Skip to content

Instantly share code, notes, and snippets.

@AdheipSingh

AdheipSingh/druid-pay.yaml

Last active August 28, 2020 19:07
Show Gist options
  • Save AdheipSingh/9791655b8ea063fe27dcac5e0fcbea8c to your computer and use it in GitHub Desktop.
Save AdheipSingh/9791655b8ea063fe27dcac5e0fcbea8c to your computer and use it in GitHub Desktop.
Download ZIP
druid-pay.yaml
Raw
druid-pay.yaml
apiVersion: druid.apache.org/v1alpha1
kind: Druid
metadata:
name: cluster
spec:
podAnnotations:
iam.amazonaws.com/role: arn:aws:iam::91243143143423403742:role/my-role
env:
- name: AWS_REGION
value: ap-south-1
commonConfigMountPath: /opt/druid/conf/druid/cluster/_common
rollingDeploy: true
image: "apache/incubator-druid:0.16.0-incubating"
startScript: /druid.sh
common.runtime.properties: |
#
# Monitoring
#
druid.monitoring.monitors=["org.apache.druid.java.util.metrics.JvmMonitor"]
#druid.emitter=noop
druid.emitter.logging.logLevel=debug
# Storage type of double columns
# ommiting this will lead to index double as float at the storage layer
druid.indexing.doubleStorage=double
#
# Extensions
#
druid.extensions.directory=/opt/druid/extensions
druid.extensions.loadList=["druid-s3-extensions","druid-kafka-indexing-service","druid-datasketches","postgresql-metadata-storage"]
# Log all runtime properties on startup. Disable to avoid logging properties on startup:
druid.startup.logging.logProperties=true
#
# Service discovery
#
druid.selectors.indexing.serviceName=druid/overlord
druid.selectors.coordinator.serviceName=druid/coordinator
druid.sql.enable=true
deepStorage:
spec:
properties: |-
druid.storage.type=s3
druid.storage.bucket=singh-druid
druid.storage.baseKey=druid/segments
druid.indexer.logs.directory=data/logs/
type: default
metadataStore:
spec:
properties: |-
druid.metadata.storage.type=postgresql
druid.metadata.storage.connector.connectURI=jdbc:postgresql://postgres.druid.svc.cluster.local:5432/druiddb
druid.metadata.storage.connector.password=admin123
druid.metadata.storage.connector.createTables=true
type: default
zookeeper:
spec:
properties: |-
druid.zk.service.host=zk-cs.druid.svc.cluster.local
druid.zk.paths.base=/druid
type: default
jvm.options: |-
-server
-XX:+PrintFlagsFinal
-XX:MaxDirectMemorySize=10240g
-XX:+UnlockExperimentalVMOptions
-XX:+UseCGroupMemoryLimitForHeap
-Duser.timezone=UTC
-Dfile.encoding=UTF-8
-Dlog4j.debug
-XX:+ExitOnOutOfMemoryError
-XX:HeapDumpPath=/druid/data/logs
-XX:+HeapDumpOnOutOfMemoryError
-XX:+UseG1GC
-Djava.util.logging.manager=org.apache.logging.log4j.jul.LogManager
-XX:+UnlockDiagnosticVMOptions
-XX:+PrintSafepointStatistics
-XX:PrintSafepointStatisticsCount=1
-XX:+PrintGCDetails
-XX:+PrintGCDateStamps
-XX:+PrintGCApplicationStoppedTime
-XX:+PrintGCApplicationConcurrentTime
-XX:+UseGCLogFileRotation
-XX:NumberOfGCLogFiles=50
-XX:GCLogFileSize=50m
-Xloggc:/druid/data/logs/gc.log
nodes:
brokers:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-query
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
druid.port: 8082
extra.jvm.options: |-
-Xmx2G
-Xms2G
nodeConfigMountPath: /opt/druid/conf/druid/cluster/query/broker
nodeType: broker
podDisruptionBudgetSpec:
maxUnavailable: 1
replicas: 1
resources:
limits:
cpu: "1"
memory: 6G
requests:
cpu: "1"
memory: 6G
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8082
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8082
runtime.properties: |
druid.service=druid/broker
druid.plaintextPort=8082
# HTTP server settings
druid.server.http.numThreads=25
# HTTP client settings
druid.broker.http.numConnections=5
# Processing threads and buffers
druid.processing.buffer.sizeBytes=1073741824
druid.processing.numThreads=1
druid.processing.tmpDir=var/druid/processing
services:
-
metadata:
name: broker-%s-service
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8082
targetPort: 8082
type: ClusterIP
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="debug">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
volumeClaimTemplates:
-
metadata:
name: data-volume
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 20Gi
storageClassName: zone-a-storage
volumeMounts:
-
mountPath: /druid/data
name: data-volume
autoscaler:
maxReplicas: 10
minReplicas: 1
scaleTargetRef:
apiVersion: apps/v1
kind: StatefulSet
name: druid-cluster-brokers
metrics:
- type: Resource
resource:
name: cpu
targetAverageUtilization: 60
- type: Resource
resource:
name: memory
targetAverageUtilization: 60
securityContext:
fsGroup: 1000
runAsGroup: 1000
runAsUser: 1000
coordinators:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-master
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="debug">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
druid.port: 8081
extra.jvm.options: |-
-Xmx1G
-Xms1G
nodeConfigMountPath: /opt/druid/conf/druid/cluster/master/coordinator
nodeType: coordinator
podDisruptionBudgetSpec:
maxUnavailable: 1
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8081
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8081
replicas: 1
resources:
limits:
cpu: "1"
memory: 6G
requests:
cpu: "1"
memory: 6G
runtime.properties: |
druid.service=druid/coordinator
druid.coordinator.startDelay=PT30S
druid.coordinator.period=PT30S
druid.coordinator.kill.on=true
druid.coordinator.kill.period=PT2H
druid.coordinator.kill.durationToRetain=PT0s
druid.coordinator.kill.maxSegments=5000
services:
-
metadata:
name: coordinator-%s-service
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8081
targetPort: 8081
type: ClusterIP
volumeMounts:
-
mountPath: /druid/data
name: data-volume
volumes:
-
emptyDir: {}
name: data-volume
securityContext:
fsGroup: 1000
runAsGroup: 1000
runAsUser: 1000
autoscaler:
maxReplicas: 10
minReplicas: 1
scaleTargetRef:
apiVersion: apps/v1
kind: StatefulSet
name: druid-cluster-coordinators
metrics:
- type: Resource
resource:
name: cpu
targetAverageUtilization: 60
- type: Resource
resource:
name: memory
targetAverageUtilization: 60
historicals:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-data
druid.port: 8083
extra.jvm.options: |-
-Xmx1G
-Xms1G
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="debug">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
nodeType: historical
podDisruptionBudgetSpec:
maxUnavailable: 1
nodeConfigMountPath: /opt/druid/conf/druid/cluster/data/historical
replicas: 1
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8083
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8083
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
resources:
limits:
cpu: "1"
memory: 8G
requests:
cpu: "1"
memory: 8G
runtime.properties: |
druid.service=druid/historical
druid.server.http.numThreads=10
druid.processing.buffer.sizeBytes=1073741824
druid.server.maxSize=1099511627776
druid.segmentCache.locations=[{\"path\":\"/druid/data/segments\",\"maxSize\":1099511627776}]
druid.processing.numThreads=2
services:
-
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8083
targetPort: 8083
type: ClusterIP
volumeClaimTemplates:
-
metadata:
name: data-volume
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 30Gi
storageClassName: zone-a-storage
volumeMounts:
-
mountPath: /druid/data
name: data-volume
securityContext:
fsGroup: 0
runAsGroup: 0
runAsUser: 0
middlemanagers:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-data
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
druid.port: 8091
extra.jvm.options: |-
-Xmx4G
-Xms4G
nodeType: middleManager
nodeConfigMountPath: /opt/druid/conf/druid/cluster/data/middlemanager
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="info">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
podDisruptionBudgetSpec:
maxUnavailable: 1
ports:
-
containerPort: 8100
name: peon-0-pt
-
containerPort: 8101
name: peon-1-pt
-
containerPort: 8102
name: peon-2-pt
-
containerPort: 8103
name: peon-3-pt
-
containerPort: 8104
name: peon-4-pt
replicas: 1
resources:
limits:
cpu: "2"
memory: 5Gi
requests:
cpu: "2"
memory: 5Gi
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8091
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8091
runtime.properties: |-
druid.service=druid/middleManager
druid.worker.capacity=4
druid.indexer.runner.javaOpts=-server -XX:MaxDirectMemorySize=10240g -Duser.timezone=UTC -Dfile.encoding=UTF-8 -Djava.io.tmpdir=/druid/data/tmp -Dlog4j.debug -XX:+UnlockDiagnosticVMOptions -XX:+PrintSafepointStatistics -XX:PrintSafepointStatisticsCount=1 -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+PrintGCApplicationStoppedTime -XX:+PrintGCApplicationConcurrentTime -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=50 -XX:GCLogFileSize=10m -XX:+ExitOnOutOfMemoryError -XX:+HeapDumpOnOutOfMemoryError -XX:+UseG1GC -Djava.util.logging.manager=org.apache.logging.log4j.jul.LogManager -XX:HeapDumpPath=/druid/data/logs/peon.%t.%p.hprof -Xms10G -Xmx10G
druid.indexer.task.baseTaskDir=/druid/data/baseTaskDir
druid.server.http.numThreads=10
druid.indexer.fork.property.druid.processing.buffer.sizeBytes=1
druid.indexer.fork.property.druid.processing.numMergeBuffers=1
druid.indexer.fork.property.druid.processing.numThreads=1
# Processing threads and buffers on Peons
druid.indexer.fork.property.druid.processing.numMergeBuffers=2
druid.indexer.fork.property.druid.processing.buffer.sizeBytes=100000000
druid.indexer.fork.property.druid.processing.numThreads=1
services:
-
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8091
targetPort: 8091
-
name: peon-port-0
port: 8100
targetPort: 8100
-
name: peon-port-1
port: 8101
targetPort: 8101
-
name: peon-port-2
port: 8102
targetPort: 8102
-
name: peon-port-3
port: 8103
targetPort: 8103
-
name: peon-port-4
port: 8104
targetPort: 8104
type: ClusterIP
volumeClaimTemplates:
-
metadata:
name: data-volume
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 30Gi
storageClassName: zone-a-storage
volumeMounts:
-
mountPath: /druid/data
name: data-volume
securityContext:
fsGroup: 0
runAsGroup: 0
runAsUser: 0
autoscaler:
maxReplicas: 10
minReplicas: 1
scaleTargetRef:
apiVersion: apps/v1
kind: StatefulSet
name: druid-cluster-middlemanagers
metrics:
- type: Resource
resource:
name: cpu
targetAverageUtilization: 60
- type: Resource
resource:
name: memory
targetAverageUtilization: 60
overlords:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-master
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
druid.port: 8090
extra.jvm.options: |-
-Xmx4G
-Xms4G
nodeType: overlord
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="debug">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
podDisruptionBudgetSpec:
maxUnavailable: 1
nodeConfigMountPath: /opt/druid/conf/druid/cluster/master/overlord
replicas: 1
resources:
limits:
cpu: "2"
memory: 6Gi
requests:
cpu: "2"
memory: 6Gi
runtime.properties: |-
druid.service=druid/overlord
druid.indexer.queue.startDelay=PT30S
druid.indexer.runner.type=remote
druid.indexer.storage.type=metadata
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8081
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8081
services:
-
metadata:
name: overlord-%s-service
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8090
targetPort: 8090
type: ClusterIP
volumeClaimTemplates:
-
metadata:
name: data-volume
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 10Gi
storageClassName: default
volumeMounts:
-
mountPath: /druid/data
name: data-volume
securityContext:
fsGroup: 1000
runAsGroup: 1000
runAsUser: 1000
autoscaler:
maxReplicas: 10
minReplicas: 1
scaleTargetRef:
apiVersion: apps/v1
kind: StatefulSet
name: druid-cluster-overlords
metrics:
- type: Resource
resource:
name: cpu
targetAverageUtilization: 60
- type: Resource
resource:
name: memory
targetAverageUtilization: 60
routers:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
-
matchExpressions:
-
key: node-type
operator: In
values:
- druid-query
livenessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8888
readinessProbe:
initialDelaySeconds: 30
httpGet:
path: /status/health
port: 8888
tolerations:
-
effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Exists
druid.port: 8888
extra.jvm.options: |-
-Xmx512m
-Xms512m
nodeType: router
podDisruptionBudgetSpec:
maxUnavailable: 1
nodeConfigMountPath: /opt/druid/conf/druid/cluster/query/router
replicas: 1
runtime.properties: |
druid.service=druid/router
druid.plaintextPort=8888
# HTTP proxy
druid.router.http.numConnections=50
druid.router.http.readTimeout=PT5M
druid.router.http.numMaxThreads=100
druid.server.http.numThreads=100
# 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
services:
-
metadata:
name: router-%s-service
spec:
clusterIP: None
ports:
-
name: tcp-service-port
port: 8888
targetPort: 8888
type: ClusterIP
log4j.config: |-
<Configuration status="WARN">
<Appenders>
<Console name="logline" target="SYSTEM_OUT">
<PatternLayout pattern="%d{ISO8601} %p [%t] %c - %m%n"/>
</Console>
<Console name="msgonly" target="SYSTEM_OUT">
<PatternLayout pattern="%m%n"/>
</Console>
</Appenders>
<Loggers>
<Root level="info">
<AppenderRef ref="logline"/>
</Root>
<Logger name="org.apache.druid.java.util.emitter.core.LoggingEmitter" additivity="false" level="debug">
<AppenderRef ref="msgonly"/>
</Logger>
</Loggers>
</Configuration>
volumeClaimTemplates:
-
metadata:
name: data-volume
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
storageClassName: zone-a-storage
volumeMounts:
-
mountPath: /druid/data
name: data-volume
securityContext:
fsGroup: 1000
runAsGroup: 1000
runAsUser: 1000
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment