class ScalableInstanceCount (construct) 🔹

Language	Type name
.NET	`Amazon.CDK.AWS.Sagemaker.Alpha.ScalableInstanceCount`
Go	`github.com/aws/aws-cdk-go/awscdksagemakeralpha/v2#ScalableInstanceCount`
Java	`software.amazon.awscdk.services.sagemaker.alpha.ScalableInstanceCount`
Python	`aws_cdk.aws_sagemaker_alpha.ScalableInstanceCount`
TypeScript (source)	`@aws-cdk/aws-sagemaker-alpha` » `ScalableInstanceCount`

Implements IConstruct, IDependable, IScalableTargetRef, IEnvironmentAware

A scalable sagemaker endpoint attribute.

Example

import * as sagemaker from '@aws-cdk/aws-sagemaker-alpha';

declare const model: sagemaker.Model;

const variantName = 'my-variant';
const endpointConfig = new sagemaker.EndpointConfig(this, 'EndpointConfig', {
  instanceProductionVariants: [
    {
      model: model,
      variantName: variantName,
    },
  ]
});

const endpoint = new sagemaker.Endpoint(this, 'Endpoint', { endpointConfig });
const productionVariant = endpoint.findInstanceProductionVariant(variantName);
const instanceCount = productionVariant.autoScaleInstanceCount({
  maxCapacity: 3
});
instanceCount.scaleOnInvocations('LimitRPS', {
  maxRequestsPerSecond: 30,
});

Initializer

new ScalableInstanceCount(scope: Construct, id: string, props: ScalableInstanceCountProps)

Parameters

scope Construct
id string
props ScalableInstanceCountProps

Constructs a new instance of the ScalableInstanceCount class.

Construct Props

Name	Type	Description
dimension🔹	`string`	Scalable dimension of the attribute.
maxCapacity🔹	`number`	Maximum capacity to scale to.
resourceId🔹	`string`	Resource ID of the attribute.
role🔹	`IRole`	Role to use for scaling.
serviceNamespace🔹	`ServiceNamespace`	Service namespace of the scalable attribute.
minCapacity?🔹	`number`	Minimum capacity to scale to.

dimension🔹

Type: string

Scalable dimension of the attribute.

maxCapacity🔹

Type: number

Maximum capacity to scale to.

resourceId🔹

Type: string

Resource ID of the attribute.

role🔹

Type: IRole

Role to use for scaling.

serviceNamespace🔹

Type: ServiceNamespace

Service namespace of the scalable attribute.

minCapacity?🔹

Type: number (optional, default: 1)

Minimum capacity to scale to.

Properties

Name	Type	Description
env🔹	`ResourceEnvironment`	The environment this resource belongs to.
node🔹	`Node`	The tree node.
scalableTargetRef🔹	`ScalableTargetReference`	A reference to a ScalableTarget resource.

env🔹

Type: ResourceEnvironment

The environment this resource belongs to.

For resources that are created and managed in a Stack (those created by creating new class instances like new Role(), new Bucket(), etc.), this is always the same as the environment of the stack they belong to.

For referenced resources (those obtained from referencing methods like Role.fromRoleArn(), Bucket.fromBucketName(), etc.), they might be different than the stack they were imported into.

node🔹

Type: Node

The tree node.

scalableTargetRef🔹

Type: ScalableTargetReference

A reference to a ScalableTarget resource.

Methods

Name	Description
scaleOnInvocations(id, props)🔹	Scales in or out to achieve a target requests per second per instance.
toString()🔹	Returns a string representation of this construct.

scaleOnInvocations(id, props)🔹

public scaleOnInvocations(id: string, props: InvocationsScalingProps): void