batch_reboot_cluster_nodes async ¶

async def batch_reboot_cluster_nodes(
    self,
    *,
    config_overrides: Optional[AsyncSageMakerClientConfig] = None,
    cluster_name: Optional[
        "capo_sagemaker.types.cluster_name_or_arn.ClusterNameOrArn"
    ] = None,
    node_ids: Optional[
        "capo_sagemaker.types.cluster_node_ids.ClusterNodeIds"
    ] = None,
    node_logical_ids: Optional[
        "capo_sagemaker.types.cluster_node_logical_id_list.ClusterNodeLogicalIdList"
    ] = None,
) -> "capo_sagemaker.types.batch_reboot_cluster_nodes_response.BatchRebootClusterNodesResponse":
    """<p>Reboots specific nodes within a SageMaker HyperPod cluster using a soft recovery mechanism. <code>BatchRebootClusterNodes</code> performs a graceful reboot of the specified nodes by calling the Amazon Elastic Compute Cloud <code>RebootInstances</code> API, which attempts to cleanly shut down the operating system before restarting the instance.</p> <p>This operation is useful for recovering from transient issues or applying certain configuration changes that require a restart.</p> <note> <ul> <li> <p>Rebooting a node may cause temporary service interruption for workloads running on that node. Ensure your workloads can handle node restarts or use appropriate scheduling to minimize impact.</p> </li> <li> <p>You can reboot up to 25 nodes in a single request.</p> </li> <li> <p>For SageMaker HyperPod clusters using the Slurm workload manager, ensure rebooting nodes will not disrupt critical cluster operations.</p> </li> </ul> </note>

    Args:
        cluster_name: <p>The name or Amazon Resource Name (ARN) of the SageMaker HyperPod cluster containing the nodes to reboot.</p>
        node_ids: <p>A list of EC2 instance IDs to reboot using soft recovery. You can specify between 1 and 25 instance IDs.</p> <note> <ul> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> <li> <p>Each instance ID must follow the pattern <code>i-</code> followed by 17 hexadecimal characters (for example, <code>i-0123456789abcdef0</code>).</p> </li> </ul> </note>
        node_logical_ids: <p>A list of logical node IDs to reboot using soft recovery. You can specify between 1 and 25 logical node IDs.</p> <p>The <code>NodeLogicalId</code> is a unique identifier that persists throughout the node's lifecycle and can be used to track nodes that are still being provisioned and don't yet have an EC2 instance ID assigned.</p> <important> <ul> <li> <p>This parameter is only supported for clusters using <code>Continuous</code> as the <code>NodeProvisioningMode</code>. For clusters using the default provisioning mode, use <code>NodeIds</code> instead.</p> </li> <li> <p>Either <code>NodeIds</code> or <code>NodeLogicalIds</code> must be provided (or both), but at least one is required.</p> </li> </ul> </important>

    Raises:
        capo_sagemaker.errors.resource_not_found.ResourceNotFound: <p>Resource being access is not found.</p>
        capo_sagemaker.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    async def _handler(
        req: "AsyncOperationRequest[capo_sagemaker.types.batch_reboot_cluster_nodes_request.BatchRebootClusterNodesRequest]",
    ) -> AsyncOperationResponse[
        "capo_sagemaker.types.batch_reboot_cluster_nodes_response.BatchRebootClusterNodesResponse"
    ]:
        import capo_sagemaker._operations.sage_maker.batch_reboot_cluster_nodes

        (
            output,
            http_response,
        ) = await capo_sagemaker._operations.sage_maker.batch_reboot_cluster_nodes.async_batch_reboot_cluster_nodes(
            req.options, req.input
        )
        return AsyncOperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("BatchRebootClusterNodes")
    )
    input_: capo_sagemaker.types.batch_reboot_cluster_nodes_request.BatchRebootClusterNodesRequest = {}
    if cluster_name is not None:
        input_["cluster_name"] = cluster_name
    if node_ids is not None:
        input_["node_ids"] = node_ids
    if node_logical_ids is not None:
        input_["node_logical_ids"] = node_logical_ids

    response = await aexecute_pipeline(
        AsyncOperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    await response.response.aclose()
    return response.output