public final class DedicatedResources extends GeneratedMessageV3 implements DedicatedResourcesOrBuilder
A description of resources that are dedicated to a DeployedModel or
DeployedIndex, and that need a higher degree of manual configuration.
Protobuf type google.cloud.aiplatform.v1beta1.DedicatedResources
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT,int)
com.google.protobuf.GeneratedMessageV3.<T>emptyList(java.lang.Class<T>)
com.google.protobuf.GeneratedMessageV3.internalGetMapFieldReflection(int)
Static Fields
public static final int AUTOSCALING_METRIC_SPECS_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int FLEX_START_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int MACHINE_SPEC_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int MAX_REPLICA_COUNT_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int MIN_REPLICA_COUNT_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int REQUIRED_REPLICA_COUNT_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int SPOT_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
Static Methods
public static DedicatedResources getDefaultInstance()
public static final Descriptors.Descriptor getDescriptor()
public static DedicatedResources.Builder newBuilder()
public static DedicatedResources.Builder newBuilder(DedicatedResources prototype)
public static DedicatedResources parseDelimitedFrom(InputStream input)
public static DedicatedResources parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static DedicatedResources parseFrom(byte[] data)
| Parameter |
| Name |
Description |
data |
byte[]
|
public static DedicatedResources parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static DedicatedResources parseFrom(ByteString data)
public static DedicatedResources parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static DedicatedResources parseFrom(CodedInputStream input)
public static DedicatedResources parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static DedicatedResources parseFrom(InputStream input)
public static DedicatedResources parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static DedicatedResources parseFrom(ByteBuffer data)
public static DedicatedResources parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static Parser<DedicatedResources> parser()
Methods
public boolean equals(Object obj)
| Parameter |
| Name |
Description |
obj |
Object
|
Overrides
public AutoscalingMetricSpec getAutoscalingMetricSpecs(int index)
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
| Name |
Description |
index |
int
|
public int getAutoscalingMetricSpecsCount()
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
| Type |
Description |
int |
|
public List<AutoscalingMetricSpec> getAutoscalingMetricSpecsList()
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public AutoscalingMetricSpecOrBuilder getAutoscalingMetricSpecsOrBuilder(int index)
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
| Name |
Description |
index |
int
|
public List<? extends AutoscalingMetricSpecOrBuilder> getAutoscalingMetricSpecsOrBuilderList()
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
| Type |
Description |
List<? extends com.google.cloud.aiplatform.v1beta1.AutoscalingMetricSpecOrBuilder> |
|
public DedicatedResources getDefaultInstanceForType()
public FlexStart getFlexStart()
| Returns |
| Type |
Description |
FlexStart |
The flexStart.
|
public FlexStartOrBuilder getFlexStartOrBuilder()
public MachineSpec getMachineSpec()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public MachineSpecOrBuilder getMachineSpecOrBuilder()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public int getMaxReplicaCount()
Immutable. The maximum number of replicas that may be deployed on when the
traffic against it increases. If the requested value is too large, the
deployment will error, but if deployment succeeds then the ability to scale
to that many replicas is guaranteed (barring service outages). If traffic
increases beyond what its replicas at maximum may handle, a portion of the
traffic will be dropped. If this value is not provided, will use
min_replica_count
as the default value.
The value of this field impacts the charge against Vertex CPU and GPU
quotas. Specifically, you will be charged for (max_replica_count *
number of cores in the selected machine type) and (max_replica_count *
number of GPUs per replica in the selected machine type).
int32 max_replica_count = 3 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
| Type |
Description |
int |
The maxReplicaCount.
|
public int getMinReplicaCount()
Required. Immutable. The minimum number of machine replicas that will be
always deployed on. This value must be greater than or equal to 1.
If traffic increases, it may dynamically be deployed onto more replicas,
and as traffic decreases, some of these extra replicas may be freed.
int32 min_replica_count = 2 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
| Returns |
| Type |
Description |
int |
The minReplicaCount.
|
public Parser<DedicatedResources> getParserForType()
Overrides
public int getRequiredReplicaCount()
Optional. Number of required available replicas for the deployment to
succeed. This field is only needed when partial deployment/mutation is
desired. If set, the deploy/mutate operation will succeed once
available_replica_count reaches required_replica_count, and the rest of
the replicas will be retried. If not set, the default
required_replica_count will be min_replica_count.
int32 required_replica_count = 9 [(.google.api.field_behavior) = OPTIONAL];
| Returns |
| Type |
Description |
int |
The requiredReplicaCount.
|
public int getSerializedSize()
| Returns |
| Type |
Description |
int |
|
Overrides
Optional. If true, schedule the deployment workload on spot
VMs.
bool spot = 5 [(.google.api.field_behavior) = OPTIONAL];
| Returns |
| Type |
Description |
boolean |
The spot.
|
public boolean hasFlexStart()
| Returns |
| Type |
Description |
boolean |
Whether the flexStart field is set.
|
public boolean hasMachineSpec()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
| Returns |
| Type |
Description |
boolean |
Whether the machineSpec field is set.
|
| Returns |
| Type |
Description |
int |
|
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public DedicatedResources.Builder newBuilderForType()
protected DedicatedResources.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
| Returns |
| Type |
Description |
Object |
|
Overrides
public DedicatedResources.Builder toBuilder()
public void writeTo(CodedOutputStream output)
Overrides
