K8s集群+Rancher Server：部署DolphinScheduler 3.2.2集群-EW帮帮网

K8s集群+Rancher Server：部署DolphinScheduler 3.2.2集群

一、环境准备

1、软件准备

序号	环境名称	说明	版本号
1	Rancher Server	k8s运维平台	v2.5.7
2	Kubectl	k8s集群管理命令行工具	v2.5.7
3	apache-dolphinscheduler	ETL	3.2.2

2、环境规划

序号	IP	HostName	操作系统	K8s角色	说明
1	192.168.255.140	harbor	Anolis OS 8.9 x86 64位	Harbor服务	Kubernetes 管理平台
1	192.168.255.141	rancher	Anolis OS 8.9 x86 64位	Rancher服务	Kubernetes 管理平台
2	192.168.255.142	master	Anolis OS 8.9 x86 64位	控制节点	Kubernetes Master
3	192.168.255.143	worker01	Anolis OS 8.9 x86 64位	工作节点	Kubernetes Master高可用节点，如果不需要高可用，可不部署此服务器
4	192.168.255.144	worker02	Anolis OS 8.9 x86 64位	工作节点	Kubernetes Worker
5	192.168.255.145	worker03	Anolis OS 8.9 x86 64位	工作节点	Kubernetes Worker
6	192.168.255.146	worker04	Anolis OS 8.9 x86 64位	工作节点	Kubernetes Worker
7	192.168.255.147	worker05	Anolis OS 8.9 x86 64位	工作节点	Kubernetes Worker

二、部署

1、下载apache-dolphinscheduler源码

在这里插入图片描述

[root@master ~]# mkdir /opt/dolphinscheduler
#
[root@master ~]# cd /opt/dolphinscheduler
[root@master dolphinscheduler]# curl -Lo https://dlcdn.apache.org/dolphinscheduler/3.2.2/apache-dolphinscheduler-3.2.2-src.tar.gz
[root@master dolphinscheduler]# tar -xzvf ./apache-dolphinscheduler-3.2.2-src.tar.gz

2、修改Chart的镜像地址配置

（1）、修改Chart.yaml配置文件
将 repository: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami 改为 repository: https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami

[root@master dolphinscheduler]# cd /opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler
[root@master dolphinscheduler]# vim Chart.yaml

# Application charts are a collection of templates that can be packaged into versioned archives
# to be deployed.
#
# Library charts provide useful utilities or functions for the chart developer. They're included as
# a dependency of application charts to inject those utilities and functions into the rendering
# pipeline. Library charts do not define any templates and therefore cannot be deployed.
type: application

# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
version: 3.3.0-alpha

# This is the version number of the application being deployed. This version number should be
# incremented each time you make changes to the application.
appVersion: 3.3.0-alpha

dependencies:
- name: postgresql
  version: 10.3.18
  # Due to a change in the Bitnami repo, https://charts.bitnami.com/bitnami was truncated only
  # containing entries for the latest 6 months (from January 2022 on).
  # This URL: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami
  # contains the full 'index.yaml'.
  # See detail here: https://github.com/bitnami/charts/issues/10833
  #repository: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami
  repository: https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami
  condition: postgresql.enabled
- name: zookeeper
  version: 6.5.3
  # Same as above.
  #repository: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami
  repository: https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami
  condition: zookeeper.enabled
- name: mysql
  version: 9.4.1
  #repository: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami
  repository: https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami
  condition: mysql.enabled
- name: minio
  version: 11.10.13
  #repository: https://raw.githubusercontent.com/bitnami/charts/archive-full-index/bitnami
  repository: https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami
  condition: minio.enabled

（2）、执行helm更新
Chart.yaml配置文件修改完成后执行下面的命令：

[root@master dolphinscheduler]# helm repo add bitnami-full-index  https://raw.gitmirror.com/bitnami/charts/archive-full-index/bitnami
[root@master dolphinscheduler]# helm repo add bitnami https://charts.bitnami.com/bitnami
[root@master dolphinscheduler]# helm dependency update .

（3）、解压依赖文件
helm更新完成后，在当前目录会新生成【charts】目录，该目录下就是过helm更新下载到本地的依赖文件，如下图所示：
在这里插入图片描述

解压依赖包文件，因为本次安装除了Mysql都需要同步安装，所以要解压minio-11.10.13.tgz，postgresql-10.3.18.tgz，zookeeper-6.5.3.tgz这几个压缩包

[root@master dolphinscheduler]# tar -zxvf minio-11.10.13.tgz
[root@master dolphinscheduler]# tar -zxvf postgresql-10.3.18.tgz
[root@master dolphinscheduler]# tar -zxvf zookeeper-6.5.3.tgz

在这里插入图片描述

3、修改Dolphinscheduler的Helm配置文件

cd /opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler
vim values.yaml

（1）、修改初始镜像

需要修改busybox和dolphinscheduler各个组件的镜像地址，修改后如下：

# -- World time and date for cities in all time zones
timezone: "Asia/Shanghai"

# -- Used to detect whether dolphinscheduler dependent services such as database are ready
initImage:
  # -- Image pull policy. Options: Always, Never, IfNotPresent
  pullPolicy: "IfNotPresent"
  # -- Specify initImage repository
  #busybox: "busybox:1.30.1"
  busybox: "registry.cn-hangzhou.aliyuncs.com/docker_image-ljx/busybox:1.30.1"

image:
  # -- Docker image repository for the DolphinScheduler
  registry: registry.cn-hangzhou.aliyuncs.com/docker_image-ljx
  # -- Docker image version for the DolphinScheduler
  tag: 3.2.2
  # -- Image pull policy. Options: Always, Never, IfNotPresent
  pullPolicy: "IfNotPresent"
  # -- Specify a imagePullSecrets
  pullSecret: ""
  # -- master image
  master: dolphinscheduler-master
  # -- worker image
  worker: dolphinscheduler-worker
  # -- api-server image
  api: dolphinscheduler-api
  # -- alert-server image
  alert: dolphinscheduler-alert-server
  # -- tools image
  tools: dolphinscheduler-tools

（2）、修改postgresql配置

本文安装依赖的数据库配置了默认的数据库postgresql，参见配置datasource.profile: postgresql，但是values.yaml的默认配置中并没有配置postgresql镜像，会导致postgresql镜像拉取失败。

本文dolphinscheduler依赖于bitnami postgresql的Chart，且已经在上一步解压了。获取镜像地址的方式只需进入解压目录（/opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler/charts/postgresql）。

查看postgresql的values.yaml（/opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler/charts/postgresql/values.yaml）找到镜像地址：

image:
  registry: docker.io
  repository: bitnami/postgresql
  tag: 11.11.0-debian-10-r71
  ## Specify a imagePullPolicy
  ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
  ## ref: http://kubernetes.io/docs/user-guide/images/#pre-pulling-images
  ##
  pullPolicy: IfNotPresent
  ## Optionally specify an array of imagePullSecrets.
  ## Secrets must be manually created in the namespace.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
  ##
  # pullSecrets:
  #   - myRegistryKeySecretName

  ## Set to true if you would like to see extra information on logs
  ## It turns BASH and/or NAMI debugging in the image
  ##
  debug: false

复制上述配置文件中的image配置信息，如下图所示：
在这里插入图片描述
将上步复制到image粘贴至/opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler/values.yaml配置文件中postgresql配置项下，如下所示：

datasource:
  # -- The profile of datasource
  profile: postgresql

postgresql:
  image:
    registry: docker.io
    repository: bitnami/postgresql
    tag: 11.11.0-debian-10-r71
  # -- If not exists external PostgreSQL, by default, the DolphinScheduler will use a internal PostgreSQL
  enabled: true
  # -- The username for internal PostgreSQL
  postgresqlUsername: "root"
  # -- The password for internal PostgreSQL
  postgresqlPassword: "root"
  # -- The database for internal PostgreSQL
  postgresqlDatabase: "dolphinscheduler"
  # -- The driverClassName for internal PostgreSQL
  driverClassName: "org.postgresql.Driver"
  # -- The params for internal PostgreSQL
  params: "characterEncoding=utf8"
  persistence:
    # -- Set postgresql.persistence.enabled to true to mount a new volume for internal PostgreSQL
    enabled: false
    # -- `PersistentVolumeClaim` size
    size: "20Gi"
    # -- PostgreSQL data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClass: "-"

（3）、修改minio配置

查看minio的values.yaml（/opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler/charts/minio/values.yaml）找到镜像地址：

image:
  registry: docker.io
  repository: bitnami/minio
  tag: 2022.10.29-debian-11-r0
  digest: ""
  ## Specify a imagePullPolicy
  ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
  ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images
  ##
  pullPolicy: IfNotPresent
  ## Optionally specify an array of imagePullSecrets.
  ## Secrets must be manually created in the namespace.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
  ## e.g:
  ## pullSecrets:
  ##   - myRegistryKeySecretName
  ##
  pullSecrets: []
  ## Set to true if you would like to see extra information on logs
  ##
  debug: false

minio:
  image:
    registry: docker.io
    repository: bitnami/minio
    tag: 2022.10.29-debian-11-r0

  # -- Deploy minio and configure it as the default storage for DolphinScheduler, note this is for demo only, not for production.
  enabled: true
  auth:
    # -- minio username
    rootUser: minioadmin
    # -- minio password
    rootPassword: minioadmin
  persistence:
    # -- Set minio.persistence.enabled to true to mount a new volume for internal minio
    enabled: false
  # -- minio default buckets
  defaultBuckets: "dolphinscheduler"

（4）、修改zookeeper配置

查看zookeeper的values.yaml（/opt/dolphinscheduler/apache-dolphinscheduler-3.2.2-src/deploy/kubernetes/dolphinscheduler/charts/zookeeper/values.yaml）找到镜像地址：

image:
  registry: docker.io
  repository: bitnami/zookeeper
  tag: 3.6.2-debian-10-r185

  ## Specify a imagePullPolicy
  ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
  ## ref: http://kubernetes.io/docs/user-guide/images/#pre-pulling-images
  ##
  pullPolicy: IfNotPresent
  ## Optionally specify an array of imagePullSecrets.
  ## Secrets must be manually created in the namespace.
  ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
  ##
  # pullSecrets:
  #   - myRegistryKeySecretName
  ## Set to true if you would like to see extra information on logs
  ## It turns BASH and/or NAMI debugging in the image
  ##
  debug: false

zookeeper:
  image:
    registry: docker.io
    repository: bitnami/zookeeper
    tag: 3.6.2-debian-10-r185

  # -- If not exists external registry, the zookeeper registry will be used by default.
  enabled: true
  service:
    # -- The port of zookeeper
    port: 2181
  # -- A list of comma separated Four Letter Words commands to use
  fourlwCommandsWhitelist: "srvr,ruok,wchs,cons"
  persistence:
    # -- Set `zookeeper.persistence.enabled` to true to mount a new volume for internal ZooKeeper
    enabled: false
    # -- PersistentVolumeClaim size
    size: "20Gi"
    # -- ZooKeeper data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClass: "-"

（5）、修改master配置

master:
  # -- Enable or disable the Master component
  enabled: true
  replicas: "1"
  resources:
    limits:
      memory: "4Gi"
      cpu: "4"
    requests:
      memory: "2Gi"
      cpu: "500m"  
  persistentVolumeClaim:
    # -- Set `worker.persistentVolumeClaim.enabled` to `true` to enable `persistentVolumeClaim` for `worker`
    enabled: true
    ## dolphinscheduler data volume
    dataPersistentVolume:
      # -- Set `worker.persistentVolumeClaim.dataPersistentVolume.enabled` to `true` to mount a data volume for `worker`
      enabled: true
      # -- `PersistentVolumeClaim` access modes
      accessModes:
      - "ReadWriteOnce"
      # -- `Worker` data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClassName: "-"
      # -- `PersistentVolumeClaim` size
      storage: "20Gi"
  env:
    # -- The jvm options for master server
    JAVA_OPTS: "-Xms1g -Xmx1g -Xmn512m"

（6）、修改worker配置

nfs-storage存储卷的创建
sc.yaml配置文件如下

## 创建了一个存储类
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
  name: nfs-storage
  annotations:
    storageclass.kubernetes.io/is-default-class: "true"
provisioner: k8s-sigs.io/nfs-subdir-external-provisioner
parameters:
  archiveOnDelete: "true"  ## 删除pv的时候，pv的内容是否要备份

---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nfs-client
  labels:
    app: nfs-client
  # replace with namespace where provisioner is deployed
  namespace: default
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: nfs-client
  template:
    metadata:
      labels:
        app: nfs-client
    spec:
      serviceAccountName: nfs-client
      containers:
        - name: nfs-client
          image: registry.cn-hangzhou.aliyuncs.com/lfy_k8s_images/nfs-subdir-external-provisioner:v4.0.2
          # resources:
          #    limits:
          #      cpu: 10m
          #    requests:
          #      cpu: 10m
          volumeMounts:
            - name: nfs-client-root
              mountPath: /persistentvolumes
          env:
            - name: PROVISIONER_NAME
              value: k8s-sigs.io/nfs-subdir-external-provisioner
            - name: NFS_SERVER
              value: 192.168.255.140 ## 指定自己nfs服务器地址
            - name: NFS_PATH  
              value: /data/nfsdata  ## nfs服务器共享的目录
      volumes:
        - name: nfs-client-root
          nfs:
            server: 192.168.255.140
            path: /data/nfsdata
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: nfs-client
  # replace with namespace where provisioner is deployed
  namespace: default
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: nfs-client-runner
rules:
  - apiGroups: [""]
    resources: ["nodes"]
    verbs: ["get", "list", "watch"]
  - apiGroups: [""]
    resources: ["persistentvolumes"]
    verbs: ["get", "list", "watch", "create", "delete"]
  - apiGroups: [""]
    resources: ["persistentvolumeclaims"]
    verbs: ["get", "list", "watch", "update"]
  - apiGroups: ["storage.k8s.io"]
    resources: ["storageclasses"]
    verbs: ["get", "list", "watch"]
  - apiGroups: [""]
    resources: ["events"]
    verbs: ["create", "update", "patch"]
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: run-nfs-client
subjects:
  - kind: ServiceAccount
    name: nfs-client
    # replace with namespace where provisioner is deployed
    namespace: default
roleRef:
  kind: ClusterRole
  name: nfs-client-runner
  apiGroup: rbac.authorization.k8s.io
---
kind: Role
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: leader-locking-nfs-client
  # replace with namespace where provisioner is deployed
  namespace: default
rules:
  - apiGroups: [""]
    resources: ["endpoints"]
    verbs: ["get", "list", "watch", "create", "update", "patch"]
---
kind: RoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: leader-locking-nfs-client
  # replace with namespace where provisioner is deployed
  namespace: default
subjects:
  - kind: ServiceAccount
    name: nfs-client
    # replace with namespace where provisioner is deployed
    namespace: default
roleRef:
  kind: Role
  name: leader-locking-nfs-client
  apiGroup: rbac.authorization.k8s.io

执行命令：

# 执行发布安装
kubectl apply -f sc.yaml

# 查看nfs-client-provisioner pod 是否安装成功
kubectl get pod -A

Worker节点配置如下：

worker:
  # -- Enable or disable the Worker component
  enabled: true
  replicas: "1"
  resources:
    limits:
      memory: "4Gi"
      cpu: "2"
    requests:
      memory: "2Gi"
      cpu: "500m"  
  persistentVolumeClaim:
    # -- Set `worker.persistentVolumeClaim.enabled` to `true` to enable `persistentVolumeClaim` for `worker`
    enabled: true
    ## dolphinscheduler data volume
    dataPersistentVolume:
      # -- Set `worker.persistentVolumeClaim.dataPersistentVolume.enabled` to `true` to mount a data volume for `worker`
      enabled: true
      # -- `PersistentVolumeClaim` access modes
      accessModes:
      - "ReadWriteOnce"
      # -- `Worker` data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClassName: "nfs-storage"
      # -- `PersistentVolumeClaim` size
      storage: "20Gi"
  env:
    # -- The jvm options for master server
    JAVA_OPTS: "-Xms1g -Xmx1g -Xmn512m"

（6）、修改alter配置

alert:
  # -- Enable or disable the Worker component
  enabled: true
  replicas: "1"
  resources:
    limits:
      memory: "2Gi"
      cpu: "1"
    requests:
      memory: "1Gi"
      cpu: "500m"
  persistentVolumeClaim:
    # -- Set `worker.persistentVolumeClaim.enabled` to `true` to enable `persistentVolumeClaim` for `worker`
    enabled: true
    ## dolphinscheduler data volume
    dataPersistentVolume:
      # -- Set `worker.persistentVolumeClaim.dataPersistentVolume.enabled` to `true` to mount a data volume for `worker`
      enabled: true
      # -- `PersistentVolumeClaim` access modes
      accessModes:
      - "ReadWriteOnce"
      # -- `Worker` data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClassName: "-"
      # -- `PersistentVolumeClaim` size
      storage: "20Gi"
  env:
    # -- The jvm options for master server
    JAVA_OPTS: "-Xms1g -Xmx1g -Xmn512m"

完整的values.yaml配置文件如下：

#
# 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.

# -- World time and date for cities in all time zones
timezone: "Asia/Shanghai"

# -- Used to detect whether dolphinscheduler dependent services such as database are ready
initImage:
  # -- Image pull policy. Options: Always, Never, IfNotPresent
  pullPolicy: "IfNotPresent"
  # -- Specify initImage repository
  busybox: "registry.cn-hangzhou.aliyuncs.com/docker_image-ljx/busybox:1.30.1"

image:
  # -- Docker image repository for the DolphinScheduler
  registry: registry.cn-hangzhou.aliyuncs.com/docker_image-ljx
  # -- Docker image version for the DolphinScheduler
  tag: 3.2.2
  # -- Image pull policy. Options: Always, Never, IfNotPresent
  pullPolicy: "IfNotPresent"
  # -- Specify a imagePullSecrets
  pullSecret: ""
  # -- master image
  master: dolphinscheduler-master
  # -- worker image
  worker: dolphinscheduler-worker
  # -- api-server image
  api: dolphinscheduler-api
  # -- alert-server image
  alert: dolphinscheduler-alert-server
  # -- tools image
  tools: dolphinscheduler-tools

datasource:
  # -- The profile of datasource
  profile: postgresql

postgresql:
  image:
    registry: docker.io
    repository: bitnami/postgresql
    tag: 11.11.0-debian-10-r71
  # -- If not exists external PostgreSQL, by default, the DolphinScheduler will use a internal PostgreSQL
  enabled: true
  # -- The username for internal PostgreSQL
  postgresqlUsername: "root"
  # -- The password for internal PostgreSQL
  postgresqlPassword: "root"
  # -- The database for internal PostgreSQL
  postgresqlDatabase: "dolphinscheduler"
  # -- The driverClassName for internal PostgreSQL
  driverClassName: "org.postgresql.Driver"
  # -- The params for internal PostgreSQL
  params: "characterEncoding=utf8"
  persistence:
    # -- Set postgresql.persistence.enabled to true to mount a new volume for internal PostgreSQL
    enabled: false
    # -- `PersistentVolumeClaim` size
    size: "20Gi"
    # -- PostgreSQL data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClass: "-"

mysql:
  image:
    registry: docker.io
    repository: bitnami/mysql
    tag: 8.0.31-debian-11-r0
  # -- If not exists external MySQL, by default, the DolphinScheduler will use a internal MySQL
  enabled: false
  # -- mysql driverClassName
  driverClassName: "com.mysql.cj.jdbc.Driver"
  auth:
    # -- mysql username
    username: "ds"
    # -- mysql password
    password: "ds"
    # -- mysql database
    database: "dolphinscheduler"
    # -- mysql params
    params: "characterEncoding=utf8"
  primary:
    persistence:
      # -- Set mysql.primary.persistence.enabled to true to mount a new volume for internal MySQL
      enabled: false
      # -- `PersistentVolumeClaim` size
      size: "20Gi"
      # -- MySQL data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClass: "-"

minio:
  image:
    registry: docker.io
    repository: bitnami/minio
    tag: 2022.10.29-debian-11-r0
  # -- Deploy minio and configure it as the default storage for DolphinScheduler, note this is for demo only, not for production.
  enabled: true
  auth:
    # -- minio username
    rootUser: minioadmin
    # -- minio password
    rootPassword: minioadmin
  persistence:
    # -- Set minio.persistence.enabled to true to mount a new volume for internal minio
    enabled: false
  # -- minio default buckets
  defaultBuckets: "dolphinscheduler"


externalDatabase:
  # -- If exists external database, and set postgresql.enable value to false.
  # external database will be used, otherwise Dolphinscheduler's internal database will be used.
  enabled: false
  # -- The type of external database, supported types: postgresql, mysql
  type: "postgresql"
  # -- The host of external database
  host: "localhost"
  # -- The port of external database
  port: "5432"
  # -- The username of external database
  username: "root"
  # -- The password of external database
  password: "root"
  # -- The database of external database
  database: "dolphinscheduler"
  # -- The params of external database
  params: "characterEncoding=utf8"
  # -- The driverClassName of external database
  driverClassName: "org.postgresql.Driver"

zookeeper:
  image:
    registry: docker.io
    repository: bitnami/zookeeper
    tag: 3.6.2-debian-10-r185
  # -- If not exists external registry, the zookeeper registry will be used by default.
  enabled: true
  service:
    # -- The port of zookeeper
    port: 2181
  # -- A list of comma separated Four Letter Words commands to use
  fourlwCommandsWhitelist: "srvr,ruok,wchs,cons"
  persistence:
    # -- Set `zookeeper.persistence.enabled` to true to mount a new volume for internal ZooKeeper
    enabled: false
    # -- PersistentVolumeClaim size
    size: "20Gi"
    # -- ZooKeeper data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClass: "-"

registryEtcd:
  # -- If you want to use Etcd for your registry center, change this value to true. And set zookeeper.enabled to false
  enabled: false
  # -- Etcd endpoints
  endpoints: ""
  # -- Etcd namespace
  namespace: "dolphinscheduler"
  # -- Etcd user
  user: ""
  # -- Etcd passWord
  passWord: ""
  # -- Etcd authority
  authority: ""
  # Please create a new folder: deploy/kubernetes/dolphinscheduler/etcd-certs
  ssl:
    # -- If your Etcd server has configured with ssl, change this value to true. About certification files you can see [here](https://github.com/etcd-io/jetcd/blob/main/docs/SslConfig.md) for how to convert.
    enabled: false
    # -- CertFile file path
    certFile: "etcd-certs/ca.crt"
    # -- keyCertChainFile file path
    keyCertChainFile: "etcd-certs/client.crt"
    # -- keyFile file path
    keyFile: "etcd-certs/client.pem"

registryJdbc:
  # -- If you want to use JDbc for your registry center, change this value to true. And set zookeeper.enabled and registryEtcd.enabled to false
  enabled: false
  # -- Used to schedule refresh the ephemeral data/ lock
  termRefreshInterval: 2s
  # -- Used to calculate the expire time
  termExpireTimes: 3
  hikariConfig:
    # -- Default use same Dolphinscheduler's database, if you want to use other database please change `enabled` to `true` and change other configs
    enabled: false
    # -- Default use same Dolphinscheduler's database if you don't change this value. If you set this value, Registry jdbc's database type will use it
    driverClassName: com.mysql.cj.jdbc.Driver
    # -- Default use same Dolphinscheduler's database if you don't change this value. If you set this value, Registry jdbc's database type will use it
    jdbcurl: jdbc:mysql://
    # -- Default use same Dolphinscheduler's database if you don't change this value. If you set this value, Registry jdbc's database type will use it
    username: ""
    # -- Default use same Dolphinscheduler's database if you don't change this value. If you set this value, Registry jdbc's database type will use it
    password: ""

## If exists external registry and set zookeeper.enable value to false, the external registry will be used.
externalRegistry:
  # -- If exists external registry and set `zookeeper.enable` && `registryEtcd.enabled` && `registryJdbc.enabled` to false, specify the external registry plugin name
  registryPluginName: "zookeeper"
  # -- If exists external registry and set `zookeeper.enable` && `registryEtcd.enabled` && `registryJdbc.enabled` to false, specify the external registry servers
  registryServers: "127.0.0.1:2181"

security:
  authentication:
    # -- Authentication types (supported types: PASSWORD,LDAP,CASDOOR_SSO)
    type: PASSWORD
    # IF you set type `LDAP`, below config will be effective
    ldap:
      # -- LDAP urls
      urls: ldap://ldap.forumsys.com:389/
      # -- LDAP base dn
      basedn: dc=example,dc=com
      # -- LDAP username
      username: cn=read-only-admin,dc=example,dc=com
      # -- LDAP password
      password: password
      user:
        # -- Admin user account when you log-in with LDAP
        admin: read-only-admin
        # -- LDAP user identity attribute
        identityattribute: uid
        # -- LDAP user email attribute
        emailattribute: mail
        # -- action when ldap user is not exist,default value: CREATE. Optional values include(CREATE,DENY)
        notexistaction: CREATE
      ssl:
        # -- LDAP ssl switch
        enable: false
        # -- LDAP jks file absolute path, do not change this value
        truststore: "/opt/ldapkeystore.jks"
        # -- LDAP jks file base64 content.
        # If you use macOS, please run `base64 -b 0 -i /path/to/your.jks`.
        # If you use Linux, please run `base64 -w 0 /path/to/your.jks`.
        # If you use Windows, please run `certutil -f -encode /path/to/your.jks`.
        # Then copy the base64 content to below field in one line
        jksbase64content: ""
        # -- LDAP jks password
        truststorepassword: ""

conf:
  # -- auto restart, if true, all components will be restarted automatically after the common configuration is updated. if false, you need to restart the components manually. default is false
  auto: false
  # common configuration
  common:
    # -- user data local directory path, please make sure the directory exists and have read write permissions
    data.basedir.path: /tmp/dolphinscheduler

    # -- resource storage type: HDFS, S3, OSS, GCS, ABS, NONE
    resource.storage.type: S3

    # -- resource store on HDFS/S3 path, resource file will store to this base path, self configuration, please make sure the directory exists on hdfs and have read write permissions. "/dolphinscheduler" is recommended
    resource.storage.upload.base.path: /dolphinscheduler

    # -- The AWS access key. if resource.storage.type=S3 or use EMR-Task, This configuration is required
    resource.aws.access.key.id: minioadmin

    # -- The AWS secret access key. if resource.storage.type=S3 or use EMR-Task, This configuration is required
    resource.aws.secret.access.key: minioadmin

    # -- The AWS Region to use. if resource.storage.type=S3 or use EMR-Task, This configuration is required
    resource.aws.region: ca-central-1

    # -- The name of the bucket. You need to create them by yourself. Otherwise, the system cannot start. All buckets in Amazon S3 share a single namespace; ensure the bucket is given a unique name.
    resource.aws.s3.bucket.name: dolphinscheduler

    # -- You need to set this parameter when private cloud s3. If S3 uses public cloud, you only need to set resource.aws.region or set to the endpoint of a public cloud such as S3.cn-north-1.amazonaws.com.cn
    resource.aws.s3.endpoint: http://minio:9000

    # -- alibaba cloud access key id, required if you set resource.storage.type=OSS
    resource.alibaba.cloud.access.key.id: <your-access-key-id>

    # -- alibaba cloud access key secret, required if you set resource.storage.type=OSS
    resource.alibaba.cloud.access.key.secret: <your-access-key-secret>

    # -- alibaba cloud region, required if you set resource.storage.type=OSS
    resource.alibaba.cloud.region: cn-hangzhou

    # -- oss bucket name, required if you set resource.storage.type=OSS
    resource.alibaba.cloud.oss.bucket.name: dolphinscheduler

    # -- oss bucket endpoint, required if you set resource.storage.type=OSS
    resource.alibaba.cloud.oss.endpoint: https://oss-cn-hangzhou.aliyuncs.com

    # -- azure storage account name, required if you set resource.storage.type=ABS
    resource.azure.client.id: minioadmin

    # -- azure storage account key, required if you set resource.storage.type=ABS
    resource.azure.client.secret: minioadmin

    # -- azure storage subId, required if you set resource.storage.type=ABS
    resource.azure.subId: minioadmin

    # -- azure storage tenantId, required if you set resource.storage.type=ABS
    resource.azure.tenant.id: minioadmin

    # -- if resource.storage.type=HDFS, the user must have the permission to create directories under the HDFS root path
    resource.hdfs.root.user: hdfs

    # -- if resource.storage.type=S3, the value like: s3a://dolphinscheduler; if resource.storage.type=HDFS and namenode HA is enabled, you need to copy core-site.xml and hdfs-site.xml to conf dir
    resource.hdfs.fs.defaultFS: hdfs://mycluster:8020

    # -- whether to startup kerberos
    hadoop.security.authentication.startup.state: false

    # -- java.security.krb5.conf path
    java.security.krb5.conf.path: /opt/krb5.conf

    # -- login user from keytab username
    login.user.keytab.username: hdfs-mycluster@ESZ.COM

    # -- login user from keytab path
    login.user.keytab.path: /opt/hdfs.headless.keytab

    # -- kerberos expire time, the unit is hour
    kerberos.expire.time: 2

    # -- resourcemanager port, the default value is 8088 if not specified
    resource.manager.httpaddress.port: 8088

    # -- if resourcemanager HA is enabled, please set the HA IPs; if resourcemanager is single, keep this value empty
    yarn.resourcemanager.ha.rm.ids: 192.168.xx.xx,192.168.xx.xx

    # -- if resourcemanager HA is enabled or not use resourcemanager, please keep the default value; If resourcemanager is single, you only need to replace ds1 to actual resourcemanager hostname
    yarn.application.status.address: http://ds1:%s/ws/v1/cluster/apps/%s

    # -- job history status url when application number threshold is reached(default 10000, maybe it was set to 1000)
    yarn.job.history.status.address: http://ds1:19888/ws/v1/history/mapreduce/jobs/%s

    # -- datasource encryption enable
    datasource.encryption.enable: false

    # -- datasource encryption salt
    datasource.encryption.salt: '!@#$%^&*'

    # -- data quality option
    data-quality.jar.dir:

    # -- Whether hive SQL is executed in the same session
    support.hive.oneSession: false

    # -- use sudo or not, if set true, executing user is tenant user and deploy user needs sudo permissions; if set false, executing user is the deploy user and doesn't need sudo permissions
    sudo.enable: true

    # -- development state
    development.state: false

    # -- rpc port
    alert.rpc.port: 50052

    # -- set path of conda.sh
    conda.path: /opt/anaconda3/etc/profile.d/conda.sh

    # -- Task resource limit state
    task.resource.limit.state: false

    # -- mlflow task plugin preset repository
    ml.mlflow.preset_repository: https://github.com/apache/dolphinscheduler-mlflow

    # -- mlflow task plugin preset repository version
    ml.mlflow.preset_repository_version: "main"

    # -- way to collect applicationId: log, aop
    appId.collect: log

common:
  ## Configmap
  configmap:
    # -- The jvm options for dolphinscheduler, suitable for all servers
    DOLPHINSCHEDULER_OPTS: ""
    # -- User data directory path, self configuration, please make sure the directory exists and have read write permissions
    DATA_BASEDIR_PATH: "/tmp/dolphinscheduler"

    # -- Resource store on HDFS/S3 path, please make sure the directory exists on hdfs and have read write permissions
    RESOURCE_UPLOAD_PATH: "/dolphinscheduler"

    # dolphinscheduler env
    # -- Set `HADOOP_HOME` for DolphinScheduler's task environment
    HADOOP_HOME: "/opt/soft/hadoop"
    # -- Set `HADOOP_CONF_DIR` for DolphinScheduler's task environment
    HADOOP_CONF_DIR: "/opt/soft/hadoop/etc/hadoop"
    # -- Set `SPARK_HOME` for DolphinScheduler's task environment
    SPARK_HOME: "/opt/soft/spark"
    # -- Set `PYTHON_LAUNCHER` for DolphinScheduler's task environment
    PYTHON_LAUNCHER: "/usr/bin/python/bin/python3"
    # -- Set `JAVA_HOME` for DolphinScheduler's task environment
    JAVA_HOME: "/opt/java/openjdk"
    # -- Set `HIVE_HOME` for DolphinScheduler's task environment
    HIVE_HOME: "/opt/soft/hive"
    # -- Set `FLINK_HOME` for DolphinScheduler's task environment
    FLINK_HOME: "/opt/soft/flink"
    # -- Set `DATAX_LAUNCHER` for DolphinScheduler's task environment
    DATAX_LAUNCHER: "/opt/soft/datax/bin/datax.py"
  ## Shared storage persistence mounted into api, master and worker, such as Hadoop, Spark, Flink and DataX binary package
  sharedStoragePersistence:
    # -- Set `common.sharedStoragePersistence.enabled` to `true` to mount a shared storage volume for Hadoop, Spark binary and etc
    enabled: false
    # -- The mount path for the shared storage volume
    mountPath: "/opt/soft"
    # -- `PersistentVolumeClaim` access modes, must be `ReadWriteMany`
    accessModes:
    - "ReadWriteMany"
    # -- Shared Storage persistent volume storage class, must support the access mode: ReadWriteMany
    storageClassName: "-"
    # -- `PersistentVolumeClaim` size
    storage: "20Gi"
  ## If RESOURCE_STORAGE_TYPE is HDFS and FS_DEFAULT_FS is file:///, fsFileResourcePersistence should be enabled for resource storage
  fsFileResourcePersistence:
    # -- Set `common.fsFileResourcePersistence.enabled` to `true` to mount a new file resource volume for `api` and `worker`
    enabled: false
    # -- `PersistentVolumeClaim` access modes, must be `ReadWriteMany`
    accessModes:
    - "ReadWriteMany"
    # -- Resource persistent volume storage class, must support the access mode: `ReadWriteMany`
    storageClassName: "-"
    # -- `PersistentVolumeClaim` size
    storage: "20Gi"

master:
  # -- Enable or disable the Master component
  enabled: true
  # -- 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: "1"
  # -- 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: [node-affinity](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity)
  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: [assign-pod-node](https://kubernetes.io/docs/concepts/scheduling-eviction/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.
  # More info: [manage-resources-containers](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/)
  #resources: {}
  resources:
    limits:
      memory: "4Gi"
      cpu: "4"
    requests:
      memory: "2Gi"
      cpu: "500m"
  # -- enable configure custom config
  enableCustomizedConfig: false
  # -- configure aligned with https://github.com/apache/dolphinscheduler/blob/dev/dolphinscheduler-master/src/main/resources/application.yaml
  customizedConfig: { }
  #  customizedConfig:
  #    application.yaml: |
  #      profiles:
  #        active: postgresql
  #      banner:
  #        charset: UTF-8
  #      jackson:
  #        time-zone: UTC
  #        date-format: "yyyy-MM-dd HH:mm:ss"
  # -- Periodic probe of container liveness. Container will be restarted if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  livenessProbe:
    # -- Turn on and off liveness probe
    enabled: true
    # -- Delay before liveness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  readinessProbe:
    # -- Turn on and off readiness probe
    enabled: true
    # -- Delay before readiness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    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:
    # -- Set `master.persistentVolumeClaim.enabled` to `true` to mount a new volume for `master`
    enabled: false
    # -- `PersistentVolumeClaim` access modes
    accessModes:
    - "ReadWriteOnce"
    # -- `Master` logs data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClassName: "-"
    # -- `PersistentVolumeClaim` size
    storage: "20Gi"
  env:
    # -- The jvm options for master server
    JAVA_OPTS: "-Xms1g -Xmx1g -Xmn512m"
    # -- Master execute thread number to limit process instances
    MASTER_EXEC_THREADS: "100"
    # -- Master execute task number in parallel per process instance
    MASTER_EXEC_TASK_NUM: "20"
    # -- Master dispatch task number per batch
    MASTER_DISPATCH_TASK_NUM: "3"
    # -- Master host selector to select a suitable worker, optional values include Random, RoundRobin, LowerWeight
    MASTER_HOST_SELECTOR: "LowerWeight"
    # -- Master max heartbeat interval
    MASTER_MAX_HEARTBEAT_INTERVAL: "10s"
    # -- Master heartbeat error threshold
    MASTER_HEARTBEAT_ERROR_THRESHOLD: "5"
    # -- Master commit task retry times
    MASTER_TASK_COMMIT_RETRYTIMES: "5"
    # -- master commit task interval, the unit is second
    MASTER_TASK_COMMIT_INTERVAL: "1s"
    # -- master state wheel interval, the unit is second
    MASTER_STATE_WHEEL_INTERVAL: "5s"
    # -- If set true, will open master overload protection
    MASTER_SERVER_LOAD_PROTECTION_ENABLED: false
    # -- Master max system cpu usage, when the master's system cpu usage is smaller then this value, master server can execute workflow.
    MASTER_SERVER_LOAD_PROTECTION_MAX_SYSTEM_CPU_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Master max jvm cpu usage, when the master's jvm cpu usage is smaller then this value, master server can execute workflow.
    MASTER_SERVER_LOAD_PROTECTION_MAX_JVM_CPU_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Master max System memory usage , when the master's system memory usage is smaller then this value, master server can execute workflow.
    MASTER_SERVER_LOAD_PROTECTION_MAX_SYSTEM_MEMORY_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Master max disk usage , when the master's disk usage is smaller then this value, master server can execute workflow.
    MASTER_SERVER_LOAD_PROTECTION_MAX_DISK_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Master failover interval, the unit is minute
    MASTER_FAILOVER_INTERVAL: "10m"
    # -- Master kill application when handle failover
    MASTER_KILL_APPLICATION_WHEN_HANDLE_FAILOVER: "true"
  service:
    # -- annotations may need to be set when want to scrapy metrics by prometheus but not install prometheus operator
    annotations: {}
    # -- serviceMonitor for prometheus operator
    serviceMonitor:
      # -- Enable or disable master serviceMonitor
      enabled: false
      # -- serviceMonitor.interval interval at which metrics should be scraped
      interval: 15s
      # -- serviceMonitor.path path of the metrics endpoint
      path: /actuator/prometheus
      # -- serviceMonitor.labels ServiceMonitor extra labels
      labels: {}
      # -- serviceMonitor.annotations ServiceMonitor annotations
      annotations: {}

worker:
  # -- Enable or disable the Worker component
  enabled: true
  # -- 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: [node-affinity](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity)
  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: [assign-pod-node](https://kubernetes.io/docs/concepts/scheduling-eviction/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.
  # More info: [manage-resources-containers](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/)
  #resources: {}
  resources:
    limits:
      memory: "4Gi"
      cpu: "2"
    requests:
      memory: "2Gi"
      cpu: "500m"

  # -- Periodic probe of container liveness. Container will be restarted if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  # -- enable configure custom config
  enableCustomizedConfig: false
  # -- configure aligned with https://github.com/apache/dolphinscheduler/blob/dev/dolphinscheduler-worker/src/main/resources/application.yaml
  customizedConfig: { }
#  customizedConfig:
#    application.yaml: |
#      banner:
#        charset: UTF-8
#      jackson:
#        time-zone: UTC
#        date-format: "yyyy-MM-dd HH:mm:ss"
  livenessProbe:
    # -- Turn on and off liveness probe
    enabled: true
    # -- Delay before liveness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  readinessProbe:
    # -- Turn on and off readiness probe
    enabled: true
    # -- Delay before readiness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    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:
    # -- Set `worker.persistentVolumeClaim.enabled` to `true` to enable `persistentVolumeClaim` for `worker`
    enabled: false
    ## dolphinscheduler data volume
    dataPersistentVolume:
      # -- Set `worker.persistentVolumeClaim.dataPersistentVolume.enabled` to `true` to mount a data volume for `worker`
      enabled: false
      # -- `PersistentVolumeClaim` access modes
      accessModes:
      - "ReadWriteOnce"
      # -- `Worker` data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClassName: "nfs-storage"
      # -- `PersistentVolumeClaim` size
      storage: "20Gi"
    ## dolphinscheduler logs volume
    logsPersistentVolume:
      # -- Set `worker.persistentVolumeClaim.logsPersistentVolume.enabled` to `true` to mount a logs volume for `worker`
      enabled: false
      # -- `PersistentVolumeClaim` access modes
      accessModes:
      - "ReadWriteOnce"
      # -- `Worker` logs data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
      storageClassName: "-"
      # -- `PersistentVolumeClaim` size
      storage: "20Gi"
  env:
    # -- If set true, will open worker overload protection
    WORKER_SERVER_LOAD_PROTECTION_ENABLED: false
    # -- Worker max system cpu usage, when the worker's system cpu usage is smaller then this value, worker server can be dispatched tasks.
    WORKER_SERVER_LOAD_PROTECTION_MAX_SYSTEM_CPU_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Worker max jvm cpu usage, when the worker's jvm cpu usage is smaller then this value, worker server can be dispatched tasks.
    WORKER_SERVER_LOAD_PROTECTION_MAX_JVM_CPU_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Worker max memory usage , when the worker's memory usage is smaller then this value, worker server can be dispatched tasks.
    WORKER_SERVER_LOAD_PROTECTION_MAX_SYSTEM_MEMORY_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Worker max disk usage , when the worker's disk usage is smaller then this value, worker server can be dispatched tasks.
    WORKER_SERVER_LOAD_PROTECTION_MAX_DISK_USAGE_PERCENTAGE_THRESHOLDS: 0.7
    # -- Worker execute thread number to limit task instances
    WORKER_EXEC_THREADS: "100"
    # -- Worker heartbeat interval
    WORKER_MAX_HEARTBEAT_INTERVAL: "10s"
    # -- Worker host weight to dispatch tasks
    WORKER_HOST_WEIGHT: "100"
    # -- tenant corresponds to the user of the system, which is used by the worker to submit the job. If system does not have this user, it will be automatically created after the parameter worker.tenant.auto.create is true.
    WORKER_TENANT_CONFIG_AUTO_CREATE_TENANT_ENABLED: true
    # -- Scenes to be used for distributed users. For example, users created by FreeIpa are stored in LDAP. This parameter only applies to Linux, When this parameter is true, worker.tenant.auto.create has no effect and will not automatically create tenants.
    WORKER_TENANT_CONFIG_DISTRIBUTED_TENANT: false
    # -- If set true, will use worker bootstrap user as the tenant to execute task when the tenant is `default`;
    DEFAULT_TENANT_ENABLED: false

  keda:
    # -- Enable or disable the Keda component
    enabled: false
    # -- Keda namespace labels
    namespaceLabels: { }

    # -- How often KEDA polls the DolphinScheduler DB to report new scale requests to the HPA
    pollingInterval: 5

    # -- How many seconds KEDA will wait before scaling to zero.
    # Note that HPA has a separate cooldown period for scale-downs
    cooldownPeriod: 30

    # -- Minimum number of workers created by keda
    minReplicaCount: 0

    # -- Maximum number of workers created by keda
    maxReplicaCount: 3

    # -- Specify HPA related options
    advanced: { }
    # horizontalPodAutoscalerConfig:
    #   behavior:
    #     scaleDown:
    #       stabilizationWindowSeconds: 300
    #       policies:
    #         - type: Percent
    #           value: 100
    #           periodSeconds: 15
  service:
    # -- annotations may need to be set when want to scrapy metrics by prometheus but not install prometheus operator
    annotations: {}
    # -- serviceMonitor for prometheus operator
    serviceMonitor:
      # -- Enable or disable worker serviceMonitor
      enabled: false
      # -- serviceMonitor.interval interval at which metrics should be scraped
      interval: 15s
      # -- serviceMonitor.path path of the metrics endpoint
      path: /actuator/prometheus
      # -- serviceMonitor.labels ServiceMonitor extra labels
      labels: {}
      # -- serviceMonitor.annotations ServiceMonitor annotations
      annotations: {}


alert:
  # -- Enable or disable the Alert-Server component
  enabled: true
  # -- 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 of deployment. Can be "Recreate" or "RollingUpdate"
    type: "RollingUpdate"
    rollingUpdate:
      # -- The maximum number of pods that can be scheduled above the desired number of pods
      maxSurge: "25%"
      # -- The maximum number of pods that can be unavailable during the update
      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: {}
  # -- Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  # More info: [node-affinity](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity)
  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: [assign-pod-node](https://kubernetes.io/docs/concepts/scheduling-eviction/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.
  # More info: [manage-resources-containers](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/)
  #resources: {}
  resources:
    limits:
      memory: "2Gi"
      cpu: "1"
    requests:
      memory: "1Gi"
      cpu: "500m"
  # -- enable configure custom config
  enableCustomizedConfig: false
  # -- configure aligned with https://github.com/apache/dolphinscheduler/blob/dev/dolphinscheduler-alert/dolphinscheduler-alert-server/src/main/resources/application.yaml
  customizedConfig: { }
  #  customizedConfig:
  #    application.yaml: |
  #      profiles:
  #        active: postgresql
  #      banner:
  #        charset: UTF-8
  #      jackson:
  #        time-zone: UTC
  #        date-format: "yyyy-MM-dd HH:mm:ss"
  # -- Periodic probe of container liveness. Container will be restarted if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  livenessProbe:
    # -- Turn on and off liveness probe
    enabled: true
    # -- Delay before liveness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  readinessProbe:
    # -- Turn on and off readiness probe
    enabled: true
    # -- Delay before readiness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  # More info: [persistentvolumeclaims](https://kubernetes.io/docs/concepts/storage/persistent-volumes/#persistentvolumeclaims)
  persistentVolumeClaim:
    # -- Set `alert.persistentVolumeClaim.enabled` to `true` to mount a new volume for `alert`
    enabled: false
    # -- `PersistentVolumeClaim` access modes
    accessModes:
    - "ReadWriteOnce"
    # -- `Alert` logs data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClassName: "-"
    # -- `PersistentVolumeClaim` size
    storage: "20Gi"
  env:
    # -- The jvm options for alert server
    JAVA_OPTS: "-Xms512m -Xmx512m -Xmn256m"
  service:
    # -- annotations may need to be set when want to scrapy metrics by prometheus but not install prometheus operator
    annotations: {}
    # -- serviceMonitor for prometheus operator
    serviceMonitor:
      # -- Enable or disable alert-server serviceMonitor
      enabled: false
      # -- serviceMonitor.interval interval at which metrics should be scraped
      interval: 15s
      # -- serviceMonitor.path path of the metrics endpoint
      path: /actuator/prometheus
      # -- serviceMonitor.labels ServiceMonitor extra labels
      labels: {}
      # -- serviceMonitor.annotations ServiceMonitor annotations
      annotations: {}


api:
  # -- Enable or disable the API-Server component
  enabled: true
  # -- 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 of deployment. Can be "Recreate" or "RollingUpdate"
    type: "RollingUpdate"
    rollingUpdate:
      # -- The maximum number of pods that can be scheduled above the desired number of pods
      maxSurge: "25%"
      # -- The maximum number of pods that can be unavailable during the update
      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: {}
  # -- Affinity is a group of affinity scheduling rules. If specified, the pod's scheduling constraints.
  # More info: [node-affinity](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity)
  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: [assign-pod-node](https://kubernetes.io/docs/concepts/scheduling-eviction/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.
  # More info: [manage-resources-containers](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/)
  #resources: {}
  resources:
    limits:
      memory: "2Gi"
      cpu: "4"
    requests:
      memory: "1Gi"
      cpu: "500m"
  # -- enable configure custom config
  enableCustomizedConfig: false
  # -- configure aligned with https://github.com/apache/dolphinscheduler/blob/dev/dolphinscheduler-api/src/main/resources/application.yaml
  customizedConfig: { }
  #  customizedConfig:
  #    application.yaml: |
  #      profiles:
  #        active: postgresql
  #      banner:
  #        charset: UTF-8
  #      jackson:
  #        time-zone: UTC
  #        date-format: "yyyy-MM-dd HH:mm:ss"
  # -- Periodic probe of container liveness. Container will be restarted if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  livenessProbe:
    # -- Turn on and off liveness probe
    enabled: true
    # -- Delay before liveness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails.
  # More info: [container-probes](https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes)
  readinessProbe:
    # -- Turn on and off readiness probe
    enabled: true
    # -- Delay before readiness probe is initiated
    initialDelaySeconds: "30"
    # -- How often to perform the probe
    periodSeconds: "30"
    # -- When the probe times out
    timeoutSeconds: "5"
    # -- Minimum consecutive failures for the probe
    failureThreshold: "3"
    # -- Minimum consecutive successes for the probe
    successThreshold: "1"
  # -- PersistentVolumeClaim represents a reference to a PersistentVolumeClaim in the same namespace.
  # More info: [persistentvolumeclaims](https://kubernetes.io/docs/concepts/storage/persistent-volumes/#persistentvolumeclaims)
  persistentVolumeClaim:
    # -- Set `api.persistentVolumeClaim.enabled` to `true` to mount a new volume for `api`
    enabled: false
    # -- `PersistentVolumeClaim` access modes
    accessModes:
    - "ReadWriteOnce"
    # -- `api` logs data persistent volume storage class. If set to "-", storageClassName: "", which disables dynamic provisioning
    storageClassName: "-"
    # -- `PersistentVolumeClaim` size
    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 api service is exposed when type=NodePort
    nodePort: ""
    # -- pythonNodePort is the port on each node on which this python api service is exposed when type=NodePort
    pythonNodePort: ""
    # -- 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: {}
    # -- serviceMonitor for prometheus operator
    serviceMonitor:
      # -- Enable or disable api-server serviceMonitor
      enabled: false
      # -- serviceMonitor.interval interval at which metrics should be scraped
      interval: 15s
      # -- serviceMonitor.path path of the metrics endpoint
      path: /dolphinscheduler/actuator/prometheus
      # -- serviceMonitor.labels ServiceMonitor extra labels
      labels: {}
      # -- serviceMonitor.annotations ServiceMonitor annotations
      annotations: {}
  env:
    # -- The jvm options for api server
    JAVA_OPTS: "-Xms512m -Xmx512m -Xmn256m"
  taskTypeFilter:
    # -- Enable or disable the task type filter.
    # If set to true, the API-Server will return tasks of a specific type set in api.taskTypeFilter.task
    # Note: This feature only filters tasks to return a specific type on the WebUI. However, you can still create any task that DolphinScheduler supports via the API.
    enabled: false
    # -- taskTypeFilter.taskType task type
    # -- ref: [task-type-config.yaml](https://github.com/apache/dolphinscheduler/blob/dev/dolphinscheduler-api/src/main/resources/task-type-config.yaml)
    task: {}
    #  example task sets
    #  universal:
    #    - 'SQL'
    #  cloud: []
    #  logic: []
    #  dataIntegration: []
    #  dataQuality: []
    #  machineLearning: []
    #  other: []


ingress:
  # -- Enable ingress
  enabled: true
  # -- Ingress host
  host: "dolphinscheduler.tyzwkj.cn"
  # -- Ingress path
  path: "/dolphinscheduler"
  # -- Ingress annotations
  annotations: {}
  tls:
    # -- Enable ingress tls
    enabled: false
    # -- Ingress tls secret name
    secretName: "dolphinscheduler-tls"

3、执行安装

（1）、安装前检查

[root@master dolphinscheduler]# helm template dolphinscheduler -f values.yaml ./

（2）、安装

[root@master dolphinscheduler]# kubectl create namespace dolphinscheduler
[root@master dolphinscheduler]# helm -n dolphinscheduler  install dolphinscheduler -f values.yaml  ./

在这里插入图片描述

（3）、查看安装进度

[root@master dolphinscheduler]# kubectl get all -n dolphinscheduler

在这里插入图片描述

（4）、添加ingress配置实现访问ui

【重点】
配置完成后，Dolphinscheduler管理端的UI访问地址为： http://dolphinscheduler.tyzwkj.cn/dolphinscheduler/ui/，但是此时由于dolphinscheduler.tyzwkj.cn自定义域名还不能自动解析，需要在本地hosts文件中添加路由后才可以访问
在这里插入图片描述

4、登录

配置完hosts后在浏览器中输入http://dolphinscheduler.tyzwkj.cn/dolphinscheduler/ui/
用户名：admin
密码：dolphinscheduler123
在这里插入图片描述
结束，以上就是通过k8s部署Apache Dolphinscheduler集群的全部内容。

K8s集群+Rancher Server：部署DolphinScheduler 3.2.2集群