add_job_flow_steps ¶

def add_job_flow_steps(
    self,
    *,
    config_overrides: Optional[EMRClientConfig] = None,
    job_flow_id: Optional[
        "capo_emr.types.xml_string_max_len256.XmlStringMaxLen256"
    ] = None,
    steps: Optional["capo_emr.types.step_config_list.StepConfigList"] = None,
    execution_role_arn: Optional["capo_emr.types.arn_type.ArnType"] = None,
) -> "capo_emr.types.add_job_flow_steps_output.AddJobFlowStepsOutput":
    """<p>AddJobFlowSteps adds new steps to a running cluster. A maximum of 256 steps are allowed in each job flow.</p> <p>If your cluster 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 SSH to connect to the master node and submitting queries directly to the software running on the master node, such as Hive and Hadoop.</p> <p>A step specifies the location of a JAR file stored either on the master node of the cluster or in Amazon S3. Each step is performed by the main function of the main class of the JAR file. The main class can be specified either in the manifest of the JAR or by using the MainFunction parameter of the step.</p> <p>Amazon EMR executes each step in the order listed. For a step to be considered complete, the main function must exit with a zero exit code and all Hadoop jobs started while the step was running must have completed and run successfully.</p> <p>You can only add steps to a cluster that is in one of the following states: STARTING, BOOTSTRAPPING, RUNNING, or WAITING.</p> <note> <p>The string values passed into <code>HadoopJarStep</code> object cannot exceed a total of 10240 characters.</p> </note>

    Args:
        job_flow_id: <p>A string that uniquely identifies the job flow. This identifier is returned by <a>RunJobFlow</a> and can also be obtained from <a>ListClusters</a>. </p>
        steps: <p> A list of <a>StepConfig</a> to be executed by the job flow. </p>
        execution_role_arn: <p>The Amazon Resource Name (ARN) of the runtime role for a step on the cluster. The runtime role can be a cross-account IAM role. The runtime role ARN is a combination of account ID, role name, and role type using the following format: <code>arn:partition:service:region:account:resource</code>. </p> <p>For example, <code>arn:aws:IAM::1234567890:role/ReadOnly</code> is a correctly formatted runtime role ARN.</p>

    Raises:
        capo_emr.errors.internal_server_error.InternalServerError: <p>Indicates that an error occurred while processing the request and that the request was not completed.</p>
        capo_emr.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_emr.types.add_job_flow_steps_input.AddJobFlowStepsInput]",
    ) -> OperationResponse[
        "capo_emr.types.add_job_flow_steps_output.AddJobFlowStepsOutput"
    ]:
        import capo_emr._operations.elastic_map_reduce.add_job_flow_steps

        output, http_response = (
            capo_emr._operations.elastic_map_reduce.add_job_flow_steps.add_job_flow_steps(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("AddJobFlowSteps")
    )
    input_: capo_emr.types.add_job_flow_steps_input.AddJobFlowStepsInput = {}
    if job_flow_id is not None:
        input_["job_flow_id"] = job_flow_id
    if steps is not None:
        input_["steps"] = steps
    if execution_role_arn is not None:
        input_["execution_role_arn"] = execution_role_arn

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output