yandex.DataprocCluster
Explore with Pulumi AI
Manages a Data Proc cluster. For more information, see the official documentation.
Example Usage
using System.IO;
using Pulumi;
using Yandex = Pulumi.Yandex;
class MyStack : Stack
{
public MyStack()
{
var fooVpcNetwork = new Yandex.VpcNetwork("fooVpcNetwork", new Yandex.VpcNetworkArgs
{
});
var fooVpcSubnet = new Yandex.VpcSubnet("fooVpcSubnet", new Yandex.VpcSubnetArgs
{
Zone = "ru-central1-b",
NetworkId = fooVpcNetwork.Id,
V4CidrBlocks =
{
"10.1.0.0/24",
},
});
var dataprocIamServiceAccount = new Yandex.IamServiceAccount("dataprocIamServiceAccount", new Yandex.IamServiceAccountArgs
{
Description = "service account to manage Dataproc Cluster",
});
var fooResourcemanagerFolder = Output.Create(Yandex.GetResourcemanagerFolder.InvokeAsync(new Yandex.GetResourcemanagerFolderArgs
{
FolderId = "some_folder_id",
}));
var dataprocResourcemanagerFolderIamBinding = new Yandex.ResourcemanagerFolderIamBinding("dataprocResourcemanagerFolderIamBinding", new Yandex.ResourcemanagerFolderIamBindingArgs
{
FolderId = fooResourcemanagerFolder.Apply(fooResourcemanagerFolder => fooResourcemanagerFolder.Id),
Role = "mdb.dataproc.agent",
Members =
{
dataprocIamServiceAccount.Id.Apply(id => $"serviceAccount:{id}"),
},
});
// required in order to create bucket
var bucket_creator = new Yandex.ResourcemanagerFolderIamBinding("bucket-creator", new Yandex.ResourcemanagerFolderIamBindingArgs
{
FolderId = fooResourcemanagerFolder.Apply(fooResourcemanagerFolder => fooResourcemanagerFolder.Id),
Role = "editor",
Members =
{
dataprocIamServiceAccount.Id.Apply(id => $"serviceAccount:{id}"),
},
});
var fooIamServiceAccountStaticAccessKey = new Yandex.IamServiceAccountStaticAccessKey("fooIamServiceAccountStaticAccessKey", new Yandex.IamServiceAccountStaticAccessKeyArgs
{
ServiceAccountId = dataprocIamServiceAccount.Id,
});
var fooStorageBucket = new Yandex.StorageBucket("fooStorageBucket", new Yandex.StorageBucketArgs
{
Bucket = "foo",
AccessKey = fooIamServiceAccountStaticAccessKey.AccessKey,
SecretKey = fooIamServiceAccountStaticAccessKey.SecretKey,
}, new CustomResourceOptions
{
DependsOn =
{
bucket_creator,
},
});
var fooDataprocCluster = new Yandex.DataprocCluster("fooDataprocCluster", new Yandex.DataprocClusterArgs
{
Bucket = fooStorageBucket.Bucket,
Description = "Dataproc Cluster created by Terraform",
Labels =
{
{ "created_by", "terraform" },
},
ServiceAccountId = dataprocIamServiceAccount.Id,
ZoneId = "ru-central1-b",
ClusterConfig = new Yandex.Inputs.DataprocClusterClusterConfigArgs
{
Hadoop = new Yandex.Inputs.DataprocClusterClusterConfigHadoopArgs
{
Services =
{
"HDFS",
"YARN",
"SPARK",
"TEZ",
"MAPREDUCE",
"HIVE",
},
Properties =
{
{ "yarn:yarn.resourcemanager.am.max-attempts", "5" },
},
SshPublicKeys =
{
File.ReadAllText("~/.ssh/id_rsa.pub"),
},
},
SubclusterSpecs =
{
new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecArgs
{
Name = "main",
Role = "MASTERNODE",
Resources = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecResourcesArgs
{
ResourcePresetId = "s2.small",
DiskTypeId = "network-hdd",
DiskSize = 20,
},
SubnetId = fooVpcSubnet.Id,
HostsCount = 1,
},
new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecArgs
{
Name = "data",
Role = "DATANODE",
Resources = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecResourcesArgs
{
ResourcePresetId = "s2.small",
DiskTypeId = "network-hdd",
DiskSize = 20,
},
SubnetId = fooVpcSubnet.Id,
HostsCount = 2,
},
new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecArgs
{
Name = "compute",
Role = "COMPUTENODE",
Resources = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecResourcesArgs
{
ResourcePresetId = "s2.small",
DiskTypeId = "network-hdd",
DiskSize = 20,
},
SubnetId = fooVpcSubnet.Id,
HostsCount = 2,
},
new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecArgs
{
Name = "compute_autoscaling",
Role = "COMPUTENODE",
Resources = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecResourcesArgs
{
ResourcePresetId = "s2.small",
DiskTypeId = "network-hdd",
DiskSize = 20,
},
SubnetId = fooVpcSubnet.Id,
HostsCount = 2,
AutoscalingConfig = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs
{
MaxHostsCount = 10,
MeasurementDuration = 60,
WarmupDuration = 60,
StabilizationDuration = 120,
Preemptible = false,
DecommissionTimeout = 60,
},
},
},
},
}, new CustomResourceOptions
{
DependsOn =
{
dataprocResourcemanagerFolderIamBinding,
},
});
}
}
package main
import (
"fmt"
"io/ioutil"
"github.com/pulumi/pulumi-yandex/sdk/go/yandex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func readFileOrPanic(path string) pulumi.StringPtrInput {
data, err := ioutil.ReadFile(path)
if err != nil {
panic(err.Error())
}
return pulumi.String(string(data))
}
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
fooVpcNetwork, err := yandex.NewVpcNetwork(ctx, "fooVpcNetwork", nil)
if err != nil {
return err
}
fooVpcSubnet, err := yandex.NewVpcSubnet(ctx, "fooVpcSubnet", &yandex.VpcSubnetArgs{
Zone: pulumi.String("ru-central1-b"),
NetworkId: fooVpcNetwork.ID(),
V4CidrBlocks: pulumi.StringArray{
pulumi.String("10.1.0.0/24"),
},
})
if err != nil {
return err
}
dataprocIamServiceAccount, err := yandex.NewIamServiceAccount(ctx, "dataprocIamServiceAccount", &yandex.IamServiceAccountArgs{
Description: pulumi.String("service account to manage Dataproc Cluster"),
})
if err != nil {
return err
}
opt0 := "some_folder_id"
fooResourcemanagerFolder, err := yandex.LookupResourcemanagerFolder(ctx, &GetResourcemanagerFolderArgs{
FolderId: &opt0,
}, nil)
if err != nil {
return err
}
dataprocResourcemanagerFolderIamBinding, err := yandex.NewResourcemanagerFolderIamBinding(ctx, "dataprocResourcemanagerFolderIamBinding", &yandex.ResourcemanagerFolderIamBindingArgs{
FolderId: pulumi.String(fooResourcemanagerFolder.Id),
Role: pulumi.String("mdb.dataproc.agent"),
Members: pulumi.StringArray{
dataprocIamServiceAccount.ID().ApplyT(func(id string) (string, error) {
return fmt.Sprintf("%v%v", "serviceAccount:", id), nil
}).(pulumi.StringOutput),
},
})
if err != nil {
return err
}
_, err = yandex.NewResourcemanagerFolderIamBinding(ctx, "bucket-creator", &yandex.ResourcemanagerFolderIamBindingArgs{
FolderId: pulumi.String(fooResourcemanagerFolder.Id),
Role: pulumi.String("editor"),
Members: pulumi.StringArray{
dataprocIamServiceAccount.ID().ApplyT(func(id string) (string, error) {
return fmt.Sprintf("%v%v", "serviceAccount:", id), nil
}).(pulumi.StringOutput),
},
})
if err != nil {
return err
}
fooIamServiceAccountStaticAccessKey, err := yandex.NewIamServiceAccountStaticAccessKey(ctx, "fooIamServiceAccountStaticAccessKey", &yandex.IamServiceAccountStaticAccessKeyArgs{
ServiceAccountId: dataprocIamServiceAccount.ID(),
})
if err != nil {
return err
}
fooStorageBucket, err := yandex.NewStorageBucket(ctx, "fooStorageBucket", &yandex.StorageBucketArgs{
Bucket: pulumi.String("foo"),
AccessKey: fooIamServiceAccountStaticAccessKey.AccessKey,
SecretKey: fooIamServiceAccountStaticAccessKey.SecretKey,
}, pulumi.DependsOn([]pulumi.Resource{
bucket_creator,
}))
if err != nil {
return err
}
_, err = yandex.NewDataprocCluster(ctx, "fooDataprocCluster", &yandex.DataprocClusterArgs{
Bucket: fooStorageBucket.Bucket,
Description: pulumi.String("Dataproc Cluster created by Terraform"),
Labels: pulumi.StringMap{
"created_by": pulumi.String("terraform"),
},
ServiceAccountId: dataprocIamServiceAccount.ID(),
ZoneId: pulumi.String("ru-central1-b"),
ClusterConfig: &DataprocClusterClusterConfigArgs{
Hadoop: &DataprocClusterClusterConfigHadoopArgs{
Services: pulumi.StringArray{
pulumi.String("HDFS"),
pulumi.String("YARN"),
pulumi.String("SPARK"),
pulumi.String("TEZ"),
pulumi.String("MAPREDUCE"),
pulumi.String("HIVE"),
},
Properties: pulumi.StringMap{
"yarn:yarn.resourcemanager.am.max-attempts": pulumi.String("5"),
},
SshPublicKeys: pulumi.StringArray{
readFileOrPanic("~/.ssh/id_rsa.pub"),
},
},
SubclusterSpecs: DataprocClusterClusterConfigSubclusterSpecArray{
&DataprocClusterClusterConfigSubclusterSpecArgs{
Name: pulumi.String("main"),
Role: pulumi.String("MASTERNODE"),
Resources: &DataprocClusterClusterConfigSubclusterSpecResourcesArgs{
ResourcePresetId: pulumi.String("s2.small"),
DiskTypeId: pulumi.String("network-hdd"),
DiskSize: pulumi.Int(20),
},
SubnetId: fooVpcSubnet.ID(),
HostsCount: pulumi.Int(1),
},
&DataprocClusterClusterConfigSubclusterSpecArgs{
Name: pulumi.String("data"),
Role: pulumi.String("DATANODE"),
Resources: &DataprocClusterClusterConfigSubclusterSpecResourcesArgs{
ResourcePresetId: pulumi.String("s2.small"),
DiskTypeId: pulumi.String("network-hdd"),
DiskSize: pulumi.Int(20),
},
SubnetId: fooVpcSubnet.ID(),
HostsCount: pulumi.Int(2),
},
&DataprocClusterClusterConfigSubclusterSpecArgs{
Name: pulumi.String("compute"),
Role: pulumi.String("COMPUTENODE"),
Resources: &DataprocClusterClusterConfigSubclusterSpecResourcesArgs{
ResourcePresetId: pulumi.String("s2.small"),
DiskTypeId: pulumi.String("network-hdd"),
DiskSize: pulumi.Int(20),
},
SubnetId: fooVpcSubnet.ID(),
HostsCount: pulumi.Int(2),
},
&DataprocClusterClusterConfigSubclusterSpecArgs{
Name: pulumi.String("compute_autoscaling"),
Role: pulumi.String("COMPUTENODE"),
Resources: &DataprocClusterClusterConfigSubclusterSpecResourcesArgs{
ResourcePresetId: pulumi.String("s2.small"),
DiskTypeId: pulumi.String("network-hdd"),
DiskSize: pulumi.Int(20),
},
SubnetId: fooVpcSubnet.ID(),
HostsCount: pulumi.Int(2),
AutoscalingConfig: &DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs{
MaxHostsCount: pulumi.Int(10),
MeasurementDuration: pulumi.Int(60),
WarmupDuration: pulumi.Int(60),
StabilizationDuration: pulumi.Int(120),
Preemptible: pulumi.Bool(false),
DecommissionTimeout: pulumi.Int(60),
},
},
},
},
}, pulumi.DependsOn([]pulumi.Resource{
dataprocResourcemanagerFolderIamBinding,
}))
if err != nil {
return err
}
return nil
})
}
Coming soon!
import pulumi
import pulumi_yandex as yandex
foo_vpc_network = yandex.VpcNetwork("fooVpcNetwork")
foo_vpc_subnet = yandex.VpcSubnet("fooVpcSubnet",
zone="ru-central1-b",
network_id=foo_vpc_network.id,
v4_cidr_blocks=["10.1.0.0/24"])
dataproc_iam_service_account = yandex.IamServiceAccount("dataprocIamServiceAccount", description="service account to manage Dataproc Cluster")
foo_resourcemanager_folder = yandex.get_resourcemanager_folder(folder_id="some_folder_id")
dataproc_resourcemanager_folder_iam_binding = yandex.ResourcemanagerFolderIamBinding("dataprocResourcemanagerFolderIamBinding",
folder_id=foo_resourcemanager_folder.id,
role="mdb.dataproc.agent",
members=[dataproc_iam_service_account.id.apply(lambda id: f"serviceAccount:{id}")])
# required in order to create bucket
bucket_creator = yandex.ResourcemanagerFolderIamBinding("bucket-creator",
folder_id=foo_resourcemanager_folder.id,
role="editor",
members=[dataproc_iam_service_account.id.apply(lambda id: f"serviceAccount:{id}")])
foo_iam_service_account_static_access_key = yandex.IamServiceAccountStaticAccessKey("fooIamServiceAccountStaticAccessKey", service_account_id=dataproc_iam_service_account.id)
foo_storage_bucket = yandex.StorageBucket("fooStorageBucket",
bucket="foo",
access_key=foo_iam_service_account_static_access_key.access_key,
secret_key=foo_iam_service_account_static_access_key.secret_key,
opts=pulumi.ResourceOptions(depends_on=[bucket_creator]))
foo_dataproc_cluster = yandex.DataprocCluster("fooDataprocCluster",
bucket=foo_storage_bucket.bucket,
description="Dataproc Cluster created by Terraform",
labels={
"created_by": "terraform",
},
service_account_id=dataproc_iam_service_account.id,
zone_id="ru-central1-b",
cluster_config=yandex.DataprocClusterClusterConfigArgs(
hadoop=yandex.DataprocClusterClusterConfigHadoopArgs(
services=[
"HDFS",
"YARN",
"SPARK",
"TEZ",
"MAPREDUCE",
"HIVE",
],
properties={
"yarn:yarn.resourcemanager.am.max-attempts": "5",
},
ssh_public_keys=[(lambda path: open(path).read())("~/.ssh/id_rsa.pub")],
),
subcluster_specs=[
yandex.DataprocClusterClusterConfigSubclusterSpecArgs(
name="main",
role="MASTERNODE",
resources=yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs(
resource_preset_id="s2.small",
disk_type_id="network-hdd",
disk_size=20,
),
subnet_id=foo_vpc_subnet.id,
hosts_count=1,
),
yandex.DataprocClusterClusterConfigSubclusterSpecArgs(
name="data",
role="DATANODE",
resources=yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs(
resource_preset_id="s2.small",
disk_type_id="network-hdd",
disk_size=20,
),
subnet_id=foo_vpc_subnet.id,
hosts_count=2,
),
yandex.DataprocClusterClusterConfigSubclusterSpecArgs(
name="compute",
role="COMPUTENODE",
resources=yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs(
resource_preset_id="s2.small",
disk_type_id="network-hdd",
disk_size=20,
),
subnet_id=foo_vpc_subnet.id,
hosts_count=2,
),
yandex.DataprocClusterClusterConfigSubclusterSpecArgs(
name="compute_autoscaling",
role="COMPUTENODE",
resources=yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs(
resource_preset_id="s2.small",
disk_type_id="network-hdd",
disk_size=20,
),
subnet_id=foo_vpc_subnet.id,
hosts_count=2,
autoscaling_config=yandex.DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs(
max_hosts_count=10,
measurement_duration=60,
warmup_duration=60,
stabilization_duration=120,
preemptible=False,
decommission_timeout=60,
),
),
],
),
opts=pulumi.ResourceOptions(depends_on=[dataproc_resourcemanager_folder_iam_binding]))
import * as pulumi from "@pulumi/pulumi";
import * as yandex from "@pulumi/yandex";
import * from "fs";
const fooVpcNetwork = new yandex.VpcNetwork("fooVpcNetwork", {});
const fooVpcSubnet = new yandex.VpcSubnet("fooVpcSubnet", {
zone: "ru-central1-b",
networkId: fooVpcNetwork.id,
v4CidrBlocks: ["10.1.0.0/24"],
});
const dataprocIamServiceAccount = new yandex.IamServiceAccount("dataprocIamServiceAccount", {description: "service account to manage Dataproc Cluster"});
const fooResourcemanagerFolder = yandex.getResourcemanagerFolder({
folderId: "some_folder_id",
});
const dataprocResourcemanagerFolderIamBinding = new yandex.ResourcemanagerFolderIamBinding("dataprocResourcemanagerFolderIamBinding", {
folderId: fooResourcemanagerFolder.then(fooResourcemanagerFolder => fooResourcemanagerFolder.id),
role: "mdb.dataproc.agent",
members: [pulumi.interpolate`serviceAccount:${dataprocIamServiceAccount.id}`],
});
// required in order to create bucket
const bucket_creator = new yandex.ResourcemanagerFolderIamBinding("bucket-creator", {
folderId: fooResourcemanagerFolder.then(fooResourcemanagerFolder => fooResourcemanagerFolder.id),
role: "editor",
members: [pulumi.interpolate`serviceAccount:${dataprocIamServiceAccount.id}`],
});
const fooIamServiceAccountStaticAccessKey = new yandex.IamServiceAccountStaticAccessKey("fooIamServiceAccountStaticAccessKey", {serviceAccountId: dataprocIamServiceAccount.id});
const fooStorageBucket = new yandex.StorageBucket("fooStorageBucket", {
bucket: "foo",
accessKey: fooIamServiceAccountStaticAccessKey.accessKey,
secretKey: fooIamServiceAccountStaticAccessKey.secretKey,
}, {
dependsOn: [bucket_creator],
});
const fooDataprocCluster = new yandex.DataprocCluster("fooDataprocCluster", {
bucket: fooStorageBucket.bucket,
description: "Dataproc Cluster created by Terraform",
labels: {
created_by: "terraform",
},
serviceAccountId: dataprocIamServiceAccount.id,
zoneId: "ru-central1-b",
clusterConfig: {
hadoop: {
services: [
"HDFS",
"YARN",
"SPARK",
"TEZ",
"MAPREDUCE",
"HIVE",
],
properties: {
"yarn:yarn.resourcemanager.am.max-attempts": 5,
},
sshPublicKeys: [fs.readFileSync("~/.ssh/id_rsa.pub")],
},
subclusterSpecs: [
{
name: "main",
role: "MASTERNODE",
resources: {
resourcePresetId: "s2.small",
diskTypeId: "network-hdd",
diskSize: 20,
},
subnetId: fooVpcSubnet.id,
hostsCount: 1,
},
{
name: "data",
role: "DATANODE",
resources: {
resourcePresetId: "s2.small",
diskTypeId: "network-hdd",
diskSize: 20,
},
subnetId: fooVpcSubnet.id,
hostsCount: 2,
},
{
name: "compute",
role: "COMPUTENODE",
resources: {
resourcePresetId: "s2.small",
diskTypeId: "network-hdd",
diskSize: 20,
},
subnetId: fooVpcSubnet.id,
hostsCount: 2,
},
{
name: "compute_autoscaling",
role: "COMPUTENODE",
resources: {
resourcePresetId: "s2.small",
diskTypeId: "network-hdd",
diskSize: 20,
},
subnetId: fooVpcSubnet.id,
hostsCount: 2,
autoscalingConfig: {
maxHostsCount: 10,
measurementDuration: 60,
warmupDuration: 60,
stabilizationDuration: 120,
preemptible: false,
decommissionTimeout: 60,
},
},
],
},
}, {
dependsOn: [dataprocResourcemanagerFolderIamBinding],
});
Coming soon!
Create DataprocCluster Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new DataprocCluster(name: string, args: DataprocClusterArgs, opts?: CustomResourceOptions);
@overload
def DataprocCluster(resource_name: str,
args: DataprocClusterArgs,
opts: Optional[ResourceOptions] = None)
@overload
def DataprocCluster(resource_name: str,
opts: Optional[ResourceOptions] = None,
cluster_config: Optional[DataprocClusterClusterConfigArgs] = None,
service_account_id: Optional[str] = None,
bucket: Optional[str] = None,
deletion_protection: Optional[bool] = None,
description: Optional[str] = None,
folder_id: Optional[str] = None,
host_group_ids: Optional[Sequence[str]] = None,
labels: Optional[Mapping[str, str]] = None,
name: Optional[str] = None,
security_group_ids: Optional[Sequence[str]] = None,
ui_proxy: Optional[bool] = None,
zone_id: Optional[str] = None)
func NewDataprocCluster(ctx *Context, name string, args DataprocClusterArgs, opts ...ResourceOption) (*DataprocCluster, error)
public DataprocCluster(string name, DataprocClusterArgs args, CustomResourceOptions? opts = null)
public DataprocCluster(String name, DataprocClusterArgs args)
public DataprocCluster(String name, DataprocClusterArgs args, CustomResourceOptions options)
type: yandex:DataprocCluster
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 DataprocClusterArgs
- 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 DataprocClusterArgs
- 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 DataprocClusterArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args DataprocClusterArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args DataprocClusterArgs
- 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 dataprocClusterResource = new Yandex.DataprocCluster("dataprocClusterResource", new()
{
ClusterConfig = new Yandex.Inputs.DataprocClusterClusterConfigArgs
{
SubclusterSpecs = new[]
{
new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecArgs
{
HostsCount = 0,
Name = "string",
Resources = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecResourcesArgs
{
DiskSize = 0,
ResourcePresetId = "string",
DiskTypeId = "string",
},
Role = "string",
SubnetId = "string",
AutoscalingConfig = new Yandex.Inputs.DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs
{
MaxHostsCount = 0,
CpuUtilizationTarget = 0,
DecommissionTimeout = 0,
MeasurementDuration = 0,
Preemptible = false,
StabilizationDuration = 0,
WarmupDuration = 0,
},
Id = "string",
},
},
Hadoop = new Yandex.Inputs.DataprocClusterClusterConfigHadoopArgs
{
Properties =
{
{ "string", "string" },
},
Services = new[]
{
"string",
},
SshPublicKeys = new[]
{
"string",
},
},
VersionId = "string",
},
ServiceAccountId = "string",
Bucket = "string",
DeletionProtection = false,
Description = "string",
FolderId = "string",
HostGroupIds = new[]
{
"string",
},
Labels =
{
{ "string", "string" },
},
Name = "string",
SecurityGroupIds = new[]
{
"string",
},
UiProxy = false,
ZoneId = "string",
});
example, err := yandex.NewDataprocCluster(ctx, "dataprocClusterResource", &yandex.DataprocClusterArgs{
ClusterConfig: &yandex.DataprocClusterClusterConfigArgs{
SubclusterSpecs: yandex.DataprocClusterClusterConfigSubclusterSpecArray{
&yandex.DataprocClusterClusterConfigSubclusterSpecArgs{
HostsCount: pulumi.Int(0),
Name: pulumi.String("string"),
Resources: &yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs{
DiskSize: pulumi.Int(0),
ResourcePresetId: pulumi.String("string"),
DiskTypeId: pulumi.String("string"),
},
Role: pulumi.String("string"),
SubnetId: pulumi.String("string"),
AutoscalingConfig: &yandex.DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs{
MaxHostsCount: pulumi.Int(0),
CpuUtilizationTarget: pulumi.Float64(0),
DecommissionTimeout: pulumi.Int(0),
MeasurementDuration: pulumi.Int(0),
Preemptible: pulumi.Bool(false),
StabilizationDuration: pulumi.Int(0),
WarmupDuration: pulumi.Int(0),
},
Id: pulumi.String("string"),
},
},
Hadoop: &yandex.DataprocClusterClusterConfigHadoopArgs{
Properties: pulumi.StringMap{
"string": pulumi.String("string"),
},
Services: pulumi.StringArray{
pulumi.String("string"),
},
SshPublicKeys: pulumi.StringArray{
pulumi.String("string"),
},
},
VersionId: pulumi.String("string"),
},
ServiceAccountId: pulumi.String("string"),
Bucket: pulumi.String("string"),
DeletionProtection: pulumi.Bool(false),
Description: pulumi.String("string"),
FolderId: pulumi.String("string"),
HostGroupIds: pulumi.StringArray{
pulumi.String("string"),
},
Labels: pulumi.StringMap{
"string": pulumi.String("string"),
},
Name: pulumi.String("string"),
SecurityGroupIds: pulumi.StringArray{
pulumi.String("string"),
},
UiProxy: pulumi.Bool(false),
ZoneId: pulumi.String("string"),
})
var dataprocClusterResource = new DataprocCluster("dataprocClusterResource", DataprocClusterArgs.builder()
.clusterConfig(DataprocClusterClusterConfigArgs.builder()
.subclusterSpecs(DataprocClusterClusterConfigSubclusterSpecArgs.builder()
.hostsCount(0)
.name("string")
.resources(DataprocClusterClusterConfigSubclusterSpecResourcesArgs.builder()
.diskSize(0)
.resourcePresetId("string")
.diskTypeId("string")
.build())
.role("string")
.subnetId("string")
.autoscalingConfig(DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs.builder()
.maxHostsCount(0)
.cpuUtilizationTarget(0)
.decommissionTimeout(0)
.measurementDuration(0)
.preemptible(false)
.stabilizationDuration(0)
.warmupDuration(0)
.build())
.id("string")
.build())
.hadoop(DataprocClusterClusterConfigHadoopArgs.builder()
.properties(Map.of("string", "string"))
.services("string")
.sshPublicKeys("string")
.build())
.versionId("string")
.build())
.serviceAccountId("string")
.bucket("string")
.deletionProtection(false)
.description("string")
.folderId("string")
.hostGroupIds("string")
.labels(Map.of("string", "string"))
.name("string")
.securityGroupIds("string")
.uiProxy(false)
.zoneId("string")
.build());
dataproc_cluster_resource = yandex.DataprocCluster("dataprocClusterResource",
cluster_config=yandex.DataprocClusterClusterConfigArgs(
subcluster_specs=[yandex.DataprocClusterClusterConfigSubclusterSpecArgs(
hosts_count=0,
name="string",
resources=yandex.DataprocClusterClusterConfigSubclusterSpecResourcesArgs(
disk_size=0,
resource_preset_id="string",
disk_type_id="string",
),
role="string",
subnet_id="string",
autoscaling_config=yandex.DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs(
max_hosts_count=0,
cpu_utilization_target=0,
decommission_timeout=0,
measurement_duration=0,
preemptible=False,
stabilization_duration=0,
warmup_duration=0,
),
id="string",
)],
hadoop=yandex.DataprocClusterClusterConfigHadoopArgs(
properties={
"string": "string",
},
services=["string"],
ssh_public_keys=["string"],
),
version_id="string",
),
service_account_id="string",
bucket="string",
deletion_protection=False,
description="string",
folder_id="string",
host_group_ids=["string"],
labels={
"string": "string",
},
name="string",
security_group_ids=["string"],
ui_proxy=False,
zone_id="string")
const dataprocClusterResource = new yandex.DataprocCluster("dataprocClusterResource", {
clusterConfig: {
subclusterSpecs: [{
hostsCount: 0,
name: "string",
resources: {
diskSize: 0,
resourcePresetId: "string",
diskTypeId: "string",
},
role: "string",
subnetId: "string",
autoscalingConfig: {
maxHostsCount: 0,
cpuUtilizationTarget: 0,
decommissionTimeout: 0,
measurementDuration: 0,
preemptible: false,
stabilizationDuration: 0,
warmupDuration: 0,
},
id: "string",
}],
hadoop: {
properties: {
string: "string",
},
services: ["string"],
sshPublicKeys: ["string"],
},
versionId: "string",
},
serviceAccountId: "string",
bucket: "string",
deletionProtection: false,
description: "string",
folderId: "string",
hostGroupIds: ["string"],
labels: {
string: "string",
},
name: "string",
securityGroupIds: ["string"],
uiProxy: false,
zoneId: "string",
});
type: yandex:DataprocCluster
properties:
bucket: string
clusterConfig:
hadoop:
properties:
string: string
services:
- string
sshPublicKeys:
- string
subclusterSpecs:
- autoscalingConfig:
cpuUtilizationTarget: 0
decommissionTimeout: 0
maxHostsCount: 0
measurementDuration: 0
preemptible: false
stabilizationDuration: 0
warmupDuration: 0
hostsCount: 0
id: string
name: string
resources:
diskSize: 0
diskTypeId: string
resourcePresetId: string
role: string
subnetId: string
versionId: string
deletionProtection: false
description: string
folderId: string
hostGroupIds:
- string
labels:
string: string
name: string
securityGroupIds:
- string
serviceAccountId: string
uiProxy: false
zoneId: string
DataprocCluster Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
The DataprocCluster resource accepts the following input properties:
- Cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- Service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - Bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - Deletion
Protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - Description string
- Description of the Data Proc cluster.
- Folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- Host
Group List<string>Ids - A list of host group IDs to place VMs of the cluster on.
- Labels Dictionary<string, string>
- A set of key/value label pairs to assign to the Data Proc cluster.
- Name string
- Name of the Data Proc subcluster.
- Security
Group List<string>Ids - A list of security group IDs that the cluster belongs to.
- Ui
Proxy bool - Whether to enable UI Proxy feature.
- Zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- Cluster
Config DataprocCluster Cluster Config Args - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- Service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - Bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - Deletion
Protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - Description string
- Description of the Data Proc cluster.
- Folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- Host
Group []stringIds - A list of host group IDs to place VMs of the cluster on.
- Labels map[string]string
- A set of key/value label pairs to assign to the Data Proc cluster.
- Name string
- Name of the Data Proc subcluster.
- Security
Group []stringIds - A list of security group IDs that the cluster belongs to.
- Ui
Proxy bool - Whether to enable UI Proxy feature.
- Zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- service
Account StringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - bucket String
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - deletion
Protection Boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description String
- Description of the Data Proc cluster.
- folder
Id String - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group List<String>Ids - A list of host group IDs to place VMs of the cluster on.
- labels Map<String,String>
- A set of key/value label pairs to assign to the Data Proc cluster.
- name String
- Name of the Data Proc subcluster.
- security
Group List<String>Ids - A list of security group IDs that the cluster belongs to.
- ui
Proxy Boolean - Whether to enable UI Proxy feature.
- zone
Id String - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - deletion
Protection boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description string
- Description of the Data Proc cluster.
- folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group string[]Ids - A list of host group IDs to place VMs of the cluster on.
- labels {[key: string]: string}
- A set of key/value label pairs to assign to the Data Proc cluster.
- name string
- Name of the Data Proc subcluster.
- security
Group string[]Ids - A list of security group IDs that the cluster belongs to.
- ui
Proxy boolean - Whether to enable UI Proxy feature.
- zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- cluster_
config DataprocCluster Cluster Config Args - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- service_
account_ strid - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - bucket str
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - deletion_
protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description str
- Description of the Data Proc cluster.
- folder_
id str - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host_
group_ Sequence[str]ids - A list of host group IDs to place VMs of the cluster on.
- labels Mapping[str, str]
- A set of key/value label pairs to assign to the Data Proc cluster.
- name str
- Name of the Data Proc subcluster.
- security_
group_ Sequence[str]ids - A list of security group IDs that the cluster belongs to.
- ui_
proxy bool - Whether to enable UI Proxy feature.
- zone_
id str - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- cluster
Config Property Map - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- service
Account StringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - bucket String
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - deletion
Protection Boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description String
- Description of the Data Proc cluster.
- folder
Id String - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group List<String>Ids - A list of host group IDs to place VMs of the cluster on.
- labels Map<String>
- A set of key/value label pairs to assign to the Data Proc cluster.
- name String
- Name of the Data Proc subcluster.
- security
Group List<String>Ids - A list of security group IDs that the cluster belongs to.
- ui
Proxy Boolean - Whether to enable UI Proxy feature.
- zone
Id String - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
Outputs
All input properties are implicitly available as output properties. Additionally, the DataprocCluster resource produces the following output properties:
- created_
at str - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- id str
- The provider-assigned unique ID for this managed resource.
Look up Existing DataprocCluster Resource
Get an existing DataprocCluster 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?: DataprocClusterState, opts?: CustomResourceOptions): DataprocCluster
@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None,
bucket: Optional[str] = None,
cluster_config: Optional[DataprocClusterClusterConfigArgs] = None,
created_at: Optional[str] = None,
deletion_protection: Optional[bool] = None,
description: Optional[str] = None,
folder_id: Optional[str] = None,
host_group_ids: Optional[Sequence[str]] = None,
labels: Optional[Mapping[str, str]] = None,
name: Optional[str] = None,
security_group_ids: Optional[Sequence[str]] = None,
service_account_id: Optional[str] = None,
ui_proxy: Optional[bool] = None,
zone_id: Optional[str] = None) -> DataprocCluster
func GetDataprocCluster(ctx *Context, name string, id IDInput, state *DataprocClusterState, opts ...ResourceOption) (*DataprocCluster, error)
public static DataprocCluster Get(string name, Input<string> id, DataprocClusterState? state, CustomResourceOptions? opts = null)
public static DataprocCluster get(String name, Output<String> id, DataprocClusterState state, CustomResourceOptions options)
Resource lookup is not supported in YAML
- 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.
- Bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - Cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- Created
At string - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- Deletion
Protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - Description string
- Description of the Data Proc cluster.
- Folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- Host
Group List<string>Ids - A list of host group IDs to place VMs of the cluster on.
- Labels Dictionary<string, string>
- A set of key/value label pairs to assign to the Data Proc cluster.
- Name string
- Name of the Data Proc subcluster.
- Security
Group List<string>Ids - A list of security group IDs that the cluster belongs to.
- Service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - Ui
Proxy bool - Whether to enable UI Proxy feature.
- Zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- Bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - Cluster
Config DataprocCluster Cluster Config Args - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- Created
At string - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- Deletion
Protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - Description string
- Description of the Data Proc cluster.
- Folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- Host
Group []stringIds - A list of host group IDs to place VMs of the cluster on.
- Labels map[string]string
- A set of key/value label pairs to assign to the Data Proc cluster.
- Name string
- Name of the Data Proc subcluster.
- Security
Group []stringIds - A list of security group IDs that the cluster belongs to.
- Service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - Ui
Proxy bool - Whether to enable UI Proxy feature.
- Zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- bucket String
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- created
At String - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- deletion
Protection Boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description String
- Description of the Data Proc cluster.
- folder
Id String - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group List<String>Ids - A list of host group IDs to place VMs of the cluster on.
- labels Map<String,String>
- A set of key/value label pairs to assign to the Data Proc cluster.
- name String
- Name of the Data Proc subcluster.
- security
Group List<String>Ids - A list of security group IDs that the cluster belongs to.
- service
Account StringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - ui
Proxy Boolean - Whether to enable UI Proxy feature.
- zone
Id String - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- bucket string
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - cluster
Config DataprocCluster Cluster Config - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- created
At string - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- deletion
Protection boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description string
- Description of the Data Proc cluster.
- folder
Id string - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group string[]Ids - A list of host group IDs to place VMs of the cluster on.
- labels {[key: string]: string}
- A set of key/value label pairs to assign to the Data Proc cluster.
- name string
- Name of the Data Proc subcluster.
- security
Group string[]Ids - A list of security group IDs that the cluster belongs to.
- service
Account stringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - ui
Proxy boolean - Whether to enable UI Proxy feature.
- zone
Id string - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- bucket str
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - cluster_
config DataprocCluster Cluster Config Args - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- created_
at str - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- deletion_
protection bool - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description str
- Description of the Data Proc cluster.
- folder_
id str - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host_
group_ Sequence[str]ids - A list of host group IDs to place VMs of the cluster on.
- labels Mapping[str, str]
- A set of key/value label pairs to assign to the Data Proc cluster.
- name str
- Name of the Data Proc subcluster.
- security_
group_ Sequence[str]ids - A list of security group IDs that the cluster belongs to.
- service_
account_ strid - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - ui_
proxy bool - Whether to enable UI Proxy feature.
- zone_
id str - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
- bucket String
- Name of the Object Storage bucket to use for Data Proc jobs. Data Proc Agent saves output of job driver's process to specified bucket. In order for this to work service account (specified by the
service_account_id
argument) should be given permission to create objects within this bucket. - cluster
Config Property Map - Configuration and resources for hosts that should be created with the cluster. The structure is documented below.
- created
At String - (Computed) The Data Proc cluster creation timestamp.
cluster_config.0.subcluster_spec.X.id
- (Computed) ID of the subcluster.
- deletion
Protection Boolean - Inhibits deletion of the cluster. Can be either
true
orfalse
. - description String
- Description of the Data Proc cluster.
- folder
Id String - ID of the folder to create a cluster in. If it is not provided, the default provider folder is used.
- host
Group List<String>Ids - A list of host group IDs to place VMs of the cluster on.
- labels Map<String>
- A set of key/value label pairs to assign to the Data Proc cluster.
- name String
- Name of the Data Proc subcluster.
- security
Group List<String>Ids - A list of security group IDs that the cluster belongs to.
- service
Account StringId - Service account to be used by the Data Proc agent to access resources of Yandex.Cloud. Selected service account should have
mdb.dataproc.agent
role on the folder where the Data Proc cluster will be located. - ui
Proxy Boolean - Whether to enable UI Proxy feature.
- zone
Id String - ID of the availability zone to create cluster in. If it is not provided, the default provider zone is used.
Supporting Types
DataprocClusterClusterConfig, DataprocClusterClusterConfigArgs
- Subcluster
Specs List<DataprocCluster Cluster Config Subcluster Spec> - Configuration of the Data Proc subcluster. The structure is documented below.
- Hadoop
Dataproc
Cluster Cluster Config Hadoop - Data Proc specific options. The structure is documented below.
- Version
Id string - Version of Data Proc image.
- Subcluster
Specs []DataprocCluster Cluster Config Subcluster Spec - Configuration of the Data Proc subcluster. The structure is documented below.
- Hadoop
Dataproc
Cluster Cluster Config Hadoop - Data Proc specific options. The structure is documented below.
- Version
Id string - Version of Data Proc image.
- subcluster
Specs List<DataprocCluster Cluster Config Subcluster Spec> - Configuration of the Data Proc subcluster. The structure is documented below.
- hadoop
Dataproc
Cluster Cluster Config Hadoop - Data Proc specific options. The structure is documented below.
- version
Id String - Version of Data Proc image.
- subcluster
Specs DataprocCluster Cluster Config Subcluster Spec[] - Configuration of the Data Proc subcluster. The structure is documented below.
- hadoop
Dataproc
Cluster Cluster Config Hadoop - Data Proc specific options. The structure is documented below.
- version
Id string - Version of Data Proc image.
- subcluster_
specs Sequence[DataprocCluster Cluster Config Subcluster Spec] - Configuration of the Data Proc subcluster. The structure is documented below.
- hadoop
Dataproc
Cluster Cluster Config Hadoop - Data Proc specific options. The structure is documented below.
- version_
id str - Version of Data Proc image.
- subcluster
Specs List<Property Map> - Configuration of the Data Proc subcluster. The structure is documented below.
- hadoop Property Map
- Data Proc specific options. The structure is documented below.
- version
Id String - Version of Data Proc image.
DataprocClusterClusterConfigHadoop, DataprocClusterClusterConfigHadoopArgs
- Properties Dictionary<string, string>
- A set of key/value pairs that are used to configure cluster services.
- Services List<string>
- List of services to run on Data Proc cluster.
- Ssh
Public List<string>Keys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
- Properties map[string]string
- A set of key/value pairs that are used to configure cluster services.
- Services []string
- List of services to run on Data Proc cluster.
- Ssh
Public []stringKeys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
- properties Map<String,String>
- A set of key/value pairs that are used to configure cluster services.
- services List<String>
- List of services to run on Data Proc cluster.
- ssh
Public List<String>Keys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
- properties {[key: string]: string}
- A set of key/value pairs that are used to configure cluster services.
- services string[]
- List of services to run on Data Proc cluster.
- ssh
Public string[]Keys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
- properties Mapping[str, str]
- A set of key/value pairs that are used to configure cluster services.
- services Sequence[str]
- List of services to run on Data Proc cluster.
- ssh_
public_ Sequence[str]keys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
- properties Map<String>
- A set of key/value pairs that are used to configure cluster services.
- services List<String>
- List of services to run on Data Proc cluster.
- ssh
Public List<String>Keys - List of SSH public keys to put to the hosts of the cluster. For information on how to connect to the cluster, see the official documentation.
DataprocClusterClusterConfigSubclusterSpec, DataprocClusterClusterConfigSubclusterSpecArgs
- Hosts
Count int - Number of hosts within Data Proc subcluster.
- Name string
- Name of the Data Proc subcluster.
- Resources
Dataproc
Cluster Cluster Config Subcluster Spec Resources - Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- Role string
- Role of the subcluster in the Data Proc cluster.
- Subnet
Id string - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- Autoscaling
Config DataprocCluster Cluster Config Subcluster Spec Autoscaling Config - Autoscaling configuration for compute subclusters.
- Id string
- (Computed) ID of a new Data Proc cluster.
- Hosts
Count int - Number of hosts within Data Proc subcluster.
- Name string
- Name of the Data Proc subcluster.
- Resources
Dataproc
Cluster Cluster Config Subcluster Spec Resources - Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- Role string
- Role of the subcluster in the Data Proc cluster.
- Subnet
Id string - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- Autoscaling
Config DataprocCluster Cluster Config Subcluster Spec Autoscaling Config - Autoscaling configuration for compute subclusters.
- Id string
- (Computed) ID of a new Data Proc cluster.
- hosts
Count Integer - Number of hosts within Data Proc subcluster.
- name String
- Name of the Data Proc subcluster.
- resources
Dataproc
Cluster Cluster Config Subcluster Spec Resources - Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- role String
- Role of the subcluster in the Data Proc cluster.
- subnet
Id String - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- autoscaling
Config DataprocCluster Cluster Config Subcluster Spec Autoscaling Config - Autoscaling configuration for compute subclusters.
- id String
- (Computed) ID of a new Data Proc cluster.
- hosts
Count number - Number of hosts within Data Proc subcluster.
- name string
- Name of the Data Proc subcluster.
- resources
Dataproc
Cluster Cluster Config Subcluster Spec Resources - Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- role string
- Role of the subcluster in the Data Proc cluster.
- subnet
Id string - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- autoscaling
Config DataprocCluster Cluster Config Subcluster Spec Autoscaling Config - Autoscaling configuration for compute subclusters.
- id string
- (Computed) ID of a new Data Proc cluster.
- hosts_
count int - Number of hosts within Data Proc subcluster.
- name str
- Name of the Data Proc subcluster.
- resources
Dataproc
Cluster Cluster Config Subcluster Spec Resources - Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- role str
- Role of the subcluster in the Data Proc cluster.
- subnet_
id str - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- autoscaling_
config DataprocCluster Cluster Config Subcluster Spec Autoscaling Config - Autoscaling configuration for compute subclusters.
- id str
- (Computed) ID of a new Data Proc cluster.
- hosts
Count Number - Number of hosts within Data Proc subcluster.
- name String
- Name of the Data Proc subcluster.
- resources Property Map
- Resources allocated to each host of the Data Proc subcluster. The structure is documented below.
- role String
- Role of the subcluster in the Data Proc cluster.
- subnet
Id String - The ID of the subnet, to which hosts of the subcluster belong. Subnets of all the subclusters must belong to the same VPC network.
- autoscaling
Config Property Map - Autoscaling configuration for compute subclusters.
- id String
- (Computed) ID of a new Data Proc cluster.
DataprocClusterClusterConfigSubclusterSpecAutoscalingConfig, DataprocClusterClusterConfigSubclusterSpecAutoscalingConfigArgs
- Max
Hosts intCount - Maximum number of nodes in autoscaling subclusters.
- Cpu
Utilization doubleTarget - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- Decommission
Timeout int - Timeout to gracefully decommission nodes during downscaling. In seconds.
- Measurement
Duration int - Time in seconds allotted for averaging metrics.
- Preemptible bool
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- Stabilization
Duration int - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- Warmup
Duration int - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
- Max
Hosts intCount - Maximum number of nodes in autoscaling subclusters.
- Cpu
Utilization float64Target - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- Decommission
Timeout int - Timeout to gracefully decommission nodes during downscaling. In seconds.
- Measurement
Duration int - Time in seconds allotted for averaging metrics.
- Preemptible bool
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- Stabilization
Duration int - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- Warmup
Duration int - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
- max
Hosts IntegerCount - Maximum number of nodes in autoscaling subclusters.
- cpu
Utilization DoubleTarget - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- decommission
Timeout Integer - Timeout to gracefully decommission nodes during downscaling. In seconds.
- measurement
Duration Integer - Time in seconds allotted for averaging metrics.
- preemptible Boolean
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- stabilization
Duration Integer - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- warmup
Duration Integer - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
- max
Hosts numberCount - Maximum number of nodes in autoscaling subclusters.
- cpu
Utilization numberTarget - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- decommission
Timeout number - Timeout to gracefully decommission nodes during downscaling. In seconds.
- measurement
Duration number - Time in seconds allotted for averaging metrics.
- preemptible boolean
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- stabilization
Duration number - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- warmup
Duration number - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
- max_
hosts_ intcount - Maximum number of nodes in autoscaling subclusters.
- cpu_
utilization_ floattarget - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- decommission_
timeout int - Timeout to gracefully decommission nodes during downscaling. In seconds.
- measurement_
duration int - Time in seconds allotted for averaging metrics.
- preemptible bool
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- stabilization_
duration int - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- warmup_
duration int - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
- max
Hosts NumberCount - Maximum number of nodes in autoscaling subclusters.
- cpu
Utilization NumberTarget - Defines an autoscaling rule based on the average CPU utilization of the instance group. If not set default autoscaling metric will be used.
- decommission
Timeout Number - Timeout to gracefully decommission nodes during downscaling. In seconds.
- measurement
Duration Number - Time in seconds allotted for averaging metrics.
- preemptible Boolean
- Bool flag -- whether to use preemptible compute instances. Preemptible instances are stopped at least once every 24 hours, and can be stopped at any time if their resources are needed by Compute. For more information, see Preemptible Virtual Machines.
- stabilization
Duration Number - Minimum amount of time in seconds allotted for monitoring before Instance Groups can reduce the number of instances in the group. During this time, the group size doesn't decrease, even if the new metric values indicate that it should.
- warmup
Duration Number - The warmup time of the instance in seconds. During this time, traffic is sent to the instance, but instance metrics are not collected.
DataprocClusterClusterConfigSubclusterSpecResources, DataprocClusterClusterConfigSubclusterSpecResourcesArgs
- Disk
Size int - Volume of the storage available to a host, in gigabytes.
- Resource
Preset stringId - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- Disk
Type stringId - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
- Disk
Size int - Volume of the storage available to a host, in gigabytes.
- Resource
Preset stringId - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- Disk
Type stringId - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
- disk
Size Integer - Volume of the storage available to a host, in gigabytes.
- resource
Preset StringId - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- disk
Type StringId - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
- disk
Size number - Volume of the storage available to a host, in gigabytes.
- resource
Preset stringId - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- disk
Type stringId - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
- disk_
size int - Volume of the storage available to a host, in gigabytes.
- resource_
preset_ strid - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- disk_
type_ strid - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
- disk
Size Number - Volume of the storage available to a host, in gigabytes.
- resource
Preset StringId - The ID of the preset for computational resources available to a host. All available presets are listed in the documentation.
- disk
Type StringId - Type of the storage of a host. One of
network-hdd
(default) ornetwork-ssd
.
Import
A cluster can be imported using the id
of the resource, e.g.
$ pulumi import yandex:index/dataprocCluster:DataprocCluster foo cluster_id
To learn more about importing existing cloud resources, see Importing resources.
Package Details
- Repository
- Yandex pulumi/pulumi-yandex
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the
yandex
Terraform Provider.