Cloud AI Platform v1 API - Class AutoscalingMetricSpec (3.4.0)

public sealed class AutoscalingMetricSpec : IMessage<AutoscalingMetricSpec>, IEquatable<AutoscalingMetricSpec>, IDeepCloneable<AutoscalingMetricSpec>, IBufferMessage, IMessage

Reference documentation and code samples for the Cloud AI Platform v1 API class AutoscalingMetricSpec.

The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.

Inheritance

object > AutoscalingMetricSpec

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

AutoscalingMetricSpec()

public AutoscalingMetricSpec()

AutoscalingMetricSpec(AutoscalingMetricSpec)

public AutoscalingMetricSpec(AutoscalingMetricSpec other)
Parameter
Name Description
other AutoscalingMetricSpec

Properties

MetricName

public string MetricName { get; set; }

Required. The resource metric name. Supported metrics:

  • For Online Prediction:
  • aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
  • aiplatform.googleapis.com/prediction/online/cpu/utilization
Property Value
Type Description
string

Target

public int Target { get; set; }

The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

Property Value
Type Description
int