/AWS1/CL_SGMRECOMMENDATIONJO06

Specifies conditions for stopping a job. When a job reaches a stopping condition limit, SageMaker ends the job.

CONSTRUCTOR

IMPORTING

Optional arguments:

iv_maxinvocations TYPE /AWS1/SGMINTEGER /AWS1/SGMINTEGER

The maximum number of requests per minute expected for the endpoint.

it_modellatencythresholds TYPE /AWS1/CL_SGMMODELLATENCYTHRESH=>TT_MODELLATENCYTHRESHOLDS TT_MODELLATENCYTHRESHOLDS

The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time 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.

iv_flatinvocations TYPE /AWS1/SGMFLATINVOCATIONS /AWS1/SGMFLATINVOCATIONS

Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.

---

Queryable Attributes

MaxInvocations

The maximum number of requests per minute expected for the endpoint.

Accessible with the following methods

Method	Description
GET_MAXINVOCATIONS()	Getter for MAXINVOCATIONS, with configurable default
ASK_MAXINVOCATIONS()	Getter for MAXINVOCATIONS w/ exceptions if field has no valu
HAS_MAXINVOCATIONS()	Determine if MAXINVOCATIONS has a value

ModelLatencyThresholds

The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time 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_MODELLATENCYTHRESHOLDS()	Getter for MODELLATENCYTHRESHOLDS, with configurable default
ASK_MODELLATENCYTHRESHOLDS()	Getter for MODELLATENCYTHRESHOLDS w/ exceptions if field has
HAS_MODELLATENCYTHRESHOLDS()	Determine if MODELLATENCYTHRESHOLDS has a value

FlatInvocations

Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.

Accessible with the following methods

Method	Description
GET_FLATINVOCATIONS()	Getter for FLATINVOCATIONS, with configurable default
ASK_FLATINVOCATIONS()	Getter for FLATINVOCATIONS w/ exceptions if field has no val
HAS_FLATINVOCATIONS()	Determine if FLATINVOCATIONS has a value