在 Amazon EMR 中使用 Flink 作业

List<StepConfig> stepConfigs = new ArrayList<StepConfig>();
  
HadoopJarStepConfig flinkWordCountConf = new HadoopJarStepConfig()
    .withJar("command-runner.jar")
    .withArgs("flink", "run", "-m", "yarn-cluster", "-yid", "application_1473169569237_0002", "-yn", "2", "/usr/lib/flink/examples/streaming/WordCount.jar", 
      "--input", "s3://myBucket/pg11.txt", "--output", "s3://myBucket/alice2/");
  
StepConfig flinkRunWordCount = new StepConfig()
  .withName("Flink add a wordcount step")
  .withActionOnFailure("CONTINUE")
  .withHadoopJarStep(flinkWordCountConf);
  
stepConfigs.add(flinkRunWordCount); 
  
AddJobFlowStepsResult res = emr.addJobFlowSteps(new AddJobFlowStepsRequest()
   .withJobFlowId("myClusterId")
   .withSteps(stepConfigs));

aws emr add-steps --cluster-id <j-XXXXXXXX> \
--steps Type=CUSTOM_JAR,Name=Flink_Submit_To_Long_Running,Jar=command-runner.jar,\
Args="flink","run","-m","yarn-cluster","-yid","application_1473169569237_0002",\
"/usr/lib/flink/examples/streaming/WordCount.jar",\
"--input","s3://myBucket/pg11.txt","--output","s3://myBucket/alice2/" \
--region <region-code> 

import java.util.ArrayList;
import java.util.List;
import com.amazonaws.AmazonClientException;
import com.amazonaws.auth.AWSCredentials;
import com.amazonaws.auth.AWSStaticCredentialsProvider;
import com.amazonaws.auth.profile.ProfileCredentialsProvider;
import com.amazonaws.services.elasticmapreduce.AmazonElasticMapReduce;
import com.amazonaws.services.elasticmapreduce.AmazonElasticMapReduceClientBuilder;
import com.amazonaws.services.elasticmapreduce.model.*;

public class Main_test {

	public static void main(String[] args) {
		AWSCredentials credentials_profile = null;
		try {
			credentials_profile = new ProfileCredentialsProvider("default").getCredentials();
		} catch (Exception e) {
			throw new AmazonClientException(
					"Cannot load credentials from .aws/credentials file. " +
							"Make sure that the credentials file exists and the profile name is specified within it.",
					e);
		}

		AmazonElasticMapReduce emr = AmazonElasticMapReduceClientBuilder.standard()
				.withCredentials(new AWSStaticCredentialsProvider(credentials_profile))
				.withRegion(Regions.US_WEST_1)
				.build();

		List<StepConfig> stepConfigs = new ArrayList<StepConfig>();
		HadoopJarStepConfig flinkWordCountConf = new HadoopJarStepConfig()
				.withJar("command-runner.jar")
				.withArgs("bash", "-c", "flink", "run", "-m", "yarn-cluster", "-yn", "2",
						"/usr/lib/flink/examples/streaming/WordCount.jar", "--input", "s3://path/to/input-file.txt", "--output",
						"s3://path/to/output/");

		StepConfig flinkRunWordCountStep = new StepConfig()
				.withName("Flink add a wordcount step and terminate")
				.withActionOnFailure("CONTINUE")
				.withHadoopJarStep(flinkWordCountConf);

		stepConfigs.add(flinkRunWordCountStep);

		Application flink = new Application().withName("Flink");

		RunJobFlowRequest request = new RunJobFlowRequest()
				.withName("flink-transient")
				.withReleaseLabel("emr-5.20.0")
				.withApplications(flink)
				.withServiceRole("EMR_DefaultRole")
				.withJobFlowRole("EMR_EC2_DefaultRole")
				.withLogUri("s3://path/to/my/logfiles")
				.withInstances(new JobFlowInstancesConfig()
						.withEc2KeyName("myEc2Key")
						.withEc2SubnetId("subnet-12ab3c45")
						.withInstanceCount(3)
						.withKeepJobFlowAliveWhenNoSteps(false)
						.withMasterInstanceType("m4.large")
						.withSlaveInstanceType("m4.large"))
				.withSteps(stepConfigs);

		RunJobFlowResult result = emr.runJobFlow(request);
		System.out.println("The cluster ID is " + result.toString());

	}

}

使用 create-cluster 子命令创建一个临时集群，该集群在 Flink 作业完成时终止：

aws emr create-cluster --release-label emr-5.2.1 \
--name "Flink_Transient" \
--applications Name=Flink \
--configurations file://./configurations.json \
--region us-east-1 \
--log-uri s3://myLogUri \
--auto-terminate
--instance-type m5.xlarge \
--instance-count 2 \
--service-role EMR_DefaultRole_V2 \ 
--ec2-attributes KeyName=<YourKeyName>,InstanceProfile=EMR_EC2_DefaultRole \
--steps Type=CUSTOM_JAR,Jar=command-runner.jar,Name=Flink_Long_Running_Session,\
Args="bash","-c","\"flink run -m yarn-cluster /usr/lib/flink/examples/streaming/WordCount.jar
--input s3://myBucket/pg11.txt --output s3://myBucket/alice/""