Docs Home
Google Cloud v8.21.0 published on Wednesday, Mar 5, 2025 by Pulumi
gcp.dataplex.Task
Explore with Pulumi AI
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
- How-to Guides
Example Usage
Dataplex Task Basic
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const project = gcp.organizations.getProject({});
const example = new gcp.dataplex.Lake("example", {
name: "tf-test-lake_72490",
location: "us-central1",
project: "my-project-name",
});
const exampleTask = new gcp.dataplex.Task("example", {
taskId: "tf-test-task_89605",
location: "us-central1",
lake: example.name,
description: "Test Task Basic",
displayName: "task-basic",
labels: {
count: "3",
},
triggerSpec: {
type: "RECURRING",
disabled: false,
maxRetries: 3,
startTime: "2023-10-02T15:01:23Z",
schedule: "1 * * * *",
},
executionSpec: {
serviceAccount: project.then(project => `${project.number}-compute@developer.gserviceaccount.com`),
project: "my-project-name",
maxJobExecutionLifetime: "100s",
kmsKey: "234jn2kjn42k3n423",
},
spark: {
pythonScriptFile: "gs://dataproc-examples/pyspark/hello-world/hello-world.py",
},
project: "my-project-name",
});
import pulumi
import pulumi_gcp as gcp
project = gcp.organizations.get_project()
example = gcp.dataplex.Lake("example",
name="tf-test-lake_72490",
location="us-central1",
project="my-project-name")
example_task = gcp.dataplex.Task("example",
task_id="tf-test-task_89605",
location="us-central1",
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": f"{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")
package main
import (
"fmt"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/dataplex"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
project, err := organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
if err != nil {
return err
}
example, err := dataplex.NewLake(ctx, "example", &dataplex.LakeArgs{
Name: pulumi.String("tf-test-lake_72490"),
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
_, err = dataplex.NewTask(ctx, "example", &dataplex.TaskArgs{
TaskId: pulumi.String("tf-test-task_89605"),
Location: pulumi.String("us-central1"),
Lake: example.Name,
Description: pulumi.String("Test Task Basic"),
DisplayName: pulumi.String("task-basic"),
Labels: pulumi.StringMap{
"count": pulumi.String("3"),
},
TriggerSpec: &dataplex.TaskTriggerSpecArgs{
Type: pulumi.String("RECURRING"),
Disabled: pulumi.Bool(false),
MaxRetries: pulumi.Int(3),
StartTime: pulumi.String("2023-10-02T15:01:23Z"),
Schedule: pulumi.String("1 * * * *"),
},
ExecutionSpec: &dataplex.TaskExecutionSpecArgs{
ServiceAccount: pulumi.Sprintf("%v-compute@developer.gserviceaccount.com", project.Number),
Project: pulumi.String("my-project-name"),
MaxJobExecutionLifetime: pulumi.String("100s"),
KmsKey: pulumi.String("234jn2kjn42k3n423"),
},
Spark: &dataplex.TaskSparkArgs{
PythonScriptFile: pulumi.String("gs://dataproc-examples/pyspark/hello-world/hello-world.py"),
},
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var project = Gcp.Organizations.GetProject.Invoke();
var example = new Gcp.DataPlex.Lake("example", new()
{
Name = "tf-test-lake_72490",
Location = "us-central1",
Project = "my-project-name",
});
var exampleTask = new Gcp.DataPlex.Task("example", new()
{
TaskId = "tf-test-task_89605",
Location = "us-central1",
Lake = example.Name,
Description = "Test Task Basic",
DisplayName = "task-basic",
Labels =
{
{ "count", "3" },
},
TriggerSpec = new Gcp.DataPlex.Inputs.TaskTriggerSpecArgs
{
Type = "RECURRING",
Disabled = false,
MaxRetries = 3,
StartTime = "2023-10-02T15:01:23Z",
Schedule = "1 * * * *",
},
ExecutionSpec = new Gcp.DataPlex.Inputs.TaskExecutionSpecArgs
{
ServiceAccount = $"{project.Apply(getProjectResult => getProjectResult.Number)}-compute@developer.gserviceaccount.com",
Project = "my-project-name",
MaxJobExecutionLifetime = "100s",
KmsKey = "234jn2kjn42k3n423",
},
Spark = new Gcp.DataPlex.Inputs.TaskSparkArgs
{
PythonScriptFile = "gs://dataproc-examples/pyspark/hello-world/hello-world.py",
},
Project = "my-project-name",
});
});
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.organizations.OrganizationsFunctions;
import com.pulumi.gcp.organizations.inputs.GetProjectArgs;
import com.pulumi.gcp.dataplex.Lake;
import com.pulumi.gcp.dataplex.LakeArgs;
import com.pulumi.gcp.dataplex.Task;
import com.pulumi.gcp.dataplex.TaskArgs;
import com.pulumi.gcp.dataplex.inputs.TaskTriggerSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
final var project = OrganizationsFunctions.getProject();
var example = new Lake("example", LakeArgs.builder()
.name("tf-test-lake_72490")
.location("us-central1")
.project("my-project-name")
.build());
var exampleTask = new Task("exampleTask", TaskArgs.builder()
.taskId("tf-test-task_89605")
.location("us-central1")
.lake(example.name())
.description("Test Task Basic")
.displayName("task-basic")
.labels(Map.of("count", "3"))
.triggerSpec(TaskTriggerSpecArgs.builder()
.type("RECURRING")
.disabled(false)
.maxRetries(3)
.startTime("2023-10-02T15:01:23Z")
.schedule("1 * * * *")
.build())
.executionSpec(TaskExecutionSpecArgs.builder()
.serviceAccount(String.format("%s-compute@developer.gserviceaccount.com", project.applyValue(getProjectResult -> getProjectResult.number())))
.project("my-project-name")
.maxJobExecutionLifetime("100s")
.kmsKey("234jn2kjn42k3n423")
.build())
.spark(TaskSparkArgs.builder()
.pythonScriptFile("gs://dataproc-examples/pyspark/hello-world/hello-world.py")
.build())
.project("my-project-name")
.build());
}
}
resources:
example:
type: gcp:dataplex:Lake
properties:
name: tf-test-lake_72490
location: us-central1
project: my-project-name
exampleTask:
type: gcp:dataplex:Task
name: example
properties:
taskId: tf-test-task_89605
location: us-central1
lake: ${example.name}
description: Test Task Basic
displayName: task-basic
labels:
count: '3'
triggerSpec:
type: RECURRING
disabled: false
maxRetries: 3
startTime: 2023-10-02T15:01:23Z
schedule: 1 * * * *
executionSpec:
serviceAccount: ${project.number}-compute@developer.gserviceaccount.com
project: my-project-name
maxJobExecutionLifetime: 100s
kmsKey: 234jn2kjn42k3n423
spark:
pythonScriptFile: gs://dataproc-examples/pyspark/hello-world/hello-world.py
project: my-project-name
variables:
project:
fn::invoke:
function: gcp:organizations:getProject
arguments: {}
Dataplex Task Spark
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
// VPC network
const _default = new gcp.compute.Network("default", {
name: "tf-test-workstation-cluster_56730",
autoCreateSubnetworks: true,
});
const project = gcp.organizations.getProject({});
const exampleSpark = new gcp.dataplex.Lake("example_spark", {
name: "tf-test-lake_95154",
location: "us-central1",
project: "my-project-name",
});
const exampleSparkTask = new gcp.dataplex.Task("example_spark", {
taskId: "tf-test-task_64336",
location: "us-central1",
lake: exampleSpark.name,
triggerSpec: {
type: "ON_DEMAND",
},
description: "task-spark-terraform",
executionSpec: {
serviceAccount: project.then(project => `${project.number}-compute@developer.gserviceaccount.com`),
args: {
TASK_ARGS: "--output_location,gs://spark-job/task-result, --output_format, json",
},
},
spark: {
infrastructureSpec: {
batch: {
executorsCount: 2,
maxExecutorsCount: 100,
},
containerImage: {
image: "test-image",
javaJars: ["test-java-jars.jar"],
pythonPackages: ["gs://bucket-name/my/path/to/lib.tar.gz"],
properties: {
name: "wrench",
mass: "1.3kg",
count: "3",
},
},
vpcNetwork: {
networkTags: ["test-network-tag"],
subNetwork: _default.id,
},
},
fileUris: ["gs://terrafrom-test/test.csv"],
archiveUris: ["gs://terraform-test/test.csv"],
sqlScript: "show databases",
},
project: "my-project-name",
});
import pulumi
import pulumi_gcp as gcp
# VPC network
default = gcp.compute.Network("default",
name="tf-test-workstation-cluster_56730",
auto_create_subnetworks=True)
project = gcp.organizations.get_project()
example_spark = gcp.dataplex.Lake("example_spark",
name="tf-test-lake_95154",
location="us-central1",
project="my-project-name")
example_spark_task = gcp.dataplex.Task("example_spark",
task_id="tf-test-task_64336",
location="us-central1",
lake=example_spark.name,
trigger_spec={
"type": "ON_DEMAND",
},
description="task-spark-terraform",
execution_spec={
"service_account": f"{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": default.id,
},
},
"file_uris": ["gs://terrafrom-test/test.csv"],
"archive_uris": ["gs://terraform-test/test.csv"],
"sql_script": "show databases",
},
project="my-project-name")
package main
import (
"fmt"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/compute"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/dataplex"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
// VPC network
_default, err := compute.NewNetwork(ctx, "default", &compute.NetworkArgs{
Name: pulumi.String("tf-test-workstation-cluster_56730"),
AutoCreateSubnetworks: pulumi.Bool(true),
})
if err != nil {
return err
}
project, err := organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
if err != nil {
return err
}
exampleSpark, err := dataplex.NewLake(ctx, "example_spark", &dataplex.LakeArgs{
Name: pulumi.String("tf-test-lake_95154"),
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
_, err = dataplex.NewTask(ctx, "example_spark", &dataplex.TaskArgs{
TaskId: pulumi.String("tf-test-task_64336"),
Location: pulumi.String("us-central1"),
Lake: exampleSpark.Name,
TriggerSpec: &dataplex.TaskTriggerSpecArgs{
Type: pulumi.String("ON_DEMAND"),
},
Description: pulumi.String("task-spark-terraform"),
ExecutionSpec: &dataplex.TaskExecutionSpecArgs{
ServiceAccount: pulumi.Sprintf("%v-compute@developer.gserviceaccount.com", project.Number),
Args: pulumi.StringMap{
"TASK_ARGS": pulumi.String("--output_location,gs://spark-job/task-result, --output_format, json"),
},
},
Spark: &dataplex.TaskSparkArgs{
InfrastructureSpec: &dataplex.TaskSparkInfrastructureSpecArgs{
Batch: &dataplex.TaskSparkInfrastructureSpecBatchArgs{
ExecutorsCount: pulumi.Int(2),
MaxExecutorsCount: pulumi.Int(100),
},
ContainerImage: &dataplex.TaskSparkInfrastructureSpecContainerImageArgs{
Image: pulumi.String("test-image"),
JavaJars: pulumi.StringArray{
pulumi.String("test-java-jars.jar"),
},
PythonPackages: pulumi.StringArray{
pulumi.String("gs://bucket-name/my/path/to/lib.tar.gz"),
},
Properties: pulumi.StringMap{
"name": pulumi.String("wrench"),
"mass": pulumi.String("1.3kg"),
"count": pulumi.String("3"),
},
},
VpcNetwork: &dataplex.TaskSparkInfrastructureSpecVpcNetworkArgs{
NetworkTags: pulumi.StringArray{
pulumi.String("test-network-tag"),
},
SubNetwork: _default.ID(),
},
},
FileUris: pulumi.StringArray{
pulumi.String("gs://terrafrom-test/test.csv"),
},
ArchiveUris: pulumi.StringArray{
pulumi.String("gs://terraform-test/test.csv"),
},
SqlScript: pulumi.String("show databases"),
},
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
// VPC network
var @default = new Gcp.Compute.Network("default", new()
{
Name = "tf-test-workstation-cluster_56730",
AutoCreateSubnetworks = true,
});
var project = Gcp.Organizations.GetProject.Invoke();
var exampleSpark = new Gcp.DataPlex.Lake("example_spark", new()
{
Name = "tf-test-lake_95154",
Location = "us-central1",
Project = "my-project-name",
});
var exampleSparkTask = new Gcp.DataPlex.Task("example_spark", new()
{
TaskId = "tf-test-task_64336",
Location = "us-central1",
Lake = exampleSpark.Name,
TriggerSpec = new Gcp.DataPlex.Inputs.TaskTriggerSpecArgs
{
Type = "ON_DEMAND",
},
Description = "task-spark-terraform",
ExecutionSpec = new Gcp.DataPlex.Inputs.TaskExecutionSpecArgs
{
ServiceAccount = $"{project.Apply(getProjectResult => getProjectResult.Number)}-compute@developer.gserviceaccount.com",
Args =
{
{ "TASK_ARGS", "--output_location,gs://spark-job/task-result, --output_format, json" },
},
},
Spark = new Gcp.DataPlex.Inputs.TaskSparkArgs
{
InfrastructureSpec = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecArgs
{
Batch = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecBatchArgs
{
ExecutorsCount = 2,
MaxExecutorsCount = 100,
},
ContainerImage = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecContainerImageArgs
{
Image = "test-image",
JavaJars = new[]
{
"test-java-jars.jar",
},
PythonPackages = new[]
{
"gs://bucket-name/my/path/to/lib.tar.gz",
},
Properties =
{
{ "name", "wrench" },
{ "mass", "1.3kg" },
{ "count", "3" },
},
},
VpcNetwork = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecVpcNetworkArgs
{
NetworkTags = new[]
{
"test-network-tag",
},
SubNetwork = @default.Id,
},
},
FileUris = new[]
{
"gs://terrafrom-test/test.csv",
},
ArchiveUris = new[]
{
"gs://terraform-test/test.csv",
},
SqlScript = "show databases",
},
Project = "my-project-name",
});
});
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.compute.Network;
import com.pulumi.gcp.compute.NetworkArgs;
import com.pulumi.gcp.organizations.OrganizationsFunctions;
import com.pulumi.gcp.organizations.inputs.GetProjectArgs;
import com.pulumi.gcp.dataplex.Lake;
import com.pulumi.gcp.dataplex.LakeArgs;
import com.pulumi.gcp.dataplex.Task;
import com.pulumi.gcp.dataplex.TaskArgs;
import com.pulumi.gcp.dataplex.inputs.TaskTriggerSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkInfrastructureSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkInfrastructureSpecBatchArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkInfrastructureSpecContainerImageArgs;
import com.pulumi.gcp.dataplex.inputs.TaskSparkInfrastructureSpecVpcNetworkArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
// VPC network
var default_ = new Network("default", NetworkArgs.builder()
.name("tf-test-workstation-cluster_56730")
.autoCreateSubnetworks(true)
.build());
final var project = OrganizationsFunctions.getProject();
var exampleSpark = new Lake("exampleSpark", LakeArgs.builder()
.name("tf-test-lake_95154")
.location("us-central1")
.project("my-project-name")
.build());
var exampleSparkTask = new Task("exampleSparkTask", TaskArgs.builder()
.taskId("tf-test-task_64336")
.location("us-central1")
.lake(exampleSpark.name())
.triggerSpec(TaskTriggerSpecArgs.builder()
.type("ON_DEMAND")
.build())
.description("task-spark-terraform")
.executionSpec(TaskExecutionSpecArgs.builder()
.serviceAccount(String.format("%s-compute@developer.gserviceaccount.com", project.applyValue(getProjectResult -> getProjectResult.number())))
.args(Map.of("TASK_ARGS", "--output_location,gs://spark-job/task-result, --output_format, json"))
.build())
.spark(TaskSparkArgs.builder()
.infrastructureSpec(TaskSparkInfrastructureSpecArgs.builder()
.batch(TaskSparkInfrastructureSpecBatchArgs.builder()
.executorsCount(2)
.maxExecutorsCount(100)
.build())
.containerImage(TaskSparkInfrastructureSpecContainerImageArgs.builder()
.image("test-image")
.javaJars("test-java-jars.jar")
.pythonPackages("gs://bucket-name/my/path/to/lib.tar.gz")
.properties(Map.ofEntries(
Map.entry("name", "wrench"),
Map.entry("mass", "1.3kg"),
Map.entry("count", "3")
))
.build())
.vpcNetwork(TaskSparkInfrastructureSpecVpcNetworkArgs.builder()
.networkTags("test-network-tag")
.subNetwork(default_.id())
.build())
.build())
.fileUris("gs://terrafrom-test/test.csv")
.archiveUris("gs://terraform-test/test.csv")
.sqlScript("show databases")
.build())
.project("my-project-name")
.build());
}
}
resources:
# VPC network
default:
type: gcp:compute:Network
properties:
name: tf-test-workstation-cluster_56730
autoCreateSubnetworks: true
exampleSpark:
type: gcp:dataplex:Lake
name: example_spark
properties:
name: tf-test-lake_95154
location: us-central1
project: my-project-name
exampleSparkTask:
type: gcp:dataplex:Task
name: example_spark
properties:
taskId: tf-test-task_64336
location: us-central1
lake: ${exampleSpark.name}
triggerSpec:
type: ON_DEMAND
description: task-spark-terraform
executionSpec:
serviceAccount: ${project.number}-compute@developer.gserviceaccount.com
args:
TASK_ARGS: --output_location,gs://spark-job/task-result, --output_format, json
spark:
infrastructureSpec:
batch:
executorsCount: 2
maxExecutorsCount: 100
containerImage:
image: test-image
javaJars:
- test-java-jars.jar
pythonPackages:
- gs://bucket-name/my/path/to/lib.tar.gz
properties:
name: wrench
mass: 1.3kg
count: '3'
vpcNetwork:
networkTags:
- test-network-tag
subNetwork: ${default.id}
fileUris:
- gs://terrafrom-test/test.csv
archiveUris:
- gs://terraform-test/test.csv
sqlScript: show databases
project: my-project-name
variables:
project:
fn::invoke:
function: gcp:organizations:getProject
arguments: {}
Dataplex Task Notebook
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
// VPC network
const _default = new gcp.compute.Network("default", {
name: "tf-test-workstation-cluster_34962",
autoCreateSubnetworks: true,
});
const project = gcp.organizations.getProject({});
const exampleNotebook = new gcp.dataplex.Lake("example_notebook", {
name: "tf-test-lake_74000",
location: "us-central1",
project: "my-project-name",
});
const exampleNotebookTask = new gcp.dataplex.Task("example_notebook", {
taskId: "tf-test-task_75125",
location: "us-central1",
lake: exampleNotebook.name,
triggerSpec: {
type: "RECURRING",
schedule: "1 * * * *",
},
executionSpec: {
serviceAccount: project.then(project => `${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",
infrastructureSpec: {
batch: {
executorsCount: 2,
maxExecutorsCount: 100,
},
containerImage: {
image: "test-image",
javaJars: ["test-java-jars.jar"],
pythonPackages: ["gs://bucket-name/my/path/to/lib.tar.gz"],
properties: {
name: "wrench",
mass: "1.3kg",
count: "3",
},
},
vpcNetwork: {
networkTags: ["test-network-tag"],
network: _default.id,
},
},
fileUris: ["gs://terraform-test/test.csv"],
archiveUris: ["gs://terraform-test/test.csv"],
},
project: "my-project-name",
});
import pulumi
import pulumi_gcp as gcp
# VPC network
default = gcp.compute.Network("default",
name="tf-test-workstation-cluster_34962",
auto_create_subnetworks=True)
project = gcp.organizations.get_project()
example_notebook = gcp.dataplex.Lake("example_notebook",
name="tf-test-lake_74000",
location="us-central1",
project="my-project-name")
example_notebook_task = gcp.dataplex.Task("example_notebook",
task_id="tf-test-task_75125",
location="us-central1",
lake=example_notebook.name,
trigger_spec={
"type": "RECURRING",
"schedule": "1 * * * *",
},
execution_spec={
"service_account": f"{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": default.id,
},
},
"file_uris": ["gs://terraform-test/test.csv"],
"archive_uris": ["gs://terraform-test/test.csv"],
},
project="my-project-name")
package main
import (
"fmt"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/compute"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/dataplex"
"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
// VPC network
_default, err := compute.NewNetwork(ctx, "default", &compute.NetworkArgs{
Name: pulumi.String("tf-test-workstation-cluster_34962"),
AutoCreateSubnetworks: pulumi.Bool(true),
})
if err != nil {
return err
}
project, err := organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
if err != nil {
return err
}
exampleNotebook, err := dataplex.NewLake(ctx, "example_notebook", &dataplex.LakeArgs{
Name: pulumi.String("tf-test-lake_74000"),
Location: pulumi.String("us-central1"),
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
_, err = dataplex.NewTask(ctx, "example_notebook", &dataplex.TaskArgs{
TaskId: pulumi.String("tf-test-task_75125"),
Location: pulumi.String("us-central1"),
Lake: exampleNotebook.Name,
TriggerSpec: &dataplex.TaskTriggerSpecArgs{
Type: pulumi.String("RECURRING"),
Schedule: pulumi.String("1 * * * *"),
},
ExecutionSpec: &dataplex.TaskExecutionSpecArgs{
ServiceAccount: pulumi.Sprintf("%v-compute@developer.gserviceaccount.com", project.Number),
Args: pulumi.StringMap{
"TASK_ARGS": pulumi.String("--output_location,gs://spark-job-jars-anrajitha/task-result, --output_format, json"),
},
},
Notebook: &dataplex.TaskNotebookArgs{
Notebook: pulumi.String("gs://terraform-test/test-notebook.ipynb"),
InfrastructureSpec: &dataplex.TaskNotebookInfrastructureSpecArgs{
Batch: &dataplex.TaskNotebookInfrastructureSpecBatchArgs{
ExecutorsCount: pulumi.Int(2),
MaxExecutorsCount: pulumi.Int(100),
},
ContainerImage: &dataplex.TaskNotebookInfrastructureSpecContainerImageArgs{
Image: pulumi.String("test-image"),
JavaJars: pulumi.StringArray{
pulumi.String("test-java-jars.jar"),
},
PythonPackages: pulumi.StringArray{
pulumi.String("gs://bucket-name/my/path/to/lib.tar.gz"),
},
Properties: pulumi.StringMap{
"name": pulumi.String("wrench"),
"mass": pulumi.String("1.3kg"),
"count": pulumi.String("3"),
},
},
VpcNetwork: &dataplex.TaskNotebookInfrastructureSpecVpcNetworkArgs{
NetworkTags: pulumi.StringArray{
pulumi.String("test-network-tag"),
},
Network: _default.ID(),
},
},
FileUris: pulumi.StringArray{
pulumi.String("gs://terraform-test/test.csv"),
},
ArchiveUris: pulumi.StringArray{
pulumi.String("gs://terraform-test/test.csv"),
},
},
Project: pulumi.String("my-project-name"),
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
// VPC network
var @default = new Gcp.Compute.Network("default", new()
{
Name = "tf-test-workstation-cluster_34962",
AutoCreateSubnetworks = true,
});
var project = Gcp.Organizations.GetProject.Invoke();
var exampleNotebook = new Gcp.DataPlex.Lake("example_notebook", new()
{
Name = "tf-test-lake_74000",
Location = "us-central1",
Project = "my-project-name",
});
var exampleNotebookTask = new Gcp.DataPlex.Task("example_notebook", new()
{
TaskId = "tf-test-task_75125",
Location = "us-central1",
Lake = exampleNotebook.Name,
TriggerSpec = new Gcp.DataPlex.Inputs.TaskTriggerSpecArgs
{
Type = "RECURRING",
Schedule = "1 * * * *",
},
ExecutionSpec = new Gcp.DataPlex.Inputs.TaskExecutionSpecArgs
{
ServiceAccount = $"{project.Apply(getProjectResult => getProjectResult.Number)}-compute@developer.gserviceaccount.com",
Args =
{
{ "TASK_ARGS", "--output_location,gs://spark-job-jars-anrajitha/task-result, --output_format, json" },
},
},
Notebook = new Gcp.DataPlex.Inputs.TaskNotebookArgs
{
Notebook = "gs://terraform-test/test-notebook.ipynb",
InfrastructureSpec = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecArgs
{
Batch = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecBatchArgs
{
ExecutorsCount = 2,
MaxExecutorsCount = 100,
},
ContainerImage = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecContainerImageArgs
{
Image = "test-image",
JavaJars = new[]
{
"test-java-jars.jar",
},
PythonPackages = new[]
{
"gs://bucket-name/my/path/to/lib.tar.gz",
},
Properties =
{
{ "name", "wrench" },
{ "mass", "1.3kg" },
{ "count", "3" },
},
},
VpcNetwork = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecVpcNetworkArgs
{
NetworkTags = new[]
{
"test-network-tag",
},
Network = @default.Id,
},
},
FileUris = new[]
{
"gs://terraform-test/test.csv",
},
ArchiveUris = new[]
{
"gs://terraform-test/test.csv",
},
},
Project = "my-project-name",
});
});
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.compute.Network;
import com.pulumi.gcp.compute.NetworkArgs;
import com.pulumi.gcp.organizations.OrganizationsFunctions;
import com.pulumi.gcp.organizations.inputs.GetProjectArgs;
import com.pulumi.gcp.dataplex.Lake;
import com.pulumi.gcp.dataplex.LakeArgs;
import com.pulumi.gcp.dataplex.Task;
import com.pulumi.gcp.dataplex.TaskArgs;
import com.pulumi.gcp.dataplex.inputs.TaskTriggerSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskExecutionSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskNotebookArgs;
import com.pulumi.gcp.dataplex.inputs.TaskNotebookInfrastructureSpecArgs;
import com.pulumi.gcp.dataplex.inputs.TaskNotebookInfrastructureSpecBatchArgs;
import com.pulumi.gcp.dataplex.inputs.TaskNotebookInfrastructureSpecContainerImageArgs;
import com.pulumi.gcp.dataplex.inputs.TaskNotebookInfrastructureSpecVpcNetworkArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
// VPC network
var default_ = new Network("default", NetworkArgs.builder()
.name("tf-test-workstation-cluster_34962")
.autoCreateSubnetworks(true)
.build());
final var project = OrganizationsFunctions.getProject();
var exampleNotebook = new Lake("exampleNotebook", LakeArgs.builder()
.name("tf-test-lake_74000")
.location("us-central1")
.project("my-project-name")
.build());
var exampleNotebookTask = new Task("exampleNotebookTask", TaskArgs.builder()
.taskId("tf-test-task_75125")
.location("us-central1")
.lake(exampleNotebook.name())
.triggerSpec(TaskTriggerSpecArgs.builder()
.type("RECURRING")
.schedule("1 * * * *")
.build())
.executionSpec(TaskExecutionSpecArgs.builder()
.serviceAccount(String.format("%s-compute@developer.gserviceaccount.com", project.applyValue(getProjectResult -> getProjectResult.number())))
.args(Map.of("TASK_ARGS", "--output_location,gs://spark-job-jars-anrajitha/task-result, --output_format, json"))
.build())
.notebook(TaskNotebookArgs.builder()
.notebook("gs://terraform-test/test-notebook.ipynb")
.infrastructureSpec(TaskNotebookInfrastructureSpecArgs.builder()
.batch(TaskNotebookInfrastructureSpecBatchArgs.builder()
.executorsCount(2)
.maxExecutorsCount(100)
.build())
.containerImage(TaskNotebookInfrastructureSpecContainerImageArgs.builder()
.image("test-image")
.javaJars("test-java-jars.jar")
.pythonPackages("gs://bucket-name/my/path/to/lib.tar.gz")
.properties(Map.ofEntries(
Map.entry("name", "wrench"),
Map.entry("mass", "1.3kg"),
Map.entry("count", "3")
))
.build())
.vpcNetwork(TaskNotebookInfrastructureSpecVpcNetworkArgs.builder()
.networkTags("test-network-tag")
.network(default_.id())
.build())
.build())
.fileUris("gs://terraform-test/test.csv")
.archiveUris("gs://terraform-test/test.csv")
.build())
.project("my-project-name")
.build());
}
}
resources:
# VPC network
default:
type: gcp:compute:Network
properties:
name: tf-test-workstation-cluster_34962
autoCreateSubnetworks: true
exampleNotebook:
type: gcp:dataplex:Lake
name: example_notebook
properties:
name: tf-test-lake_74000
location: us-central1
project: my-project-name
exampleNotebookTask:
type: gcp:dataplex:Task
name: example_notebook
properties:
taskId: tf-test-task_75125
location: us-central1
lake: ${exampleNotebook.name}
triggerSpec:
type: RECURRING
schedule: 1 * * * *
executionSpec:
serviceAccount: ${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
infrastructureSpec:
batch:
executorsCount: 2
maxExecutorsCount: 100
containerImage:
image: test-image
javaJars:
- test-java-jars.jar
pythonPackages:
- gs://bucket-name/my/path/to/lib.tar.gz
properties:
name: wrench
mass: 1.3kg
count: '3'
vpcNetwork:
networkTags:
- test-network-tag
network: ${default.id}
fileUris:
- gs://terraform-test/test.csv
archiveUris:
- gs://terraform-test/test.csv
project: my-project-name
variables:
project:
fn::invoke:
function: gcp:organizations:getProject
arguments: {}
Create Task Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new Task(name: string, args: TaskArgs, opts?: CustomResourceOptions);@overload
def Task(resource_name: str,
args: TaskArgs,
opts: Optional[ResourceOptions] = None)
@overload
def Task(resource_name: str,
opts: Optional[ResourceOptions] = None,
execution_spec: Optional[TaskExecutionSpecArgs] = None,
trigger_spec: Optional[TaskTriggerSpecArgs] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
labels: Optional[Mapping[str, str]] = None,
lake: Optional[str] = None,
location: Optional[str] = None,
notebook: Optional[TaskNotebookArgs] = None,
project: Optional[str] = None,
spark: Optional[TaskSparkArgs] = None,
task_id: Optional[str] = None)func NewTask(ctx *Context, name string, args TaskArgs, opts ...ResourceOption) (*Task, error)public Task(string name, TaskArgs args, CustomResourceOptions? opts = null)type: gcp:dataplex:Task
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
Parameters
- name string
- The unique name of the resource.
- args TaskArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args TaskArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args TaskArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args TaskArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args TaskArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Constructor example
The following reference example uses placeholder values for all input properties.
var taskResource = new Gcp.DataPlex.Task("taskResource", new()
{
ExecutionSpec = new Gcp.DataPlex.Inputs.TaskExecutionSpecArgs
{
ServiceAccount = "string",
Args =
{
{ "string", "string" },
},
KmsKey = "string",
MaxJobExecutionLifetime = "string",
Project = "string",
},
TriggerSpec = new Gcp.DataPlex.Inputs.TaskTriggerSpecArgs
{
Type = "string",
Disabled = false,
MaxRetries = 0,
Schedule = "string",
StartTime = "string",
},
Description = "string",
DisplayName = "string",
Labels =
{
{ "string", "string" },
},
Lake = "string",
Location = "string",
Notebook = new Gcp.DataPlex.Inputs.TaskNotebookArgs
{
Notebook = "string",
ArchiveUris = new[]
{
"string",
},
FileUris = new[]
{
"string",
},
InfrastructureSpec = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecArgs
{
Batch = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecBatchArgs
{
ExecutorsCount = 0,
MaxExecutorsCount = 0,
},
ContainerImage = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecContainerImageArgs
{
Image = "string",
JavaJars = new[]
{
"string",
},
Properties =
{
{ "string", "string" },
},
PythonPackages = new[]
{
"string",
},
},
VpcNetwork = new Gcp.DataPlex.Inputs.TaskNotebookInfrastructureSpecVpcNetworkArgs
{
Network = "string",
NetworkTags = new[]
{
"string",
},
SubNetwork = "string",
},
},
},
Project = "string",
Spark = new Gcp.DataPlex.Inputs.TaskSparkArgs
{
ArchiveUris = new[]
{
"string",
},
FileUris = new[]
{
"string",
},
InfrastructureSpec = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecArgs
{
Batch = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecBatchArgs
{
ExecutorsCount = 0,
MaxExecutorsCount = 0,
},
ContainerImage = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecContainerImageArgs
{
Image = "string",
JavaJars = new[]
{
"string",
},
Properties =
{
{ "string", "string" },
},
PythonPackages = new[]
{
"string",
},
},
VpcNetwork = new Gcp.DataPlex.Inputs.TaskSparkInfrastructureSpecVpcNetworkArgs
{
Network = "string",
NetworkTags = new[]
{
"string",
},
SubNetwork = "string",
},
},
MainClass = "string",
MainJarFileUri = "string",
PythonScriptFile = "string",
SqlScript = "string",
SqlScriptFile = "string",
},
TaskId = "string",
});
example, err := dataplex.NewTask(ctx, "taskResource", &dataplex.TaskArgs{
ExecutionSpec: &dataplex.TaskExecutionSpecArgs{
ServiceAccount: pulumi.String("string"),
Args: pulumi.StringMap{
"string": pulumi.String("string"),
},
KmsKey: pulumi.String("string"),
MaxJobExecutionLifetime: pulumi.String("string"),
Project: pulumi.String("string"),
},
TriggerSpec: &dataplex.TaskTriggerSpecArgs{
Type: pulumi.String("string"),
Disabled: pulumi.Bool(false),
MaxRetries: pulumi.Int(0),
Schedule: pulumi.String("string"),
StartTime: pulumi.String("string"),
},
Description: pulumi.String("string"),
DisplayName: pulumi.String("string"),
Labels: pulumi.StringMap{
"string": pulumi.String("string"),
},
Lake: pulumi.String("string"),
Location: pulumi.String("string"),
Notebook: &dataplex.TaskNotebookArgs{
Notebook: pulumi.String("string"),
ArchiveUris: pulumi.StringArray{
pulumi.String("string"),
},
FileUris: pulumi.StringArray{
pulumi.String("string"),
},
InfrastructureSpec: &dataplex.TaskNotebookInfrastructureSpecArgs{
Batch: &dataplex.TaskNotebookInfrastructureSpecBatchArgs{
ExecutorsCount: pulumi.Int(0),
MaxExecutorsCount: pulumi.Int(0),
},
ContainerImage: &dataplex.TaskNotebookInfrastructureSpecContainerImageArgs{
Image: pulumi.String("string"),
JavaJars: pulumi.StringArray{
pulumi.String("string"),
},
Properties: pulumi.StringMap{
"string": pulumi.String("string"),
},
PythonPackages: pulumi.StringArray{
pulumi.String("string"),
},
},
VpcNetwork: &dataplex.TaskNotebookInfrastructureSpecVpcNetworkArgs{
Network: pulumi.String("string"),
NetworkTags: pulumi.StringArray{
pulumi.String("string"),
},
SubNetwork: pulumi.String("string"),
},
},
},
Project: pulumi.String("string"),
Spark: &dataplex.TaskSparkArgs{
ArchiveUris: pulumi.StringArray{
pulumi.String("string"),
},
FileUris: pulumi.StringArray{
pulumi.String("string"),
},
InfrastructureSpec: &dataplex.TaskSparkInfrastructureSpecArgs{
Batch: &dataplex.TaskSparkInfrastructureSpecBatchArgs{
ExecutorsCount: pulumi.Int(0),
MaxExecutorsCount: pulumi.Int(0),
},
ContainerImage: &dataplex.TaskSparkInfrastructureSpecContainerImageArgs{
Image: pulumi.String("string"),
JavaJars: pulumi.StringArray{
pulumi.String("string"),
},
Properties: pulumi.StringMap{
"string": pulumi.String("string"),
},
PythonPackages: pulumi.StringArray{
pulumi.String("string"),
},
},
VpcNetwork: &dataplex.TaskSparkInfrastructureSpecVpcNetworkArgs{
Network: pulumi.String("string"),
NetworkTags: pulumi.StringArray{
pulumi.String("string"),
},
SubNetwork: pulumi.String("string"),
},
},
MainClass: pulumi.String("string"),
MainJarFileUri: pulumi.String("string"),
PythonScriptFile: pulumi.String("string"),
SqlScript: pulumi.String("string"),
SqlScriptFile: pulumi.String("string"),
},
TaskId: pulumi.String("string"),
})
var taskResource = new Task("taskResource", TaskArgs.builder()
.executionSpec(TaskExecutionSpecArgs.builder()
.serviceAccount("string")
.args(Map.of("string", "string"))
.kmsKey("string")
.maxJobExecutionLifetime("string")
.project("string")
.build())
.triggerSpec(TaskTriggerSpecArgs.builder()
.type("string")
.disabled(false)
.maxRetries(0)
.schedule("string")
.startTime("string")
.build())
.description("string")
.displayName("string")
.labels(Map.of("string", "string"))
.lake("string")
.location("string")
.notebook(TaskNotebookArgs.builder()
.notebook("string")
.archiveUris("string")
.fileUris("string")
.infrastructureSpec(TaskNotebookInfrastructureSpecArgs.builder()
.batch(TaskNotebookInfrastructureSpecBatchArgs.builder()
.executorsCount(0)
.maxExecutorsCount(0)
.build())
.containerImage(TaskNotebookInfrastructureSpecContainerImageArgs.builder()
.image("string")
.javaJars("string")
.properties(Map.of("string", "string"))
.pythonPackages("string")
.build())
.vpcNetwork(TaskNotebookInfrastructureSpecVpcNetworkArgs.builder()
.network("string")
.networkTags("string")
.subNetwork("string")
.build())
.build())
.build())
.project("string")
.spark(TaskSparkArgs.builder()
.archiveUris("string")
.fileUris("string")
.infrastructureSpec(TaskSparkInfrastructureSpecArgs.builder()
.batch(TaskSparkInfrastructureSpecBatchArgs.builder()
.executorsCount(0)
.maxExecutorsCount(0)
.build())
.containerImage(TaskSparkInfrastructureSpecContainerImageArgs.builder()
.image("string")
.javaJars("string")
.properties(Map.of("string", "string"))
.pythonPackages("string")
.build())
.vpcNetwork(TaskSparkInfrastructureSpecVpcNetworkArgs.builder()
.network("string")
.networkTags("string")
.subNetwork("string")
.build())
.build())
.mainClass("string")
.mainJarFileUri("string")
.pythonScriptFile("string")
.sqlScript("string")
.sqlScriptFile("string")
.build())
.taskId("string")
.build());
task_resource = gcp.dataplex.Task("taskResource",
execution_spec={
"service_account": "string",
"args": {
"string": "string",
},
"kms_key": "string",
"max_job_execution_lifetime": "string",
"project": "string",
},
trigger_spec={
"type": "string",
"disabled": False,
"max_retries": 0,
"schedule": "string",
"start_time": "string",
},
description="string",
display_name="string",
labels={
"string": "string",
},
lake="string",
location="string",
notebook={
"notebook": "string",
"archive_uris": ["string"],
"file_uris": ["string"],
"infrastructure_spec": {
"batch": {
"executors_count": 0,
"max_executors_count": 0,
},
"container_image": {
"image": "string",
"java_jars": ["string"],
"properties": {
"string": "string",
},
"python_packages": ["string"],
},
"vpc_network": {
"network": "string",
"network_tags": ["string"],
"sub_network": "string",
},
},
},
project="string",
spark={
"archive_uris": ["string"],
"file_uris": ["string"],
"infrastructure_spec": {
"batch": {
"executors_count": 0,
"max_executors_count": 0,
},
"container_image": {
"image": "string",
"java_jars": ["string"],
"properties": {
"string": "string",
},
"python_packages": ["string"],
},
"vpc_network": {
"network": "string",
"network_tags": ["string"],
"sub_network": "string",
},
},
"main_class": "string",
"main_jar_file_uri": "string",
"python_script_file": "string",
"sql_script": "string",
"sql_script_file": "string",
},
task_id="string")
const taskResource = new gcp.dataplex.Task("taskResource", {
executionSpec: {
serviceAccount: "string",
args: {
string: "string",
},
kmsKey: "string",
maxJobExecutionLifetime: "string",
project: "string",
},
triggerSpec: {
type: "string",
disabled: false,
maxRetries: 0,
schedule: "string",
startTime: "string",
},
description: "string",
displayName: "string",
labels: {
string: "string",
},
lake: "string",
location: "string",
notebook: {
notebook: "string",
archiveUris: ["string"],
fileUris: ["string"],
infrastructureSpec: {
batch: {
executorsCount: 0,
maxExecutorsCount: 0,
},
containerImage: {
image: "string",
javaJars: ["string"],
properties: {
string: "string",
},
pythonPackages: ["string"],
},
vpcNetwork: {
network: "string",
networkTags: ["string"],
subNetwork: "string",
},
},
},
project: "string",
spark: {
archiveUris: ["string"],
fileUris: ["string"],
infrastructureSpec: {
batch: {
executorsCount: 0,
maxExecutorsCount: 0,
},
containerImage: {
image: "string",
javaJars: ["string"],
properties: {
string: "string",
},
pythonPackages: ["string"],
},
vpcNetwork: {
network: "string",
networkTags: ["string"],
subNetwork: "string",
},
},
mainClass: "string",
mainJarFileUri: "string",
pythonScriptFile: "string",
sqlScript: "string",
sqlScriptFile: "string",
},
taskId: "string",
});
type: gcp:dataplex:Task
properties:
description: string
displayName: string
executionSpec:
args:
string: string
kmsKey: string
maxJobExecutionLifetime: string
project: string
serviceAccount: string
labels:
string: string
lake: string
location: string
notebook:
archiveUris:
- string
fileUris:
- string
infrastructureSpec:
batch:
executorsCount: 0
maxExecutorsCount: 0
containerImage:
image: string
javaJars:
- string
properties:
string: string
pythonPackages:
- string
vpcNetwork:
network: string
networkTags:
- string
subNetwork: string
notebook: string
project: string
spark:
archiveUris:
- string
fileUris:
- string
infrastructureSpec:
batch:
executorsCount: 0
maxExecutorsCount: 0
containerImage:
image: string
javaJars:
- string
properties:
string: string
pythonPackages:
- string
vpcNetwork:
network: string
networkTags:
- string
subNetwork: string
mainClass: string
mainJarFileUri: string
pythonScriptFile: string
sqlScript: string
sqlScriptFile: string
taskId: string
triggerSpec:
disabled: false
maxRetries: 0
schedule: string
startTime: string
type: string
Task Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.
The Task resource accepts the following input properties:
- Execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- Trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- Description string
- User-provided description of the task.
- Display
Name string - User friendly display name.
- Labels Dictionary<string, string>
- 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.
- Lake string
- The lake in which the task will be created in.
- Location string
- The location in which the task will be created in.
- Notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Project string
- Spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Task
Id string - The task Id of the task.
- Execution
Spec TaskExecution Spec Args - Configuration for the cluster Structure is documented below.
- Trigger
Spec TaskTrigger Spec Args - Configuration for the cluster Structure is documented below.
- Description string
- User-provided description of the task.
- Display
Name string - User friendly display name.
- Labels map[string]string
- 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.
- Lake string
- The lake in which the task will be created in.
- Location string
- The location in which the task will be created in.
- Notebook
Task
Notebook Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Project string
- Spark
Task
Spark Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Task
Id string - The task Id of the task.
- execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- description String
- User-provided description of the task.
- display
Name String - User friendly display name.
- labels Map<String,String>
- 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.
- lake String
- The lake in which the task will be created in.
- location String
- The location in which the task will be created in.
- notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project String
- spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- task
Id String - The task Id of the task.
- execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- description string
- User-provided description of the task.
- display
Name string - User friendly display name.
- labels {[key: string]: string}
- 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.
- lake string
- The lake in which the task will be created in.
- location string
- The location in which the task will be created in.
- notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project string
- spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- task
Id string - The task Id of the task.
- execution_
spec TaskExecution Spec Args - Configuration for the cluster Structure is documented below.
- trigger_
spec TaskTrigger Spec Args - Configuration for the cluster Structure is documented below.
- description str
- User-provided description of the task.
- display_
name str - User friendly display name.
- labels Mapping[str, str]
- 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.
- lake str
- The lake in which the task will be created in.
- location str
- The location in which the task will be created in.
- notebook
Task
Notebook Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project str
- spark
Task
Spark Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- task_
id str - The task Id of the task.
- execution
Spec Property Map - Configuration for the cluster Structure is documented below.
- trigger
Spec Property Map - Configuration for the cluster Structure is documented below.
- description String
- User-provided description of the task.
- display
Name String - User friendly display name.
- labels Map<String>
- 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.
- lake String
- The lake in which the task will be created in.
- location String
- The location in which the task will be created in.
- notebook Property Map
- A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project String
- spark Property Map
- A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- task
Id String - The task Id of the task.
Outputs
All input properties are implicitly available as output properties. Additionally, the Task resource produces the following output properties:
- Create
Time string - The time when the task was created.
- Effective
Labels Dictionary<string, string> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- Execution
Statuses List<TaskExecution Status> - Configuration for the cluster Structure is documented below.
- Id string
- The provider-assigned unique ID for this managed resource.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Pulumi
Labels Dictionary<string, string> - The combination of labels configured directly on the resource and default labels configured on the provider.
- State string
- (Output) Execution state for the job.
- Uid string
- (Output) System generated globally unique ID for the job.
- Update
Time string - (Output) Last update time of the status.
- Create
Time string - The time when the task was created.
- Effective
Labels map[string]string - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- Execution
Statuses []TaskExecution Status - Configuration for the cluster Structure is documented below.
- Id string
- The provider-assigned unique ID for this managed resource.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Pulumi
Labels map[string]string - The combination of labels configured directly on the resource and default labels configured on the provider.
- State string
- (Output) Execution state for the job.
- Uid string
- (Output) System generated globally unique ID for the job.
- Update
Time string - (Output) Last update time of the status.
- create
Time String - The time when the task was created.
- effective
Labels Map<String,String> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Statuses List<TaskExecution Status> - Configuration for the cluster Structure is documented below.
- id String
- The provider-assigned unique ID for this managed resource.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- pulumi
Labels Map<String,String> - The combination of labels configured directly on the resource and default labels configured on the provider.
- state String
- (Output) Execution state for the job.
- uid String
- (Output) System generated globally unique ID for the job.
- update
Time String - (Output) Last update time of the status.
- create
Time string - The time when the task was created.
- effective
Labels {[key: string]: string} - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Statuses TaskExecution Status[] - Configuration for the cluster Structure is documented below.
- id string
- The provider-assigned unique ID for this managed resource.
- name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- pulumi
Labels {[key: string]: string} - The combination of labels configured directly on the resource and default labels configured on the provider.
- state string
- (Output) Execution state for the job.
- uid string
- (Output) System generated globally unique ID for the job.
- update
Time string - (Output) Last update time of the status.
- create_
time str - The time when the task was created.
- effective_
labels Mapping[str, str] - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution_
statuses Sequence[TaskExecution Status] - Configuration for the cluster Structure is documented below.
- id str
- The provider-assigned unique ID for this managed resource.
- name str
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- pulumi_
labels Mapping[str, str] - The combination of labels configured directly on the resource and default labels configured on the provider.
- state str
- (Output) Execution state for the job.
- uid str
- (Output) System generated globally unique ID for the job.
- update_
time str - (Output) Last update time of the status.
- create
Time String - The time when the task was created.
- effective
Labels Map<String> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Statuses List<Property Map> - Configuration for the cluster Structure is documented below.
- id String
- The provider-assigned unique ID for this managed resource.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- pulumi
Labels Map<String> - The combination of labels configured directly on the resource and default labels configured on the provider.
- state String
- (Output) Execution state for the job.
- uid String
- (Output) System generated globally unique ID for the job.
- update
Time String - (Output) Last update time of the status.
Look up Existing Task Resource
Get an existing Task resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, state?: TaskState, opts?: CustomResourceOptions): Task@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None,
create_time: Optional[str] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
effective_labels: Optional[Mapping[str, str]] = None,
execution_spec: Optional[TaskExecutionSpecArgs] = None,
execution_statuses: Optional[Sequence[TaskExecutionStatusArgs]] = None,
labels: Optional[Mapping[str, str]] = None,
lake: Optional[str] = None,
location: Optional[str] = None,
name: Optional[str] = None,
notebook: Optional[TaskNotebookArgs] = None,
project: Optional[str] = None,
pulumi_labels: Optional[Mapping[str, str]] = None,
spark: Optional[TaskSparkArgs] = None,
state: Optional[str] = None,
task_id: Optional[str] = None,
trigger_spec: Optional[TaskTriggerSpecArgs] = None,
uid: Optional[str] = None,
update_time: Optional[str] = None) -> Taskfunc GetTask(ctx *Context, name string, id IDInput, state *TaskState, opts ...ResourceOption) (*Task, error)public static Task Get(string name, Input<string> id, TaskState? state, CustomResourceOptions? opts = null)public static Task get(String name, Output<String> id, TaskState state, CustomResourceOptions options)resources: _: type: gcp:dataplex:Task get: id: ${id}- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- resource_name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- Create
Time string - The time when the task was created.
- Description string
- User-provided description of the task.
- Display
Name string - User friendly display name.
- Effective
Labels Dictionary<string, string> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- Execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- Execution
Statuses List<TaskExecution Status> - Configuration for the cluster Structure is documented below.
- Labels Dictionary<string, string>
- 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.
- Lake string
- The lake in which the task will be created in.
- Location string
- The location in which the task will be created in.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Project string
- Pulumi
Labels Dictionary<string, string> - The combination of labels configured directly on the resource and default labels configured on the provider.
- Spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- State string
- (Output) Execution state for the job.
- Task
Id string - The task Id of the task.
- Trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- Uid string
- (Output) System generated globally unique ID for the job.
- Update
Time string - (Output) Last update time of the status.
- Create
Time string - The time when the task was created.
- Description string
- User-provided description of the task.
- Display
Name string - User friendly display name.
- Effective
Labels map[string]string - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- Execution
Spec TaskExecution Spec Args - Configuration for the cluster Structure is documented below.
- Execution
Statuses []TaskExecution Status Args - Configuration for the cluster Structure is documented below.
- Labels map[string]string
- 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.
- Lake string
- The lake in which the task will be created in.
- Location string
- The location in which the task will be created in.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Notebook
Task
Notebook Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- Project string
- Pulumi
Labels map[string]string - The combination of labels configured directly on the resource and default labels configured on the provider.
- Spark
Task
Spark Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- State string
- (Output) Execution state for the job.
- Task
Id string - The task Id of the task.
- Trigger
Spec TaskTrigger Spec Args - Configuration for the cluster Structure is documented below.
- Uid string
- (Output) System generated globally unique ID for the job.
- Update
Time string - (Output) Last update time of the status.
- create
Time String - The time when the task was created.
- description String
- User-provided description of the task.
- display
Name String - User friendly display name.
- effective
Labels Map<String,String> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- execution
Statuses List<TaskExecution Status> - Configuration for the cluster Structure is documented below.
- labels Map<String,String>
- 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.
- lake String
- The lake in which the task will be created in.
- location String
- The location in which the task will be created in.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project String
- pulumi
Labels Map<String,String> - The combination of labels configured directly on the resource and default labels configured on the provider.
- spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- state String
- (Output) Execution state for the job.
- task
Id String - The task Id of the task.
- trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- uid String
- (Output) System generated globally unique ID for the job.
- update
Time String - (Output) Last update time of the status.
- create
Time string - The time when the task was created.
- description string
- User-provided description of the task.
- display
Name string - User friendly display name.
- effective
Labels {[key: string]: string} - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Spec TaskExecution Spec - Configuration for the cluster Structure is documented below.
- execution
Statuses TaskExecution Status[] - Configuration for the cluster Structure is documented below.
- labels {[key: string]: string}
- 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.
- lake string
- The lake in which the task will be created in.
- location string
- The location in which the task will be created in.
- name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- notebook
Task
Notebook - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project string
- pulumi
Labels {[key: string]: string} - The combination of labels configured directly on the resource and default labels configured on the provider.
- spark
Task
Spark - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- state string
- (Output) Execution state for the job.
- task
Id string - The task Id of the task.
- trigger
Spec TaskTrigger Spec - Configuration for the cluster Structure is documented below.
- uid string
- (Output) System generated globally unique ID for the job.
- update
Time string - (Output) Last update time of the status.
- create_
time str - The time when the task was created.
- description str
- User-provided description of the task.
- display_
name str - User friendly display name.
- effective_
labels Mapping[str, str] - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution_
spec TaskExecution Spec Args - Configuration for the cluster Structure is documented below.
- execution_
statuses Sequence[TaskExecution Status Args] - Configuration for the cluster Structure is documented below.
- labels Mapping[str, str]
- 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.
- lake str
- The lake in which the task will be created in.
- location str
- The location in which the task will be created in.
- name str
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- notebook
Task
Notebook Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project str
- pulumi_
labels Mapping[str, str] - The combination of labels configured directly on the resource and default labels configured on the provider.
- spark
Task
Spark Args - A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- state str
- (Output) Execution state for the job.
- task_
id str - The task Id of the task.
- trigger_
spec TaskTrigger Spec Args - Configuration for the cluster Structure is documented below.
- uid str
- (Output) System generated globally unique ID for the job.
- update_
time str - (Output) Last update time of the status.
- create
Time String - The time when the task was created.
- description String
- User-provided description of the task.
- display
Name String - User friendly display name.
- effective
Labels Map<String> - All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
- execution
Spec Property Map - Configuration for the cluster Structure is documented below.
- execution
Statuses List<Property Map> - Configuration for the cluster Structure is documented below.
- labels Map<String>
- 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.
- lake String
- The lake in which the task will be created in.
- location String
- The location in which the task will be created in.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- notebook Property Map
- A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- project String
- pulumi
Labels Map<String> - The combination of labels configured directly on the resource and default labels configured on the provider.
- spark Property Map
- A service with manual scaling runs continuously, allowing you to perform complex initialization and rely on the state of its memory over time.
- state String
- (Output) Execution state for the job.
- task
Id String - The task Id of the task.
- trigger
Spec Property Map - Configuration for the cluster Structure is documented below.
- uid String
- (Output) System generated globally unique ID for the job.
- update
Time String - (Output) Last update time of the status.
Supporting Types
TaskExecutionSpec, TaskExecutionSpecArgs
- Service
Account string - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- Args Dictionary<string, string>
- 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' }.
- Kms
Key string - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- Max
Job stringExecution Lifetime - 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'.
- Project string
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Service
Account string - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- Args map[string]string
- 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' }.
- Kms
Key string - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- Max
Job stringExecution Lifetime - 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'.
- Project string
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- service
Account String - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- args Map<String,String>
- 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' }.
- kms
Key String - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- max
Job StringExecution Lifetime - 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'.
- project String
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- service
Account string - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- args {[key: string]: string}
- 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' }.
- kms
Key string - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- max
Job stringExecution Lifetime - 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'.
- project string
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- service_
account str - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- args Mapping[str, str]
- 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' }.
- kms_
key str - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- max_
job_ strexecution_ lifetime - 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'.
- project str
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- service
Account String - Service account to use to execute a task. If not provided, the default Compute service account for the project is used.
- args Map<String>
- 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' }.
- kms
Key String - The Cloud KMS key to use for encryption, of the form: projects/{project_number}/locations/{locationId}/keyRings/{key-ring-name}/cryptoKeys/{key-name}.
- max
Job StringExecution Lifetime - 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'.
- project String
- The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
TaskExecutionStatus, TaskExecutionStatusArgs
- Latest
Jobs List<TaskExecution Status Latest Job> - (Output) latest job execution. Structure is documented below.
- Update
Time string - (Output) Last update time of the status.
- Latest
Jobs []TaskExecution Status Latest Job - (Output) latest job execution. Structure is documented below.
- Update
Time string - (Output) Last update time of the status.
- latest
Jobs List<TaskExecution Status Latest Job> - (Output) latest job execution. Structure is documented below.
- update
Time String - (Output) Last update time of the status.
- latest
Jobs TaskExecution Status Latest Job[] - (Output) latest job execution. Structure is documented below.
- update
Time string - (Output) Last update time of the status.
- latest_
jobs Sequence[TaskExecution Status Latest Job] - (Output) latest job execution. Structure is documented below.
- update_
time str - (Output) Last update time of the status.
- latest
Jobs List<Property Map> - (Output) latest job execution. Structure is documented below.
- update
Time String - (Output) Last update time of the status.
TaskExecutionStatusLatestJob, TaskExecutionStatusLatestJobArgs
- End
Time string - (Output) The time when the job ended.
- Message string
- (Output) Additional information about the current state.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Retry
Count int - (Output) The number of times the job has been retried (excluding the initial attempt).
- Service string
- (Output) The underlying service running a job.
- Service
Job string - (Output) The full resource name for the job run under a particular service.
- Start
Time string - (Output) The time when the job was started.
- State string
- (Output) Execution state for the job.
- Uid string
- (Output) System generated globally unique ID for the job.
- End
Time string - (Output) The time when the job ended.
- Message string
- (Output) Additional information about the current state.
- Name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- Retry
Count int - (Output) The number of times the job has been retried (excluding the initial attempt).
- Service string
- (Output) The underlying service running a job.
- Service
Job string - (Output) The full resource name for the job run under a particular service.
- Start
Time string - (Output) The time when the job was started.
- State string
- (Output) Execution state for the job.
- Uid string
- (Output) System generated globally unique ID for the job.
- end
Time String - (Output) The time when the job ended.
- message String
- (Output) Additional information about the current state.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- retry
Count Integer - (Output) The number of times the job has been retried (excluding the initial attempt).
- service String
- (Output) The underlying service running a job.
- service
Job String - (Output) The full resource name for the job run under a particular service.
- start
Time String - (Output) The time when the job was started.
- state String
- (Output) Execution state for the job.
- uid String
- (Output) System generated globally unique ID for the job.
- end
Time string - (Output) The time when the job ended.
- message string
- (Output) Additional information about the current state.
- name string
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- retry
Count number - (Output) The number of times the job has been retried (excluding the initial attempt).
- service string
- (Output) The underlying service running a job.
- service
Job string - (Output) The full resource name for the job run under a particular service.
- start
Time string - (Output) The time when the job was started.
- state string
- (Output) Execution state for the job.
- uid string
- (Output) System generated globally unique ID for the job.
- end_
time str - (Output) The time when the job ended.
- message str
- (Output) Additional information about the current state.
- name str
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- retry_
count int - (Output) The number of times the job has been retried (excluding the initial attempt).
- service str
- (Output) The underlying service running a job.
- service_
job str - (Output) The full resource name for the job run under a particular service.
- start_
time str - (Output) The time when the job was started.
- state str
- (Output) Execution state for the job.
- uid str
- (Output) System generated globally unique ID for the job.
- end
Time String - (Output) The time when the job ended.
- message String
- (Output) Additional information about the current state.
- name String
- (Output) The relative resource name of the job, of the form: projects/{project_number}/locations/{locationId}/lakes/{lakeId}/tasks/{taskId}/jobs/{jobId}.
- retry
Count Number - (Output) The number of times the job has been retried (excluding the initial attempt).
- service String
- (Output) The underlying service running a job.
- service
Job String - (Output) The full resource name for the job run under a particular service.
- start
Time String - (Output) The time when the job was started.
- state String
- (Output) Execution state for the job.
- uid String
- (Output) System generated globally unique ID for the job.
TaskNotebook, TaskNotebookArgs
- Notebook string
- 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).
- Archive
Uris List<string> - 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.
- File
Uris List<string> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- Infrastructure
Spec TaskNotebook Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- Notebook string
- 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).
- Archive
Uris []string - 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.
- File
Uris []string - Cloud Storage URIs of files to be placed in the working directory of each executor.
- Infrastructure
Spec TaskNotebook Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- notebook String
- 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).
- archive
Uris List<String> - 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.
- file
Uris List<String> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec TaskNotebook Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- notebook string
- 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).
- archive
Uris string[] - 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.
- file
Uris string[] - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec TaskNotebook Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- notebook str
- 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).
- archive_
uris Sequence[str] - 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.
- file_
uris Sequence[str] - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure_
spec TaskNotebook Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- notebook String
- 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).
- archive
Uris List<String> - 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.
- file
Uris List<String> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec Property Map - Infrastructure specification for the execution. Structure is documented below.
TaskNotebookInfrastructureSpec, TaskNotebookInfrastructureSpecArgs
- Batch
Task
Notebook Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- Container
Image TaskNotebook Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- Vpc
Network TaskNotebook Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- Batch
Task
Notebook Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- Container
Image TaskNotebook Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- Vpc
Network TaskNotebook Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Notebook Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image TaskNotebook Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network TaskNotebook Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Notebook Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image TaskNotebook Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network TaskNotebook Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Notebook Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container_
image TaskNotebook Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc_
network TaskNotebook Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch Property Map
- Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image Property Map - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network Property Map - Vpc network. Structure is documented below.
TaskNotebookInfrastructureSpecBatch, TaskNotebookInfrastructureSpecBatchArgs
- Executors
Count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- Max
Executors intCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- Executors
Count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- Max
Executors intCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count Integer - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors IntegerCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count number - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors numberCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors_
count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max_
executors_ intcount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count Number - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors NumberCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
TaskNotebookInfrastructureSpecContainerImage, TaskNotebookInfrastructureSpecContainerImageArgs
- Image string
- Container image to use.
- Java
Jars List<string> - 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
- Properties Dictionary<string, string>
- 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.
- Python
Packages List<string> - 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
- Image string
- Container image to use.
- Java
Jars []string - 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
- Properties map[string]string
- 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.
- Python
Packages []string - 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
- image String
- Container image to use.
- java
Jars List<String> - 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
- properties Map<String,String>
- 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.
- python
Packages List<String> - 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
- image string
- Container image to use.
- java
Jars string[] - 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
- properties {[key: string]: string}
- 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.
- python
Packages string[] - 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
- image str
- Container image to use.
- java_
jars Sequence[str] - 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
- properties Mapping[str, str]
- 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.
- python_
packages Sequence[str] - 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
- image String
- Container image to use.
- java
Jars List<String> - 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
- properties Map<String>
- 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.
- python
Packages List<String> - 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
TaskNotebookInfrastructureSpecVpcNetwork, TaskNotebookInfrastructureSpecVpcNetworkArgs
- Network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<string>
- List of network tags to apply to the job.
- Sub
Network string - The Cloud VPC sub-network in which the job is run.
- Network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- []string
- List of network tags to apply to the job.
- Sub
Network string - The Cloud VPC sub-network in which the job is run.
- network String
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<String>
- List of network tags to apply to the job.
- sub
Network String - The Cloud VPC sub-network in which the job is run.
- network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- string[]
- List of network tags to apply to the job.
- sub
Network string - The Cloud VPC sub-network in which the job is run.
- network str
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- Sequence[str]
- List of network tags to apply to the job.
- sub_
network str - The Cloud VPC sub-network in which the job is run.
- network String
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<String>
- List of network tags to apply to the job.
- sub
Network String - The Cloud VPC sub-network in which the job is run.
TaskSpark, TaskSparkArgs
- Archive
Uris List<string> - 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.
- File
Uris List<string> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- Infrastructure
Spec TaskSpark Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- Main
Class string - 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).
- Main
Jar stringFile Uri - 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).
- Python
Script stringFile - 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 string - The query text. The execution args are used to declare a set of script variables (set key='value';).
- Sql
Script stringFile - 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';).
- Archive
Uris []string - 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.
- File
Uris []string - Cloud Storage URIs of files to be placed in the working directory of each executor.
- Infrastructure
Spec TaskSpark Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- Main
Class string - 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).
- Main
Jar stringFile Uri - 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).
- Python
Script stringFile - 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 string - The query text. The execution args are used to declare a set of script variables (set key='value';).
- Sql
Script stringFile - 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';).
- archive
Uris List<String> - 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.
- file
Uris List<String> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec TaskSpark Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- main
Class String - 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).
- main
Jar StringFile Uri - 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).
- python
Script StringFile - 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 String - The query text. The execution args are used to declare a set of script variables (set key='value';).
- sql
Script StringFile - 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';).
- archive
Uris string[] - 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.
- file
Uris string[] - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec TaskSpark Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- main
Class string - 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).
- main
Jar stringFile Uri - 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).
- python
Script stringFile - 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 string - The query text. The execution args are used to declare a set of script variables (set key='value';).
- sql
Script stringFile - 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';).
- archive_
uris Sequence[str] - 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.
- file_
uris Sequence[str] - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure_
spec TaskSpark Infrastructure Spec - Infrastructure specification for the execution. Structure is documented below.
- main_
class str - 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).
- main_
jar_ strfile_ uri - 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).
- python_
script_ strfile - 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 str - The query text. The execution args are used to declare a set of script variables (set key='value';).
- sql_
script_ strfile - 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';).
- archive
Uris List<String> - 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.
- file
Uris List<String> - Cloud Storage URIs of files to be placed in the working directory of each executor.
- infrastructure
Spec Property Map - Infrastructure specification for the execution. Structure is documented below.
- main
Class String - 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).
- main
Jar StringFile Uri - 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).
- python
Script StringFile - 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 String - The query text. The execution args are used to declare a set of script variables (set key='value';).
- sql
Script StringFile - 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';).
TaskSparkInfrastructureSpec, TaskSparkInfrastructureSpecArgs
- Batch
Task
Spark Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- Container
Image TaskSpark Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- Vpc
Network TaskSpark Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- Batch
Task
Spark Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- Container
Image TaskSpark Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- Vpc
Network TaskSpark Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Spark Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image TaskSpark Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network TaskSpark Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Spark Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image TaskSpark Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network TaskSpark Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch
Task
Spark Infrastructure Spec Batch - Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container_
image TaskSpark Infrastructure Spec Container Image - Container Image Runtime Configuration. Structure is documented below.
- vpc_
network TaskSpark Infrastructure Spec Vpc Network - Vpc network. Structure is documented below.
- batch Property Map
- Compute resources needed for a Task when using Dataproc Serverless. Structure is documented below.
- container
Image Property Map - Container Image Runtime Configuration. Structure is documented below.
- vpc
Network Property Map - Vpc network. Structure is documented below.
TaskSparkInfrastructureSpecBatch, TaskSparkInfrastructureSpecBatchArgs
- Executors
Count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- Max
Executors intCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- Executors
Count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- Max
Executors intCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count Integer - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors IntegerCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count number - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors numberCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors_
count int - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max_
executors_ intcount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
- executors
Count Number - Total number of job executors. Executor Count should be between 2 and 100. [Default=2]
- max
Executors NumberCount - Max configurable executors. If maxExecutorsCount > executorsCount, then auto-scaling is enabled. Max Executor Count should be between 2 and 1000. [Default=1000]
TaskSparkInfrastructureSpecContainerImage, TaskSparkInfrastructureSpecContainerImageArgs
- Image string
- Container image to use.
- Java
Jars List<string> - 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
- Properties Dictionary<string, string>
- 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.
- Python
Packages List<string> - 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
- Image string
- Container image to use.
- Java
Jars []string - 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
- Properties map[string]string
- 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.
- Python
Packages []string - 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
- image String
- Container image to use.
- java
Jars List<String> - 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
- properties Map<String,String>
- 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.
- python
Packages List<String> - 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
- image string
- Container image to use.
- java
Jars string[] - 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
- properties {[key: string]: string}
- 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.
- python
Packages string[] - 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
- image str
- Container image to use.
- java_
jars Sequence[str] - 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
- properties Mapping[str, str]
- 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.
- python_
packages Sequence[str] - 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
- image String
- Container image to use.
- java
Jars List<String> - 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
- properties Map<String>
- 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.
- python
Packages List<String> - 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
TaskSparkInfrastructureSpecVpcNetwork, TaskSparkInfrastructureSpecVpcNetworkArgs
- Network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<string>
- List of network tags to apply to the job.
- Sub
Network string - The Cloud VPC sub-network in which the job is run.
- Network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- []string
- List of network tags to apply to the job.
- Sub
Network string - The Cloud VPC sub-network in which the job is run.
- network String
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<String>
- List of network tags to apply to the job.
- sub
Network String - The Cloud VPC sub-network in which the job is run.
- network string
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- string[]
- List of network tags to apply to the job.
- sub
Network string - The Cloud VPC sub-network in which the job is run.
- network str
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- Sequence[str]
- List of network tags to apply to the job.
- sub_
network str - The Cloud VPC sub-network in which the job is run.
- network String
- The Cloud VPC network in which the job is run. By default, the Cloud VPC network named Default within the project is used.
- List<String>
- List of network tags to apply to the job.
- sub
Network String - The Cloud VPC sub-network in which the job is run.
TaskTriggerSpec, TaskTriggerSpecArgs
- Type string
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - Disabled bool
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- Max
Retries int - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- Schedule string
- 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 ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.
- Start
Time string - The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.
- Type string
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - Disabled bool
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- Max
Retries int - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- Schedule string
- Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.
- Start
Time string - The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.
- type String
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - disabled Boolean
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- max
Retries Integer - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- schedule String
- Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.
- start
Time String - The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.
- type string
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - disabled boolean
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- max
Retries number - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- schedule string
- Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.
- start
Time string - The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.
- type str
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - disabled bool
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- max_
retries int - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- schedule str
- Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${IANA_TIME_ZONE}' or 'TZ=${IANA_TIME_ZONE}'. The ${IANA_TIME_ZONE} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *. This field is required for RECURRING tasks.
- start_
time str - The first run of the task will be after this time. If not specified, the task will run shortly after being submitted if ON_DEMAND and based on the schedule if RECURRING.
- type String
- Trigger type of the user-specified Task
Possible values are:
ON_DEMAND,RECURRING. - disabled Boolean
- Prevent the task from executing. This does not cancel already running tasks. It is intended to temporarily disable RECURRING tasks.
- max
Retries Number - Number of retry attempts before aborting. Set to zero to never attempt to retry a failed task.
- schedule String
- Cron schedule (https://en.wikipedia.org/wiki/Cron) for running tasks periodically. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: 'CRON_TZ=${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.
- start
Time String - 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.
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}}
When using the pulumi import command, Task can be imported using one of the formats above. For example:
$ pulumi import gcp:dataplex/task:Task default projects/{{project}}/locations/{{location}}/lakes/{{lake}}/tasks/{{task_id}}
$ pulumi import gcp:dataplex/task:Task default {{project}}/{{location}}/{{lake}}/{{task_id}}
$ pulumi import gcp:dataplex/task:Task default {{location}}/{{lake}}/{{task_id}}
To learn more about importing existing cloud resources, see Importing resources.
Package Details
- Repository
- Google Cloud (GCP) Classic pulumi/pulumi-gcp
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the
google-betaTerraform Provider.