druid-k8s-s3.yaml

apiVersion: "druid.apache.org/v1alpha1"
kind: "Druid"
metadata:
  name: druid-cluster
spec:
  image: apache/druid:0.21.1
  # Optionally specify image for all nodes. Can be specify on nodes also
  # imagePullSecrets:
  # - name: tutu
  startScript: /druid.sh
  podLabels:
    environment: stage
    release: alpha
  podAnnotations:
    annotation: "precisa existir um podAnnotations e label para o plugin do k8s funcionar"
  readinessProbe:
    httpGet:
      path: /status/health
      port: 8088
  securityContext:
    fsGroup: 1000
    runAsUser: 1000
    runAsGroup: 1000
  services:
    - spec:
        type: ClusterIP
        clusterIP: None
  commonConfigMountPath: "/opt/druid/conf/druid/cluster/_common"
  jvm.options: |-
    -server
    -XX:MaxDirectMemorySize=10240g
    -Duser.timezone=UTC
    -Dfile.encoding=UTF-8
    -Dlog4j.trace
    -Djava.util.logging.manager=org.apache.logging.log4j.jul.LogManager
    -Djava.io.tmpdir=/druid/data
  log4j.config: |-
    <?xml version="1.0" encoding="UTF-8" ?>
    <Configuration status="WARN">
        <Appenders>
            <Console name="Console" target="SYSTEM_OUT">
                <PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
            </Console>
        </Appenders>
        <Loggers>
            <Root level="trace">
                <AppenderRef ref="Console"/>
            </Root>
        </Loggers>
    </Configuration>
  common.runtime.properties: |

    # Metadata Store

    druid.metadata.storage.type=postgresql
    druid.metadata.storage.connector.connectURI=jdbc:postgresql://druid-pg.pgo.svc.cluster.local:5432/druid-pg
    druid.metadata.storage.connector.host=druid-pg.pgo.svc.cluster.local
    druid.metadata.storage.connector.port=5432
    # only at first run = true, otherwise some errors appears
    druid.metadata.storage.connector.createTables=false
    druid.metadata.storage.connector.user=testuser
    druid.metadata.storage.connector.password=pgopass

    # protections
    druid.server.http.maxSubqueryRows=1000000

    # Deep Storage
    druid.storage.type=s3
    druid.storage.bucket=bucket-name
    druid.storage.baseKey=druid/segments

    # s3 config
    druid.storage.disableAcl=true
    druid.s3.enablePathStyleAccess=true
    druid.s3.endpoint.url=s3.us-west-004.backblazeb2.com
    druid.s3.protocol=https
    druid.s3.endpoint.signingRegion=us-west-004


    #
    # Extensions
    #
    druid.extensions.loadList=["druid-kafka-indexing-service", "druid-s3-extensions", "postgresql-metadata-storage", "druid-kubernetes-extensions", "druid-histogram", "druid-datasketches", "druid-avro-extensions", "druid-bloom-filter"]

    druid.discovery.k8s.clusterIdentifier=us-west-prod-druid


    #
    # Service discovery
    #
    druid.selectors.indexing.serviceName=druid/overlord
    druid.selectors.coordinator.serviceName=druid/coordinator

    druid.indexer.logs.type=s3
    druid.indexer.logs.s3Bucket=bucket-name
    druid.indexer.logs.s3Prefix=druid/indexing-logs

    druid.segmentCache.locations=[{"path":"/druid/data/segment-cache","maxSize":10737418240}]
    druid.indexer.logs.directory=/druid/data/indexing-logs
    druid.lookup.enableLookupSyncOnStartup=false
  volumeMounts:
    - mountPath: /druid/data
      name: data-volume
  volumes:
    - name: data-volume
      emptyDir: {}
  env:
    - name: POD_NAME
      valueFrom:
        fieldRef:
          fieldPath: metadata.name
    - name: POD_NAMESPACE
      valueFrom:
        fieldRef:
          fieldPath: metadata.namespace
    - name: AWS_REGION
      value: "us-west-004"
    - name: AWS_ACCESS_KEY_ID
      value: "000000000000000000000000"
    - name: AWS_SECRET_ACCESS_KEY
      value: "K0000000000000000000000000"

  nodes:
    brokers:
      # Optionally specify for running broker as Deployment
      # kind: Deployment
      nodeType: "broker"
      # Optionally specify for broker nodes
      # imagePullSecrets:
      # - name: tutu
      druid.port: 8088
      nodeConfigMountPath: "/opt/druid/conf/druid/cluster/query/broker"
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: 1Gi
      runtime.properties: |
        druid.service=druid/broker

        # HTTP server threads
        druid.broker.http.numConnections=50
        druid.server.http.numThreads=60

        # disable zk
        druid.zk.service.enabled=false
        druid.serverview.type=http
        druid.coordinator.loadqueuepeon.type=http
        druid.indexer.runner.type=httpRemote
        druid.discovery.type=k8s

        # Processing threads and buffers
        druid.processing.buffer.sizeBytes=500MiB
        druid.processing.numMergeBuffers=4
        druid.processing.numThreads=2
        druid.sql.enable=true
        druid.server.http.defaultQueryTimeout=3000000
      extra.jvm.options: |-
        -Xmx1G
        -Xms1G

    coordinators:
      # Optionally specify for running coordinator as Deployment
      # kind: Deployment
      nodeType: "coordinator"
      druid.port: 8088
      nodeConfigMountPath: "/opt/druid/conf/druid/cluster/master/coordinator-overlord"
      replicas: 1
      resources:
        requests:
          cpu: "0.1"
          memory: 512Mi
      runtime.properties: |
        druid.service=druid/coordinator

        # HTTP server threads
        druid.coordinator.startDelay=PT30S
        druid.coordinator.period=PT30S

        # disable zk
        druid.zk.service.enabled=false
        druid.serverview.type=http
        druid.coordinator.loadqueuepeon.type=http
        druid.indexer.runner.type=httpRemote
        druid.discovery.type=k8s

        # Configure this coordinator to also run as Overlord
        druid.coordinator.asOverlord.enabled=true
        druid.coordinator.asOverlord.overlordService=druid/overlord
        druid.indexer.queue.startDelay=PT30S
        druid.indexer.runner.type=local
      extra.jvm.options: |-
        -Xmx512M
        -Xms512M

    historicals:
      nodeType: "historical"
      druid.port: 8088
      nodeConfigMountPath: "/opt/druid/conf/druid/cluster/data/historical"
      replicas: 1
      resources:
        requests:
          cpu: "0.1"
          memory: 1000Mi
      runtime.properties: |
        # Segment storage
        druid.segmentCache.locations=[{\"path\":\"/druid/data/segment-cache\",\"maxSize\":10737418240}]
        druid.server.maxSize=10737418240

        druid.service=druid/historical
        druid.server.http.numThreads=5
        druid.processing.buffer.sizeBytes=536870912
        druid.processing.numMergeBuffers=1
        druid.processing.numThreads=1

        # disable zk
        druid.zk.service.enabled=false
        druid.serverview.type=http
        druid.coordinator.loadqueuepeon.type=http
        druid.indexer.runner.type=httpRemote
        druid.discovery.type=k8s

        druid.historical.cache.useCache=false
        druid.historical.cache.populateCache=false
        druid.server.http.defaultQueryTimeout=3000000

      extra.jvm.options: |-
        -Xmx1000M
        -Xms1000M

    routers:
      nodeType: "router"
      druid.port: 8088
      nodeConfigMountPath: "/opt/druid/conf/druid/cluster/query/router"
      replicas: 1
      resources:
        requests:
          cpu: "0.1"
          memory: 512Mi
      runtime.properties: |
        druid.service=druid/router

        # HTTP proxy
        druid.router.http.numConnections=10
        druid.router.http.readTimeout=PT5M
        druid.router.http.numMaxThreads=10
        druid.server.http.numThreads=10

        # Service discovery
        druid.router.defaultBrokerServiceName=druid/broker
        druid.router.coordinatorServiceName=druid/coordinator

        # Management proxy to coordinator / overlord: required for unified web console.
        druid.router.managementProxy.enabled=true

        # disable zk
        druid.zk.service.enabled=false
        druid.serverview.type=http
        druid.coordinator.loadqueuepeon.type=http
        druid.indexer.runner.type=httpRemote
        druid.discovery.type=k8s

      extra.jvm.options: |-
        -Xmx512M
        -Xms512M