Skip to content

RollingUpdatePolicy

Source code in docs_src/capo_sagemaker/types/rolling_update_policy.py
class RollingUpdatePolicy(TypedDict, closed=True):
    maximum_batch_size: NotRequired["capo_sagemaker.types.capacity_size.CapacitySize"]
    """<p>Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count.</p>"""
    wait_interval_in_seconds: NotRequired[
        "capo_sagemaker.types.wait_interval_in_seconds.WaitIntervalInSeconds"
    ]
    """<p>The length of the baking period, during which SageMaker monitors alarms for each batch on the new fleet.</p>"""
    maximum_execution_timeout_in_seconds: NotRequired[
        "capo_sagemaker.types.maximum_execution_timeout_in_seconds.MaximumExecutionTimeoutInSeconds"
    ]
    """<p>The time limit for the total deployment. Exceeding this limit causes a timeout.</p>"""
    rollback_maximum_batch_size: NotRequired[
        "capo_sagemaker.types.capacity_size.CapacitySize"
    ]
    """<p>Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback.</p>"""

maximum_batch_size instance-attribute

maximum_batch_size: NotRequired[CapacitySize]

Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count.

maximum_execution_timeout_in_seconds instance-attribute

maximum_execution_timeout_in_seconds: NotRequired[MaximumExecutionTimeoutInSeconds]

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

rollback_maximum_batch_size instance-attribute

rollback_maximum_batch_size: NotRequired[CapacitySize]

Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback.

wait_interval_in_seconds instance-attribute

wait_interval_in_seconds: NotRequired[WaitIntervalInSeconds]

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