/AWS1/CL_SGMSCAPOLICYMETRIC

The metric for a scaling policy.

CONSTRUCTOR

IMPORTING

Optional arguments:

iv_invocationsperinstance TYPE /AWS1/SGMINTEGER /AWS1/SGMINTEGER

The number of invocations sent to a model, normalized by InstanceCount in each ProductionVariant. 1/numberOfInstances is sent as the value on each request, where numberOfInstances is the number of active instances for the ProductionVariant behind the endpoint at the time of the request.

iv_modellatency TYPE /AWS1/SGMINTEGER /AWS1/SGMINTEGER

The interval of time taken by a model to respond as viewed from SageMaker. This interval includes the local communication times taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.

---

Queryable Attributes

InvocationsPerInstance

The number of invocations sent to a model, normalized by InstanceCount in each ProductionVariant. 1/numberOfInstances is sent as the value on each request, where numberOfInstances is the number of active instances for the ProductionVariant behind the endpoint at the time of the request.

Accessible with the following methods

Method	Description
GET_INVOCATIONSPERINSTANCE()	Getter for INVOCATIONSPERINSTANCE, with configurable default
ASK_INVOCATIONSPERINSTANCE()	Getter for INVOCATIONSPERINSTANCE w/ exceptions if field has
HAS_INVOCATIONSPERINSTANCE()	Determine if INVOCATIONSPERINSTANCE has a value

ModelLatency

The interval of time taken by a model to respond as viewed from SageMaker. This interval includes the local communication times taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.

Accessible with the following methods

Method	Description
GET_MODELLATENCY()	Getter for MODELLATENCY, with configurable default
ASK_MODELLATENCY()	Getter for MODELLATENCY w/ exceptions if field has no value
HAS_MODELLATENCY()	Determine if MODELLATENCY has a value