DataprocCluster


Property Value
Google Cloud Service Name Dataproc
Google Cloud Service Documentation /dataproc/docs/
Google Cloud REST Resource Name v1.projects.regions.clusters
Google Cloud REST Resource Documentation /dataproc/docs/reference/rest/v1/projects.regions.clusters
Config Connector Resource Short Names gcpdataproccluster
gcpdataprocclusters
dataproccluster
Config Connector Service Name dataproc.googleapis.com
Config Connector Resource Fully Qualified Name dataprocclusters.dataproc.cnrm.cloud.google.com
Can Be Referenced by IAMPolicy/IAMPolicyMember Yes
IAMPolicy/IAMPartialPolicy Supports Conditions Yes
IAMPolicyMember Supports Conditions No
Supports IAM Audit Configs No
IAM External Reference Format

projects/{{project}}/regions/{{location}}/clusters/{{name}}

Config Connector Default Average Reconcile Interval In Seconds 600

Custom Resource Definition Properties

Spec

Schema

config:
  autoscalingConfig:
    policyRef:
      external: string
      name: string
      namespace: string
  dataprocMetricConfig:
    metrics:
    - metricOverrides:
      - string
      metricSource: string
  encryptionConfig:
    gcePdKmsKeyRef:
      external: string
      name: string
      namespace: string
  endpointConfig:
    enableHttpPortAccess: boolean
  gceClusterConfig:
    confidentialInstanceConfig:
      enableConfidentialCompute: boolean
    internalIPOnly: boolean
    metadata:
      string: string
    networkRef:
      external: string
      name: string
      namespace: string
    nodeGroupAffinity:
      nodeGroupRef:
        external: string
        name: string
        namespace: string
    privateIPv6GoogleAccess: string
    reservationAffinity:
      consumeReservationType: string
      key: string
      values:
      - string
    serviceAccountRef:
      external: string
      name: string
      namespace: string
    serviceAccountScopes:
    - string
    shieldedInstanceConfig:
      enableIntegrityMonitoring: boolean
      enableSecureBoot: boolean
      enableVtpm: boolean
    subnetworkRef:
      external: string
      name: string
      namespace: string
    tags:
    - string
    zone: string
  initializationActions:
  - executableFile: string
    executionTimeout: string
  lifecycleConfig:
    autoDeleteTime: string
    autoDeleteTtl: string
    idleDeleteTtl: string
  masterConfig:
    accelerators:
    - acceleratorCount: integer
      acceleratorType: string
    diskConfig:
      bootDiskSizeGb: integer
      bootDiskType: string
      localSsdInterface: string
      numLocalSsds: integer
    imageRef:
      external: string
      name: string
      namespace: string
    machineType: string
    minCpuPlatform: string
    numInstances: integer
    preemptibility: string
  metastoreConfig:
    dataprocMetastoreServiceRef:
      external: string
      name: string
      namespace: string
  secondaryWorkerConfig:
    accelerators:
    - acceleratorCount: integer
      acceleratorType: string
    diskConfig:
      bootDiskSizeGb: integer
      bootDiskType: string
      localSsdInterface: string
      numLocalSsds: integer
    imageRef:
      external: string
      name: string
      namespace: string
    machineType: string
    minCpuPlatform: string
    numInstances: integer
    preemptibility: string
  securityConfig:
    identityConfig:
      userServiceAccountMapping:
        string: string
    kerberosConfig:
      crossRealmTrustAdminServer: string
      crossRealmTrustKdc: string
      crossRealmTrustRealm: string
      crossRealmTrustSharedPassword: string
      enableKerberos: boolean
      kdcDbKey: string
      keyPassword: string
      keystore: string
      keystorePassword: string
      kmsKeyRef:
        external: string
        name: string
        namespace: string
      realm: string
      rootPrincipalPassword: string
      tgtLifetimeHours: integer
      truststore: string
      truststorePassword: string
  softwareConfig:
    imageVersion: string
    optionalComponents:
    - string
    properties:
      string: string
  stagingBucketRef:
    external: string
    name: string
    namespace: string
  tempBucketRef:
    external: string
    name: string
    namespace: string
  workerConfig:
    accelerators:
    - acceleratorCount: integer
      acceleratorType: string
    diskConfig:
      bootDiskSizeGb: integer
      bootDiskType: string
      localSsdInterface: string
      numLocalSsds: integer
    imageRef:
      external: string
      name: string
      namespace: string
    machineType: string
    minCpuPlatform: string
    numInstances: integer
    preemptibility: string
location: string
projectRef:
  external: string
  name: string
  namespace: string
resourceID: string
virtualClusterConfig:
  auxiliaryServicesConfig:
    metastoreConfig:
      dataprocMetastoreServiceRef:
        external: string
        name: string
        namespace: string
    sparkHistoryServerConfig:
      dataprocClusterRef:
        external: string
        name: string
        namespace: string
  kubernetesClusterConfig:
    gkeClusterConfig:
      gkeClusterTargetRef:
        external: string
        name: string
        namespace: string
      nodePoolTarget:
      - nodePoolConfig:
          autoscaling:
            maxNodeCount: integer
            minNodeCount: integer
          config:
            accelerators:
            - acceleratorCount: integer
              acceleratorType: string
              gpuPartitionSize: string
            bootDiskKmsKey: string
            ephemeralStorageConfig:
              localSsdCount: integer
            localSsdCount: integer
            machineType: string
            minCpuPlatform: string
            preemptible: boolean
            spot: boolean
          locations:
          - string
        nodePoolRef:
          external: string
          name: string
          namespace: string
        roles:
        - string
    kubernetesNamespace: string
    kubernetesSoftwareConfig:
      componentVersion:
        string: string
      properties:
        string: string
  stagingBucketRef:
    external: string
    name: string
    namespace: string
Fields

config

Optional

object

Immutable. The cluster config. Note that Dataproc may set default values, and values may change when clusters are updated.

config.autoscalingConfig

Optional

object

Immutable. Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset.

config.autoscalingConfig.policyRef

Optional

object

Immutable.

config.autoscalingConfig.policyRef.external

Optional

string

Optional. The autoscaling policy used by the cluster. Only resource names including projectid and location (region) are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]` * `projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]` Note that the policy must be in the same project and Dataproc region. Allowed value: The Google Cloud resource name of a `DataprocAutoscalingPolicy` resource (format: `projects/{{project}}/locations/{{location}}/autoscalingPolicies/{{name}}`).

config.autoscalingConfig.policyRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.autoscalingConfig.policyRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.dataprocMetricConfig

Optional

object

Immutable. Optional. The config for Dataproc metrics.

config.dataprocMetricConfig.metrics

Required*

list (object)

Immutable. Required. Metrics sources to enable.

config.dataprocMetricConfig.metrics[]

Required*

object

config.dataprocMetricConfig.metrics[].metricOverrides

Optional

list (string)

Immutable. Optional. Specify one or more [available OSS metrics] (https://cloud.google.com/dataproc/docs/guides/monitoring#available_oss_metrics) to collect for the metric course (for the `SPARK` metric source, any [Spark metric] (https://spark.apache.org/docs/latest/monitoring.html#metrics) can be specified). Provide metrics in the following format: `METRIC_SOURCE:INSTANCE:GROUP:METRIC` Use camelcase as appropriate. Examples: ``` yarn:ResourceManager:QueueMetrics:AppsCompleted spark:driver:DAGScheduler:job.allJobs sparkHistoryServer:JVM:Memory:NonHeapMemoryUsage.committed hiveserver2:JVM:Memory:NonHeapMemoryUsage.used ``` Notes: * Only the specified overridden metrics will be collected for the metric source. For example, if one or more `spark:executive` metrics are listed as metric overrides, other `SPARK` metrics will not be collected. The collection of the default metrics for other OSS metric sources is unaffected. For example, if both `SPARK` andd `YARN` metric sources are enabled, and overrides are provided for Spark metrics only, all default YARN metrics will be collected.

config.dataprocMetricConfig.metrics[].metricOverrides[]

Optional

string

config.dataprocMetricConfig.metrics[].metricSource

Required*

string

Immutable. Required. Default metrics are collected unless `metricOverrides` are specified for the metric source (see [Available OSS metrics] (https://cloud.google.com/dataproc/docs/guides/monitoring#available_oss_metrics) for more information). Possible values: METRIC_SOURCE_UNSPECIFIED, MONITORING_AGENT_DEFAULTS, HDFS, SPARK, YARN, SPARK_HISTORY_SERVER, HIVESERVER2

config.encryptionConfig

Optional

object

Immutable. Optional. Encryption settings for the cluster.

config.encryptionConfig.gcePdKmsKeyRef

Optional

object

Immutable.

config.encryptionConfig.gcePdKmsKeyRef.external

Optional

string

Optional. The Cloud KMS key name to use for PD disk encryption for all instances in the cluster. Allowed value: The `selfLink` field of a `KMSCryptoKey` resource.

config.encryptionConfig.gcePdKmsKeyRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.encryptionConfig.gcePdKmsKeyRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.endpointConfig

Optional

object

Immutable. Optional. Port/endpoint configuration for this cluster

config.endpointConfig.enableHttpPortAccess

Optional

boolean

Immutable. Optional. If true, enable http access to specific ports on the cluster from external sources. Defaults to false.

config.gceClusterConfig

Optional

object

Immutable. Optional. The shared Compute Engine config settings for all instances in a cluster.

config.gceClusterConfig.confidentialInstanceConfig

Optional

object

Immutable. Optional. Confidential Instance Config for clusters using [Confidential VMs](https://cloud.google.com/compute/confidential-vm/docs).

config.gceClusterConfig.confidentialInstanceConfig.enableConfidentialCompute

Optional

boolean

Immutable. Optional. Defines whether the instance should have confidential compute enabled.

config.gceClusterConfig.internalIPOnly

Optional

boolean

Immutable. Optional. If true, all instances in the cluster will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This `internal_ip_only` restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.

config.gceClusterConfig.metadata

Optional

map (key: string, value: string)

Immutable. The Compute Engine metadata entries to add to all instances (see [Project and instance metadata](https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata)).

config.gceClusterConfig.networkRef

Optional

object

Immutable.

config.gceClusterConfig.networkRef.external

Optional

string

Optional. The Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither `network_uri` nor `subnetwork_uri` is specified, the "default" network of the project is used, if it exists. Cannot be a "Custom Subnet Network" (see [Using Subnetworks](https://cloud.google.com/compute/docs/subnetworks) for more information). A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default` * `projects/[project_id]/regions/global/default` * `default` Allowed value: The `selfLink` field of a `ComputeNetwork` resource.

config.gceClusterConfig.networkRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.gceClusterConfig.networkRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.gceClusterConfig.nodeGroupAffinity

Optional

object

Immutable. Optional. Node Group Affinity for sole-tenant clusters.

config.gceClusterConfig.nodeGroupAffinity.nodeGroupRef

Required*

object

Immutable.

config.gceClusterConfig.nodeGroupAffinity.nodeGroupRef.external

Optional

string

Required. The URI of a sole-tenant [node group resource](https://cloud.google.com/compute/docs/reference/rest/v1/nodeGroups) that the cluster will be created on. A full URL, partial URI, or node group name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-central1-a/nodeGroups/node-group-1` * `projects/[project_id]/zones/us-central1-a/nodeGroups/node-group-1` * `node-group-1` Allowed value: The `selfLink` field of a `ComputeNodeGroup` resource.

config.gceClusterConfig.nodeGroupAffinity.nodeGroupRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.gceClusterConfig.nodeGroupAffinity.nodeGroupRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.gceClusterConfig.privateIPv6GoogleAccess

Optional

string

Immutable. Optional. The type of IPv6 access for a cluster. Possible values: PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED, INHERIT_FROM_SUBNETWORK, OUTBOUND, BIDIRECTIONAL

config.gceClusterConfig.reservationAffinity

Optional

object

Immutable. Optional. Reservation Affinity for consuming Zonal reservation.

config.gceClusterConfig.reservationAffinity.consumeReservationType

Optional

string

Immutable. Optional. Type of reservation to consume Possible values: TYPE_UNSPECIFIED, NO_RESERVATION, ANY_RESERVATION, SPECIFIC_RESERVATION

config.gceClusterConfig.reservationAffinity.key

Optional

string

Immutable. Optional. Corresponds to the label key of reservation resource.

config.gceClusterConfig.reservationAffinity.values

Optional

list (string)

Immutable. Optional. Corresponds to the label values of reservation resource.

config.gceClusterConfig.reservationAffinity.values[]

Optional

string

config.gceClusterConfig.serviceAccountRef

Optional

object

Immutable.

config.gceClusterConfig.serviceAccountRef.external

Optional

string

Optional. The [Dataproc service account](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc) (also see [VM Data Plane identity](https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity)) used by Dataproc cluster VM instances to access Google Cloud Platform services. If not specified, the [Compute Engine default service account](https://cloud.google.com/compute/docs/access/service-accounts#default_service_account) is used. Allowed value: The `email` field of an `IAMServiceAccount` resource.

config.gceClusterConfig.serviceAccountRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.gceClusterConfig.serviceAccountRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.gceClusterConfig.serviceAccountScopes

Optional

list (string)

Immutable. Optional. The URIs of service account scopes to be included in Compute Engine instances. The following base set of scopes is always included: * https://www.googleapis.com/auth/cloud.useraccounts.readonly * https://www.googleapis.com/auth/devstorage.read_write * https://www.googleapis.com/auth/logging.write If no scopes are specified, the following defaults are also provided: * https://www.googleapis.com/auth/bigquery * https://www.googleapis.com/auth/bigtable.admin.table * https://www.googleapis.com/auth/bigtable.data * https://www.googleapis.com/auth/devstorage.full_control

config.gceClusterConfig.serviceAccountScopes[]

Optional

string

config.gceClusterConfig.shieldedInstanceConfig

Optional

object

Immutable. Optional. Shielded Instance Config for clusters using [Compute Engine Shielded VMs](https://cloud.google.com/security/shielded-cloud/shielded-vm).

config.gceClusterConfig.shieldedInstanceConfig.enableIntegrityMonitoring

Optional

boolean

Immutable. Optional. Defines whether instances have integrity monitoring enabled.

config.gceClusterConfig.shieldedInstanceConfig.enableSecureBoot

Optional

boolean

Immutable. Optional. Defines whether instances have Secure Boot enabled.

config.gceClusterConfig.shieldedInstanceConfig.enableVtpm

Optional

boolean

Immutable. Optional. Defines whether instances have the vTPM enabled.

config.gceClusterConfig.subnetworkRef

Optional

object

Immutable.

config.gceClusterConfig.subnetworkRef.external

Optional

string

Optional. The Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/subnetworks/sub0` * `projects/[project_id]/regions/us-east1/subnetworks/sub0` * `sub0` Allowed value: The `selfLink` field of a `ComputeSubnetwork` resource.

config.gceClusterConfig.subnetworkRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.gceClusterConfig.subnetworkRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.gceClusterConfig.tags

Optional

list (string)

Immutable. The Compute Engine tags to add to all instances (see [Tagging instances](https://cloud.google.com/compute/docs/label-or-tag-resources#tags)).

config.gceClusterConfig.tags[]

Optional

string

config.gceClusterConfig.zone

Optional

string

Immutable. Optional. The zone where the Compute Engine cluster will be located. On a create request, it is required in the "global" region. If omitted in a non-global Dataproc region, the service will pick a zone in the corresponding Compute Engine region. On a get request, zone will always be present. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]` * `projects/[project_id]/zones/[zone]` * `us-central1-f`

config.initializationActions

Optional

list (object)

Immutable. Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's `role` metadata to run an executable on a master or worker node, as shown below using `curl` (you can also use `wget`): ROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1/instance/attributes/dataproc-role) if [[ "${ROLE}" == 'Master' ]]; then ... master specific actions ... else ... worker specific actions ... fi

config.initializationActions[]

Optional

object

config.initializationActions[].executableFile

Required*

string

Immutable. Required. Cloud Storage URI of executable file.

config.initializationActions[].executionTimeout

Optional

string

Immutable. Optional. Amount of time executable has to complete. Default is 10 minutes (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)). Cluster creation fails with an explanatory error message (the name of the executable that caused the error and the exceeded timeout period) if the executable is not completed at end of the timeout period.

config.lifecycleConfig

Optional

object

Immutable. Optional. Lifecycle setting for the cluster.

config.lifecycleConfig.autoDeleteTime

Optional

string

Immutable. Optional. The time when cluster will be auto-deleted (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).

config.lifecycleConfig.autoDeleteTtl

Optional

string

Immutable. Optional. The lifetime duration of cluster. The cluster will be auto-deleted at the end of this period. Minimum value is 10 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).

config.lifecycleConfig.idleDeleteTtl

Optional

string

Immutable. Optional. The duration to keep the cluster alive while idling (when no jobs are running). Passing this threshold will cause the cluster to be deleted. Minimum value is 5 minutes; maximum value is 14 days (see JSON representation of [Duration](https://developers.google.com/protocol-buffers/docs/proto3#json)).

config.masterConfig

Optional

object

Immutable. Optional. The Compute Engine config settings for the master instance in a cluster.

config.masterConfig.accelerators

Optional

list (object)

Immutable. Optional. The Compute Engine accelerator configuration for these instances.

config.masterConfig.accelerators[]

Optional

object

config.masterConfig.accelerators[].acceleratorCount

Optional

integer

Immutable. The number of the accelerator cards of this type exposed to this instance.

config.masterConfig.accelerators[].acceleratorType

Optional

string

Immutable. Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See [Compute Engine AcceleratorTypes](https://cloud.google.com/compute/docs/reference/beta/acceleratorTypes). Examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `nvidia-tesla-k80` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the accelerator type resource, for example, `nvidia-tesla-k80`.

config.masterConfig.diskConfig

Optional

object

Immutable. Optional. Disk option config settings.

config.masterConfig.diskConfig.bootDiskSizeGb

Optional

integer

Immutable. Optional. Size in GB of the boot disk (default is 500GB).

config.masterConfig.diskConfig.bootDiskType

Optional

string

Immutable. Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-balanced" (Persistent Disk Balanced Solid State Drive), "pd-ssd" (Persistent Disk Solid State Drive), or "pd-standard" (Persistent Disk Hard Disk Drive). See [Disk types](https://cloud.google.com/compute/docs/disks#disk-types).

config.masterConfig.diskConfig.localSsdInterface

Optional

string

Immutable. Optional. Interface type of local SSDs (default is "scsi"). Valid values: "scsi" (Small Computer System Interface), "nvme" (Non-Volatile Memory Express). See [local SSD performance](https://cloud.google.com/compute/docs/disks/local-ssd#performance).

config.masterConfig.diskConfig.numLocalSsds

Optional

integer

Immutable. Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and [HDFS](https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.

config.masterConfig.imageRef

Optional

object

Immutable.

config.masterConfig.imageRef.external

Optional

string

Optional. The Compute Engine image resource used for cluster instances. The URI can represent an image or image family. Image examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/[image-id]` * `projects/[project_id]/global/images/[image-id]` * `image-id` Image family examples. Dataproc will use the most recent image from the family: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/family/[custom-image-family-name]` * `projects/[project_id]/global/images/family/[custom-image-family-name]` If the URI is unspecified, it will be inferred from `SoftwareConfig.image_version` or the system default. Allowed value: The `selfLink` field of a `ComputeImage` resource.

config.masterConfig.imageRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.masterConfig.imageRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.masterConfig.machineType

Optional

string

Immutable. Optional. The Compute Engine machine type used for cluster instances. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `n1-standard-2` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the machine type resource, for example, `n1-standard-2`.

config.masterConfig.minCpuPlatform

Optional

string

Immutable. Optional. Specifies the minimum cpu platform for the Instance Group. See [Dataproc -> Minimum CPU Platform](https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu).

config.masterConfig.numInstances

Optional

integer

Immutable. Optional. The number of VM instances in the instance group. For [HA cluster](/dataproc/docs/concepts/configuring-clusters/high-availability) [master_config](#FIELDS.master_config) groups, **must be set to 3**. For standard cluster [master_config](#FIELDS.master_config) groups, **must be set to 1**.

config.masterConfig.preemptibility

Optional

string

Immutable. Optional. Specifies the preemptibility of the instance group. The default value for master and worker groups is `NON_PREEMPTIBLE`. This default cannot be changed. The default value for secondary instances is `PREEMPTIBLE`. Possible values: PREEMPTIBILITY_UNSPECIFIED, NON_PREEMPTIBLE, PREEMPTIBLE

config.metastoreConfig

Optional

object

Immutable. Optional. Metastore configuration.

config.metastoreConfig.dataprocMetastoreServiceRef

Required*

object

Immutable.

config.metastoreConfig.dataprocMetastoreServiceRef.external

Optional

string

Required. Resource name of an existing Dataproc Metastore service. Example: * `projects/[project_id]/locations/[dataproc_region]/services/[service-name]`

config.metastoreConfig.dataprocMetastoreServiceRef.name

Optional

string

[WARNING] DataprocMetastoreService not yet supported in Config Connector, use 'external' field to reference existing resources. Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.metastoreConfig.dataprocMetastoreServiceRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.secondaryWorkerConfig

Optional

object

Immutable. Optional. The Compute Engine config settings for additional worker instances in a cluster.

config.secondaryWorkerConfig.accelerators

Optional

list (object)

Immutable. Optional. The Compute Engine accelerator configuration for these instances.

config.secondaryWorkerConfig.accelerators[]

Optional

object

config.secondaryWorkerConfig.accelerators[].acceleratorCount

Optional

integer

Immutable. The number of the accelerator cards of this type exposed to this instance.

config.secondaryWorkerConfig.accelerators[].acceleratorType

Optional

string

Immutable. Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See [Compute Engine AcceleratorTypes](https://cloud.google.com/compute/docs/reference/beta/acceleratorTypes). Examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `nvidia-tesla-k80` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the accelerator type resource, for example, `nvidia-tesla-k80`.

config.secondaryWorkerConfig.diskConfig

Optional

object

Immutable. Optional. Disk option config settings.

config.secondaryWorkerConfig.diskConfig.bootDiskSizeGb

Optional

integer

Immutable. Optional. Size in GB of the boot disk (default is 500GB).

config.secondaryWorkerConfig.diskConfig.bootDiskType

Optional

string

Immutable. Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-balanced" (Persistent Disk Balanced Solid State Drive), "pd-ssd" (Persistent Disk Solid State Drive), or "pd-standard" (Persistent Disk Hard Disk Drive). See [Disk types](https://cloud.google.com/compute/docs/disks#disk-types).

config.secondaryWorkerConfig.diskConfig.localSsdInterface

Optional

string

Immutable. Optional. Interface type of local SSDs (default is "scsi"). Valid values: "scsi" (Small Computer System Interface), "nvme" (Non-Volatile Memory Express). See [local SSD performance](https://cloud.google.com/compute/docs/disks/local-ssd#performance).

config.secondaryWorkerConfig.diskConfig.numLocalSsds

Optional

integer

Immutable. Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and [HDFS](https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.

config.secondaryWorkerConfig.imageRef

Optional

object

Immutable.

config.secondaryWorkerConfig.imageRef.external

Optional

string

Optional. The Compute Engine image resource used for cluster instances. The URI can represent an image or image family. Image examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/[image-id]` * `projects/[project_id]/global/images/[image-id]` * `image-id` Image family examples. Dataproc will use the most recent image from the family: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/family/[custom-image-family-name]` * `projects/[project_id]/global/images/family/[custom-image-family-name]` If the URI is unspecified, it will be inferred from `SoftwareConfig.image_version` or the system default. Allowed value: The `selfLink` field of a `ComputeImage` resource.

config.secondaryWorkerConfig.imageRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.secondaryWorkerConfig.imageRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.secondaryWorkerConfig.machineType

Optional

string

Immutable. Optional. The Compute Engine machine type used for cluster instances. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `n1-standard-2` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the machine type resource, for example, `n1-standard-2`.

config.secondaryWorkerConfig.minCpuPlatform

Optional

string

Immutable. Optional. Specifies the minimum cpu platform for the Instance Group. See [Dataproc -> Minimum CPU Platform](https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu).

config.secondaryWorkerConfig.numInstances

Optional

integer

Immutable. Optional. The number of VM instances in the instance group. For [HA cluster](/dataproc/docs/concepts/configuring-clusters/high-availability) [master_config](#FIELDS.master_config) groups, **must be set to 3**. For standard cluster [master_config](#FIELDS.master_config) groups, **must be set to 1**.

config.secondaryWorkerConfig.preemptibility

Optional

string

Immutable. Optional. Specifies the preemptibility of the instance group. The default value for master and worker groups is `NON_PREEMPTIBLE`. This default cannot be changed. The default value for secondary instances is `PREEMPTIBLE`. Possible values: PREEMPTIBILITY_UNSPECIFIED, NON_PREEMPTIBLE, PREEMPTIBLE

config.securityConfig

Optional

object

Immutable. Optional. Security settings for the cluster.

config.securityConfig.identityConfig

Optional

object

Immutable. Optional. Identity related configuration, including service account based secure multi-tenancy user mappings.

config.securityConfig.identityConfig.userServiceAccountMapping

Required*

map (key: string, value: string)

Immutable. Required. Map of user to service account.

config.securityConfig.kerberosConfig

Optional

object

Immutable. Optional. Kerberos related configuration.

config.securityConfig.kerberosConfig.crossRealmTrustAdminServer

Optional

string

Immutable. Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.

config.securityConfig.kerberosConfig.crossRealmTrustKdc

Optional

string

Immutable. Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.

config.securityConfig.kerberosConfig.crossRealmTrustRealm

Optional

string

Immutable. Optional. The remote realm the Dataproc on-cluster KDC will trust, should the user enable cross realm trust.

config.securityConfig.kerberosConfig.crossRealmTrustSharedPassword

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the shared password between the on-cluster Kerberos realm and the remote trusted realm, in a cross realm trust relationship.

config.securityConfig.kerberosConfig.enableKerberos

Optional

boolean

Immutable. Optional. Flag to indicate whether to Kerberize the cluster (default: false). Set this field to true to enable Kerberos on a cluster.

config.securityConfig.kerberosConfig.kdcDbKey

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the master key of the KDC database.

config.securityConfig.kerberosConfig.keyPassword

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided key. For the self-signed certificate, this password is generated by Dataproc.

config.securityConfig.kerberosConfig.keystore

Optional

string

Immutable. Optional. The Cloud Storage URI of the keystore file used for SSL encryption. If not provided, Dataproc will provide a self-signed certificate.

config.securityConfig.kerberosConfig.keystorePassword

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided keystore. For the self-signed certificate, this password is generated by Dataproc.

config.securityConfig.kerberosConfig.kmsKeyRef

Optional

object

Immutable.

config.securityConfig.kerberosConfig.kmsKeyRef.external

Optional

string

Optional. The uri of the KMS key used to encrypt various sensitive files. Allowed value: The `selfLink` field of a `KMSCryptoKey` resource.

config.securityConfig.kerberosConfig.kmsKeyRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.securityConfig.kerberosConfig.kmsKeyRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.securityConfig.kerberosConfig.realm

Optional

string

Immutable. Optional. The name of the on-cluster Kerberos realm. If not specified, the uppercased domain of hostnames will be the realm.

config.securityConfig.kerberosConfig.rootPrincipalPassword

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the root principal password.

config.securityConfig.kerberosConfig.tgtLifetimeHours

Optional

integer

Immutable. Optional. The lifetime of the ticket granting ticket, in hours. If not specified, or user specifies 0, then default value 10 will be used.

config.securityConfig.kerberosConfig.truststore

Optional

string

Immutable. Optional. The Cloud Storage URI of the truststore file used for SSL encryption. If not provided, Dataproc will provide a self-signed certificate.

config.securityConfig.kerberosConfig.truststorePassword

Optional

string

Immutable. Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided truststore. For the self-signed certificate, this password is generated by Dataproc.

config.softwareConfig

Optional

object

Immutable. Optional. The config settings for software inside the cluster.

config.softwareConfig.imageVersion

Optional

string

Immutable. Optional. The version of software inside the cluster. It must be one of the supported [Dataproc Versions](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#supported_dataproc_versions), such as "1.2" (including a subminor version, such as "1.2.29"), or the ["preview" version](https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#other_versions). If unspecified, it defaults to the latest Debian version.

config.softwareConfig.optionalComponents

Optional

list (string)

Immutable. Optional. The set of components to activate on the cluster.

config.softwareConfig.optionalComponents[]

Optional

string

config.softwareConfig.properties

Optional

map (key: string, value: string)

Immutable. Optional. The properties to set on daemon config files. Property keys are specified in `prefix:property` format, for example `core:hadoop.tmp.dir`. The following are supported prefixes and their mappings: * capacity-scheduler: `capacity-scheduler.xml` * core: `core-site.xml` * distcp: `distcp-default.xml` * hdfs: `hdfs-site.xml` * hive: `hive-site.xml` * mapred: `mapred-site.xml` * pig: `pig.properties` * spark: `spark-defaults.conf` * yarn: `yarn-site.xml` For more information, see [Cluster properties](https://cloud.google.com/dataproc/docs/concepts/cluster-properties).

config.stagingBucketRef

Optional

object

Immutable.

config.stagingBucketRef.external

Optional

string

Optional. A Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, Cloud Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see [Dataproc staging bucket](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). **This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.** Allowed value: The Google Cloud resource name of a `StorageBucket` resource (format: `{{name}}`).

config.stagingBucketRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.stagingBucketRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.tempBucketRef

Optional

object

Immutable.

config.tempBucketRef.external

Optional

string

Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs data, such as Spark and MapReduce history files. If you do not specify a temp bucket, Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's temp bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket. The default bucket has a TTL of 90 days, but you can use any TTL (or none) if you specify a bucket. **This field requires a Cloud Storage bucket name, not a URI to a Cloud Storage bucket.** Allowed value: The Google Cloud resource name of a `StorageBucket` resource (format: `{{name}}`).

config.tempBucketRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.tempBucketRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.workerConfig

Optional

object

Immutable. Optional. The Compute Engine config settings for worker instances in a cluster.

config.workerConfig.accelerators

Optional

list (object)

Immutable. Optional. The Compute Engine accelerator configuration for these instances.

config.workerConfig.accelerators[]

Optional

object

config.workerConfig.accelerators[].acceleratorCount

Optional

integer

Immutable. The number of the accelerator cards of this type exposed to this instance.

config.workerConfig.accelerators[].acceleratorType

Optional

string

Immutable. Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See [Compute Engine AcceleratorTypes](https://cloud.google.com/compute/docs/reference/beta/acceleratorTypes). Examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `projects/[project_id]/zones/us-east1-a/acceleratorTypes/nvidia-tesla-k80` * `nvidia-tesla-k80` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the accelerator type resource, for example, `nvidia-tesla-k80`.

config.workerConfig.diskConfig

Optional

object

Immutable. Optional. Disk option config settings.

config.workerConfig.diskConfig.bootDiskSizeGb

Optional

integer

Immutable. Optional. Size in GB of the boot disk (default is 500GB).

config.workerConfig.diskConfig.bootDiskType

Optional

string

Immutable. Optional. Type of the boot disk (default is "pd-standard"). Valid values: "pd-balanced" (Persistent Disk Balanced Solid State Drive), "pd-ssd" (Persistent Disk Solid State Drive), or "pd-standard" (Persistent Disk Hard Disk Drive). See [Disk types](https://cloud.google.com/compute/docs/disks#disk-types).

config.workerConfig.diskConfig.localSsdInterface

Optional

string

Immutable. Optional. Interface type of local SSDs (default is "scsi"). Valid values: "scsi" (Small Computer System Interface), "nvme" (Non-Volatile Memory Express). See [local SSD performance](https://cloud.google.com/compute/docs/disks/local-ssd#performance).

config.workerConfig.diskConfig.numLocalSsds

Optional

integer

Immutable. Optional. Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and [HDFS](https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.

config.workerConfig.imageRef

Optional

object

Immutable.

config.workerConfig.imageRef.external

Optional

string

Optional. The Compute Engine image resource used for cluster instances. The URI can represent an image or image family. Image examples: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/[image-id]` * `projects/[project_id]/global/images/[image-id]` * `image-id` Image family examples. Dataproc will use the most recent image from the family: * `https://www.googleapis.com/compute/beta/projects/[project_id]/global/images/family/[custom-image-family-name]` * `projects/[project_id]/global/images/family/[custom-image-family-name]` If the URI is unspecified, it will be inferred from `SoftwareConfig.image_version` or the system default. Allowed value: The `selfLink` field of a `ComputeImage` resource.

config.workerConfig.imageRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

config.workerConfig.imageRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

config.workerConfig.machineType

Optional

string

Immutable. Optional. The Compute Engine machine type used for cluster instances. A full URL, partial URI, or short name are valid. Examples: * `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2` * `n1-standard-2` **Auto Zone Exception**: If you are using the Dataproc [Auto Zone Placement](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement) feature, you must use the short name of the machine type resource, for example, `n1-standard-2`.

config.workerConfig.minCpuPlatform

Optional

string

Immutable. Optional. Specifies the minimum cpu platform for the Instance Group. See [Dataproc -> Minimum CPU Platform](https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu).

config.workerConfig.numInstances

Optional

integer

Immutable. Optional. The number of VM instances in the instance group. For [HA cluster](/dataproc/docs/concepts/configuring-clusters/high-availability) [master_config](#FIELDS.master_config) groups, **must be set to 3**. For standard cluster [master_config](#FIELDS.master_config) groups, **must be set to 1**.

config.workerConfig.preemptibility

Optional

string

Immutable. Optional. Specifies the preemptibility of the instance group. The default value for master and worker groups is `NON_PREEMPTIBLE`. This default cannot be changed. The default value for secondary instances is `PREEMPTIBLE`. Possible values: PREEMPTIBILITY_UNSPECIFIED, NON_PREEMPTIBLE, PREEMPTIBLE

location

Required

string

Immutable. The location for the resource, usually a GCP region.

projectRef

Optional

object

Immutable. The Project that this resource belongs to.

projectRef.external

Optional

string

Required. The Google Cloud Platform project ID that the cluster belongs to. Allowed value: The Google Cloud resource name of a `Project` resource (format: `projects/{{name}}`).

projectRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

projectRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

resourceID

Optional

string

Immutable. Optional. The name of the resource. Used for creation and acquisition. When unset, the value of `metadata.name` is used as the default.

virtualClusterConfig

Optional

object

Immutable. Optional. The virtual cluster config is used when creating a Dataproc cluster that does not directly control the underlying compute resources, for example, when creating a [Dataproc-on-GKE cluster](https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke). Dataproc may set default values, and values may change when clusters are updated. Exactly one of config or virtual_cluster_config must be specified.

virtualClusterConfig.auxiliaryServicesConfig

Optional

object

Immutable. Optional. Configuration of auxiliary services used by this cluster.

virtualClusterConfig.auxiliaryServicesConfig.metastoreConfig

Optional

object

Immutable. Optional. The Hive Metastore configuration for this workload.

virtualClusterConfig.auxiliaryServicesConfig.metastoreConfig.dataprocMetastoreServiceRef

Required*

object

Immutable.

virtualClusterConfig.auxiliaryServicesConfig.metastoreConfig.dataprocMetastoreServiceRef.external

Optional

string

Required. Resource name of an existing Dataproc Metastore service. Example: * `projects/[project_id]/locations/[dataproc_region]/services/[service-name]`

virtualClusterConfig.auxiliaryServicesConfig.metastoreConfig.dataprocMetastoreServiceRef.name

Optional

string

[WARNING] DataprocMetastoreService not yet supported in Config Connector, use 'external' field to reference existing resources. Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

virtualClusterConfig.auxiliaryServicesConfig.metastoreConfig.dataprocMetastoreServiceRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

virtualClusterConfig.auxiliaryServicesConfig.sparkHistoryServerConfig

Optional

object

Immutable. Optional. The Spark History Server configuration for the workload.

virtualClusterConfig.auxiliaryServicesConfig.sparkHistoryServerConfig.dataprocClusterRef

Optional

object

Immutable.

virtualClusterConfig.auxiliaryServicesConfig.sparkHistoryServerConfig.dataprocClusterRef.external

Optional

string

Optional. Resource name of an existing Dataproc Cluster to act as a Spark History Server for the workload. Example: * `projects/[project_id]/regions/[region]/clusters/[cluster_name]` Allowed value: The `selfLink` field of a `DataprocCluster` resource.

virtualClusterConfig.auxiliaryServicesConfig.sparkHistoryServerConfig.dataprocClusterRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

virtualClusterConfig.auxiliaryServicesConfig.sparkHistoryServerConfig.dataprocClusterRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

virtualClusterConfig.kubernetesClusterConfig

Required*

object

Immutable. Required. The configuration for running the Dataproc cluster on Kubernetes.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig

Required*

object

Immutable. Required. The configuration for running the Dataproc cluster on GKE.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.gkeClusterTargetRef

Optional

object

Immutable.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.gkeClusterTargetRef.external

Optional

string

Optional. A target GKE cluster to deploy to. It must be in the same project and region as the Dataproc cluster (the GKE cluster can be zonal or regional). Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}' Allowed value: The `selfLink` field of a `ContainerCluster` resource.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.gkeClusterTargetRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.gkeClusterTargetRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget

Optional

list (object)

Immutable. Optional. GKE node pools where workloads will be scheduled. At least one node pool must be assigned the `DEFAULT` GkeNodePoolTarget.Role. If a `GkeNodePoolTarget` is not specified, Dataproc constructs a `DEFAULT` `GkeNodePoolTarget`. Each role can be given to only one `GkeNodePoolTarget`. All node pools must have the same location settings.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[]

Optional

object

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig

Optional

object

Immutable. Input only. The configuration for the GKE node pool. If specified, Dataproc attempts to create a node pool with the specified shape. If one with the same name already exists, it is verified against all specified fields. If a field differs, the virtual cluster creation will fail. If omitted, any node pool with the specified name is used. If a node pool with the specified name does not exist, Dataproc create a node pool with default values. This is an input only field. It will not be returned by the API.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.autoscaling

Optional

object

Immutable. Optional. The autoscaler configuration for this node pool. The autoscaler is enabled only when a valid configuration is present.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.autoscaling.maxNodeCount

Optional

integer

Immutable. The maximum number of nodes in the node pool. Must be >= min_node_count, and must be > 0. **Note:** Quota must be sufficient to scale up the cluster.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.autoscaling.minNodeCount

Optional

integer

Immutable. The minimum number of nodes in the node pool. Must be >= 0 and <= max_node_count.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config

Optional

object

Immutable. Optional. The node pool configuration.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.accelerators

Optional

list (object)

Immutable. Optional. A list of [hardware accelerators](https://cloud.google.com/compute/docs/gpus) to attach to each node.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.accelerators[]

Optional

object

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.accelerators[].acceleratorCount

Optional

integer

Immutable. The number of accelerator cards exposed to an instance.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.accelerators[].acceleratorType

Optional

string

Immutable. The accelerator type resource namename (see GPUs on Compute Engine).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.accelerators[].gpuPartitionSize

Optional

string

Immutable. Size of partitions to create on the GPU. Valid values are described in the NVIDIA [mig user guide](https://docs.nvidia.com/datacenter/tesla/mig-user-guide/#partitioning).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.bootDiskKmsKey

Optional

string

Immutable. Optional. The [Customer Managed Encryption Key (CMEK)] (https://cloud.google.com/kubernetes-engine/docs/how-to/using-cmek) used to encrypt the boot disk attached to each node in the node pool. Specify the key using the following format: `projects/KEY_PROJECT_ID/locations/LOCATION/keyRings/RING_NAME/cryptoKeys/KEY_NAME`.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.ephemeralStorageConfig

Optional

object

Immutable. Optional. Parameters for the ephemeral storage filesystem. If unspecified, ephemeral storage is backed by the boot disk.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.ephemeralStorageConfig.localSsdCount

Optional

integer

Immutable. Number of local SSDs to use to back ephemeral storage. Uses NVMe interfaces. Each local SSD is 375 GB in size. If zero, it means to disable using local SSDs as ephemeral storage.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.localSsdCount

Optional

integer

Immutable. Optional. The number of local SSD disks to attach to the node, which is limited by the maximum number of disks allowable per zone (see [Adding Local SSDs](https://cloud.google.com/compute/docs/disks/local-ssd)).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.machineType

Optional

string

Immutable. Optional. The name of a Compute Engine [machine type](https://cloud.google.com/compute/docs/machine-types).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.minCpuPlatform

Optional

string

Immutable. Optional. [Minimum CPU platform](https://cloud.google.com/compute/docs/instances/specify-min-cpu-platform) to be used by this instance. The instance may be scheduled on the specified or a newer CPU platform. Specify the friendly names of CPU platforms, such as "Intel Haswell"` or Intel Sandy Bridge".

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.preemptible

Optional

boolean

Immutable. Optional. Whether the nodes are created as legacy [preemptible VM instances] (https://cloud.google.com/compute/docs/instances/preemptible). Also see Spot VMs, preemptible VM instances without a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the `CONTROLLER` [role] (/dataproc/docs/reference/rest/v1/projects.regions.clusters#role) or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.config.spot

Optional

boolean

Immutable. Optional. Whether the nodes are created as [Spot VM instances] (https://cloud.google.com/compute/docs/instances/spot). Spot VMs are the latest update to legacy preemptible VMs. Spot VMs do not have a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the `CONTROLLER` [role](/dataproc/docs/reference/rest/v1/projects.regions.clusters#role) or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.locations

Optional

list (string)

Immutable. Optional. The list of Compute Engine [zones](https://cloud.google.com/compute/docs/zones#available) where node pool nodes associated with a Dataproc on GKE virtual cluster will be located. **Note:** All node pools associated with a virtual cluster must be located in the same region as the virtual cluster, and they must be located in the same zone within that region. If a location is not specified during node pool creation, Dataproc on GKE will choose the zone.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolConfig.locations[]

Optional

string

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolRef

Required*

object

Immutable.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolRef.external

Optional

string

Required. The target GKE node pool. Format: 'projects/{project}/locations/{location}/clusters/{cluster}/nodePools/{node_pool}' Allowed value: The `selfLink` field of a `ContainerNodePool` resource.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].nodePoolRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].roles

Required*

list (string)

Immutable. Required. The roles associated with the GKE node pool.

virtualClusterConfig.kubernetesClusterConfig.gkeClusterConfig.nodePoolTarget[].roles[]

Required*

string

virtualClusterConfig.kubernetesClusterConfig.kubernetesNamespace

Optional

string

Immutable. Optional. A namespace within the Kubernetes cluster to deploy into. If this namespace does not exist, it is created. If it exists, Dataproc verifies that another Dataproc VirtualCluster is not installed into it. If not specified, the name of the Dataproc Cluster is used.

virtualClusterConfig.kubernetesClusterConfig.kubernetesSoftwareConfig

Optional

object

Immutable. Optional. The software configuration for this Dataproc cluster running on Kubernetes.

virtualClusterConfig.kubernetesClusterConfig.kubernetesSoftwareConfig.componentVersion

Optional

map (key: string, value: string)

Immutable. The components that should be installed in this Dataproc cluster. The key must be a string from the KubernetesComponent enumeration. The value is the version of the software to be installed. At least one entry must be specified.

virtualClusterConfig.kubernetesClusterConfig.kubernetesSoftwareConfig.properties

Optional

map (key: string, value: string)

Immutable. The properties to set on daemon config files. Property keys are specified in `prefix:property` format, for example `spark:spark.kubernetes.container.image`. The following are supported prefixes and their mappings: * spark: `spark-defaults.conf` For more information, see [Cluster properties](https://cloud.google.com/dataproc/docs/concepts/cluster-properties).

virtualClusterConfig.stagingBucketRef

Optional

object

Immutable.

virtualClusterConfig.stagingBucketRef.external

Optional

string

Optional. A Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, Cloud Dataproc will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see [Dataproc staging and temp buckets](https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). **This field requires a Cloud Storage bucket name, not a `gs://...` URI to a Cloud Storage bucket.** Allowed value: The Google Cloud resource name of a `StorageBucket` resource (format: `{{name}}`).

virtualClusterConfig.stagingBucketRef.name

Optional

string

Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

virtualClusterConfig.stagingBucketRef.namespace

Optional

string

Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/

* Field is required when parent field is specified

Status

Schema

clusterUuid: string
conditions:
- lastTransitionTime: string
  message: string
  reason: string
  status: string
  type: string
config:
  endpointConfig:
    httpPorts:
      string: string
  lifecycleConfig:
    idleStartTime: string
  masterConfig:
    instanceNames:
    - string
    instanceReferences:
    - instanceId: string
      instanceName: string
      publicEciesKey: string
      publicKey: string
    isPreemptible: boolean
    managedGroupConfig:
      instanceGroupManagerName: string
      instanceTemplateName: string
  secondaryWorkerConfig:
    instanceNames:
    - string
    instanceReferences:
    - instanceId: string
      instanceName: string
      publicEciesKey: string
      publicKey: string
    isPreemptible: boolean
    managedGroupConfig:
      instanceGroupManagerName: string
      instanceTemplateName: string
  workerConfig:
    instanceNames:
    - string
    instanceReferences:
    - instanceId: string
      instanceName: string
      publicEciesKey: string
      publicKey: string
    isPreemptible: boolean
    managedGroupConfig:
      instanceGroupManagerName: string
      instanceTemplateName: string
metrics:
  hdfsMetrics:
    string: string
  yarnMetrics:
    string: string
observedGeneration: integer
status:
  detail: string
  state: string
  stateStartTime: string
  substate: string
statusHistory:
- detail: string
  state: string
  stateStartTime: string
  substate: string
Fields
clusterUuid

string

Output only. A cluster UUID (Unique Universal Identifier). Dataproc generates this value when it creates the cluster.

conditions

list (object)

Conditions represent the latest available observation of the resource's current state.

conditions[]

object

conditions[].lastTransitionTime

string

Last time the condition transitioned from one status to another.

conditions[].message

string

Human-readable message indicating details about last transition.

conditions[].reason

string

Unique, one-word, CamelCase reason for the condition's last transition.

conditions[].status

string

Status is the status of the condition. Can be True, False, Unknown.

conditions[].type

string

Type is the type of the condition.

config

object

config.endpointConfig

object

config.endpointConfig.httpPorts

map (key: string, value: string)

Output only. The map of port descriptions to URLs. Will only be populated if enable_http_port_access is true.

config.lifecycleConfig

object

config.lifecycleConfig.idleStartTime

string

Output only. The time when cluster became idle (most recent job finished) and became eligible for deletion due to idleness (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).

config.masterConfig

object

config.masterConfig.instanceNames

list (string)

Output only. The list of instance names. Dataproc derives the names from `cluster_name`, `num_instances`, and the instance group.

config.masterConfig.instanceNames[]

string

config.masterConfig.instanceReferences

list (object)

Output only. List of references to Compute Engine instances.

config.masterConfig.instanceReferences[]

object

config.masterConfig.instanceReferences[].instanceId

string

The unique identifier of the Compute Engine instance.

config.masterConfig.instanceReferences[].instanceName

string

The user-friendly name of the Compute Engine instance.

config.masterConfig.instanceReferences[].publicEciesKey

string

The public ECIES key used for sharing data with this instance.

config.masterConfig.instanceReferences[].publicKey

string

The public RSA key used for sharing data with this instance.

config.masterConfig.isPreemptible

boolean

Output only. Specifies that this instance group contains preemptible instances.

config.masterConfig.managedGroupConfig

object

Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups.

config.masterConfig.managedGroupConfig.instanceGroupManagerName

string

Output only. The name of the Instance Group Manager for this group.

config.masterConfig.managedGroupConfig.instanceTemplateName

string

Output only. The name of the Instance Template used for the Managed Instance Group.

config.secondaryWorkerConfig

object

config.secondaryWorkerConfig.instanceNames

list (string)

Output only. The list of instance names. Dataproc derives the names from `cluster_name`, `num_instances`, and the instance group.

config.secondaryWorkerConfig.instanceNames[]

string

config.secondaryWorkerConfig.instanceReferences

list (object)

Output only. List of references to Compute Engine instances.

config.secondaryWorkerConfig.instanceReferences[]

object

config.secondaryWorkerConfig.instanceReferences[].instanceId

string

The unique identifier of the Compute Engine instance.

config.secondaryWorkerConfig.instanceReferences[].instanceName

string

The user-friendly name of the Compute Engine instance.

config.secondaryWorkerConfig.instanceReferences[].publicEciesKey

string

The public ECIES key used for sharing data with this instance.

config.secondaryWorkerConfig.instanceReferences[].publicKey

string

The public RSA key used for sharing data with this instance.

config.secondaryWorkerConfig.isPreemptible

boolean

Output only. Specifies that this instance group contains preemptible instances.

config.secondaryWorkerConfig.managedGroupConfig

object

Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups.

config.secondaryWorkerConfig.managedGroupConfig.instanceGroupManagerName

string

Output only. The name of the Instance Group Manager for this group.

config.secondaryWorkerConfig.managedGroupConfig.instanceTemplateName

string

Output only. The name of the Instance Template used for the Managed Instance Group.

config.workerConfig

object

config.workerConfig.instanceNames

list (string)

Output only. The list of instance names. Dataproc derives the names from `cluster_name`, `num_instances`, and the instance group.

config.workerConfig.instanceNames[]

string

config.workerConfig.instanceReferences

list (object)

Output only. List of references to Compute Engine instances.

config.workerConfig.instanceReferences[]

object

config.workerConfig.instanceReferences[].instanceId

string

The unique identifier of the Compute Engine instance.

config.workerConfig.instanceReferences[].instanceName

string

The user-friendly name of the Compute Engine instance.

config.workerConfig.instanceReferences[].publicEciesKey

string

The public ECIES key used for sharing data with this instance.

config.workerConfig.instanceReferences[].publicKey

string

The public RSA key used for sharing data with this instance.

config.workerConfig.isPreemptible

boolean

Output only. Specifies that this instance group contains preemptible instances.

config.workerConfig.managedGroupConfig

object

Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups.

config.workerConfig.managedGroupConfig.instanceGroupManagerName

string

Output only. The name of the Instance Group Manager for this group.

config.workerConfig.managedGroupConfig.instanceTemplateName

string

Output only. The name of the Instance Template used for the Managed Instance Group.

metrics

object

Output only. Contains cluster daemon metrics such as HDFS and YARN stats. **Beta Feature**: This report is available for testing purposes only. It may be changed before final release.

metrics.hdfsMetrics

map (key: string, value: string)

The HDFS metrics.

metrics.yarnMetrics

map (key: string, value: string)

The YARN metrics.

observedGeneration

integer

ObservedGeneration is the generation of the resource that was most recently observed by the Config Connector controller. If this is equal to metadata.generation, then that means that the current reported status reflects the most recent desired state of the resource.

status

object

Output only. Cluster status.

status.detail

string

Optional. Output only. Details of cluster's state.

status.state

string

Output only. The cluster's state. Possible values: UNKNOWN, CREATING, RUNNING, ERROR, DELETING, UPDATING, STOPPING, STOPPED, STARTING

status.stateStartTime

string

Output only. Time when this state was entered (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).

status.substate

string

Output only. Additional state information that includes status reported by the agent. Possible values: UNSPECIFIED, UNHEALTHY, STALE_STATUS

statusHistory

list (object)

Output only. The previous cluster status.

statusHistory[]

object

statusHistory[].detail

string

Optional. Output only. Details of cluster's state.

statusHistory[].state

string

Output only. The cluster's state. Possible values: UNKNOWN, CREATING, RUNNING, ERROR, DELETING, UPDATING, STOPPING, STOPPED, STARTING

statusHistory[].stateStartTime

string

Output only. Time when this state was entered (see JSON representation of [Timestamp](https://developers.google.com/protocol-buffers/docs/proto3#json)).

statusHistory[].substate

string

Output only. Additional state information that includes status reported by the agent. Possible values: UNSPECIFIED, UNHEALTHY, STALE_STATUS

Sample YAML(s)

Typical Use Case

# Copyright 2020 Google LLC
#
# Licensed 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.

apiVersion: dataproc.cnrm.cloud.google.com/v1beta1
kind: DataprocCluster
metadata:
  annotations:
    cnrm.cloud.google.com/management-conflict-prevention-policy: "none"
  name: dataproccluster-sample
  labels:
    label-one: "value-one"
spec:
  location: "us-central1"
  config:
    autoscalingConfig:
      policyRef:
        name: dataproccluster-dep
    stagingBucketRef:
      name: dataproccluster-dep-staging
    masterConfig:
      diskConfig:
        bootDiskSizeGb: 30
        bootDiskType: pd-standard
      machineType: "n2-standard-2"
      numInstances: 1
    workerConfig:
      numInstances: 2
      machineType: "n2-standard-2"
      diskConfig:
        bootDiskSizeGb: 30
        numLocalSsds: 1
    softwareConfig:
      imageVersion: "2.0.39-debian10"
    gceClusterConfig:
      tags:
      - "foo"
      - "bar"
    initializationActions:
    - executableFile: "gs://dataproc-initialization-actions/stackdriver/stackdriver.sh"
      executionTimeout: "500s"
---
apiVersion: dataproc.cnrm.cloud.google.com/v1beta1
kind: DataprocAutoscalingPolicy
metadata:
  annotations:
  name: dataproccluster-dep
spec:
  location: "us-central1"
  workerConfig:
    maxInstances: 5
  secondaryWorkerConfig:
    maxInstances: 2
  basicAlgorithm:
    yarnConfig:
      gracefulDecommissionTimeout: "30s"
      scaleDownFactor: 0.5
      scaleUpFactor: 0.5
---
apiVersion: storage.cnrm.cloud.google.com/v1beta1
kind: StorageBucket
metadata:
  annotations:
    cnrm.cloud.google.com/force-destroy: "true"
  labels:
    label-one: "value-one"
  name: dataproccluster-dep-staging
spec:
  # StorageBucket names must be globally unique. Replace ${PROJECT_ID?} with your project ID.
  resourceID: ${PROJECT_ID?}-dataproccluster-dep-staging
  bucketPolicyOnly: true