Package software.amazon.awscdk.services.sagemaker

Interface CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty

All Superinterfaces:

software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Jsii$Proxy

Enclosing class:

CfnInferenceComponent

@Stability(Stable)
public static interface CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty
extends software.amazon.jsii.JsiiSerializable

Specifies a rolling deployment strategy for updating a SageMaker AI inference component.

Example:

 // The code below shows an example of how to instantiate this type.
 // The values are placeholders you should change.
 import software.amazon.awscdk.services.sagemaker.*;
 InferenceComponentRollingUpdatePolicyProperty inferenceComponentRollingUpdatePolicyProperty = InferenceComponentRollingUpdatePolicyProperty.builder()
         .maximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
                 .type("type")
                 .value(123)
                 .build())
         .maximumExecutionTimeoutInSeconds(123)
         .rollbackMaximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
                 .type("type")
                 .value(123)
                 .build())
         .waitIntervalInSeconds(123)
         .build();
 

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.html

Nested Class Summary

Nested Classes

Modifier and Type	Interface	Description
static final class	CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Builder	A builder for CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty
static final class	CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Jsii$Proxy	An implementation for CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty

Method Summary

Modifier and Type	Method	Description
static CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Builder	builder()
default Object	getMaximumBatchSize()	The batch size for each rolling step in the deployment process.
default Number	getMaximumExecutionTimeoutInSeconds()	The time limit for the total deployment.
default Object	getRollbackMaximumBatchSize()	The batch size for a rollback to the old endpoint fleet.
default Number	getWaitIntervalInSeconds()	The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

Method Details

getMaximumBatchSize

@Stability(Stable)
@Nullable
default Object getMaximumBatchSize()

The batch size for each rolling step in the deployment process.

For each step, SageMaker AI provisions capacity on the new endpoint fleet, routes traffic to that fleet, and terminates capacity on the old endpoint fleet. The value must be between 5% to 50% of the copy count of the inference component.

Returns union: either IResolvable or CfnInferenceComponent.InferenceComponentCapacitySizeProperty

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.html#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumbatchsize

getMaximumExecutionTimeoutInSeconds

@Stability(Stable)
@Nullable
default Number getMaximumExecutionTimeoutInSeconds()

The time limit for the total deployment.

Exceeding this limit causes a timeout.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.html#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-maximumexecutiontimeoutinseconds

getRollbackMaximumBatchSize

@Stability(Stable)
@Nullable
default Object getRollbackMaximumBatchSize()

The batch size for a rollback to the old endpoint fleet.

If this field is absent, the value is set to the default, which is 100% of the total capacity. When the default is used, SageMaker AI provisions the entire capacity of the old fleet at once during rollback.

Returns union: either IResolvable or CfnInferenceComponent.InferenceComponentCapacitySizeProperty

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.html#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-rollbackmaximumbatchsize

getWaitIntervalInSeconds

@Stability(Stable)
@Nullable
default Number getWaitIntervalInSeconds()

The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.

See Also:

• http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy.html#cfn-sagemaker-inferencecomponent-inferencecomponentrollingupdatepolicy-waitintervalinseconds

builder

@Stability(Stable)
static CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Builder builder()

Returns:

a CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty.Builder of CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty