Databricks · Schema

CreateClusterRequest

AIAnalyticsApache SparkBig DataClean RoomsCloud ComputingDataData AnalyticsData EngineeringData GovernanceDelta LakeDelta SharingETLIdentity ManagementLakehouseMachine LearningMLflowModel ServingSecuritySQLUnity CatalogVector SearchVisualize

Properties

Name Type Description
cluster_name string A human-readable name for the cluster. This does not need to be unique.
spark_version string The runtime version of the cluster. You can retrieve a list of available runtime versions using the Runtime Versions API.
node_type_id string The node type for worker nodes. This field determines the cloud provider instance type.
driver_node_type_id string The node type for the Spark driver. If not specified, defaults to the same value as node_type_id.
num_workers integer Number of worker nodes for a fixed-size cluster. A cluster has one Spark driver and num_workers executors. Set to 0 for a single-node cluster.
spark_conf object A map of Spark configuration key-value pairs. These override the default Spark configuration values.
custom_tags object Additional tags for cluster resources. Tags are propagated to the cloud provider for cost tracking.
spark_env_vars object Environment variables for all Spark processes. Use {{secrets/scope/key}} to reference secrets.
autotermination_minutes integer Minutes of inactivity after which the cluster is automatically terminated. 0 disables auto-termination.
enable_elastic_disk boolean Whether to autoscale local storage. When enabled, Databricks monitors disk usage and attaches additional disks as needed.
instance_pool_id string The optional ID of the instance pool to use for cluster nodes.
policy_id string The ID of the cluster policy to apply. Cluster policies constrain the configuration settings.
enable_local_disk_encryption boolean Whether to encrypt data on local disks.
runtime_engine string The runtime engine. PHOTON enables the Photon vectorized query engine for faster performance.
data_security_mode string Data security mode for the cluster.
single_user_name string The user name (email) of the single user for SINGLE_USER access mode.
init_scripts array Init scripts to run when the cluster starts.
ssh_public_keys array SSH public keys to add to each Spark node.
View JSON Schema on GitHub

JSON Schema

databricks-create-cluster-request-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "CreateClusterRequest",
  "type": "object",
  "properties": {
    "cluster_name": {
      "type": "string",
      "description": "A human-readable name for the cluster. This does not need to be unique."
    },
    "spark_version": {
      "type": "string",
      "description": "The runtime version of the cluster. You can retrieve a list of available runtime versions using the Runtime Versions API."
    },
    "node_type_id": {
      "type": "string",
      "description": "The node type for worker nodes. This field determines the cloud provider instance type."
    },
    "driver_node_type_id": {
      "type": "string",
      "description": "The node type for the Spark driver. If not specified, defaults to the same value as node_type_id."
    },
    "num_workers": {
      "type": "integer",
      "description": "Number of worker nodes for a fixed-size cluster. A cluster has one Spark driver and num_workers executors. Set to 0 for a single-node cluster."
    },
    "spark_conf": {
      "type": "object",
      "description": "A map of Spark configuration key-value pairs. These override the default Spark configuration values."
    },
    "custom_tags": {
      "type": "object",
      "description": "Additional tags for cluster resources. Tags are propagated to the cloud provider for cost tracking."
    },
    "spark_env_vars": {
      "type": "object",
      "description": "Environment variables for all Spark processes. Use {{secrets/scope/key}} to reference secrets."
    },
    "autotermination_minutes": {
      "type": "integer",
      "description": "Minutes of inactivity after which the cluster is automatically terminated. 0 disables auto-termination."
    },
    "enable_elastic_disk": {
      "type": "boolean",
      "description": "Whether to autoscale local storage. When enabled, Databricks monitors disk usage and attaches additional disks as needed."
    },
    "instance_pool_id": {
      "type": "string",
      "description": "The optional ID of the instance pool to use for cluster nodes."
    },
    "policy_id": {
      "type": "string",
      "description": "The ID of the cluster policy to apply. Cluster policies constrain the configuration settings."
    },
    "enable_local_disk_encryption": {
      "type": "boolean",
      "description": "Whether to encrypt data on local disks."
    },
    "runtime_engine": {
      "type": "string",
      "description": "The runtime engine. PHOTON enables the Photon vectorized query engine for faster performance."
    },
    "data_security_mode": {
      "type": "string",
      "description": "Data security mode for the cluster."
    },
    "single_user_name": {
      "type": "string",
      "description": "The user name (email) of the single user for SINGLE_USER access mode."
    },
    "init_scripts": {
      "type": "array",
      "description": "Init scripts to run when the cluster starts."
    },
    "ssh_public_keys": {
      "type": "array",
      "description": "SSH public keys to add to each Spark node."
    }
  }
}