diff --git a/sample/sagemaker/2017-07-24/service-2.json b/sample/sagemaker/2017-07-24/service-2.json index 0c609f9..54f7967 100644 --- a/sample/sagemaker/2017-07-24/service-2.json +++ b/sample/sagemaker/2017-07-24/service-2.json @@ -67,6 +67,20 @@ ], "documentation":"

Attaches your Amazon Elastic Block Store (Amazon EBS) volume to a node in your EKS-orchestrated HyperPod cluster.

This API works with the Amazon Elastic Block Store (Amazon EBS) Container Storage Interface (CSI) driver to manage the lifecycle of persistent storage in your HyperPod EKS clusters.

" }, + "BatchAddClusterNodes":{ + "name":"BatchAddClusterNodes", + "http":{ + "method":"POST", + "requestUri":"/" + }, + "input":{"shape":"BatchAddClusterNodesRequest"}, + "output":{"shape":"BatchAddClusterNodesResponse"}, + "errors":[ + {"shape":"ResourceNotFound"}, + {"shape":"ResourceLimitExceeded"} + ], + "documentation":"

Adds nodes to a HyperPod cluster by incrementing the target count for one or more instance groups. This operation returns a unique NodeLogicalId for each node being added, which can be used to track the provisioning status of the node. This API provides a safer alternative to UpdateCluster for scaling operations by avoiding unintended configuration changes.

This API is only supported for clusters using Continuous as the NodeProvisioningMode.

" + }, "BatchDeleteClusterNodes":{ "name":"BatchDeleteClusterNodes", "http":{ @@ -1748,6 +1762,19 @@ ], "documentation":"

Retrieves information of a SageMaker HyperPod cluster.

" }, + "DescribeClusterEvent":{ + "name":"DescribeClusterEvent", + "http":{ + "method":"POST", + "requestUri":"/" + }, + "input":{"shape":"DescribeClusterEventRequest"}, + "output":{"shape":"DescribeClusterEventResponse"}, + "errors":[ + {"shape":"ResourceNotFound"} + ], + "documentation":"

Retrieves detailed information about a specific event for a given HyperPod cluster. This functionality is only supported when the NodeProvisioningMode is set to Continuous.

" + }, "DescribeClusterNode":{ "name":"DescribeClusterNode", "http":{ @@ -2709,6 +2736,19 @@ ], "documentation":"

List the candidates created for the job.

" }, + "ListClusterEvents":{ + "name":"ListClusterEvents", + "http":{ + "method":"POST", + "requestUri":"/" + }, + "input":{"shape":"ListClusterEventsRequest"}, + "output":{"shape":"ListClusterEventsResponse"}, + "errors":[ + {"shape":"ResourceNotFound"} + ], + "documentation":"

Retrieves a list of event summaries for a specified HyperPod cluster. The operation supports filtering, sorting, and pagination of results. This functionality is only supported when the NodeProvisioningMode is set to Continuous.

" + }, "ListClusterNodes":{ "name":"ListClusterNodes", "http":{ @@ -4623,6 +4663,36 @@ } } }, + "AddClusterNodeSpecification":{ + "type":"structure", + "required":[ + "InstanceGroupName", + "IncrementTargetCountBy" + ], + "members":{ + "InstanceGroupName":{ + "shape":"ClusterInstanceGroupName", + "documentation":"

The name of the instance group to which you want to add nodes.

" + }, + "IncrementTargetCountBy":{ + "shape":"AddClusterNodeSpecificationIncrementTargetCountByInteger", + "documentation":"

The number of nodes to add to the specified instance group. The total number of nodes across all instance groups in a single request cannot exceed 50.

" + } + }, + "documentation":"

Specifies an instance group and the number of nodes to add to it.

" + }, + "AddClusterNodeSpecificationIncrementTargetCountByInteger":{ + "type":"integer", + "box":true, + "max":50, + "min":1 + }, + "AddClusterNodeSpecificationList":{ + "type":"list", + "member":{"shape":"AddClusterNodeSpecification"}, + "max":5, + "min":1 + }, "AddTagsInput":{ "type":"structure", "required":[ @@ -4655,6 +4725,16 @@ "max":3, "min":0 }, + "AdditionalEnis":{ + "type":"structure", + "members":{ + "EfaEnis":{ + "shape":"EfaEnis", + "documentation":"

A list of Elastic Fabric Adapter (EFA) ENIs associated with the instance.

" + } + }, + "documentation":"

Information about additional Elastic Network Interfaces (ENIs) associated with an instance.

" + }, "AdditionalInferenceSpecificationDefinition":{ "type":"structure", "required":[ @@ -6688,6 +6768,94 @@ "min":1, "pattern":"[a-zA-Z0-9](-*[a-zA-Z0-9])*" }, + "BatchAddClusterNodesError":{ + "type":"structure", + "required":[ + "InstanceGroupName", + "ErrorCode", + "FailedCount" + ], + "members":{ + "InstanceGroupName":{ + "shape":"InstanceGroupName", + "documentation":"

The name of the instance group for which the error occurred.

" + }, + "ErrorCode":{ + "shape":"BatchAddClusterNodesErrorCode", + "documentation":"

The error code associated with the failure. Possible values include InstanceGroupNotFound and InvalidInstanceGroupState.

" + }, + "FailedCount":{ + "shape":"BatchAddFailureCount", + "documentation":"

The number of nodes that failed to be added to the specified instance group.

" + }, + "Message":{ + "shape":"String", + "documentation":"

A descriptive message providing additional details about the error.

" + } + }, + "documentation":"

Information about an error that occurred during the node addition operation.

" + }, + "BatchAddClusterNodesErrorCode":{ + "type":"string", + "enum":[ + "InstanceGroupNotFound", + "InvalidInstanceGroupStatus" + ] + }, + "BatchAddClusterNodesErrorList":{ + "type":"list", + "member":{"shape":"BatchAddClusterNodesError"} + }, + "BatchAddClusterNodesRequest":{ + "type":"structure", + "required":[ + "ClusterName", + "NodesToAdd" + ], + "members":{ + "ClusterName":{ + "shape":"ClusterNameOrArn", + "documentation":"

The name of the HyperPod cluster to which you want to add nodes.

" + }, + "ClientToken":{ + "shape":"BatchAddClusterNodesRequestClientTokenString", + "documentation":"

A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. This token is valid for 8 hours. If you retry the request with the same client token within this timeframe and the same parameters, the API returns the same set of NodeLogicalIds with their latest status.

", + "idempotencyToken":true + }, + "NodesToAdd":{ + "shape":"AddClusterNodeSpecificationList", + "documentation":"

A list of instance groups and the number of nodes to add to each. You can specify up to 5 instance groups in a single request, with a maximum of 50 nodes total across all instance groups.

" + } + } + }, + "BatchAddClusterNodesRequestClientTokenString":{ + "type":"string", + "max":64, + "min":0, + "pattern":"[\\x21-\\x7E]+" + }, + "BatchAddClusterNodesResponse":{ + "type":"structure", + "required":[ + "Successful", + "Failed" + ], + "members":{ + "Successful":{ + "shape":"NodeAdditionResultList", + "documentation":"

A list of NodeLogicalIDs that were successfully added to the cluster. The NodeLogicalID is unique per cluster and does not change between instance replacements. Each entry includes a NodeLogicalId that can be used to track the node's provisioning status (with DescribeClusterNode), the instance group name, and the current status of the node.

" + }, + "Failed":{ + "shape":"BatchAddClusterNodesErrorList", + "documentation":"

A list of errors that occurred during the node addition operation. Each entry includes the instance group name, error code, number of failed additions, and an error message.

" + } + } + }, + "BatchAddFailureCount":{ + "type":"integer", + "box":true, + "min":1 + }, "BatchDataCaptureConfig":{ "type":"structure", "required":["DestinationS3Uri"], @@ -6708,6 +6876,35 @@ }, "documentation":"

Configuration to control how SageMaker captures inference data for batch transform jobs.

" }, + "BatchDeleteClusterNodeLogicalIdsError":{ + "type":"structure", + "required":[ + "Code", + "Message", + "NodeLogicalId" + ], + "members":{ + "Code":{ + "shape":"BatchDeleteClusterNodesErrorCode", + "documentation":"

The error code associated with the failure. Possible values include NodeLogicalIdNotFound, InvalidNodeStatus, and InternalError.

" + }, + "Message":{ + "shape":"String", + "documentation":"

A descriptive message providing additional details about the error.

" + }, + "NodeLogicalId":{ + "shape":"ClusterNodeLogicalId", + "documentation":"

The NodeLogicalId of the node that could not be deleted.

" + } + }, + "documentation":"

Information about an error that occurred when attempting to delete a node identified by its NodeLogicalId.

" + }, + "BatchDeleteClusterNodeLogicalIdsErrorList":{ + "type":"list", + "member":{"shape":"BatchDeleteClusterNodeLogicalIdsError"}, + "max":99, + "min":1 + }, "BatchDeleteClusterNodesError":{ "type":"structure", "required":[ @@ -6756,6 +6953,10 @@ "NodeIds":{ "shape":"ClusterNodeIds", "documentation":"

A list of node IDs to be deleted from the specified cluster.

" + }, + "NodeLogicalIds":{ + "shape":"ClusterNodeLogicalIdList", + "documentation":"

A list of NodeLogicalIds identifying the nodes to be deleted. You can specify up to 50 NodeLogicalIds. You must specify either NodeLogicalIds, InstanceIds, or both, with a combined maximum of 50 identifiers.

" } } }, @@ -6769,6 +6970,14 @@ "Successful":{ "shape":"ClusterNodeIds", "documentation":"

A list of node IDs that were successfully deleted from the specified cluster.

" + }, + "FailedNodeLogicalIds":{ + "shape":"BatchDeleteClusterNodeLogicalIdsErrorList", + "documentation":"

A list of NodeLogicalIds that could not be deleted, along with error information explaining why the deletion failed.

" + }, + "SuccessfulNodeLogicalIds":{ + "shape":"ClusterNodeLogicalIdList", + "documentation":"

A list of NodeLogicalIds that were successfully deleted from the cluster.

" } } }, @@ -7174,10 +7383,31 @@ }, "documentation":"

The SageMaker Canvas application settings.

" }, + "CapacityReservation":{ + "type":"structure", + "members":{ + "Arn":{ + "shape":"String", + "documentation":"

The Amazon Resource Name (ARN) of the Capacity Reservation.

" + }, + "Type":{ + "shape":"CapacityReservationType", + "documentation":"

The type of Capacity Reservation. Valid values are ODCR (On-Demand Capacity Reservation) or CRG (Capacity Reservation Group).

" + } + }, + "documentation":"

Information about the Capacity Reservation used by an instance or instance group.

" + }, "CapacityReservationPreference":{ "type":"string", "enum":["capacity-reservations-only"] }, + "CapacityReservationType":{ + "type":"string", + "enum":[ + "ODCR", + "CRG" + ] + }, "CapacitySize":{ "type":"structure", "required":[ @@ -8070,6 +8300,120 @@ "max":16384, "min":1 }, + "ClusterEventDetail":{ + "type":"structure", + "required":[ + "EventId", + "ClusterArn", + "ClusterName", + "ResourceType", + "EventTime" + ], + "members":{ + "EventId":{ + "shape":"EventId", + "documentation":"

The unique identifier (UUID) of the event.

" + }, + "ClusterArn":{ + "shape":"ClusterArn", + "documentation":"

The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event.

" + }, + "ClusterName":{ + "shape":"ClusterName", + "documentation":"

The name of the SageMaker HyperPod cluster associated with the event.

" + }, + "InstanceGroupName":{ + "shape":"ClusterInstanceGroupName", + "documentation":"

The name of the instance group associated with the event, if applicable.

" + }, + "InstanceId":{ + "shape":"String", + "documentation":"

The EC2 instance ID associated with the event, if applicable.

" + }, + "ResourceType":{ + "shape":"ClusterEventResourceType", + "documentation":"

The type of resource associated with the event. Valid values are \"Cluster\", \"InstanceGroup\", or \"Instance\".

" + }, + "EventTime":{ + "shape":"Timestamp", + "documentation":"

The timestamp when the event occurred.

" + }, + "EventDetails":{ + "shape":"EventDetails", + "documentation":"

Additional details about the event, including event-specific metadata.

" + }, + "Description":{ + "shape":"String", + "documentation":"

A human-readable description of the event.

" + } + }, + "documentation":"

Detailed information about a specific event in a HyperPod cluster.

" + }, + "ClusterEventMaxResults":{ + "type":"integer", + "box":true, + "max":100, + "min":1 + }, + "ClusterEventResourceType":{ + "type":"string", + "enum":[ + "Cluster", + "InstanceGroup", + "Instance" + ] + }, + "ClusterEventSummaries":{ + "type":"list", + "member":{"shape":"ClusterEventSummary"}, + "max":100, + "min":0 + }, + "ClusterEventSummary":{ + "type":"structure", + "required":[ + "EventId", + "ClusterArn", + "ClusterName", + "ResourceType", + "EventTime" + ], + "members":{ + "EventId":{ + "shape":"EventId", + "documentation":"

The unique identifier (UUID) of the event.

" + }, + "ClusterArn":{ + "shape":"ClusterArn", + "documentation":"

The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event.

" + }, + "ClusterName":{ + "shape":"ClusterName", + "documentation":"

The name of the SageMaker HyperPod cluster associated with the event.

" + }, + "InstanceGroupName":{ + "shape":"ClusterInstanceGroupName", + "documentation":"

The name of the instance group associated with the event, if applicable.

" + }, + "InstanceId":{ + "shape":"String", + "documentation":"

The EC2 instance ID associated with the event, if applicable.

" + }, + "ResourceType":{ + "shape":"ClusterEventResourceType", + "documentation":"

The type of resource associated with the event. Valid values are \"Cluster\", \"InstanceGroup\", or \"Instance\".

" + }, + "EventTime":{ + "shape":"Timestamp", + "documentation":"

The timestamp when the event occurred.

" + }, + "Description":{ + "shape":"String", + "documentation":"

A brief, human-readable description of the event.

" + } + }, + "documentation":"

A summary of an event in a SageMaker HyperPod cluster.

" + }, "ClusterInstanceCount":{ "type":"integer", "box":true, @@ -8134,6 +8478,14 @@ "ScheduledUpdateConfig":{ "shape":"ScheduledUpdateConfig", "documentation":"

The configuration object of the schedule that SageMaker follows when updating the AMI.

" + }, + "CurrentImageId":{ + "shape":"ImageId", + "documentation":"

The ID of the Amazon Machine Image (AMI) currently in use by the instance group.

" + }, + "DesiredImageId":{ + "shape":"ImageId", + "documentation":"

The ID of the Amazon Machine Image (AMI) desired for the instance group.

" } }, "documentation":"

Details of an instance group in a SageMaker HyperPod cluster.

" @@ -8201,6 +8553,10 @@ "ScheduledUpdateConfig":{ "shape":"ScheduledUpdateConfig", "documentation":"

The configuration object of the schedule that SageMaker uses to update the AMI.

" + }, + "ImageId":{ + "shape":"ImageId", + "documentation":"

When configuring your HyperPod cluster, you can specify an image ID using one of the following options:

f you choose to use a custom AMI (CustomAmiId), ensure it meets the following requirements:

When updating the instance group's AMI through the UpdateClusterSoftware operation, if an instance group uses a custom AMI, you must provide an ImageId or use the default as input.

" } }, "documentation":"

The specifications of an instance group that you need to define.

" @@ -8239,7 +8595,8 @@ "Pending", "ShuttingDown", "SystemUpdating", - "DeepHealthCheckInProgress" + "DeepHealthCheckInProgress", + "NotFound" ] }, "ClusterInstanceStatusDetails":{ @@ -8415,6 +8772,24 @@ "min":1, "pattern":"[\\S\\s]+" }, + "ClusterMetadata":{ + "type":"structure", + "members":{ + "FailureMessage":{ + "shape":"String", + "documentation":"

An error message describing why the cluster level operation (such as creating, updating, or deleting) failed.

" + }, + "EksRoleAccessEntries":{ + "shape":"EksRoleAccessEntries", + "documentation":"

A list of Amazon EKS IAM role ARNs associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters.

" + }, + "SlrAccessEntry":{ + "shape":"String", + "documentation":"

The Service-Linked Role (SLR) associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters.

" + } + }, + "documentation":"

Metadata information about a SageMaker HyperPod cluster showing information about the cluster level operations, such as creating, updating, and deleting.

" + }, "ClusterName":{ "type":"string", "max":63, @@ -8438,6 +8813,10 @@ "shape":"String", "documentation":"

The ID of the instance.

" }, + "NodeLogicalId":{ + "shape":"ClusterNodeLogicalId", + "documentation":"

A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId.

" + }, "InstanceStatus":{ "shape":"ClusterInstanceStatusDetails", "documentation":"

The status of the instance.

" @@ -8485,6 +8864,14 @@ "Placement":{ "shape":"ClusterInstancePlacement", "documentation":"

The placement details of the SageMaker HyperPod cluster node.

" + }, + "CurrentImageId":{ + "shape":"ImageId", + "documentation":"

The ID of the Amazon Machine Image (AMI) currently in use by the node.

" + }, + "DesiredImageId":{ + "shape":"ImageId", + "documentation":"

The ID of the Amazon Machine Image (AMI) desired for the node.

" } }, "documentation":"

Details of an instance (also called a node interchangeably) in a SageMaker HyperPod cluster.

" @@ -8501,6 +8888,22 @@ "max":3000, "min":1 }, + "ClusterNodeLogicalId":{ + "type":"string", + "max":128, + "min":1, + "pattern":"[a-zA-Z0-9][a-zA-Z0-9\\-]*[a-zA-Z0-9]" + }, + "ClusterNodeLogicalIdList":{ + "type":"list", + "member":{"shape":"ClusterNodeLogicalId"}, + "max":99, + "min":1 + }, + "ClusterNodeProvisioningMode":{ + "type":"string", + "enum":["Continuous"] + }, "ClusterNodeRecovery":{ "type":"string", "enum":[ @@ -8530,6 +8933,10 @@ "shape":"String", "documentation":"

The ID of the instance.

" }, + "NodeLogicalId":{ + "shape":"String", + "documentation":"

A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId. This field is only included when IncludeNodeLogicalIds is set to True in the ListClusterNodes request.

" + }, "InstanceType":{ "shape":"ClusterInstanceType", "documentation":"

The type of the instance.

" @@ -10000,6 +10407,10 @@ "NodeRecovery":{ "shape":"ClusterNodeRecovery", "documentation":"

The node recovery mode for the SageMaker HyperPod cluster. When set to Automatic, SageMaker HyperPod will automatically reboot or replace faulty nodes when issues are detected. When set to None, cluster administrators will need to manually manage any faulty cluster instances.

" + }, + "NodeProvisioningMode":{ + "shape":"ClusterNodeProvisioningMode", + "documentation":"

The mode for provisioning nodes in the cluster. You can specify the following modes:

" } } }, @@ -14948,6 +15359,32 @@ } } }, + "DescribeClusterEventRequest":{ + "type":"structure", + "required":[ + "EventId", + "ClusterName" + ], + "members":{ + "EventId":{ + "shape":"EventId", + "documentation":"

The unique identifier (UUID) of the event to describe. This ID can be obtained from the ListClusterEvents operation.

" + }, + "ClusterName":{ + "shape":"ClusterNameOrArn", + "documentation":"

The name or Amazon Resource Name (ARN) of the HyperPod cluster associated with the event.

" + } + } + }, + "DescribeClusterEventResponse":{ + "type":"structure", + "members":{ + "EventDetails":{ + "shape":"ClusterEventDetail", + "documentation":"

Detailed information about the requested cluster event, including event metadata for various resource types such as Cluster, InstanceGroup, Instance, and their associated attributes.

" + } + } + }, "DescribeClusterNodeRequest":{ "type":"structure", "required":["ClusterName"], @@ -14959,6 +15396,10 @@ "NodeId":{ "shape":"ClusterNodeId", "documentation":"

The ID of the SageMaker HyperPod cluster node.

" + }, + "NodeLogicalId":{ + "shape":"ClusterNodeLogicalId", + "documentation":"

The logical identifier of the node to describe. You can specify either NodeLogicalId or InstanceId, but not both. NodeLogicalId can be used to describe nodes that are still being provisioned and don't yet have an InstanceId assigned.

" } } }, @@ -15026,6 +15467,10 @@ "NodeRecovery":{ "shape":"ClusterNodeRecovery", "documentation":"

The node recovery mode configured for the SageMaker HyperPod cluster.

" + }, + "NodeProvisioningMode":{ + "shape":"ClusterNodeProvisioningMode", + "documentation":"

The mode used for provisioning nodes in the cluster.

" } } }, @@ -20362,6 +20807,10 @@ "type":"list", "member":{"shape":"Edge"} }, + "EfaEnis":{ + "type":"list", + "member":{"shape":"String"} + }, "EfsUid":{ "type":"string", "max":10, @@ -20374,6 +20823,10 @@ "min":20, "pattern":"arn:aws[a-z\\-]*:eks:[a-z0-9\\-]*:[0-9]{12}:cluster\\/[0-9A-Za-z][A-Za-z0-9\\-_]{0,99}" }, + "EksRoleAccessEntries":{ + "type":"list", + "member":{"shape":"String"} + }, "EmrServerlessComputeConfig":{ "type":"structure", "required":["ExecutionRoleARN"], @@ -20927,6 +21380,47 @@ }, "documentation":"

This is an error field object that contains the error code and the reason for an operation failure.

" }, + "EventDetails":{ + "type":"structure", + "members":{ + "EventMetadata":{ + "shape":"EventMetadata", + "documentation":"

Metadata specific to the event, which may include information about the cluster, instance group, or instance involved.

" + } + }, + "documentation":"

Detailed information about a specific event, including event metadata.

" + }, + "EventId":{ + "type":"string", + "pattern":"[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}" + }, + "EventMetadata":{ + "type":"structure", + "members":{ + "Cluster":{ + "shape":"ClusterMetadata", + "documentation":"

Metadata specific to cluster-level events.

" + }, + "InstanceGroup":{ + "shape":"InstanceGroupMetadata", + "documentation":"

Metadata specific to instance group-level events.

" + }, + "InstanceGroupScaling":{ + "shape":"InstanceGroupScalingMetadata", + "documentation":"

Metadata related to instance group scaling events.

" + }, + "Instance":{ + "shape":"InstanceMetadata", + "documentation":"

Metadata specific to instance-level events.

" + } + }, + "documentation":"

Metadata associated with a cluster event, which may include details about various resource types.

", + "union":true + }, + "EventSortBy":{ + "type":"string", + "enum":["EventTime"] + }, "ExcludeFeaturesAttribute":{ "type":"string", "max":100, @@ -23573,6 +24067,12 @@ "min":1, "pattern":"\\S(.*\\S)?" }, + "ImageId":{ + "type":"string", + "max":21, + "min":7, + "pattern":"ami-[0-9a-fA-F]{8,17}|default" + }, "ImageName":{ "type":"string", "max":63, @@ -23798,6 +24298,10 @@ "box":true, "min":0 }, + "IncludeNodeLogicalIdsBoolean":{ + "type":"boolean", + "box":true + }, "InferenceComponentArn":{ "type":"string", "max":2048, @@ -24563,6 +25067,36 @@ }, "documentation":"

Defines an instance group for heterogeneous cluster training. When requesting a training job using the CreateTrainingJob API, you can configure multiple instance groups .

" }, + "InstanceGroupMetadata":{ + "type":"structure", + "members":{ + "FailureMessage":{ + "shape":"String", + "documentation":"

An error message describing why the instance group level operation (such as creating, scaling, or deleting) failed.

" + }, + "AvailabilityZoneId":{ + "shape":"String", + "documentation":"

The ID of the Availability Zone where the instance group is located.

" + }, + "CapacityReservation":{ + "shape":"CapacityReservation", + "documentation":"

Information about the Capacity Reservation used by the instance group.

" + }, + "SubnetId":{ + "shape":"String", + "documentation":"

The ID of the subnet where the instance group is located.

" + }, + "SecurityGroupIds":{ + "shape":"SecurityGroupIds", + "documentation":"

A list of security group IDs associated with the instance group.

" + }, + "AmiOverride":{ + "shape":"String", + "documentation":"

If you use a custom Amazon Machine Image (AMI) for the instance group, this field shows the ID of the custom AMI.

" + } + }, + "documentation":"

Metadata information about an instance group in a SageMaker HyperPod cluster.

" + }, "InstanceGroupName":{ "type":"string", "max":64, @@ -24575,6 +25109,24 @@ "max":5, "min":0 }, + "InstanceGroupScalingMetadata":{ + "type":"structure", + "members":{ + "InstanceCount":{ + "shape":"InstanceCount", + "documentation":"

The current number of instances in the group.

" + }, + "TargetCount":{ + "shape":"TargetCount", + "documentation":"

The desired number of instances for the group after scaling.

" + }, + "FailureMessage":{ + "shape":"String", + "documentation":"

An error message describing why the scaling operation failed, if applicable.

" + } + }, + "documentation":"

Metadata information about scaling operations for an instance group.

" + }, "InstanceGroupStatus":{ "type":"string", "enum":[ @@ -24598,6 +25150,36 @@ "max":5, "min":0 }, + "InstanceMetadata":{ + "type":"structure", + "members":{ + "CustomerEni":{ + "shape":"String", + "documentation":"

The ID of the customer-managed Elastic Network Interface (ENI) associated with the instance.

" + }, + "AdditionalEnis":{ + "shape":"AdditionalEnis", + "documentation":"

Information about additional Elastic Network Interfaces (ENIs) associated with the instance.

" + }, + "CapacityReservation":{ + "shape":"CapacityReservation", + "documentation":"

Information about the Capacity Reservation used by the instance.

" + }, + "FailureMessage":{ + "shape":"String", + "documentation":"

An error message describing why the instance creation or update failed, if applicable.

" + }, + "LcsExecutionState":{ + "shape":"String", + "documentation":"

The execution state of the Lifecycle Script (LCS) for the instance.

" + }, + "NodeLogicalId":{ + "shape":"ClusterNodeLogicalId", + "documentation":"

The unique logical identifier of the node within the cluster. The ID used here is the same object as in the BatchAddClusterNodes API.

" + } + }, + "documentation":"

Metadata information about an instance in a HyperPod cluster.

" + }, "InstanceMetadataServiceConfiguration":{ "type":"structure", "required":["MinimumInstanceMetadataServiceVersion"], @@ -25977,6 +26559,65 @@ } } }, + "ListClusterEventsRequest":{ + "type":"structure", + "required":["ClusterName"], + "members":{ + "ClusterName":{ + "shape":"ClusterNameOrArn", + "documentation":"

The name or Amazon Resource Name (ARN) of the HyperPod cluster for which to list events.

" + }, + "InstanceGroupName":{ + "shape":"ClusterInstanceGroupName", + "documentation":"

The name of the instance group to filter events. If specified, only events related to this instance group are returned.

" + }, + "NodeId":{ + "shape":"ClusterNodeId", + "documentation":"

The EC2 instance ID to filter events. If specified, only events related to this instance are returned.

" + }, + "EventTimeAfter":{ + "shape":"Timestamp", + "documentation":"

The start of the time range for filtering events. Only events that occurred after this time are included in the results.

" + }, + "EventTimeBefore":{ + "shape":"Timestamp", + "documentation":"

The end of the time range for filtering events. Only events that occurred before this time are included in the results.

" + }, + "SortBy":{ + "shape":"EventSortBy", + "documentation":"

The field to use for sorting the event list. Currently, the only supported value is EventTime.

" + }, + "SortOrder":{ + "shape":"SortOrder", + "documentation":"

The order in which to sort the results. Valid values are Ascending or Descending (the default is Descending).

" + }, + "ResourceType":{ + "shape":"ClusterEventResourceType", + "documentation":"

The type of resource for which to filter events. Valid values are Cluster, InstanceGroup, or Instance.

" + }, + "MaxResults":{ + "shape":"ClusterEventMaxResults", + "documentation":"

The maximum number of events to return in the response. Valid range is 1 to 100.

" + }, + "NextToken":{ + "shape":"NextToken", + "documentation":"

A token to retrieve the next set of results. This token is obtained from the output of a previous ListClusterEvents call.

" + } + } + }, + "ListClusterEventsResponse":{ + "type":"structure", + "members":{ + "NextToken":{ + "shape":"NextToken", + "documentation":"

A token to retrieve the next set of results. Include this token in subsequent ListClusterEvents calls to fetch more events.

" + }, + "Events":{ + "shape":"ClusterEventSummaries", + "documentation":"

A list of event summaries matching the specified criteria.

" + } + } + }, "ListClusterNodesRequest":{ "type":"structure", "required":["ClusterName"], @@ -26012,6 +26653,10 @@ "SortOrder":{ "shape":"SortOrder", "documentation":"

The sort order for results. The default value is Ascending.

" + }, + "IncludeNodeLogicalIds":{ + "shape":"IncludeNodeLogicalIdsBoolean", + "documentation":"

Specifies whether to include nodes that are still being provisioned in the response. When set to true, the response includes all nodes regardless of their provisioning status. When set to False (default), only nodes with assigned InstanceIds are returned.

" } } }, @@ -32697,6 +33342,33 @@ "min":0, "pattern":".*" }, + "NodeAdditionResult":{ + "type":"structure", + "required":[ + "NodeLogicalId", + "InstanceGroupName", + "Status" + ], + "members":{ + "NodeLogicalId":{ + "shape":"ClusterNodeLogicalId", + "documentation":"

A unique identifier assigned to the node that can be used to track its provisioning status through the DescribeClusterNode operation.

" + }, + "InstanceGroupName":{ + "shape":"ClusterInstanceGroupName", + "documentation":"

The name of the instance group to which the node was added.

" + }, + "Status":{ + "shape":"ClusterInstanceStatus", + "documentation":"

The current status of the node. Possible values include Pending, Running, Failed, ShuttingDown, SystemUpdating, DeepHealthCheckInProgress, and NotFound.

" + } + }, + "documentation":"

Information about a node that was successfully added to the cluster.

" + }, + "NodeAdditionResultList":{ + "type":"list", + "member":{"shape":"NodeAdditionResult"} + }, "NodeUnavailabilityType":{ "type":"string", "enum":[ @@ -39768,6 +40440,11 @@ "type":"string", "min":1 }, + "TargetCount":{ + "type":"integer", + "box":true, + "min":0 + }, "TargetDevice":{ "type":"string", "enum":[ @@ -42523,6 +43200,10 @@ "DeploymentConfig":{ "shape":"DeploymentConfiguration", "documentation":"

The configuration to use when updating the AMI versions.

" + }, + "ImageId":{ + "shape":"ImageId", + "documentation":"

When configuring your HyperPod cluster, you can specify an image ID using one of the following options:

f you choose to use a custom AMI (CustomAmiId), ensure it meets the following requirements:

When updating the instance group's AMI through the UpdateClusterSoftware operation, if an instance group uses a custom AMI, you must provide an ImageId or use the default as input.

" } } }, diff --git a/src/sagemaker_core/main/code_injection/shape_dag.py b/src/sagemaker_core/main/code_injection/shape_dag.py index b1a25c7..2f2a21e 100644 --- a/src/sagemaker_core/main/code_injection/shape_dag.py +++ b/src/sagemaker_core/main/code_injection/shape_dag.py @@ -43,6 +43,22 @@ ], "type": "structure", }, + "AddClusterNodeSpecification": { + "members": [ + {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, + { + "name": "IncrementTargetCountBy", + "shape": "AddClusterNodeSpecificationIncrementTargetCountByInteger", + "type": "integer", + }, + ], + "type": "structure", + }, + "AddClusterNodeSpecificationList": { + "member_shape": "AddClusterNodeSpecification", + "member_type": "structure", + "type": "list", + }, "AddTagsInput": { "members": [ {"name": "ResourceArn", "shape": "ResourceArn", "type": "string"}, @@ -59,6 +75,10 @@ "member_type": "string", "type": "list", }, + "AdditionalEnis": { + "members": [{"name": "EfaEnis", "shape": "EfaEnis", "type": "list"}], + "type": "structure", + }, "AdditionalInferenceSpecificationDefinition": { "members": [ {"name": "Name", "shape": "EntityName", "type": "string"}, @@ -782,6 +802,39 @@ "members": [{"name": "Mode", "shape": "AutotuneMode", "type": "string"}], "type": "structure", }, + "BatchAddClusterNodesError": { + "members": [ + {"name": "InstanceGroupName", "shape": "InstanceGroupName", "type": "string"}, + {"name": "ErrorCode", "shape": "BatchAddClusterNodesErrorCode", "type": "string"}, + {"name": "FailedCount", "shape": "BatchAddFailureCount", "type": "integer"}, + {"name": "Message", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, + "BatchAddClusterNodesErrorList": { + "member_shape": "BatchAddClusterNodesError", + "member_type": "structure", + "type": "list", + }, + "BatchAddClusterNodesRequest": { + "members": [ + {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, + { + "name": "ClientToken", + "shape": "BatchAddClusterNodesRequestClientTokenString", + "type": "string", + }, + {"name": "NodesToAdd", "shape": "AddClusterNodeSpecificationList", "type": "list"}, + ], + "type": "structure", + }, + "BatchAddClusterNodesResponse": { + "members": [ + {"name": "Successful", "shape": "NodeAdditionResultList", "type": "list"}, + {"name": "Failed", "shape": "BatchAddClusterNodesErrorList", "type": "list"}, + ], + "type": "structure", + }, "BatchDataCaptureConfig": { "members": [ {"name": "DestinationS3Uri", "shape": "S3Uri", "type": "string"}, @@ -790,6 +843,19 @@ ], "type": "structure", }, + "BatchDeleteClusterNodeLogicalIdsError": { + "members": [ + {"name": "Code", "shape": "BatchDeleteClusterNodesErrorCode", "type": "string"}, + {"name": "Message", "shape": "String", "type": "string"}, + {"name": "NodeLogicalId", "shape": "ClusterNodeLogicalId", "type": "string"}, + ], + "type": "structure", + }, + "BatchDeleteClusterNodeLogicalIdsErrorList": { + "member_shape": "BatchDeleteClusterNodeLogicalIdsError", + "member_type": "structure", + "type": "list", + }, "BatchDeleteClusterNodesError": { "members": [ {"name": "Code", "shape": "BatchDeleteClusterNodesErrorCode", "type": "string"}, @@ -807,6 +873,7 @@ "members": [ {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, {"name": "NodeIds", "shape": "ClusterNodeIds", "type": "list"}, + {"name": "NodeLogicalIds", "shape": "ClusterNodeLogicalIdList", "type": "list"}, ], "type": "structure", }, @@ -814,6 +881,16 @@ "members": [ {"name": "Failed", "shape": "BatchDeleteClusterNodesErrorList", "type": "list"}, {"name": "Successful", "shape": "ClusterNodeIds", "type": "list"}, + { + "name": "FailedNodeLogicalIds", + "shape": "BatchDeleteClusterNodeLogicalIdsErrorList", + "type": "list", + }, + { + "name": "SuccessfulNodeLogicalIds", + "shape": "ClusterNodeLogicalIdList", + "type": "list", + }, ], "type": "structure", }, @@ -1102,6 +1179,13 @@ ], "type": "structure", }, + "CapacityReservation": { + "members": [ + {"name": "Arn", "shape": "String", "type": "string"}, + {"name": "Type", "shape": "CapacityReservationType", "type": "string"}, + ], + "type": "structure", + }, "CapacitySize": { "members": [ {"name": "Type", "shape": "CapacitySizeType", "type": "string"}, @@ -1367,6 +1451,38 @@ ], "type": "structure", }, + "ClusterEventDetail": { + "members": [ + {"name": "EventId", "shape": "EventId", "type": "string"}, + {"name": "ClusterArn", "shape": "ClusterArn", "type": "string"}, + {"name": "ClusterName", "shape": "ClusterName", "type": "string"}, + {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, + {"name": "InstanceId", "shape": "String", "type": "string"}, + {"name": "ResourceType", "shape": "ClusterEventResourceType", "type": "string"}, + {"name": "EventTime", "shape": "Timestamp", "type": "timestamp"}, + {"name": "EventDetails", "shape": "EventDetails", "type": "structure"}, + {"name": "Description", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, + "ClusterEventSummaries": { + "member_shape": "ClusterEventSummary", + "member_type": "structure", + "type": "list", + }, + "ClusterEventSummary": { + "members": [ + {"name": "EventId", "shape": "EventId", "type": "string"}, + {"name": "ClusterArn", "shape": "ClusterArn", "type": "string"}, + {"name": "ClusterName", "shape": "ClusterName", "type": "string"}, + {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, + {"name": "InstanceId", "shape": "String", "type": "string"}, + {"name": "ResourceType", "shape": "ClusterEventResourceType", "type": "string"}, + {"name": "EventTime", "shape": "Timestamp", "type": "timestamp"}, + {"name": "Description", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, "ClusterInstanceGroupDetails": { "members": [ {"name": "CurrentCount", "shape": "ClusterNonNegativeInstanceCount", "type": "integer"}, @@ -1395,6 +1511,8 @@ "shape": "ScheduledUpdateConfig", "type": "structure", }, + {"name": "CurrentImageId", "shape": "ImageId", "type": "string"}, + {"name": "DesiredImageId", "shape": "ImageId", "type": "string"}, ], "type": "structure", }, @@ -1424,6 +1542,7 @@ "shape": "ScheduledUpdateConfig", "type": "structure", }, + {"name": "ImageId", "shape": "ImageId", "type": "string"}, ], "type": "structure", }, @@ -1469,10 +1588,19 @@ ], "type": "structure", }, + "ClusterMetadata": { + "members": [ + {"name": "FailureMessage", "shape": "String", "type": "string"}, + {"name": "EksRoleAccessEntries", "shape": "EksRoleAccessEntries", "type": "list"}, + {"name": "SlrAccessEntry", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, "ClusterNodeDetails": { "members": [ {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, {"name": "InstanceId", "shape": "String", "type": "string"}, + {"name": "NodeLogicalId", "shape": "ClusterNodeLogicalId", "type": "string"}, { "name": "InstanceStatus", "shape": "ClusterInstanceStatusDetails", @@ -1493,10 +1621,17 @@ {"name": "PrivatePrimaryIpv6", "shape": "ClusterPrivatePrimaryIpv6", "type": "string"}, {"name": "PrivateDnsHostname", "shape": "ClusterPrivateDnsHostname", "type": "string"}, {"name": "Placement", "shape": "ClusterInstancePlacement", "type": "structure"}, + {"name": "CurrentImageId", "shape": "ImageId", "type": "string"}, + {"name": "DesiredImageId", "shape": "ImageId", "type": "string"}, ], "type": "structure", }, "ClusterNodeIds": {"member_shape": "ClusterNodeId", "member_type": "string", "type": "list"}, + "ClusterNodeLogicalIdList": { + "member_shape": "ClusterNodeLogicalId", + "member_type": "string", + "type": "list", + }, "ClusterNodeSummaries": { "member_shape": "ClusterNodeSummary", "member_type": "structure", @@ -1506,6 +1641,7 @@ "members": [ {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, {"name": "InstanceId", "shape": "String", "type": "string"}, + {"name": "NodeLogicalId", "shape": "String", "type": "string"}, {"name": "InstanceType", "shape": "ClusterInstanceType", "type": "string"}, {"name": "LaunchTime", "shape": "Timestamp", "type": "timestamp"}, {"name": "LastSoftwareUpdateTime", "shape": "Timestamp", "type": "timestamp"}, @@ -2103,6 +2239,11 @@ {"name": "Tags", "shape": "TagList", "type": "list"}, {"name": "Orchestrator", "shape": "ClusterOrchestrator", "type": "structure"}, {"name": "NodeRecovery", "shape": "ClusterNodeRecovery", "type": "string"}, + { + "name": "NodeProvisioningMode", + "shape": "ClusterNodeProvisioningMode", + "type": "string", + }, ], "type": "structure", }, @@ -4441,10 +4582,22 @@ ], "type": "structure", }, + "DescribeClusterEventRequest": { + "members": [ + {"name": "EventId", "shape": "EventId", "type": "string"}, + {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, + ], + "type": "structure", + }, + "DescribeClusterEventResponse": { + "members": [{"name": "EventDetails", "shape": "ClusterEventDetail", "type": "structure"}], + "type": "structure", + }, "DescribeClusterNodeRequest": { "members": [ {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, {"name": "NodeId", "shape": "ClusterNodeId", "type": "string"}, + {"name": "NodeLogicalId", "shape": "ClusterNodeLogicalId", "type": "string"}, ], "type": "structure", }, @@ -4472,6 +4625,11 @@ {"name": "VpcConfig", "shape": "VpcConfig", "type": "structure"}, {"name": "Orchestrator", "shape": "ClusterOrchestrator", "type": "structure"}, {"name": "NodeRecovery", "shape": "ClusterNodeRecovery", "type": "string"}, + { + "name": "NodeProvisioningMode", + "shape": "ClusterNodeProvisioningMode", + "type": "string", + }, ], "type": "structure", }, @@ -6693,6 +6851,8 @@ "type": "structure", }, "Edges": {"member_shape": "Edge", "member_type": "structure", "type": "list"}, + "EfaEnis": {"member_shape": "String", "member_type": "string", "type": "list"}, + "EksRoleAccessEntries": {"member_shape": "String", "member_type": "string", "type": "list"}, "EmrServerlessComputeConfig": { "members": [{"name": "ExecutionRoleARN", "shape": "RoleArn", "type": "string"}], "type": "structure", @@ -6908,6 +7068,23 @@ ], "type": "structure", }, + "EventDetails": { + "members": [{"name": "EventMetadata", "shape": "EventMetadata", "type": "structure"}], + "type": "structure", + }, + "EventMetadata": { + "members": [ + {"name": "Cluster", "shape": "ClusterMetadata", "type": "structure"}, + {"name": "InstanceGroup", "shape": "InstanceGroupMetadata", "type": "structure"}, + { + "name": "InstanceGroupScaling", + "shape": "InstanceGroupScalingMetadata", + "type": "structure", + }, + {"name": "Instance", "shape": "InstanceMetadata", "type": "structure"}, + ], + "type": "structure", + }, "ExecutionRoleArns": {"member_shape": "RoleArn", "member_type": "string", "type": "list"}, "Experiment": { "members": [ @@ -8366,12 +8543,42 @@ ], "type": "structure", }, + "InstanceGroupMetadata": { + "members": [ + {"name": "FailureMessage", "shape": "String", "type": "string"}, + {"name": "AvailabilityZoneId", "shape": "String", "type": "string"}, + {"name": "CapacityReservation", "shape": "CapacityReservation", "type": "structure"}, + {"name": "SubnetId", "shape": "String", "type": "string"}, + {"name": "SecurityGroupIds", "shape": "SecurityGroupIds", "type": "list"}, + {"name": "AmiOverride", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, "InstanceGroupNames": { "member_shape": "InstanceGroupName", "member_type": "string", "type": "list", }, + "InstanceGroupScalingMetadata": { + "members": [ + {"name": "InstanceCount", "shape": "InstanceCount", "type": "integer"}, + {"name": "TargetCount", "shape": "TargetCount", "type": "integer"}, + {"name": "FailureMessage", "shape": "String", "type": "string"}, + ], + "type": "structure", + }, "InstanceGroups": {"member_shape": "InstanceGroup", "member_type": "structure", "type": "list"}, + "InstanceMetadata": { + "members": [ + {"name": "CustomerEni", "shape": "String", "type": "string"}, + {"name": "AdditionalEnis", "shape": "AdditionalEnis", "type": "structure"}, + {"name": "CapacityReservation", "shape": "CapacityReservation", "type": "structure"}, + {"name": "FailureMessage", "shape": "String", "type": "string"}, + {"name": "LcsExecutionState", "shape": "String", "type": "string"}, + {"name": "NodeLogicalId", "shape": "ClusterNodeLogicalId", "type": "string"}, + ], + "type": "structure", + }, "InstanceMetadataServiceConfiguration": { "members": [ { @@ -8943,6 +9150,28 @@ ], "type": "structure", }, + "ListClusterEventsRequest": { + "members": [ + {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, + {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, + {"name": "NodeId", "shape": "ClusterNodeId", "type": "string"}, + {"name": "EventTimeAfter", "shape": "Timestamp", "type": "timestamp"}, + {"name": "EventTimeBefore", "shape": "Timestamp", "type": "timestamp"}, + {"name": "SortBy", "shape": "EventSortBy", "type": "string"}, + {"name": "SortOrder", "shape": "SortOrder", "type": "string"}, + {"name": "ResourceType", "shape": "ClusterEventResourceType", "type": "string"}, + {"name": "MaxResults", "shape": "ClusterEventMaxResults", "type": "integer"}, + {"name": "NextToken", "shape": "NextToken", "type": "string"}, + ], + "type": "structure", + }, + "ListClusterEventsResponse": { + "members": [ + {"name": "NextToken", "shape": "NextToken", "type": "string"}, + {"name": "Events", "shape": "ClusterEventSummaries", "type": "list"}, + ], + "type": "structure", + }, "ListClusterNodesRequest": { "members": [ {"name": "ClusterName", "shape": "ClusterNameOrArn", "type": "string"}, @@ -8957,6 +9186,11 @@ {"name": "NextToken", "shape": "NextToken", "type": "string"}, {"name": "SortBy", "shape": "ClusterSortBy", "type": "string"}, {"name": "SortOrder", "shape": "SortOrder", "type": "string"}, + { + "name": "IncludeNodeLogicalIds", + "shape": "IncludeNodeLogicalIdsBoolean", + "type": "boolean", + }, ], "type": "structure", }, @@ -11803,6 +12037,19 @@ ], "type": "structure", }, + "NodeAdditionResult": { + "members": [ + {"name": "NodeLogicalId", "shape": "ClusterNodeLogicalId", "type": "string"}, + {"name": "InstanceGroupName", "shape": "ClusterInstanceGroupName", "type": "string"}, + {"name": "Status", "shape": "ClusterInstanceStatus", "type": "string"}, + ], + "type": "structure", + }, + "NodeAdditionResultList": { + "member_shape": "NodeAdditionResult", + "member_type": "structure", + "type": "list", + }, "NotebookInstanceAcceleratorTypes": { "member_shape": "NotebookInstanceAcceleratorType", "member_type": "string", @@ -15457,6 +15704,7 @@ "type": "list", }, {"name": "DeploymentConfig", "shape": "DeploymentConfiguration", "type": "structure"}, + {"name": "ImageId", "shape": "ImageId", "type": "string"}, ], "type": "structure", }, diff --git a/src/sagemaker_core/main/resources.py b/src/sagemaker_core/main/resources.py index 097a079..64e5221 100644 --- a/src/sagemaker_core/main/resources.py +++ b/src/sagemaker_core/main/resources.py @@ -3223,6 +3223,7 @@ class Cluster(Base): vpc_config: orchestrator: The type of orchestrator used for the SageMaker HyperPod cluster. node_recovery: The node recovery mode configured for the SageMaker HyperPod cluster. + node_provisioning_mode: The mode used for provisioning nodes in the cluster. """ @@ -3238,6 +3239,7 @@ class Cluster(Base): vpc_config: Optional[shapes.VpcConfig] = Unassigned() orchestrator: Optional[shapes.ClusterOrchestrator] = Unassigned() node_recovery: Optional[str] = Unassigned() + node_provisioning_mode: Optional[str] = Unassigned() def get_name(self) -> str: attributes = vars(self) @@ -3287,6 +3289,7 @@ def create( tags: Optional[List[shapes.Tag]] = Unassigned(), orchestrator: Optional[shapes.ClusterOrchestrator] = Unassigned(), node_recovery: Optional[str] = Unassigned(), + node_provisioning_mode: Optional[str] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> Optional["Cluster"]: @@ -3301,6 +3304,7 @@ def create( tags: Custom tags for managing the SageMaker HyperPod cluster as an Amazon Web Services resource. You can add tags to your cluster in the same way you add them in other Amazon Web Services services that support tagging. To learn more about tagging Amazon Web Services resources in general, see Tagging Amazon Web Services Resources User Guide. orchestrator: The type of orchestrator to use for the SageMaker HyperPod cluster. Currently, the only supported value is "eks", which is to use an Amazon Elastic Kubernetes Service (EKS) cluster as the orchestrator. node_recovery: The node recovery mode for the SageMaker HyperPod cluster. When set to Automatic, SageMaker HyperPod will automatically reboot or replace faulty nodes when issues are detected. When set to None, cluster administrators will need to manually manage any faulty cluster instances. + node_provisioning_mode: The mode for provisioning nodes in the cluster. You can specify the following modes: Continuous: Scaling behavior that enables 1) concurrent operation execution within instance groups, 2) continuous retry mechanisms for failed operations, 3) enhanced customer visibility into cluster events through detailed event streams, 4) partial provisioning capabilities. Your clusters and instance groups remain InService while scaling. This mode is only supported for EKS orchestrated clusters. session: Boto3 session. region: Region name. @@ -3337,6 +3341,7 @@ def create( "Tags": tags, "Orchestrator": orchestrator, "NodeRecovery": node_recovery, + "NodeProvisioningMode": node_provisioning_mode, } operation_input_args = Base.populate_chained_attributes( @@ -3731,6 +3736,7 @@ def get_all( def get_node( self, node_id: Optional[str] = Unassigned(), + node_logical_id: Optional[str] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> Optional[shapes.ClusterNodeDetails]: @@ -3739,6 +3745,7 @@ def get_node( Parameters: node_id: The ID of the SageMaker HyperPod cluster node. + node_logical_id: The logical identifier of the node to describe. You can specify either NodeLogicalId or InstanceId, but not both. NodeLogicalId can be used to describe nodes that are still being provisioned and don't yet have an InstanceId assigned. session: Boto3 session. region: Region name. @@ -3761,6 +3768,7 @@ def get_node( operation_input_args = { "ClusterName": self.cluster_name, "NodeId": node_id, + "NodeLogicalId": node_logical_id, } # serialize the input request operation_input_args = serialize(operation_input_args) @@ -3785,6 +3793,7 @@ def get_all_nodes( instance_group_name_contains: Optional[str] = Unassigned(), sort_by: Optional[str] = Unassigned(), sort_order: Optional[str] = Unassigned(), + include_node_logical_ids: Optional[bool] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> ResourceIterator[shapes.ClusterNodeDetails]: @@ -3799,6 +3808,7 @@ def get_all_nodes( next_token: If the result of the previous ListClusterNodes request was truncated, the response includes a NextToken. To retrieve the next set of cluster nodes, use the token in the next request. sort_by: The field by which to sort results. The default value is CREATION_TIME. sort_order: The sort order for results. The default value is Ascending. + include_node_logical_ids: Specifies whether to include nodes that are still being provisioned in the response. When set to true, the response includes all nodes regardless of their provisioning status. When set to False (default), only nodes with assigned InstanceIds are returned. session: Boto3 session. region: Region name. @@ -3825,6 +3835,7 @@ def get_all_nodes( "InstanceGroupNameContains": instance_group_name_contains, "SortBy": sort_by, "SortOrder": sort_order, + "IncludeNodeLogicalIds": include_node_logical_ids, } # serialize the input request operation_input_args = serialize(operation_input_args) @@ -3847,6 +3858,7 @@ def get_all_nodes( def update_software( self, deployment_config: Optional[shapes.DeploymentConfiguration] = Unassigned(), + image_id: Optional[str] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> None: @@ -3855,6 +3867,7 @@ def update_software( Parameters: deployment_config: The configuration to use when updating the AMI versions. + image_id: When configuring your HyperPod cluster, you can specify an image ID using one of the following options: HyperPodPublicAmiId: Use a HyperPod public AMI CustomAmiId: Use your custom AMI default: Use the default latest system image f you choose to use a custom AMI (CustomAmiId), ensure it meets the following requirements: Encryption: The custom AMI must be unencrypted. Ownership: The custom AMI must be owned by the same Amazon Web Services account that is creating the HyperPod cluster. Volume support: Only the primary AMI snapshot volume is supported; additional AMI volumes are not supported. When updating the instance group's AMI through the UpdateClusterSoftware operation, if an instance group uses a custom AMI, you must provide an ImageId or use the default as input. session: Boto3 session. region: Region name. @@ -3876,6 +3889,7 @@ def update_software( "ClusterName": self.cluster_name, "InstanceGroups": self.instance_groups, "DeploymentConfig": deployment_config, + "ImageId": image_id, } # serialize the input request operation_input_args = serialize(operation_input_args) @@ -3893,6 +3907,7 @@ def update_software( def batch_delete_nodes( self, node_ids: Optional[List[str]] = Unassigned(), + node_logical_ids: Optional[List[str]] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> Optional[shapes.BatchDeleteClusterNodesResponse]: @@ -3901,6 +3916,7 @@ def batch_delete_nodes( Parameters: node_ids: A list of node IDs to be deleted from the specified cluster. For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes. If you need to delete more than 99 instances, contact Support for assistance. + node_logical_ids: A list of NodeLogicalIds identifying the nodes to be deleted. You can specify up to 50 NodeLogicalIds. You must specify either NodeLogicalIds, InstanceIds, or both, with a combined maximum of 50 identifiers. session: Boto3 session. region: Region name. @@ -3923,6 +3939,7 @@ def batch_delete_nodes( operation_input_args = { "ClusterName": self.cluster_name, "NodeIds": node_ids, + "NodeLogicalIds": node_logical_ids, } # serialize the input request operation_input_args = serialize(operation_input_args) diff --git a/src/sagemaker_core/main/shapes.py b/src/sagemaker_core/main/shapes.py index 7f7d405..4c9c898 100644 --- a/src/sagemaker_core/main/shapes.py +++ b/src/sagemaker_core/main/shapes.py @@ -494,6 +494,21 @@ class ActionSummary(Base): last_modified_time: Optional[datetime.datetime] = Unassigned() +class AddClusterNodeSpecification(Base): + """ + AddClusterNodeSpecification + Specifies an instance group and the number of nodes to add to it. + + Attributes + ---------------------- + instance_group_name: The name of the instance group to which you want to add nodes. + increment_target_count_by: The number of nodes to add to the specified instance group. The total number of nodes across all instance groups in a single request cannot exceed 50. + """ + + instance_group_name: str + increment_target_count_by: int + + class Tag(Base): """ Tag @@ -509,6 +524,19 @@ class Tag(Base): value: str +class AdditionalEnis(Base): + """ + AdditionalEnis + Information about additional Elastic Network Interfaces (ENIs) associated with an instance. + + Attributes + ---------------------- + efa_enis: A list of Elastic Fabric Adapter (EFA) ENIs associated with the instance. + """ + + efa_enis: Optional[List[str]] = Unassigned() + + class ModelAccessConfig(Base): """ ModelAccessConfig @@ -2400,6 +2428,42 @@ class Autotune(Base): mode: str +class BatchAddClusterNodesError(Base): + """ + BatchAddClusterNodesError + Information about an error that occurred during the node addition operation. + + Attributes + ---------------------- + instance_group_name: The name of the instance group for which the error occurred. + error_code: The error code associated with the failure. Possible values include InstanceGroupNotFound and InvalidInstanceGroupState. + failed_count: The number of nodes that failed to be added to the specified instance group. + message: A descriptive message providing additional details about the error. + """ + + instance_group_name: str + error_code: str + failed_count: int + message: Optional[str] = Unassigned() + + +class NodeAdditionResult(Base): + """ + NodeAdditionResult + Information about a node that was successfully added to the cluster. + + Attributes + ---------------------- + node_logical_id: A unique identifier assigned to the node that can be used to track its provisioning status through the DescribeClusterNode operation. + instance_group_name: The name of the instance group to which the node was added. + status: The current status of the node. Possible values include Pending, Running, Failed, ShuttingDown, SystemUpdating, DeepHealthCheckInProgress, and NotFound. + """ + + node_logical_id: str + instance_group_name: str + status: str + + class BatchDataCaptureConfig(Base): """ BatchDataCaptureConfig @@ -2417,6 +2481,23 @@ class BatchDataCaptureConfig(Base): generate_inference_id: Optional[bool] = Unassigned() +class BatchDeleteClusterNodeLogicalIdsError(Base): + """ + BatchDeleteClusterNodeLogicalIdsError + Information about an error that occurred when attempting to delete a node identified by its NodeLogicalId. + + Attributes + ---------------------- + code: The error code associated with the failure. Possible values include NodeLogicalIdNotFound, InvalidNodeStatus, and InternalError. + message: A descriptive message providing additional details about the error. + node_logical_id: The NodeLogicalId of the node that could not be deleted. + """ + + code: str + message: str + node_logical_id: str + + class BatchDeleteClusterNodesError(Base): """ BatchDeleteClusterNodesError @@ -2442,10 +2523,14 @@ class BatchDeleteClusterNodesResponse(Base): ---------------------- failed: A list of errors encountered when deleting the specified nodes. successful: A list of node IDs that were successfully deleted from the specified cluster. + failed_node_logical_ids: A list of NodeLogicalIds that could not be deleted, along with error information explaining why the deletion failed. + successful_node_logical_ids: A list of NodeLogicalIds that were successfully deleted from the cluster. """ failed: Optional[List[BatchDeleteClusterNodesError]] = Unassigned() successful: Optional[List[str]] = Unassigned() + failed_node_logical_ids: Optional[List[BatchDeleteClusterNodeLogicalIdsError]] = Unassigned() + successful_node_logical_ids: Optional[List[str]] = Unassigned() class BatchDescribeModelPackageError(Base): @@ -2901,6 +2986,21 @@ class CanvasAppSettings(Base): emr_serverless_settings: Optional[EmrServerlessSettings] = Unassigned() +class CapacityReservation(Base): + """ + CapacityReservation + Information about the Capacity Reservation used by an instance or instance group. + + Attributes + ---------------------- + arn: The Amazon Resource Name (ARN) of the Capacity Reservation. + type: The type of Capacity Reservation. Valid values are ODCR (On-Demand Capacity Reservation) or CRG (Capacity Reservation Group). + """ + + arn: Optional[str] = Unassigned() + type: Optional[str] = Unassigned() + + class CapacitySizeConfig(Base): """ CapacitySizeConfig @@ -3287,6 +3387,174 @@ class ClusterEbsVolumeConfig(Base): volume_size_in_gb: Optional[int] = Unassigned() +class ClusterMetadata(Base): + """ + ClusterMetadata + Metadata information about a SageMaker HyperPod cluster showing information about the cluster level operations, such as creating, updating, and deleting. + + Attributes + ---------------------- + failure_message: An error message describing why the cluster level operation (such as creating, updating, or deleting) failed. + eks_role_access_entries: A list of Amazon EKS IAM role ARNs associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters. + slr_access_entry: The Service-Linked Role (SLR) associated with the cluster. This is created by SageMaker HyperPod on your behalf and only applies for EKS-orchestrated clusters. + """ + + failure_message: Optional[str] = Unassigned() + eks_role_access_entries: Optional[List[str]] = Unassigned() + slr_access_entry: Optional[str] = Unassigned() + + +class InstanceGroupMetadata(Base): + """ + InstanceGroupMetadata + Metadata information about an instance group in a SageMaker HyperPod cluster. + + Attributes + ---------------------- + failure_message: An error message describing why the instance group level operation (such as creating, scaling, or deleting) failed. + availability_zone_id: The ID of the Availability Zone where the instance group is located. + capacity_reservation: Information about the Capacity Reservation used by the instance group. + subnet_id: The ID of the subnet where the instance group is located. + security_group_ids: A list of security group IDs associated with the instance group. + ami_override: If you use a custom Amazon Machine Image (AMI) for the instance group, this field shows the ID of the custom AMI. + """ + + failure_message: Optional[str] = Unassigned() + availability_zone_id: Optional[str] = Unassigned() + capacity_reservation: Optional[CapacityReservation] = Unassigned() + subnet_id: Optional[str] = Unassigned() + security_group_ids: Optional[List[str]] = Unassigned() + ami_override: Optional[str] = Unassigned() + + +class InstanceGroupScalingMetadata(Base): + """ + InstanceGroupScalingMetadata + Metadata information about scaling operations for an instance group. + + Attributes + ---------------------- + instance_count: The current number of instances in the group. + target_count: The desired number of instances for the group after scaling. + failure_message: An error message describing why the scaling operation failed, if applicable. + """ + + instance_count: Optional[int] = Unassigned() + target_count: Optional[int] = Unassigned() + failure_message: Optional[str] = Unassigned() + + +class InstanceMetadata(Base): + """ + InstanceMetadata + Metadata information about an instance in a HyperPod cluster. + + Attributes + ---------------------- + customer_eni: The ID of the customer-managed Elastic Network Interface (ENI) associated with the instance. + additional_enis: Information about additional Elastic Network Interfaces (ENIs) associated with the instance. + capacity_reservation: Information about the Capacity Reservation used by the instance. + failure_message: An error message describing why the instance creation or update failed, if applicable. + lcs_execution_state: The execution state of the Lifecycle Script (LCS) for the instance. + node_logical_id: The unique logical identifier of the node within the cluster. The ID used here is the same object as in the BatchAddClusterNodes API. + """ + + customer_eni: Optional[str] = Unassigned() + additional_enis: Optional[AdditionalEnis] = Unassigned() + capacity_reservation: Optional[CapacityReservation] = Unassigned() + failure_message: Optional[str] = Unassigned() + lcs_execution_state: Optional[str] = Unassigned() + node_logical_id: Optional[str] = Unassigned() + + +class EventMetadata(Base): + """ + EventMetadata + Metadata associated with a cluster event, which may include details about various resource types. + + Attributes + ---------------------- + cluster: Metadata specific to cluster-level events. + instance_group: Metadata specific to instance group-level events. + instance_group_scaling: Metadata related to instance group scaling events. + instance: Metadata specific to instance-level events. + """ + + cluster: Optional[ClusterMetadata] = Unassigned() + instance_group: Optional[InstanceGroupMetadata] = Unassigned() + instance_group_scaling: Optional[InstanceGroupScalingMetadata] = Unassigned() + instance: Optional[InstanceMetadata] = Unassigned() + + +class EventDetails(Base): + """ + EventDetails + Detailed information about a specific event, including event metadata. + + Attributes + ---------------------- + event_metadata: Metadata specific to the event, which may include information about the cluster, instance group, or instance involved. + """ + + event_metadata: Optional[EventMetadata] = Unassigned() + + +class ClusterEventDetail(Base): + """ + ClusterEventDetail + Detailed information about a specific event in a HyperPod cluster. + + Attributes + ---------------------- + event_id: The unique identifier (UUID) of the event. + cluster_arn: The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event. + cluster_name: The name of the SageMaker HyperPod cluster associated with the event. + instance_group_name: The name of the instance group associated with the event, if applicable. + instance_id: The EC2 instance ID associated with the event, if applicable. + resource_type: The type of resource associated with the event. Valid values are "Cluster", "InstanceGroup", or "Instance". + event_time: The timestamp when the event occurred. + event_details: Additional details about the event, including event-specific metadata. + description: A human-readable description of the event. + """ + + event_id: str + cluster_arn: str + cluster_name: Union[str, object] + resource_type: str + event_time: datetime.datetime + instance_group_name: Optional[str] = Unassigned() + instance_id: Optional[str] = Unassigned() + event_details: Optional[EventDetails] = Unassigned() + description: Optional[str] = Unassigned() + + +class ClusterEventSummary(Base): + """ + ClusterEventSummary + A summary of an event in a SageMaker HyperPod cluster. + + Attributes + ---------------------- + event_id: The unique identifier (UUID) of the event. + cluster_arn: The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster associated with the event. + cluster_name: The name of the SageMaker HyperPod cluster associated with the event. + instance_group_name: The name of the instance group associated with the event, if applicable. + instance_id: The EC2 instance ID associated with the event, if applicable. + resource_type: The type of resource associated with the event. Valid values are "Cluster", "InstanceGroup", or "Instance". + event_time: The timestamp when the event occurred. + description: A brief, human-readable description of the event. + """ + + event_id: str + cluster_arn: str + cluster_name: Union[str, object] + resource_type: str + event_time: datetime.datetime + instance_group_name: Optional[str] = Unassigned() + instance_id: Optional[str] = Unassigned() + description: Optional[str] = Unassigned() + + class ClusterLifeCycleConfig(Base): """ ClusterLifeCycleConfig @@ -3383,6 +3651,8 @@ class ClusterInstanceGroupDetails(Base): training_plan_status: The current status of the training plan associated with this cluster instance group. override_vpc_config: The customized Amazon VPC configuration at the instance group level that overrides the default Amazon VPC configuration of the SageMaker HyperPod cluster. scheduled_update_config: The configuration object of the schedule that SageMaker follows when updating the AMI. + current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the instance group. + desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the instance group. """ current_count: Optional[int] = Unassigned() @@ -3399,6 +3669,8 @@ class ClusterInstanceGroupDetails(Base): training_plan_status: Optional[str] = Unassigned() override_vpc_config: Optional[VpcConfig] = Unassigned() scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned() + current_image_id: Optional[str] = Unassigned() + desired_image_id: Optional[str] = Unassigned() class ClusterInstanceGroupSpecification(Base): @@ -3419,6 +3691,7 @@ class ClusterInstanceGroupSpecification(Base): training_plan_arn: The Amazon Resource Name (ARN); of the training plan to use for this cluster instance group. For more information about how to reserve GPU capacity for your SageMaker HyperPod clusters using Amazon SageMaker Training Plan, see CreateTrainingPlan . override_vpc_config: To configure multi-AZ deployments, customize the Amazon VPC configuration at the instance group level. You can specify different subnets and security groups across different AZs in the instance group specification to override a SageMaker HyperPod cluster's default Amazon VPC configuration. For more information about deploying a cluster in multiple AZs, see Setting up SageMaker HyperPod clusters across multiple AZs. When your Amazon VPC and subnets support IPv6, network communications differ based on the cluster orchestration platform: Slurm-orchestrated clusters automatically configure nodes with dual IPv6 and IPv4 addresses, allowing immediate IPv6 network communications. In Amazon EKS-orchestrated clusters, nodes receive dual-stack addressing, but pods can only use IPv6 when the Amazon EKS cluster is explicitly IPv6-enabled. For information about deploying an IPv6 Amazon EKS cluster, see Amazon EKS IPv6 Cluster Deployment. Additional resources for IPv6 configuration: For information about adding IPv6 support to your VPC, see to IPv6 Support for VPC. For information about creating a new IPv6-compatible VPC, see Amazon VPC Creation Guide. To configure SageMaker HyperPod with a custom Amazon VPC, see Custom Amazon VPC Setup for SageMaker HyperPod. scheduled_update_config: The configuration object of the schedule that SageMaker uses to update the AMI. + image_id: When configuring your HyperPod cluster, you can specify an image ID using one of the following options: HyperPodPublicAmiId: Use a HyperPod public AMI CustomAmiId: Use your custom AMI default: Use the default latest system image f you choose to use a custom AMI (CustomAmiId), ensure it meets the following requirements: Encryption: The custom AMI must be unencrypted. Ownership: The custom AMI must be owned by the same Amazon Web Services account that is creating the HyperPod cluster. Volume support: Only the primary AMI snapshot volume is supported; additional AMI volumes are not supported. When updating the instance group's AMI through the UpdateClusterSoftware operation, if an instance group uses a custom AMI, you must provide an ImageId or use the default as input. """ instance_count: int @@ -3432,6 +3705,7 @@ class ClusterInstanceGroupSpecification(Base): training_plan_arn: Optional[str] = Unassigned() override_vpc_config: Optional[VpcConfig] = Unassigned() scheduled_update_config: Optional[ScheduledUpdateConfig] = Unassigned() + image_id: Optional[str] = Unassigned() class ClusterInstancePlacement(Base): @@ -3473,6 +3747,7 @@ class ClusterNodeDetails(Base): ---------------------- instance_group_name: The instance group name in which the instance is. instance_id: The ID of the instance. + node_logical_id: A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId. instance_status: The status of the instance. instance_type: The type of the instance. launch_time: The time when the instance is launched. @@ -3485,10 +3760,13 @@ class ClusterNodeDetails(Base): private_primary_ipv6: The private primary IPv6 address of the SageMaker HyperPod cluster node when configured with an Amazon VPC that supports IPv6 and includes subnets with IPv6 addressing enabled in either the cluster Amazon VPC configuration or the instance group Amazon VPC configuration. private_dns_hostname: The private DNS hostname of the SageMaker HyperPod cluster node. placement: The placement details of the SageMaker HyperPod cluster node. + current_image_id: The ID of the Amazon Machine Image (AMI) currently in use by the node. + desired_image_id: The ID of the Amazon Machine Image (AMI) desired for the node. """ instance_group_name: Optional[str] = Unassigned() instance_id: Optional[str] = Unassigned() + node_logical_id: Optional[str] = Unassigned() instance_status: Optional[ClusterInstanceStatusDetails] = Unassigned() instance_type: Optional[str] = Unassigned() launch_time: Optional[datetime.datetime] = Unassigned() @@ -3501,6 +3779,8 @@ class ClusterNodeDetails(Base): private_primary_ipv6: Optional[str] = Unassigned() private_dns_hostname: Optional[str] = Unassigned() placement: Optional[ClusterInstancePlacement] = Unassigned() + current_image_id: Optional[str] = Unassigned() + desired_image_id: Optional[str] = Unassigned() class ClusterNodeSummary(Base): @@ -3512,6 +3792,7 @@ class ClusterNodeSummary(Base): ---------------------- instance_group_name: The name of the instance group in which the instance is. instance_id: The ID of the instance. + node_logical_id: A unique identifier for the node that persists throughout its lifecycle, from provisioning request to termination. This identifier can be used to track the node even before it has an assigned InstanceId. This field is only included when IncludeNodeLogicalIds is set to True in the ListClusterNodes request. instance_type: The type of the instance. launch_time: The time when the instance is launched. last_software_update_time: The time when SageMaker last updated the software of the instances in the cluster. @@ -3523,6 +3804,7 @@ class ClusterNodeSummary(Base): instance_type: str launch_time: datetime.datetime instance_status: ClusterInstanceStatusDetails + node_logical_id: Optional[str] = Unassigned() last_software_update_time: Optional[datetime.datetime] = Unassigned() diff --git a/src/sagemaker_core/tools/api_coverage.json b/src/sagemaker_core/tools/api_coverage.json index e0b0d52..3652405 100644 --- a/src/sagemaker_core/tools/api_coverage.json +++ b/src/sagemaker_core/tools/api_coverage.json @@ -1 +1 @@ -{"SupportedAPIs": 363, "UnsupportedAPIs": 10} \ No newline at end of file +{"SupportedAPIs": 363, "UnsupportedAPIs": 13} \ No newline at end of file diff --git a/tst/tools/test_resources_codegen.py b/tst/tools/test_resources_codegen.py index 725c16a..76d465d 100644 --- a/tst/tools/test_resources_codegen.py +++ b/tst/tools/test_resources_codegen.py @@ -1254,6 +1254,7 @@ def test_get_node(self): def get_node( self, node_id: Optional[str] = Unassigned(), + node_logical_id: Optional[str] = Unassigned(), session: Optional[Session] = None, region: Optional[str] = None, ) -> Optional[shapes.ClusterNodeDetails]: @@ -1262,6 +1263,7 @@ def get_node( Parameters: node_id: The ID of the SageMaker HyperPod cluster node. + node_logical_id: The logical identifier of the node to describe. You can specify either NodeLogicalId or InstanceId, but not both. NodeLogicalId can be used to describe nodes that are still being provisioned and don't yet have an InstanceId assigned. session: Boto3 session. region: Region name. @@ -1285,6 +1287,7 @@ def get_node( operation_input_args = { 'ClusterName': self.cluster_name, 'NodeId': node_id, + 'NodeLogicalId': node_logical_id, } # serialize the input request operation_input_args = serialize(operation_input_args)