ClusterConfig

import type { ClusterConfig } from "https://googleapis.deno.dev/v1/dataproc:v1.ts";

The cluster config.

interface ClusterConfig {

autoscalingConfig?: AutoscalingConfig;

auxiliaryNodeGroups?: AuxiliaryNodeGroup[];

configBucket?: string;

dataprocMetricConfig?: DataprocMetricConfig;

encryptionConfig?: EncryptionConfig;

endpointConfig?: EndpointConfig;

gceClusterConfig?: GceClusterConfig;

gkeClusterConfig?: GkeClusterConfig;

initializationActions?: NodeInitializationAction[];

lifecycleConfig?: LifecycleConfig;

masterConfig?: InstanceGroupConfig;

metastoreConfig?: MetastoreConfig;

secondaryWorkerConfig?: InstanceGroupConfig;

securityConfig?: SecurityConfig;

softwareConfig?: SoftwareConfig;

tempBucket?: string;

workerConfig?: InstanceGroupConfig;

}

§Properties

autoscalingConfig?: AutoscalingConfig

[src]

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

auxiliaryNodeGroups?: AuxiliaryNodeGroup[]

[src]

Optional. The node group settings.

configBucket?: string

[src]

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.

dataprocMetricConfig?: DataprocMetricConfig

[src]

Optional. The config for Dataproc metrics.

encryptionConfig?: EncryptionConfig

[src]

Optional. Encryption settings for the cluster.

endpointConfig?: EndpointConfig

[src]

Optional. Port/endpoint configuration for this cluster

gceClusterConfig?: GceClusterConfig

[src]

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

gkeClusterConfig?: GkeClusterConfig

[src]

Optional. BETA. The Kubernetes Engine config for Dataproc clusters deployed to The Kubernetes Engine config for Dataproc clusters deployed to Kubernetes. These config settings are mutually exclusive with Compute Engine-based options, such as gce_cluster_config, master_config, worker_config, secondary_worker_config, and autoscaling_config.

initializationActions?: NodeInitializationAction[]

[src]

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

lifecycleConfig?: LifecycleConfig

[src]

Optional. Lifecycle setting for the cluster.

masterConfig?: InstanceGroupConfig

[src]

Optional. The Compute Engine config settings for the cluster's master instance.

metastoreConfig?: MetastoreConfig

[src]

Optional. Metastore configuration.

secondaryWorkerConfig?: InstanceGroupConfig

[src]

Optional. The Compute Engine config settings for a cluster's secondary worker instances

securityConfig?: SecurityConfig

[src]

Optional. Security settings for the cluster.

softwareConfig?: SoftwareConfig

[src]

Optional. The config settings for cluster software.

tempBucket?: string

[src]

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 (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.

workerConfig?: InstanceGroupConfig

[src]

Optional. The Compute Engine config settings for the cluster's worker instances.