Class: Google::Cloud::AIPlatform::V1::AutoscalingMetricSpec

Inherits:

Object

Object
Google::Cloud::AIPlatform::V1::AutoscalingMetricSpec

show all

Extended by:: Protobuf::MessageExts::ClassMethods

Includes:: Protobuf::MessageExts

Defined in:: proto_docs/google/cloud/aiplatform/v1/machine_resources.rb

Overview

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

Instance Attribute Summary collapse

#metric_name ⇒ ::String
Required.
#target ⇒ ::Integer
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.

Instance Attribute Details

#metric_name ⇒ `::String`

Returns 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.

Returns:

(::String) —
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

# File 'proto_docs/google/cloud/aiplatform/v1/machine_resources.rb', line 249

class AutoscalingMetricSpec
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#target ⇒ `::Integer`

Returns 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.