com.google.api.services.ml.v1.model

Class GoogleCloudMlV1AutoScaling

java.lang.Object

java.util.AbstractMap<String,Object>

com.google.api.client.util.GenericData

com.google.api.client.json.GenericJson

com.google.api.services.ml.v1.model.GoogleCloudMlV1AutoScaling

All Implemented Interfaces:

Cloneable, Map<String,Object>

public final class GoogleCloudMlV1AutoScaling
extends GenericJson

Options for automatically scaling a model.

This is the Java data model class that specifies how to parse/serialize into the JSON that is transmitted over HTTP when working with the AI Platform Training & Prediction API. For a detailed explanation see: https://developers.google.com/api-client-library/java/google-http-java-client/json

Author:

Google, Inc.

Nested Class Summary

Nested classes/interfaces inherited from class com.google.api.client.util.GenericData

GenericData.Flags

Nested classes/interfaces inherited from class java.util.AbstractMap

AbstractMap.SimpleEntry<K,V>, AbstractMap.SimpleImmutableEntry<K,V>

Nested classes/interfaces inherited from interface java.util.Map

Map.Entry<K,V>

Constructor Summary

Constructors

Constructor and Description
GoogleCloudMlV1AutoScaling()

Method Summary

Modifier and Type	Method and Description
GoogleCloudMlV1AutoScaling	clone()
Integer	getMaxNodes() The maximum number of nodes to scale this model under load.
List<GoogleCloudMlV1MetricSpec>	getMetrics() MetricSpec contains the specifications to use to calculate the desired nodes count.
Integer	getMinNodes() Optional.
GoogleCloudMlV1AutoScaling	set(String fieldName, Object value)
GoogleCloudMlV1AutoScaling	setMaxNodes(Integer maxNodes) The maximum number of nodes to scale this model under load.
GoogleCloudMlV1AutoScaling	setMetrics(List<GoogleCloudMlV1MetricSpec> metrics) MetricSpec contains the specifications to use to calculate the desired nodes count.
GoogleCloudMlV1AutoScaling	setMinNodes(Integer minNodes) Optional.

Methods inherited from class com.google.api.client.json.GenericJson

getFactory, setFactory, toPrettyString, toString

Methods inherited from class com.google.api.client.util.GenericData

entrySet, equals, get, getClassInfo, getUnknownKeys, hashCode, put, putAll, remove, setUnknownKeys

Methods inherited from class java.util.AbstractMap

clear, containsKey, containsValue, isEmpty, keySet, size, values

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface java.util.Map

compute, computeIfAbsent, computeIfPresent, forEach, getOrDefault, merge, putIfAbsent, remove, replace, replace, replaceAll

Constructor Detail

GoogleCloudMlV1AutoScaling

public GoogleCloudMlV1AutoScaling()

Method Detail

getMaxNodes

public Integer getMaxNodes()

The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.

Returns:

value or null for none

setMaxNodes

public GoogleCloudMlV1AutoScaling setMaxNodes(Integer maxNodes)

The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.

Parameters:

maxNodes - maxNodes or null for none

getMetrics

public List<GoogleCloudMlV1MetricSpec> getMetrics()

MetricSpec contains the specifications to use to calculate the desired nodes count.

Returns:

value or null for none

setMetrics

public GoogleCloudMlV1AutoScaling setMetrics(List<GoogleCloudMlV1MetricSpec> metrics)

MetricSpec contains the specifications to use to calculate the desired nodes count.

Parameters:

metrics - metrics or null for none

getMinNodes

public Integer getMinNodes()

Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs /machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/models/versions}?update_mask=autoScaling.minNodes -d @./update_body.json

Returns:

value or null for none

setMinNodes

public GoogleCloudMlV1AutoScaling setMinNodes(Integer minNodes)

Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs /machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/models/versions}?update_mask=autoScaling.minNodes -d @./update_body.json

Parameters:

minNodes - minNodes or null for none

set

public GoogleCloudMlV1AutoScaling set(String fieldName,
                                      Object value)

Overrides:

set in class GenericJson

clone

public GoogleCloudMlV1AutoScaling clone()

Overrides:

clone in class GenericJson