Настройка Ranger для Spark в Kubernetes с помощью CLI

{
  "isEnabled": true,
  "type": "hive",
  "name": "spark_k8s", (1)
  "displayName": "spark_k8s",
  "description": "Service for Kubernetes Spark",
  "configs": {
    "username": "spark", (2)
    "password": "bigdata", (3)
    "ranger.plugin.audit.filters": "[ {'accessResult': 'DENIED', 'isAudited': true}, {'actions':['METADATA OPERATION'], 'isAudited': false}, {'users':['hive','hue'],'actions':['SHOW_ROLES'],'isAudited':false} ]",
    "jdbc.driverClassName": "org.apache.hive.jdbc.HiveDriver",
    "jdbc.url": "jdbc:hive2://tsn-adh-k8s-2.ru-central1.internal:10002" (4)
  }
}

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: SparkApplication
metadata:
  name: spark-application
  namespace: spark-applications (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:
  #  principal: user@EXAMPLE.COM
  #
  #  # CLI reads the local files and creates the kerberos-ccache Secret on 'adc apply'.
  #  # Alternative - keytab mode: replace this block with:
  #  #   keytab:
  #  #     secretName: <name-of-existing-keytab-secret>
  #  ticketCache:
  #    #secretName: custom-ticket-cache
  #    externalSecretName: existing-ticket-cache
  #    #ticketPath: /tmp/krb5cc_1000
  #    #krb5ConfPath: /etc/krb5.conf

  ## Ranger plugin configuration.
  ## Uncomment and fill the lines below. adc apply derives the rest.
  ranger: (4)
  #  # fill ranger.plugin.spark.policy.rest.url below with Ranger endpoint, e.g. https://adps-adc.ru-central1.internal:6182
  #   # fill ranger.plugin.spark.service.name below with Ranger service name you want to use for product, e.g. adc_spark_id_1
    security:
      ranger.plugin.spark.policy.rest.url: "http://tsn-adps-2.ru-central1.internal:6080"
      ranger.plugin.spark.service.name: "spark_k8s"
      ranger.plugin.spark.use.rangerGroups: "True"
      ranger.plugin.spark.use.only.rangerGroups: "True"
  #
  #  # fill xasecure.audit.destination.solr.zookeepers below with Zookeepers endpoints to resolve solr service, e.g. adps-adc.ru-central1.internal:2181/Arenadata.Hadoop-2.solr.server
    audit:
      xasecure.audit.destination.solr.zookeepers: "tsn-adps-2.ru-central1.internal:2181/Arenadata.Hadoop-40.solr.server"
  #
  #  # Local Ranger files 'adc apply' writes into the configs Secret.
  #  # Relative paths are resolved against the config file.
  #  files:
  #    jceksStorePath: /path/to/ranger.jceks

  ## 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-ssl-secret
  #  externalSecretName: existing-ssl-secret
  #
  #  # 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-spark-hadoop-configs
  #
  #  ## Or let ADC create the Secret.
  #  #secretName: custom-spark-hadoop-configs

  ## Use an external Ranger configs Secret instead of the one rendered by ADC.
  #rangerConfigsSecret:
  #  # Use a Secret managed outside ADC.
  #  externalSecretName: existing-spark-ranger-configs
  #
  #  ## Or let ADC create the Secret.
  #  #secretName: custom-spark-ranger-configs

  # Spark application main resource (e.g. local:///opt/spark/examples/jars/spark-examples.jar).
  mainApplicationFile: "local:///opt/spark/examples/jars/spark-examples.jar" (5)

  ## HDFS or local directory for the Spark event log.
  ## When set, the CLI adds spark.eventLog.enabled=true, spark.eventLog.dir,
  ## spark.eventLog.rolling.enabled=true and spark.eventLog.rolling.interval=30s to sparkConf.
  #eventLogDir: ""

  ## Fully-qualified main class name. Required for Java/Scala applications.
  mainClass: "org.apache.spark.examples.sql.SparkSQLExample" (6)

  # ServiceAccount used by the Spark driver, also injected into
  # spark.kubernetes.authenticate.driver.serviceAccountName. The CLI creates it, plus a Role
  # and RoleBinding for Spark pods, by default (create: true). Set create: false to skip that
  # and only reference a ServiceAccount managed elsewhere.
  # The Role rules are managed by the CLI and cannot be customized.
  serviceAccount: (7)
    create: true
    name: spark-application
  job: (8)
    ## true (default) deletes the spark-submit Job pod after it finishes; set false to keep it for debugging.
    deleteOnTermination: false

    #resources:
    #  limits:
    #    cpu: "1"
    #    memory: 512Mi
    #  requests:
    #    cpu: 500m
    #    memory: 64Mi

    ## Component arguments. Key-value pairs passed to the component configuration.
    #args:
    #  executor-memory: 1g
    #  num-executors: "2"

  ## Application arguments appended after mainApplicationFile.
  args:
    - "100"

  # Spark configuration entries (spark.*).
  sparkConf: (9)
    spark.artifactory.dir.path: /tmp/artifacts
    spark.jars.ivy: /tmp/ivy
    spark.local.dir: /tmp/data
    spark.sql.catalog.spark_catalog: org.apache.iceberg.spark.SparkSessionCatalog
    spark.sql.extensions: org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,org.apache.kyuubi.plugin.spark.authz.ranger.RangerSparkExtension
    spark.sql.security.confblacklist: spark.sql.extensions

  ## Seconds after the application finishes (Succeeded, or Failed with no
  ## retries left) before the SparkApplication is deleted. Omit to keep it
  ## until explicit deletion.
  #ttlSecondsAfterFinished: 3600 (10)

  ## Celeborn remote shuffle service for Spark.
  ## tiers mirror the cluster's storage.tiers: local (SSD/HDD) and MEMORY advertise their name only,
  ## remote (S3/HDFS) also set dir (and, for S3, credentials). Ozone is an HDFS tier with an ofs:// dir.
  #celeborn:
  #  # Storage tiers mirroring the cluster's storage.tiers so the client advertises the same layers.
  #  # type: SSD, HDD, S3, HDFS, MEMORY. SSD/HDD and MEMORY are advertise-only here (no dir; worker-only
  #  # fields ignored); remote S3/HDFS set dir (s3a:// for S3; hdfs:// or ofs:// for Ozone on HDFS). Example:
  #  #   - type: MEMORY   # cache tier; pair with a durable tier below, no dir
  #  #   - type: SSD      # advertise-only on the client, no dir needed
  #  #   - dir: s3a://bucket/celeborn
  #  #     s3: { endpoint: https://s3:9878, region: us-east-1 }
  #  #     type: S3
  #  #   - dir: hdfs://nn/celeborn   # or ofs://om/volume/bucket/celeborn for Ozone
  #  #     type: HDFS
  #  tiers:
  #    - dir: s3a://shuffle/my-cluster
  #      s3:
  #        accessKey: <access-key>
  #        endpoint: https://s3.endpoint:443
  #        pathStyleAccess: true
  #        region: <region>
  #        secretKey: <secret-key>
  #      type: S3
  #  masterEndpoint: ""
  #  extraSparkConf:
  #    spark.sql.adaptive.enabled: "true"
  #
  #  # Enable TLS on the client's RPC connection to the Celeborn cluster.
  #  # When true the CLI renders spark.celeborn.ssl.* into the Spark conf
  #  # and requires the ssl section with trustStoreKey.
  #  rpcEncryption: false
  #
  #  # Enable TLS on the client's data module, which carries shuffle push/fetch
  #  # traffic between executors and workers. Requires the ssl section with trustStoreKey.
  #  dataEncryption: false

  ## YuniKorn scheduler configuration for queue selection and Gang scheduling.
  ## Uncomment the block to route the Spark job into a YuniKorn queue; the CLI renders the
  ## scheduler name, queue labels and gang annotations into sparkConf.
  #yunikorn:
  #  queue: root.analytics
  #  taskGroups:
  #    - minMember: 1
  #      minResource:
  #        cpu: "1"
  #        memory: 1433Mi
  #      name: spark-driver
  #    - minMember: 2
  #      minResource:
  #        cpu: "1"
  #        memory: 1433Mi
  #      name: spark-executor

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

---
apiVersion: v1
kind: Secret
metadata:
  name: spark-application-configs
  namespace: spark-applications
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-application-configs-ranger
  namespace: spark-applications
stringData:
  ranger-spark-audit.xml: |-
    <configuration>
      <property>
        <name>xasecure.audit.destination.solr</name>
        <value>true</value>
      </property>
      <property>
        <name>xasecure.audit.destination.solr.batch.filespool.dir</name>
        <value>/tmp/ranger/spark_plugin/audit_solr_spool</value>
      </property>
      <property>
        <name>xasecure.audit.destination.solr.zookeepers</name>
        <value>tsn-adps-2.ru-central1.internal:2181/Arenadata.Hadoop-40.solr.server</value>
      </property>
      <property>
        <name>xasecure.audit.is.enabled</name>
        <value>True</value>
      </property>
    </configuration>
  ranger-spark-security.xml: |-
    <configuration>
      <property>
        <name>ranger.plugin.spark.enable.implicit.userstore.enricher</name>
        <value>True</value>
      </property>
      <property>
        <name>ranger.plugin.spark.policy.cache.dir</name>
        <value>/tmp/ranger/spark/policycache</value>
      </property>
      <property>
        <name>ranger.plugin.spark.policy.rest.url</name>
        <value>http://tsn-adps-2.ru-central1.internal:6080</value>
      </property>
      <property>
        <name>ranger.plugin.spark.policy.source.impl</name>
        <value>org.apache.ranger.admin.client.RangerAdminRESTClient</value>
      </property>
      <property>
        <name>ranger.plugin.spark.service.name</name>
        <value>spark_k8s</value>
      </property>
      <property>
        <name>ranger.plugin.spark.use.only.rangerGroups</name>
        <value>True</value>
      </property>
      <property>
        <name>ranger.plugin.spark.use.rangerGroups</name>
        <value>True</value>
      </property>
    </configuration>
type: Opaque
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: spark-application
  namespace: spark-applications
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
  name: spark-application
  namespace: spark-applications
rules:
- apiGroups:
  - ""
  resources:
  - pods
  - configmaps
  - persistentvolumeclaims
  - services
  - secrets
  verbs:
  - get
  - list
  - watch
  - create
  - update
  - patch
  - delete
  - deletecollection
- apiGroups:
  - networking.k8s.io
  resources:
  - networkpolicies
  verbs:
  - get
  - list
  - watch
  - create
  - update
  - patch
  - delete
- apiGroups:
  - events.k8s.io
  resources:
  - events
  verbs:
  - create
  - patch
  - update
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
  name: spark-application
  namespace: spark-applications
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: spark-application
subjects:
- kind: ServiceAccount
  name: spark-application
  namespace: spark-applications
---
apiVersion: spark.arenadata.io/v1alpha1
kind: SparkApplication
metadata:
  name: spark-application
  namespace: spark-applications
spec:
  args:
  - "100"
  driver:
    metadata: {}
    spec:
      image: hub.arenadata.io/adc-enterprise/spark3:<tag>
      imagePullPolicy: Always
  executor:
    metadata: {}
    spec:
      image: hub.arenadata.io/adc-enterprise/spark3:<tag>
      imagePullPolicy: Always
  hadoopConfigsSecretName: spark-application-configs
  job:
    deleteOnTermination: false
    metadata: {}
    spec:
      image: hub.arenadata.io/adc-enterprise/spark3:<tag>
      imagePullPolicy: Always
  mainApplicationFile: local:///opt/spark/examples/jars/spark-examples.jar
  mainClass: org.apache.spark.examples.sql.SparkSQLExample
  serviceAccountName: spark-application
  sparkConf:
    spark.artifactory.dir.path: /tmp/artifacts
    spark.jars.ivy: /tmp/ivy
    spark.kubernetes.authenticate.driver.serviceAccountName: spark-application
    spark.kubernetes.namespace: spark-applications
    spark.local.dir: /tmp/data
    spark.sql.catalog.spark_catalog: org.apache.iceberg.spark.SparkSessionCatalog
    spark.sql.extensions: org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions,org.apache.kyuubi.plugin.spark.authz.ranger.RangerSparkExtension
    spark.sql.security.confblacklist: spark.sql.extensions
  sparkConfigsSecretName: spark-application-configs-ranger
status: {}