Class: Aws::SageMaker::Types::InferenceComponentRollingUpdatePolicy

Inherits:
Struct
  • Object
show all
Includes:
Aws::Structure
Defined in:
lib/aws-sdk-sagemaker/types.rb

Overview

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

See Also:

Constant Summary collapse

SENSITIVE = 
[]

Instance Attribute Summary collapse

Instance Attribute Details

#maximum_batch_size ⇒ Types::InferenceComponentCapacitySize

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:



25810
25811
25812
25813
25814
25815
25816
25817
 
# File 'lib/aws-sdk-sagemaker/types.rb', line 25810

class InferenceComponentRollingUpdatePolicy < Struct.new(
  :maximum_batch_size,
  :wait_interval_in_seconds,
  :maximum_execution_timeout_in_seconds,
  :rollback_maximum_batch_size)
  SENSITIVE = []
  include Aws::Structure
end

#maximum_execution_timeout_in_seconds ⇒ Integer

The time limit for the total deployment. Exceeding this limit causes a timeout.

Returns:

  • (Integer) 


25810
25811
25812
25813
25814
25815
25816
25817
 
# File 'lib/aws-sdk-sagemaker/types.rb', line 25810

class InferenceComponentRollingUpdatePolicy < Struct.new(
  :maximum_batch_size,
  :wait_interval_in_seconds,
  :maximum_execution_timeout_in_seconds,
  :rollback_maximum_batch_size)
  SENSITIVE = []
  include Aws::Structure
end

#rollback_maximum_batch_size ⇒ Types::InferenceComponentCapacitySize

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:



25810
25811
25812
25813
25814
25815
25816
25817
 
# File 'lib/aws-sdk-sagemaker/types.rb', line 25810

class InferenceComponentRollingUpdatePolicy < Struct.new(
  :maximum_batch_size,
  :wait_interval_in_seconds,
  :maximum_execution_timeout_in_seconds,
  :rollback_maximum_batch_size)
  SENSITIVE = []
  include Aws::Structure
end

#wait_interval_in_seconds ⇒ Integer

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

Returns:

  • (Integer) 


25810
25811
25812
25813
25814
25815
25816
25817
 
# File 'lib/aws-sdk-sagemaker/types.rb', line 25810

class InferenceComponentRollingUpdatePolicy < Struct.new(
  :maximum_batch_size,
  :wait_interval_in_seconds,
  :maximum_execution_timeout_in_seconds,
  :rollback_maximum_batch_size)
  SENSITIVE = []
  include Aws::Structure
end