Get Scaling Configuration Recommendation
sagemaker_get_scaling_configuration_recommendation | R Documentation |
Starts an Amazon SageMaker Inference Recommender autoscaling recommendation job¶
Description¶
Starts an Amazon SageMaker Inference Recommender autoscaling recommendation job. Returns recommendations for autoscaling policies that you can apply to your SageMaker endpoint.
Usage¶
sagemaker_get_scaling_configuration_recommendation(
InferenceRecommendationsJobName, RecommendationId, EndpointName,
TargetCpuUtilizationPerCore, ScalingPolicyObjective)
Arguments¶
InferenceRecommendationsJobName
[required] The name of a previously completed Inference Recommender job.
RecommendationId
The recommendation ID of a previously completed inference recommendation. This ID should come from one of the recommendations returned by the job specified in the
InferenceRecommendationsJobName
field.Specify either this field or the
EndpointName
field.EndpointName
The name of an endpoint benchmarked during a previously completed inference recommendation job. This name should come from one of the recommendations returned by the job specified in the
InferenceRecommendationsJobName
field.Specify either this field or the
RecommendationId
field.TargetCpuUtilizationPerCore
The percentage of how much utilization you want an instance to use before autoscaling. The default value is 50%.
ScalingPolicyObjective
An object where you specify the anticipated traffic pattern for an endpoint.
Value¶
A list with the following syntax:
list(
InferenceRecommendationsJobName = "string",
RecommendationId = "string",
EndpointName = "string",
TargetCpuUtilizationPerCore = 123,
ScalingPolicyObjective = list(
MinInvocationsPerMinute = 123,
MaxInvocationsPerMinute = 123
),
Metric = list(
InvocationsPerInstance = 123,
ModelLatency = 123
),
DynamicScalingConfiguration = list(
MinCapacity = 123,
MaxCapacity = 123,
ScaleInCooldown = 123,
ScaleOutCooldown = 123,
ScalingPolicies = list(
list(
TargetTracking = list(
MetricSpecification = list(
Predefined = list(
PredefinedMetricType = "string"
),
Customized = list(
MetricName = "string",
Namespace = "string",
Statistic = "Average"|"Minimum"|"Maximum"|"SampleCount"|"Sum"
)
),
TargetValue = 123.0
)
)
)
)
)