@Generated(value="com.amazonaws:aws-java-sdk-code-generator") public class ScalingPolicyMetric extends Object implements Serializable, Cloneable, StructuredPojo
The metric for a scaling policy.
Constructor and Description |
---|
ScalingPolicyMetric() |
Modifier and Type | Method and Description |
---|---|
ScalingPolicyMetric |
clone() |
boolean |
equals(Object obj) |
Integer |
getInvocationsPerInstance()
The number of invocations sent to a model, normalized by
InstanceCount in each ProductionVariant. |
Integer |
getModelLatency()
The interval of time taken by a model to respond as viewed from SageMaker.
|
int |
hashCode() |
void |
marshall(ProtocolMarshaller protocolMarshaller)
Marshalls this structured data using the given
ProtocolMarshaller . |
void |
setInvocationsPerInstance(Integer invocationsPerInstance)
The number of invocations sent to a model, normalized by
InstanceCount in each ProductionVariant. |
void |
setModelLatency(Integer modelLatency)
The interval of time taken by a model to respond as viewed from SageMaker.
|
String |
toString()
Returns a string representation of this object.
|
ScalingPolicyMetric |
withInvocationsPerInstance(Integer invocationsPerInstance)
The number of invocations sent to a model, normalized by
InstanceCount in each ProductionVariant. |
ScalingPolicyMetric |
withModelLatency(Integer modelLatency)
The interval of time taken by a model to respond as viewed from SageMaker.
|
public void setInvocationsPerInstance(Integer 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.
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.public Integer getInvocationsPerInstance()
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.
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.public ScalingPolicyMetric withInvocationsPerInstance(Integer 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.
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.public void setModelLatency(Integer 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.
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.public Integer getModelLatency()
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.
public ScalingPolicyMetric withModelLatency(Integer 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.
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.public String toString()
toString
in class Object
Object.toString()
public ScalingPolicyMetric clone()
public void marshall(ProtocolMarshaller protocolMarshaller)
StructuredPojo
ProtocolMarshaller
.marshall
in interface StructuredPojo
protocolMarshaller
- Implementation of ProtocolMarshaller
used to marshall this object's data.