Interface ProductionVariantManagedInstanceScalingScaleInPolicy.Builder

All Superinterfaces:

Buildable, CopyableBuilder<ProductionVariantManagedInstanceScalingScaleInPolicy.Builder,ProductionVariantManagedInstanceScalingScaleInPolicy>, SdkBuilder<ProductionVariantManagedInstanceScalingScaleInPolicy.Builder,ProductionVariantManagedInstanceScalingScaleInPolicy>, SdkPojo

Enclosing class:

ProductionVariantManagedInstanceScalingScaleInPolicy

@Mutable
@NotThreadSafe
public static interface ProductionVariantManagedInstanceScalingScaleInPolicy.Builder
extends SdkPojo, CopyableBuilder<ProductionVariantManagedInstanceScalingScaleInPolicy.Builder,ProductionVariantManagedInstanceScalingScaleInPolicy>

Method Summary

Modifier and Type	Method	Description
ProductionVariantManagedInstanceScalingScaleInPolicy.Builder	cooldownInMinutes(Integer cooldownInMinutes)	The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities.
ProductionVariantManagedInstanceScalingScaleInPolicy.Builder	maximumStepSize(Integer maximumStepSize)	The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation.
ProductionVariantManagedInstanceScalingScaleInPolicy.Builder	strategy(String strategy)	The strategy for scaling in instances.
ProductionVariantManagedInstanceScalingScaleInPolicy.Builder	strategy(ManagedInstanceScalingScaleInStrategy strategy)	The strategy for scaling in instances.

Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder

copy

Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder

applyMutation, build

Methods inherited from interface software.amazon.awssdk.core.SdkPojo

equalsBySdkFields, sdkFieldNameToField, sdkFields

Method Details

strategy

ProductionVariantManagedInstanceScalingScaleInPolicy.Builder strategy(String strategy)

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. Consolidation honors the scheduling configuration of each inference component. For example, if an inference component specifies Availability Zone balance, consolidation only proceeds when the resulting distribution does not increase the imbalance.

Parameters:

strategy - 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. Consolidation honors the scheduling configuration of each inference component. For example, if an inference component specifies Availability Zone balance, consolidation only proceeds when the resulting distribution does not increase the imbalance.

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

• ManagedInstanceScalingScaleInStrategy
• ManagedInstanceScalingScaleInStrategy

strategy

ProductionVariantManagedInstanceScalingScaleInPolicy.Builder strategy(ManagedInstanceScalingScaleInStrategy strategy)

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. Consolidation honors the scheduling configuration of each inference component. For example, if an inference component specifies Availability Zone balance, consolidation only proceeds when the resulting distribution does not increase the imbalance.

Parameters:

strategy - 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. Consolidation honors the scheduling configuration of each inference component. For example, if an inference component specifies Availability Zone balance, consolidation only proceeds when the resulting distribution does not increase the imbalance.

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

• ManagedInstanceScalingScaleInStrategy
• ManagedInstanceScalingScaleInStrategy

maximumStepSize

ProductionVariantManagedInstanceScalingScaleInPolicy.Builder maximumStepSize(Integer maximumStepSize)

The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation.

Default value: 1.

Parameters:

maximumStepSize - The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation.

Default value: 1.

Returns:

Returns a reference to this object so that method calls can be chained together.

cooldownInMinutes

ProductionVariantManagedInstanceScalingScaleInPolicy.Builder cooldownInMinutes(Integer cooldownInMinutes)

The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities.

Default value: 20.

Parameters:

cooldownInMinutes - The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities.

Default value: 20.

Returns:

Returns a reference to this object so that method calls can be chained together.