v5.18.0/website/docs/r/dataplex_task.html.markdown - terraform-provider-google-beta - Git at Google

 ---
 # ----------------------------------------------------------------------------
 #
 #     ***     AUTO GENERATED CODE    ***    Type: MMv1     ***
 #
 # ----------------------------------------------------------------------------
 #
 #     This file is automatically generated by Magic Modules and manual
 #     changes will be clobbered when the file is regenerated.
 #
 #     Please read more about how to change this file in
 #     .github/CONTRIBUTING.md.
 #
 # ----------------------------------------------------------------------------
 subcategory: "Dataplex"
 description: |-
   A Dataplex task represents the work that you want Dataplex to do on a schedule.
 ---

 # google\_dataplex\_task

 A Dataplex task represents the work that you want Dataplex to do on a schedule. It encapsulates code, parameters, and the schedule.


 To get more information about Task, see:

 * [API documentation](https://cloud.google.com/dataplex/docs/reference/rest/v1/projects.locations.lakes.tasks)
 * How-to Guides
     * [Official Documentation](https://cloud.google.com/dataplex/docs)

 ## Example Usage - Dataplex Task Basic


 ```hcl
 data "google_project" "project" {

 }

 resource "google_dataplex_lake" "example" {
   name         = "tf-test-lake%{random_suffix}"
   location     = "us-central1"
   project = "my-project-name"
 }


 resource "google_dataplex_task" "example" {

     task_id      = "tf-test-task%{random_suffix}"
     location     = "us-central1"
     lake         = google_dataplex_lake.example.name

     description = "Test Task Basic"

     display_name = "task-basic"

     labels = { "count": "3" }

     trigger_spec  {
         type = "RECURRING"
         disabled = false
         max_retries = 3
         start_time = "2023-10-02T15:01:23Z"
         schedule = "1 * * * *"
     }

     execution_spec {
         service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
         project = "my-project-name"
         max_job_execution_lifetime = "100s"
         kms_key = "234jn2kjn42k3n423"
     }

     spark {
         python_script_file = "gs://dataproc-examples/pyspark/hello-world/hello-world.py"

     }

     project = "my-project-name"

 }
 ```
 ## Example Usage - Dataplex Task Spark


 ```hcl
 # VPC network
 resource "google_compute_network" "default" {
     name                    = "tf-test-workstation-cluster%{random_suffix}"
     auto_create_subnetworks = true
 }

 data "google_project" "project" {

 }

 resource "google_dataplex_lake" "example_spark" {
   name         = "tf-test-lake%{random_suffix}"
   location     = "us-central1"
   project = "my-project-name"
 }


 resource "google_dataplex_task" "example_spark" {

     task_id      = "tf-test-task%{random_suffix}"
     location     = "us-central1"
     lake         = google_dataplex_lake.example_spark.name
     trigger_spec  {
         type = "ON_DEMAND"
     }

     description = "task-spark-terraform"

     execution_spec {
         service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
         args = {
             TASK_ARGS  = "--output_location,gs://spark-job/task-result, --output_format, json"
         }

     }

     spark {
         infrastructure_spec  {
             batch {
                 executors_count = 2
                 max_executors_count = 100
             }
             container_image {
                 image = "test-image"
                 java_jars = ["test-java-jars.jar"]
                 python_packages = ["gs://bucket-name/my/path/to/lib.tar.gz"]
                 properties = { "name": "wrench", "mass": "1.3kg", "count": "3" }
             }
             vpc_network  {
                     network_tags = ["test-network-tag"]
                     sub_network = google_compute_network.default.id
                 }
         }
         file_uris = ["gs://terrafrom-test/test.csv"]
         archive_uris = ["gs://terraform-test/test.csv"]
         sql_script = "show databases"
     }

     project = "my-project-name"

 }
 ```
 ## Example Usage - Dataplex Task Notebook


 ```hcl
 # VPC network
 resource "google_compute_network" "default" {
     name                    = "tf-test-workstation-cluster%{random_suffix}"
     auto_create_subnetworks = true
 }


 data "google_project" "project" {

 }

 resource "google_dataplex_lake" "example_notebook" {
   name         = "tf-test-lake%{random_suffix}"
   location     = "us-central1"
   project = "my-project-name"
 }


 resource "google_dataplex_task" "example_notebook" {

     task_id      = "tf-test-task%{random_suffix}"
     location     = "us-central1"
     lake         = google_dataplex_lake.example_notebook.name
     trigger_spec  {
         type = "RECURRING"
         schedule = "1 * * * *"
     }

     execution_spec {
         service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
         args = {
             TASK_ARGS  = "--output_location,gs://spark-job-jars-anrajitha/task-result, --output_format, json"
         }
     }
     notebook {
         notebook = "gs://terraform-test/test-notebook.ipynb"
         infrastructure_spec  {
             batch {
                 executors_count = 2
                 max_executors_count = 100
             }
             container_image {
                 image = "test-image"
                 java_jars = ["test-java-jars.jar"]
                 python_packages = ["gs://bucket-name/my/path/to/lib.tar.gz"]
                 properties = { "name": "wrench", "mass": "1.3kg", "count": "3" }
             }
             vpc_network  {
                     network_tags = ["test-network-tag"]
                     network = google_compute_network.default.id
                 }
         }
         file_uris = ["gs://terraform-test/test.csv"]
         archive_uris = ["gs://terraform-test/test.csv"]

     }
     project = "my-project-name"


 }
 ```

 ## Argument Reference

 The following arguments are supported:


 * `trigger_spec` -
   (Required)
   Configuration for the cluster
   Structure is [documented below](#nested_trigger_spec).

 * `execution_spec` -
   (Required)
   Configuration for the cluster
   Structure is [documented below](#nested_execution_spec).


 <a name="nested_trigger_spec"></a>The `trigger_spec` block supports:

 * `type` -
   (Required)
   Trigger type of the user-specified Task
   Possible values are: `ON_DEMAND`, `RECURRING`.

 * `start_time` -
   (Optional)
   The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.

 * `disabled` -
   (Optional)
   Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.

 * `max_retries` -
   (Optional)
   Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.

 * `schedule` -
   (Optional)
   Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.

 <a name="nested_execution_spec"></a>The `execution_spec` block supports:

 * `args` -
   (Optional)
   The arguments to pass to the task. The args can use placeholders of the format ${placeholder} as part of key/value string. These will be interpolated before passing the args to the driver. Currently supported placeholders: - ${taskId} - ${job_time} To pass positional args, set the key as TASK_ARGS. The value should be a comma-separated string of all the positional arguments. To use a delimiter other than comma, refer to https://cloud.google.com/sdk/gcloud/reference/topic/escaping. In case of other keys being present in the args, then TASK_ARGS will be passed as the last argument. An object containing a list of 'key': value pairs. Example: { 'name': 'wrench', 'mass': '1.3kg', 'count': '3' }.

 * `service_account` -
   (Required)
   Service account to use to execute a task. If not provided, the default Compute service account for the project is used.

 * `project` -
   (Optional)
   The project in which jobs are run. By default, the project containing the Lake is used. If a project is provided, the ExecutionSpec.service_account must belong to this project.

 * `max_job_execution_lifetime` -
   (Optional)
   The maximum duration after which the job execution is expired. A duration in seconds with up to nine fractional digits, ending with 's'. Example: '3.5s'.

 * `kms_key` -
   (Optional)
   The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.

 - - -


 * `description` -
   (Optional)
   User-provided description of the task.

 * `display_name` -
   (Optional)
   User friendly display name.

 * `labels` -
   (Optional)
   User-defined labels for the task.

   **Note**: This field is non-authoritative, and will only manage the labels present in your configuration.
   Please refer to the field `effective_labels` for all of the labels present on the resource.

 * `spark` -
   (Optional)
   A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
   Structure is [documented below](#nested_spark).

 * `notebook` -
   (Optional)
   A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
   Structure is [documented below](#nested_notebook).

 * `location` -
   (Optional)
   The location in which the task will be created in.

 * `lake` -
   (Optional)
   The lake in which the task will be created in.

 * `task_id` -
   (Optional)
   The task Id of the task.

 * `project` - (Optional) The ID of the project in which the resource belongs.
     If it is not provided, the provider project is used.


 <a name="nested_spark"></a>The `spark` block supports:

 * `file_uris` -
   (Optional)
   Cloud Storage URIs of files to be placed in the working directory of each executor.

 * `archive_uris` -
   (Optional)
   Cloud Storage URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

 * `infrastructure_spec` -
   (Optional)
   Infrastructure specification for the execution.
   Structure is [documented below](#nested_infrastructure_spec).

 * `main_jar_file_uri` -
   (Optional)
   The Cloud Storage URI of the jar file that contains the main class. The execution args are passed in as a sequence of named process arguments (--key=value).

 * `main_class` -
   (Optional)
   The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris. The execution args are passed in as a sequence of named process arguments (--key=value).

 * `python_script_file` -
   (Optional)
   The Gcloud Storage URI of the main Python file to use as the driver. Must be a .py file. The execution args are passed in as a sequence of named process arguments (--key=value).

 * `sql_script_file` -
   (Optional)
   A reference to a query file. This can be the Cloud Storage URI of the query file or it can the path to a SqlScript Content. The execution args are used to declare a set of script variables (set key='value';).

 * `sql_script` -
   (Optional)
   The query text. The execution args are used to declare a set of script variables (set key='value';).


 <a name="nested_infrastructure_spec"></a>The `infrastructure_spec` block supports:

 * `batch` -
   (Optional)
   Compute resources needed for a Task when using Dataproc Serverless.
   Structure is [documented below](#nested_batch).

 * `container_image` -
   (Optional)
   Container Image Runtime Configuration.
   Structure is [documented below](#nested_container_image).

 * `vpc_network` -
   (Optional)
   Vpc network.
   Structure is [documented below](#nested_vpc_network).


 <a name="nested_batch"></a>The `batch` block supports:

 * `executors_count` -
   (Optional)
   Total number of job executors. Executor Count should be between 2 and 100. [Default=2]

 * `max_executors_count` -
   (Optional)
   Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]

 <a name="nested_container_image"></a>The `container_image` block supports:

 * `image` -
   (Optional)
   Container image to use.

 * `java_jars` -
   (Optional)
   A list of Java JARS to add to the classpath. Valid input includes Cloud Storage URIs to Jar binaries. For example, gs://bucket-name/my/path/to/file.jar

 * `python_packages` -
   (Optional)
   A list of python packages to be installed. Valid formats include Cloud Storage URI to a PIP installable library. For example, gs://bucket-name/my/path/to/lib.tar.gz

 * `properties` -
   (Optional)
   Override to common configuration of open source components installed on the Dataproc cluster. The properties to set on daemon config files. Property keys are specified in prefix:property format, for example core:hadoop.tmp.dir. For more information, see Cluster properties.

 <a name="nested_vpc_network"></a>The `vpc_network` block supports:

 * `network_tags` -
   (Optional)
   List of network tags to apply to the job.

 * `network` -
   (Optional)
   The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.

 * `sub_network` -
   (Optional)
   The Cloud VPC sub-network in which the job is run.

 <a name="nested_notebook"></a>The `notebook` block supports:

 * `notebook` -
   (Required)
   Path to input notebook. This can be the Cloud Storage URI of the notebook file or the path to a Notebook Content. The execution args are accessible as environment variables (TASK_key=value).

 * `infrastructure_spec` -
   (Optional)
   Infrastructure specification for the execution.
   Structure is [documented below](#nested_infrastructure_spec).

 * `file_uris` -
   (Optional)
   Cloud Storage URIs of files to be placed in the working directory of each executor.

 * `archive_uris` -
   (Optional)
   Cloud Storage URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.


 <a name="nested_infrastructure_spec"></a>The `infrastructure_spec` block supports:

 * `batch` -
   (Optional)
   Compute resources needed for a Task when using Dataproc Serverless.
   Structure is [documented below](#nested_batch).

 * `container_image` -
   (Optional)
   Container Image Runtime Configuration.
   Structure is [documented below](#nested_container_image).

 * `vpc_network` -
   (Optional)
   Vpc network.
   Structure is [documented below](#nested_vpc_network).


 <a name="nested_batch"></a>The `batch` block supports:

 * `executors_count` -
   (Optional)
   Total number of job executors. Executor Count should be between 2 and 100. [Default=2]

 * `max_executors_count` -
   (Optional)
   Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]

 <a name="nested_container_image"></a>The `container_image` block supports:

 * `image` -
   (Optional)
   Container image to use.

 * `java_jars` -
   (Optional)
   A list of Java JARS to add to the classpath. Valid input includes Cloud Storage URIs to Jar binaries. For example, gs://bucket-name/my/path/to/file.jar

 * `python_packages` -
   (Optional)
   A list of python packages to be installed. Valid formats include Cloud Storage URI to a PIP installable library. For example, gs://bucket-name/my/path/to/lib.tar.gz

 * `properties` -
   (Optional)
   Override to common configuration of open source components installed on the Dataproc cluster. The properties to set on daemon config files. Property keys are specified in prefix:property format, for example core:hadoop.tmp.dir. For more information, see Cluster properties.

 <a name="nested_vpc_network"></a>The `vpc_network` block supports:

 * `network_tags` -
   (Optional)
   List of network tags to apply to the job.

 * `network` -
   (Optional)
   The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.

 * `sub_network` -
   (Optional)
   The Cloud VPC sub-network in which the job is run.

 ## Attributes Reference

 In addition to the arguments listed above, the following computed attributes are exported:

 * `id` - an identifier for the resource with format `projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}`

 * `name` -
   The relative resource name of the task, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/ tasks/{name}.

 * `uid` -
   System generated globally unique ID for the task. This ID will be different if the task is deleted and re-created with the same name.

 * `create_time` -
   The time when the task was created.

 * `update_time` -
   The time when the task was last updated.

 * `state` -
   Current state of the task.

 * `execution_status` -
   Configuration for the cluster
   Structure is [documented below](#nested_execution_status).

 * `terraform_labels` -
   The combination of labels configured directly on the resource
    and default labels configured on the provider.

 * `effective_labels` -
   All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Terraform, other clients and services.


 <a name="nested_execution_status"></a>The `execution_status` block contains:

 * `update_time` -
   (Output)
   Last update time of the status.

 * `latest_job` -
   (Output)
   latest job execution.
   Structure is [documented below](#nested_latest_job).


 <a name="nested_latest_job"></a>The `latest_job` block contains:

 * `name` -
   (Output)
   The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.

 * `uid` -
   (Output)
   System generated globally unique ID for the job.

 * `start_time` -
   (Output)
   The time when the job was started.

 * `end_time` -
   (Output)
   The time when the job ended.

 * `state` -
   (Output)
   Execution state for the job.

 * `retry_count` -
   (Output)
   The number of times the job has been retried (excluding the initial attempt).

 * `service` -
   (Output)
   The underlying service running a job.

 * `service_job` -
   (Output)
   The full resource name for the job run under a particular service.

 * `message` -
   (Output)
   Additional information about the current state.

 ## Timeouts

 This resource provides the following
 [Timeouts](https://developer.hashicorp.com/terraform/plugin/sdkv2/resources/retries-and-customizable-timeouts) configuration options:

 - `create` - Default is 5 minutes.
 - `update` - Default is 5 minutes.
 - `delete` - Default is 5 minutes.

 ## Import


 Task can be imported using any of these accepted formats:

 * `projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}`
 * `{{project}}/{{location}}/{{lake}}/{{task_id}}`
 * `{{location}}/{{lake}}/{{task_id}}`


 In Terraform v1.5.0 and later, use an [`import` block](https://developer.hashicorp.com/terraform/language/import) to import Task using one of the formats above. For example:

 ```tf
 import {
   id = "projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}"
   to = google_dataplex_task.default
 }
 ```

 When using the [`terraform import` command](https://developer.hashicorp.com/terraform/cli/commands/import), Task can be imported using one of the formats above. For example:

 ```
 $ terraform import google_dataplex_task.default projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}
 $ terraform import google_dataplex_task.default {{project}}/{{location}}/{{lake}}/{{task_id}}
 $ terraform import google_dataplex_task.default {{location}}/{{lake}}/{{task_id}}
 ```

 ## User Project Overrides

 This resource supports [User Project Overrides](https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference#user_project_override).
	---
	# ----------------------------------------------------------------------------
	#
	# * AUTO GENERATED CODE * Type: MMv1 ***
	#
	# ----------------------------------------------------------------------------
	#
	# This file is automatically generated by Magic Modules and manual
	# changes will be clobbered when the file is regenerated.
	#
	# Please read more about how to change this file in
	# .github/CONTRIBUTING.md.
	#
	# ----------------------------------------------------------------------------
	subcategory: "Dataplex"
	description: \|-
	A Dataplex task represents the work that you want Dataplex to do on a schedule.
	---

	# google\_dataplex\_task

	A Dataplex task represents the work that you want Dataplex to do on a schedule. It encapsulates code, parameters, and the schedule.


	To get more information about Task, see:

	* [API documentation](https://cloud.google.com/dataplex/docs/reference/rest/v1/projects.locations.lakes.tasks)
	* How-to Guides
	* [Official Documentation](https://cloud.google.com/dataplex/docs)

	## Example Usage - Dataplex Task Basic


	```hcl
	data "google_project" "project" {

	}

	resource "google_dataplex_lake" "example" {
	name = "tf-test-lake%{random_suffix}"
	location = "us-central1"
	project = "my-project-name"
	}


	resource "google_dataplex_task" "example" {

	task_id = "tf-test-task%{random_suffix}"
	location = "us-central1"
	lake = google_dataplex_lake.example.name

	description = "Test Task Basic"

	display_name = "task-basic"

	labels = { "count": "3" }

	trigger_spec {
	type = "RECURRING"
	disabled = false
	max_retries = 3
	start_time = "2023-10-02T15:01:23Z"
	schedule = "1 * * * *"
	}

	execution_spec {
	service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
	project = "my-project-name"
	max_job_execution_lifetime = "100s"
	kms_key = "234jn2kjn42k3n423"
	}

	spark {
	python_script_file = "gs://dataproc-examples/pyspark/hello-world/hello-world.py"

	}

	project = "my-project-name"

	}
	```
	## Example Usage - Dataplex Task Spark


	```hcl
	# VPC network
	resource "google_compute_network" "default" {
	name = "tf-test-workstation-cluster%{random_suffix}"
	auto_create_subnetworks = true
	}

	data "google_project" "project" {

	}

	resource "google_dataplex_lake" "example_spark" {
	name = "tf-test-lake%{random_suffix}"
	location = "us-central1"
	project = "my-project-name"
	}


	resource "google_dataplex_task" "example_spark" {

	task_id = "tf-test-task%{random_suffix}"
	location = "us-central1"
	lake = google_dataplex_lake.example_spark.name
	trigger_spec {
	type = "ON_DEMAND"
	}

	description = "task-spark-terraform"

	execution_spec {
	service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
	args = {
	TASK_ARGS = "--output_location,gs://spark-job/task-result, --output_format, json"
	}

	}

	spark {
	infrastructure_spec {
	batch {
	executors_count = 2
	max_executors_count = 100
	}
	container_image {
	image = "test-image"
	java_jars = ["test-java-jars.jar"]
	python_packages = ["gs://bucket-name/my/path/to/lib.tar.gz"]
	properties = { "name": "wrench", "mass": "1.3kg", "count": "3" }
	}
	vpc_network {
	network_tags = ["test-network-tag"]
	sub_network = google_compute_network.default.id
	}
	}
	file_uris = ["gs://terrafrom-test/test.csv"]
	archive_uris = ["gs://terraform-test/test.csv"]
	sql_script = "show databases"
	}

	project = "my-project-name"

	}
	```
	## Example Usage - Dataplex Task Notebook


	```hcl
	# VPC network
	resource "google_compute_network" "default" {
	name = "tf-test-workstation-cluster%{random_suffix}"
	auto_create_subnetworks = true
	}


	data "google_project" "project" {

	}

	resource "google_dataplex_lake" "example_notebook" {
	name = "tf-test-lake%{random_suffix}"
	location = "us-central1"
	project = "my-project-name"
	}


	resource "google_dataplex_task" "example_notebook" {

	task_id = "tf-test-task%{random_suffix}"
	location = "us-central1"
	lake = google_dataplex_lake.example_notebook.name
	trigger_spec {
	type = "RECURRING"
	schedule = "1 * * * *"
	}

	execution_spec {
	service_account = "${data.google_project.project.number}-compute@developer.gserviceaccount.com"
	args = {
	TASK_ARGS = "--output_location,gs://spark-job-jars-anrajitha/task-result, --output_format, json"
	}
	}
	notebook {
	notebook = "gs://terraform-test/test-notebook.ipynb"
	infrastructure_spec {
	batch {
	executors_count = 2
	max_executors_count = 100
	}
	container_image {
	image = "test-image"
	java_jars = ["test-java-jars.jar"]
	python_packages = ["gs://bucket-name/my/path/to/lib.tar.gz"]
	properties = { "name": "wrench", "mass": "1.3kg", "count": "3" }
	}
	vpc_network {
	network_tags = ["test-network-tag"]
	network = google_compute_network.default.id
	}
	}
	file_uris = ["gs://terraform-test/test.csv"]
	archive_uris = ["gs://terraform-test/test.csv"]

	}
	project = "my-project-name"


	}
	```

	## Argument Reference

	The following arguments are supported:


	* `trigger_spec` -
	(Required)
	Configuration for the cluster
	Structure is [documented below](#nested_trigger_spec).

	* `execution_spec` -
	(Required)
	Configuration for the cluster
	Structure is [documented below](#nested_execution_spec).


	<a name="nested_trigger_spec"></a>The `trigger_spec` block supports:

	* `type` -
	(Required)
	Trigger type of the user-specified Task
	Possible values are: `ON_DEMAND`, `RECURRING`.

	* `start_time` -
	(Optional)
	The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.

	* `disabled` -
	(Optional)
	Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.

	* `max_retries` -
	(Optional)
	Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.

	* `schedule` -
	(Optional)
	Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * , or TZ=America/New_York 1 * * *. This field is required for RECURRING tasks.

	<a name="nested_execution_spec"></a>The `execution_spec` block supports:

	* `args` -
	(Optional)
	The arguments to pass to the task. The args can use placeholders of the format ${placeholder} as part of key/value string. These will be interpolated before passing the args to the driver. Currently supported placeholders: - ${taskId} - ${job_time} To pass positional args, set the key as TASK_ARGS. The value should be a comma-separated string of all the positional arguments. To use a delimiter other than comma, refer to https://cloud.google.com/sdk/gcloud/reference/topic/escaping. In case of other keys being present in the args, then TASK_ARGS will be passed as the last argument. An object containing a list of 'key': value pairs. Example: { 'name': 'wrench', 'mass': '1.3kg', 'count': '3' }.

	* `service_account` -
	(Required)
	Service account to use to execute a task. If not provided, the default Compute service account for the project is used.

	* `project` -
	(Optional)
	The project in which jobs are run. By default, the project containing the Lake is used. If a project is provided, the ExecutionSpec.service_account must belong to this project.

	* `max_job_execution_lifetime` -
	(Optional)
	The maximum duration after which the job execution is expired. A duration in seconds with up to nine fractional digits, ending with 's'. Example: '3.5s'.

	* `kms_key` -
	(Optional)
	The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.

	- - -


	* `description` -
	(Optional)
	User-provided description of the task.

	* `display_name` -
	(Optional)
	User friendly display name.

	* `labels` -
	(Optional)
	User-defined labels for the task.

	Note: This field is non-authoritative, and will only manage the labels present in your configuration.
	Please refer to the field `effective_labels` for all of the labels present on the resource.

	* `spark` -
	(Optional)
	A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
	Structure is [documented below](#nested_spark).

	* `notebook` -
	(Optional)
	A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
	Structure is [documented below](#nested_notebook).

	* `location` -
	(Optional)
	The location in which the task will be created in.

	* `lake` -
	(Optional)
	The lake in which the task will be created in.

	* `task_id` -
	(Optional)
	The task Id of the task.

	* `project` - (Optional) The ID of the project in which the resource belongs.
	If it is not provided, the provider project is used.


	<a name="nested_spark"></a>The `spark` block supports:

	* `file_uris` -
	(Optional)
	Cloud Storage URIs of files to be placed in the working directory of each executor.

	* `archive_uris` -
	(Optional)
	Cloud Storage URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.

	* `infrastructure_spec` -
	(Optional)
	Infrastructure specification for the execution.
	Structure is [documented below](#nested_infrastructure_spec).

	* `main_jar_file_uri` -
	(Optional)
	The Cloud Storage URI of the jar file that contains the main class. The execution args are passed in as a sequence of named process arguments (--key=value).

	* `main_class` -
	(Optional)
	The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris. The execution args are passed in as a sequence of named process arguments (--key=value).

	* `python_script_file` -
	(Optional)
	The Gcloud Storage URI of the main Python file to use as the driver. Must be a .py file. The execution args are passed in as a sequence of named process arguments (--key=value).

	* `sql_script_file` -
	(Optional)
	A reference to a query file. This can be the Cloud Storage URI of the query file or it can the path to a SqlScript Content. The execution args are used to declare a set of script variables (set key='value';).

	* `sql_script` -
	(Optional)
	The query text. The execution args are used to declare a set of script variables (set key='value';).


	<a name="nested_infrastructure_spec"></a>The `infrastructure_spec` block supports:

	* `batch` -
	(Optional)
	Compute resources needed for a Task when using Dataproc Serverless.
	Structure is [documented below](#nested_batch).

	* `container_image` -
	(Optional)
	Container Image Runtime Configuration.
	Structure is [documented below](#nested_container_image).

	* `vpc_network` -
	(Optional)
	Vpc network.
	Structure is [documented below](#nested_vpc_network).


	<a name="nested_batch"></a>The `batch` block supports:

	* `executors_count` -
	(Optional)
	Total number of job executors. Executor Count should be between 2 and 100. [Default=2]

	* `max_executors_count` -
	(Optional)
	Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]

	<a name="nested_container_image"></a>The `container_image` block supports:

	* `image` -
	(Optional)
	Container image to use.

	* `java_jars` -
	(Optional)
	A list of Java JARS to add to the classpath. Valid input includes Cloud Storage URIs to Jar binaries. For example, gs://bucket-name/my/path/to/file.jar

	* `python_packages` -
	(Optional)
	A list of python packages to be installed. Valid formats include Cloud Storage URI to a PIP installable library. For example, gs://bucket-name/my/path/to/lib.tar.gz

	* `properties` -
	(Optional)
	Override to common configuration of open source components installed on the Dataproc cluster. The properties to set on daemon config files. Property keys are specified in prefix:property format, for example core:hadoop.tmp.dir. For more information, see Cluster properties.

	<a name="nested_vpc_network"></a>The `vpc_network` block supports:

	* `network_tags` -
	(Optional)
	List of network tags to apply to the job.

	* `network` -
	(Optional)
	The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.

	* `sub_network` -
	(Optional)
	The Cloud VPC sub-network in which the job is run.

	<a name="nested_notebook"></a>The `notebook` block supports:

	* `notebook` -
	(Required)
	Path to input notebook. This can be the Cloud Storage URI of the notebook file or the path to a Notebook Content. The execution args are accessible as environment variables (TASK_key=value).

	* `infrastructure_spec` -
	(Optional)
	Infrastructure specification for the execution.
	Structure is [documented below](#nested_infrastructure_spec).

	* `file_uris` -
	(Optional)
	Cloud Storage URIs of files to be placed in the working directory of each executor.

	* `archive_uris` -
	(Optional)
	Cloud Storage URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.


	<a name="nested_infrastructure_spec"></a>The `infrastructure_spec` block supports:

	* `batch` -
	(Optional)
	Compute resources needed for a Task when using Dataproc Serverless.
	Structure is [documented below](#nested_batch).

	* `container_image` -
	(Optional)
	Container Image Runtime Configuration.
	Structure is [documented below](#nested_container_image).

	* `vpc_network` -
	(Optional)
	Vpc network.
	Structure is [documented below](#nested_vpc_network).


	<a name="nested_batch"></a>The `batch` block supports:

	* `executors_count` -
	(Optional)
	Total number of job executors. Executor Count should be between 2 and 100. [Default=2]

	* `max_executors_count` -
	(Optional)
	Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]

	<a name="nested_container_image"></a>The `container_image` block supports:

	* `image` -
	(Optional)
	Container image to use.

	* `java_jars` -
	(Optional)
	A list of Java JARS to add to the classpath. Valid input includes Cloud Storage URIs to Jar binaries. For example, gs://bucket-name/my/path/to/file.jar

	* `python_packages` -
	(Optional)
	A list of python packages to be installed. Valid formats include Cloud Storage URI to a PIP installable library. For example, gs://bucket-name/my/path/to/lib.tar.gz

	* `properties` -
	(Optional)
	Override to common configuration of open source components installed on the Dataproc cluster. The properties to set on daemon config files. Property keys are specified in prefix:property format, for example core:hadoop.tmp.dir. For more information, see Cluster properties.

	<a name="nested_vpc_network"></a>The `vpc_network` block supports:

	* `network_tags` -
	(Optional)
	List of network tags to apply to the job.

	* `network` -
	(Optional)
	The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.

	* `sub_network` -
	(Optional)
	The Cloud VPC sub-network in which the job is run.

	## Attributes Reference

	In addition to the arguments listed above, the following computed attributes are exported:

	* `id` - an identifier for the resource with format `projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}`

	* `name` -
	The relative resource name of the task, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/ tasks/{name}.

	* `uid` -
	System generated globally unique ID for the task. This ID will be different if the task is deleted and re-created with the same name.

	* `create_time` -
	The time when the task was created.

	* `update_time` -
	The time when the task was last updated.

	* `state` -
	Current state of the task.

	* `execution_status` -
	Configuration for the cluster
	Structure is [documented below](#nested_execution_status).

	* `terraform_labels` -
	The combination of labels configured directly on the resource
	and default labels configured on the provider.

	* `effective_labels` -
	All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Terraform, other clients and services.


	<a name="nested_execution_status"></a>The `execution_status` block contains:

	* `update_time` -
	(Output)
	Last update time of the status.

	* `latest_job` -
	(Output)
	latest job execution.
	Structure is [documented below](#nested_latest_job).


	<a name="nested_latest_job"></a>The `latest_job` block contains:

	* `name` -
	(Output)
	The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.

	* `uid` -
	(Output)
	System generated globally unique ID for the job.

	* `start_time` -
	(Output)
	The time when the job was started.

	* `end_time` -
	(Output)
	The time when the job ended.

	* `state` -
	(Output)
	Execution state for the job.

	* `retry_count` -
	(Output)
	The number of times the job has been retried (excluding the initial attempt).

	* `service` -
	(Output)
	The underlying service running a job.

	* `service_job` -
	(Output)
	The full resource name for the job run under a particular service.

	* `message` -
	(Output)
	Additional information about the current state.

	## Timeouts

	This resource provides the following
	[Timeouts](https://developer.hashicorp.com/terraform/plugin/sdkv2/resources/retries-and-customizable-timeouts) configuration options:

	- `create` - Default is 5 minutes.
	- `update` - Default is 5 minutes.
	- `delete` - Default is 5 minutes.

	## Import


	Task can be imported using any of these accepted formats:

	* `projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}`
	* `{{project}}/{{location}}/{{lake}}/{{task_id}}`
	* `{{location}}/{{lake}}/{{task_id}}`


	In Terraform v1.5.0 and later, use an [`import` block](https://developer.hashicorp.com/terraform/language/import) to import Task using one of the formats above. For example:

	```tf
	import {
	id = "projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}"
	to = google_dataplex_task.default
	}
	```

	When using the [`terraform import` command](https://developer.hashicorp.com/terraform/cli/commands/import), Task can be imported using one of the formats above. For example:

	```
	$ terraform import google_dataplex_task.default projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}
	$ terraform import google_dataplex_task.default {{project}}/{{location}}/{{lake}}/{{task_id}}
	$ terraform import google_dataplex_task.default {{location}}/{{lake}}/{{task_id}}
	```

	## User Project Overrides

	This resource supports [User Project Overrides](https://registry.terraform.io/providers/hashicorp/google/latest/docs/guides/provider_reference#user_project_override).