DolphinScheduler/deploy/kubernetes/dolphinscheduler/values.yaml

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

# Default values for dolphinscheduler-chart.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

timezone: "Asia/Shanghai"

image:
  registry: "dolphinscheduler.docker.scarf.sh/apache"
  tag: "3.0.0-beta-1"
  pullPolicy: "IfNotPresent"
  pullSecret: ""

## If not exists external database, by default, Dolphinscheduler's database will use it.
postgresql:
  enabled: true
  postgresqlUsername: "root"
  postgresqlPassword: "root"
  postgresqlDatabase: "dolphinscheduler"
  persistence:
    enabled: false
    size: "20Gi"
    storageClass: "-"

## If exists external database, and set postgresql.enable value to false.
## external database will be used, otherwise Dolphinscheduler's database will be used.
externalDatabase:
  type: "postgresql"
  host: "localhost"
  port: "5432"
  username: "root"
  password: "root"
  database: "dolphinscheduler"
  params: "characterEncoding=utf8"

## If not exists external registry, the zookeeper registry will be used by default.
zookeeper:
  enabled: true
  fourlwCommandsWhitelist: "srvr,ruok,wchs,cons"
  persistence:
    enabled: false
    size: "20Gi"
    storageClass: "-"

## If exists external registry and set zookeeper.enable value to false, the external registry will be used.
externalRegistry:
  registryPluginDir: "lib/plugin/registry"
  registryPluginName: "zookeeper"
  registryServers: "127.0.0.1:2181"

common:
  ## Configmap
  configmap:
    DOLPHINSCHEDULER_OPTS: ""
    DATA_BASEDIR_PATH: "/tmp/dolphinscheduler"
    RESOURCE_STORAGE_TYPE: "HDFS"
    RESOURCE_UPLOAD_PATH: "/dolphinscheduler"
    FS_DEFAULT_FS: "file:///"
    FS_S3A_ENDPOINT: "s3.xxx.amazonaws.com"
    FS_S3A_ACCESS_KEY: "xxxxxxx"
    FS_S3A_SECRET_KEY: "xxxxxxx"
    HADOOP_SECURITY_AUTHENTICATION_STARTUP_STATE: "false"
    JAVA_SECURITY_KRB5_CONF_PATH: "/opt/krb5.conf"
    LOGIN_USER_KEYTAB_USERNAME: "hdfs@HADOOP.COM"
    LOGIN_USER_KEYTAB_PATH: "/opt/hdfs.keytab"
    KERBEROS_EXPIRE_TIME: "2"
    HDFS_ROOT_USER: "hdfs"
    RESOURCE_MANAGER_HTTPADDRESS_PORT: "8088"
    YARN_RESOURCEMANAGER_HA_RM_IDS: ""
    YARN_APPLICATION_STATUS_ADDRESS: "http://ds1:%s/ws/v1/cluster/apps/%s"
    YARN_JOB_HISTORY_STATUS_ADDRESS: "http://ds1:19888/ws/v1/history/mapreduce/jobs/%s"
    DATASOURCE_ENCRYPTION_ENABLE: "false"
    DATASOURCE_ENCRYPTION_SALT: "!@#$%^&*"
    SUDO_ENABLE: "true"
    # dolphinscheduler env
    HADOOP_HOME: "/opt/soft/hadoop"
    HADOOP_CONF_DIR: "/opt/soft/hadoop/etc/hadoop"
    SPARK_HOME1: "/opt/soft/spark1"
    SPARK_HOME2: "/opt/soft/spark2"
    PYTHON_HOME: "/usr/bin/python"
    JAVA_HOME: "/usr/local/openjdk-8"
    HIVE_HOME: "/opt/soft/hive"
    FLINK_HOME: "/opt/soft/flink"
    DATAX_HOME: "/opt/soft/datax"
  ## Shared storage persistence mounted into api, master and worker, such as Hadoop, Spark, Flink and DataX binary package
  sharedStoragePersistence:
    enabled: false
    mountPath: "/opt/soft"
    accessModes:
    - "ReadWriteMany"
    ## storageClassName must support the access mode: ReadWriteMany
    storageClassName: "-"
    storage: "20Gi"
  ## If RESOURCE_STORAGE_TYPE is HDFS and FS_DEFAULT_FS is file:///, fsFileResourcePersistence should be enabled for resource storage
  fsFileResourcePersistence:
    enabled: false
    accessModes:
    - "ReadWriteMany"
    ## storageClassName must support the access mode: ReadWriteMany
    storageClassName: "-"
    storage: "20Gi"

master:
  ## PodManagementPolicy controls how pods are created during initial scale up, when replacing pods on nodes, or when scaling down.
  podManagementPolicy: "Parallel"
  ## Replicas is the desired number of replicas of the given Template.
  replicas: "3"
  ## You can use annotations to attach arbitrary non-identifying metadata to objects.
  ## Clients such as tools and libraries can retrieve this metadata.
  annotations: {}
  ## Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  ## More info: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#affinity-v1-core
  affinity: {}
  ## NodeSelector is a selector which must be true for the pod to fit on a node.
  ## Selector which must match a node's labels for the pod to be scheduled on that node.
  ## More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
  nodeSelector: {}
  ## Tolerations are appended (excluding duplicates) to pods running with this RuntimeClass during admission,
  ## effectively unioning the set of nodes tolerated by the pod and the RuntimeClass.
  tolerations: []
  ## Compute Resources required by this container. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container
  resources: {}
  # resources:
  #   limits:
  #     memory: "8Gi"
  #     cpu: "4"
  #   requests:
  #     memory: "2Gi"
  #     cpu: "500m"
  ## Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  livenessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  readinessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  ## The StatefulSet controller is responsible for mapping network identities to claims in a way that maintains the identity of a pod.
  ## Every claim in this list must have at least one matching (by name) volumeMount in one container in the template.
  ## A claim in this list takes precedence over any volumes in the template, with the same name.
  persistentVolumeClaim:
    enabled: false
    accessModes:
    - "ReadWriteOnce"
    storageClassName: "-"
    storage: "20Gi"
  env:
    JAVA_OPTS: "-Xms1g -Xmx1g -Xmn512m"
    MASTER_EXEC_THREADS: "100"
    MASTER_EXEC_TASK_NUM: "20"
    MASTER_DISPATCH_TASK_NUM: "3"
    MASTER_HOST_SELECTOR: "LowerWeight"
    MASTER_HEARTBEAT_INTERVAL: "10"
    MASTER_TASK_COMMIT_RETRYTIMES: "5"
    MASTER_TASK_COMMIT_INTERVAL: "1000"
    MASTER_MAX_CPU_LOAD_AVG: "-1"
    MASTER_RESERVED_MEMORY: "0.3"
    MASTER_FAILOVER_INTERVAL: 10
    MASTER_KILL_YARN_JOB_WHEN_HANDLE_FAILOVER: "true"

worker:
  ## PodManagementPolicy controls how pods are created during initial scale up, when replacing pods on nodes, or when scaling down.
  podManagementPolicy: "Parallel"
  ## Replicas is the desired number of replicas of the given Template.
  replicas: "3"
  ## You can use annotations to attach arbitrary non-identifying metadata to objects.
  ## Clients such as tools and libraries can retrieve this metadata.
  annotations: {}
  ## Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  ## More info: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#affinity-v1-core
  affinity: {}
  ## NodeSelector is a selector which must be true for the pod to fit on a node.
  ## Selector which must match a node's labels for the pod to be scheduled on that node.
  ## More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
  nodeSelector: {}
  ## Tolerations are appended (excluding duplicates) to pods running with this RuntimeClass during admission,
  ## effectively unioning the set of nodes tolerated by the pod and the RuntimeClass.
  tolerations: []
  ## Compute Resources required by this container. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container
  resources: {}
  # resources:
  #   limits:
  #     memory: "8Gi"
  #     cpu: "4"
  #   requests:
  #     memory: "2Gi"
  #     cpu: "500m"
  ## Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  livenessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  readinessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  ## The StatefulSet controller is responsible for mapping network identities to claims in a way that maintains the identity of a pod.
  ## Every claim in this list must have at least one matching (by name) volumeMount in one container in the template.
  ## A claim in this list takes precedence over any volumes in the template, with the same name.
  persistentVolumeClaim:
    enabled: false
    ## dolphinscheduler data volume
    dataPersistentVolume:
      enabled: false
      accessModes:
      - "ReadWriteOnce"
      storageClassName: "-"
      storage: "20Gi"
    ## dolphinscheduler logs volume
    logsPersistentVolume:
      enabled: false
      accessModes:
      - "ReadWriteOnce"
      storageClassName: "-"
      storage: "20Gi"
  env:
    WORKER_GROUPS_0: default
    WORKER_MAX_CPU_LOAD_AVG: "-1"
    WORKER_RESERVED_MEMORY: "0.3"
    WORKER_EXEC_THREADS: "100"
    WORKER_HEARTBEAT_INTERVAL: "10"
    WORKER_HOST_WEIGHT: "100"
    WORKER_GROUPS: "default"

alert:
  ## Number of desired pods. This is a pointer to distinguish between explicit zero and not specified. Defaults to 1.
  replicas: 1
  ## The deployment strategy to use to replace existing pods with new ones.
  strategy:
    type: "RollingUpdate"
    rollingUpdate:
      maxSurge: "25%"
      maxUnavailable: "25%"
  ## You can use annotations to attach arbitrary non-identifying metadata to objects.
  ## Clients such as tools and libraries can retrieve this metadata.
  annotations: {}
  ## NodeSelector is a selector which must be true for the pod to fit on a node.
  ## Selector which must match a node's labels for the pod to be scheduled on that node.
  ## More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
  affinity: {}
  ## Compute Resources required by this container. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container
  nodeSelector: {}
  ## Tolerations are appended (excluding duplicates) to pods running with this RuntimeClass during admission,
  ## effectively unioning the set of nodes tolerated by the pod and the RuntimeClass.
  tolerations: []
  ## Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  ## More info: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#affinity-v1-core
  resources: {}
  # resources:
  #   limits:
  #     memory: "2Gi"
  #     cpu: "1"
  #   requests:
  #     memory: "1Gi"
  #     cpu: "500m"
  ## Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  livenessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  readinessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  ## More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims
  persistentVolumeClaim:
    enabled: false
    accessModes:
    - "ReadWriteOnce"
    storageClassName: "-"
    storage: "20Gi"
  env:
    JAVA_OPTS: "-Xms512m -Xmx512m -Xmn256m"

api:
  ## Number of desired pods. This is a pointer to distinguish between explicit zero and not specified. Defaults to 1.
  replicas: "1"
  ## The deployment strategy to use to replace existing pods with new ones.
  strategy:
    type: "RollingUpdate"
    rollingUpdate:
      maxSurge: "25%"
      maxUnavailable: "25%"
  ## You can use annotations to attach arbitrary non-identifying metadata to objects.
  ## Clients such as tools and libraries can retrieve this metadata.
  annotations: {}
  ## NodeSelector is a selector which must be true for the pod to fit on a node.
  ## Selector which must match a node's labels for the pod to be scheduled on that node.
  ## More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
  affinity: {}
  ## Compute Resources required by this container. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container
  nodeSelector: {}
  ## Tolerations are appended (excluding duplicates) to pods running with this RuntimeClass during admission,
  ## effectively unioning the set of nodes tolerated by the pod and the RuntimeClass.
  tolerations: []
  ## Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  ## More info: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#affinity-v1-core
  resources: {}
  # resources:
  #   limits:
  #     memory: "2Gi"
  #     cpu: "1"
  #   requests:
  #     memory: "1Gi"
  #     cpu: "500m"
  ## Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  livenessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated.
  ## More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes
  readinessProbe:
    enabled: true
    initialDelaySeconds: "30"
    periodSeconds: "30"
    timeoutSeconds: "5"
    failureThreshold: "3"
    successThreshold: "1"
  ## PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  ## More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims
  persistentVolumeClaim:
    enabled: false
    accessModes:
    - "ReadWriteOnce"
    storageClassName: "-"
    storage: "20Gi"
  service:
    ## type determines how the Service is exposed. Defaults to ClusterIP. Valid options are ExternalName, ClusterIP, NodePort, and LoadBalancer
    type: "ClusterIP"
    ## clusterIP is the IP address of the service and is usually assigned randomly by the master
    clusterIP: ""
    ## nodePort is the port on each node on which this service is exposed when type=NodePort
    nodePort: ""
    ## externalIPs is a list of IP addresses for which nodes in the cluster will also accept traffic for this service
    externalIPs: []
    ## externalName is the external reference that kubedns or equivalent will return as a CNAME record for this service, requires Type to be ExternalName
    externalName: ""
    ## loadBalancerIP when service.type is LoadBalancer. LoadBalancer will get created with the IP specified in this field
    loadBalancerIP: ""
    ## annotations may need to be set when service.type is LoadBalancer
    ## service.beta.kubernetes.io/aws-load-balancer-ssl-cert: arn:aws:acm:us-east-1:EXAMPLE_CERT
    annotations: {}
  env:
    JAVA_OPTS: "-Xms512m -Xmx512m -Xmn256m"

ingress:
  enabled: false
  host: "dolphinscheduler.org"
  path: "/dolphinscheduler"
  annotations: {}
  tls:
    enabled: false
    secretName: "dolphinscheduler-tls"