Struct InferenceComponentRollingUpdatePolicy

#[non_exhaustive]
pub struct InferenceComponentRollingUpdatePolicy {
    pub maximum_batch_size: Option<InferenceComponentCapacitySize>,
    pub wait_interval_in_seconds: Option<i32>,
    pub maximum_execution_timeout_in_seconds: Option<i32>,
    pub rollback_maximum_batch_size: Option<InferenceComponentCapacitySize>,
}

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

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

maximum_batch_size: Option<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.

wait_interval_in_seconds: Option<i32>

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

maximum_execution_timeout_in_seconds: Option<i32>

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

rollback_maximum_batch_size: Option<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.

Implementations

impl InferenceComponentRollingUpdatePolicy

pub fn maximum_batch_size(&self) -> Option<&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.

pub fn wait_interval_in_seconds(&self) -> Option<i32>

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

pub fn maximum_execution_timeout_in_seconds(&self) -> Option<i32>

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

pub fn rollback_maximum_batch_size( &self, ) -> Option<&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.

impl InferenceComponentRollingUpdatePolicy

pub fn builder() -> InferenceComponentRollingUpdatePolicyBuilder

Creates a new builder-style object to manufacture InferenceComponentRollingUpdatePolicy.

Trait Implementations

impl Clone for InferenceComponentRollingUpdatePolicy

fn clone(&self) -> InferenceComponentRollingUpdatePolicy

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for InferenceComponentRollingUpdatePolicy

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for InferenceComponentRollingUpdatePolicy

fn eq(&self, other: &InferenceComponentRollingUpdatePolicy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for InferenceComponentRollingUpdatePolicy