aws-sdk-sagemaker 1.259.0 → 1.260.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0d2515128ef79ca8ccf13a36a69ecc525ff9d79545bc9c455dc987af7a50cb60
-  data.tar.gz: 55514ebf0ac1ec80f0ac2c955ad30620ee4e6fbdd3fde34758f0800c342cbb97
+  metadata.gz: 2589d5cd4826661e7504b3ed54c6b9c455b07260d4ef28a4d2c176815e45c729
+  data.tar.gz: db5af3252d504b04fcf42e843d05d102e42b8c9f1227e84bfab957af0f787d5c
 SHA512:
-  metadata.gz: e0a8efa87315e0c8000f61ecbb54bf0b9990ca020a81e8bf290982ae6144cc655992b7fbe541839e8eec27436953d6254c82488cd575266fa9868afac4c7f5fd
-  data.tar.gz: bc5f713b51325fc5af5336f96094638baf939c792f31cd1cbceae40068356547bd4608b12d169e6ae706874a2f656974db3d8e5bd25e5bdc0bb4d64aa3db99e2
+  metadata.gz: 1fcd84da3dc70c36b6ea187764b4df34bd4a6579e52ca87c27b574e62542300e52a7775af2b422c8b98cbf8b8d9a955d8a1cd13402f7d437eab0a7c6c7e2f796
+  data.tar.gz: b84e0ba2ee87e940bac12b21cb53d154afcc3865fc02baa8160c71984cdf4330fb80454f3f6914d3fffc5eb65c12ca21a3bfaa390727570b461928d44aa3ac68

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.260.0 (2024-09-09)
+------------------
+
+* Feature - Amazon Sagemaker supports orchestrating SageMaker HyperPod clusters with Amazon EKS
+
 1.259.0 (2024-09-05)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.259.0
+1.260.0

data/lib/aws-sdk-sagemaker/client.rb

@@ -1873,6 +1873,18 @@ module Aws::SageMaker
     #
     #   [1]: https://docs.aws.amazon.com/tag-editor/latest/userguide/tagging.html
     #
+    # @option params [Types::ClusterOrchestrator] :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.
+    #
+    # @option params [String] :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.
+    #
     # @return [Types::CreateClusterResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
     #
     #   * {Types::CreateClusterResponse#cluster_arn #cluster_arn} => String
@@ -1890,7 +1902,7 @@ module Aws::SageMaker
     #           source_s3_uri: "S3Uri", # required
     #           on_create: "ClusterLifeCycleConfigFileName", # required
     #         },
-    #         execution_role: "IAMRoleArn", # required
+    #         execution_role: "RoleArn", # required
     #         threads_per_core: 1,
     #         instance_storage_configs: [
     #           {
@@ -1899,6 +1911,7 @@ module Aws::SageMaker
     #             },
     #           },
     #         ],
+    #         on_start_deep_health_checks: ["InstanceStress"], # accepts InstanceStress, InstanceConnectivity
     #       },
     #     ],
     #     vpc_config: {
@@ -1911,6 +1924,12 @@ module Aws::SageMaker
     #         value: "TagValue", # required
     #       },
     #     ],
+    #     orchestrator: {
+    #       eks: { # required
+    #         cluster_arn: "EksClusterArn", # required
+    #       },
+    #     },
+    #     node_recovery: "Automatic", # accepts Automatic, None
     #   })
     #
     # @example Response structure
@@ -12062,6 +12081,8 @@ module Aws::SageMaker
     #   * {Types::DescribeClusterResponse#failure_message #failure_message} => String
     #   * {Types::DescribeClusterResponse#instance_groups #instance_groups} => Array<Types::ClusterInstanceGroupDetails>
     #   * {Types::DescribeClusterResponse#vpc_config #vpc_config} => Types::VpcConfig
+    #   * {Types::DescribeClusterResponse#orchestrator #orchestrator} => Types::ClusterOrchestrator
+    #   * {Types::DescribeClusterResponse#node_recovery #node_recovery} => String
     #
     # @example Request syntax with placeholder values
     #
@@ -12087,10 +12108,14 @@ module Aws::SageMaker
     #   resp.instance_groups[0].threads_per_core #=> Integer
     #   resp.instance_groups[0].instance_storage_configs #=> Array
     #   resp.instance_groups[0].instance_storage_configs[0].ebs_volume_config.volume_size_in_gb #=> Integer
+    #   resp.instance_groups[0].on_start_deep_health_checks #=> Array
+    #   resp.instance_groups[0].on_start_deep_health_checks[0] #=> String, one of "InstanceStress", "InstanceConnectivity"
     #   resp.vpc_config.security_group_ids #=> Array
     #   resp.vpc_config.security_group_ids[0] #=> String
     #   resp.vpc_config.subnets #=> Array
     #   resp.vpc_config.subnets[0] #=> String
+    #   resp.orchestrator.eks.cluster_arn #=> String
+    #   resp.node_recovery #=> String, one of "Automatic", "None"
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeCluster AWS API Documentation
     #
@@ -12126,7 +12151,7 @@ module Aws::SageMaker
     #
     #   resp.node_details.instance_group_name #=> String
     #   resp.node_details.instance_id #=> String
-    #   resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating"
+    #   resp.node_details.instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress"
     #   resp.node_details.instance_status.message #=> String
     #   resp.node_details.instance_type #=> String, one of "ml.p4d.24xlarge", "ml.p4de.24xlarge", "ml.p5.48xlarge", "ml.trn1.32xlarge", "ml.trn1n.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.12xlarge", "ml.c5.18xlarge", "ml.c5.24xlarge", "ml.c5n.large", "ml.c5n.2xlarge", "ml.c5n.4xlarge", "ml.c5n.9xlarge", "ml.c5n.18xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.8xlarge", "ml.m5.12xlarge", "ml.m5.16xlarge", "ml.m5.24xlarge", "ml.t3.medium", "ml.t3.large", "ml.t3.xlarge", "ml.t3.2xlarge"
     #   resp.node_details.launch_time #=> Time
@@ -18137,7 +18162,7 @@ module Aws::SageMaker
     #   resp.cluster_node_summaries[0].instance_id #=> String
     #   resp.cluster_node_summaries[0].instance_type #=> String, one of "ml.p4d.24xlarge", "ml.p4de.24xlarge", "ml.p5.48xlarge", "ml.trn1.32xlarge", "ml.trn1n.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.12xlarge", "ml.c5.18xlarge", "ml.c5.24xlarge", "ml.c5n.large", "ml.c5n.2xlarge", "ml.c5n.4xlarge", "ml.c5n.9xlarge", "ml.c5n.18xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.8xlarge", "ml.m5.12xlarge", "ml.m5.16xlarge", "ml.m5.24xlarge", "ml.t3.medium", "ml.t3.large", "ml.t3.xlarge", "ml.t3.2xlarge"
     #   resp.cluster_node_summaries[0].launch_time #=> Time
-    #   resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating"
+    #   resp.cluster_node_summaries[0].instance_status.status #=> String, one of "Running", "Failure", "Pending", "ShuttingDown", "SystemUpdating", "DeepHealthCheckInProgress"
     #   resp.cluster_node_summaries[0].instance_status.message #=> String
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterNodes AWS API Documentation
@@ -24719,6 +24744,10 @@ module Aws::SageMaker
     # @option params [required, Array<Types::ClusterInstanceGroupSpecification>] :instance_groups
     #   Specify the instance groups to update.
     #
+    # @option params [String] :node_recovery
+    #   The node recovery mode to be applied to the SageMaker HyperPod
+    #   cluster.
+    #
     # @return [Types::UpdateClusterResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
     #
     #   * {Types::UpdateClusterResponse#cluster_arn #cluster_arn} => String
@@ -24736,7 +24765,7 @@ module Aws::SageMaker
     #           source_s3_uri: "S3Uri", # required
     #           on_create: "ClusterLifeCycleConfigFileName", # required
     #         },
-    #         execution_role: "IAMRoleArn", # required
+    #         execution_role: "RoleArn", # required
     #         threads_per_core: 1,
     #         instance_storage_configs: [
     #           {
@@ -24745,8 +24774,10 @@ module Aws::SageMaker
     #             },
     #           },
     #         ],
+    #         on_start_deep_health_checks: ["InstanceStress"], # accepts InstanceStress, InstanceConnectivity
     #       },
     #     ],
+    #     node_recovery: "Automatic", # accepts Automatic, None
     #   })
     #
     # @example Response structure
@@ -27737,7 +27768,7 @@ module Aws::SageMaker
         tracer: tracer
       )
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.259.0'
+      context[:gem_version] = '1.260.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemaker/client_api.rb

@@ -283,9 +283,12 @@ module Aws::SageMaker
     ClusterNameOrArn = Shapes::StringShape.new(name: 'ClusterNameOrArn')
     ClusterNodeDetails = Shapes::StructureShape.new(name: 'ClusterNodeDetails')
     ClusterNodeId = Shapes::StringShape.new(name: 'ClusterNodeId')
+    ClusterNodeRecovery = Shapes::StringShape.new(name: 'ClusterNodeRecovery')
     ClusterNodeSummaries = Shapes::ListShape.new(name: 'ClusterNodeSummaries')
     ClusterNodeSummary = Shapes::StructureShape.new(name: 'ClusterNodeSummary')
     ClusterNonNegativeInstanceCount = Shapes::IntegerShape.new(name: 'ClusterNonNegativeInstanceCount')
+    ClusterOrchestrator = Shapes::StructureShape.new(name: 'ClusterOrchestrator')
+    ClusterOrchestratorEksConfig = Shapes::StructureShape.new(name: 'ClusterOrchestratorEksConfig')
     ClusterPrivateDnsHostname = Shapes::StringShape.new(name: 'ClusterPrivateDnsHostname')
     ClusterPrivatePrimaryIp = Shapes::StringShape.new(name: 'ClusterPrivatePrimaryIp')
     ClusterSortBy = Shapes::StringShape.new(name: 'ClusterSortBy')
@@ -510,6 +513,7 @@ module Aws::SageMaker
     DebugRuleConfigurations = Shapes::ListShape.new(name: 'DebugRuleConfigurations')
     DebugRuleEvaluationStatus = Shapes::StructureShape.new(name: 'DebugRuleEvaluationStatus')
     DebugRuleEvaluationStatuses = Shapes::ListShape.new(name: 'DebugRuleEvaluationStatuses')
+    DeepHealthCheckType = Shapes::StringShape.new(name: 'DeepHealthCheckType')
     DefaultEbsStorageSettings = Shapes::StructureShape.new(name: 'DefaultEbsStorageSettings')
     DefaultGid = Shapes::IntegerShape.new(name: 'DefaultGid')
     DefaultSpaceSettings = Shapes::StructureShape.new(name: 'DefaultSpaceSettings')
@@ -812,6 +816,7 @@ module Aws::SageMaker
     EdgeVersion = Shapes::StringShape.new(name: 'EdgeVersion')
     Edges = Shapes::ListShape.new(name: 'Edges')
     EfsUid = Shapes::StringShape.new(name: 'EfsUid')
+    EksClusterArn = Shapes::StringShape.new(name: 'EksClusterArn')
     EmrServerlessComputeConfig = Shapes::StructureShape.new(name: 'EmrServerlessComputeConfig')
     EmrServerlessSettings = Shapes::StructureShape.new(name: 'EmrServerlessSettings')
     EmrSettings = Shapes::StructureShape.new(name: 'EmrSettings')
@@ -1048,7 +1053,6 @@ module Aws::SageMaker
     HyperbandStrategyConfig = Shapes::StructureShape.new(name: 'HyperbandStrategyConfig')
     HyperbandStrategyMaxResource = Shapes::IntegerShape.new(name: 'HyperbandStrategyMaxResource')
     HyperbandStrategyMinResource = Shapes::IntegerShape.new(name: 'HyperbandStrategyMinResource')
-    IAMRoleArn = Shapes::StringShape.new(name: 'IAMRoleArn')
     IamIdentity = Shapes::StructureShape.new(name: 'IamIdentity')
     IamPolicyConstraints = Shapes::StructureShape.new(name: 'IamPolicyConstraints')
     IdempotencyToken = Shapes::StringShape.new(name: 'IdempotencyToken')
@@ -1638,6 +1642,7 @@ module Aws::SageMaker
     OidcConfigForResponse = Shapes::StructureShape.new(name: 'OidcConfigForResponse')
     OidcEndpoint = Shapes::StringShape.new(name: 'OidcEndpoint')
     OidcMemberDefinition = Shapes::StructureShape.new(name: 'OidcMemberDefinition')
+    OnStartDeepHealthChecks = Shapes::ListShape.new(name: 'OnStartDeepHealthChecks')
     OnlineStoreConfig = Shapes::StructureShape.new(name: 'OnlineStoreConfig')
     OnlineStoreConfigUpdate = Shapes::StructureShape.new(name: 'OnlineStoreConfigUpdate')
     OnlineStoreSecurityConfig = Shapes::StructureShape.new(name: 'OnlineStoreSecurityConfig')
@@ -2962,9 +2967,10 @@ module Aws::SageMaker
     ClusterInstanceGroupDetails.add_member(:instance_group_name, Shapes::ShapeRef.new(shape: ClusterInstanceGroupName, location_name: "InstanceGroupName"))
     ClusterInstanceGroupDetails.add_member(:instance_type, Shapes::ShapeRef.new(shape: ClusterInstanceType, location_name: "InstanceType"))
     ClusterInstanceGroupDetails.add_member(:life_cycle_config, Shapes::ShapeRef.new(shape: ClusterLifeCycleConfig, location_name: "LifeCycleConfig"))
-    ClusterInstanceGroupDetails.add_member(:execution_role, Shapes::ShapeRef.new(shape: IAMRoleArn, location_name: "ExecutionRole"))
+    ClusterInstanceGroupDetails.add_member(:execution_role, Shapes::ShapeRef.new(shape: RoleArn, location_name: "ExecutionRole"))
     ClusterInstanceGroupDetails.add_member(:threads_per_core, Shapes::ShapeRef.new(shape: ClusterThreadsPerCore, location_name: "ThreadsPerCore"))
     ClusterInstanceGroupDetails.add_member(:instance_storage_configs, Shapes::ShapeRef.new(shape: ClusterInstanceStorageConfigs, location_name: "InstanceStorageConfigs"))
+    ClusterInstanceGroupDetails.add_member(:on_start_deep_health_checks, Shapes::ShapeRef.new(shape: OnStartDeepHealthChecks, location_name: "OnStartDeepHealthChecks"))
     ClusterInstanceGroupDetails.struct_class = Types::ClusterInstanceGroupDetails
 
     ClusterInstanceGroupDetailsList.member = Shapes::ShapeRef.new(shape: ClusterInstanceGroupDetails)
@@ -2973,9 +2979,10 @@ module Aws::SageMaker
     ClusterInstanceGroupSpecification.add_member(:instance_group_name, Shapes::ShapeRef.new(shape: ClusterInstanceGroupName, required: true, location_name: "InstanceGroupName"))
     ClusterInstanceGroupSpecification.add_member(:instance_type, Shapes::ShapeRef.new(shape: ClusterInstanceType, required: true, location_name: "InstanceType"))
     ClusterInstanceGroupSpecification.add_member(:life_cycle_config, Shapes::ShapeRef.new(shape: ClusterLifeCycleConfig, required: true, location_name: "LifeCycleConfig"))
-    ClusterInstanceGroupSpecification.add_member(:execution_role, Shapes::ShapeRef.new(shape: IAMRoleArn, required: true, location_name: "ExecutionRole"))
+    ClusterInstanceGroupSpecification.add_member(:execution_role, Shapes::ShapeRef.new(shape: RoleArn, required: true, location_name: "ExecutionRole"))
     ClusterInstanceGroupSpecification.add_member(:threads_per_core, Shapes::ShapeRef.new(shape: ClusterThreadsPerCore, location_name: "ThreadsPerCore"))
     ClusterInstanceGroupSpecification.add_member(:instance_storage_configs, Shapes::ShapeRef.new(shape: ClusterInstanceStorageConfigs, location_name: "InstanceStorageConfigs"))
+    ClusterInstanceGroupSpecification.add_member(:on_start_deep_health_checks, Shapes::ShapeRef.new(shape: OnStartDeepHealthChecks, location_name: "OnStartDeepHealthChecks"))
     ClusterInstanceGroupSpecification.struct_class = Types::ClusterInstanceGroupSpecification
 
     ClusterInstanceGroupSpecifications.member = Shapes::ShapeRef.new(shape: ClusterInstanceGroupSpecification)
@@ -3022,6 +3029,12 @@ module Aws::SageMaker
     ClusterNodeSummary.add_member(:instance_status, Shapes::ShapeRef.new(shape: ClusterInstanceStatusDetails, required: true, location_name: "InstanceStatus"))
     ClusterNodeSummary.struct_class = Types::ClusterNodeSummary
 
+    ClusterOrchestrator.add_member(:eks, Shapes::ShapeRef.new(shape: ClusterOrchestratorEksConfig, required: true, location_name: "Eks"))
+    ClusterOrchestrator.struct_class = Types::ClusterOrchestrator
+
+    ClusterOrchestratorEksConfig.add_member(:cluster_arn, Shapes::ShapeRef.new(shape: EksClusterArn, required: true, location_name: "ClusterArn"))
+    ClusterOrchestratorEksConfig.struct_class = Types::ClusterOrchestratorEksConfig
+
     ClusterSummaries.member = Shapes::ShapeRef.new(shape: ClusterSummary)
 
     ClusterSummary.add_member(:cluster_arn, Shapes::ShapeRef.new(shape: ClusterArn, required: true, location_name: "ClusterArn"))
@@ -3252,6 +3265,8 @@ module Aws::SageMaker
     CreateClusterRequest.add_member(:instance_groups, Shapes::ShapeRef.new(shape: ClusterInstanceGroupSpecifications, required: true, location_name: "InstanceGroups"))
     CreateClusterRequest.add_member(:vpc_config, Shapes::ShapeRef.new(shape: VpcConfig, location_name: "VpcConfig"))
     CreateClusterRequest.add_member(:tags, Shapes::ShapeRef.new(shape: TagList, location_name: "Tags"))
+    CreateClusterRequest.add_member(:orchestrator, Shapes::ShapeRef.new(shape: ClusterOrchestrator, location_name: "Orchestrator"))
+    CreateClusterRequest.add_member(:node_recovery, Shapes::ShapeRef.new(shape: ClusterNodeRecovery, location_name: "NodeRecovery"))
     CreateClusterRequest.struct_class = Types::CreateClusterRequest
 
     CreateClusterResponse.add_member(:cluster_arn, Shapes::ShapeRef.new(shape: ClusterArn, required: true, location_name: "ClusterArn"))
@@ -4468,6 +4483,8 @@ module Aws::SageMaker
     DescribeClusterResponse.add_member(:failure_message, Shapes::ShapeRef.new(shape: String, location_name: "FailureMessage"))
     DescribeClusterResponse.add_member(:instance_groups, Shapes::ShapeRef.new(shape: ClusterInstanceGroupDetailsList, required: true, location_name: "InstanceGroups"))
     DescribeClusterResponse.add_member(:vpc_config, Shapes::ShapeRef.new(shape: VpcConfig, location_name: "VpcConfig"))
+    DescribeClusterResponse.add_member(:orchestrator, Shapes::ShapeRef.new(shape: ClusterOrchestrator, location_name: "Orchestrator"))
+    DescribeClusterResponse.add_member(:node_recovery, Shapes::ShapeRef.new(shape: ClusterNodeRecovery, location_name: "NodeRecovery"))
     DescribeClusterResponse.struct_class = Types::DescribeClusterResponse
 
     DescribeCodeRepositoryInput.add_member(:code_repository_name, Shapes::ShapeRef.new(shape: EntityName, required: true, location_name: "CodeRepositoryName"))
@@ -8389,6 +8406,8 @@ module Aws::SageMaker
     OidcMemberDefinition.add_member(:groups, Shapes::ShapeRef.new(shape: Groups, location_name: "Groups"))
     OidcMemberDefinition.struct_class = Types::OidcMemberDefinition
 
+    OnStartDeepHealthChecks.member = Shapes::ShapeRef.new(shape: DeepHealthCheckType)
+
     OnlineStoreConfig.add_member(:security_config, Shapes::ShapeRef.new(shape: OnlineStoreSecurityConfig, location_name: "SecurityConfig"))
     OnlineStoreConfig.add_member(:enable_online_store, Shapes::ShapeRef.new(shape: Boolean, location_name: "EnableOnlineStore"))
     OnlineStoreConfig.add_member(:ttl_duration, Shapes::ShapeRef.new(shape: TtlDuration, location_name: "TtlDuration"))
@@ -9968,6 +9987,7 @@ module Aws::SageMaker
 
     UpdateClusterRequest.add_member(:cluster_name, Shapes::ShapeRef.new(shape: ClusterNameOrArn, required: true, location_name: "ClusterName"))
     UpdateClusterRequest.add_member(:instance_groups, Shapes::ShapeRef.new(shape: ClusterInstanceGroupSpecifications, required: true, location_name: "InstanceGroups"))
+    UpdateClusterRequest.add_member(:node_recovery, Shapes::ShapeRef.new(shape: ClusterNodeRecovery, location_name: "NodeRecovery"))
     UpdateClusterRequest.struct_class = Types::UpdateClusterRequest
 
     UpdateClusterResponse.add_member(:cluster_arn, Shapes::ShapeRef.new(shape: ClusterArn, required: true, location_name: "ClusterArn"))

data/lib/aws-sdk-sagemaker/types.rb

@@ -4157,6 +4157,11 @@ module Aws::SageMaker
     #   SageMaker HyperPod cluster instance group.
     #   @return [Array<Types::ClusterInstanceStorageConfig>]
     #
+    # @!attribute [rw] on_start_deep_health_checks
+    #   A flag indicating whether deep health checks should be performed
+    #   when the cluster instance group is created or updated.
+    #   @return [Array<String>]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterInstanceGroupDetails AWS API Documentation
     #
     class ClusterInstanceGroupDetails < Struct.new(
@@ -4167,7 +4172,8 @@ module Aws::SageMaker
       :life_cycle_config,
       :execution_role,
       :threads_per_core,
-      :instance_storage_configs)
+      :instance_storage_configs,
+      :on_start_deep_health_checks)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -4214,6 +4220,11 @@ module Aws::SageMaker
     #   the SageMaker HyperPod cluster instance group.
     #   @return [Array<Types::ClusterInstanceStorageConfig>]
     #
+    # @!attribute [rw] on_start_deep_health_checks
+    #   A flag indicating whether deep health checks should be performed
+    #   when the cluster instance group is created or updated.
+    #   @return [Array<String>]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterInstanceGroupSpecification AWS API Documentation
     #
     class ClusterInstanceGroupSpecification < Struct.new(
@@ -4223,7 +4234,8 @@ module Aws::SageMaker
       :life_cycle_config,
       :execution_role,
       :threads_per_core,
-      :instance_storage_configs)
+      :instance_storage_configs,
+      :on_start_deep_health_checks)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -4436,6 +4448,37 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
+    # The type of orchestrator used for the SageMaker HyperPod cluster.
+    #
+    # @!attribute [rw] eks
+    #   The Amazon EKS cluster used as the orchestrator for the SageMaker
+    #   HyperPod cluster.
+    #   @return [Types::ClusterOrchestratorEksConfig]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterOrchestrator AWS API Documentation
+    #
+    class ClusterOrchestrator < Struct.new(
+      :eks)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # The configuration settings for the Amazon EKS cluster used as the
+    # orchestrator for the SageMaker HyperPod cluster.
+    #
+    # @!attribute [rw] cluster_arn
+    #   The Amazon Resource Name (ARN) of the Amazon EKS cluster associated
+    #   with the SageMaker HyperPod cluster.
+    #   @return [String]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterOrchestratorEksConfig AWS API Documentation
+    #
+    class ClusterOrchestratorEksConfig < Struct.new(
+      :cluster_arn)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Lists a summary of the properties of a SageMaker HyperPod cluster.
     #
     # @!attribute [rw] cluster_arn
@@ -5738,13 +5781,29 @@ module Aws::SageMaker
     #   [1]: https://docs.aws.amazon.com/tag-editor/latest/userguide/tagging.html
     #   @return [Array<Types::Tag>]
     #
+    # @!attribute [rw] 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.
+    #   @return [Types::ClusterOrchestrator]
+    #
+    # @!attribute [rw] 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.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CreateClusterRequest AWS API Documentation
     #
     class CreateClusterRequest < Struct.new(
       :cluster_name,
       :instance_groups,
       :vpc_config,
-      :tags)
+      :tags,
+      :orchestrator,
+      :node_recovery)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -12807,6 +12866,15 @@ module Aws::SageMaker
     #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html
     #   @return [Types::VpcConfig]
     #
+    # @!attribute [rw] orchestrator
+    #   The type of orchestrator used for the SageMaker HyperPod cluster.
+    #   @return [Types::ClusterOrchestrator]
+    #
+    # @!attribute [rw] node_recovery
+    #   The node recovery mode configured for the SageMaker HyperPod
+    #   cluster.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeClusterResponse AWS API Documentation
     #
     class DescribeClusterResponse < Struct.new(
@@ -12816,7 +12884,9 @@ module Aws::SageMaker
       :creation_time,
       :failure_message,
       :instance_groups,
-      :vpc_config)
+      :vpc_config,
+      :orchestrator,
+      :node_recovery)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -44979,11 +45049,17 @@ module Aws::SageMaker
     #   Specify the instance groups to update.
     #   @return [Array<Types::ClusterInstanceGroupSpecification>]
     #
+    # @!attribute [rw] node_recovery
+    #   The node recovery mode to be applied to the SageMaker HyperPod
+    #   cluster.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/UpdateClusterRequest AWS API Documentation
     #
     class UpdateClusterRequest < Struct.new(
       :cluster_name,
-      :instance_groups)
+      :instance_groups,
+      :node_recovery)
       SENSITIVE = []
       include Aws::Structure
     end

data/lib/aws-sdk-sagemaker.rb

@@ -53,6 +53,6 @@ require_relative 'aws-sdk-sagemaker/customizations'
 # @!group service
 module Aws::SageMaker
 
-  GEM_VERSION = '1.259.0'
+  GEM_VERSION = '1.260.0'
 
 end

data/sig/client.rbs

@@ -712,7 +712,8 @@ module Aws
                                       volume_size_in_gb: ::Integer
                                     }?
                                   },
-                                ]?
+                                ]?,
+                                on_start_deep_health_checks: Array[("InstanceStress" | "InstanceConnectivity")]?
                               },
                             ],
                             ?vpc_config: {
@@ -724,7 +725,13 @@ module Aws
                                 key: ::String,
                                 value: ::String
                               },
-                            ]
+                            ],
+                            ?orchestrator: {
+                              eks: {
+                                cluster_arn: ::String
+                              }
+                            },
+                            ?node_recovery: ("Automatic" | "None")
                           ) -> _CreateClusterResponseSuccess
                         | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _CreateClusterResponseSuccess
 
@@ -4889,6 +4896,8 @@ module Aws
         def failure_message: () -> ::String
         def instance_groups: () -> ::Array[Types::ClusterInstanceGroupDetails]
         def vpc_config: () -> Types::VpcConfig
+        def orchestrator: () -> Types::ClusterOrchestrator
+        def node_recovery: () -> ("Automatic" | "None")
       end
       # https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMaker/Client.html#describe_cluster-instance_method
       def describe_cluster: (
@@ -8075,9 +8084,11 @@ module Aws
                                       volume_size_in_gb: ::Integer
                                     }?
                                   },
-                                ]?
+                                ]?,
+                                on_start_deep_health_checks: Array[("InstanceStress" | "InstanceConnectivity")]?
                               },
-                            ]
+                            ],
+                            ?node_recovery: ("Automatic" | "None")
                           ) -> _UpdateClusterResponseSuccess
                         | (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _UpdateClusterResponseSuccess
 

data/sig/types.rbs

@@ -710,6 +710,7 @@ module Aws::SageMaker
       attr_accessor execution_role: ::String
       attr_accessor threads_per_core: ::Integer
       attr_accessor instance_storage_configs: ::Array[Types::ClusterInstanceStorageConfig]
+      attr_accessor on_start_deep_health_checks: ::Array[("InstanceStress" | "InstanceConnectivity")]
       SENSITIVE: []
     end
 
@@ -721,6 +722,7 @@ module Aws::SageMaker
       attr_accessor execution_role: ::String
       attr_accessor threads_per_core: ::Integer
       attr_accessor instance_storage_configs: ::Array[Types::ClusterInstanceStorageConfig]
+      attr_accessor on_start_deep_health_checks: ::Array[("InstanceStress" | "InstanceConnectivity")]
       SENSITIVE: []
     end
 
@@ -731,7 +733,7 @@ module Aws::SageMaker
     end
 
     class ClusterInstanceStatusDetails
-      attr_accessor status: ("Running" | "Failure" | "Pending" | "ShuttingDown" | "SystemUpdating")
+      attr_accessor status: ("Running" | "Failure" | "Pending" | "ShuttingDown" | "SystemUpdating" | "DeepHealthCheckInProgress")
       attr_accessor message: ::String
       SENSITIVE: []
     end
@@ -777,6 +779,16 @@ module Aws::SageMaker
       SENSITIVE: []
     end
 
+    class ClusterOrchestrator
+      attr_accessor eks: Types::ClusterOrchestratorEksConfig
+      SENSITIVE: []
+    end
+
+    class ClusterOrchestratorEksConfig
+      attr_accessor cluster_arn: ::String
+      SENSITIVE: []
+    end
+
     class ClusterSummary
       attr_accessor cluster_arn: ::String
       attr_accessor cluster_name: ::String
@@ -1048,6 +1060,8 @@ module Aws::SageMaker
       attr_accessor instance_groups: ::Array[Types::ClusterInstanceGroupSpecification]
       attr_accessor vpc_config: Types::VpcConfig
       attr_accessor tags: ::Array[Types::Tag]
+      attr_accessor orchestrator: Types::ClusterOrchestrator
+      attr_accessor node_recovery: ("Automatic" | "None")
       SENSITIVE: []
     end
 
@@ -2668,6 +2682,8 @@ module Aws::SageMaker
       attr_accessor failure_message: ::String
       attr_accessor instance_groups: ::Array[Types::ClusterInstanceGroupDetails]
       attr_accessor vpc_config: Types::VpcConfig
+      attr_accessor orchestrator: Types::ClusterOrchestrator
+      attr_accessor node_recovery: ("Automatic" | "None")
       SENSITIVE: []
     end
 
@@ -9337,6 +9353,7 @@ module Aws::SageMaker
     class UpdateClusterRequest
       attr_accessor cluster_name: ::String
       attr_accessor instance_groups: ::Array[Types::ClusterInstanceGroupSpecification]
+      attr_accessor node_recovery: ("Automatic" | "None")
       SENSITIVE: []
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.259.0
+  version: 1.260.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-05 00:00:00.000000000 Z
+date: 2024-09-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core