FROM apache/flink:1.15.3-scala_2.12
# 需要用到的jar包
# flink-cdc
ADD lib/flink-sql-connector-mysql-cdc-2.3.0.jar /opt/flink/lib/
# jdbc連接器
ADD lib/flink-connector-jdbc-1.15.3.jar /opt/flink/lib/
# mysql驅動
ADD lib/mysql-connector-j-8.0.32.jar /opt/flink/lib/
# oracle驅動
ADD lib/ojdbc8-21.9.0.0.jar /opt/flink/lib/
# 文件系統(tǒng)插件需要放到插件目錄,按規(guī)范放置
RUN mkdir /opt/flink/plugins/s3-fs-presto && cp -f /opt/flink/opt/flink-s3-fs-presto-1.15.3.jar /opt/flink/plugins/s3-fs-presto/

docker build -t sivdead/flink:1.15.3_scala_2.12 -f .\DockerFile .

apiVersion: v1
kind: ConfigMap
metadata:
  name: flink-config
  namespace: szyx-flink
  labels:
    app: flink
data:
  flink-conf.yaml: |+
    kubernetes.cluster-id: szyx-flink
    # 所在的命名空間
    kubernetes.namespace: szyx-flink
    jobmanager.rpc.address: flink-jobmanager
    taskmanager.numberOfTaskSlots: 2
    blob.server.port: 6124
    jobmanager.rpc.port: 6123
    taskmanager.rpc.port: 6122
    queryable-state.proxy.ports: 6125
    jobmanager.memory.process.size: 1600m
    taskmanager.memory.process.size: 2867m
    parallelism.default: 2
    execution.checkpointing.interval: 10s    
    # 文件系統(tǒng)
    fs.default-scheme: s3
    # minio地址
    s3.endpoint: https://minio.k8s.io:9000
    # minio的bucket
    s3.flink.bucket: szyxflink
    s3.access-key: <minio賬號>
    s3.secret-key: <minio密碼>
    # 狀態(tài)存儲格式
    state.backend: rocksdb
    s3.path.style.access: true
    blob.storage.directory: /opt/flink/tmp/blob
    web.upload.dir: /opt/flink/tmp/upload
    io.tmp.dirs: /opt/flink/tmp
    # 狀態(tài)管理
    # checkpoint存儲地址
    state.checkpoints.dir: s3://szyxflink/state/checkpoint
    # savepoint存儲地址
    state.savepoints.dir: s3://szyxflink/state/savepoint
    # checkpoint間隔
    execution.checkpointing.interval: 5000
    execution.checkpointing.mode: EXACTLY_ONCE
    # checkpoint保留數(shù)量
    state.checkpoints.num-retained: 3
    # history-server# 監(jiān)視以下目錄中已完成的作業(yè)
    jobmanager.archive.fs.dir: s3://szyxflink/completed-jobs
    # 每 10 秒刷新一次
    historyserver.archive.fs.refresh-interval: 10000
    historyserver.archive.fs.dir: s3://szyxflink/completed-jobs
    # 高可用
    high-availability: org.apache.flink.kubernetes.highavailability.KubernetesHaServicesFactory
    high-availability.storageDir: s3://szyxflink/ha
    # 每6個小時觸發(fā)一次savepoint
    kubernetes.operator.periodic.savepoint.interval: 6h
    kubernetes.operator.savepoint.history.max.age: 24h
    kubernetes.operator.savepoint.history.max.count: 5
    # Restart of unhealthy job deployments
    kubernetes.operator.cluster.health-check.enabled: true
    # Restart failed job deployments 
    kubernetes.operator.job.restart.failed: true
  log4j-console.properties: |+
    # This affects logging for both user code and Flink
    rootLogger.level = INFO
    rootLogger.appenderRef.console.ref = ConsoleAppender
    rootLogger.appenderRef.rolling.ref = RollingFileAppender
    # Uncomment this if you want to _only_ change Flink's logging
    #logger.flink.name = org.apache.flink
    #logger.flink.level = INFO
    # The following lines keep the log level of common libraries/connectors on
    # log level INFO. The root logger does not override this. You have to manually
    # change the log levels here.
    logger.akka.name = akka
    logger.akka.level = INFO
    logger.kafka.name= org.apache.kafka
    logger.kafka.level = INFO
    logger.hadoop.name = org.apache.hadoop
    logger.hadoop.level = INFO
    logger.zookeeper.name = org.apache.zookeeper
    logger.zookeeper.level = INFO
    # Log all infos to the console
    appender.console.name = ConsoleAppender
    appender.console.type = CONSOLE
    appender.console.layout.type = PatternLayout
    appender.console.layout.pattern = %d{yyyy-MM-dd HH:mm:ss,SSS} %-5p %-60c %x - %m%n
    # Log all infos in the given rolling file
    appender.rolling.name = RollingFileAppender
    appender.rolling.type = RollingFile
    appender.rolling.append = false
    appender.rolling.fileName = ${sys:log.file}
    appender.rolling.filePattern = ${sys:log.file}.%i
    appender.rolling.layout.type = PatternLayout
    appender.rolling.layout.pattern = %d{yyyy-MM-dd HH:mm:ss,SSS} %-5p %-60c %x - %m%n
    appender.rolling.policies.type = Policies
    appender.rolling.policies.size.type = SizeBasedTriggeringPolicy
    appender.rolling.policies.size.size=100MB
    appender.rolling.strategy.type = DefaultRolloverStrategy
    appender.rolling.strategy.max = 10
    # Suppress the irrelevant (wrong) warnings from the Netty channel handler
    logger.netty.name = org.jboss.netty.channel.DefaultChannelPipeline
    logger.netty.level = OFF

apiVersion: v1
kind: ServiceAccount
metadata:
  name: flink-service-account
  namespace: szyx-flink
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  namespace: szyx-flink
  name: flink
rules:
- apiGroups: [""]
  resources: ["pods", "services"，"configmaps"]
  verbs: ["create", "get", "list", "watch", "delete"]
- apiGroups: [""]
  resources: ["pods/log"]
  verbs: ["get"]
- apiGroups: ["batch"]
  resources: ["jobs"]
  verbs: ["create", "get", "list", "watch", "delete"]
- apiGroups: ["extensions"]
  resources: ["ingresses"]
  verbs: ["create", "get", "list", "watch", "delete"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  namespace: szyx-flink
  name: flink-role-binding
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: flink
subjects:
- kind: ServiceAccount
  name: flink-service-account
  namespace: flink

apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: flink-tmp
  namespace: szyx-flink
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 40Gi

apiVersion: apps/v1
kind: Deployment
metadata:
  name: flink-jobmanager
  namespace: szyx-flink
spec:
  replicas: 1 # Set the value to greater than 1 to start standby JobManagers
  selector:
    matchLabels:
      app: flink
      component: jobmanager
  template:
    metadata:
      labels:
        app: flink
        component: jobmanager
    spec:
      containers:
      - name: jobmanager
        imagePullPolicy: Always
        image: sivdead/flink:1.15.3_scala_2.12
        env:
        # 注入POD的ip到容器內
        - name: POD_IP
          valueFrom:
            fieldRef:
              apiVersion: v1
              fieldPath: status.podIP
        # 時區(qū)
        - name: TZ
          value: Asia/Shanghai
        # The following args overwrite the value of jobmanager.rpc.address configured in the configuration config map to POD_IP.
        args: ["jobmanager", "$(POD_IP)"]
        ports:
        - containerPort: 6123
          name: rpc
        - containerPort: 6124
          name: blob-server
        - containerPort: 8081
          name: webui
        livenessProbe:
          tcpSocket:
            port: 6123
          initialDelaySeconds: 30
          periodSeconds: 60
        resources:
          requests:
            memory: "8192Mi"
            cpu: "4"
          limits:
            memory: "8192Mi"
            cpu: "4"
        volumeMounts:
        - name: flink-config-volume
          mountPath: /opt/flink/conf
        - name: tmp-dir
          mountPath: /opt/flink/tmp
        securityContext:
          runAsUser: 9999  # refers to user _flink_ from official flink image, change if necessary
      serviceAccountName: flink-service-account # Service account which has the permissions to create, edit, delete ConfigMaps
      # 節(jié)點選擇器
      nodeSelector:
        zone: mainland
      # 節(jié)點容忍
      tolerations:
        - key: zone
          value: mainland
          effect: NoSchedule
      volumes:
      - name: flink-config-volume
        configMap:
          name: flink-config
          items:
          - key: flink-conf.yaml
            path: flink-conf.yaml
          - key: log4j-console.properties
            path: log4j-console.properties
        name: tmp-dir
        persistentVolumeClaim:
          claimName: flink-tmp

apiVersion: v1
kind: Service
metadata:
  name: flink-jobmanager
spec:
  type: ClusterIP
  ports:
  - name: rpc
    port: 6123
  - name: blob-server
    port: 6124
  - name: webui
    port: 8081
  selector:
    app: flink
    component: jobmanager

apiVersion: extensions/v1beta1
kind: Ingress
metadata:
  annotations:
    # 因為有可能需要上傳jar包,所以需要設置大一些
    nginx.ingress.kubernetes.io/proxy-body-size: 300m
    nginx.ingress.kubernetes.io/rewrite-target: /$1
  name: job-manager
  namespace: szyx-flink
spec:
  rules:
  - host: flink.k8s.io
    http:
      paths:
      - backend:
          serviceName: flink-jobmanager
          servicePort: 8081
        path: /flink/(.*)

apiVersion: apps/v1
kind: Deployment
metadata:
  name: flink-taskmanager
  namespace: szyx-flink
spec:
  replicas: 2
  selector:
    matchLabels:
      app: flink
      component: taskmanager
  template:
    metadata:
      labels:
        app: flink
        component: taskmanager
    spec:
      containers:
      - name: taskmanager
        imagePullPolicy: Always
        image: sivdead/flink:1.15.3_scala_2.12
        args: ["taskmanager"]
        ports:
        - containerPort: 6122
          name: rpc
        - containerPort: 6125
          name: query-state
        livenessProbe:
          tcpSocket:
            port: 6122
          initialDelaySeconds: 30
          periodSeconds: 60
        volumeMounts:
        - name: flink-config-volume
          mountPath: /opt/flink/conf/
        securityContext:
          runAsUser: 9999  # refers to user _flink_ from official flink image, change if necessary
        resources:
          requests:
            memory: "8192Mi"
            cpu: "4"
          limits:
            memory: "8192Mi"
            cpu: "4"
            # 節(jié)點選擇器
      nodeSelector:
        zone: mainland
      # 節(jié)點容忍
      tolerations:
        - key: zone
          value: mainland
          effect: NoSchedule
      volumes:
      - name: flink-config-volume
        configMap:
          name: flink-config
          items:
          - key: flink-conf.yaml
            path: flink-conf.yaml
          - key: log4j-console.properties
            path: log4j-console.properties