README.md

Databricks Workspace Terraform module

Terraform module used for Databricks Workspace configuration and Resources creation

Usage

This module provides an ability for Databricks Workspace configuration and Resources creation, for example:

1. Default Shared Autoscaling cluster
2. ADLS Gen2 Mount
3. Secret scope and its secrets
4. Users for Standard SKU Worspaces

# Prerequisite resources
data "azurerm_databricks_workspace" "example" {
  name                = "example-workspace"
  resource_group_name = "example-rg"
}

# Databricks Provider configuration
provider "databricks" {
  alias                       = "main"
  host                        = data.azurerm_databricks_workspace.example.workspace_url
  azure_workspace_resource_id = data.azurerm_databricks_workspace.example.id
}

# Key Vault which contains Service Principal credentials (App ID and Secret) for mounting ADLS Gen 2
data "azurerm_key_vault" "example" {
  name                = "example-key-vault"
  resource_group_name = "example-rg"
}

data "azurerm_storage_account" "example" {
  name                = "examplestorage"
  resource_group_name = "example-rg"
}

# Databricks Runtime module usage example
module "databricks_runtime_core" {
  source  = "data-platform-hq/databricks-runtime/databricks"

  sku          = "standard"
  workspace_id = data.azurerm_databricks_workspace.example.workspace_id
  
  # Databricks user
  users        = ["user1", "user2"]  

  # Default cluster parameters
  custom_default_cluster_name  = "databricks_example_custer"
  cluster_nodes_availability   = "SPOT_AZURE" # it required to increase Regional Spot quotas  
  cluster_log_conf_destination = "dbfs:/cluster-logs"

  # Parameters of Service principal used for ADLS mount
  # Imports App ID and Secret of Service Principal from target Key Vault
  key_vault_id             =  data.azurerm_key_vault.example.id
  sp_client_id_secret_name = "sp-client-id" # secret's name that stores Service Principal App ID
  sp_key_secret_name       = "sp-key" # secret's name that stores Service Principal Secret Key
  tenant_id_secret_name    = "infra-arm-tenant-id" # secret's name that stores tenant id value

  # Additional Secret Scope
  secret_scope = [{
    scope_name = "extra-scope"
    acl        = null # Only group names are allowed. If left empty then only Workspace admins could access these keys
    secrets    = [
      { key = "secret-name", string_value = "secret-value"}
    ]
  }]

  mountpoints = {
    storage_account_name = data.azurerm_storage_account.example.name
    container_name       = "example_container"
  }

  providers = {
    databricks = databricks.main
  }
}

Requirements

Name	Version
terraform	>=1.0.0
azurerm	>= 4.0.1
databricks	>=1.9.2

Providers

Name	Version
azurerm	>= 4.0.1
databricks	>=1.9.2

Modules

No modules.

Resources

Name	Type
azurerm_role_assignment.this	resource
databricks_cluster.this	resource
databricks_mount.adls	resource
databricks_secret.main	resource
databricks_secret.this	resource
databricks_secret_scope.main	resource
databricks_secret_scope.this	resource
databricks_token.pat	resource
databricks_user.this	resource
azurerm_key_vault_secret.sp_client_id	data source
azurerm_key_vault_secret.sp_key	data source
azurerm_key_vault_secret.tenant_id	data source

Inputs

Name	Description	Type	Default	Required
autotermination_minutes	Automatically terminate the cluster after being inactive for this time in minutes. If not set, Databricks won't automatically terminate an inactive cluster. If specified, the threshold must be between 10 and 10000 minutes. You can also set this value to 0 to explicitly disable automatic termination.	number	15	no
cluster_log_conf_destination	Provide a dbfs location to push all cluster logs to certain location	string	""	no
cluster_nodes_availability	Availability type used for all subsequent nodes past the first_on_demand ones: [SPOT_AZURE|SPOT_WITH_FALLBACK_AZURE|ON_DEMAND_AZURE]	string	null	no
custom_default_cluster_name	Databricks cluster name, which does not have to be unique	string	null	no
data_security_mode	Security features of the cluster	string	"NONE"	no
first_on_demand	The first first_on_demand nodes of the cluster will be placed on on-demand instances: [[:number]]	number	0	no
key_vault_id	ID of the Key Vault instance where the Secret resides	string	n/a	yes
max_workers	The maximum number of workers to which the cluster can scale up when overloaded. max_workers must be strictly greater than min_workers.	number	2	no
min_workers	The minimum number of workers to which the cluster can scale down when underutilized. It is also the initial number of workers the cluster will have after creation.	number	1	no
mountpoints	Mountpoints for databricks	map(object({ storage_account_name = string container_name = string }))	{}	no
node_type	Databricks_node_type id	string	"Standard_D3_v2"	no
pat_token_lifetime_seconds	The lifetime of the token, in seconds. If no lifetime is specified, the token remains valid indefinitely	number	315569520	no
permissions	Databricks Workspace permission maps	list(map(string))	[ { "object_id": null, "role": null } ]	no
secret_scope	Provides an ability to create custom Secret Scope, store secrets in it and assigning ACL for access management scope_name - name of Secret Scope to create; acl - list of objects, where 'principal' custom group name, this group is created in 'Premium' module; 'permission' is one of "READ", "WRITE", "MANAGE"; secrets - list of objects, where object's 'key' param is created key name and 'string_value' is a value for it;	list(object({ scope_name = string acl = optional(list(object({ principal = string permission = string }))) secrets = optional(list(object({ key = string string_value = string }))) }))	[ { "acl": null, "scope_name": null, "secrets": null } ]	no
single_user_name	single user cluster mode	string	null	no
sp_client_id_secret_name	The name of Azure Key Vault secret that contains ClientID of Service Principal to access in Azure Key Vault	string	n/a	yes
sp_key_secret_name	The name of Azure Key Vault secret that contains client secret of Service Principal to access in Azure Key Vault	string	n/a	yes
spark_conf	Map with key-value pairs to fine-tune Spark clusters, where you can provide custom Spark configuration properties in a cluster configuration.	map(any)	{}	no
spark_env_vars	Map with environment variable key-value pairs to fine-tune Spark clusters. Key-value pairs of the form (X,Y) are exported (i.e., X='Y') while launching the driver and workers.	map(any)	{}	no
spark_version	Runtime version	string	"11.3.x-scala2.12"	no
spot_bid_max_price	The max price for Azure spot instances. Use -1 to specify lowest price.	number	-1	no
tenant_id_secret_name	The name of Azure Key Vault secret that contains tenant ID secret of Service Principal to access in Azure Key Vault	string	n/a	yes
users	List of users to access Databricks	list(string)	[]	no
workspace_id	Databricks Workspace ID	string	n/a	yes

Outputs

Name	Description
cluster_id	Databricks Cluster Id
token	Databricks Personal Authorization Token

License

Apache 2 Licensed. For more information please see LICENSE