Smaws_Client_EMR.Typestype nonrec xml_string_max_len256_list = xml_string_max_len256 listtype nonrec xml_string_list = xml_string listtype nonrec volume_specification = {throughput : throughput_val option;The throughput, in mebibyte per second (MiB/s). This optional parameter can be a number from 125 - 1000 and is valid only for gp3 volumes.
*)size_in_g_b : integer;The volume size, in gibibytes (GiB). This can be a number from 1 - 1024. If the volume type is EBS-optimized, the minimum value is 10.
*)iops : integer option;The number of I/O operations per second (IOPS) that the volume supports.
*)volume_type : string_;The volume type. Volume types supported are gp3, gp2, io1, st1, sc1, and standard.
*)}EBS volume specifications such as volume type, IOPS, size (GiB) and throughput (MiB/s) that are requested for the EBS volume attached to an Amazon EC2 instance in the cluster.
type nonrec username_password = {password : xml_string_max_len256 option;The password associated with the temporary credentials that you use to connect to cluster endpoints.
*)username : xml_string_max_len256 option;The username associated with the temporary credentials that you use to connect to cluster endpoints.
*)}The username and password that you use to connect to cluster endpoints.
type nonrec update_studio_session_mapping_input = {session_policy_arn : xml_string_max_len256;The Amazon Resource Name (ARN) of the session policy to associate with the specified user or group.
*)identity_type : identity_type;Specifies whether the identity to update is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user or group to update. For more information, see UserName and DisplayName in the IAM Identity Center Identity Store API Reference. Either IdentityName or IdentityId must be specified.
identity_id : xml_string_max_len256 option;studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio.
*)}type nonrec invalid_request_exception = {message : error_message option;The message associated with the exception.
*)error_code : error_code option;The error code associated with the exception.
*)}This exception occurs when there is something wrong with user input.
type nonrec subnet_id_list = string_ listtype nonrec update_studio_input = {encryption_key_arn : xml_string option;The KMS key identifier (ARN) used to encrypt Amazon EMR Studio workspace and notebook files when backed up to Amazon S3.
*)default_s3_location : xml_string option;The Amazon S3 location to back up Workspaces and notebook files for the Amazon EMR Studio.
*)subnet_ids : subnet_id_list option;A list of subnet IDs to associate with the Amazon EMR Studio. The list can include new subnet IDs, but must also include all of the subnet IDs previously associated with the Studio. The list order does not matter. A Studio can have a maximum of 5 subnets. The subnets must belong to the same VPC as the Studio.
*)description : xml_string_max_len256 option;A detailed description to assign to the Amazon EMR Studio.
*)name : xml_string_max_len256 option;A descriptive name for the Amazon EMR Studio.
*)studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio to update.
*)}type nonrec internal_server_exception = {message : error_message option;The message associated with the exception.
*)}This exception occurs when there is an internal failure in the Amazon EMR service.
type nonrec unit_ = | COUNT_PER_SECOND| TERA_BITS_PER_SECOND| GIGA_BITS_PER_SECOND| MEGA_BITS_PER_SECOND| KILO_BITS_PER_SECOND| BITS_PER_SECOND| TERA_BYTES_PER_SECOND| GIGA_BYTES_PER_SECOND| MEGA_BYTES_PER_SECOND| KILO_BYTES_PER_SECOND| BYTES_PER_SECOND| COUNT| PERCENT| TERA_BITS| GIGA_BITS| MEGA_BITS| KILO_BITS| BITS| TERA_BYTES| GIGA_BYTES| MEGA_BYTES| KILO_BYTES| BYTES| MILLI_SECONDS| MICRO_SECONDS| SECONDS| NONEtype nonrec terminate_session_output = {state : session_state;The state of the session after the terminate request has been accepted.
*)session_id : session_id;The ID of the terminated session.
*)cluster_id : cluster_id;The ID of the cluster that the session belonged to.
*)}Output of the TerminateSession operation.
type nonrec terminate_session_input = {session_id : session_id;The ID of the session to terminate.
*)cluster_id : cluster_id;The ID of the cluster that the session belongs to.
*)}Input to the TerminateSession operation.
type nonrec terminate_job_flows_input = {job_flow_ids : xml_string_list;A list of job flows to be shut down.
*)}Input to the TerminateJobFlows operation.
type nonrec tag = {value : string_ option;key : string_ option;A user-defined key, which is the minimum required information for a valid tag. For more information, see Tag.
*)}A key-value pair containing user-defined metadata that you can associate with an Amazon EMR resource. Tags make it easier to associate clusters in various ways, such as grouping clusters to track your Amazon EMR resource allocation costs. For more information, see Tag Clusters.
type nonrec tag_list = tag listtype nonrec supported_products_list = xml_string_max_len256 listtype nonrec supported_product_config = {args : xml_string_list option;The list of user-supplied arguments.
*)name : xml_string_max_len256 option;The name of the product configuration.
*)}The list of supported product configurations that allow user-supplied arguments. Amazon EMR accepts these arguments and forwards them to the corresponding installation script as bootstrap action arguments.
type nonrec supported_instance_type = {architecture : string_ option;The CPU architecture, for example X86_64 or AARCH64.
ebs_storage_only : boolean_ option;Indicates whether the SupportedInstanceType only supports Amazon EBS.
number_of_disks : integer option;Number of disks for the SupportedInstanceType. This value is 0 for Amazon EBS-only instance types.
ebs_optimized_by_default : boolean_ option;Indicates whether the SupportedInstanceType uses Amazon EBS optimization by default.
ebs_optimized_available : boolean_ option;Indicates whether the SupportedInstanceType supports Amazon EBS optimization.
instance_family_id : string_ option;The Amazon EC2 family and generation for the SupportedInstanceType.
is64_bits_only : boolean_ option;Indicates whether the SupportedInstanceType only supports 64-bit architecture.
vcp_u : integer option;The number of vCPUs available for the SupportedInstanceType.
storage_g_b : integer option;StorageGB represents the storage capacity of the SupportedInstanceType. This value is 0 for Amazon EBS-only instance types.
memory_g_b : float_ option;The amount of memory that is available to Amazon EMR from the SupportedInstanceType. The kernel and hypervisor software consume some memory, so this value might be lower than the overall memory for the instance type.
type_ : string_ option;}An instance type that the specified Amazon EMR release supports.
type nonrec supported_instance_types_list = supported_instance_type listtype nonrec studio_summary = {creation_time : date option;The time when the Amazon EMR Studio was created.
*)auth_mode : auth_mode option;Specifies whether the Studio authenticates users using IAM or IAM Identity Center.
*)url : xml_string_max_len256 option;The unique access URL of the Amazon EMR Studio.
*)description : xml_string_max_len256 option;The detailed description of the Amazon EMR Studio.
*)vpc_id : xml_string_max_len256 option;The ID of the Virtual Private Cloud (Amazon VPC) associated with the Amazon EMR Studio.
*)name : xml_string_max_len256 option;The name of the Amazon EMR Studio.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}Details for an Amazon EMR Studio, including ID, Name, VPC, and Description. To fetch additional details such as subnets, IAM roles, security groups, and tags for the Studio, use the DescribeStudio API.
type nonrec studio_summary_list = studio_summary listtype nonrec studio = {encryption_key_arn : xml_string option;The KMS key identifier (ARN) used to encrypt Amazon EMR Studio workspace and notebook files when backed up to Amazon S3.
*)idc_user_assignment : idc_user_assignment option;Indicates whether the Studio has REQUIRED or OPTIONAL IAM Identity Center user assignment. If the value is set to REQUIRED, users must be explicitly assigned to the Studio application to access the Studio.
trusted_identity_propagation_enabled : boolean_object option;Indicates whether the Studio has Trusted identity propagation enabled. The default value is false.
idc_instance_arn : arn_type option;The ARN of the IAM Identity Center instance the Studio application belongs to.
*)idp_relay_state_parameter_name : xml_string_max_len256 option;The name of your identity provider's RelayState parameter.
idp_auth_url : xml_string option;Your identity provider's authentication endpoint. Amazon EMR Studio redirects federated users to this endpoint for authentication when logging in to a Studio with the Studio URL.
*)default_s3_location : xml_string option;The Amazon S3 location to back up Amazon EMR Studio Workspaces and notebook files.
*)creation_time : date option;The time the Amazon EMR Studio was created.
*)url : xml_string option;The unique access URL of the Amazon EMR Studio.
*)engine_security_group_id : xml_string_max_len256 option;The ID of the Engine security group associated with the Amazon EMR Studio. The Engine security group allows inbound network traffic from resources in the Workspace security group.
*)workspace_security_group_id : xml_string_max_len256 option;The ID of the Workspace security group associated with the Amazon EMR Studio. The Workspace security group allows outbound network traffic to resources in the Engine security group and to the internet.
*)user_role : xml_string option;The name of the IAM role assumed by users logged in to the Amazon EMR Studio. A Studio only requires a UserRole when you use IAM authentication.
service_role : xml_string option;The name of the IAM role assumed by the Amazon EMR Studio.
*)subnet_ids : subnet_id_list option;The list of IDs of the subnets associated with the Amazon EMR Studio.
*)vpc_id : xml_string_max_len256 option;The ID of the VPC associated with the Amazon EMR Studio.
*)auth_mode : auth_mode option;Specifies whether the Amazon EMR Studio authenticates users with IAM or IAM Identity Center.
*)description : xml_string_max_len256 option;The detailed description of the Amazon EMR Studio.
*)name : xml_string_max_len256 option;The name of the Amazon EMR Studio.
*)studio_arn : xml_string_max_len256 option;The Amazon Resource Name (ARN) of the Amazon EMR Studio.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}Details for an Amazon EMR Studio including ID, creation time, name, and so on.
type nonrec string_list = string_ listtype nonrec stop_notebook_execution_input = {notebook_execution_id : xml_string_max_len256;The unique identifier of the notebook execution.
*)}type nonrec step_timeline = {end_date_time : date option;The date and time when the cluster step execution completed or failed.
*)start_date_time : date option;The date and time when the cluster step execution started.
*)creation_date_time : date option;The date and time when the cluster step was created.
*)}The timeline of the cluster step lifecycle.
type nonrec hadoop_step_config = {args : string_list option;The list of command line arguments to pass to the JAR file's main function for execution.
*)main_class : string_ option;The name of the main class in the specified Java file. If not specified, the JAR file should specify a main class in its manifest file.
*)properties : string_map option;The list of Java properties that are set when the step runs. You can use these properties to pass key-value pairs to your main function.
*)jar : string_ option;The path to the JAR file that runs during the step.
*)}A cluster step consisting of a JAR file whose main function will be executed. The main function submits a job for Hadoop to execute and waits for the job to finish or fail.
type nonrec step_state_change_reason = {message : string_ option;The descriptive message for the state change reason.
*)code : step_state_change_reason_code option;The programmable code for the state change reason. Note: Currently, the service provides no code for the state change.
*)}The details of the step state change reason.
type nonrec failure_details = {log_file : string_ option;The path to the log file where the step failure root cause was originally recorded.
*)message : string_ option;The descriptive message including the error the Amazon EMR service has identified as the cause of step failure. This is text from an error log that describes the root cause of the failure.
*)reason : string_ option;The reason for the step failure. In the case where the service cannot successfully determine the root cause of the failure, it returns "Unknown Error" as a reason.
*)}The details of the step failure. The service attempts to detect the root cause for many common failures.
type nonrec step_status = {timeline : step_timeline option;The timeline of the cluster step status over time.
*)failure_details : failure_details option;The details for the step failure including reason, message, and log file path where the root cause was identified.
*)state_change_reason : step_state_change_reason option;The reason for the step execution status change.
*)state : step_state option;The execution state of the cluster step.
*)}The execution status details of the cluster step.
type nonrec step_summary = {encryption_key_arn : string_ option;The KMS key ARN to encrypt the logs published to the given Amazon S3 destination.
*)log_uri : string_ option;The Amazon S3 destination URI for log publishing.
*)status : step_status option;The current execution status details of the cluster step.
*)action_on_failure : action_on_failure option;The action to take when the cluster step fails. Possible values are TERMINATE_CLUSTER, CANCEL_AND_WAIT, and CONTINUE. TERMINATE_JOB_FLOW is available for backward compatibility.
*)config : hadoop_step_config option;The Hadoop job configuration of the cluster step.
*)name : string_ option;The name of the cluster step.
*)id : step_id option;The identifier of the cluster step.
*)}The summary of the cluster step.
type nonrec step_summary_list = step_summary listtype nonrec step_state_list = step_state listtype nonrec s3_monitoring_configuration = {encryption_key_arn : xml_string option;The KMS key ARN to encrypt the logs published to the given Amazon S3 destination.
*)log_uri : xml_string option;The Amazon S3 destination URI for log publishing.
*)}The Amazon S3 configuration for monitoring log publishing. You can configure your step to send log information to Amazon S3. When it's specified, it takes precedence over the cluster's logging configuration. If you don't specify this configuration entirely, or omit individual fields, EMR falls back to cluster-level logging behavior.
type nonrec step_monitoring_configuration = {s3_monitoring_configuration : s3_monitoring_configuration option;The Amazon S3 configuration for monitoring log publishing. You can configure your step to send log information to Amazon S3. When it's specified, it takes precedence over the cluster's logging configuration. If you don't specify this configuration entirely, or omit individual fields, EMR falls back to cluster-level logging behavior.
*)}Object that holds configuration properties for logging.
type nonrec step_ids_list = xml_string_max_len256 listtype nonrec step_execution_status_detail = {last_state_change_reason : xml_string option;A description of the step's current state.
*)end_date_time : date option;The completion date and time of the step.
*)start_date_time : date option;The start date and time of the step.
*)creation_date_time : date;The creation date and time of the step.
*)state : step_execution_state;The state of the step.
*)}The execution state of a step.
type nonrec key_value = {value : xml_string option;The value part of the identified key.
*)key : xml_string option;The unique identifier of a key-value pair.
*)}A key-value pair.
type nonrec key_value_list = key_value listtype nonrec hadoop_jar_step_config = {args : xml_string_list option;A list of command line arguments passed to the JAR file's main function when executed.
*)main_class : xml_string option;The name of the main class in the specified Java file. If not specified, the JAR file should specify a Main-Class in its manifest file.
*)jar : xml_string;A path to a JAR file run during the step.
*)properties : key_value_list option;A list of Java properties that are set when the step runs. You can use these properties to pass key-value pairs to your main function.
*)}A job flow step consisting of a JAR file whose main function will be executed. The main function submits a job for Hadoop to execute and waits for the job to finish or fail.
type nonrec step_config = {step_monitoring_configuration : step_monitoring_configuration option;Object that holds configuration properties for logging.
*)hadoop_jar_step : hadoop_jar_step_config;The JAR file used for the step.
*)action_on_failure : action_on_failure option;The action to take when the step fails. Use one of the following values:
TERMINATE_CLUSTER - Shuts down the cluster.CANCEL_AND_WAIT - Cancels any pending steps and returns the cluster to the WAITING state.CONTINUE - Continues to the next step in the queue.TERMINATE_JOB_FLOW - Shuts down the cluster. TERMINATE_JOB_FLOW is provided for backward compatibility. We recommend using TERMINATE_CLUSTER instead.If a cluster's StepConcurrencyLevel is greater than 1, do not use AddJobFlowSteps to submit a step with this parameter set to CANCEL_AND_WAIT or TERMINATE_CLUSTER. The step is not submitted and the action fails with a message that the ActionOnFailure setting is not valid.
If you change a cluster's StepConcurrencyLevel to be greater than 1 while a step is running, the ActionOnFailure parameter may not behave as you expect. In this case, for a step that fails with this parameter set to CANCEL_AND_WAIT, pending steps and the running step are not canceled; for a step that fails with this parameter set to TERMINATE_CLUSTER, the cluster does not terminate.
name : xml_string_max_len256;The name of the step.
*)}Specification for a cluster (job flow) step.
type nonrec step_detail = {execution_status_detail : step_execution_status_detail;The description of the step status.
*)step_config : step_config;The step configuration.
*)}Combines the execution state and configuration of a step.
type nonrec step_detail_list = step_detail listtype nonrec step_config_list = step_config listtype nonrec step = {encryption_key_arn : string_ option;The KMS key ARN to encrypt the logs published to the given Amazon S3 destination.
*)log_uri : string_ option;The Amazon S3 destination URI for log publishing.
*)execution_role_arn : optional_arn_type option;The Amazon Resource Name (ARN) of the runtime role for a step on the cluster. The runtime role can be a cross-account IAM role. The runtime role ARN is a combination of account ID, role name, and role type using the following format: arn:partition:service:region:account:resource.
For example, arn:aws:IAM::1234567890:role/ReadOnly is a correctly formatted runtime role ARN.
status : step_status option;The current execution status details of the cluster step.
*)action_on_failure : action_on_failure option;The action to take when the cluster step fails. Possible values are TERMINATE_CLUSTER, CANCEL_AND_WAIT, and CONTINUE. TERMINATE_JOB_FLOW is provided for backward compatibility. We recommend using TERMINATE_CLUSTER instead.
If a cluster's StepConcurrencyLevel is greater than 1, do not use AddJobFlowSteps to submit a step with this parameter set to CANCEL_AND_WAIT or TERMINATE_CLUSTER. The step is not submitted and the action fails with a message that the ActionOnFailure setting is not valid.
If you change a cluster's StepConcurrencyLevel to be greater than 1 while a step is running, the ActionOnFailure parameter may not behave as you expect. In this case, for a step that fails with this parameter set to CANCEL_AND_WAIT, pending steps and the running step are not canceled; for a step that fails with this parameter set to TERMINATE_CLUSTER, the cluster does not terminate.
config : hadoop_step_config option;The Hadoop job configuration of the cluster step.
*)name : string_ option;The name of the cluster step.
*)id : step_id option;The identifier of the cluster step.
*)}This represents a step in a cluster.
type nonrec start_session_output = {state : session_state option;The state of the session at the time the request returned. When a session is first created, it enters the SUBMITTED state.
account_id : xml_string_max_len256 option;The Amazon Web Services account ID that owns the session.
*)arn : arn_type option;The output contains the ARN of the session.
*)cluster_id : cluster_id option;The ID of the cluster that the session was started on.
*)id : session_id;The output contains the ID of the session.
*)}Output of the StartSession operation.
type configuration = {properties : string_map option;A set of properties specified within a configuration classification.
*)configurations : configuration_list option;A list of additional configurations to apply within a configuration object.
*)classification : string_ option;The classification within a configuration.
*)}Amazon EMR releases 4.x or later.
An optional configuration specification to be used when provisioning cluster instances, which can include configurations for applications and software bundled with Amazon EMR. A configuration consists of a classification, properties, and optional nested configurations. A classification refers to an application-specific configuration file. Properties are the settings you want to change in that file. For more information, see Configuring Applications.
and configuration_list = configuration listtype nonrec log_types_map = (xml_string * xml_string_list) listtype nonrec session_cloud_watch_logging_configuration = {log_types : log_types_map option;A map of log component names (for example, SPARK_DRIVER, SPARK_EXECUTOR) to the list of log types to publish for that component (for example, stdout, stderr).
encryption_key_arn : xml_string option;The Amazon Resource Name (ARN) of the KMS key used to encrypt the logs published to CloudWatch Logs.
*)log_stream_name_prefix : xml_string option;The prefix applied to the log stream name where session logs are published.
*)log_group : xml_string option;The name of the log group where session logs are published.
*)enabled : boolean_ option;Whether CloudWatch Logs is enabled for the session.
*)}The CloudWatch Logs configuration for a session.
type nonrec session_managed_logging_configuration = {encryption_key_arn : xml_string option;The Amazon Resource Name (ARN) of the KMS key used to encrypt the managed logs.
*)enabled : boolean_ option;Whether Amazon EMR-managed logging is enabled for the session.
*)}The Amazon EMR-managed logging configuration for a session.
type nonrec session_s3_logging_configuration = {log_types : log_types_map option;A map of log component names (for example, SPARK_DRIVER, SPARK_EXECUTOR) to the list of log types to publish for that component (for example, stdout, stderr).
encryption_key_arn : xml_string option;The Amazon Resource Name (ARN) of the KMS key used to encrypt logs published to Amazon S3.
*)log_uri : xml_string option;The Amazon S3 destination URI where session logs are published.
*)enabled : boolean_ option;Whether Amazon S3 logging is enabled for the session.
*)}The Amazon S3 logging configuration for a session.
type nonrec session_monitoring_configuration = {s3_logging_configuration : session_s3_logging_configuration option;The Amazon S3 logging configuration for the session.
*)managed_logging_configuration : session_managed_logging_configuration option;The Amazon EMR-managed logging configuration for the session.
*)cloud_watch_logging_configuration : session_cloud_watch_logging_configuration
option;The CloudWatch Logs configuration for the session.
*)}The monitoring configuration for a session. Controls where session logs are published.
type nonrec long = Smaws_Lib.CoreTypes.Int64.ttype nonrec start_session_input = {client_request_token : client_request_token option;A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If you retry a request that completed successfully using the same client request token, the service returns the original response without performing the operation again.
*)session_idle_timeout_in_minutes : long option;The idle timeout, in minutes. If the session is idle for this duration, Amazon EMR EC2 automatically terminates it.
*)monitoring_configuration : session_monitoring_configuration option;The monitoring configuration that controls where session logs are published, such as Amazon S3, CloudWatch, or managed logging.
*)engine_configurations : configuration_list option;The configuration overrides for the session. Only runtime configuration overrides are supported.
*)execution_role_arn : iam_role_arn option;The execution role ARN for the session. Amazon EMR uses this role to access Amazon Web Services resources on your behalf during session execution.
*)cluster_id : cluster_id;The ID of the cluster on which to start the session.
*)name : xml_string_max_len256 option;An optional name for the session.
*)}Input to the StartSession operation.
type nonrec start_notebook_execution_output = {notebook_execution_id : xml_string_max_len256 option;The unique identifier of the notebook execution.
*)}type nonrec execution_engine_config = {execution_role_arn : iam_role_arn option;The execution role ARN required for the notebook execution.
*)master_instance_security_group_id : xml_string_max_len256 option;An optional unique ID of an Amazon EC2 security group to associate with the master instance of the Amazon EMR cluster for this notebook execution. For more information see Specifying Amazon EC2 Security Groups for Amazon EMR Notebooks in the EMR Management Guide.
*)type_ : execution_engine_type option;The type of execution engine. A value of EMR specifies an Amazon EMR cluster.
id : xml_string_max_len256;The unique identifier of the execution engine. For an Amazon EMR cluster, this is the cluster ID.
*)}Specifies the execution engine (cluster) to run the notebook and perform the notebook execution, for example, an Amazon EMR cluster.
type nonrec notebook_s3_location_from_input = {key : uri_string option;The key to the Amazon S3 location that stores the notebook execution input.
*)bucket : xml_string_max_len256 option;The Amazon S3 bucket that stores the notebook execution input.
*)}The Amazon S3 location that stores the notebook execution input.
type nonrec output_notebook_s3_location_from_input = {key : uri_string option;The key to the Amazon S3 location that stores the notebook execution output.
*)bucket : xml_string_max_len256 option;The Amazon S3 bucket that stores the notebook execution output.
*)}The Amazon S3 location that stores the notebook execution output.
type nonrec environment_variables_map =
(xml_string_max_len256 * xml_string) listtype nonrec start_notebook_execution_input = {environment_variables : environment_variables_map option;The environment variables associated with the notebook execution.
*)output_notebook_format : output_notebook_format option;The output format for the notebook execution.
*)output_notebook_s3_location : output_notebook_s3_location_from_input option;The Amazon S3 location for the notebook execution output.
*)notebook_s3_location : notebook_s3_location_from_input option;The Amazon S3 location for the notebook execution input.
*)notebook_instance_security_group_id : xml_string_max_len256 option;The unique identifier of the Amazon EC2 security group to associate with the Amazon EMR Notebook for this notebook execution.
*)service_role : xml_string;The name or ARN of the IAM role that is used as the service role for Amazon EMR (the Amazon EMR role) for the notebook execution.
*)execution_engine : execution_engine_config;Specifies the execution engine (cluster) that runs the notebook execution.
*)notebook_params : xml_string option;Input parameters in JSON format passed to the Amazon EMR Notebook at runtime for execution.
*)notebook_execution_name : xml_string_max_len256 option;An optional name for the notebook execution.
*)relative_path : xml_string option;The path and file name of the notebook file for this execution, relative to the path specified for the Amazon EMR Notebook. For example, if you specify a path of s3://MyBucket/MyNotebooks when you create an Amazon EMR Notebook for a notebook with an ID of e-ABCDEFGHIJK1234567890ABCD (the EditorID of this request), and you specify a RelativePath of my_notebook_executions/notebook_execution.ipynb, the location of the file for the notebook execution is s3://MyBucket/MyNotebooks/e-ABCDEFGHIJK1234567890ABCD/my_notebook_executions/notebook_execution.ipynb.
editor_id : xml_string_max_len256 option;The unique identifier of the Amazon EMR Notebook to use for notebook execution.
*)}type nonrec spot_resizing_specification = {allocation_strategy : spot_provisioning_allocation_strategy option;Specifies the allocation strategy to use to launch Spot instances during a resize. If you run Amazon EMR releases 6.9.0 or higher, the default is price-capacity-optimized. If you run Amazon EMR releases 6.8.0 or lower, the default is capacity-optimized.
timeout_duration_minutes : whole_number option;Spot resize timeout in minutes. If Spot Instances are not provisioned within this time, the resize workflow will stop provisioning of Spot instances. Minimum value is 5 minutes and maximum value is 10,080 minutes (7 days). The timeout applies to all resize workflows on the Instance Fleet. The resize could be triggered by Amazon EMR Managed Scaling or by the customer (via Amazon EMR Console, Amazon EMR CLI modify-instance-fleet or Amazon EMR SDK ModifyInstanceFleet API) or by Amazon EMR due to Amazon EC2 Spot Reclamation.
*)}The resize specification for Spot Instances in the instance fleet, which contains the resize timeout period.
type nonrec spot_provisioning_specification = {allocation_strategy : spot_provisioning_allocation_strategy option;Specifies one of the following strategies to launch Spot Instance fleets: capacity-optimized, price-capacity-optimized, lowest-price, or diversified, and capacity-optimized-prioritized. For more information on the provisioning strategies, see Allocation strategies for Spot Instances in the Amazon EC2 User Guide for Linux Instances.
When you launch a Spot Instance fleet with the old console, it automatically launches with the capacity-optimized strategy. You can't change the allocation strategy from the old console.
block_duration_minutes : whole_number option;The defined duration for Spot Instances (also known as Spot blocks) in minutes. When specified, the Spot Instance does not terminate before the defined duration expires, and defined duration pricing for Spot Instances applies. Valid values are 60, 120, 180, 240, 300, or 360. The duration period starts as soon as a Spot Instance receives its instance ID. At the end of the duration, Amazon EC2 marks the Spot Instance for termination and provides a Spot Instance termination notice, which gives the instance a two-minute warning before it terminates.
Spot Instances with a defined duration (also known as Spot blocks) are no longer available to new customers from July 1, 2021. For customers who have previously used the feature, we will continue to support Spot Instances with a defined duration until December 31, 2022.
*)timeout_action : spot_provisioning_timeout_action;The action to take when TargetSpotCapacity has not been fulfilled when the TimeoutDurationMinutes has expired; that is, when all Spot Instances could not be provisioned within the Spot provisioning timeout. Valid values are TERMINATE_CLUSTER and SWITCH_TO_ON_DEMAND. SWITCH_TO_ON_DEMAND specifies that if no Spot Instances are available, On-Demand Instances should be provisioned to fulfill any remaining Spot capacity.
timeout_duration_minutes : whole_number;The Spot provisioning timeout period in minutes. If Spot Instances are not provisioned within this time period, the TimeOutAction is taken. Minimum value is 5 and maximum value is 1440. The timeout applies only during initial provisioning, when the cluster is first created.
}The launch specification for Spot Instances in the instance fleet, which determines the defined duration, provisioning timeout behavior, and allocation strategy.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions. Spot Instance allocation strategy is available in Amazon EMR releases 5.12.1 and later.
Spot Instances with a defined duration (also known as Spot blocks) are no longer available to new customers from July 1, 2021. For customers who have previously used the feature, we will continue to support Spot Instances with a defined duration until December 31, 2022.
type nonrec simplified_application = {version : string_ option;The returned release label application version. For example, 3.2.1.
name : string_ option;The returned release label application name. For example, hadoop.
}The returned release label application names or versions.
type nonrec simplified_application_list = simplified_application listtype nonrec simple_scaling_policy_configuration = {cool_down : integer option;The amount of time, in seconds, after a scaling activity completes before any further trigger-related scaling activities can start. The default value is 0.
*)scaling_adjustment : integer;The amount by which to scale in or scale out, based on the specified AdjustmentType. A positive value adds to the instance group's Amazon EC2 instance count while a negative number removes instances. If AdjustmentType is set to EXACT_CAPACITY, the number should only be a positive integer. If AdjustmentType is set to PERCENT_CHANGE_IN_CAPACITY, the value should express the percentage as an integer. For example, -20 indicates a decrease in 20% increments of cluster capacity.
adjustment_type : adjustment_type option;The way in which Amazon EC2 instances are added (if ScalingAdjustment is a positive number) or terminated (if ScalingAdjustment is a negative number) each time the scaling activity is triggered. CHANGE_IN_CAPACITY is the default. CHANGE_IN_CAPACITY indicates that the Amazon EC2 instance count increments or decrements by ScalingAdjustment, which should be expressed as an integer. PERCENT_CHANGE_IN_CAPACITY indicates the instance count increments or decrements by the percentage specified by ScalingAdjustment, which should be expressed as an integer. For example, 20 indicates an increase in 20% increments of cluster capacity. EXACT_CAPACITY indicates the scaling activity results in an instance group with the number of Amazon EC2 instances specified by ScalingAdjustment, which should be expressed as a positive integer.
}An automatic scaling configuration, which describes how the policy adds or removes instances, the cooldown period, and the number of Amazon EC2 instances that will be added each time the CloudWatch metric alarm condition is satisfied.
type nonrec ec2_instance_ids_list = instance_id listtype nonrec instance_resize_policy = {instance_termination_timeout : integer option;Decommissioning timeout override for the specific list of instances to be terminated.
*)instances_to_protect : ec2_instance_ids_list option;Specific list of instances to be protected when shrinking an instance group.
*)instances_to_terminate : ec2_instance_ids_list option;Specific list of instances to be terminated when shrinking an instance group.
*)}Custom policy for requesting termination protection or termination of specific instances when shrinking an instance group.
type nonrec shrink_policy = {instance_resize_policy : instance_resize_policy option;Custom policy for requesting termination protection or termination of specific instances when shrinking an instance group.
*)decommission_timeout : integer option;The desired timeout for decommissioning an instance. Overrides the default YARN decommissioning timeout.
*)}Policy for customizing shrink operations. Allows configuration of decommissioning timeout and targeted instance shrinking.
type nonrec set_visible_to_all_users_input = {visible_to_all_users : boolean_;A value of true indicates that an IAM principal in the Amazon Web Services account can perform Amazon EMR actions on the cluster that the IAM policies attached to the principal allow. A value of false indicates that only the IAM principal that created the cluster and the Amazon Web Services root user can perform Amazon EMR actions on the cluster.
job_flow_ids : xml_string_list;The unique identifier of the job flow (cluster).
*)}The input to the SetVisibleToAllUsers action.
type nonrec set_unhealthy_node_replacement_input = {unhealthy_node_replacement : boolean_object;Indicates whether to turn on or turn off graceful unhealthy node replacement.
*)job_flow_ids : xml_string_list;The list of strings that uniquely identify the clusters for which to turn on unhealthy node replacement. You can get these identifiers by running the RunJobFlow or the DescribeJobFlows operations.
}type nonrec set_termination_protection_input = {termination_protected : boolean_;A Boolean that indicates whether to protect the cluster and prevent the Amazon EC2 instances in the cluster from shutting down due to API calls, user intervention, or job-flow error.
*)job_flow_ids : xml_string_list;A list of strings that uniquely identify the clusters to protect. This identifier is returned by RunJobFlow and can also be obtained from DescribeJobFlows .
}The input argument to the TerminationProtection operation.
type nonrec set_keep_job_flow_alive_when_no_steps_input = {keep_job_flow_alive_when_no_steps : boolean_;A Boolean that indicates whether to terminate the cluster after all steps are executed.
*)job_flow_ids : xml_string_list;A list of strings that uniquely identify the clusters to protect. This identifier is returned by RunJobFlow and can also be obtained from DescribeJobFlows.
*)}type nonrec session_state_list = session_state listtype nonrec session_mapping_summary = {creation_time : date option;The time the session mapping was created.
*)session_policy_arn : xml_string_max_len256 option;The Amazon Resource Name (ARN) of the session policy associated with the user or group.
*)identity_type : identity_type option;Specifies whether the identity mapped to the Amazon EMR Studio is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user or group. For more information, see UserName and DisplayName in the IAM Identity Center Identity Store API Reference.
*)identity_id : xml_string_max_len256 option;The globally unique identifier (GUID) of the user or group from the IAM Identity Center Identity Store.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}Details for an Amazon EMR Studio session mapping. The details do not include the time the session mapping was last modified.
type nonrec session_mapping_summary_list = session_mapping_summary listtype nonrec session_mapping_detail = {last_modified_time : date option;The time the session mapping was last modified.
*)creation_time : date option;The time the session mapping was created.
*)session_policy_arn : xml_string_max_len256 option;The Amazon Resource Name (ARN) of the session policy associated with the user or group.
*)identity_type : identity_type option;Specifies whether the identity mapped to the Amazon EMR Studio is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user or group. For more information, see UserName and DisplayName in the IAM Identity Center Identity Store API Reference.
*)identity_id : xml_string_max_len256 option;The globally unique identifier (GUID) of the user or group.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}Details for an Amazon EMR Studio session mapping including creation time, user or group ID, Studio ID, and so on.
Describes the certificate authority used to establish an mTLS connection to the Spark Connect server when connecting directly over VPC peering.
type nonrec session = {server_url : xml_string option;The Spark Connect server URL for the session. Use this URL with the Credentials returned by GetSessionEndpoint to connect directly to the session over VPC peering.
session_idle_timeout_in_minutes : long option;The idle timeout, in minutes. If the session is idle for this duration, Amazon EMR automatically terminates it.
*)monitoring_configuration : session_monitoring_configuration option;The monitoring configuration for the session.
*)engine_configurations : configuration_list option;The configuration overrides for the session. Only runtime configuration overrides are supported.
*)idle_since : date option;The date and time that the session last entered the IDLE state.
ended_at : date option;The date and time that the session was terminated or failed.
*)started_at : date option;The date and time that the session entered the STARTED state.
updated_at : date option;The date and time that the session was last updated.
*)created_at : date option;The date and time that the session was created.
*)account_id : xml_string_max_len256 option;The Amazon Web Services account ID that owns the session.
*)execution_role_arn : iam_role_arn option;The execution role ARN for the session. Amazon EMR uses this role to access Amazon Web Services resources on your behalf during session execution.
*)release_label : xml_string_max_len256 option;The Amazon EMR release label of the cluster that the session is running on.
*)state_change_reason : xml_string option;A human-readable message describing the most recent state change.
*)state : session_state;The current state of the session. Valid values are SUBMITTED, STARTING, STARTED, IDLE, BUSY, TERMINATING, TERMINATED, and FAILED.
arn : arn_type;The Amazon Resource Name (ARN) of the session.
*)name : xml_string_max_len256 option;The name of the session, if one was provided at creation time.
*)cluster_id : cluster_id;The ID of the cluster that the session belongs to.
*)id : session_id;The ID of the session.
*)}Detailed information about a Spark Connect session.
type nonrec session_list = session listtype nonrec security_groups_list = xml_string_max_len256 listtype nonrec security_configuration_summary = {creation_date_time : date option;The date and time the security configuration was created.
*)name : xml_string option;The name of the security configuration.
*)}The creation date and time, and name, of a security configuration.
type nonrec security_configuration_list = security_configuration_summary listtype nonrec script_bootstrap_action_config = {args : xml_string_list option;A list of command line arguments to pass to the bootstrap action script.
*)path : xml_string;Location in Amazon S3 of the script to run during a bootstrap action.
*)}Configuration of the script to run during a bootstrap action.
A CloudWatch dimension, which is specified using a Key (known as a Name in CloudWatch), Value pair. By default, Amazon EMR uses one dimension whose Key is JobFlowID and Value is a variable representing the cluster ID, which is ${emr.clusterId}. This enables the rule to bootstrap when the cluster ID becomes available.
type nonrec metric_dimension_list = metric_dimension listtype nonrec cloud_watch_alarm_definition = {dimensions : metric_dimension_list option;A CloudWatch metric dimension.
*)unit_ : unit_ option;The unit of measure associated with the CloudWatch metric being watched. The value specified for Unit must correspond to the units specified in the CloudWatch metric.
threshold : non_negative_double;The value against which the specified statistic is compared.
*)statistic : statistic option;The statistic to apply to the metric associated with the alarm. The default is AVERAGE.
period : integer;The period, in seconds, over which the statistic is applied. CloudWatch metrics for Amazon EMR are emitted every five minutes (300 seconds), so if you specify a CloudWatch metric, specify 300.
namespace : string_ option;The namespace for the CloudWatch metric. The default is AWS/ElasticMapReduce.
metric_name : string_;The name of the CloudWatch metric that is watched to determine an alarm condition.
*)evaluation_periods : integer option;The number of periods, in five-minute increments, during which the alarm condition must exist before the alarm triggers automatic scaling activity. The default value is 1.
comparison_operator : comparison_operator;Determines how the metric specified by MetricName is compared to the value specified by Threshold.
}The definition of a CloudWatch metric alarm, which determines when an automatic scaling activity is triggered. When the defined alarm conditions are satisfied, scaling activity begins.
type nonrec scaling_trigger = {cloud_watch_alarm_definition : cloud_watch_alarm_definition;The definition of a CloudWatch metric alarm. When the defined alarm conditions are met along with other trigger parameters, scaling activity begins.
*)}The conditions that trigger an automatic scaling activity.
type nonrec scaling_action = {simple_scaling_policy_configuration : simple_scaling_policy_configuration;The type of adjustment the automatic scaling activity makes when triggered, and the periodicity of the adjustment.
*)market : market_type option;Not available for instance groups. Instance groups use the market type specified for the group.
*)}The type of adjustment the automatic scaling activity makes when triggered, and the periodicity of the adjustment.
type nonrec scaling_rule = {trigger : scaling_trigger;The CloudWatch alarm definition that determines when automatic scaling activity is triggered.
*)action : scaling_action;The conditions that trigger an automatic scaling activity.
*)description : string_ option;A friendly, more verbose description of the automatic scaling rule.
*)name : string_;The name used to identify an automatic scaling rule. Rule names must be unique within a scaling policy.
*)}A scale-in or scale-out rule that defines scaling activity, including the CloudWatch metric alarm that triggers activity, how Amazon EC2 instances are added or removed, and the periodicity of adjustments. The automatic scaling policy for an instance group can comprise one or more automatic scaling rules.
type nonrec scaling_rule_list = scaling_rule listtype nonrec scaling_constraints = {max_capacity : integer;The upper boundary of Amazon EC2 instances in an instance group beyond which scaling activities are not allowed to grow. Scale-out activities will not add instances beyond this boundary.
*)min_capacity : integer;The lower boundary of Amazon EC2 instances in an instance group below which scaling activities are not allowed to shrink. Scale-in activities will not terminate instances below this boundary.
*)}The upper and lower Amazon EC2 instance limits for an automatic scaling policy. Automatic scaling activities triggered by automatic scaling rules will not cause an instance group to grow above or below these limits.
type nonrec log_type_map = (log_type * log_upload_policy_value) listtype nonrec s3_logging_configuration = {log_type_upload_policy : log_type_map option;A map that specifies the upload policy for each log type. The key is the log type, and the value is the upload policy.
Valid log types:
system-logs: EMR Daemon logs.application-logs: Framework logs from Hadoop, Spark, Hive and other applications running on the cluster.persistent-ui-logs: Logs required for persistent application UIs such as Spark History Server and Tez UI.Valid upload policies:
emr-managed: Standard behavior. Logs are uploaded to S3 bucket as configured in your LogUri, with certain logs retained by the service for operational support and troubleshooting purposes.on-customer-s3only: Logs are uploaded only to the customer-specified S3 bucket. This requires you to specify a LogUri when creating the cluster. Persistent-ui-logs cannot have on-customer-s3only policy. Allowed policies for persistent-ui-logs are emr-managed and disabled.disabled: No S3 upload for this log type.}Configuration for S3 logging behavior in EMR clusters. Defines how different types of logs are uploaded to S3 based on the specified upload policies for each log type.
type nonrec run_job_flow_output = {cluster_arn : arn_type option;The Amazon Resource Name (ARN) of the cluster.
*)job_flow_id : xml_string_max_len256 option;A unique identifier for the job flow.
*)}The result of the RunJobFlow operation.
type nonrec ebs_block_device_config = {volumes_per_instance : integer option;Number of EBS volumes with a specific volume configuration that are associated with every instance in the instance group
*)volume_specification : volume_specification;EBS volume specifications such as volume type, IOPS, size (GiB) and throughput (MiB/s) that are requested for the EBS volume attached to an Amazon EC2 instance in the cluster.
*)}Configuration of requested EBS block device associated with the instance group with count of volumes that are associated to every instance.
type nonrec ebs_block_device_config_list = ebs_block_device_config listtype nonrec ebs_configuration = {ebs_optimized : boolean_object option;Indicates whether an Amazon EBS volume is EBS-optimized. The default is false. You should explicitly set this value to true to enable the Amazon EBS-optimized setting for an EC2 instance.
*)ebs_block_device_configs : ebs_block_device_config_list option;An array of Amazon EBS volume specifications attached to a cluster instance.
*)}The Amazon EBS configuration of a cluster instance.
type nonrec auto_scaling_policy = {rules : scaling_rule_list;The scale-in and scale-out rules that comprise the automatic scaling policy.
*)constraints : scaling_constraints;The upper and lower Amazon EC2 instance limits for an automatic scaling policy. Automatic scaling activity will not cause an instance group to grow above or below these limits.
*)}An automatic scaling policy for a core instance group or task instance group in an Amazon EMR cluster. An automatic scaling policy defines how an instance group dynamically adds and terminates Amazon EC2 instances in response to the value of a CloudWatch metric. See PutAutoScalingPolicy.
type nonrec instance_group_config = {custom_ami_id : xml_string_max_len256 option;The custom AMI ID to use for the provisioned instance group.
*)auto_scaling_policy : auto_scaling_policy option;An automatic scaling policy for a core instance group or task instance group in an Amazon EMR cluster. The automatic scaling policy defines how an instance group dynamically adds and terminates Amazon EC2 instances in response to the value of a CloudWatch metric. See PutAutoScalingPolicy.
ebs_configuration : ebs_configuration option;EBS configurations that will be attached to each Amazon EC2 instance in the instance group.
*)configurations : configuration_list option;Amazon EMR releases 4.x or later.
The list of configurations supplied for an Amazon EMR cluster instance group. You can specify a separate configuration for each instance group (master, core, and task).
*)instance_count : integer;Target number of instances for the instance group.
*)instance_type : instance_type;The Amazon EC2 instance type for all instances in the instance group.
*)bid_price : xml_string_max_len256 option;The bid price for each Amazon EC2 Spot Instance type as defined by InstanceType. Expressed in USD. If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
instance_role : instance_role_type;The role of the instance group in the cluster.
*)market : market_type option;Market type of the Amazon EC2 instances used to create a cluster node.
*)name : xml_string_max_len256 option;Friendly name given to the instance group.
*)}Configuration defining a new instance group.
type nonrec instance_group_config_list = instance_group_config listtype nonrec instance_type_config = {priority : non_negative_double option;The priority at which Amazon EMR launches the Amazon EC2 instances with this instance type. Priority starts at 0, which is the highest priority. Amazon EMR considers the highest priority first.
*)custom_ami_id : xml_string_max_len256 option;The custom AMI ID to use for the instance type.
*)configurations : configuration_list option;A configuration classification that applies when provisioning cluster instances, which can include configurations for applications and software that run on the cluster.
*)ebs_configuration : ebs_configuration option;The configuration of Amazon Elastic Block Store (Amazon EBS) attached to each instance as defined by InstanceType.
bid_price_as_percentage_of_on_demand_price : non_negative_double option;The bid price, as a percentage of On-Demand price, for each Amazon EC2 Spot Instance as defined by InstanceType. Expressed as a number (for example, 20 specifies 20%). If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
bid_price : xml_string_max_len256 option;The bid price for each Amazon EC2 Spot Instance type as defined by InstanceType. Expressed in USD. If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
weighted_capacity : whole_number option;The number of units that a provisioned instance of this type provides toward fulfilling the target capacities defined in InstanceFleetConfig. This value is 1 for a master instance fleet, and must be 1 or greater for core and task instance fleets. Defaults to 1 if not specified.
instance_type : instance_type;An Amazon EC2 instance type, such as m3.xlarge.
}An instance type configuration for each instance type in an instance fleet, which determines the Amazon EC2 instances Amazon EMR attempts to provision to fulfill On-Demand and Spot target capacities. When you use an allocation strategy, you can include a maximum of 30 instance type configurations for a fleet. For more information about how to use an allocation strategy, see Configure Instance Fleets. Without an allocation strategy, you may specify a maximum of five instance type configurations for a fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_type_config_list = instance_type_config listtype nonrec on_demand_capacity_reservation_options = {capacity_reservation_resource_group_arn : xml_string_max_len256 option;The ARN of the Capacity Reservation resource group in which to run the instance.
*)capacity_reservation_preference : on_demand_capacity_reservation_preference
option;Indicates the instance's Capacity Reservation preferences. Possible preferences include:
open - The instance can run in any open Capacity Reservation that has matching attributes (instance type, platform, Availability Zone).none - The instance avoids running in a Capacity Reservation even if one is available. The instance runs as an On-Demand Instance.usage_strategy : on_demand_capacity_reservation_usage_strategy option;Indicates whether to use unused Capacity Reservations for fulfilling On-Demand capacity.
If you specify use-capacity-reservations-first, the fleet uses unused Capacity Reservations to fulfill On-Demand capacity up to the target On-Demand capacity. If multiple instance pools have unused Capacity Reservations, the On-Demand allocation strategy (lowest-price) is applied. If the number of unused Capacity Reservations is less than the On-Demand target capacity, the remaining On-Demand target capacity is launched according to the On-Demand allocation strategy (lowest-price).
If you do not specify a value, the fleet fulfills the On-Demand capacity according to the chosen On-Demand allocation strategy.
*)}Describes the strategy for using unused Capacity Reservations for fulfilling On-Demand capacity.
type nonrec on_demand_provisioning_specification = {capacity_reservation_options : on_demand_capacity_reservation_options option;The launch specification for On-Demand instances in the instance fleet, which determines the allocation strategy.
*)allocation_strategy : on_demand_provisioning_allocation_strategy;Specifies the strategy to use in launching On-Demand instance fleets. Available options are lowest-price and prioritized. lowest-price specifies to launch the instances with the lowest price first, and prioritized specifies that Amazon EMR should launch the instances with the highest priority first. The default is lowest-price.
}The launch specification for On-Demand Instances in the instance fleet, which determines the allocation strategy.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions. On-Demand Instances allocation strategy is available in Amazon EMR releases 5.12.1 and later.
type nonrec instance_fleet_provisioning_specifications = {on_demand_specification : on_demand_provisioning_specification option;The launch specification for On-Demand Instances in the instance fleet, which determines the allocation strategy and capacity reservation options.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions. On-Demand Instances allocation strategy is available in Amazon EMR releases 5.12.1 and later.
*)spot_specification : spot_provisioning_specification option;The launch specification for Spot instances in the fleet, which determines the allocation strategy, defined duration, and provisioning timeout behavior.
*)}The launch specification for On-Demand and Spot Instances in the fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions. On-Demand and Spot instance allocation strategies are available in Amazon EMR releases 5.12.1 and later.
type nonrec on_demand_resizing_specification = {capacity_reservation_options : on_demand_capacity_reservation_options option;allocation_strategy : on_demand_provisioning_allocation_strategy option;Specifies the allocation strategy to use to launch On-Demand instances during a resize. The default is lowest-price.
timeout_duration_minutes : whole_number option;On-Demand resize timeout in minutes. If On-Demand Instances are not provisioned within this time, the resize workflow stops. The minimum value is 5 minutes, and the maximum value is 10,080 minutes (7 days). The timeout applies to all resize workflows on the Instance Fleet. The resize could be triggered by Amazon EMR Managed Scaling or by the customer (via Amazon EMR Console, Amazon EMR CLI modify-instance-fleet or Amazon EMR SDK ModifyInstanceFleet API) or by Amazon EMR due to Amazon EC2 Spot Reclamation.
*)}The resize specification for On-Demand Instances in the instance fleet, which contains the resize timeout period.
type nonrec instance_fleet_resizing_specifications = {on_demand_resize_specification : on_demand_resizing_specification option;The resize specification for On-Demand Instances in the instance fleet, which contains the allocation strategy, capacity reservation options, and the resize timeout period.
*)spot_resize_specification : spot_resizing_specification option;The resize specification for Spot Instances in the instance fleet, which contains the allocation strategy and the resize timeout period.
*)}The resize specification for On-Demand and Spot Instances in the fleet.
type nonrec instance_fleet_config = {context : xml_string_max_len256 option;Reserved.
*)resize_specifications : instance_fleet_resizing_specifications option;The resize specification for the instance fleet.
*)launch_specifications : instance_fleet_provisioning_specifications option;The launch specification for the instance fleet.
*)instance_type_configs : instance_type_config_list option;The instance type configurations that define the Amazon EC2 instances in the instance fleet.
*)target_spot_capacity : whole_number option;The target capacity of Spot units for the instance fleet, which determines how many Spot Instances to provision. When the instance fleet launches, Amazon EMR tries to provision Spot Instances as specified by InstanceTypeConfig. Each instance configuration has a specified WeightedCapacity. When a Spot Instance is provisioned, the WeightedCapacity units count toward the target capacity. Amazon EMR provisions instances until the target capacity is totally fulfilled, even if this results in an overage. For example, if there are 2 units remaining to fulfill capacity, and Amazon EMR can only provision an instance with a WeightedCapacity of 5 units, the instance is provisioned, and the target capacity is exceeded by 3 units.
If not specified or set to 0, only On-Demand Instances are provisioned for the instance fleet. At least one of TargetSpotCapacity and TargetOnDemandCapacity should be greater than 0. For a master instance fleet, only one of TargetSpotCapacity and TargetOnDemandCapacity can be specified, and its value must be 1.
target_on_demand_capacity : whole_number option;The target capacity of On-Demand units for the instance fleet, which determines how many On-Demand Instances to provision. When the instance fleet launches, Amazon EMR tries to provision On-Demand Instances as specified by InstanceTypeConfig. Each instance configuration has a specified WeightedCapacity. When an On-Demand Instance is provisioned, the WeightedCapacity units count toward the target capacity. Amazon EMR provisions instances until the target capacity is totally fulfilled, even if this results in an overage. For example, if there are 2 units remaining to fulfill capacity, and Amazon EMR can only provision an instance with a WeightedCapacity of 5 units, the instance is provisioned, and the target capacity is exceeded by 3 units.
If not specified or set to 0, only Spot Instances are provisioned for the instance fleet using TargetSpotCapacity. At least one of TargetSpotCapacity and TargetOnDemandCapacity should be greater than 0. For a master instance fleet, only one of TargetSpotCapacity and TargetOnDemandCapacity can be specified, and its value must be 1.
instance_fleet_type : instance_fleet_type;The node type that the instance fleet hosts. Valid values are MASTER, CORE, and TASK.
*)name : xml_string_max_len256 option;The friendly name of the instance fleet.
*)}The configuration that defines an instance fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_fleet_config_list = instance_fleet_config listtype nonrec placement_type = {availability_zones : xml_string_max_len256_list option;When multiple Availability Zones are specified, Amazon EMR evaluates them and launches instances in the optimal Availability Zone. AvailabilityZones is used for instance fleets, while AvailabilityZone (singular) is used for uniform instance groups.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
*)availability_zone : xml_string option;The Amazon EC2 Availability Zone for the cluster. AvailabilityZone is used for uniform instance groups, while AvailabilityZones (plural) is used for instance fleets.
}The Amazon EC2 Availability Zone configuration of the cluster (job flow).
type nonrec job_flow_instances_config = {additional_slave_security_groups : security_groups_list option;A list of additional Amazon EC2 security group IDs for the core and task nodes.
*)additional_master_security_groups : security_groups_list option;A list of additional Amazon EC2 security group IDs for the master node.
*)service_access_security_group : xml_string_max_len256 option;The identifier of the Amazon EC2 security group for the Amazon EMR service to access clusters in VPC private subnets.
*)emr_managed_slave_security_group : xml_string_max_len256 option;The identifier of the Amazon EC2 security group for the core and task nodes. If you specify EmrManagedSlaveSecurityGroup, you must also specify EmrManagedMasterSecurityGroup.
emr_managed_master_security_group : xml_string_max_len256 option;The identifier of the Amazon EC2 security group for the master node. If you specify EmrManagedMasterSecurityGroup, you must also specify EmrManagedSlaveSecurityGroup.
ec2_subnet_ids : xml_string_max_len256_list option;Applies to clusters that use the instance fleet configuration. When multiple Amazon EC2 subnet IDs are specified, Amazon EMR evaluates them and launches instances in the optimal subnet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
*)ec2_subnet_id : xml_string_max_len256 option;Applies to clusters that use the uniform instance group configuration. To launch the cluster in Amazon Virtual Private Cloud (Amazon VPC), set this parameter to the identifier of the Amazon VPC subnet where you want the cluster to launch. If you do not specify this value and your account supports EC2-Classic, the cluster launches in EC2-Classic.
*)hadoop_version : xml_string_max_len256 option;Applies only to Amazon EMR release versions earlier than 4.0. The Hadoop version for the cluster. Valid inputs are "0.18" (no longer maintained), "0.20" (no longer maintained), "0.20.205" (no longer maintained), "1.0.3", "2.2.0", or "2.4.0". If you do not set this value, the default of 0.18 is used, unless the AmiVersion parameter is set in the RunJobFlow call, in which case the default version of Hadoop for that AMI version is used.
unhealthy_node_replacement : boolean_object option;Indicates whether Amazon EMR should gracefully replace core nodes that have degraded within the cluster.
*)termination_protected : boolean_ option;Specifies whether to lock the cluster to prevent the Amazon EC2 instances from being terminated by API call, user intervention, or in the event of a job-flow error.
*)keep_job_flow_alive_when_no_steps : boolean_ option;Specifies whether the cluster should remain available after completing all steps. Defaults to false. For more information about configuring cluster termination, see Control Cluster Termination in the EMR Management Guide.
placement : placement_type option;The Availability Zone in which the cluster runs.
*)ec2_key_name : xml_string_max_len256 option;The name of the Amazon EC2 key pair that can be used to connect to the master node using SSH as the user called "hadoop."
*)instance_fleets : instance_fleet_config_list option;The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
Describes the Amazon EC2 instances and instance configurations for clusters that use the instance fleet configuration.
*)instance_groups : instance_group_config_list option;Configuration for the instance groups in a cluster.
*)instance_count : integer option;The number of Amazon EC2 instances in the cluster.
*)slave_instance_type : instance_type option;The Amazon EC2 instance type of the core and task nodes.
*)master_instance_type : instance_type option;The Amazon EC2 instance type of the master node.
*)}A description of the Amazon EC2 instance on which the cluster (job flow) runs. A valid JobFlowInstancesConfig must contain either InstanceGroups or InstanceFleets. They cannot be used together. You may also have MasterInstanceType, SlaveInstanceType, and InstanceCount (all three must be present), but we don't recommend this configuration.
type nonrec bootstrap_action_config = {script_bootstrap_action : script_bootstrap_action_config;The script run by the bootstrap action.
*)name : xml_string_max_len256;The name of the bootstrap action.
*)}Configuration of a bootstrap action.
type nonrec bootstrap_action_config_list = bootstrap_action_config listtype nonrec new_supported_products_list = supported_product_config listtype nonrec application = {additional_info : string_map option;This option is for advanced users only. This is meta information about third-party applications that third-party vendors use for testing purposes.
*)args : string_list option;Arguments for Amazon EMR to pass to the application.
*)version : string_ option;The version of the application.
*)name : string_ option;The name of the application.
*)}With Amazon EMR release version 4.0 and later, the only accepted parameter is the application name. To pass arguments to applications, you use configuration classifications specified using configuration JSON objects. For more information, see Configuring Applications.
With earlier Amazon EMR releases, the application is any Amazon or third-party software that you can add to the cluster. This structure contains a list of strings that indicates the software to use with the cluster and accepts a user argument list. Amazon EMR accepts and forwards the argument list to the corresponding installation script as bootstrap action argument.
type nonrec application_list = application listtype nonrec kerberos_attributes = {ad_domain_join_password : xml_string_max_len256 option;The Active Directory password for ADDomainJoinUser.
ad_domain_join_user : xml_string_max_len256 option;Required only when establishing a cross-realm trust with an Active Directory domain. A user with sufficient privileges to join resources to the domain.
*)cross_realm_trust_principal_password : xml_string_max_len256 option;Required only when establishing a cross-realm trust with a KDC in a different realm. The cross-realm principal password, which must be identical across realms.
*)kdc_admin_password : xml_string_max_len256;The password used within the cluster for the kadmin service on the cluster-dedicated KDC, which maintains Kerberos principals, password policies, and keytabs for the cluster.
*)realm : xml_string_max_len256;The name of the Kerberos realm to which all nodes in a cluster belong. For example, EC2.INTERNAL.
}Attributes for Kerberos configuration when Kerberos authentication is enabled using a security configuration. For more information see Use Kerberos Authentication in the Amazon EMR Management Guide.
type nonrec compute_limits = {maximum_core_capacity_units : integer option;The upper boundary of Amazon EC2 units for core node type in a cluster. It is measured through vCPU cores or instances for instance groups and measured through units for instance fleets. The core units are not allowed to scale beyond this boundary. The parameter is used to split capacity allocation between core and task nodes.
*)maximum_on_demand_capacity_units : integer option;The upper boundary of On-Demand Amazon EC2 units. It is measured through vCPU cores or instances for instance groups and measured through units for instance fleets. The On-Demand units are not allowed to scale beyond this boundary. The parameter is used to split capacity allocation between On-Demand and Spot Instances.
*)maximum_capacity_units : integer;The upper boundary of Amazon EC2 units. It is measured through vCPU cores or instances for instance groups and measured through units for instance fleets. Managed scaling activities are not allowed beyond this boundary. The limit only applies to the core and task nodes. The master node cannot be scaled after initial configuration.
*)minimum_capacity_units : integer;The lower boundary of Amazon EC2 units. It is measured through vCPU cores or instances for instance groups and measured through units for instance fleets. Managed scaling activities are not allowed beyond this boundary. The limit only applies to the core and task nodes. The master node cannot be scaled after initial configuration.
*)unit_type : compute_limits_unit_type;The unit type used for specifying a managed scaling policy.
*)}The Amazon EC2 unit limits for a managed scaling policy. The managed scaling activity of a cluster can not be above or below these limits. The limit only applies to the core and task nodes. The master node cannot be scaled after initial configuration.
type nonrec managed_scaling_policy = {scaling_strategy : scaling_strategy option;Determines whether a custom scaling utilization performance index can be set. Possible values include ADVANCED or DEFAULT.
*)utilization_performance_index : utilization_performance_index_integer option;An integer value that represents an advanced scaling strategy. Setting a higher value optimizes for performance. Setting a lower value optimizes for resource conservation. Setting the value to 50 balances performance and resource conservation. Possible values are 1, 25, 50, 75, and 100.
*)compute_limits : compute_limits option;The Amazon EC2 unit limits for a managed scaling policy. The managed scaling activity of a cluster is not allowed to go above or below these limits. The limit only applies to the core and task nodes. The master node cannot be scaled after initial configuration.
*)}Managed scaling policy for an Amazon EMR cluster. The policy specifies the limits for resources that can be added or terminated from a cluster. The policy only applies to the core and task nodes. The master node cannot be scaled after initial configuration.
type nonrec placement_group_config = {placement_strategy : placement_group_strategy option;Amazon EC2 Placement Group strategy associated with instance role.
Starting with Amazon EMR release 5.23.0, the only supported placement strategy is SPREAD for the MASTER instance role.
instance_role : instance_role_type;Role of the instance in the cluster.
Starting with Amazon EMR release 5.23.0, the only supported instance role is MASTER.
}Placement group configuration for an Amazon EMR cluster. The configuration specifies the placement strategy that can be applied to instance roles during cluster creation.
To use this configuration, consider attaching managed policy AmazonElasticMapReducePlacementGroupPolicy to the Amazon EMR role.
type nonrec placement_group_config_list = placement_group_config listtype nonrec auto_termination_policy = {idle_timeout : long option;Specifies the amount of idle time in seconds after which the cluster automatically terminates. You can specify a minimum of 60 seconds and a maximum of 604800 seconds (seven days).
*)}An auto-termination policy for an Amazon EMR cluster. An auto-termination policy defines the amount of idle time in seconds after which a cluster automatically terminates. For alternative cluster termination options, see Control cluster termination.
type nonrec cloud_watch_log_configuration = {log_types : log_types_map option;A map of log types to file names for publishing logs to the standard output or standard error streams for CloudWatch. Valid log types include STEP_LOGS, SPARK_DRIVER, and SPARK_EXECUTOR. Valid file names for each type include STDOUT and STDERR.
*)encryption_key_arn : xml_string option;The ARN of the encryption key used to encrypt the logs.
*)log_stream_name_prefix : xml_string option;The prefix of the log stream name.
*)log_group_name : xml_string option;The name of the CloudWatch log group where logs are published.
*)enabled : boolean_;Specifies if CloudWatch logging is enabled.
*)}Holds CloudWatch log configuration settings and metadata that specify settings like log files to monitor and where to send them.
type nonrec monitoring_configuration = {s3_logging_configuration : s3_logging_configuration option;S3 logging configuration that controls how different types of logs (system logs, application logs, and persistent UI logs) are uploaded to S3. Each log type can be configured with a specific upload policy.
*)cloud_watch_log_configuration : cloud_watch_log_configuration option;CloudWatch log configuration settings and metadata that specify settings like log files to monitor and where to send them.
*)}Contains CloudWatch log configuration and S3 logging configuration metadata and settings.
type nonrec run_job_flow_input = {session_enabled : boolean_object option;Indicates whether Spark Connect sessions are enabled on the cluster. When set to true, you can start Spark Connect sessions using the StartSession operation.
monitoring_configuration : monitoring_configuration option;Contains CloudWatch log configuration metadata and settings.
*)extended_support : boolean_object option;Reserved.
*)ebs_root_volume_throughput : integer option;The throughput, in MiB/s, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 6.15.0 and later.
*)ebs_root_volume_iops : integer option;The IOPS, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 6.15.0 and later.
*)os_release_label : xml_string_max_len256 option;Specifies a particular Amazon Linux release for all nodes in a cluster launch RunJobFlow request. If a release is not specified, Amazon EMR uses the latest validated Amazon Linux release for cluster launch.
*)auto_termination_policy : auto_termination_policy option;placement_group_configs : placement_group_config_list option;The specified placement group configuration for an Amazon EMR cluster.
*)managed_scaling_policy : managed_scaling_policy option;The specified managed scaling policy for an Amazon EMR cluster.
*)step_concurrency_level : integer option;Specifies the number of steps that can be executed concurrently. The default value is 1. The maximum value is 256.
kerberos_attributes : kerberos_attributes option;Attributes for Kerberos configuration when Kerberos authentication is enabled using a security configuration. For more information see Use Kerberos Authentication in the Amazon EMR Management Guide.
*)repo_upgrade_on_boot : repo_upgrade_on_boot option;Applies only when CustomAmiID is used. Specifies which updates from the Amazon Linux AMI package repositories to apply automatically when the instance boots using the AMI. If omitted, the default is SECURITY, which indicates that only security updates are applied. If NONE is specified, no updates are applied, and all updates must be applied manually.
ebs_root_volume_size : integer option;The size, in GiB, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 4.x and later.
*)custom_ami_id : xml_string_max_len256 option;Available only in Amazon EMR releases 5.7.0 and later. The ID of a custom Amazon EBS-backed Linux AMI. If specified, Amazon EMR uses this AMI when it launches cluster Amazon EC2 instances. For more information about custom AMIs in Amazon EMR, see Using a Custom AMI in the Amazon EMR Management Guide. If omitted, the cluster uses the base Linux AMI for the ReleaseLabel specified. For Amazon EMR releases 2.x and 3.x, use AmiVersion instead.
For information about creating a custom AMI, see Creating an Amazon EBS-Backed Linux AMI in the Amazon Elastic Compute Cloud User Guide for Linux Instances. For information about finding an AMI ID, see Finding a Linux AMI.
*)scale_down_behavior : scale_down_behavior option;Specifies the way that individual Amazon EC2 instances terminate when an automatic scale-in activity occurs or an instance group is resized. TERMINATE_AT_INSTANCE_HOUR indicates that Amazon EMR terminates nodes at the instance-hour boundary, regardless of when the request to terminate the instance was submitted. This option is only available with Amazon EMR 5.1.0 and later and is the default for clusters created using that version. TERMINATE_AT_TASK_COMPLETION indicates that Amazon EMR adds nodes to a deny list and drains tasks from nodes before terminating the Amazon EC2 instances, regardless of the instance-hour boundary. With either behavior, Amazon EMR removes the least active nodes first and blocks instance termination if it could lead to HDFS corruption. TERMINATE_AT_TASK_COMPLETION available only in Amazon EMR releases 4.1.0 and later, and is the default for releases of Amazon EMR earlier than 5.1.0.
auto_scaling_role : xml_string option;An IAM role for automatic scaling policies. The default role is EMR_AutoScaling_DefaultRole. The IAM role provides permissions that the automatic scaling feature requires to launch and terminate Amazon EC2 instances in an instance group.
security_configuration : xml_string option;The name of a security configuration to apply to the cluster.
*)service_role : xml_string option;The IAM role that Amazon EMR assumes in order to access Amazon Web Services resources on your behalf. If you've created a custom service role path, you must specify it for the service role when you launch your cluster.
*)job_flow_role : xml_string option;Also called instance profile and Amazon EC2 role. An IAM role for an Amazon EMR cluster. The Amazon EC2 instances of the cluster assume this role. The default role is EMR_EC2_DefaultRole. In order to use the default role, you must have already created it using the CLI or console.
visible_to_all_users : boolean_ option;The VisibleToAllUsers parameter is no longer supported. By default, the value is set to true. Setting it to false now has no effect.
Set this value to true so that IAM principals in the Amazon Web Services account associated with the cluster can perform Amazon EMR actions on the cluster that their IAM policies allow. This value defaults to true for clusters created using the Amazon EMR API or the CLI create-cluster command.
When set to false, only the IAM principal that created the cluster and the Amazon Web Services account root user can perform Amazon EMR actions for the cluster, regardless of the IAM permissions policies attached to other IAM principals. For more information, see Understanding the Amazon EMR cluster VisibleToAllUsers setting in the Amazon EMR Management Guide.
configurations : configuration_list option;For Amazon EMR releases 4.0 and later. The list of configurations supplied for the Amazon EMR cluster that you are creating.
*)applications : application_list option;Applies to Amazon EMR releases 4.0 and later. A case-insensitive list of applications for Amazon EMR to install and configure when launching the cluster. For a list of applications available for each Amazon EMR release version, see the Amazon EMRRelease Guide.
*)new_supported_products : new_supported_products_list option;For Amazon EMR releases 3.x and 2.x. For Amazon EMR releases 4.x and later, use Applications.
A list of strings that indicates third-party software to use with the job flow that accepts a user argument list. Amazon EMR accepts and forwards the argument list to the corresponding installation script as bootstrap action arguments. For more information, see "Launch a Job Flow on the MapR Distribution for Hadoop" in the Amazon EMR Developer Guide. Supported values are:
supported_products : supported_products_list option;For Amazon EMR releases 3.x and 2.x. For Amazon EMR releases 4.x and later, use Applications.
A list of strings that indicates third-party software to use. For more information, see the Amazon EMR Developer Guide. Currently supported values are:
bootstrap_actions : bootstrap_action_config_list option;A list of bootstrap actions to run before Hadoop starts on the cluster nodes.
*)step_execution_role_arn : arn_type option;The Amazon Resource Name (ARN) of the runtime role for steps specified in the RunJobFlow request. The runtime role can be a cross-account IAM role. The runtime role ARN is a combination of account ID, role name, and role type using the following format: arn:partition:iam::account-id:role/role-name.
For example, arn:aws:iam::1234567890:role/ReadOnly is a correctly formatted runtime role ARN.
This parameter applies only to steps included in the Steps parameter of this RunJobFlow request. It does not apply to steps added later to the cluster.
steps : step_config_list option;A list of steps to run.
*)instances : job_flow_instances_config;A specification of the number and type of Amazon EC2 instances.
*)release_label : xml_string_max_len256 option;The Amazon EMR release label, which determines the version of open-source application packages installed on the cluster. Release labels are in the form emr-x.x.x, where x.x.x is an Amazon EMR release version such as emr-5.14.0. For more information about Amazon EMR release versions and included application versions and features, see https://docs.aws.amazon.com/emr/latest/ReleaseGuide/. The release label applies only to Amazon EMR releases version 4.0 and later. Earlier versions use AmiVersion.
ami_version : xml_string_max_len256 option;Applies only to Amazon EMR AMI versions 3.x and 2.x. For Amazon EMR releases 4.0 and later, ReleaseLabel is used. To specify a custom AMI, use CustomAmiID.
additional_info : xml_string option;A JSON string for selecting additional features.
*)log_encryption_kms_key_id : xml_string option;The KMS key used for encrypting log files. If a value is not provided, the logs remain encrypted by AES-256. This attribute is only available with Amazon EMR releases 5.30.0 and later, excluding Amazon EMR 6.0.0.
*)log_uri : xml_string option;The location in Amazon S3 to write the log files of the job flow. If a value is not provided, logs are not created.
*)name : xml_string_max_len256;The name of the job flow.
*)}Input to the RunJobFlow operation.
This input identifies an Amazon EMR resource and a list of tags to remove.
type nonrec remove_managed_scaling_policy_input = {cluster_id : cluster_id;Specifies the ID of the cluster from which the managed scaling policy will be removed.
*)}type nonrec remove_auto_termination_policy_input = {cluster_id : cluster_id;Specifies the ID of the Amazon EMR cluster from which the auto-termination policy will be removed.
*)}type nonrec remove_auto_scaling_policy_input = {instance_group_id : instance_group_id;Specifies the ID of the instance group to which the scaling policy is applied.
*)cluster_id : cluster_id;Specifies the ID of a cluster. The instance group to which the automatic scaling policy is applied is within this cluster.
*)}type nonrec release_label_filter = {application : string_ option;Optional release label application filter. For example, spark@2.1.0.
prefix : string_ option;Optional release label version prefix filter. For example, emr-5.
}The release label filters by application or version prefix.
type nonrec put_managed_scaling_policy_input = {managed_scaling_policy : managed_scaling_policy;Specifies the constraints for the managed scaling policy.
*)cluster_id : cluster_id;Specifies the ID of an Amazon EMR cluster where the managed scaling policy is attached.
*)}type nonrec port_range = {max_range : port option;The smallest port number in a specified range of port numbers.
*)min_range : port;The smallest port number in a specified range of port numbers.
*)}A list of port ranges that are permitted to allow inbound traffic from all public IP addresses. To specify a single port, use the same value for MinRange and MaxRange.
type nonrec port_ranges = port_range listtype nonrec block_public_access_configuration = {properties : string_map option;A set of properties specified within a configuration classification.
*)configurations : configuration_list option;A list of additional configurations to apply within a configuration object.
*)classification : string_ option;The classification within a configuration.
*)permitted_public_security_group_rule_ranges : port_ranges option;Specifies ports and port ranges that are permitted to have security group rules that allow inbound traffic from all public sources. For example, if Port 23 (Telnet) is specified for PermittedPublicSecurityGroupRuleRanges, Amazon EMR allows cluster creation if a security group associated with the cluster has a rule that allows inbound traffic on Port 23 from IPv4 0.0.0.0/0 or IPv6 port ::/0 as the source.
By default, Port 22, which is used for SSH access to the cluster Amazon EC2 instances, is in the list of PermittedPublicSecurityGroupRuleRanges.
block_public_security_group_rules : boolean_;Indicates whether Amazon EMR block public access is enabled (true) or disabled (false). By default, the value is false for accounts that have created Amazon EMR clusters before July 2019. For accounts created after this, the default is true.
}A configuration for Amazon EMR block public access. When BlockPublicSecurityGroupRules is set to true, Amazon EMR prevents cluster creation if one of the cluster's security groups has a rule that allows inbound traffic from 0.0.0.0/0 or ::/0 on a port, unless the port is specified as an exception using PermittedPublicSecurityGroupRuleRanges.
type nonrec put_block_public_access_configuration_input = {block_public_access_configuration : block_public_access_configuration;A configuration for Amazon EMR block public access. The configuration applies to all clusters created in your account for the current Region. The configuration specifies whether block public access is enabled. If block public access is enabled, security groups associated with the cluster cannot have rules that allow inbound traffic from 0.0.0.0/0 or ::/0 on a port, unless the port is specified as an exception using PermittedPublicSecurityGroupRuleRanges in the BlockPublicAccessConfiguration. By default, Port 22 (SSH) is an exception, and public access is allowed on this port. You can change this by updating BlockPublicSecurityGroupRules to remove the exception.
For accounts that created clusters in a Region before November 25, 2019, block public access is disabled by default in that Region. To use this feature, you must manually enable and configure it. For accounts that did not create an Amazon EMR cluster in a Region before this date, block public access is enabled by default in that Region.
*)}type nonrec put_auto_termination_policy_input = {auto_termination_policy : auto_termination_policy option;Specifies the auto-termination policy to attach to the cluster.
*)cluster_id : cluster_id;Specifies the ID of the Amazon EMR cluster to which the auto-termination policy will be attached.
*)}type nonrec auto_scaling_policy_state_change_reason = {message : string_ option;A friendly, more verbose message that accompanies an automatic scaling policy state change.
*)code : auto_scaling_policy_state_change_reason_code option;The code indicating the reason for the change in status.USER_REQUEST indicates that the scaling policy status was changed by a user. PROVISION_FAILURE indicates that the status change was because the policy failed to provision. CLEANUP_FAILURE indicates an error.
}The reason for an AutoScalingPolicyStatus change.
type nonrec auto_scaling_policy_status = {state_change_reason : auto_scaling_policy_state_change_reason option;The reason for a change in status.
*)state : auto_scaling_policy_state option;Indicates the status of the automatic scaling policy.
*)}The status of an automatic scaling policy.
type nonrec auto_scaling_policy_description = {rules : scaling_rule_list option;The scale-in and scale-out rules that comprise the automatic scaling policy.
*)constraints : scaling_constraints option;The upper and lower Amazon EC2 instance limits for an automatic scaling policy. Automatic scaling activity will not cause an instance group to grow above or below these limits.
*)status : auto_scaling_policy_status option;The status of an automatic scaling policy.
*)}An automatic scaling policy for a core instance group or task instance group in an Amazon EMR cluster. The automatic scaling policy defines how an instance group dynamically adds and terminates Amazon EC2 instances in response to the value of a CloudWatch metric. See PutAutoScalingPolicy.
type nonrec put_auto_scaling_policy_output = {cluster_arn : arn_type option;The Amazon Resource Name (ARN) of the cluster.
*)auto_scaling_policy : auto_scaling_policy_description option;The automatic scaling policy definition.
*)instance_group_id : instance_group_id option;Specifies the ID of the instance group to which the scaling policy is applied.
*)cluster_id : cluster_id option;Specifies the ID of a cluster. The instance group to which the automatic scaling policy is applied is within this cluster.
*)}type nonrec put_auto_scaling_policy_input = {auto_scaling_policy : auto_scaling_policy;Specifies the definition of the automatic scaling policy.
*)instance_group_id : instance_group_id;Specifies the ID of the instance group to which the automatic scaling policy is applied.
*)cluster_id : cluster_id;Specifies the ID of a cluster. The instance group to which the automatic scaling policy is applied is within this cluster.
*)}type nonrec persistent_app_ui_type_list = persistent_app_ui_type listtype nonrec persistent_app_u_i = {last_state_change_reason : xml_string option;The reason the persistent application user interface object was last changed.
*)last_modified_time : date option;The date and time the persistent application user interface object was last changed.
*)creation_time : date option;The creation date and time for the persistent application user interface object.
*)persistent_app_ui_status : xml_string_max_len256 option;The status for the persistent application user interface object.
*)persistent_app_ui_type_list : persistent_app_ui_type_list option;The type list for the persistent application user interface object. Valid values include SHS, YTS, or TEZ.
*)persistent_app_ui_id : xml_string_max_len256 option;The identifier for the persistent application user interface object.
*)}Holds persistent application user interface information. Applications installed on the Amazon EMR cluster publish user interfaces as web sites to monitor cluster activity.
type nonrec output_notebook_s3_location_for_output = {key : uri_string option;The key to the Amazon S3 location that stores the notebook execution output.
*)bucket : xml_string_max_len256 option;The Amazon S3 bucket that stores the notebook execution output.
*)}The Amazon S3 location that stores the notebook execution output.
type nonrec os_release = {label : string_ option;The Amazon Linux release specified for a cluster in the RunJobFlow request. The format is as shown in Amazon Linux 2 Release Notes. For example, 2.0.20220218.1.
*)}The Amazon Linux release specified for a cluster in the RunJobFlow request.
type nonrec os_release_list = os_release listtype nonrec notebook_s3_location_for_output = {key : uri_string option;The key to the Amazon S3 location that stores the notebook execution input.
*)bucket : xml_string_max_len256 option;The Amazon S3 bucket that stores the notebook execution input.
*)}The Amazon S3 location that stores the notebook execution input.
type nonrec notebook_execution_summary = {execution_engine_id : xml_string option;The unique ID of the execution engine for the notebook execution.
*)notebook_s3_location : notebook_s3_location_for_output option;The Amazon S3 location that stores the notebook execution input.
*)end_time : date option;The timestamp when notebook execution started.
*)start_time : date option;The timestamp when notebook execution started.
*)status : notebook_execution_status option;The status of the notebook execution.
START_PENDING indicates that the cluster has received the execution request but execution has not begun.STARTING indicates that the execution is starting on the cluster.RUNNING indicates that the execution is being processed by the cluster.FINISHING indicates that execution processing is in the final stages.FINISHED indicates that the execution has completed without error.FAILING indicates that the execution is failing and will not finish successfully.FAILED indicates that the execution failed.STOP_PENDING indicates that the cluster has received a StopNotebookExecution request and the stop is pending.STOPPING indicates that the cluster is in the process of stopping the execution as a result of a StopNotebookExecution request.STOPPED indicates that the execution stopped because of a StopNotebookExecution request.notebook_execution_name : xml_string_max_len256 option;The name of the notebook execution.
*)editor_id : xml_string_max_len256 option;The unique identifier of the editor associated with the notebook execution.
*)notebook_execution_id : xml_string_max_len256 option;The unique identifier of the notebook execution.
*)}Details for a notebook execution. The details include information such as the unique ID and status of the notebook execution.
type nonrec notebook_execution_summary_list = notebook_execution_summary listtype nonrec notebook_execution = {environment_variables : environment_variables_map option;The environment variables associated with the notebook execution.
*)output_notebook_format : output_notebook_format option;The output format for the notebook execution.
*)output_notebook_s3_location : output_notebook_s3_location_for_output option;The Amazon S3 location for the notebook execution output.
*)notebook_s3_location : notebook_s3_location_for_output option;The Amazon S3 location that stores the notebook execution input.
*)notebook_instance_security_group_id : xml_string_max_len256 option;The unique identifier of the Amazon EC2 security group associated with the Amazon EMR Notebook instance. For more information see Specifying Amazon EC2 Security Groups for Amazon EMR Notebooks in the Amazon EMR Management Guide.
*)last_state_change_reason : xml_string option;The reason for the latest status change of the notebook execution.
*)output_notebook_ur_i : xml_string option;The location of the notebook execution's output file in Amazon S3.
*)arn : xml_string_max_len256 option;The Amazon Resource Name (ARN) of the notebook execution.
*)end_time : date option;The timestamp when notebook execution ended.
*)start_time : date option;The timestamp when notebook execution started.
*)status : notebook_execution_status option;The status of the notebook execution.
START_PENDING indicates that the cluster has received the execution request but execution has not begun.STARTING indicates that the execution is starting on the cluster.RUNNING indicates that the execution is being processed by the cluster.FINISHING indicates that execution processing is in the final stages.FINISHED indicates that the execution has completed without error.FAILING indicates that the execution is failing and will not finish successfully.FAILED indicates that the execution failed.STOP_PENDING indicates that the cluster has received a StopNotebookExecution request and the stop is pending.STOPPING indicates that the cluster is in the process of stopping the execution as a result of a StopNotebookExecution request.STOPPED indicates that the execution stopped because of a StopNotebookExecution request.notebook_params : xml_string option;Input parameters in JSON format passed to the Amazon EMR Notebook at runtime for execution.
*)notebook_execution_name : xml_string_max_len256 option;A name for the notebook execution.
*)execution_engine : execution_engine_config option;The execution engine, such as an Amazon EMR cluster, used to run the Amazon EMR notebook and perform the notebook execution.
*)editor_id : xml_string_max_len256 option;The unique identifier of the Amazon EMR Notebook that is used for the notebook execution.
*)notebook_execution_id : xml_string_max_len256 option;The unique identifier of a notebook execution.
*)}A notebook execution. An execution is a specific instance that an Amazon EMR Notebook is run using the StartNotebookExecution action.
type nonrec ec2_instance_ids_to_terminate_list = instance_id listtype nonrec instance_group_modify_config = {configurations : configuration_list option;A list of new or modified configurations to apply for an instance group.
*)reconfiguration_type : reconfiguration_type option;Type of reconfiguration requested. Valid values are MERGE and OVERWRITE.
*)shrink_policy : shrink_policy option;Policy for customizing shrink operations.
*)ec2_instance_ids_to_terminate : ec2_instance_ids_to_terminate_list option;The Amazon EC2 InstanceIds to terminate. After you terminate the instances, the instance group will not return to its original requested size.
*)instance_count : integer option;Target size for the instance group.
*)instance_group_id : xml_string_max_len256;Unique ID of the instance group to modify.
*)}Modify the size or configurations of an instance group.
type nonrec instance_group_modify_config_list =
instance_group_modify_config listtype nonrec modify_instance_groups_input = {instance_groups : instance_group_modify_config_list option;Instance groups to change.
*)cluster_id : cluster_id option;The ID of the cluster to which the instance group belongs.
*)}Change the size of some instance groups.
type nonrec instance_fleet_modify_config = {context : xml_string_max_len256 option;Reserved.
*)instance_type_configs : instance_type_config_list option;An array of InstanceTypeConfig objects that specify how Amazon EMR provisions Amazon EC2 instances when it fulfills On-Demand and Spot capacities. For more information, see InstanceTypeConfig.
*)resize_specifications : instance_fleet_resizing_specifications option;The resize specification for the instance fleet.
*)target_spot_capacity : whole_number option;The target capacity of Spot units for the instance fleet. For more information, see InstanceFleetConfig$TargetSpotCapacity.
target_on_demand_capacity : whole_number option;The target capacity of On-Demand units for the instance fleet. For more information see InstanceFleetConfig$TargetOnDemandCapacity.
instance_fleet_id : instance_fleet_id;A unique identifier for the instance fleet.
*)}Configuration parameters for an instance fleet modification request.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec modify_instance_fleet_input = {instance_fleet : instance_fleet_modify_config;The configuration parameters of the instance fleet.
*)cluster_id : cluster_id;The unique identifier of the cluster.
*)}type nonrec modify_cluster_output = {extended_support : boolean_object option;Reserved.
*)step_concurrency_level : integer option;The number of steps that can be executed concurrently.
*)}type nonrec modify_cluster_input = {extended_support : boolean_object option;Reserved.
*)step_concurrency_level : integer option;The number of steps that can be executed concurrently. You can specify a minimum of 1 step and a maximum of 256 steps. We recommend that you do not change this parameter while steps are running or the ActionOnFailure setting may not behave as expected. For more information see Step$ActionOnFailure.
cluster_id : string_;The unique identifier of the cluster.
*)}type nonrec list_supported_instance_types_output = {marker : string_ option;The pagination token that marks the next set of results to retrieve.
*)supported_instance_types : supported_instance_types_list option;The list of instance types that the release specified in ListSupportedInstanceTypesInput$ReleaseLabel supports, filtered by Amazon Web Services Region.
}type nonrec list_supported_instance_types_input = {marker : string_ option;The pagination token that marks the next set of results to retrieve.
*)release_label : string_;The Amazon EMR release label determines the versions of open-source application packages that Amazon EMR has installed on the cluster. Release labels are in the format emr-x.x.x, where x.x.x is an Amazon EMR release number such as emr-6.10.0. For more information about Amazon EMR releases and their included application versions and features, see the Amazon EMR Release Guide.
}type nonrec list_studios_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)studios : studio_summary_list option;The list of Studio summary objects.
*)}type nonrec list_studios_input = {marker : marker option;The pagination token that indicates the set of results to retrieve.
*)}type nonrec list_studio_session_mappings_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)session_mappings : session_mapping_summary_list option;A list of session mapping summary objects. Each object includes session mapping details such as creation time, identity type (user or group), and Amazon EMR Studio ID.
*)}type nonrec list_studio_session_mappings_input = {marker : marker option;The pagination token that indicates the set of results to retrieve.
*)identity_type : identity_type option;Specifies whether to return session mappings for users or groups. If not specified, the results include session mapping details for both users and groups.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}type nonrec list_steps_output = {marker : marker option;The maximum number of steps that a single ListSteps action returns is 50. To return a longer list of steps, use multiple ListSteps actions along with the Marker parameter, which is a pagination token that indicates the next set of results to retrieve.
steps : step_summary_list option;The filtered list of steps for the cluster.
*)}This output contains the list of steps returned in reverse order. This means that the last step is the first element in the list.
type nonrec list_steps_input = {marker : marker option;The maximum number of steps that a single ListSteps action returns is 50. To return a longer list of steps, use multiple ListSteps actions along with the Marker parameter, which is a pagination token that indicates the next set of results to retrieve.
step_ids : xml_string_list option;The filter to limit the step list based on the identifier of the steps. You can specify a maximum of ten Step IDs. The character constraint applies to the overall length of the array.
*)step_states : step_state_list option;The filter to limit the step list based on certain states.
*)cluster_id : cluster_id;The identifier of the cluster for which to list the steps.
*)}This input determines which steps to list.
type nonrec list_sessions_output = {next_token : string_ option;The pagination token to use in a subsequent ListSessions call to retrieve the next page of results. This field is absent when there are no more results.
sessions : session_list option;The sessions that match the request.
*)}Output of the ListSessions operation.
type nonrec list_sessions_input = {max_results : max_results_number option;The maximum number of sessions to return in each page of results.
*)next_token : string_ option;The pagination token returned by a previous ListSessions call. Use it to retrieve the next page of results.
session_states : session_state_list option;An optional filter that limits the results to sessions in the specified states.
*)cluster_id : cluster_id;The ID of the cluster to list sessions for.
*)}Input to the ListSessions operation.
type nonrec list_security_configurations_output = {marker : marker option;A pagination token that indicates the next set of results to retrieve. Include the marker in the next ListSecurityConfiguration call to retrieve the next page of results, if required.
*)security_configurations : security_configuration_list option;The creation date and time, and name, of each security configuration.
*)}type nonrec list_security_configurations_input = {marker : marker option;The pagination token that indicates the set of results to retrieve.
*)}type nonrec list_release_labels_output = {next_token : string_ option;Used to paginate the next page of results if specified in the next ListReleaseLabels request.
release_labels : string_list option;The returned release labels.
*)}type nonrec list_release_labels_input = {max_results : max_results_number option;Defines the maximum number of release labels to return in a single response. The default is 100.
next_token : string_ option;Specifies the next page of results. If NextToken is not specified, which is usually the case for the first request of ListReleaseLabels, the first page of results are determined by other filtering parameters or by the latest version. The ListReleaseLabels request fails if the identity (Amazon Web Services account ID) and all filtering parameters are different from the original request, or if the NextToken is expired or tampered with.
filters : release_label_filter option;Filters the results of the request. Prefix specifies the prefix of release labels to return. Application specifies the application (with/without version) of release labels to return.
}type nonrec list_notebook_executions_output = {marker : marker option;A pagination token that a subsequent ListNotebookExecutions can use to determine the next set of results to retrieve.
notebook_executions : notebook_execution_summary_list option;A list of notebook executions.
*)}type nonrec list_notebook_executions_input = {execution_engine_id : xml_string option;The unique ID of the execution engine.
*)marker : marker option;The pagination token, returned by a previous ListNotebookExecutions call, that indicates the start of the list for this ListNotebookExecutions call.
to_ : date option;The end of time range filter for listing notebook executions. The default is the current timestamp.
*)from_ : date option;The beginning of time range filter for listing notebook executions. The default is the timestamp of 30 days ago.
*)status : notebook_execution_status option;The status filter for listing notebook executions.
START_PENDING indicates that the cluster has received the execution request but execution has not begun.STARTING indicates that the execution is starting on the cluster.RUNNING indicates that the execution is being processed by the cluster.FINISHING indicates that execution processing is in the final stages.FINISHED indicates that the execution has completed without error.FAILING indicates that the execution is failing and will not finish successfully.FAILED indicates that the execution failed.STOP_PENDING indicates that the cluster has received a StopNotebookExecution request and the stop is pending.STOPPING indicates that the cluster is in the process of stopping the execution as a result of a StopNotebookExecution request.STOPPED indicates that the execution stopped because of a StopNotebookExecution request.editor_id : xml_string_max_len256 option;The unique ID of the editor associated with the notebook execution.
*)}type nonrec instance_state_change_reason = {message : string_ option;The status change reason description.
*)code : instance_state_change_reason_code option;The programmable code for the state change reason.
*)}The details of the status change reason for the instance.
type nonrec instance_timeline = {end_date_time : date option;The date and time when the instance was terminated.
*)ready_date_time : date option;The date and time when the instance was ready to perform tasks.
*)creation_date_time : date option;The creation date and time of the instance.
*)}The timeline of the instance lifecycle.
type nonrec instance_status = {timeline : instance_timeline option;The timeline of the instance status over time.
*)state_change_reason : instance_state_change_reason option;The details of the status change reason for the instance.
*)state : instance_state option;The current state of the instance.
*)}The instance status details.
type nonrec ebs_volume = {volume_id : string_ option;The volume identifier of the EBS volume.
*)device : string_ option;The device name that is exposed to the instance, such as /dev/sdh.
*)}EBS block device that's attached to an Amazon EC2 instance.
type nonrec ebs_volume_list = ebs_volume listtype nonrec instance = {ebs_volumes : ebs_volume_list option;The list of Amazon EBS volumes that are attached to this instance.
*)instance_type : instance_type option;The Amazon EC2 instance type, for example m3.xlarge.
market : market_type option;The instance purchasing option. Valid values are ON_DEMAND or SPOT.
instance_fleet_id : instance_fleet_id option;The unique identifier of the instance fleet to which an Amazon EC2 instance belongs.
*)instance_group_id : string_ option;The identifier of the instance group to which this instance belongs.
*)status : instance_status option;The current status of the instance.
*)private_ip_address : string_ option;The private IP address of the instance.
*)private_dns_name : string_ option;The private DNS name of the instance.
*)public_ip_address : string_ option;The public IP address of the instance.
*)public_dns_name : string_ option;The public DNS name of the instance.
*)ec2_instance_id : instance_id option;The unique identifier of the instance in Amazon EC2.
*)id : instance_id option;The unique identifier for the instance in Amazon EMR.
*)}Represents an Amazon EC2 instance provisioned as part of cluster.
type nonrec instance_list = instance listtype nonrec list_instances_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)instances : instance_list option;The list of instances for the cluster and given filters.
*)}This output contains the list of instances.
type nonrec instance_group_type_list = instance_group_type listtype nonrec instance_state_list = instance_state listtype nonrec list_instances_input = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)instance_states : instance_state_list option;A list of instance states that will filter the instances returned with this request.
*)instance_fleet_type : instance_fleet_type option;The node type of the instance fleet. For example MASTER, CORE, or TASK.
*)instance_fleet_id : instance_fleet_id option;The unique identifier of the instance fleet.
*)instance_group_types : instance_group_type_list option;The type of instance group for which to list the instances.
*)instance_group_id : instance_group_id option;The identifier of the instance group for which to list the instances.
*)cluster_id : cluster_id;The identifier of the cluster for which to list the instances.
*)}This input determines which instances to list.
type nonrec instance_group_state_change_reason = {message : string_ option;The status change reason description.
*)code : instance_group_state_change_reason_code option;The programmable code for the state change reason.
*)}The status change reason details for the instance group.
type nonrec instance_group_timeline = {end_date_time : date option;The date and time when the instance group terminated.
*)ready_date_time : date option;The date and time when the instance group became ready to perform tasks.
*)creation_date_time : date option;The creation date and time of the instance group.
*)}The timeline of the instance group lifecycle.
type nonrec instance_group_status = {timeline : instance_group_timeline option;The timeline of the instance group status over time.
*)state_change_reason : instance_group_state_change_reason option;The status change reason details for the instance group.
*)state : instance_group_state option;The current state of the instance group.
*)}The details of the instance group status.
type nonrec ebs_block_device = {device : string_ option;The device name that is exposed to the instance, such as /dev/sdh.
*)volume_specification : volume_specification option;EBS volume specifications such as volume type, IOPS, size (GiB) and throughput (MiB/s) that are requested for the EBS volume attached to an Amazon EC2 instance in the cluster.
*)}Configuration of requested EBS block device associated with the instance group.
type nonrec ebs_block_device_list = ebs_block_device listtype nonrec instance_group = {custom_ami_id : xml_string_max_len256 option;The custom AMI ID to use for the provisioned instance group.
*)auto_scaling_policy : auto_scaling_policy_description option;An automatic scaling policy for a core instance group or task instance group in an Amazon EMR cluster. The automatic scaling policy defines how an instance group dynamically adds and terminates Amazon EC2 instances in response to the value of a CloudWatch metric. See PutAutoScalingPolicy.
*)shrink_policy : shrink_policy option;Policy for customizing shrink operations.
*)ebs_optimized : boolean_object option;If the instance group is EBS-optimized. An Amazon EBS-optimized instance uses an optimized configuration stack and provides additional, dedicated capacity for Amazon EBS I/O.
*)ebs_block_devices : ebs_block_device_list option;The EBS block devices that are mapped to this instance group.
*)last_successfully_applied_configurations_version : long option;The version number of a configuration specification that was successfully applied for an instance group last time.
*)last_successfully_applied_configurations : configuration_list option;A list of configurations that were successfully applied for an instance group last time.
*)configurations_version : long option;The version number of the requested configuration specification for this instance group.
*)configurations : configuration_list option;Amazon EMR releases 4.x or later.
The list of configurations supplied for an Amazon EMR cluster instance group. You can specify a separate configuration for each instance group (master, core, and task).
*)status : instance_group_status option;The current status of the instance group.
*)running_instance_count : integer option;The number of instances currently running in this instance group.
*)requested_instance_count : integer option;The target number of instances for the instance group.
*)instance_type : instance_type option;The Amazon EC2 instance type for all instances in the instance group.
*)bid_price : string_ option;The bid price for each Amazon EC2 Spot Instance type as defined by InstanceType. Expressed in USD. If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
instance_group_type : instance_group_type option;The type of the instance group. Valid values are MASTER, CORE or TASK.
*)market : market_type option;The marketplace to provision instances for this group. Valid values are ON_DEMAND or SPOT.
*)name : string_ option;The name of the instance group.
*)id : instance_group_id option;The identifier of the instance group.
*)}This entity represents an instance group, which is a group of instances that have common purpose. For example, CORE instance group is used for HDFS.
type nonrec instance_group_list = instance_group listtype nonrec list_instance_groups_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)instance_groups : instance_group_list option;The list of instance groups for the cluster and given filters.
*)}This input determines which instance groups to retrieve.
type nonrec list_instance_groups_input = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)cluster_id : cluster_id;The identifier of the cluster for which to list the instance groups.
*)}This input determines which instance groups to retrieve.
type nonrec instance_fleet_state_change_reason = {message : string_ option;An explanatory message.
*)code : instance_fleet_state_change_reason_code option;A code corresponding to the reason the state change occurred.
*)}Provides status change reason details for the instance fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_fleet_timeline = {end_date_time : date option;The time and date the instance fleet terminated.
*)ready_date_time : date option;The time and date the instance fleet was ready to run jobs.
*)creation_date_time : date option;The time and date the instance fleet was created.
*)}Provides historical timestamps for the instance fleet, including the time of creation, the time it became ready to run jobs, and the time of termination.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_fleet_status = {timeline : instance_fleet_timeline option;Provides historical timestamps for the instance fleet, including the time of creation, the time it became ready to run jobs, and the time of termination.
*)state_change_reason : instance_fleet_state_change_reason option;Provides status change reason details for the instance fleet.
*)state : instance_fleet_state option;A code representing the instance fleet status.
PROVISIONING—The instance fleet is provisioning Amazon EC2 resources and is not yet ready to run jobs.BOOTSTRAPPING—Amazon EC2 instances and other resources have been provisioned and the bootstrap actions specified for the instances are underway.RUNNING—Amazon EC2 instances and other resources are running. They are either executing jobs or waiting to execute jobs.RESIZING—A resize operation is underway. Amazon EC2 instances are either being added or removed.SUSPENDED—A resize operation could not complete. Existing Amazon EC2 instances are running, but instances can't be added or removed.TERMINATING—The instance fleet is terminating Amazon EC2 instances.TERMINATED—The instance fleet is no longer active, and all Amazon EC2 instances have been terminated.}The status of the instance fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_type_specification = {priority : non_negative_double option;The priority at which Amazon EMR launches the Amazon EC2 instances with this instance type. Priority starts at 0, which is the highest priority. Amazon EMR considers the highest priority first.
*)custom_ami_id : xml_string_max_len256 option;The custom AMI ID to use for the instance type.
*)ebs_optimized : boolean_object option;Evaluates to TRUE when the specified InstanceType is EBS-optimized.
ebs_block_devices : ebs_block_device_list option;The configuration of Amazon Elastic Block Store (Amazon EBS) attached to each instance as defined by InstanceType.
configurations : configuration_list option;A configuration classification that applies when provisioning cluster instances, which can include configurations for applications and software bundled with Amazon EMR.
*)bid_price_as_percentage_of_on_demand_price : non_negative_double option;The bid price, as a percentage of On-Demand price, for each Amazon EC2 Spot Instance as defined by InstanceType. Expressed as a number (for example, 20 specifies 20%).
bid_price : xml_string_max_len256 option;The bid price for each Amazon EC2 Spot Instance type as defined by InstanceType. Expressed in USD. If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
weighted_capacity : whole_number option;The number of units that a provisioned instance of this type provides toward fulfilling the target capacities defined in InstanceFleetConfig. Capacity values represent performance characteristics such as vCPUs, memory, or I/O. If not specified, the default value is 1.
instance_type : instance_type option;The Amazon EC2 instance type, for example m3.xlarge.
}The configuration specification for each instance type in an instance fleet.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_type_specification_list = instance_type_specification listtype nonrec instance_fleet = {context : xml_string_max_len256 option;Reserved.
*)resize_specifications : instance_fleet_resizing_specifications option;The resize specification for the instance fleet.
*)launch_specifications : instance_fleet_provisioning_specifications option;Describes the launch specification for an instance fleet.
*)instance_type_specifications : instance_type_specification_list option;An array of specifications for the instance types that comprise an instance fleet.
*)provisioned_spot_capacity : whole_number option;The number of Spot units that have been provisioned for this instance fleet to fulfill TargetSpotCapacity. This provisioned capacity might be less than or greater than TargetSpotCapacity.
provisioned_on_demand_capacity : whole_number option;The number of On-Demand units that have been provisioned for the instance fleet to fulfill TargetOnDemandCapacity. This provisioned capacity might be less than or greater than TargetOnDemandCapacity.
target_spot_capacity : whole_number option;The target capacity of Spot units for the instance fleet, which determines how many Spot Instances to provision. When the instance fleet launches, Amazon EMR tries to provision Spot Instances as specified by InstanceTypeConfig. Each instance configuration has a specified WeightedCapacity. When a Spot instance is provisioned, the WeightedCapacity units count toward the target capacity. Amazon EMR provisions instances until the target capacity is totally fulfilled, even if this results in an overage. For example, if there are 2 units remaining to fulfill capacity, and Amazon EMR can only provision an instance with a WeightedCapacity of 5 units, the instance is provisioned, and the target capacity is exceeded by 3 units. You can use InstanceFleet$ProvisionedSpotCapacity to determine the Spot capacity units that have been provisioned for the instance fleet.
If not specified or set to 0, only On-Demand Instances are provisioned for the instance fleet. At least one of TargetSpotCapacity and TargetOnDemandCapacity should be greater than 0. For a master instance fleet, only one of TargetSpotCapacity and TargetOnDemandCapacity can be specified, and its value must be 1.
target_on_demand_capacity : whole_number option;The target capacity of On-Demand units for the instance fleet, which determines how many On-Demand Instances to provision. When the instance fleet launches, Amazon EMR tries to provision On-Demand Instances as specified by InstanceTypeConfig. Each instance configuration has a specified WeightedCapacity. When an On-Demand Instance is provisioned, the WeightedCapacity units count toward the target capacity. Amazon EMR provisions instances until the target capacity is totally fulfilled, even if this results in an overage. For example, if there are 2 units remaining to fulfill capacity, and Amazon EMR can only provision an instance with a WeightedCapacity of 5 units, the instance is provisioned, and the target capacity is exceeded by 3 units. You can use InstanceFleet$ProvisionedOnDemandCapacity to determine the Spot capacity units that have been provisioned for the instance fleet.
If not specified or set to 0, only Spot Instances are provisioned for the instance fleet using TargetSpotCapacity. At least one of TargetSpotCapacity and TargetOnDemandCapacity should be greater than 0. For a master instance fleet, only one of TargetSpotCapacity and TargetOnDemandCapacity can be specified, and its value must be 1.
instance_fleet_type : instance_fleet_type option;The node type that the instance fleet hosts. Valid values are MASTER, CORE, or TASK.
*)status : instance_fleet_status option;The current status of the instance fleet.
*)name : xml_string_max_len256 option;A friendly name for the instance fleet.
*)id : instance_fleet_id option;The unique identifier of the instance fleet.
*)}Describes an instance fleet, which is a group of Amazon EC2 instances that host a particular node type (master, core, or task) in an Amazon EMR cluster. Instance fleets can consist of a mix of instance types and On-Demand and Spot Instances, which are provisioned to meet a defined target capacity.
The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
type nonrec instance_fleet_list = instance_fleet listtype nonrec list_instance_fleets_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)instance_fleets : instance_fleet_list option;The list of instance fleets for the cluster and given filters.
*)}type nonrec list_instance_fleets_input = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)cluster_id : cluster_id;The unique identifier of the cluster.
*)}type nonrec cluster_state_change_reason = {message : string_ option;The descriptive message for the state change reason.
*)code : cluster_state_change_reason_code option;The programmatic code for the state change reason.
*)}The reason that the cluster changed to its current state.
type nonrec cluster_timeline = {end_date_time : date option;The date and time when the cluster was terminated.
*)ready_date_time : date option;The date and time when the cluster was ready to run steps.
*)creation_date_time : date option;The creation date and time of the cluster.
*)}Represents the timeline of the cluster's lifecycle.
type nonrec error_data = string_map listtype nonrec error_detail = {error_message : string_ option;A message that describes the error.
*)error_data : error_data option;A list of key value pairs that provides contextual information about why an error occured.
*)error_code : string_ option;The name or code associated with the error.
*)}A tuple that provides information about an error that caused a cluster to terminate.
type nonrec error_detail_list = error_detail listtype nonrec cluster_status = {error_details : error_detail_list option;A list of tuples that provides information about the errors that caused a cluster to terminate. This structure can contain up to 10 different ErrorDetail tuples.
timeline : cluster_timeline option;A timeline that represents the status of a cluster over the lifetime of the cluster.
*)state_change_reason : cluster_state_change_reason option;The reason for the cluster status change.
*)state : cluster_state option;The current state of the cluster.
*)}The detailed status of the cluster.
type nonrec cluster_summary = {outpost_arn : optional_arn_type option;The Amazon Resource Name (ARN) of the Outpost where the cluster is launched.
*)cluster_arn : arn_type option;The Amazon Resource Name of the cluster.
*)normalized_instance_hours : integer option;An approximation of the cost of the cluster, represented in m1.small/hours. This value is incremented one time for every hour an m1.small instance runs. Larger instances are weighted more, so an Amazon EC2 instance that is roughly four times more expensive would result in the normalized instance hours being incremented by four. This result is only an approximation and does not reflect the actual billing rate.
*)status : cluster_status option;The details about the current status of the cluster.
*)name : string_ option;The name of the cluster.
*)id : cluster_id option;The unique identifier for the cluster.
*)}The summary description of the cluster.
type nonrec cluster_summary_list = cluster_summary listtype nonrec list_clusters_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)clusters : cluster_summary_list option;The list of clusters for the account based on the given filters.
*)}This contains a ClusterSummaryList with the cluster details; for example, the cluster IDs, names, and status.
type nonrec cluster_state_list = cluster_state listtype nonrec list_clusters_input = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)cluster_states : cluster_state_list option;The cluster state filters to apply when listing clusters. Clusters that change state while this action runs may be not be returned as expected in the list of clusters.
*)created_before : date option;The creation date and time end value filter for listing clusters.
*)created_after : date option;The creation date and time beginning value filter for listing clusters.
*)}This input determines how the ListClusters action filters the list of clusters that it returns.
type nonrec command = {args : string_list option;Arguments for Amazon EMR to pass to the command for execution.
*)script_path : string_ option;The Amazon S3 location of the command script.
*)name : string_ option;The name of the command.
*)}An entity describing an executable that runs on a cluster.
type nonrec command_list = command listtype nonrec list_bootstrap_actions_output = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)bootstrap_actions : command_list option;The bootstrap actions associated with the cluster.
*)}This output contains the bootstrap actions detail.
type nonrec list_bootstrap_actions_input = {marker : marker option;The pagination token that indicates the next set of results to retrieve.
*)cluster_id : cluster_id;The cluster identifier for the bootstrap actions to list.
*)}This input determines which bootstrap actions to retrieve.
type nonrec instance_group_detail = {custom_ami_id : xml_string_max_len256 option;The custom AMI ID to use for the provisioned instance group.
*)end_date_time : date option;The date/time the instance group was terminated.
*)ready_date_time : date option;The date/time the instance group was available to the cluster.
*)start_date_time : date option;The date/time the instance group was started.
*)creation_date_time : date;The date/time the instance group was created.
*)last_state_change_reason : xml_string option;Details regarding the state of the instance group.
*)state : instance_group_state;State of instance group. The following values are no longer supported: STARTING, TERMINATED, and FAILED.
*)instance_running_count : integer;Actual count of running instances.
*)instance_request_count : integer;Target number of instances to run in the instance group.
*)instance_type : instance_type;Amazon EC2 instance type.
*)bid_price : xml_string_max_len256 option;The bid price for each Amazon EC2 Spot Instance type as defined by InstanceType. Expressed in USD. If neither BidPrice nor BidPriceAsPercentageOfOnDemandPrice is provided, BidPriceAsPercentageOfOnDemandPrice defaults to 100%.
instance_role : instance_role_type;Instance group role in the cluster
*)market : market_type;Market type of the Amazon EC2 instances used to create a cluster node.
*)name : xml_string_max_len256 option;Friendly name for the instance group.
*)instance_group_id : xml_string_max_len256 option;Unique identifier for the instance group.
*)}Detailed information about an instance group.
type nonrec instance_group_detail_list = instance_group_detail listtype nonrec job_flow_instances_detail = {hadoop_version : xml_string_max_len256 option;The Hadoop version for the cluster.
*)unhealthy_node_replacement : boolean_object option;Indicates whether Amazon EMR should gracefully replace core nodes that have degraded within the cluster.
*)termination_protected : boolean_ option;Specifies whether the Amazon EC2 instances in the cluster are protected from termination by API calls, user intervention, or in the event of a job-flow error.
*)keep_job_flow_alive_when_no_steps : boolean_ option;Specifies whether the cluster should remain available after completing all steps.
*)placement : placement_type option;The Amazon EC2 Availability Zone for the cluster.
*)ec2_subnet_id : xml_string_max_len256 option;For clusters launched within Amazon Virtual Private Cloud, this is the identifier of the subnet where the cluster was launched.
*)ec2_key_name : xml_string_max_len256 option;The name of an Amazon EC2 key pair that can be used to connect to the master node using SSH.
*)normalized_instance_hours : integer option;An approximation of the cost of the cluster, represented in m1.small/hours. This value is increased one time for every hour that an m1.small instance runs. Larger instances are weighted more heavily, so an Amazon EC2 instance that is roughly four times more expensive would result in the normalized instance hours being increased incrementally four times. This result is only an approximation and does not reflect the actual billing rate.
*)instance_groups : instance_group_detail_list option;Details about the instance groups in a cluster.
*)instance_count : integer;The number of Amazon EC2 instances in the cluster. If the value is 1, the same instance serves as both the master and core and task node. If the value is greater than 1, one instance is the master node and all others are core and task nodes.
*)slave_instance_type : instance_type;The Amazon EC2 core and task node instance type.
*)master_instance_id : xml_string option;The Amazon EC2 instance identifier of the master node.
*)master_public_dns_name : xml_string option;The DNS name of the master node. If the cluster is on a private subnet, this is the private DNS name. On a public subnet, this is the public DNS name.
*)master_instance_type : instance_type;The Amazon EC2 master node instance type.
*)}Specify the type of Amazon EC2 instances that the cluster (job flow) runs on.
type nonrec job_flow_execution_status_detail = {last_state_change_reason : xml_string option;Description of the job flow last changed state.
*)end_date_time : date option;The completion date and time of the job flow.
*)ready_date_time : date option;The date and time when the job flow was ready to start running bootstrap actions.
*)start_date_time : date option;The start date and time of the job flow.
*)creation_date_time : date;The creation date and time of the job flow.
*)state : job_flow_execution_state;The state of the job flow.
*)}Describes the status of the cluster (job flow).
type nonrec job_flow_execution_state_list = job_flow_execution_state listtype nonrec bootstrap_action_detail = {bootstrap_action_config : bootstrap_action_config option;A description of the bootstrap action.
*)}Reports the configuration of a bootstrap action in a cluster (job flow).
type nonrec bootstrap_action_detail_list = bootstrap_action_detail listtype nonrec job_flow_detail = {scale_down_behavior : scale_down_behavior option;The way that individual Amazon EC2 instances terminate when an automatic scale-in activity occurs or an instance group is resized. TERMINATE_AT_INSTANCE_HOUR indicates that Amazon EMR terminates nodes at the instance-hour boundary, regardless of when the request to terminate the instance was submitted. This option is only available with Amazon EMR 5.1.0 and later and is the default for clusters created using that version. TERMINATE_AT_TASK_COMPLETION indicates that Amazon EMR adds nodes to a deny list and drains tasks from nodes before terminating the Amazon EC2 instances, regardless of the instance-hour boundary. With either behavior, Amazon EMR removes the least active nodes first and blocks instance termination if it could lead to HDFS corruption. TERMINATE_AT_TASK_COMPLETION available only in Amazon EMR releases 4.1.0 and later, and is the default for releases of Amazon EMR earlier than 5.1.0.
auto_scaling_role : xml_string option;An IAM role for automatic scaling policies. The default role is EMR_AutoScaling_DefaultRole. The IAM role provides a way for the automatic scaling feature to get the required permissions it needs to launch and terminate Amazon EC2 instances in an instance group.
service_role : xml_string option;The IAM role that is assumed by the Amazon EMR service to access Amazon Web Services resources on your behalf.
*)job_flow_role : xml_string option;The IAM role that was specified when the job flow was launched. The Amazon EC2 instances of the job flow assume this role.
*)visible_to_all_users : boolean_ option;Indicates whether the cluster is visible to IAM principals in the Amazon Web Services account associated with the cluster. When true, IAM principals in the Amazon Web Services account can perform Amazon EMR cluster actions that their IAM policies allow. When false, only the IAM principal that created the cluster and the Amazon Web Services account root user can perform Amazon EMR actions, regardless of IAM permissions policies attached to other IAM principals.
The default value is true if a value is not provided when creating a cluster using the Amazon EMR API RunJobFlow command, the CLI create-cluster command, or the Amazon Web Services Management Console.
supported_products : supported_products_list option;A list of strings set by third-party software when the job flow is launched. If you are not using third-party software to manage the job flow, this value is empty.
*)bootstrap_actions : bootstrap_action_detail_list option;A list of the bootstrap actions run by the job flow.
*)steps : step_detail_list option;A list of steps run by the job flow.
*)instances : job_flow_instances_detail;Describes the Amazon EC2 instances of the job flow.
*)execution_status_detail : job_flow_execution_status_detail;Describes the execution status of the job flow.
*)ami_version : xml_string_max_len256 option;Applies only to Amazon EMR AMI versions 3.x and 2.x. For Amazon EMR releases 4.0 and later, ReleaseLabel is used. To specify a custom AMI, use CustomAmiID.
log_encryption_kms_key_id : xml_string option;The KMS key used for encrypting log files. This attribute is only available with Amazon EMR 5.30.0 and later, excluding 6.0.0.
*)log_uri : xml_string option;The location in Amazon S3 where log files for the job are stored.
*)name : xml_string_max_len256;The name of the job flow.
*)job_flow_id : xml_string_max_len256;The job flow identifier.
*)}A description of a cluster (job flow).
type nonrec job_flow_detail_list = job_flow_detail listtype nonrec instance_group_ids_list = xml_string_max_len256 listtype nonrec get_studio_session_mapping_output = {session_mapping : session_mapping_detail option;The session mapping details for the specified Amazon EMR Studio and identity, including session policy ARN and creation time.
*)}type nonrec get_studio_session_mapping_input = {identity_type : identity_type;Specifies whether the identity to fetch is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user or group to fetch. For more information, see UserName and DisplayName in the IAM Identity Center Identity Store API Reference. Either IdentityName or IdentityId must be specified.
identity_id : xml_string_max_len256 option;studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio.
*)}type nonrec get_session_output = {session : session;The output displays information about the session.
*)}Output of the GetSession operation.
type nonrec get_session_input = {session_id : session_id;The ID of the session.
*)cluster_id : cluster_id;The ID of the cluster that the session belongs to.
*)}Input to the GetSession operation.
type nonrec credentials = | UsernamePassword of username_passwordThe username and password that you use to connect to cluster endpoints.
*)The credentials that you can use to connect to cluster endpoints. Credentials consist of a username and a password.
type nonrec get_session_endpoint_output = {credentials : credentials option;Username and password used to authenticate with the Spark Connect server when connecting directly over VPC peering.
*)auth_token_expiration_time : date option;The time at which the authentication token expires. After this time, call GetSessionEndpoint again to obtain a new token.
auth_token : sensitive_string option;A time-limited authentication token used to connect to the Spark Connect endpoint.
*)endpoint : xml_string;The Spark Connect endpoint URL to use in the PySpark client.
*)}Output of the GetSessionEndpoint operation.
type nonrec get_session_endpoint_input = {session_id : session_id;The ID of the session.
*)cluster_id : cluster_id;The ID of the cluster that the session belongs to.
*)}Input to the GetSessionEndpoint operation.
type nonrec get_persistent_app_ui_presigned_url_output = {presigned_ur_l : xml_string option;The returned presigned URL.
*)presigned_url_ready : boolean_ option;Used to determine if the presigned URL is ready.
*)}type nonrec get_persistent_app_ui_presigned_url_input = {execution_role_arn : arn_type option;The execution role ARN associated with the presigned URL.
*)auth_proxy_call : boolean_object option;A boolean that represents if the caller is an authentication proxy call.
*)application_id : xml_string_max_len256 option;The application ID associated with the presigned URL.
*)persistent_app_ui_type : persistent_app_ui_type option;The persistent application user interface type associated with the presigned URL.
*)persistent_app_ui_id : xml_string_max_len256;The persistent application user interface ID associated with the presigned URL.
*)}type nonrec get_on_cluster_app_ui_presigned_url_output = {presigned_ur_l : xml_string option;The cluster's generated presigned URL.
*)presigned_url_ready : boolean_ option;Used to determine if the presigned URL is ready.
*)}type nonrec get_on_cluster_app_ui_presigned_url_input = {execution_role_arn : arn_type option;The execution role ARN associated with the cluster's application user interface presigned URL.
*)dry_run : boolean_object option;Determines if the user interface presigned URL is for a dry run.
*)application_id : xml_string_max_len256 option;The application ID associated with the cluster's application user interface presigned URL.
*)on_cluster_app_ui_type : on_cluster_app_ui_type option;The application UI type associated with the cluster's application user interface presigned URL.
*)cluster_id : xml_string_max_len256;The cluster ID associated with the cluster's application user interface presigned URL.
*)}type nonrec get_managed_scaling_policy_output = {managed_scaling_policy : managed_scaling_policy option;Specifies the managed scaling policy that is attached to an Amazon EMR cluster.
*)}type nonrec get_managed_scaling_policy_input = {cluster_id : cluster_id;Specifies the ID of the cluster for which the managed scaling policy will be fetched.
*)}type nonrec get_cluster_session_credentials_output = {expires_at : date option;The time when the credentials that are returned by the GetClusterSessionCredentials API expire.
credentials : credentials option;The credentials that you can use to connect to cluster endpoints that support username and password authentication.
*)}type nonrec get_cluster_session_credentials_input = {execution_role_arn : arn_type option;The Amazon Resource Name (ARN) of the runtime role for interactive workload submission on the cluster. The runtime role can be a cross-account IAM role. The runtime role ARN is a combination of account ID, role name, and role type using the following format: arn:partition:service:region:account:resource.
cluster_id : xml_string_max_len256;The unique identifier of the cluster.
*)}type nonrec block_public_access_configuration_metadata = {created_by_arn : arn_type;The Amazon Resource Name that created or last modified the configuration.
*)creation_date_time : date;The date and time that the configuration was created.
*)}Properties that describe the Amazon Web Services principal that created the BlockPublicAccessConfiguration using the PutBlockPublicAccessConfiguration action as well as the date and time that the configuration was created. Each time a configuration for block public access is updated, Amazon EMR updates this metadata.
type nonrec get_block_public_access_configuration_output = {block_public_access_configuration_metadata : block_public_access_configuration_metadata;Properties that describe the Amazon Web Services principal that created the BlockPublicAccessConfiguration using the PutBlockPublicAccessConfiguration action as well as the date and time that the configuration was created. Each time a configuration for block public access is updated, Amazon EMR updates this metadata.
block_public_access_configuration : block_public_access_configuration;A configuration for Amazon EMR block public access. The configuration applies to all clusters created in your account for the current Region. The configuration specifies whether block public access is enabled. If block public access is enabled, security groups associated with the cluster cannot have rules that allow inbound traffic from 0.0.0.0/0 or ::/0 on a port, unless the port is specified as an exception using PermittedPublicSecurityGroupRuleRanges in the BlockPublicAccessConfiguration. By default, Port 22 (SSH) is an exception, and public access is allowed on this port. You can change this by updating the block public access configuration to remove the exception.
For accounts that created clusters in a Region before November 25, 2019, block public access is disabled by default in that Region. To use this feature, you must manually enable and configure it. For accounts that did not create an Amazon EMR cluster in a Region before this date, block public access is enabled by default in that Region.
*)}type nonrec get_auto_termination_policy_output = {auto_termination_policy : auto_termination_policy option;Specifies the auto-termination policy that is attached to an Amazon EMR cluster.
*)}type nonrec get_auto_termination_policy_input = {cluster_id : cluster_id;Specifies the ID of the Amazon EMR cluster for which the auto-termination policy will be fetched.
*)}type nonrec describe_studio_input = {studio_id : xml_string_max_len256;The Amazon EMR Studio ID.
*)}type nonrec describe_step_output = {step : step option;The step details for the requested step identifier.
*)}This output contains the description of the cluster step.
type nonrec describe_step_input = {step_id : step_id;The identifier of the step to describe.
*)cluster_id : cluster_id;The identifier of the cluster with steps to describe.
*)}This input determines which step to describe.
type nonrec describe_security_configuration_output = {creation_date_time : date option;The date and time the security configuration was created
*)security_configuration : string_ option;The security configuration details in JSON format.
*)name : xml_string option;The name of the security configuration.
*)}type nonrec describe_security_configuration_input = {name : xml_string;The name of the security configuration.
*)}type nonrec describe_release_label_output = {available_os_releases : os_release_list option;The list of available Amazon Linux release versions for an Amazon EMR release. Contains a Label field that is formatted as shown in Amazon Linux 2 Release Notes. For example, 2.0.20220218.1.
*)next_token : string_ option;The pagination token. Reserved for future use. Currently set to null.
*)applications : simplified_application_list option;The list of applications available for the target release label. Name is the name of the application. Version is the concise version of the application.
release_label : string_ option;The target release label described in the response.
*)}type nonrec describe_release_label_input = {max_results : max_results_number option;Reserved for future use. Currently set to null.
*)next_token : string_ option;The pagination token. Reserved for future use. Currently set to null.
*)release_label : string_ option;The target release label to be described.
*)}type nonrec describe_persistent_app_ui_output = {persistent_app_u_i : persistent_app_u_i option;The persistent application user interface.
*)}type nonrec describe_persistent_app_ui_input = {persistent_app_ui_id : xml_string_max_len256;The identifier for the persistent application user interface.
*)}type nonrec describe_notebook_execution_output = {notebook_execution : notebook_execution option;Properties of the notebook execution.
*)}type nonrec describe_notebook_execution_input = {notebook_execution_id : xml_string_max_len256;The unique identifier of the notebook execution.
*)}type nonrec describe_job_flows_output = {job_flows : job_flow_detail_list option;A list of job flows matching the parameters supplied.
*)}The output for the DescribeJobFlows operation.
type nonrec describe_job_flows_input = {job_flow_states : job_flow_execution_state_list option;Return only job flows whose state is contained in this list.
*)job_flow_ids : xml_string_list option;Return only job flows whose job flow ID is contained in this list.
*)created_before : date option;Return only job flows created before this date and time.
*)created_after : date option;Return only job flows created after this date and time.
*)}The input for the DescribeJobFlows operation.
type nonrec ec2_instance_attributes = {additional_slave_security_groups : string_list option;A list of additional Amazon EC2 security group IDs for the core and task nodes.
*)additional_master_security_groups : string_list option;A list of additional Amazon EC2 security group IDs for the master node.
*)service_access_security_group : string_ option;The identifier of the Amazon EC2 security group for the Amazon EMR service to access clusters in VPC private subnets.
*)emr_managed_slave_security_group : string_ option;The identifier of the Amazon EC2 security group for the core and task nodes.
*)emr_managed_master_security_group : string_ option;The identifier of the Amazon EC2 security group for the master node.
*)iam_instance_profile : string_ option;The IAM role that was specified when the cluster was launched. The Amazon EC2 instances of the cluster assume this role.
*)requested_ec2_availability_zones : xml_string_max_len256_list option;Applies to clusters configured with the instance fleets option. Specifies one or more Availability Zones in which to launch Amazon EC2 cluster instances when the EC2-Classic network configuration is supported. Amazon EMR chooses the Availability Zone with the best fit from among the list of RequestedEc2AvailabilityZones, and then launches all cluster instances within that Availability Zone. If you do not specify this value, Amazon EMR chooses the Availability Zone for you. RequestedEc2SubnetIDs and RequestedEc2AvailabilityZones cannot be specified together.
ec2_availability_zone : string_ option;The Availability Zone in which the cluster will run.
*)requested_ec2_subnet_ids : xml_string_max_len256_list option;Applies to clusters configured with the instance fleets option. Specifies the unique identifier of one or more Amazon EC2 subnets in which to launch Amazon EC2 cluster instances. Subnets must exist within the same VPC. Amazon EMR chooses the Amazon EC2 subnet with the best fit from among the list of RequestedEc2SubnetIds, and then launches all cluster instances within that Subnet. If this value is not specified, and the account and Region support EC2-Classic networks, the cluster launches instances in the EC2-Classic network and uses RequestedEc2AvailabilityZones instead of this setting. If EC2-Classic is not supported, and no Subnet is specified, Amazon EMR chooses the subnet for you. RequestedEc2SubnetIDs and RequestedEc2AvailabilityZones cannot be specified together.
ec2_subnet_id : string_ option;Set this parameter to the identifier of the Amazon VPC subnet where you want the cluster to launch. If you do not specify this value, and your account supports EC2-Classic, the cluster launches in EC2-Classic.
*)ec2_key_name : string_ option;The name of the Amazon EC2 key pair to use when connecting with SSH into the master node as a user named "hadoop".
*)}Provides information about the Amazon EC2 instances in a cluster grouped by category. For example, key name, subnet ID, IAM instance profile, and so on.
type nonrec cluster = {session_enabled : boolean_object option;Indicates whether Spark Connect sessions are enabled on the cluster.
*)monitoring_configuration : monitoring_configuration option;Contains Cloudwatch log configuration metadata and settings.
*)extended_support : boolean_object option;Reserved.
*)ebs_root_volume_throughput : integer option;The throughput, in MiB/s, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 6.15.0 and later.
*)ebs_root_volume_iops : integer option;The IOPS, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 6.15.0 and later.
*)os_release_label : string_ option;The Amazon Linux release specified in a cluster launch RunJobFlow request. If no Amazon Linux release was specified, the default Amazon Linux release is shown in the response.
*)placement_groups : placement_group_config_list option;Placement group configured for an Amazon EMR cluster.
*)step_concurrency_level : integer option;Specifies the number of steps that can be executed concurrently.
*)outpost_arn : optional_arn_type option;The Amazon Resource Name (ARN) of the Outpost where the cluster is launched.
*)cluster_arn : arn_type option;The Amazon Resource Name of the cluster.
*)kerberos_attributes : kerberos_attributes option;Attributes for Kerberos configuration when Kerberos authentication is enabled using a security configuration. For more information see Use Kerberos Authentication in the Amazon EMR Management Guide.
*)repo_upgrade_on_boot : repo_upgrade_on_boot option;Applies only when CustomAmiID is used. Specifies the type of updates that the Amazon Linux AMI package repositories apply when an instance boots using the AMI.
ebs_root_volume_size : integer option;The size, in GiB, of the Amazon EBS root device volume of the Linux AMI that is used for each Amazon EC2 instance. Available in Amazon EMR releases 4.x and later.
*)custom_ami_id : xml_string_max_len256 option;Available only in Amazon EMR releases 5.7.0 and later. The ID of a custom Amazon EBS-backed Linux AMI if the cluster uses a custom AMI.
*)scale_down_behavior : scale_down_behavior option;The way that individual Amazon EC2 instances terminate when an automatic scale-in activity occurs or an instance group is resized. TERMINATE_AT_INSTANCE_HOUR indicates that Amazon EMR terminates nodes at the instance-hour boundary, regardless of when the request to terminate the instance was submitted. This option is only available with Amazon EMR 5.1.0 and later and is the default for clusters created using that version. TERMINATE_AT_TASK_COMPLETION indicates that Amazon EMR adds nodes to a deny list and drains tasks from nodes before terminating the Amazon EC2 instances, regardless of the instance-hour boundary. With either behavior, Amazon EMR removes the least active nodes first and blocks instance termination if it could lead to HDFS corruption. TERMINATE_AT_TASK_COMPLETION is available only in Amazon EMR releases 4.1.0 and later, and is the default for versions of Amazon EMR earlier than 5.1.0.
auto_scaling_role : xml_string option;An IAM role for automatic scaling policies. The default role is EMR_AutoScaling_DefaultRole. The IAM role provides permissions that the automatic scaling feature requires to launch and terminate Amazon EC2 instances in an instance group.
security_configuration : xml_string option;The name of the security configuration applied to the cluster.
*)configurations : configuration_list option;Applies only to Amazon EMR releases 4.x and later. The list of configurations that are supplied to the Amazon EMR cluster.
*)master_public_dns_name : string_ option;The DNS name of the master node. If the cluster is on a private subnet, this is the private DNS name. On a public subnet, this is the public DNS name.
*)normalized_instance_hours : integer option;An approximation of the cost of the cluster, represented in m1.small/hours. This value is incremented one time for every hour an m1.small instance runs. Larger instances are weighted more, so an Amazon EC2 instance that is roughly four times more expensive would result in the normalized instance hours being incremented by four. This result is only an approximation and does not reflect the actual billing rate.
*)service_role : string_ option;The IAM role that Amazon EMR assumes in order to access Amazon Web Services resources on your behalf.
*)applications : application_list option;The applications installed on this cluster.
*)visible_to_all_users : boolean_ option;Indicates whether the cluster is visible to IAM principals in the Amazon Web Services account associated with the cluster. When true, IAM principals in the Amazon Web Services account can perform Amazon EMR cluster actions on the cluster that their IAM policies allow. When false, only the IAM principal that created the cluster and the Amazon Web Services account root user can perform Amazon EMR actions, regardless of IAM permissions policies attached to other IAM principals.
The default value is true if a value is not provided when creating a cluster using the Amazon EMR API RunJobFlow command, the CLI create-cluster command, or the Amazon Web Services Management Console.
unhealthy_node_replacement : boolean_object option;Indicates whether Amazon EMR should gracefully replace Amazon EC2 core instances that have degraded within the cluster.
*)termination_protected : boolean_ option;Indicates whether Amazon EMR will lock the cluster to prevent the Amazon EC2 instances from being terminated by an API call or user intervention, or in the event of a cluster error.
*)auto_terminate : boolean_ option;Specifies whether the cluster should terminate after completing all steps.
*)release_label : string_ option;The Amazon EMR release label, which determines the version of open-source application packages installed on the cluster. Release labels are in the form emr-x.x.x, where x.x.x is an Amazon EMR release version such as emr-5.14.0. For more information about Amazon EMR release versions and included application versions and features, see https://docs.aws.amazon.com/emr/latest/ReleaseGuide/. The release label applies only to Amazon EMR releases version 4.0 and later. Earlier versions use AmiVersion.
running_ami_version : string_ option;The AMI version running on this cluster.
*)requested_ami_version : string_ option;The AMI version requested for this cluster.
*)log_encryption_kms_key_id : string_ option;The KMS key used for encrypting log files. This attribute is only available with Amazon EMR 5.30.0 and later, excluding Amazon EMR 6.0.0.
*)log_uri : string_ option;The path to the Amazon S3 location where logs for this cluster are stored.
*)instance_collection_type : instance_collection_type option;The instance fleet configuration is available only in Amazon EMR releases 4.8.0 and later, excluding 5.0.x versions.
The instance group configuration of the cluster. A value of INSTANCE_GROUP indicates a uniform instance group configuration. A value of INSTANCE_FLEET indicates an instance fleets configuration.
ec2_instance_attributes : ec2_instance_attributes option;Provides information about the Amazon EC2 instances in a cluster grouped by category. For example, key name, subnet ID, IAM instance profile, and so on.
*)status : cluster_status option;The current status details about the cluster.
*)name : string_ option;The name of the cluster. This parameter can't contain the characters <, >, $, |, or ` (backtick).
*)id : cluster_id option;The unique identifier for the cluster.
*)}The detailed description of the cluster.
type nonrec describe_cluster_output = {cluster : cluster option;This output contains the details for the requested cluster.
*)}This output contains the description of the cluster.
type nonrec describe_cluster_input = {cluster_id : cluster_id;The identifier of the cluster to describe.
*)}This input determines which cluster to describe.
type nonrec delete_studio_session_mapping_input = {identity_type : identity_type;Specifies whether the identity to delete from the Amazon EMR Studio is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user name or group to remove from the Amazon EMR Studio. For more information, see UserName and DisplayName in the IAM Identity Center Store API Reference. Either IdentityName or IdentityId must be specified.
identity_id : xml_string_max_len256 option;studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio.
*)}type nonrec delete_studio_input = {studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio.
*)}type nonrec delete_security_configuration_input = {name : xml_string;The name of the security configuration.
*)}type nonrec create_studio_session_mapping_input = {session_policy_arn : xml_string_max_len256;The Amazon Resource Name (ARN) for the session policy that will be applied to the user or group. You should specify the ARN for the session policy that you want to apply, not the ARN of your user role. For more information, see Create an Amazon EMR Studio User Role with Session Policies.
*)identity_type : identity_type;Specifies whether the identity to map to the Amazon EMR Studio is a user or a group.
*)identity_name : xml_string_max_len256 option;The name of the user or group. For more information, see UserName and DisplayName in the IAM Identity Center Identity Store API Reference. Either IdentityName or IdentityId must be specified, but not both.
identity_id : xml_string_max_len256 option;studio_id : xml_string_max_len256;The ID of the Amazon EMR Studio to which the user or group will be mapped.
*)}type nonrec create_studio_output = {url : xml_string option;The unique Studio access URL.
*)studio_id : xml_string_max_len256 option;The ID of the Amazon EMR Studio.
*)}type nonrec create_studio_input = {encryption_key_arn : xml_string option;The KMS key identifier (ARN) used to encrypt Amazon EMR Studio workspace and notebook files when backed up to Amazon S3.
*)idc_instance_arn : arn_type option;The ARN of the IAM Identity Center instance to create the Studio application.
*)idc_user_assignment : idc_user_assignment option;Specifies whether IAM Identity Center user assignment is REQUIRED or OPTIONAL. If the value is set to REQUIRED, users must be explicitly assigned to the Studio application to access the Studio.
trusted_identity_propagation_enabled : boolean_object option;A Boolean indicating whether to enable Trusted identity propagation for the Studio. The default value is false.
idp_relay_state_parameter_name : xml_string_max_len256 option;The name that your identity provider (IdP) uses for its RelayState parameter. For example, RelayState or TargetSource. Specify this value when you use IAM authentication and want to let federated users log in to a Studio using the Studio URL. The RelayState parameter differs by IdP.
idp_auth_url : xml_string option;The authentication endpoint of your identity provider (IdP). Specify this value when you use IAM authentication and want to let federated users log in to a Studio with the Studio URL and credentials from your IdP. Amazon EMR Studio redirects users to this endpoint to enter credentials.
*)default_s3_location : xml_string;The Amazon S3 location to back up Amazon EMR Studio Workspaces and notebook files.
*)engine_security_group_id : xml_string_max_len256;The ID of the Amazon EMR Studio Engine security group. The Engine security group allows inbound network traffic from the Workspace security group, and it must be in the same VPC specified by VpcId.
workspace_security_group_id : xml_string_max_len256;The ID of the Amazon EMR Studio Workspace security group. The Workspace security group allows outbound network traffic to resources in the Engine security group, and it must be in the same VPC specified by VpcId.
user_role : xml_string option;The IAM user role that users and groups assume when logged in to an Amazon EMR Studio. Only specify a UserRole when you use IAM Identity Center authentication. The permissions attached to the UserRole can be scoped down for each user or group using session policies.
service_role : xml_string;The IAM role that the Amazon EMR Studio assumes. The service role provides a way for Amazon EMR Studio to interoperate with other Amazon Web Services services.
*)subnet_ids : subnet_id_list;A list of subnet IDs to associate with the Amazon EMR Studio. A Studio can have a maximum of 5 subnets. The subnets must belong to the VPC specified by VpcId. Studio users can create a Workspace in any of the specified subnets.
vpc_id : xml_string_max_len256;The ID of the Amazon Virtual Private Cloud (Amazon VPC) to associate with the Studio.
*)auth_mode : auth_mode;Specifies whether the Studio authenticates users using IAM or IAM Identity Center.
*)description : xml_string_max_len256 option;A detailed description of the Amazon EMR Studio.
*)name : xml_string_max_len256;A descriptive name for the Amazon EMR Studio.
*)}type nonrec create_security_configuration_output = {creation_date_time : date;The date and time the security configuration was created.
*)name : xml_string;The name of the security configuration.
*)}type nonrec create_security_configuration_input = {security_configuration : string_;The security configuration details in JSON format. For JSON parameters and examples, see Use Security Configurations to Set Up Cluster Security in the Amazon EMR Management Guide.
*)name : xml_string;The name of the security configuration.
*)}type nonrec create_persistent_app_ui_output = {runtime_role_enabled_cluster : boolean_ option;Represents if the EMR on EC2 cluster that the persisent application user interface is created for is a runtime role enabled cluster or not.
*)persistent_app_ui_id : xml_string_max_len256 option;The persistent application user interface identifier.
*)}type nonrec emr_containers_config = {job_run_id : xml_string_max_len256 option;The Job run ID for the container configuration.
*)}The EMR container configuration.
type nonrec create_persistent_app_ui_input = {profiler_type : profiler_type option;The profiler type for the persistent application user interface.
*)x_referer : string_ option;The cross reference for the persistent application user interface.
*)emr_containers_config : emr_containers_config option;The EMR containers configuration.
*)target_resource_arn : arn_type;The unique Amazon Resource Name (ARN) of the target resource.
*)}type nonrec cancel_steps_info = {reason : string_ option;The reason for the failure if the CancelSteps request fails.
*)status : cancel_steps_request_status option;The status of a CancelSteps Request. The value may be SUBMITTED or FAILED.
*)step_id : step_id option;The encrypted StepId of a step.
*)}Specification of the status of a CancelSteps request. Available only in Amazon EMR version 4.8.0 and later, excluding version 5.0.0.
type nonrec cancel_steps_info_list = cancel_steps_info listtype nonrec cancel_steps_output = {cancel_steps_info_list : cancel_steps_info_list option;A list of CancelStepsInfo, which shows the status of specified cancel requests for each StepID specified.
}The output for the CancelSteps operation.
type nonrec cancel_steps_input = {step_cancellation_option : step_cancellation_option option;The option to choose to cancel RUNNING steps. By default, the value is SEND_INTERRUPT.
step_ids : step_ids_list;The list of StepIDs to cancel. Use ListSteps to get steps and their states for the specified cluster.
cluster_id : xml_string_max_len256;The ClusterID for the specified steps that will be canceled. Use RunJobFlow and ListClusters to get ClusterIDs.
}The input argument to the CancelSteps operation.
This input identifies an Amazon EMR resource and a list of tags to attach.
type nonrec add_job_flow_steps_output = {step_ids : step_ids_list option;The identifiers of the list of steps added to the job flow.
*)}The output for the AddJobFlowSteps operation.
type nonrec add_job_flow_steps_input = {execution_role_arn : arn_type option;The Amazon Resource Name (ARN) of the runtime role for a step on the cluster. The runtime role can be a cross-account IAM role. The runtime role ARN is a combination of account ID, role name, and role type using the following format: arn:partition:service:region:account:resource.
For example, arn:aws:IAM::1234567890:role/ReadOnly is a correctly formatted runtime role ARN.
steps : step_config_list;A list of StepConfig to be executed by the job flow.
job_flow_id : xml_string_max_len256;A string that uniquely identifies the job flow. This identifier is returned by RunJobFlow and can also be obtained from ListClusters.
}The input argument to the AddJobFlowSteps operation.
type nonrec add_instance_groups_output = {cluster_arn : arn_type option;The Amazon Resource Name of the cluster.
*)instance_group_ids : instance_group_ids_list option;Instance group IDs of the newly created instance groups.
*)job_flow_id : xml_string_max_len256 option;The job flow ID in which the instance groups are added.
*)}Output from an AddInstanceGroups call.
type nonrec add_instance_groups_input = {job_flow_id : xml_string_max_len256;Job flow in which to add the instance groups.
*)instance_groups : instance_group_config_list;Instance groups to add.
*)}Input to an AddInstanceGroups call.
type nonrec add_instance_fleet_output = {cluster_arn : arn_type option;The Amazon Resource Name of the cluster.
*)instance_fleet_id : instance_fleet_id option;The unique identifier of the instance fleet.
*)cluster_id : xml_string_max_len256 option;The unique identifier of the cluster.
*)}type nonrec add_instance_fleet_input = {instance_fleet : instance_fleet_config;Specifies the configuration of the instance fleet.
*)cluster_id : xml_string_max_len256;The unique identifier of the cluster.
*)}