values.yaml

# -- Number of replicas
replicaCount: 1

# -- Image registry
image:
  repository: ghcr.io/devops-ia/kafka-cruise-control
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: ""

# -- String to partially override cruise-control.fullname template (will maintain the release name)
nameOverride: ""

# -- String to fully override cruise-control.fullname template
fullnameOverride: ""

# -- Global Docker registry secret names as an array
imagePullSecrets: []

# -- Enable creation of ServiceAccount
serviceAccount:
  # Specifies whether a service account should be created
  create: true
  # Annotations to add to the service account
  annotations: {}
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""
  # Specifies if you don't want the kubelet to automatically mount
  # a ServiceAccount's API credentials
  automountServiceAccountToken: false

# -- Pod annotations
podAnnotations: {}

# -- Pod labels
podLabels: {}

# -- Privilege and access control settings for a Pod or Container
podSecurityContext: {}
  # fsGroup: 2000

# -- Privilege and access control settings
securityContext: {}
  # capabilities:
  #   drop:
  #   - ALL
  # readOnlyRootFilesystem: true
  # runAsNonRoot: true
  # runAsUser: 1000

# -- Kubernetes service to expose Pod
service:
  # -- Kubernetes Service type. Allowed values: NodePort, LoadBalancer or ClusterIP
  type: ClusterIP
  # -- Kubernetes Service port
  port: 80
  # -- Kubernetes Service health check path
  # healthPath: ""
  # -- NodePort port (only when type is NodePort)
  # nodePort: 32000
  # -- Pod expose port
  targetPort: 9090

# -- Ingress configuration to expose app
ingress:
  enabled: false
  className: ""
  annotations: {}
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  hosts:
    - host: chart-example.local
      paths:
        - path: /
          pathType: ImplementationSpecific
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

# -- The resources limits and requested
resources: {}
  # limits:
  #   cpu: "1500m"
  #   memory: 2048Mi
  # requests:
  #   cpu: 1
  #   memory: 256Mi

# -- Configure liveness checker
# </br> Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#define-startup-probes
livenessProbe:
  enabled: false
  failureThreshold: 3
  initialDelaySeconds: 180
  periodSeconds: 10
  successThreshold: 1
  timeoutSeconds: 5

# -- Custom livenessProbe
livenessProbeCustom: {}
  # httpGet:
  #   path: /dashboard
  #   port: 4000
  # failureThreshold: 3
  # initialDelaySeconds: 200
  # periodSeconds: 30
  # successThreshold: 1
  # timeoutSeconds: 5

# -- Configure readinessProbe checker
# </br> Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#define-startup-probes
readinessProbe:
  enabled: false
  failureThreshold: 3
  initialDelaySeconds: 10
  periodSeconds: 10
  successThreshold: 1
  timeoutSeconds: 1

# -- Custom readinessProbe
readinessProbeCustom: {}
  # httpGet:
  #   path: /dashboard
  #   port: 4000
  # failureThreshold: 3
  # initialDelaySeconds: 200
  # periodSeconds: 30
  # successThreshold: 1
  # timeoutSeconds: 5

# -- Configure startupProbe checker
# </br> Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#define-startup-probes
startupProbe:
  enabled: false
  failureThreshold: 30
  initialDelaySeconds: 180
  periodSeconds: 10
  successThreshold: 1
  timeoutSeconds: 5

# -- Custom startupProbe
startupProbeCustom: {}
  # httpGet:
  #   path: /dashboard
  #   port: 4000
  # failureThreshold: 3
  # initialDelaySeconds: 200
  # periodSeconds: 30
  # successThreshold: 1
  # timeoutSeconds: 5

# -- Autoscaling with CPU or memory utilization percentage
autoscaling:
  enabled: false
  minReplicas: 1
  maxReplicas: 100
  targetCPUUtilizationPercentage: 80
  # targetMemoryUtilizationPercentage: 80

# -- Additional volumes on the output Deployment definition.
volumes: []
# - name: foo
#   secret:
#     secretName: mysecret
#     optional: false

# -- Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
#   mountPath: "/etc/foo"
#   readOnly: true

# -- Node labels for pod assignment
nodeSelector: {}

# -- Tolerations for pod assignment
tolerations: []

# -- Affinity for pod assignment
affinity: {}

# -- Environment variables to configure application
# Ref: https://github.com/linkedin/cruise-control/blob/main/kafka-cruise-control-start.sh
env: {}
  # my_env: my_value

# -- Cruise Control JAAS configuration
# Sample: https://github.com/linkedin/cruise-control/blob/main/config/cruise_control_jaas.conf_template
jaas:
  enabled: false
  config: |
    // Enter appropriate Client entry for secured zookeeper client connections
    Client {
      com.sun.security.auth.module.Krb5LoginModule required
      useKeyTab=true
      keyTab="/path/to/zookeeper_client.keytab"
      storeKey=true
      useTicketCache=false
      principal="zookeeper_client@<REALM>";
    };

    // Enter appropriate KafkaClient entry if using the SASL protocol, remove if not
    KafkaClient {
      com.sun.security.auth.module.Krb5LoginModule required
      useKeyTab=true
      keyTab="/path/to/kafka_client.keytab"
      storeKey=true
      useTicketCache=false
      serviceName="kafka"
      principal="kafka_client@<REALM>";
    };

# -- Cruise Control cluster config
# Sample: https://github.com/linkedin/cruise-control/blob/main/config/clusterConfigs.json
cluster:
  min.insync.replicas: 1
  an.example.cluster.config: false

# -- Cruise Control cluster resources
capacity:
  # Allow:
  #   capacity: where each broker has the same number of cores. Sample: https://github.com/linkedin/cruise-control/blob/main/config/capacity.json
  #   capacityCores: where brokers may have varying number of cores. Sample: https://github.com/linkedin/cruise-control/blob/main/config/capacityCores.json
  #   capacityJBOD: where brokers may have variying number of mounts. Sample: https://github.com/linkedin/cruise-control/blob/main/config/capacityJBOD.json
  type: capacity
  config: |
    {
      "brokerCapacities":[
        {
          "brokerId": "-1",
          "capacity": {
            "DISK": "1024",
            "CPU": "100",
            "NW_IN": "1000",
            "NW_OUT": "1000"
          },
          "doc": "This is the default capacity. Capacity unit used for disk is in MB, cpu is in number of cores, network throughput is in KB."
        }
      ]
    }

# -- Cruise Control configuration
# Ref: https://github.com/linkedin/cruise-control/wiki/Configurations
config:
  # METADATA CLIENT
  bootstrap.servers: "localhost:9092"
  client.id: "cruise-control"
  connections.max.idle.ms: 540000
  # logdir.response.timeout.ms: 10000
  # metadata.max.age.ms: 300000
  # receive.buffer.bytes: 131072
  # reconnect.backoff.ms: 50
  # request.timeout.ms: 30000
  # send.buffer.bytes: 131072

  # LOAD MONITOR
  broker.metric.sample.store.topic: "__KafkaCruiseControlModelTrainingSamples"
  broker.metrics.window.ms: 300000
  broker.sample.store.topic.partition.count: 8
  metric.sampler.class: com.linkedin.kafka.cruisecontrol.monitor.sampling.prometheus.PrometheusMetricSampler
  metric.sampler.partition.assignor.class: "com.linkedin.kafka.cruisecontrol.monitor.sampling.DefaultMetricSamplerPartitionAssignor"
  metric.sampling.interval.ms: 120000
  min.samples.per.broker.metrics.window: 1
  min.samples.per.partition.metrics.window: 1
  num.broker.metrics.windows: 20
  num.partition.metrics.windows: 5
  num.sample.loading.threads: 8
  partition.metric.sample.store.topic: "__KafkaCruiseControlPartitionMetricSamples"
  partition.metrics.window.ms: 300000
  partition.sample.store.topic.partition.count: 8
  prometheus.server.endpoint: thanos-query.prometheus:9090
  sample.store.class: "com.linkedin.kafka.cruisecontrol.monitor.sampling.KafkaSampleStore"
  sample.store.topic.replication.factor: 2
  sampling.allow.cpu.capacity.estimation: true

  # ANALYZER
  cpu.balance.threshold: 1.1
  cpu.capacity.threshold: 0.7
  cpu.low.utilization.threshold: 0.0
  default.goals:
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.RackAwareGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.MinTopicLeadersPerBrokerGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.PotentialNwOutGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.TopicReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.LeaderReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.LeaderBytesInDistributionGoal
  disk.balance.threshold: 1.1
  disk.capacity.threshold: 0.8
  disk.low.utilization.threshold: 0.0
  # goal.balancedness.priority.weight:
  # goal.balancedness.strictness.weight:
  goals:
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.RackAwareGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.RackAwareDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.MinTopicLeadersPerBrokerGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.PotentialNwOutGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.TopicReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.LeaderReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.LeaderBytesInDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.kafkaassigner.KafkaAssignerDiskUsageDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.kafkaassigner.KafkaAssignerEvenRackAwareGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.PreferredLeaderElectionGoal
  hard.goals:
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.RackAwareGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.MinTopicLeadersPerBrokerGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.TopicReplicaDistributionGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuCapacityGoal
  intra.broker.goals:
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.IntraBrokerDiskCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.IntraBrokerDiskUsageDistributionGoal
  max.replicas.per.broker: 10000
  metric.anomaly.percentile.lower.threshold: 10.0
  metric.anomaly.percentile.upper.threshold: 90.0
  min.valid.partition.ratio: 0.95
  network.inbound.balance.threshold: 1.1
  network.inbound.capacity.threshold: 0.8
  network.inbound.low.utilization.threshold: 0.0
  network.outbound.balance.threshold: 1.1
  network.outbound.capacity.threshold: 0.8
  network.outbound.low.utilization.threshold: 0.0
  num.proposal.precompute.threads: 1
  proposal.expiration.ms: 60000
  replica.count.balance.threshold: 1.1
  topics.excluded.from.partition.movement: __consumer_offsets.*|__amazon_msk_canary.*|__amazon_msk_connect.*|__KafkaCruiseControl.*

  # EXECUTOR
  # default.replication.throttle:
  execution.progress.check.interval.ms: 10000
  max.num.cluster.partition.movements: 1250
  num.concurrent.intra.broker.partition.movements: 2
  num.concurrent.leader.movements: 1000
  num.concurrent.partition.movements.per.broker: 5
  zookeeper.security.enabled: false
  replica.movement.strategies:
  - com.linkedin.kafka.cruisecontrol.executor.strategy.PostponeUrpReplicaMovementStrategy
  - com.linkedin.kafka.cruisecontrol.executor.strategy.PrioritizeLargeReplicaMovementStrategy
  - com.linkedin.kafka.cruisecontrol.executor.strategy.PrioritizeSmallReplicaMovementStrategy
  - com.linkedin.kafka.cruisecontrol.executor.strategy.PrioritizeMinIsrWithOfflineReplicasStrategy
  - com.linkedin.kafka.cruisecontrol.executor.strategy.PrioritizeOneAboveMinIsrWithOfflineReplicasStrategy
  - com.linkedin.kafka.cruisecontrol.executor.strategy.BaseReplicaMovementStrategy
  default.replica.movement.strategies:
  - com.linkedin.kafka.cruisecontrol.executor.strategy.BaseReplicaMovementStrategy

  # ANOMALY DETECTOR
  anomaly.detection.goals:
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.RackAwareGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.MinTopicLeadersPerBrokerGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.ReplicaCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.DiskCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkInboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.NetworkOutboundCapacityGoal
  - com.linkedin.kafka.cruisecontrol.analyzer.goals.CpuCapacityGoal
  anomaly.detection.interval.ms: "10000"
  anomaly.notifier.class: com.linkedin.kafka.cruisecontrol.detector.notifier.SelfHealingNotifier
  cluster.configs.file: "config/clusterConfigs.json"
  completed.cruise.control.admin.user.task.retention.time.ms: 604800000
  completed.cruise.control.monitor.user.task.retention.time.ms: 86400000
  completed.kafka.admin.user.task.retention.time.ms: 604800000
  completed.kafka.monitor.user.task.retention.time.ms: 86400000
  completed.user.task.retention.time.ms: 86400000
  demotion.history.retention.time.ms: 1209600000
  # goal.violation.distribution.threshold.multiplier: 2.50
  max.active.user.tasks: 5
  max.cached.completed.cruise.control.admin.user.tasks: 30
  max.cached.completed.cruise.control.monitor.user.tasks: 20
  max.cached.completed.kafka.admin.user.tasks: 30
  max.cached.completed.kafka.monitor.user.tasks: 20
  max.cached.completed.user.tasks: 25
  metric.anomaly.analyzer.metrics:
  - BROKER_PRODUCE_LOCAL_TIME_MS_50TH
  - BROKER_PRODUCE_LOCAL_TIME_MS_999TH
  - BROKER_CONSUMER_FETCH_LOCAL_TIME_MS_50TH
  - BROKER_CONSUMER_FETCH_LOCAL_TIME_MS_999TH
  - BROKER_FOLLOWER_FETCH_LOCAL_TIME_MS_50TH
  - BROKER_FOLLOWER_FETCH_LOCAL_TIME_MS_999TH
  - BROKER_LOG_FLUSH_TIME_MS_50TH
  - BROKER_LOG_FLUSH_TIME_MS_999TH
  metric.anomaly.detection.interval.ms: 120000
  metric.anomaly.finder.class: com.linkedin.kafka.cruisecontrol.detector.KafkaMetricAnomalyFinder
  removal.history.retention.time.ms: 1209600000
  # self.healing.broker.failure.enabled: true
  self.healing.enabled: false
  self.healing.exclude.recently.demoted.brokers: true
  self.healing.exclude.recently.removed.brokers: true
  self.healing.disk.failure.enabled: false
  self.healing.goal.violation.enabled: false
  self.healing.maintenance.event.enabled: false
  self.healing.metric.anomaly.enabled: false
  self.healing.topic.anomaly.enabled: false
  topic.anomaly.finder.class: com.linkedin.kafka.cruisecontrol.detector.TopicReplicationFactorAnomalyFinder
  topic.config.provider.class: com.linkedin.kafka.cruisecontrol.config.KafkaAdminTopicConfigProvider

  # WEBSERVER
  webserver.accesslog.enabled: true
  webserver.api.urlprefix: /kafkacruisecontrol/*
  webserver.http.address: 0.0.0.0
  webserver.http.cors.enabled: false
  webserver.http.port: 9090
  webserver.request.maxBlockTimeMs: 10000
  webserver.session.maxExpiryTimeMs: 60000
  webserver.session.path: /
  webserver.ui.diskpath: ./cruise-control-ui/dist/
  webserver.ui.urlprefix: /*

  # SERVLET
  two.step.purgatory.max.requests: 25
  two.step.purgatory.retention.time.ms: 1209600000
  two.step.verification.enabled: false
  vertx.enabled: false

# -- Cruise Control log4j configuration
log4j:
  rootLogger.level: INFO
  appenders: console, kafkaCruiseControlAppender, operationAppender, requestAppender

  property.filename: ./logs

  appender.console.type: Console
  appender.console.name: STDOUT
  appender.console.layout.type: PatternLayout
  appender.console.layout.pattern: "[%d] %p %m (%c)%n"

  appender.kafkaCruiseControlAppender.type: RollingFile
  appender.kafkaCruiseControlAppender.name: kafkaCruiseControlFile
  appender.kafkaCruiseControlAppender.fileName: ${filename}/kafkacruisecontrol.log
  appender.kafkaCruiseControlAppender.filePattern: ${filename}/kafkacruisecontrol.log.%d{yyyy-MM-dd-HH}
  appender.kafkaCruiseControlAppender.layout.type: PatternLayout
  appender.kafkaCruiseControlAppender.layout.pattern: "[%d] %p %m (%c)%n"
  appender.kafkaCruiseControlAppender.policies.type: Policies
  appender.kafkaCruiseControlAppender.policies.time.type: TimeBasedTriggeringPolicy
  appender.kafkaCruiseControlAppender.policies.time.interval: 1

  appender.operationAppender.type: RollingFile
  appender.operationAppender.name: operationFile
  appender.operationAppender.fileName: ${filename}/kafkacruisecontrol-operation.log
  appender.operationAppender.filePattern: ${filename}/kafkacruisecontrol-operation.log.%d{yyyy-MM-dd}
  appender.operationAppender.layout.type: PatternLayout
  appender.operationAppender.layout.pattern: "[%d] %p [%c] %m %n"
  appender.operationAppender.policies.type: Policies
  appender.operationAppender.policies.time.type: TimeBasedTriggeringPolicy
  appender.operationAppender.policies.time.interval: 1

  appender.requestAppender.type: RollingFile
  appender.requestAppender.name: requestFile
  appender.requestAppender.fileName: ${filename}/kafkacruisecontrol-request.log
  appender.requestAppender.filePattern: ${filename}/kafkacruisecontrol-request.log.%d{yyyy-MM-dd-HH}
  appender.requestAppender.layout.type: PatternLayout
  appender.requestAppender.layout.pattern: "[%d] %p %m (%c)%n"
  appender.requestAppender.policies.type: Policies
  appender.requestAppender.policies.time.type: TimeBasedTriggeringPolicy
  appender.requestAppender.policies.time.interval: 1

  # Loggers
  logger.cruisecontrol.name: com.linkedin.kafka.cruisecontrol
  logger.cruisecontrol.level: info
  logger.cruisecontrol.appenderRef.kafkaCruiseControlAppender.ref: kafkaCruiseControlFile

  logger.detector.name: com.linkedin.kafka.cruisecontrol.detector
  logger.detector.level: info
  logger.detector.appenderRef.kafkaCruiseControlAppender.ref: kafkaCruiseControlFile

  logger.operationLogger.name: operationLogger
  logger.operationLogger.level: info
  logger.operationLogger.appenderRef.operationAppender.ref: operationFile

  logger.CruiseControlPublicAccessLogger.name: CruiseControlPublicAccessLogger
  logger.CruiseControlPublicAccessLogger.level: info
  logger.CruiseControlPublicAccessLogger.appenderRef.requestAppender.ref: requestFile

  rootLogger.appenderRefs: console, kafkaCruiseControlAppender
  rootLogger.appenderRef.console.ref: STDOUT
  rootLogger.appenderRef.kafkaCruiseControlAppender.ref: kafkaCruiseControlFile