Amazon Web Services Parallel Computing Service (Amazon Web Services PCS) is a managed service that makes it easier for you to run and scale your high performance computing (HPC) workloads, and build scientific and engineering models on Amazon Web Services using Slurm. For more information, see the Amazon Web Services Parallel Computing Service User Guide .

This reference describes the actions and data types of the service management API. You can use the Amazon Web Services SDKs to call the API actions in software, or use the Command Line Interface (CLI) to call the API actions manually. These API actions manage the service through an Amazon Web Services account.

The API actions operate on Amazon Web Services PCS resources. A resource is an entity in Amazon Web Services that you can work with. Amazon Web Services services create resources when you use the features of the service. Examples of Amazon Web Services PCS resources include clusters, compute node groups, and queues. For more information about resources in Amazon Web Services, see Resource  in the Resource Explorer User Guide.

An Amazon Web Services PCS compute node is an Amazon EC2 instance. You don't launch compute nodes directly. Amazon Web Services PCS uses configuration information that you provide to launch compute nodes in your Amazon Web Services account. You receive billing charges for your running compute nodes. Amazon Web Services PCS automatically terminates your compute nodes when you delete the Amazon Web Services PCS resources related to those compute nodes.

Installation

NPM
npm install @aws-sdk/client-pcs
Yarn
yarn add @aws-sdk/client-pcs
pnpm
pnpm add @aws-sdk/client-pcs

PCSClient Operations

Command
Summary
CreateClusterCommand

Creates a cluster in your account. Amazon Web Services PCS creates the cluster controller in a service-owned account. The cluster controller communicates with the cluster resources in your account. The subnets and security groups for the cluster must already exist before you use this API action.

It takes time for Amazon Web Services PCS to create the cluster. The cluster is in a Creating state until it is ready to use. There can only be 1 cluster in a Creating state per Amazon Web Services Region per Amazon Web Services account. CreateCluster fails with a ServiceQuotaExceededException if there is already a cluster in a Creating state.

CreateComputeNodeGroupCommand

Creates a managed set of compute nodes. You associate a compute node group with a cluster through 1 or more Amazon Web Services PCS queues or as part of the login fleet. A compute node group includes the definition of the compute properties and lifecycle management. Amazon Web Services PCS uses the information you provide to this API action to launch compute nodes in your account. You can only specify subnets in the same Amazon VPC as your cluster. You receive billing charges for the compute nodes that Amazon Web Services PCS launches in your account. You must already have a launch template before you call this API. For more information, see Launch an instance from a launch template  in the Amazon Elastic Compute Cloud User Guide for Linux Instances.

CreateQueueCommand

Creates a job queue. You must associate 1 or more compute node groups with the queue. You can associate 1 compute node group with multiple queues.

DeleteClusterCommand

Deletes a cluster and all its linked resources. You must delete all queues and compute node groups associated with the cluster before you can delete the cluster.

DeleteComputeNodeGroupCommand

Deletes a compute node group. You must delete all queues associated with the compute node group first.

DeleteQueueCommand

Deletes a job queue. If the compute node group associated with this queue isn't associated with any other queues, Amazon Web Services PCS terminates all the compute nodes for this queue.

GetClusterCommand

Returns detailed information about a running cluster in your account. This API action provides networking information, endpoint information for communication with the scheduler, and provisioning status.

GetComputeNodeGroupCommand

Returns detailed information about a compute node group. This API action provides networking information, EC2 instance type, compute node group status, and scheduler (such as Slurm) configuration.

GetQueueCommand

Returns detailed information about a queue. The information includes the compute node groups that the queue uses to schedule jobs.

ListClustersCommand

Returns a list of running clusters in your account.

ListComputeNodeGroupsCommand

Returns a list of all compute node groups associated with a cluster.

ListQueuesCommand

Returns a list of all queues associated with a cluster.

ListTagsForResourceCommand

Returns a list of all tags on an Amazon Web Services PCS resource.

RegisterComputeNodeGroupInstanceCommand

This API action isn't intended for you to use.

Amazon Web Services PCS uses this API action to register the compute nodes it launches in your account.

TagResourceCommand

Adds or edits tags on an Amazon Web Services PCS resource. Each tag consists of a tag key and a tag value. The tag key and tag value are case-sensitive strings. The tag value can be an empty (null) string. To add a tag, specify a new tag key and a tag value. To edit a tag, specify an existing tag key and a new tag value.

UntagResourceCommand

Deletes tags from an Amazon Web Services PCS resource. To delete a tag, specify the tag key and the Amazon Resource Name (ARN) of the Amazon Web Services PCS resource.

UpdateComputeNodeGroupCommand

Updates a compute node group. You can update many of the fields related to your compute node group including the configurations for networking, compute nodes, and settings specific to your scheduler (such as Slurm).

UpdateQueueCommand

Updates the compute node group configuration of a queue. Use this API to change the compute node groups that the queue can send jobs to.

PCSClient Configuration

Parameter
Type
Description
defaultsMode
Optional
DefaultsMode | Provider<DefaultsMode>
The @smithy/smithy-client#DefaultsMode that will be used to determine how certain default configuration options are resolved in the SDK.
disableHostPrefix
Optional
boolean
Disable dynamically changing the endpoint of the client based on the hostPrefix trait of an operation.
extensions
Optional
RuntimeExtension[]
Optional extensions
logger
Optional
Logger
Optional logger for logging debug/info/warn/error.
maxAttempts
Optional
number | Provider<number>
Value for how many times a request will be made at most in case of retry.
profile
Optional
string
Setting a client profile is similar to setting a value for the AWS_PROFILE environment variable. Setting a profile on a client in code only affects the single client instance, unlike AWS_PROFILE.When set, and only for environments where an AWS configuration file exists, fields configurable by this file will be retrieved from the specified profile within that file. Conflicting code configuration and environment variables will still have higher priority.For client credential resolution that involves checking the AWS configuration file, the client's profile (this value) will be used unless a different profile is set in the credential provider options.
region
Optional
string | Provider<string>
The AWS region to which this client will send requests
requestHandler
Optional
__HttpHandlerUserInput
The HTTP handler to use or its constructor options. Fetch in browser and Https in Nodejs.
retryMode
Optional
string | Provider<string>
Specifies which retry algorithm to use.
useDualstackEndpoint
Optional
boolean | Provider<boolean>
Enables IPv6/IPv4 dualstack endpoint.
useFipsEndpoint
Optional
boolean | Provider<boolean>
Enables FIPS compatible endpoints.
Additional config fields are described in the full configuration type: PCSClientConfig