<release-name>>-duhe-consumer-job-client-mcl"
+      #   mce-consumer: "<<release-name>>-duhe-consumer-job-client-mcp"
+      datahub_actions_ingestion_executor_consumer_group_id: "ingestion_executor"
+      datahub_actions_slack_consumer_group_id: "datahub_slack_action"
+      datahub_actions_teams_consumer_group_id: "datahub_teams_action"
+      datahub_usage_event_kafka_consumer_group_id: "datahub-usage-event-consumer-job-client"
+      metadata_change_log_kafka_consumer_group_id: "generic-mae-consumer-job-client"
+      platform_event_kafka_consumer_group_id: "generic-platform-event-job-client"
+      metadata_change_event_kafka_consumer_group_id: "mce-consumer-job-client"
+      metadata_change_proposal_kafka_consumer_group_id: "generic-mce-consumer-job-client"
     metadataChangeLog:
       hooks:
         siblings: