Установка Spark History Server в Kubernetes с помощью CLI

sites:
  core:
    fs.defaultFS: hdfs://adh
    hadoop.security.authentication: simple
    dfs.client.failover.proxy.provider.adh: org.apache.hadoop.hdfs.server.namenode.ha.ObserverReadProxyProvider
    dfs.ha.namenodes.adh: nn_tsn-adh-k8s-1,nn_tsn-adh-k8s-3
    dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-1: tsn-adh-k8s-1.ru-central1.internal:8020
    dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-3: tsn-adh-k8s-3.ru-central1.internal:8020
    dfs.nameservices: adh
  hdfs:
    dfs.client.read.shortcircuit: false
  ozone:
    ozone.om.address.adh.om_tsn-adh-k8s-1: tsn-adh-k8s-1.ru-central1.internal:9862
    ozone.om.address.adh.om_tsn-adh-k8s-2: tsn-adh-k8s-2.ru-central1.internal:9862
    ozone.om.address.adh.om_tsn-adh-k8s-3: tsn-adh-k8s-3.ru-central1.internal:9862
    ozone.om.nodes.adh: om_tsn-adh-k8s-1,om_tsn-adh-k8s-2,om_tsn-adh-k8s-3
    ozone.om.service.ids: adhom
  hive:
    hive.metastore.sasl.enabled: false
    hive.metastore.uris: thrift://tsn-adh-k8s-1.ru-central1.internal:9083
    metastore.use.SSL: false

apiVersion: adc.arenadata.io/v1alpha1
kind: SparkHistoryServer
metadata:
  name: spark-history-server
  namespace: spark-history-server (1)
spec:
  image: hub.arenadata.io/adc-enterprise/spark3:<tag> (2)

  ## Image pull secret for a private registry.
  ## Set 'externalSecretName' to reference an existing Secret,
  ## or set 'credentials' and optionally 'secretName' to let the CLI create one.
  #imagePullSecret:
  #  # Use a Secret managed outside ADC.
  #  externalSecretName: existing-registry-secret
  #
  #  ## Or let ADC create the Secret.
  #  #secretName: custom-registry-secret
  #
  #  #credentials:
  #  #  registry: registry.example.com
  #  #  username: user
  #  #  password: pass

  hadoop: (3)
    core:
      dfs.client.failover.proxy.provider.adh: org.apache.hadoop.hdfs.server.namenode.ha.ObserverReadProxyProvider
      dfs.ha.namenodes.adh: nn_tsn-adh-k8s-1,nn_tsn-adh-k8s-3
      dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-1: tsn-adh-k8s-1.ru-central1.internal:8020
      dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-3: tsn-adh-k8s-3.ru-central1.internal:8020
      dfs.nameservices: adh
      fs.defaultFS: hdfs://adh
      hadoop.security.authentication: simple
    hdfs:
      dfs.client.read.shortcircuit: "false"
    hive:
      hive.metastore.sasl.enabled: "false"
      hive.metastore.uris: thrift://tsn-adh-k8s-1.ru-central1.internal:9083
      metastore.use.SSL: "false"
    ozone:
      ozone.om.address.adh.om_tsn-adh-k8s-1: tsn-adh-k8s-1.ru-central1.internal:9862
      ozone.om.address.adh.om_tsn-adh-k8s-2: tsn-adh-k8s-2.ru-central1.internal:9862
      ozone.om.address.adh.om_tsn-adh-k8s-3: tsn-adh-k8s-3.ru-central1.internal:9862
      ozone.om.nodes.adh: om_tsn-adh-k8s-1,om_tsn-adh-k8s-2,om_tsn-adh-k8s-3
      ozone.om.service.ids: adhom

  ## Kerberos configuration for authentication.
  #kerberos:
  #  realm: EXAMPLE.COM
  #
  #  # Service name in the Kerberos principal. Defaults to the product name.
  #  service: spark-history
  #
  #  # Hostname in the Kerberos principal.
  #  # Required for a fixed service principal; leave it empty only to derive one principal per pod from the cluster domain.
  #  hostname: history.example.com
  #  keytab:
  #    # true - kerberos-operator creates the keytab Secret.
  #    # false (default) - reference an existing keytab Secret with name keytab.secretName.
  #    create: false
  #
  #    # Name of the keytab Secret.
  #    # Optional when create: true - names the generated Secret (default: <name>-keytab).
  #    # Required when create: false - must reference an existing Secret.
  #    secretName: spark-history-keytab
  #
  #    # Label selector for the Pod that generates the keytab.
  #    # Required when create: true; ignored when create: false.
  #    labelSelector:
  #      env: prod
  #    #additionalPrincipals:
  #    #  - HTTP/history-lb.example.com
  #
  #    rotation:
  #      interval: 720h
  #      checkInterval: 1h
  #  spnego: true

  ## Java KeyStore/TrustStore certificate configuration.
  ## Set externalSecretName to reference an existing Secret,
  ## or set files and optional secretName to have ADC create it.
  #ssl:
  #  ## Name of the Secret containing Java keystores.
  #  #secretName: custom-spark-history-ssl
  #  externalSecretName: existing-spark-history-ssl
  #
  #  # Key in the Secret containing the truststore file.
  #  trustStoreKey: truststore.jks
  #
  #  ## Password for the truststore (optional).
  #  #trustStorePassword: bigdata
  #
  #  ## Key in the Secret containing the keystore file (optional).
  #  #keyStoreKey: keystore.jks
  #
  #  ## Password for the keystore (optional).
  #  #keyStorePassword: bigdata
  #
  #  ## Local files 'adc apply' puts into the Secret named by ssl.secretName.
  #  ## Relative paths are resolved against the config file.
  #  #files:
  #  #  trustStorePath: /path/to/truststore.jks
  #  #  #keyStorePath: /path/to/keystore.jks

  ## Use an external Hadoop configs Secret instead of the one rendered by ADC.
  #hadoopConfigsSecret:
  #  # Use a Secret managed outside ADC.
  #  externalSecretName: existing-history-hadoop-configs
  #
  #  ## Or let ADC create the Secret.
  #  #secretName: custom-history-hadoop-configs

  ## Use an external Spark History properties Secret instead of the one rendered by ADC.
  #historyPropertiesSecret:
  #  # Use a Secret managed outside ADC.
  #  externalSecretName: existing-history-properties
  #
  #  ## Or let ADC create the Secret.
  #  #secretName: custom-history-properties

  eventLogDir: "hdfs:///logs/spark/apps" (4)
  store:
    path: /var/log/spark/history (5)
    emptyDir: {}
    #pvc: (6)
    #  size: 10Gi
    #  storageClassName: my-storage-class
    #  accessModes:
    #    - ReadWriteOnce

  ## Monitoring configuration.
  #monitoring:
  #  # Enables Prometheus metrics export from this product's pods.
  #  exportMetrics: true

  #properties:
  #  spark.history.store.maxDiskUsage: 16g

  server:
    replicas: 1
    #resources:
    #  limits:
    #    cpu: "1"
    #    memory: 1Gi
    #  requests:
    #    cpu: 400m
    #    memory: 256Mi
  #extraMountSecrets:
  #  - mountPath: /etc/spark/extra-secret
  #    options:
  #      containerName: app
  #    secretName: extra-secret

  ## Controls whether Secret/ConfigMap changes restart pods.
  ## Set enabled: false to update referenced Secrets without restarting
  ## the workload; pods keep running the previous configuration until
  ## the policy is re-enabled. Defaults to enabled.
  #configurationRollout:
  #  enabled: false

---
apiVersion: v1
kind: Secret
metadata:
  name: spark-history-server-configs
  namespace: spark-history-server
stringData:
  core-site.xml: |-
    <configuration>
      <property>
        <name>dfs.client.failover.proxy.provider.adh</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ObserverReadProxyProvider</value>
      </property>
      <property>
        <name>dfs.client.read.shortcircuit</name>
        <value>false</value>
      </property>
      <property>
        <name>dfs.ha.namenodes.adh</name>
        <value>nn_tsn-adh-k8s-1,nn_tsn-adh-k8s-3</value>
      </property>
      <property>
        <name>dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-1</name>
        <value>tsn-adh-k8s-1.ru-central1.internal:8020</value>
      </property>
      <property>
        <name>dfs.namenode.rpc-address.adh.nn_tsn-adh-k8s-3</name>
        <value>tsn-adh-k8s-3.ru-central1.internal:8020</value>
      </property>
      <property>
        <name>dfs.nameservices</name>
        <value>adh</value>
      </property>
      <property>
        <name>fs.defaultFS</name>
        <value>hdfs://adh</value>
      </property>
      <property>
        <name>hadoop.security.authentication</name>
        <value>simple</value>
      </property>
      <property>
        <name>ozone.om.address.adh.om_tsn-adh-k8s-1</name>
        <value>tsn-adh-k8s-1.ru-central1.internal:9862</value>
      </property>
      <property>
        <name>ozone.om.address.adh.om_tsn-adh-k8s-2</name>
        <value>tsn-adh-k8s-2.ru-central1.internal:9862</value>
      </property>
      <property>
        <name>ozone.om.address.adh.om_tsn-adh-k8s-3</name>
        <value>tsn-adh-k8s-3.ru-central1.internal:9862</value>
      </property>
      <property>
        <name>ozone.om.nodes.adh</name>
        <value>om_tsn-adh-k8s-1,om_tsn-adh-k8s-2,om_tsn-adh-k8s-3</value>
      </property>
      <property>
        <name>ozone.om.service.ids</name>
        <value>adhom</value>
      </property>
    </configuration>
  hive-site.xml: |-
    <configuration>
      <property>
        <name>hive.metastore.sasl.enabled</name>
        <value>false</value>
      </property>
      <property>
        <name>hive.metastore.uris</name>
        <value>thrift://tsn-adh-k8s-1.ru-central1.internal:9083</value>
      </property>
      <property>
        <name>metastore.use.SSL</name>
        <value>false</value>
      </property>
    </configuration>
type: Opaque
---
apiVersion: v1
kind: Secret
metadata:
  name: spark-history-server-spark-history-properties
  namespace: spark-history-server
stringData:
  history-server.properties: |
    spark.eventLog.dir hdfs:///logs/spark/apps
    spark.eventLog.enabled true
    spark.history.fs.logDirectory hdfs:///logs/spark/apps
    spark.history.provider org.apache.spark.deploy.history.FsHistoryProvider
    spark.history.store.path /var/log/spark/history
    spark.history.ui.port 18080
type: Opaque
---
apiVersion: spark.arenadata.io/v1alpha1
kind: SparkHistoryServer
metadata:
  name: spark-history-server
  namespace: spark-history-server
spec:
  properties:
    secretKey: history-server.properties
    secretName: spark-history-server-spark-history-properties
  server:
    metadata: {}
    replicas: 1
    spec:
      emptyDirs:
      - /var/log/spark/history
      image: hub.arenadata.io/adc-enterprise/spark3:<tag>
      imagePullPolicy: Always
      mountSecrets:
      - mountPath: /etc/hadoop/conf
        options:
          containerName: app
        secretName: spark-history-server-configs
      ports:
      - containerPort: 18080
        name: http
        servicePort: 18080
status: {}