aws-sdk-sagemaker 1.414.0 → 1.415.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/VERSION +1 -1
- data/lib/aws-sdk-sagemaker/client.rb +235 -5
- data/lib/aws-sdk-sagemaker/client_api.rb +152 -0
- data/lib/aws-sdk-sagemaker/types.rb +487 -7
- data/lib/aws-sdk-sagemaker.rb +1 -1
- data/sig/client.rbs +51 -0
- data/sig/params.rbs +7 -2
- data/sig/types.rbs +106 -2
- metadata +1 -1
|
@@ -6341,6 +6341,14 @@ module Aws::SageMaker
|
|
|
6341
6341
|
# idle before patching. All instances are uncordoned after patching
|
|
6342
6342
|
# completes. If not all instances become idle, no patching occurs
|
|
6343
6343
|
# and all instances remain on the previous AMI version.
|
|
6344
|
+
#
|
|
6345
|
+
# * `DrainFirst`: Designed for workloads that never become idle, such
|
|
6346
|
+
# as inference. Cordons instances, evicts the running pods, and then
|
|
6347
|
+
# patches each instance in batches. Each instance is uncordoned
|
|
6348
|
+
# after patching. Use `DrainPolicy` to control how long to wait for
|
|
6349
|
+
# pods to drain and what happens if the drain times out. Requires
|
|
6350
|
+
# `MaximumBatchSize` in `DeploymentConfig`. Available only for
|
|
6351
|
+
# clusters that use Amazon EKS as the orchestrator.
|
|
6344
6352
|
# @return [String]
|
|
6345
6353
|
#
|
|
6346
6354
|
# @!attribute [rw] patch_schedule
|
|
@@ -6353,12 +6361,30 @@ module Aws::SageMaker
|
|
|
6353
6361
|
# rolling patching strategy.
|
|
6354
6362
|
# @return [Types::DeploymentConfiguration]
|
|
6355
6363
|
#
|
|
6364
|
+
# @!attribute [rw] idle_wait_window_in_seconds
|
|
6365
|
+
# The maximum time, in seconds, that automatic patching waits for
|
|
6366
|
+
# instances to become idle after a scheduled patch starts. Automatic
|
|
6367
|
+
# patching uncordons instances that don't become idle within this
|
|
6368
|
+
# window, and they remain on the previous AMI version. Valid values
|
|
6369
|
+
# are from 3600 (1 hour) to 2160000 (25 days). The default is 86400
|
|
6370
|
+
# (24 hours). This setting applies only to the `WhenIdle` and
|
|
6371
|
+
# `WhenAllIdle` strategies.
|
|
6372
|
+
# @return [Integer]
|
|
6373
|
+
#
|
|
6374
|
+
# @!attribute [rw] drain_policy
|
|
6375
|
+
# The policy that controls how pods are evicted from an instance
|
|
6376
|
+
# before it is patched. Valid only when `PatchingStrategy` is
|
|
6377
|
+
# `DrainFirst`.
|
|
6378
|
+
# @return [Types::ClusterDrainPolicy]
|
|
6379
|
+
#
|
|
6356
6380
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterAutoPatchConfig AWS API Documentation
|
|
6357
6381
|
#
|
|
6358
6382
|
class ClusterAutoPatchConfig < Struct.new(
|
|
6359
6383
|
:patching_strategy,
|
|
6360
6384
|
:patch_schedule,
|
|
6361
|
-
:deployment_config
|
|
6385
|
+
:deployment_config,
|
|
6386
|
+
:idle_wait_window_in_seconds,
|
|
6387
|
+
:drain_policy)
|
|
6362
6388
|
SENSITIVE = []
|
|
6363
6389
|
include Aws::Structure
|
|
6364
6390
|
end
|
|
@@ -6380,6 +6406,14 @@ module Aws::SageMaker
|
|
|
6380
6406
|
# idle before patching. All instances are uncordoned after patching
|
|
6381
6407
|
# completes. If not all instances become idle, no patching occurs
|
|
6382
6408
|
# and all instances remain on the previous AMI version.
|
|
6409
|
+
#
|
|
6410
|
+
# * `DrainFirst`: Designed for workloads that never become idle, such
|
|
6411
|
+
# as inference. Cordons instances, evicts the running pods, and then
|
|
6412
|
+
# patches each instance in batches. Each instance is uncordoned
|
|
6413
|
+
# after patching. Use `DrainPolicy` to control how long to wait for
|
|
6414
|
+
# pods to drain and what happens if the drain times out. Requires
|
|
6415
|
+
# `MaximumBatchSize` in `DeploymentConfig`. Available only for
|
|
6416
|
+
# clusters that use Amazon EKS as the orchestrator.
|
|
6383
6417
|
# @return [String]
|
|
6384
6418
|
#
|
|
6385
6419
|
# @!attribute [rw] current_patch_schedule
|
|
@@ -6395,13 +6429,29 @@ module Aws::SageMaker
|
|
|
6395
6429
|
# The deployment configuration for rolling patch updates.
|
|
6396
6430
|
# @return [Types::DeploymentConfiguration]
|
|
6397
6431
|
#
|
|
6432
|
+
# @!attribute [rw] idle_wait_window_in_seconds
|
|
6433
|
+
# The maximum time, in seconds, that automatic patching waits for
|
|
6434
|
+
# instances to become idle after a scheduled patch starts. Automatic
|
|
6435
|
+
# patching uncordons instances that don't become idle within this
|
|
6436
|
+
# window, and they remain on the previous AMI version. The default is
|
|
6437
|
+
# 86400 (24 hours).
|
|
6438
|
+
# @return [Integer]
|
|
6439
|
+
#
|
|
6440
|
+
# @!attribute [rw] drain_policy
|
|
6441
|
+
# The policy that controls how pods are evicted from an instance
|
|
6442
|
+
# before it is patched. Applies only when `PatchingStrategy` is
|
|
6443
|
+
# `DrainFirst`.
|
|
6444
|
+
# @return [Types::ClusterDrainPolicy]
|
|
6445
|
+
#
|
|
6398
6446
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterAutoPatchConfigDetails AWS API Documentation
|
|
6399
6447
|
#
|
|
6400
6448
|
class ClusterAutoPatchConfigDetails < Struct.new(
|
|
6401
6449
|
:patching_strategy,
|
|
6402
6450
|
:current_patch_schedule,
|
|
6403
6451
|
:desired_patch_schedule,
|
|
6404
|
-
:deployment_config
|
|
6452
|
+
:deployment_config,
|
|
6453
|
+
:idle_wait_window_in_seconds,
|
|
6454
|
+
:drain_policy)
|
|
6405
6455
|
SENSITIVE = []
|
|
6406
6456
|
include Aws::Structure
|
|
6407
6457
|
end
|
|
@@ -6480,6 +6530,39 @@ module Aws::SageMaker
|
|
|
6480
6530
|
include Aws::Structure
|
|
6481
6531
|
end
|
|
6482
6532
|
|
|
6533
|
+
# Specifies how pods are evicted from an instance before it is patched
|
|
6534
|
+
# with the `DrainFirst` strategy. By default, evictions respect
|
|
6535
|
+
# Kubernetes Pod Disruption Budgets.
|
|
6536
|
+
#
|
|
6537
|
+
# @!attribute [rw] drain_timeout_in_seconds
|
|
6538
|
+
# The maximum time, in seconds, to wait for the pods on an instance to
|
|
6539
|
+
# drain. Valid values are from 0 to 5400 (90 minutes). The default is
|
|
6540
|
+
# 3600 (1 hour).
|
|
6541
|
+
# @return [Integer]
|
|
6542
|
+
#
|
|
6543
|
+
# @!attribute [rw] on_drain_timeout
|
|
6544
|
+
# The action to take if the pods on an instance don't drain within
|
|
6545
|
+
# `DrainTimeoutInSeconds`. The default is `Skip`.
|
|
6546
|
+
#
|
|
6547
|
+
# * `Skip`: Doesn't patch the instance. The instance is uncordoned
|
|
6548
|
+
# and remains on the previous AMI version. This can leave the
|
|
6549
|
+
# instance group partially patched. You can then use
|
|
6550
|
+
# UpdateClusterSoftware with the desired ImageReleaseVersion to
|
|
6551
|
+
# manually update the remaining instances.
|
|
6552
|
+
#
|
|
6553
|
+
# * `Force`: Deletes the remaining pods without respecting Pod
|
|
6554
|
+
# Disruption Budgets, and then patches the instance.
|
|
6555
|
+
# @return [String]
|
|
6556
|
+
#
|
|
6557
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterDrainPolicy AWS API Documentation
|
|
6558
|
+
#
|
|
6559
|
+
class ClusterDrainPolicy < Struct.new(
|
|
6560
|
+
:drain_timeout_in_seconds,
|
|
6561
|
+
:on_drain_timeout)
|
|
6562
|
+
SENSITIVE = []
|
|
6563
|
+
include Aws::Structure
|
|
6564
|
+
end
|
|
6565
|
+
|
|
6483
6566
|
# Defines the configuration for attaching an additional Amazon Elastic
|
|
6484
6567
|
# Block Store (EBS) volume to each instance of the SageMaker HyperPod
|
|
6485
6568
|
# cluster instance group. To learn more, see [SageMaker HyperPod release
|
|
@@ -6588,6 +6671,12 @@ module Aws::SageMaker
|
|
|
6588
6671
|
# and `Error`.
|
|
6589
6672
|
# @return [String]
|
|
6590
6673
|
#
|
|
6674
|
+
# @!attribute [rw] operation_id
|
|
6675
|
+
# The unique identifier (UUID) of the cluster operation that the event
|
|
6676
|
+
# is associated with, such as a scaling operation. This field is not
|
|
6677
|
+
# returned when the event is not associated with an operation.
|
|
6678
|
+
# @return [String]
|
|
6679
|
+
#
|
|
6591
6680
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterEventDetail AWS API Documentation
|
|
6592
6681
|
#
|
|
6593
6682
|
class ClusterEventDetail < Struct.new(
|
|
@@ -6600,7 +6689,8 @@ module Aws::SageMaker
|
|
|
6600
6689
|
:event_time,
|
|
6601
6690
|
:event_details,
|
|
6602
6691
|
:description,
|
|
6603
|
-
:event_level
|
|
6692
|
+
:event_level,
|
|
6693
|
+
:operation_id)
|
|
6604
6694
|
SENSITIVE = []
|
|
6605
6695
|
include Aws::Structure
|
|
6606
6696
|
end
|
|
@@ -6648,6 +6738,12 @@ module Aws::SageMaker
|
|
|
6648
6738
|
# and `Error`.
|
|
6649
6739
|
# @return [String]
|
|
6650
6740
|
#
|
|
6741
|
+
# @!attribute [rw] operation_id
|
|
6742
|
+
# The unique identifier (UUID) of the cluster operation that the event
|
|
6743
|
+
# is associated with, such as a scaling operation. This field is not
|
|
6744
|
+
# returned when the event is not associated with an operation.
|
|
6745
|
+
# @return [String]
|
|
6746
|
+
#
|
|
6651
6747
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterEventSummary AWS API Documentation
|
|
6652
6748
|
#
|
|
6653
6749
|
class ClusterEventSummary < Struct.new(
|
|
@@ -6659,7 +6755,8 @@ module Aws::SageMaker
|
|
|
6659
6755
|
:resource_type,
|
|
6660
6756
|
:event_time,
|
|
6661
6757
|
:description,
|
|
6662
|
-
:event_level
|
|
6758
|
+
:event_level,
|
|
6759
|
+
:operation_id)
|
|
6663
6760
|
SENSITIVE = []
|
|
6664
6761
|
include Aws::Structure
|
|
6665
6762
|
end
|
|
@@ -7777,6 +7874,107 @@ module Aws::SageMaker
|
|
|
7777
7874
|
#
|
|
7778
7875
|
class ClusterOnDemandOptions < Aws::EmptyStructure; end
|
|
7779
7876
|
|
|
7877
|
+
# A point-in-time snapshot of an instance group's scaling
|
|
7878
|
+
# configuration. This structure represents both the original
|
|
7879
|
+
# configuration before the operation and the desired configuration
|
|
7880
|
+
# requested by the operation.
|
|
7881
|
+
#
|
|
7882
|
+
# @!attribute [rw] current_count
|
|
7883
|
+
# The number of instances that were in the instance group at the time
|
|
7884
|
+
# of the operation.
|
|
7885
|
+
# @return [Integer]
|
|
7886
|
+
#
|
|
7887
|
+
# @!attribute [rw] target_count
|
|
7888
|
+
# The target number of instances for the instance group.
|
|
7889
|
+
# @return [Integer]
|
|
7890
|
+
#
|
|
7891
|
+
# @!attribute [rw] min_count
|
|
7892
|
+
# The minimum number of instances that must be available in the
|
|
7893
|
+
# instance group of a HyperPod cluster before it transitions to
|
|
7894
|
+
# `InService` status.
|
|
7895
|
+
# @return [Integer]
|
|
7896
|
+
#
|
|
7897
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterOperationScalingConfiguration AWS API Documentation
|
|
7898
|
+
#
|
|
7899
|
+
class ClusterOperationScalingConfiguration < Struct.new(
|
|
7900
|
+
:current_count,
|
|
7901
|
+
:target_count,
|
|
7902
|
+
:min_count)
|
|
7903
|
+
SENSITIVE = []
|
|
7904
|
+
include Aws::Structure
|
|
7905
|
+
end
|
|
7906
|
+
|
|
7907
|
+
# The scaling details for a single instance group that is affected by a
|
|
7908
|
+
# cluster operation.
|
|
7909
|
+
#
|
|
7910
|
+
# @!attribute [rw] instance_group_name
|
|
7911
|
+
# The name of the instance group being scaled.
|
|
7912
|
+
# @return [String]
|
|
7913
|
+
#
|
|
7914
|
+
# @!attribute [rw] status
|
|
7915
|
+
# The status of the scaling operation for this instance group. Valid
|
|
7916
|
+
# values are `InProgress`, `Superseded`, or `Done`.
|
|
7917
|
+
# @return [String]
|
|
7918
|
+
#
|
|
7919
|
+
# @!attribute [rw] original
|
|
7920
|
+
# The scaling configuration of the instance group before the scaling
|
|
7921
|
+
# operation was applied, including its current, target, and minimum
|
|
7922
|
+
# instance counts.
|
|
7923
|
+
# @return [Types::ClusterOperationScalingConfiguration]
|
|
7924
|
+
#
|
|
7925
|
+
# @!attribute [rw] desired
|
|
7926
|
+
# The desired scaling configuration of the instance group for the
|
|
7927
|
+
# scaling operation, including its target and minimum instance counts.
|
|
7928
|
+
# @return [Types::ClusterOperationScalingConfiguration]
|
|
7929
|
+
#
|
|
7930
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterOperationScalingDetails AWS API Documentation
|
|
7931
|
+
#
|
|
7932
|
+
class ClusterOperationScalingDetails < Struct.new(
|
|
7933
|
+
:instance_group_name,
|
|
7934
|
+
:status,
|
|
7935
|
+
:original,
|
|
7936
|
+
:desired)
|
|
7937
|
+
SENSITIVE = []
|
|
7938
|
+
include Aws::Structure
|
|
7939
|
+
end
|
|
7940
|
+
|
|
7941
|
+
# A summary of an operation performed on a HyperPod cluster.
|
|
7942
|
+
#
|
|
7943
|
+
# @!attribute [rw] operation_id
|
|
7944
|
+
# The unique identifier (UUID) of the operation.
|
|
7945
|
+
# @return [String]
|
|
7946
|
+
#
|
|
7947
|
+
# @!attribute [rw] cluster_arn
|
|
7948
|
+
# The Amazon Resource Name (ARN) of the HyperPod cluster associated
|
|
7949
|
+
# with the operation.
|
|
7950
|
+
# @return [String]
|
|
7951
|
+
#
|
|
7952
|
+
# @!attribute [rw] type
|
|
7953
|
+
# The type of the operation. Valid values are `Scaling` or
|
|
7954
|
+
# `DeepHealthCheck`.
|
|
7955
|
+
# @return [String]
|
|
7956
|
+
#
|
|
7957
|
+
# @!attribute [rw] status
|
|
7958
|
+
# The current status of the operation. Valid values are `InProgress`,
|
|
7959
|
+
# `Superseded`, or `Done`.
|
|
7960
|
+
# @return [String]
|
|
7961
|
+
#
|
|
7962
|
+
# @!attribute [rw] creation_time
|
|
7963
|
+
# The timestamp when the operation was created.
|
|
7964
|
+
# @return [Time]
|
|
7965
|
+
#
|
|
7966
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ClusterOperationSummary AWS API Documentation
|
|
7967
|
+
#
|
|
7968
|
+
class ClusterOperationSummary < Struct.new(
|
|
7969
|
+
:operation_id,
|
|
7970
|
+
:cluster_arn,
|
|
7971
|
+
:type,
|
|
7972
|
+
:status,
|
|
7973
|
+
:creation_time)
|
|
7974
|
+
SENSITIVE = []
|
|
7975
|
+
include Aws::Structure
|
|
7976
|
+
end
|
|
7977
|
+
|
|
7780
7978
|
# The type of orchestrator used for the SageMaker HyperPod cluster.
|
|
7781
7979
|
#
|
|
7782
7980
|
# @!attribute [rw] eks
|
|
@@ -18781,11 +18979,23 @@ module Aws::SageMaker
|
|
|
18781
18979
|
# configuration.
|
|
18782
18980
|
# @return [Types::ExtensionNodeSummary]
|
|
18783
18981
|
#
|
|
18982
|
+
# @!attribute [rw] health
|
|
18983
|
+
# The problems that affect the extension on the cluster's nodes,
|
|
18984
|
+
# grouped by cause, with the number of nodes that each problem
|
|
18985
|
+
# affects. Use it to find out why `ActiveCount` is lower than
|
|
18986
|
+
# `TotalCount`, or why the status is `Degraded`, `CreateFailed`, or
|
|
18987
|
+
# `UpdateFailed`. SageMaker HyperPod omits `Health` when no node has a
|
|
18988
|
+
# problem. Nodes where SageMaker HyperPod hasn't finished installing
|
|
18989
|
+
# or updating the extension aren't counted in any issue, unless an
|
|
18990
|
+
# earlier attempt failed on them.
|
|
18991
|
+
# @return [Types::ExtensionHealth]
|
|
18992
|
+
#
|
|
18784
18993
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeClusterExtensionResponse AWS API Documentation
|
|
18785
18994
|
#
|
|
18786
18995
|
class DescribeClusterExtensionResponse < Struct.new(
|
|
18787
18996
|
:extension_details,
|
|
18788
|
-
:node_summary
|
|
18997
|
+
:node_summary,
|
|
18998
|
+
:health)
|
|
18789
18999
|
SENSITIVE = []
|
|
18790
19000
|
include Aws::Structure
|
|
18791
19001
|
end
|
|
@@ -18828,6 +19038,72 @@ module Aws::SageMaker
|
|
|
18828
19038
|
include Aws::Structure
|
|
18829
19039
|
end
|
|
18830
19040
|
|
|
19041
|
+
# @!attribute [rw] cluster_name
|
|
19042
|
+
# The name or Amazon Resource Name (ARN) of the HyperPod cluster
|
|
19043
|
+
# associated with the operation.
|
|
19044
|
+
# @return [String]
|
|
19045
|
+
#
|
|
19046
|
+
# @!attribute [rw] operation_id
|
|
19047
|
+
# The unique identifier (UUID) of the operation to describe. This ID
|
|
19048
|
+
# can be obtained from the `ListClusterOperations` operation.
|
|
19049
|
+
# @return [String]
|
|
19050
|
+
#
|
|
19051
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeClusterOperationRequest AWS API Documentation
|
|
19052
|
+
#
|
|
19053
|
+
class DescribeClusterOperationRequest < Struct.new(
|
|
19054
|
+
:cluster_name,
|
|
19055
|
+
:operation_id)
|
|
19056
|
+
SENSITIVE = []
|
|
19057
|
+
include Aws::Structure
|
|
19058
|
+
end
|
|
19059
|
+
|
|
19060
|
+
# @!attribute [rw] operation_id
|
|
19061
|
+
# The unique identifier (UUID) of the operation.
|
|
19062
|
+
# @return [String]
|
|
19063
|
+
#
|
|
19064
|
+
# @!attribute [rw] cluster_arn
|
|
19065
|
+
# The Amazon Resource Name (ARN) of the HyperPod cluster associated
|
|
19066
|
+
# with the operation.
|
|
19067
|
+
# @return [String]
|
|
19068
|
+
#
|
|
19069
|
+
# @!attribute [rw] type
|
|
19070
|
+
# The type of the operation. Valid values are `Scaling` or
|
|
19071
|
+
# `DeepHealthCheck`.
|
|
19072
|
+
# @return [String]
|
|
19073
|
+
#
|
|
19074
|
+
# @!attribute [rw] status
|
|
19075
|
+
# The current status of the operation. Valid values are `InProgress`,
|
|
19076
|
+
# `Superseded`, or `Done`.
|
|
19077
|
+
# @return [String]
|
|
19078
|
+
#
|
|
19079
|
+
# @!attribute [rw] creation_time
|
|
19080
|
+
# The timestamp when the operation was created.
|
|
19081
|
+
# @return [Time]
|
|
19082
|
+
#
|
|
19083
|
+
# @!attribute [rw] scaling_details
|
|
19084
|
+
# The per-instance-group scaling details for the operation. This field
|
|
19085
|
+
# is populated when the operation `Type` is `Scaling`.
|
|
19086
|
+
# @return [Array<Types::ClusterOperationScalingDetails>]
|
|
19087
|
+
#
|
|
19088
|
+
# @!attribute [rw] deep_health_check_details
|
|
19089
|
+
# The deep health check details for the operation. This field is
|
|
19090
|
+
# populated when the operation `Type` is `DeepHealthCheck`.
|
|
19091
|
+
# @return [Array<Types::InstanceGroupHealthCheckConfiguration>]
|
|
19092
|
+
#
|
|
19093
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeClusterOperationResponse AWS API Documentation
|
|
19094
|
+
#
|
|
19095
|
+
class DescribeClusterOperationResponse < Struct.new(
|
|
19096
|
+
:operation_id,
|
|
19097
|
+
:cluster_arn,
|
|
19098
|
+
:type,
|
|
19099
|
+
:status,
|
|
19100
|
+
:creation_time,
|
|
19101
|
+
:scaling_details,
|
|
19102
|
+
:deep_health_check_details)
|
|
19103
|
+
SENSITIVE = []
|
|
19104
|
+
include Aws::Structure
|
|
19105
|
+
end
|
|
19106
|
+
|
|
18831
19107
|
# @!attribute [rw] cluster_name
|
|
18832
19108
|
# The string name or the Amazon Resource Name (ARN) of the SageMaker
|
|
18833
19109
|
# HyperPod cluster.
|
|
@@ -27951,6 +28227,56 @@ module Aws::SageMaker
|
|
|
27951
28227
|
include Aws::Structure
|
|
27952
28228
|
end
|
|
27953
28229
|
|
|
28230
|
+
# Contains information about the problems that affect an extension on
|
|
28231
|
+
# the nodes of a SageMaker HyperPod cluster, including how many nodes
|
|
28232
|
+
# each problem affects. `DescribeClusterExtension` returns
|
|
28233
|
+
# `ExtensionHealth` only when at least one node has a problem.
|
|
28234
|
+
#
|
|
28235
|
+
# @!attribute [rw] issues
|
|
28236
|
+
# The problems that affect the extension, grouped by cause, from the
|
|
28237
|
+
# problem that affects the most nodes to the one that affects the
|
|
28238
|
+
# fewest. SageMaker HyperPod counts each node in at most one issue.
|
|
28239
|
+
# The list contains at most 20 issues. If more than 20 different
|
|
28240
|
+
# problems exist, the list shows the 19 that affect the most nodes,
|
|
28241
|
+
# and the 20th issue has the code `Other` and counts the nodes that
|
|
28242
|
+
# the remaining problems affect.
|
|
28243
|
+
# @return [Array<Types::ExtensionHealthIssue>]
|
|
28244
|
+
#
|
|
28245
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ExtensionHealth AWS API Documentation
|
|
28246
|
+
#
|
|
28247
|
+
class ExtensionHealth < Struct.new(
|
|
28248
|
+
:issues)
|
|
28249
|
+
SENSITIVE = []
|
|
28250
|
+
include Aws::Structure
|
|
28251
|
+
end
|
|
28252
|
+
|
|
28253
|
+
# Information about a problem that affects an extension on one or more
|
|
28254
|
+
# nodes of a SageMaker HyperPod cluster, including the number of nodes
|
|
28255
|
+
# that it affects.
|
|
28256
|
+
#
|
|
28257
|
+
# @!attribute [rw] code
|
|
28258
|
+
# A code that describes the type of issue.
|
|
28259
|
+
# @return [String]
|
|
28260
|
+
#
|
|
28261
|
+
# @!attribute [rw] message
|
|
28262
|
+
# A description of the problem, for example the setting or component
|
|
28263
|
+
# to check. Every node with the same problem has the same message.
|
|
28264
|
+
# @return [String]
|
|
28265
|
+
#
|
|
28266
|
+
# @!attribute [rw] node_count
|
|
28267
|
+
# The number of nodes that have this problem.
|
|
28268
|
+
# @return [Integer]
|
|
28269
|
+
#
|
|
28270
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ExtensionHealthIssue AWS API Documentation
|
|
28271
|
+
#
|
|
28272
|
+
class ExtensionHealthIssue < Struct.new(
|
|
28273
|
+
:code,
|
|
28274
|
+
:message,
|
|
28275
|
+
:node_count)
|
|
28276
|
+
SENSITIVE = []
|
|
28277
|
+
include Aws::Structure
|
|
28278
|
+
end
|
|
28279
|
+
|
|
27954
28280
|
# A summary of an extension's installation across the nodes of a
|
|
27955
28281
|
# SageMaker HyperPod cluster.
|
|
27956
28282
|
#
|
|
@@ -27962,8 +28288,11 @@ module Aws::SageMaker
|
|
|
27962
28288
|
#
|
|
27963
28289
|
# @!attribute [rw] active_count
|
|
27964
28290
|
# The number of nodes that are running the extension's current
|
|
27965
|
-
# version and configuration.
|
|
27966
|
-
#
|
|
28291
|
+
# version and configuration. Nodes that report the extension as
|
|
28292
|
+
# unhealthy aren't counted. While SageMaker HyperPod creates or
|
|
28293
|
+
# updates the extension, `ActiveCount` is lower than `TotalCount`. To
|
|
28294
|
+
# see why nodes aren't counted, see `Health` in
|
|
28295
|
+
# `DescribeClusterExtension`.
|
|
27967
28296
|
# @return [Integer]
|
|
27968
28297
|
#
|
|
27969
28298
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ExtensionNodeSummary AWS API Documentation
|
|
@@ -28010,6 +28339,22 @@ module Aws::SageMaker
|
|
|
28010
28339
|
include Aws::Structure
|
|
28011
28340
|
end
|
|
28012
28341
|
|
|
28342
|
+
# A version of an extension that you can install on a SageMaker HyperPod
|
|
28343
|
+
# cluster.
|
|
28344
|
+
#
|
|
28345
|
+
# @!attribute [rw] extension_version
|
|
28346
|
+
# The version of the extension, in `MAJOR.MINOR.PATCH` format, for
|
|
28347
|
+
# example `1.0.0`.
|
|
28348
|
+
# @return [String]
|
|
28349
|
+
#
|
|
28350
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ExtensionVersionSummary AWS API Documentation
|
|
28351
|
+
#
|
|
28352
|
+
class ExtensionVersionSummary < Struct.new(
|
|
28353
|
+
:extension_version)
|
|
28354
|
+
SENSITIVE = []
|
|
28355
|
+
include Aws::Structure
|
|
28356
|
+
end
|
|
28357
|
+
|
|
28013
28358
|
# Configuration settings for an Amazon FSx for Lustre file system to be
|
|
28014
28359
|
# used with the cluster.
|
|
28015
28360
|
#
|
|
@@ -35853,6 +36198,13 @@ module Aws::SageMaker
|
|
|
35853
36198
|
# `Cluster`, `InstanceGroup`, or `Instance`.
|
|
35854
36199
|
# @return [String]
|
|
35855
36200
|
#
|
|
36201
|
+
# @!attribute [rw] operation_id
|
|
36202
|
+
# The unique identifier (UUID) of a cluster operation for which to
|
|
36203
|
+
# filter events. If specified, only events associated with this
|
|
36204
|
+
# operation are returned. This ID can be obtained from the
|
|
36205
|
+
# `ListClusterOperations` operation.
|
|
36206
|
+
# @return [String]
|
|
36207
|
+
#
|
|
35856
36208
|
# @!attribute [rw] max_results
|
|
35857
36209
|
# The maximum number of events to return in the response. Valid range
|
|
35858
36210
|
# is 1 to 100.
|
|
@@ -35874,6 +36226,7 @@ module Aws::SageMaker
|
|
|
35874
36226
|
:sort_by,
|
|
35875
36227
|
:sort_order,
|
|
35876
36228
|
:resource_type,
|
|
36229
|
+
:operation_id,
|
|
35877
36230
|
:max_results,
|
|
35878
36231
|
:next_token)
|
|
35879
36232
|
SENSITIVE = []
|
|
@@ -35898,6 +36251,52 @@ module Aws::SageMaker
|
|
|
35898
36251
|
include Aws::Structure
|
|
35899
36252
|
end
|
|
35900
36253
|
|
|
36254
|
+
# @!attribute [rw] extension_name
|
|
36255
|
+
# The name of the extension whose versions you want to list, for
|
|
36256
|
+
# example `sagemaker-observability`.
|
|
36257
|
+
# @return [String]
|
|
36258
|
+
#
|
|
36259
|
+
# @!attribute [rw] max_results
|
|
36260
|
+
# The maximum number of versions to return in the response. If you
|
|
36261
|
+
# don't specify a value, SageMaker HyperPod returns up to 100
|
|
36262
|
+
# versions.
|
|
36263
|
+
# @return [Integer]
|
|
36264
|
+
#
|
|
36265
|
+
# @!attribute [rw] next_token
|
|
36266
|
+
# If the result of the previous `ListClusterExtensionVersions` request
|
|
36267
|
+
# was truncated, the response includes a `NextToken`. To retrieve the
|
|
36268
|
+
# next set of versions, use the token in the next request.
|
|
36269
|
+
# @return [String]
|
|
36270
|
+
#
|
|
36271
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterExtensionVersionsRequest AWS API Documentation
|
|
36272
|
+
#
|
|
36273
|
+
class ListClusterExtensionVersionsRequest < Struct.new(
|
|
36274
|
+
:extension_name,
|
|
36275
|
+
:max_results,
|
|
36276
|
+
:next_token)
|
|
36277
|
+
SENSITIVE = []
|
|
36278
|
+
include Aws::Structure
|
|
36279
|
+
end
|
|
36280
|
+
|
|
36281
|
+
# @!attribute [rw] extension_versions
|
|
36282
|
+
# The versions of the extension that you can install, from the highest
|
|
36283
|
+
# version to the lowest.
|
|
36284
|
+
# @return [Array<Types::ExtensionVersionSummary>]
|
|
36285
|
+
#
|
|
36286
|
+
# @!attribute [rw] next_token
|
|
36287
|
+
# If the response is truncated, a token that you can use in the next
|
|
36288
|
+
# request to retrieve the next set of versions.
|
|
36289
|
+
# @return [String]
|
|
36290
|
+
#
|
|
36291
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterExtensionVersionsResponse AWS API Documentation
|
|
36292
|
+
#
|
|
36293
|
+
class ListClusterExtensionVersionsResponse < Struct.new(
|
|
36294
|
+
:extension_versions,
|
|
36295
|
+
:next_token)
|
|
36296
|
+
SENSITIVE = []
|
|
36297
|
+
include Aws::Structure
|
|
36298
|
+
end
|
|
36299
|
+
|
|
35901
36300
|
# @!attribute [rw] cluster_arn
|
|
35902
36301
|
# The Amazon Resource Name (ARN) of the SageMaker HyperPod cluster
|
|
35903
36302
|
# whose extensions you want to list.
|
|
@@ -36069,6 +36468,87 @@ module Aws::SageMaker
|
|
|
36069
36468
|
include Aws::Structure
|
|
36070
36469
|
end
|
|
36071
36470
|
|
|
36471
|
+
# @!attribute [rw] cluster_name
|
|
36472
|
+
# The name or Amazon Resource Name (ARN) of the HyperPod cluster for
|
|
36473
|
+
# which to list operations.
|
|
36474
|
+
# @return [String]
|
|
36475
|
+
#
|
|
36476
|
+
# @!attribute [rw] status
|
|
36477
|
+
# The operation status to filter by. If specified, only operations
|
|
36478
|
+
# with this status are returned. Valid values are `InProgress`,
|
|
36479
|
+
# `Superseded`, or `Done`.
|
|
36480
|
+
# @return [String]
|
|
36481
|
+
#
|
|
36482
|
+
# @!attribute [rw] type
|
|
36483
|
+
# The operation type to filter by. If specified, only operations of
|
|
36484
|
+
# this type are returned. Valid values are `Scaling` or
|
|
36485
|
+
# `DeepHealthCheck`.
|
|
36486
|
+
# @return [String]
|
|
36487
|
+
#
|
|
36488
|
+
# @!attribute [rw] creation_time_after
|
|
36489
|
+
# The start of the time range for filtering operations. Only
|
|
36490
|
+
# operations created after this time are included in the results.
|
|
36491
|
+
# @return [Time]
|
|
36492
|
+
#
|
|
36493
|
+
# @!attribute [rw] creation_time_before
|
|
36494
|
+
# The end of the time range for filtering operations. Only operations
|
|
36495
|
+
# created before this time are included in the results.
|
|
36496
|
+
# @return [Time]
|
|
36497
|
+
#
|
|
36498
|
+
# @!attribute [rw] sort_by
|
|
36499
|
+
# The field to use for sorting the operation list. Currently, the only
|
|
36500
|
+
# supported value is `CreationTime`.
|
|
36501
|
+
# @return [String]
|
|
36502
|
+
#
|
|
36503
|
+
# @!attribute [rw] sort_order
|
|
36504
|
+
# The order in which to sort the results. Valid values are `Ascending`
|
|
36505
|
+
# or `Descending` (the default is `Descending`).
|
|
36506
|
+
# @return [String]
|
|
36507
|
+
#
|
|
36508
|
+
# @!attribute [rw] max_results
|
|
36509
|
+
# The maximum number of operations to return in the response. Valid
|
|
36510
|
+
# range is 1 to 100.
|
|
36511
|
+
# @return [Integer]
|
|
36512
|
+
#
|
|
36513
|
+
# @!attribute [rw] next_token
|
|
36514
|
+
# A token to retrieve the next set of results. This token is obtained
|
|
36515
|
+
# from the output of a previous `ListClusterOperations` call.
|
|
36516
|
+
# @return [String]
|
|
36517
|
+
#
|
|
36518
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterOperationsRequest AWS API Documentation
|
|
36519
|
+
#
|
|
36520
|
+
class ListClusterOperationsRequest < Struct.new(
|
|
36521
|
+
:cluster_name,
|
|
36522
|
+
:status,
|
|
36523
|
+
:type,
|
|
36524
|
+
:creation_time_after,
|
|
36525
|
+
:creation_time_before,
|
|
36526
|
+
:sort_by,
|
|
36527
|
+
:sort_order,
|
|
36528
|
+
:max_results,
|
|
36529
|
+
:next_token)
|
|
36530
|
+
SENSITIVE = []
|
|
36531
|
+
include Aws::Structure
|
|
36532
|
+
end
|
|
36533
|
+
|
|
36534
|
+
# @!attribute [rw] next_token
|
|
36535
|
+
# A token to retrieve the next set of results. Include this token in
|
|
36536
|
+
# subsequent `ListClusterOperations` calls to fetch more operations.
|
|
36537
|
+
# @return [String]
|
|
36538
|
+
#
|
|
36539
|
+
# @!attribute [rw] cluster_operation_summaries
|
|
36540
|
+
# A list of operation summaries matching the specified criteria.
|
|
36541
|
+
# @return [Array<Types::ClusterOperationSummary>]
|
|
36542
|
+
#
|
|
36543
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListClusterOperationsResponse AWS API Documentation
|
|
36544
|
+
#
|
|
36545
|
+
class ListClusterOperationsResponse < Struct.new(
|
|
36546
|
+
:next_token,
|
|
36547
|
+
:cluster_operation_summaries)
|
|
36548
|
+
SENSITIVE = []
|
|
36549
|
+
include Aws::Structure
|
|
36550
|
+
end
|
|
36551
|
+
|
|
36072
36552
|
# @!attribute [rw] created_after
|
|
36073
36553
|
# Filter for after this creation time. The input for this parameter is
|
|
36074
36554
|
# a Unix timestamp. To convert a date and time into a Unix timestamp,
|