{ "api_version": "2009-03-31", "type": "json", "json_version": 1.1, "target_prefix": "ElasticMapReduce", "signature_version": "v4", "service_full_name": "Amazon Elastic MapReduce", "service_abbreviation": "Amazon EMR", "timestamp_format": "unixTimestamp", "endpoint_prefix": "elasticmapreduce", "documentation": "\n
This is the Amazon Elastic MapReduce API Reference. This guide provides descriptions and\n samples of the Amazon Elastic MapReduce APIs.
\n\nAmazon Elastic MapReduce (Amazon EMR) is a web service that makes it easy to process large amounts of\n data efficiently. Amazon EMR uses Hadoop processing combined with several AWS\n products to do tasks such as web indexing, data mining, log file analysis, machine\n learning, scientific simulation, and data warehousing.
\n\n ", "operations": { "AddInstanceGroups": { "name": "AddInstanceGroups", "input": { "shape_name": "AddInstanceGroupsInput", "type": "structure", "members": { "InstanceGroups": { "shape_name": "InstanceGroupConfigList", "type": "list", "members": { "shape_name": "InstanceGroupConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nFriendly name given to the instance group.
\n " }, "Market": { "shape_name": "MarketType", "type": "string", "enum": [ "ON_DEMAND", "SPOT" ], "documentation": "\nMarket type of the Amazon EC2 instances used to create a cluster node.
\n " }, "InstanceRole": { "shape_name": "InstanceRoleType", "type": "string", "enum": [ "MASTER", "CORE", "TASK" ], "documentation": "\nThe role of the instance group in the cluster.
\n ", "required": true }, "BidPrice": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nBid price for each Amazon EC2 instance in the\n instance group when launching nodes as Spot Instances, expressed in USD.
\n " }, "InstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe Amazon EC2 instance type for all instances in the instance group.
\n ", "required": true }, "InstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nTarget number of instances for the instance group.
\n ", "required": true } }, "documentation": "\nConfiguration defining a new instance group.
\n " }, "documentation": "\nInstance Groups to add.
\n ", "required": true }, "JobFlowId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nJob flow in which to add the instance groups.
\n ", "required": true } }, "documentation": "\nInput to an AddInstanceGroups call.
\n " }, "output": { "shape_name": "AddInstanceGroupsOutput", "type": "structure", "members": { "JobFlowId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe job flow ID in which the instance groups are added.
\n " }, "InstanceGroupIds": { "shape_name": "InstanceGroupIdsList", "type": "list", "members": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": null }, "documentation": "\nInstance group IDs of the newly created instance groups.
\n " } }, "documentation": "\nOutput from an AddInstanceGroups call.
\n " }, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nAddInstanceGroups adds an instance group to a running cluster.
\n\nA string that uniquely identifies the job flow. This identifier is returned by\n RunJobFlow and can also be obtained from DescribeJobFlows.
\n ", "required": true }, "Steps": { "shape_name": "StepConfigList", "type": "list", "members": { "shape_name": "StepConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the job flow step.
\n ", "required": true }, "ActionOnFailure": { "shape_name": "ActionOnFailure", "type": "string", "enum": [ "TERMINATE_JOB_FLOW", "TERMINATE_CLUSTER", "CANCEL_AND_WAIT", "CONTINUE" ], "documentation": "\nThe action to take if the job flow step fails.
\n " }, "HadoopJarStep": { "shape_name": "HadoopJarStepConfig", "type": "structure", "members": { "Properties": { "shape_name": "KeyValueList", "type": "list", "members": { "shape_name": "KeyValue", "type": "structure", "members": { "Key": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe unique identifier of a key value pair.
\n " }, "Value": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe value part of the identified key.
\n " } }, "documentation": "\nA key value pair.
\n " }, "documentation": "\nA list of Java properties that are set when the step runs. You can use these properties to\n pass key value pairs to your main function.
\n " }, "Jar": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nA path to a JAR file run during the step.
\n ", "required": true }, "MainClass": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe name of the main class in the specified Java file. If not specified, the JAR file\n should specify a Main-Class in its manifest file.
\n " }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nA list of command line arguments passed to the JAR file's main function when executed.
\n " } }, "documentation": "\nThe JAR file used for the job flow step.
\n ", "required": true } }, "documentation": "\nSpecification of a job flow step.
\n " }, "documentation": "\nA list of StepConfig to be executed by the job flow.
\n ", "required": true } }, "documentation": "\nThe input argument to the AddJobFlowSteps operation.
\n " }, "output": { "shape_name": "AddJobFlowStepsOutput", "type": "structure", "members": { "StepIds": { "shape_name": "StepIdsList", "type": "list", "members": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": null }, "documentation": "\nThe identifiers of the list of steps added to the job flow.
\n " } }, "documentation": "\nThe output for the AddJobFlowSteps operation.
\n " }, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nAddJobFlowSteps adds new steps to a running job flow. A maximum of 256 steps are allowed\n in each job flow.
\nIf your job flow is long-running (such as a Hive data warehouse) or complex, you may require more than 256 steps to process your data. You can bypass the 256-step limitation in various ways, including using the SSH shell to connect to the master node and submitting queries directly to the software running on the master node, such as Hive and Hadoop. For more information on how to do this, go to Add More than 256 Steps to a Job Flow in the Amazon Elastic MapReduce Developer's Guide.
\nA step specifies the location of a JAR file stored either on the master node of the job\n flow or in Amazon S3. Each step is performed by the main function of the main class of the\n JAR file. The main class can be specified either in the manifest of the JAR or by using the\n MainFunction parameter of the step.
\nElastic MapReduce executes each step in the order listed. For a step to be considered\n complete, the main function must exit with a zero exit code and all Hadoop jobs started\n while the step was running must have completed and run successfully.
\nYou can only add steps to a job flow that is in one of the following states: STARTING,\n BOOTSTRAPPING, RUNNING, or WAITING.
\n\nThe Amazon EMR resource identifier to which tags will be added. This value must be a cluster identifier.
\n " }, "Tags": { "shape_name": "TagList", "type": "list", "members": { "shape_name": "Tag", "type": "structure", "members": { "Key": { "shape_name": "String", "type": "string", "documentation": "\nA user-defined key, which is the minimum required information for a valid tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "Value": { "shape_name": "String", "type": "string", "documentation": "\nA user-defined value, which is optional in a tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " } }, "documentation": "\nA key/value pair that contains 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. \n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "documentation": "\nA list of tags to associate with a cluster and propagate to Amazon EC2 instances. Tags are user-defined key/value pairs that consist of a required key string with a maximum of 128 characters, and an optional value string with a maximum of 256 characters.
\n " } }, "documentation": "\nThis input identifies a cluster and a list of tags to attach.\n
\n " }, "output": { "shape_name": "AddTagsOutput", "type": "structure", "members": {}, "documentation": "\nThis output indicates the result of adding tags to a resource. \n
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nAdds tags to 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. \n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "DescribeCluster": { "name": "DescribeCluster", "input": { "shape_name": "DescribeClusterInput", "type": "structure", "members": { "ClusterId": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe identifier of the cluster to describe.
\n " } }, "documentation": "\nThis input determines which cluster to describe.
\n " }, "output": { "shape_name": "DescribeClusterOutput", "type": "structure", "members": { "Cluster": { "shape_name": "Cluster", "type": "structure", "members": { "Id": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe unique identifier for the cluster.
" }, "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the cluster.
" }, "Status": { "shape_name": "ClusterStatus", "type": "structure", "members": { "State": { "shape_name": "ClusterState", "type": "string", "enum": [ "STARTING", "BOOTSTRAPPING", "RUNNING", "WAITING", "TERMINATING", "TERMINATED", "TERMINATED_WITH_ERRORS" ], "documentation": "\nThe current state of the cluster.
\n " }, "StateChangeReason": { "shape_name": "ClusterStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "ClusterStateChangeReasonCode", "type": "string", "enum": [ "INTERNAL_ERROR", "VALIDATION_ERROR", "INSTANCE_FAILURE", "BOOTSTRAP_FAILURE", "USER_REQUEST", "STEP_FAILURE", "ALL_STEPS_COMPLETED" ], "documentation": "\nThe programmatic code for the state change reason.
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe descriptive message for the state change reason.
\n " } }, "documentation": "\nThe reason for the cluster status change.
\n " }, "Timeline": { "shape_name": "ClusterTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the cluster.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster was ready to execute steps.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster was terminated.
\n " } }, "documentation": "\nA timeline that represents the status of a cluster over the lifetime of the cluster.
\n " } }, "documentation": "\nThe current status details about the cluster.
\n " }, "Ec2InstanceAttributes": { "shape_name": "Ec2InstanceAttributes", "type": "structure", "members": { "Ec2KeyName": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the Amazon EC2 key pair to use when connecting with SSH into the master node as\n a user named \"hadoop\".
\n " }, "Ec2SubnetId": { "shape_name": "String", "type": "string", "documentation": "\n\n To launch the job flow in Amazon VPC, set this parameter to the identifier of the Amazon VPC subnet where \n you want the job flow to launch. If you do not specify this value, the job flow is launched in the normal AWS cloud, outside of \n a VPC. \n
\n\n Amazon VPC currently does not support cluster compute quadruple extra large (cc1.4xlarge) instances. \n Thus, you cannot specify the cc1.4xlarge instance type for nodes of a job flow launched in a VPC.\n
\n " }, "Ec2AvailabilityZone": { "shape_name": "String", "type": "string", "documentation": "\nThe Availability Zone in which the cluster will run.
\n " }, "IamInstanceProfile": { "shape_name": "String", "type": "string", "documentation": "\nThe IAM role that was specified when the job flow was launched. The EC2 instances of the job flow assume this role.
\n " } }, "documentation": "\nProvides information about the EC2 instances in a cluster grouped by category. For example, EC2 Key Name, Subnet Id, Instance Profile, and so on.
\n " }, "LogUri": { "shape_name": "String", "type": "string", "documentation": "\nThe path to the Amazon S3 location where logs for this cluster are stored.
\n " }, "RequestedAmiVersion": { "shape_name": "String", "type": "string", "documentation": "\nThe AMI version requested for this cluster.
\n " }, "RunningAmiVersion": { "shape_name": "String", "type": "string", "documentation": "\nThe AMI version running on this cluster. This differs from the requested version only if the requested version is a meta version, such as \"latest\".
\n " }, "AutoTerminate": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether the cluster should terminate after completing all steps.
\n " }, "TerminationProtected": { "shape_name": "Boolean", "type": "boolean", "documentation": " \nIndicates whether Amazon EMR will lock the cluster to prevent the EC2 instances from being terminated by an API call or \n user intervention, or in the event of a cluster error.
" }, "VisibleToAllUsers": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nIndicates whether the job flow is visible to all IAM users of the AWS account associated with the job flow. If this value is set to true
, all IAM users of that AWS account can view and manage the job flow if they have the proper policy permissions set. \n If this value is false
, only the IAM user that created the cluster can view and manage it. This value can be changed using the SetVisibleToAllUsers action.
The name of the application.
" }, "Version": { "shape_name": "String", "type": "string", "documentation": "\nThe version of the application.
" }, "Args": { "shape_name": "StringList", "type": "list", "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nArguments for Amazon EMR to pass to the application.
" }, "AdditionalInfo": { "shape_name": "StringMap", "type": "map", "keys": { "shape_name": "String", "type": "string", "documentation": null }, "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nThis option is for advanced users only. This is meta information about third-party applications that third-party vendors use for testing purposes.
" } }, "documentation": "\nAn 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\n script as bootstrap action argument. For more information, see Launch a Job Flow on the MapR Distribution for Hadoop. Currently supported values are:
\nThe applications installed on this cluster.
\n " }, "Tags": { "shape_name": "TagList", "type": "list", "members": { "shape_name": "Tag", "type": "structure", "members": { "Key": { "shape_name": "String", "type": "string", "documentation": "\nA user-defined key, which is the minimum required information for a valid tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "Value": { "shape_name": "String", "type": "string", "documentation": "\nA user-defined value, which is optional in a tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " } }, "documentation": "\nA key/value pair that contains 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. \n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "documentation": "\nA list of tags associated with cluster.
" } }, "documentation": "\nThis output contains the details for the requested cluster.
\n " } }, "documentation": "\nThis output contains the description of the cluster.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides cluster-level details including status, hardware and software configuration, VPC settings, and so on. For information about the cluster steps, see ListSteps.
\n \n " }, "DescribeJobFlows": { "name": "DescribeJobFlows", "input": { "shape_name": "DescribeJobFlowsInput", "type": "structure", "members": { "CreatedAfter": { "shape_name": "Date", "type": "timestamp", "documentation": "\nReturn only job flows created after this date and time.
\n " }, "CreatedBefore": { "shape_name": "Date", "type": "timestamp", "documentation": "\nReturn only job flows created before this date and time.
\n " }, "JobFlowIds": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nReturn only job flows whose job flow ID is contained in this list.
\n " }, "JobFlowStates": { "shape_name": "JobFlowExecutionStateList", "type": "list", "members": { "shape_name": "JobFlowExecutionState", "type": "string", "enum": [ "STARTING", "BOOTSTRAPPING", "RUNNING", "WAITING", "SHUTTING_DOWN", "TERMINATED", "COMPLETED", "FAILED" ], "documentation": "\nThe type of instance.
\nA small instance
\nA large instance
\nReturn only job flows whose state is contained in this list.
\n " } }, "documentation": "\nThe input for the DescribeJobFlows operation.
\n " }, "output": { "shape_name": "DescribeJobFlowsOutput", "type": "structure", "members": { "JobFlows": { "shape_name": "JobFlowDetailList", "type": "list", "members": { "shape_name": "JobFlowDetail", "type": "structure", "members": { "JobFlowId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe job flow identifier.
\n ", "required": true }, "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the job flow.
\n ", "required": true }, "LogUri": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe location in Amazon S3 where log files for the job are stored.
\n " }, "AmiVersion": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe version of the AMI used to initialize Amazon EC2 instances in the job flow. For a list of AMI versions currently \n supported by Amazon ElasticMapReduce, go to AMI Versions Supported in Elastic MapReduce in the \n Amazon Elastic MapReduce Developer's Guide.
\n " }, "ExecutionStatusDetail": { "shape_name": "JobFlowExecutionStatusDetail", "type": "structure", "members": { "State": { "shape_name": "JobFlowExecutionState", "type": "string", "enum": [ "STARTING", "BOOTSTRAPPING", "RUNNING", "WAITING", "SHUTTING_DOWN", "TERMINATED", "COMPLETED", "FAILED" ], "documentation": "\nThe state of the job flow.
\n ", "required": true }, "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the job flow.
\n ", "required": true }, "StartDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe start date and time of the job flow.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the job flow was ready to start running bootstrap actions.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe completion date and time of the job flow.
\n " }, "LastStateChangeReason": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nDescription of the job flow last changed state.
\n " } }, "documentation": "\nDescribes the execution status of the job flow.
\n ", "required": true }, "Instances": { "shape_name": "JobFlowInstancesDetail", "type": "structure", "members": { "MasterInstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe Amazon EC2 master node instance type.
\n ", "required": true }, "MasterPublicDnsName": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe DNS name of the master node.
\n " }, "MasterInstanceId": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe Amazon EC2 instance identifier of the master node.
\n " }, "SlaveInstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe Amazon EC2 slave node instance type.
\n ", "required": true }, "InstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nThe number of Amazon EC2 instances in the cluster. If the value is 1, the same instance\n serves as both the master and slave node. If the value is greater than 1, one instance is\n the master node and all others are slave nodes.
\n ", "required": true }, "InstanceGroups": { "shape_name": "InstanceGroupDetailList", "type": "list", "members": { "shape_name": "InstanceGroupDetail", "type": "structure", "members": { "InstanceGroupId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nUnique identifier for the instance group.
\n " }, "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nFriendly name for the instance group.
\n " }, "Market": { "shape_name": "MarketType", "type": "string", "enum": [ "ON_DEMAND", "SPOT" ], "documentation": "\nMarket type of the Amazon EC2 instances used to create a cluster node.
\n ", "required": true }, "InstanceRole": { "shape_name": "InstanceRoleType", "type": "string", "enum": [ "MASTER", "CORE", "TASK" ], "documentation": "\nInstance group role in the cluster
\n ", "required": true }, "BidPrice": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nBid price for EC2 Instances when launching nodes as\n Spot Instances, expressed in USD.
\n " }, "InstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nAmazon EC2 Instance type.
\n ", "required": true }, "InstanceRequestCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nTarget number of instances to run in the instance group.
\n ", "required": true }, "InstanceRunningCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nActual count of running instances.
\n ", "required": true }, "State": { "shape_name": "InstanceGroupState", "type": "string", "enum": [ "PROVISIONING", "BOOTSTRAPPING", "RUNNING", "RESIZING", "SUSPENDED", "TERMINATING", "TERMINATED", "ARRESTED", "SHUTTING_DOWN", "ENDED" ], "documentation": "\nState of instance group. The following values are deprecated: STARTING, TERMINATED, and FAILED.
\n ", "required": true }, "LastStateChangeReason": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nDetails regarding the state of the instance group.
\n " }, "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date/time the instance group was created.
\n ", "required": true }, "StartDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date/time the instance group was started.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date/time the instance group was available to the cluster.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date/time the instance group was terminated.
\n " } }, "documentation": "\nDetailed information about an instance group.
\n " }, "documentation": "\nDetails about the job flow's instance groups.
\n " }, "NormalizedInstanceHours": { "shape_name": "Integer", "type": "integer", "documentation": "\nAn approximation of the cost of the job flow, represented in m1.small/hours. This value is\n incremented once for every hour an m1.small runs. Larger instances are weighted more, so an\n Amazon EC2 instance that is roughly four times more expensive would result in the\n normalized instance hours being incremented by four. This result is only an approximation\n and does not reflect the actual billing rate.
\n " }, "Ec2KeyName": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of an Amazon EC2 key pair that can be used to ssh to the master node of job\n flow.
\n " }, "Ec2SubnetId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nFor job flows launched within Amazon Virtual Private Cloud, this value specifies the identifier of the subnet where the job flow was launched.
\n " }, "Placement": { "shape_name": "PlacementType", "type": "structure", "members": { "AvailabilityZone": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe Amazon EC2 Availability Zone for the job flow.
\n ", "required": true } }, "documentation": "\nThe Amazon EC2 Availability Zone for the job flow.
\n " }, "KeepJobFlowAliveWhenNoSteps": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether the job flow should terminate after completing all steps.
\n " }, "TerminationProtected": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether the Amazon EC2 instances in the cluster are protected from termination by API calls, \n user intervention, or in the event of a job flow error.
\n " }, "HadoopVersion": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe Hadoop version for the job flow.
\n " } }, "documentation": "\nDescribes the Amazon EC2 instances of the job flow.
\n ", "required": true }, "Steps": { "shape_name": "StepDetailList", "type": "list", "members": { "shape_name": "StepDetail", "type": "structure", "members": { "StepConfig": { "shape_name": "StepConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the job flow step.
\n ", "required": true }, "ActionOnFailure": { "shape_name": "ActionOnFailure", "type": "string", "enum": [ "TERMINATE_JOB_FLOW", "TERMINATE_CLUSTER", "CANCEL_AND_WAIT", "CONTINUE" ], "documentation": "\nThe action to take if the job flow step fails.
\n " }, "HadoopJarStep": { "shape_name": "HadoopJarStepConfig", "type": "structure", "members": { "Properties": { "shape_name": "KeyValueList", "type": "list", "members": { "shape_name": "KeyValue", "type": "structure", "members": { "Key": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe unique identifier of a key value pair.
\n " }, "Value": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe value part of the identified key.
\n " } }, "documentation": "\nA key value pair.
\n " }, "documentation": "\nA list of Java properties that are set when the step runs. You can use these properties to\n pass key value pairs to your main function.
\n " }, "Jar": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nA path to a JAR file run during the step.
\n ", "required": true }, "MainClass": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe name of the main class in the specified Java file. If not specified, the JAR file\n should specify a Main-Class in its manifest file.
\n " }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nA list of command line arguments passed to the JAR file's main function when executed.
\n " } }, "documentation": "\nThe JAR file used for the job flow step.
\n ", "required": true } }, "documentation": "\nThe step configuration.
\n ", "required": true }, "ExecutionStatusDetail": { "shape_name": "StepExecutionStatusDetail", "type": "structure", "members": { "State": { "shape_name": "StepExecutionState", "type": "string", "enum": [ "PENDING", "RUNNING", "CONTINUE", "COMPLETED", "CANCELLED", "FAILED", "INTERRUPTED" ], "documentation": "\nThe state of the job flow step.
\n ", "required": true }, "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the step.
\n ", "required": true }, "StartDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe start date and time of the step.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe completion date and time of the step.
\n " }, "LastStateChangeReason": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nA description of the step's current state.
\n " } }, "documentation": "\nThe description of the step status.
\n ", "required": true } }, "documentation": "\nCombines the execution state and configuration of a step.
\n " }, "documentation": "\nA list of steps run by the job flow.
\n " }, "BootstrapActions": { "shape_name": "BootstrapActionDetailList", "type": "list", "members": { "shape_name": "BootstrapActionDetail", "type": "structure", "members": { "BootstrapActionConfig": { "shape_name": "BootstrapActionConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the bootstrap action.
\n ", "required": true }, "ScriptBootstrapAction": { "shape_name": "ScriptBootstrapActionConfig", "type": "structure", "members": { "Path": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nLocation of the script to run during a bootstrap action. Can be either a location in Amazon\n S3 or on a local file system.
\n ", "required": true }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nA list of command line arguments to pass to the bootstrap action script.
\n " } }, "documentation": "\nThe script run by the bootstrap action.
\n ", "required": true } }, "documentation": "\nA description of the bootstrap action.
\n " } }, "documentation": "\nReports the configuration of a bootstrap action in a job flow.
\n " }, "documentation": "\nA list of the bootstrap actions run by the job flow.
\n " }, "SupportedProducts": { "shape_name": "SupportedProductsList", "type": "list", "members": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": null }, "documentation": "\nA 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.
\n " }, "VisibleToAllUsers": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether the job flow is visible to all IAM users of the AWS account associated with the job flow. If this value is set to true
, all IAM users of that AWS account can view and (if they have the proper policy permissions set) manage the job flow. If it is set to false
, only the IAM user that created the job flow can view and manage it. This value can be changed using the SetVisibleToAllUsers action.
The IAM role that was specified when the job flow was launched. The EC2 instances of the job flow assume this role.
\n " } }, "documentation": "\nA description of a job flow.
\n " }, "documentation": "\nA list of job flows matching the parameters supplied.
\n " } }, "documentation": "\nThe output for the DescribeJobFlows operation.
\n " }, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nDescribeJobFlows returns a list of job flows that match all of the supplied parameters.\n The parameters can include a list of job flow IDs, job flow states, and restrictions on job\n flow creation date and time.
\nRegardless of supplied parameters, only job flows created within the last two months are\n returned.
\nIf no parameters are supplied, then job flows matching either of the following criteria\n are returned:
\nRUNNING
, WAITING
, SHUTTING_DOWN
,\n STARTING
\n Amazon Elastic MapReduce can return a maximum of 512 job flow descriptions.
\nThe identifier of the cluster with steps to describe.
\n " }, "StepId": { "shape_name": "StepId", "type": "string", "documentation": "\nThe identifier of the step to describe.
\n " } }, "documentation": "\nThis input determines which step to describe.
\n " }, "output": { "shape_name": "DescribeStepOutput", "type": "structure", "members": { "Step": { "shape_name": "Step", "type": "structure", "members": { "Id": { "shape_name": "StepId", "type": "string", "documentation": "\nThe identifier of the cluster step.
\n " }, "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the cluster step.
\n " }, "Config": { "shape_name": "HadoopStepConfig", "type": "structure", "members": { "Jar": { "shape_name": "String", "type": "string", "documentation": "\nThe path to the JAR file that runs during the step.
\n " }, "Properties": { "shape_name": "StringMap", "type": "map", "keys": { "shape_name": "String", "type": "string", "documentation": null }, "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nThe list of Java properties that are set when the step runs. You can use these properties to\n pass key value pairs to your main function.
\n " }, "MainClass": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the main class in the specified Java file. If not specified, the JAR file\n should specify a main class in its manifest file.
\n " }, "Args": { "shape_name": "StringList", "type": "list", "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nThe list of command line arguments to pass to the JAR file's main function for execution.
\n " } }, "documentation": "\nThe Hadoop job configuration of the cluster step.\n
\n " }, "ActionOnFailure": { "shape_name": "ActionOnFailure", "type": "string", "enum": [ "TERMINATE_JOB_FLOW", "TERMINATE_CLUSTER", "CANCEL_AND_WAIT", "CONTINUE" ], "documentation": "\nThis specifies what action to take when the cluster step fails. TERMINATE_JOB_FLOW is deprecated, use TERMINATE_CLUSTER instead.\n
\n " }, "Status": { "shape_name": "StepStatus", "type": "structure", "members": { "State": { "shape_name": "StepState", "type": "string", "enum": [ "PENDING", "RUNNING", "COMPLETED", "CANCELLED", "FAILED", "INTERRUPTED" ], "documentation": "\nThe execution state of the cluster step.\n
\n " }, "StateChangeReason": { "shape_name": "StepStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "StepStateChangeReasonCode", "type": "string", "enum": [ "NONE" ], "documentation": "\nThe programmable code for the state change reason.\n
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe descriptive message for the state change reason.\n
\n " } }, "documentation": "\nThe reason for the step execution status change.\n
\n " }, "Timeline": { "shape_name": "StepTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step was created.\n
\n " }, "StartDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step execution started.\n Due to delays in step status reporting, this can display a time which pre-dates a previous call to DescribeStep that indicated the step was not yet running. \n
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step execution completed or failed. \n This can display a time that pre-dates a call to DescribeStep that indicates the step is running, due to delays in step status reporting. \n
\n " } }, "documentation": "\nThe timeline of the cluster step status over time.\n
\n " } }, "documentation": "\nThe current execution status details of the cluster step.\n
\n " } }, "documentation": "\nThe step details for the requested step identifier.
\n " } }, "documentation": "\nThis output contains the description of the cluster step.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides more detail about the cluster step.
\n " }, "ListBootstrapActions": { "name": "ListBootstrapActions", "input": { "shape_name": "ListBootstrapActionsInput", "type": "structure", "members": { "ClusterId": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe cluster identifier for the bootstrap actions to list.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Provide the pagination token from earlier API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis input determines which bootstrap actions to retrieve.
\n " }, "output": { "shape_name": "ListBootstrapActionsOutput", "type": "structure", "members": { "BootstrapActions": { "shape_name": "CommandList", "type": "list", "members": { "shape_name": "Command", "type": "structure", "members": { "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the command.
\n " }, "ScriptPath": { "shape_name": "String", "type": "string", "documentation": "\nThe Amazon S3 location of the command script.
\n " }, "Args": { "shape_name": "StringList", "type": "list", "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nArguments for Amazon EMR to pass to the command for execution.
\n " } }, "documentation": "\nAn entity describing an executable that runs on a cluster.
\n " }, "documentation": "\nThe bootstrap actions associated with the cluster.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Use the pagination token in later API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis output contains the bootstrap actions detail.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides information about the bootstrap actions associated with a cluster.
\n \n " }, "ListClusters": { "name": "ListClusters", "input": { "shape_name": "ListClustersInput", "type": "structure", "members": { "CreatedAfter": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time beginning value filter for listing clusters.
\n " }, "CreatedBefore": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time end value filter for listing clusters.
\n " }, "ClusterStates": { "shape_name": "ClusterStateList", "type": "list", "members": { "shape_name": "ClusterState", "type": "string", "enum": [ "STARTING", "BOOTSTRAPPING", "RUNNING", "WAITING", "TERMINATING", "TERMINATED", "TERMINATED_WITH_ERRORS" ], "documentation": null }, "documentation": "\nThe cluster state filters to apply when listing clusters.\n
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Provide the pagination token from earlier API calls to retrieve the next page of results. When the value is null, all results have been returned.\n
\n " } }, "documentation": "\nThis input determines how the ListClusters action filters the list of clusters that it returns.
\n " }, "output": { "shape_name": "ListClustersOutput", "type": "structure", "members": { "Clusters": { "shape_name": "ClusterSummaryList", "type": "list", "members": { "shape_name": "ClusterSummary", "type": "structure", "members": { "Id": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe unique identifier for the cluster.
\n " }, "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the cluster.
\n " }, "Status": { "shape_name": "ClusterStatus", "type": "structure", "members": { "State": { "shape_name": "ClusterState", "type": "string", "enum": [ "STARTING", "BOOTSTRAPPING", "RUNNING", "WAITING", "TERMINATING", "TERMINATED", "TERMINATED_WITH_ERRORS" ], "documentation": "\nThe current state of the cluster.
\n " }, "StateChangeReason": { "shape_name": "ClusterStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "ClusterStateChangeReasonCode", "type": "string", "enum": [ "INTERNAL_ERROR", "VALIDATION_ERROR", "INSTANCE_FAILURE", "BOOTSTRAP_FAILURE", "USER_REQUEST", "STEP_FAILURE", "ALL_STEPS_COMPLETED" ], "documentation": "\nThe programmatic code for the state change reason.
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe descriptive message for the state change reason.
\n " } }, "documentation": "\nThe reason for the cluster status change.
\n " }, "Timeline": { "shape_name": "ClusterTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the cluster.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster was ready to execute steps.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster was terminated.
\n " } }, "documentation": "\nA timeline that represents the status of a cluster over the lifetime of the cluster.
\n " } }, "documentation": "\nThe details about the current status of the cluster.
\n " } }, "documentation": "\nThe summary description of the cluster.
\n " }, "documentation": "\nThe list of clusters for the account based on the given filters.\n
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Use the pagination token in later API calls to retrieve the next page of results. When the value is null, all results have been returned. \n
\n " } }, "documentation": "\nThis contains a ClusterSummaryList with the cluster details; for example, the cluster IDs, names, and status.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides the status of all clusters visible to this AWS account. Allows you to filter the list of clusters based on certain criteria; for example, filtering by cluster creation date and time or by status.\n This call returns a maximum of 50 clusters per call, but returns a marker to track the paging of the cluster list across multiple ListClusters calls. \n
\n \n " }, "ListInstanceGroups": { "name": "ListInstanceGroups", "input": { "shape_name": "ListInstanceGroupsInput", "type": "structure", "members": { "ClusterId": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe identifier of the cluster for which to list the instance groups.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Provide the pagination token from earlier API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis input determines which instance groups to retrieve.
\n " }, "output": { "shape_name": "ListInstanceGroupsOutput", "type": "structure", "members": { "InstanceGroups": { "shape_name": "InstanceGroupList", "type": "list", "members": { "shape_name": "InstanceGroup", "type": "structure", "members": { "Id": { "shape_name": "InstanceGroupId", "type": "string", "documentation": "\nThe identifier of the instance group.
\n " }, "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the instance group.
\n " }, "Market": { "shape_name": "MarketType", "type": "string", "enum": [ "ON_DEMAND", "SPOT" ], "documentation": "\nThe marketplace to provision instances for this group. Valid values are ON_DEMAND or SPOT.
\n " }, "InstanceGroupType": { "shape_name": "InstanceGroupType", "type": "string", "enum": [ "MASTER", "CORE", "TASK" ], "documentation": "\nThe type of the instance group. Valid values are MASTER, CORE or TASK.
\n " }, "BidPrice": { "shape_name": "String", "type": "string", "documentation": "\nThe bid price for each EC2 instance in the\n instance group when launching nodes as Spot Instances, expressed in USD.
\n " }, "InstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe EC2 instance type for all instances in the instance group.
\n " }, "RequestedInstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nThe target number of instances for the instance group.
\n " }, "RunningInstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nThe number of instances currently running in this instance group.
\n " }, "Status": { "shape_name": "InstanceGroupStatus", "type": "structure", "members": { "State": { "shape_name": "InstanceGroupState", "type": "string", "enum": [ "PROVISIONING", "BOOTSTRAPPING", "RUNNING", "RESIZING", "SUSPENDED", "TERMINATING", "TERMINATED", "ARRESTED", "SHUTTING_DOWN", "ENDED" ], "documentation": "\nThe current state of the instance group. The following values are deprecated: ARRESTED, SHUTTING_DOWN, and ENDED. Use SUSPENDED, TERMINATING, and TERMINATED instead, respectively.\n
\n " }, "StateChangeReason": { "shape_name": "InstanceGroupStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "InstanceGroupStateChangeReasonCode", "type": "string", "enum": [ "INTERNAL_ERROR", "VALIDATION_ERROR", "INSTANCE_FAILURE", "CLUSTER_TERMINATED" ], "documentation": "\nThe programmable code for the state change reason.
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe status change reason description.
\n " } }, "documentation": "\nThe status change reason details for the instance group.
\n " }, "Timeline": { "shape_name": "InstanceGroupTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the instance group.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the instance group became ready to perform tasks.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the instance group terminated.
\n " } }, "documentation": "\nThe timeline of the instance group status over time.
\n " } }, "documentation": "\nThe current status of the instance group.
\n " } }, "documentation": "\nThis entity represents an instance group, which is a group of instances that have common purpose. For example, CORE instance group is used for HDFS.
\n " }, "documentation": "\nThe list of instance groups for the cluster and given filters.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Use the pagination token in later API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis input determines which instance groups to retrieve.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides all available details about the instance groups in a cluster.
\n \n " }, "ListInstances": { "name": "ListInstances", "input": { "shape_name": "ListInstancesInput", "type": "structure", "members": { "ClusterId": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe identifier of the cluster for which to list the instances.
\n " }, "InstanceGroupId": { "shape_name": "InstanceGroupId", "type": "string", "documentation": "\nThe identifier of the instance group for which to list the instances.
\n " }, "InstanceGroupTypes": { "shape_name": "InstanceGroupTypeList", "type": "list", "members": { "shape_name": "InstanceGroupType", "type": "string", "enum": [ "MASTER", "CORE", "TASK" ], "documentation": null }, "documentation": "\nThe type of instance group for which to list the instances.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Provide the pagination token from earlier API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis input determines which instances to list.
\n " }, "output": { "shape_name": "ListInstancesOutput", "type": "structure", "members": { "Instances": { "shape_name": "InstanceList", "type": "list", "members": { "shape_name": "Instance", "type": "structure", "members": { "Id": { "shape_name": "InstanceId", "type": "string", "documentation": "\nThe unique identifier for the instance in Amazon EMR.
\n " }, "Ec2InstanceId": { "shape_name": "InstanceId", "type": "string", "documentation": "\nThe unique identifier of the instance in Amazon EC2.
\n " }, "PublicDnsName": { "shape_name": "String", "type": "string", "documentation": "\nThe public DNS name of the instance.
\n " }, "PublicIpAddress": { "shape_name": "String", "type": "string", "documentation": "\nThe public IP address of the instance.
\n " }, "PrivateDnsName": { "shape_name": "String", "type": "string", "documentation": "\nThe private DNS name of the instance.
\n " }, "PrivateIpAddress": { "shape_name": "String", "type": "string", "documentation": "\nThe private IP address of the instance.
\n " }, "Status": { "shape_name": "InstanceStatus", "type": "structure", "members": { "State": { "shape_name": "InstanceState", "type": "string", "enum": [ "AWAITING_FULFILLMENT", "PROVISIONING", "BOOTSTRAPPING", "RUNNING", "TERMINATED" ], "documentation": "\nThe current state of the instance.
\n " }, "StateChangeReason": { "shape_name": "InstanceStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "InstanceStateChangeReasonCode", "type": "string", "enum": [ "INTERNAL_ERROR", "VALIDATION_ERROR", "INSTANCE_FAILURE", "BOOTSTRAP_FAILURE", "CLUSTER_TERMINATED" ], "documentation": "\nThe programmable code for the state change reason.
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe status change reason description.
\n " } }, "documentation": "\nThe details of the status change reason for the instance.
\n " }, "Timeline": { "shape_name": "InstanceTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe creation date and time of the instance.
\n " }, "ReadyDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the instance was ready to perform tasks.
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the instance was terminated.
\n " } }, "documentation": "\nThe timeline of the instance status over time.
\n " } }, "documentation": "\nThe current status of the instance.
\n " } }, "documentation": "\nRepresents an EC2 instance provisioned as part of cluster.
\n " }, "documentation": "\nThe list of instances for the cluster and given filters.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Use the pagination token in later API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis output contains the list of instances.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides information about the cluster instances that Amazon EMR provisions on behalf of a user when it creates the cluster. \n For example, this operation indicates when the EC2 instances reach the Ready state, when instances become available to Amazon EMR to use for jobs, and the IP addresses for cluster instances, etc.\n
\n " }, "ListSteps": { "name": "ListSteps", "input": { "shape_name": "ListStepsInput", "type": "structure", "members": { "ClusterId": { "shape_name": "ClusterId", "type": "string", "documentation": "\nThe identifier of the cluster for which to list the steps.
\n " }, "StepStates": { "shape_name": "StepStateList", "type": "list", "members": { "shape_name": "StepState", "type": "string", "enum": [ "PENDING", "RUNNING", "COMPLETED", "CANCELLED", "FAILED", "INTERRUPTED" ], "documentation": null }, "documentation": "\nThe filter to limit the step list based on certain states.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Provide the pagination token from earlier API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis input determines which steps to list.
\n " }, "output": { "shape_name": "ListStepsOutput", "type": "structure", "members": { "Steps": { "shape_name": "StepSummaryList", "type": "list", "members": { "shape_name": "StepSummary", "type": "structure", "members": { "Id": { "shape_name": "StepId", "type": "string", "documentation": "\nThe identifier of the cluster step.\n
\n " }, "Name": { "shape_name": "String", "type": "string", "documentation": "\nThe name of the cluster step.\n
\n " }, "Status": { "shape_name": "StepStatus", "type": "structure", "members": { "State": { "shape_name": "StepState", "type": "string", "enum": [ "PENDING", "RUNNING", "COMPLETED", "CANCELLED", "FAILED", "INTERRUPTED" ], "documentation": "\nThe execution state of the cluster step.\n
\n " }, "StateChangeReason": { "shape_name": "StepStateChangeReason", "type": "structure", "members": { "Code": { "shape_name": "StepStateChangeReasonCode", "type": "string", "enum": [ "NONE" ], "documentation": "\nThe programmable code for the state change reason.\n
\n " }, "Message": { "shape_name": "String", "type": "string", "documentation": "\nThe descriptive message for the state change reason.\n
\n " } }, "documentation": "\nThe reason for the step execution status change.\n
\n " }, "Timeline": { "shape_name": "StepTimeline", "type": "structure", "members": { "CreationDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step was created.\n
\n " }, "StartDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step execution started.\n Due to delays in step status reporting, this can display a time which pre-dates a previous call to DescribeStep that indicated the step was not yet running. \n
\n " }, "EndDateTime": { "shape_name": "Date", "type": "timestamp", "documentation": "\nThe date and time when the cluster step execution completed or failed. \n This can display a time that pre-dates a call to DescribeStep that indicates the step is running, due to delays in step status reporting. \n
\n " } }, "documentation": "\nThe timeline of the cluster step status over time.\n
\n " } }, "documentation": "\nThe current execution status details of the cluster step.\n
\n " } }, "documentation": "\nThe summary of the cluster step.
\n " }, "documentation": "\nThe filtered list of steps for the cluster.
\n " }, "Marker": { "shape_name": "Marker", "type": "string", "documentation": "\nThe pagination token is a random string indicating whether there are more results to fetch. Use the pagination token in later API calls to retrieve the next page of results. When the value is null, all results have been returned.
\n " } }, "documentation": "\nThis output contains the list of steps.
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nProvides a list of steps for the cluster. \n
\n " }, "ModifyInstanceGroups": { "name": "ModifyInstanceGroups", "input": { "shape_name": "ModifyInstanceGroupsInput", "type": "structure", "members": { "InstanceGroups": { "shape_name": "InstanceGroupModifyConfigList", "type": "list", "members": { "shape_name": "InstanceGroupModifyConfig", "type": "structure", "members": { "InstanceGroupId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nUnique ID of the instance group to expand or shrink.
\n ", "required": true }, "InstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nTarget size for the instance group.
\n " }, "EC2InstanceIdsToTerminate": { "shape_name": "EC2InstanceIdsToTerminateList", "type": "list", "members": { "shape_name": "InstanceId", "type": "string", "documentation": null }, "documentation": "\nThe EC2 InstanceIds to terminate. For advanced users only. \n Once you terminate the instances, the instance group will not return to its original requested size.
\n " } }, "documentation": "\nModify an instance group size.
\n " }, "documentation": "\nInstance groups to change.
\n " } }, "documentation": "\nChange the size of some instance groups.
\n " }, "output": null, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nModifyInstanceGroups modifies the number of nodes and configuration settings of an instance\n group. The input parameters include the new target instance count for the group and the\n instance group ID. The call will either succeed or fail atomically.
\n\nThe Amazon EMR resource identifier from which tags will be removed. This value must be a cluster identifier.
\n " }, "TagKeys": { "shape_name": "StringList", "type": "list", "members": { "shape_name": "String", "type": "string", "documentation": null }, "documentation": "\nA list of tag keys to remove from a resource.
\n " } }, "documentation": "\nThis input identifies a cluster and a list of tags to remove. \n
\n " }, "output": { "shape_name": "RemoveTagsOutput", "type": "structure", "members": {}, "documentation": "\nThis output indicates the result of removing tags from a resource. \n
\n " }, "errors": [ { "shape_name": "InternalServerException", "type": "structure", "members": { "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is an internal failure in the EMR service.
\n \n " }, { "shape_name": "InvalidRequestException", "type": "structure", "members": { "ErrorCode": { "shape_name": "ErrorCode", "type": "string", "min_length": 1, "max_length": 256, "documentation": "\nThe error code associated with the exception.
\n \n " }, "Message": { "shape_name": "ErrorMessage", "type": "string", "documentation": "\nThe message associated with the exception.
\n \n " } }, "documentation": "\nThis exception occurs when there is something wrong with user input.
\n \n " } ], "documentation": "\nRemoves tags from 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. \n For more information, see Tagging Amazon EMR Resources. \n
\n \n " }, "RunJobFlow": { "name": "RunJobFlow", "input": { "shape_name": "RunJobFlowInput", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the job flow.
\n ", "required": true }, "LogUri": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe location in Amazon S3 to write the log files of the job flow. If a value is\n not provided, logs are not created.
\n " }, "AdditionalInfo": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nA JSON string for selecting additional features.
\n " }, "AmiVersion": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe version of the Amazon Machine Image (AMI) to use when launching Amazon EC2 instances in the job flow. The following values are valid:
\nIf the AMI supports multiple versions of Hadoop (for example, AMI 1.0 supports both Hadoop 0.18 and 0.20) you can use the \n JobFlowInstancesConfig HadoopVersion
parameter\n to modify the version of Hadoop from the defaults shown above.
For details about the AMI versions currently \n supported by Amazon Elastic MapReduce, go to AMI Versions Supported in Elastic MapReduce in the \n Amazon Elastic MapReduce Developer's Guide.\n
\n " }, "Instances": { "shape_name": "JobFlowInstancesConfig", "type": "structure", "members": { "MasterInstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe EC2 instance type of the master node.
\n " }, "SlaveInstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe EC2 instance type of the slave nodes.
\n " }, "InstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nThe number of Amazon EC2 instances used to execute the job flow.
\n " }, "InstanceGroups": { "shape_name": "InstanceGroupConfigList", "type": "list", "members": { "shape_name": "InstanceGroupConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nFriendly name given to the instance group.
\n " }, "Market": { "shape_name": "MarketType", "type": "string", "enum": [ "ON_DEMAND", "SPOT" ], "documentation": "\nMarket type of the Amazon EC2 instances used to create a cluster node.
\n " }, "InstanceRole": { "shape_name": "InstanceRoleType", "type": "string", "enum": [ "MASTER", "CORE", "TASK" ], "documentation": "\nThe role of the instance group in the cluster.
\n ", "required": true }, "BidPrice": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nBid price for each Amazon EC2 instance in the\n instance group when launching nodes as Spot Instances, expressed in USD.
\n " }, "InstanceType": { "shape_name": "InstanceType", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 1, "max_length": 256, "documentation": "\nThe Amazon EC2 instance type for all instances in the instance group.
\n ", "required": true }, "InstanceCount": { "shape_name": "Integer", "type": "integer", "documentation": "\nTarget number of instances for the instance group.
\n ", "required": true } }, "documentation": "\nConfiguration defining a new instance group.
\n " }, "documentation": "\nConfiguration for the job flow's instance groups.
\n " }, "Ec2KeyName": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the Amazon EC2 key pair that can be used to ssh to the master node as\n the user called \"hadoop.\"
\n " }, "Placement": { "shape_name": "PlacementType", "type": "structure", "members": { "AvailabilityZone": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe Amazon EC2 Availability Zone for the job flow.
\n ", "required": true } }, "documentation": "\nThe Availability Zone the job flow will run in.
\n " }, "KeepJobFlowAliveWhenNoSteps": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether the job flow should terminate after completing all steps.
\n " }, "TerminationProtected": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nSpecifies whether to lock the job flow to prevent the Amazon EC2 instances from being terminated by API call, \n user intervention, or in the event of a job flow error.
\n " }, "HadoopVersion": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe Hadoop version for the job flow. Valid inputs are \"0.18\", \"0.20\", or \"0.20.205\". If you do not set this value, the default of 0.18 is used, \n unless the AmiVersion parameter is set in the RunJobFlow call, in which case the default version of Hadoop for that AMI version is used.
\n " }, "Ec2SubnetId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\n\n To launch the job flow in Amazon Virtual Private Cloud (Amazon VPC), set this parameter to the identifier of the Amazon VPC subnet where \n you want the job flow to launch. If you do not specify this value, the job flow is launched in the normal Amazon Web Services cloud, outside of an \n Amazon VPC. \n
\n\n Amazon VPC currently does not support cluster compute quadruple extra large (cc1.4xlarge) instances. \n Thus you cannot specify the cc1.4xlarge instance type for nodes of a job flow launched in a Amazon VPC.\n
\n " } }, "documentation": "\nA specification of the number and type of Amazon EC2 instances on which to run the job\n flow.
\n ", "required": true }, "Steps": { "shape_name": "StepConfigList", "type": "list", "members": { "shape_name": "StepConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the job flow step.
\n ", "required": true }, "ActionOnFailure": { "shape_name": "ActionOnFailure", "type": "string", "enum": [ "TERMINATE_JOB_FLOW", "TERMINATE_CLUSTER", "CANCEL_AND_WAIT", "CONTINUE" ], "documentation": "\nThe action to take if the job flow step fails.
\n " }, "HadoopJarStep": { "shape_name": "HadoopJarStepConfig", "type": "structure", "members": { "Properties": { "shape_name": "KeyValueList", "type": "list", "members": { "shape_name": "KeyValue", "type": "structure", "members": { "Key": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe unique identifier of a key value pair.
\n " }, "Value": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe value part of the identified key.
\n " } }, "documentation": "\nA key value pair.
\n " }, "documentation": "\nA list of Java properties that are set when the step runs. You can use these properties to\n pass key value pairs to your main function.
\n " }, "Jar": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nA path to a JAR file run during the step.
\n ", "required": true }, "MainClass": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nThe name of the main class in the specified Java file. If not specified, the JAR file\n should specify a Main-Class in its manifest file.
\n " }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nA list of command line arguments passed to the JAR file's main function when executed.
\n " } }, "documentation": "\nThe JAR file used for the job flow step.
\n ", "required": true } }, "documentation": "\nSpecification of a job flow step.
\n " }, "documentation": "\nA list of steps to be executed by the job flow.
\n " }, "BootstrapActions": { "shape_name": "BootstrapActionConfigList", "type": "list", "members": { "shape_name": "BootstrapActionConfig", "type": "structure", "members": { "Name": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nThe name of the bootstrap action.
\n ", "required": true }, "ScriptBootstrapAction": { "shape_name": "ScriptBootstrapActionConfig", "type": "structure", "members": { "Path": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": "\nLocation of the script to run during a bootstrap action. Can be either a location in Amazon\n S3 or on a local file system.
\n ", "required": true }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nA list of command line arguments to pass to the bootstrap action script.
\n " } }, "documentation": "\nThe script run by the bootstrap action.
\n ", "required": true } }, "documentation": "\nConfiguration of a bootstrap action.
\n " }, "documentation": "\nA list of bootstrap actions that will be run before Hadoop is started on the cluster\n nodes.
\n " }, "SupportedProducts": { "shape_name": "SupportedProductsList", "type": "list", "members": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": null }, "documentation": "\nA list of strings that indicates third-party software to use with the job flow. For more information, go to Use Third Party Applications with Amazon EMR. Currently supported values are:
\nThe name of the product configuration.
\n " }, "Args": { "shape_name": "XmlStringList", "type": "list", "members": { "shape_name": "XmlString", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 10280, "documentation": null }, "documentation": "\nThe list of user-supplied arguments.
\n " } }, "documentation": "\nThe list of supported product configurations which allow user-supplied arguments. EMR accepts these arguments and forwards them to the corresponding installation script as bootstrap action arguments.
\n " }, "documentation": "\nA list of strings that indicates third-party software to use with the job flow that accepts a user argument list. EMR accepts and forwards the argument list to the corresponding installation\n script as bootstrap action arguments. For more information, see Launch a Job Flow on the MapR Distribution for Hadoop. Currently supported values are:
\nWhether the job flow is visible to all IAM users of the AWS account associated with the job flow. If this value is set to true
, all IAM users of that AWS account can view and (if they have the proper policy permissions set) manage the job flow. If it is set to false
, only the IAM user that created the job flow can view and manage it.
An IAM role for the job flow. The EC2 instances of the job flow assume this role. The default role is EMRJobflowDefault
. In order to use the default role, you must have already created it using the CLI.
A user-defined key, which is the minimum required information for a valid tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "Value": { "shape_name": "String", "type": "string", "documentation": "\nA user-defined value, which is optional in a tag.\n For more information, see Tagging Amazon EMR Resources. \n
\n " } }, "documentation": "\nA key/value pair that contains 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. \n For more information, see Tagging Amazon EMR Resources. \n
\n " }, "documentation": "\nA list of tags to associate with a cluster and propagate to Amazon EC2 instances.
\n " } }, "documentation": "\nInput to the RunJobFlow operation.
\n " }, "output": { "shape_name": "RunJobFlowOutput", "type": "structure", "members": { "JobFlowId": { "shape_name": "XmlStringMaxLen256", "type": "string", "pattern": "[\\u0020-\\uD7FF\\uE000-\\uFFFD\\uD800\\uDC00-\\uDBFF\\uDFFF\\r\\n\\t]*", "min_length": 0, "max_length": 256, "documentation": "\nAn unique identifier for the job flow.
\n " } }, "documentation": "\nThe result of the RunJobFlow operation.
\n " }, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\n RunJobFlow creates and starts running a new job flow. The job flow will run the steps\n specified. Once the job flow completes, the cluster is stopped and the HDFS partition is\n lost. To prevent loss of data, configure the last step of the job flow to store results in\n Amazon S3. If the JobFlowInstancesConfig KeepJobFlowAliveWhenNoSteps
parameter is\n set to TRUE
, the job flow will transition to the WAITING state rather than\n shutting down once the steps have completed.
For additional protection, you can set the \n JobFlowInstancesConfig TerminationProtected
parameter to TRUE
to lock the \n job flow and prevent it from being \n terminated by API call, user intervention, or in the event of a job flow error.
A maximum of 256 steps are allowed in each job flow.
\n \nIf your job flow is long-running (such as a Hive data warehouse) or complex, you may require more than 256 steps to process your data. You can bypass the 256-step limitation in various ways, including using the SSH shell to connect to the master node and submitting queries directly to the software running on the master node, such as Hive and Hadoop. For more information on how to do this, go to Add More than 256 Steps to a Job Flow in the Amazon Elastic MapReduce Developer's Guide.
\n\nFor long running job flows, we recommend that you periodically store your results.
\n\nA list of strings that uniquely identify the job flows to protect. This identifier is returned by\n RunJobFlow and can also be obtained from DescribeJobFlows .
\n ", "required": true }, "TerminationProtected": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nA Boolean that indicates whether to protect the job flow and \n prevent the Amazon EC2 instances in the cluster from shutting down due to \n API calls, user intervention, or job-flow error.
\n ", "required": true } }, "documentation": "\nThe input argument to the TerminationProtection operation.
\n " }, "output": null, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nSetTerminationProtection locks a job flow so the Amazon EC2 instances in the cluster \n cannot be terminated by user intervention, an API call, or in the event of a job-flow error. \n The cluster still terminates upon successful completion of the job flow. Calling \n SetTerminationProtection on a job flow is analogous to calling the \n Amazon EC2 DisableAPITermination API on all of the EC2 instances in a cluster.
\n \nSetTerminationProtection is used to prevent accidental termination of a job flow and to \n ensure that in the event of an error, the instances will persist so you can recover \n any data stored in their ephemeral instance storage.
\n \n To terminate a job flow that has been locked by setting SetTerminationProtection to true
, \n you must first unlock the job flow by a subsequent call to SetTerminationProtection \n in which you set the value to false
.
For more information, go to Protecting a Job Flow from Termination in the \n Amazon Elastic MapReduce Developer's Guide.
\nIdentifiers of the job flows to receive the new visibility setting.
\n ", "required": true }, "VisibleToAllUsers": { "shape_name": "Boolean", "type": "boolean", "documentation": "\nWhether the specified job flows are visible to all IAM users of the AWS account associated with the job flow. If this value is set to True, all IAM users of that AWS account can view and, if they have the proper IAM policy permissions set, manage the job flows. If it is set to False, only the IAM user that created a job flow can view and manage it.
\n ", "required": true } }, "documentation": "\nThe input to the SetVisibleToAllUsers action.
\n " }, "output": null, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\nSets whether all AWS Identity and Access Management (IAM) users under your account can access the specified job flows. This action works on running job flows. You can also set the visibility of \n a job flow when you launch it using the VisibleToAllUsers
parameter of RunJobFlow. The SetVisibleToAllUsers action can be called only by an IAM user who created the job flow or the AWS account that owns the job flow.
A list of job flows to be shutdown.
\n ", "required": true } }, "documentation": "\nInput to the TerminateJobFlows operation.
\n " }, "output": null, "errors": [ { "shape_name": "InternalServerError", "type": "structure", "members": {}, "documentation": "\nIndicates that an error occurred while processing the request and that the request was not\n completed.
\n " } ], "documentation": "\n\n TerminateJobFlows shuts a list of job flows down. When a job flow is shut down, any step\n not yet completed is canceled and the EC2 instances on which the job flow is running are\n stopped. Any log files not already saved are uploaded to Amazon S3 if a LogUri was\n specified when the job flow was created. \n
\n\n The call to TerminateJobFlows is asynchronous. Depending on the configuration of the job flow, \n it may take up to 5-20 minutes for the job flow to \n completely terminate and release allocated resources, such as Amazon EC2 instances.\n
\n \n