interface ScaleInPolicyProperty
| Language | Type name |
|---|---|
.NET | Amazon.CDK.CfnPropertyMixins.AWS.SageMaker.CfnEndpointConfigPropsMixin.ScaleInPolicyProperty |
Go | github.com/aws/aws-cdk-go/awscdkcfnpropertymixins/v2/awssagemaker#CfnEndpointConfigPropsMixin_ScaleInPolicyProperty |
Java | software.amazon.awscdk.cfnpropertymixins.services.sagemaker.CfnEndpointConfigPropsMixin.ScaleInPolicyProperty |
Python | aws_cdk.cfn_property_mixins.aws_sagemaker.CfnEndpointConfigPropsMixin.ScaleInPolicyProperty |
TypeScript | @aws-cdk/cfn-property-mixins » aws_sagemaker » CfnEndpointConfigPropsMixin » ScaleInPolicyProperty |
Specifies how the endpoint releases instances when managed instance scaling scales in.
Example
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from '@aws-cdk/cfn-property-mixins';
const scaleInPolicyProperty: sagemaker.CfnEndpointConfigPropsMixin.ScaleInPolicyProperty = {
cooldownInMinutes: 123,
maximumStepSize: 123,
strategy: 'strategy',
};
Properties
| Name | Type | Description |
|---|---|---|
| cooldown | number | The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. |
| maximum | number | The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. |
| strategy? | string | The strategy for scaling in instances. |
cooldownInMinutes?
Type:
number
(optional)
The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities.
Valid values are 5 to 1440. The default is 20.
maximumStepSize?
Type:
number
(optional)
The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation.
Valid values are 1 to 100. The default is 1.
strategy?
Type:
string
(optional)
The strategy for scaling in instances.
IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.

.NET
Go
Java
Python
TypeScript