Configure MiniIO for druid deep storage

helmcharts/bootstrapper/values.yaml

@@ -10,6 +10,7 @@ namespaces:
 - kong-ingress
 - kubernetes-reflector
 - loki
+- minio
 - monitoring
 - postgresql
 - redis

helmcharts/global-values.yaml

@@ -27,8 +27,9 @@ defaults:
     volume_autoscaler_namespace: &volume-autoscaler-namespace "volume-autoscaler"
     hms_namespace: &hms_namespace "hms"
     trino_namespace: &trino_namespace "trino"
+    minio_namespace: &minio_namespace "minio"
     opentelemetry-collector: &opentelemetry-collector "otel"
-    
+
   postgres:
     pghost: &pghost "postgresql-hl.postgresql.svc.cluster.local"
     obsrv_username: &psql-obsrv-user "obsrv"
@@ -479,6 +480,10 @@ trino:
 lakehouse-connector:
   namespace: *flink_namespace
 
+minio:
+  namespace: *minio_namespace
+  fullnameOverride: "minio"
+
 global:
   env: *env
   building_block: *building-block

helmcharts/images.yaml

@@ -275,6 +275,12 @@ images: &images
     tag: 3.6.0
     digest: ""
 
+  minio: &minio
+    registry: docker.io
+    repository: bitnami/minio
+    tag: 2024.11.7-debian-12-r0
+    digest: ""
+
   # kafka-connector: &kafka-connector
   #   # registry: ""
   #   # repository: kafka-connector
@@ -540,7 +546,11 @@ internal: &internal
   lakehouse-connector:
     image:
       <<: *lakehouse-connector
-
+
+  minio:
+    image:
+      <<: *minio
+
   opentelemetry-collector:
     image:
     <<: *opentelemetry-collector

helmcharts/kitchen/install.sh

@@ -97,6 +97,12 @@ additional)
     "azure")
         cp -rf ../services/azure-exporter additional/charts/
         ;;
+    "gcp")
+        echo "No additional services for GCP."
+        ;;    
+    *)
+        cp -rf ../services/minio additional/charts/
+        ;;
     esac
 
     helm $cmd additional ./additional -n obsrv -f global-resource-values.yaml -f global-values.yaml -f images.yaml -f $cloud_file_name --debug

helmcharts/local-datacenter.yaml

@@ -11,14 +11,14 @@ global:
   storage_provider: &storage_provider "aws"
   cloud_storage_region: "us-east-2"
 
-  s3_bucket: &s3-bucket "obsrv-data"
-  s3_access_key: &s3-access-key "7xSgQhiRnJg3pUzvIiBV"
-  s3_secret_key: &s3-secret-access-key "4R4n5Hz8vcJLjWvtWAuQSR1tQzwCFMIBFpT26Au3"
+  s3_bucket: &s3-bucket "druid-storage"
+  s3_access_key: &s3-access-key "minioadmin"
+  s3_secret_key: &s3-secret-access-key "198CImxTlly79Dx9ZCDJ"
   region: &region "ap-south-1"
-  s3_endpoint_url: &s3-endpoint-url "http://192.168.1.2:9000"
+  s3_endpoint_url: &s3-endpoint-url "http://minio.minio.svc.cluster.local:9000"
   s3_path_style_access: &s3-path-style-access "true"
   s3_protocol: &s3-protocol "http"
-  s3_signing_region: &s3-signing-region "ap-south-1"
+  s3_signing_region: &s3-signing-region "us-east-1"
   backup_bucket: &backup_bucket ""
   checkpoint_bucket: &checkpoint_bucket ""
 
@@ -49,7 +49,9 @@ druid-raw-cluster:
   s3_access_key: *s3-access-key
   s3_secret_key: *s3-secret-access-key
   druid_s3_endpoint_url: *s3-endpoint-url
-  druid_s3_endpoint_signingRegion: *s3-path-style-access
+  druid_s3_endpoint_signingRegion: *s3-signing-region
+  druid_s3_protocol: *s3-protocol
+  druid_s3_path_style_access: *s3-path-style-access
 
 kafka:
   persistence:

helmcharts/services/druid-raw-cluster/templates/druid_statefulset.yaml

@@ -76,6 +76,8 @@ spec:
     druid.storage.baseKey={{ .Values.druid_storage_baseKey }}
     druid.s3.endpoint.url={{ .Values.druid_s3_endpoint_url }}
     druid.s3.endpoint.signingRegion={{ .Values.druid_s3_endpoint_signingRegion }}
+    druid.s3.protocol={{ .Values.druid_s3_protocol }}
+    druid.s3.enablePathStyleAccess={{ .Values.druid_s3_path_style_access }}
     # Azure
     druid.azure.account = {{ .Values.global.azure_storage_account_name }}
     druid.azure.key = {{ .Values.global.azure_storage_account_key }}
@@ -128,7 +130,7 @@ spec:
     druid.request.logging.type={{ .Values.druid_request_logging_type }}
     druid.request.logging.dir={{ .Values.druid_request_logging_dir }}
     druid.javascript.enabled=true
-    druid.sql.enable={{ .Values.druid_sql_enable }}
+    druid.sql.enable={{ .Values.druid_sql_enable }} 
   env:
     - name: POD_NAME
       valueFrom:
@@ -152,7 +154,6 @@ spec:
       runtime.properties: |
         druid.service={{ .Values.druid_broker_service }}
         # HTTP server threads
-        #testing
         druid.broker.http.numConnections={{ .Values.druid_broker_http_numConnections }}
         druid.server.http.numThreads={{ .Values.druid_broker_http_numThreads }}
         # Processing threads and buffers
@@ -212,7 +213,6 @@ spec:
       extra.jvm.options: |-
         -Xms{{ .Values.druid_coordinator_min_heap_size }}
         -Xmx{{ .Values.druid_coordinator_max_heap_size }}
-
       readinessProbe:
         httpGet:
           path: /status/health
@@ -521,4 +521,4 @@ spec:
         #   cpu: {{ .Values.druid_router_pod_cpu_request }}
         # limits:
         #   memory: {{ .Values.druid_router_pod_memory_limit }}
-        #   cpu: {{ .Values.druid_router_pod_cpu_limit }}
+        #   cpu: {{ .Values.druid_router_pod_cpu_limit }}

helmcharts/services/druid-raw-cluster/values.yaml

@@ -40,6 +40,8 @@ s3_bucket: "" # bucket name
 druid_storage_baseKey: druid/segments
 druid_s3_endpoint_url: ""
 druid_s3_endpoint_signingRegion: ""
+druid_s3_protocol: "https"
+druid_s3_path_style_access: "false"
 
 # Azure Container Details
 azure_storage_account_name: ""

helmcharts/services/minio/.helmignore

@@ -0,0 +1,25 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+# img folder
+img/
+# Changelog
+CHANGELOG.md