本地运行yarn实现wordcount报错Exit code: 1 Exception message: /bin/bash: 第 0 行:fg: 无任务控制 Stack trace: ExitCo

eclipse控制台输出错误信息

Container id: container_1531823680410_0003_02_000001
Exit code: 1
Exception message: /bin/bash: 第 0 行:fg: 无任务控制

Stack trace: ExitCodeException exitCode=1: /bin/bash: 第 0 行:fg: 无任务控制

    at org.apache.hadoop.util.Shell.runCommand(Shell.java:972)
    at org.apache.hadoop.util.Shell.run(Shell.java:869)
    at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:1170)
    at org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer(DefaultContainerExecutor.java:236)
    at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:305)
    at org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call(ContainerLaunch.java:84)
    at java.util.concurrent.FutureTask.run(FutureTask.java:266)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
    at java.lang.Thread.run(Thread.java:748)

Container exited with a non-zero exit code 1
For more detailed output, check the application tracking page: http://master:8088/cluster/app/application_1531823680410_0003 Then click on links to logs of each attempt.
. Failing the application.
[INFO ] 2018-07-17 20:11:34,978 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1436)
Counters: 0
 

 

原因：因为在wondows系统中无法使用#!/bin/bash 平台兼容性的问题的

1:解决：打成jar包放在linux下运行。ok

2:跨平台提交的参数

//：如果要从windows系统中运行这个job提交客户端的程序，则需要加这个跨平台提交的参数
        conf.set("mapreduce.app-submission.cross-platform","true");

如果打成jar包提交到linux中去，跨平台提交的参数可以去掉

解决：

这里把代码粘一下：

WordcountMapper.java

package cn.edu360.mr.wc;

import java.io.IOException;


import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * KEYIN ：是map task读取到的数据的key的类型，是一行的起始偏移量Long
 * VALUEIN:是map task读取到的数据的value的类型，是一行的内容String
 * 
 * KEYOUT：是用户的自定义map方法要返回的结果kv数据的key的类型，在wordcount逻辑中，我们需要返回的是单词String
 * VALUEOUT:是用户的自定义map方法要返回的结果kv数据的value的类型，在wordcount逻辑中，我们需要返回的是整数Integer
 * 
 * 
 * 但是，在mapreduce中，map产生的数据需要传输给reduce，需要进行序列化和反序列化，而jdk中的原生序列化机制产生的数据量比较冗余，就会导致数据在mapreduce运行过程中传输效率低下
 * 所以，hadoop专门设计了自己的序列化机制，那么，mapreduce中传输的数据类型就必须实现hadoop自己的序列化接口
 * 
 * hadoop为jdk中的常用基本类型Long String Integer Float等数据类型封住了自己的实现了hadoop序列化接口的类型：LongWritable,Text,IntWritable,FloatWritable
 * 
 * 
 * 
 * 
 * @author ThinkPad
 *
 */
public class WordcountMapper extends Mapper{
	
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
			//切单词
			String line = value.toString();
			String[] words = line.split(" ");
			
			for(String word : words){
				context.write(new Text(word),new IntWritable(1));
			}
			
		
	}
	
	
}

WordcountReduce.java

package cn.edu360.mr.wc;

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordcountReduce extends Reducer{
	
	@Override
	protected void reduce(Text key, Iterable values,Context context) throws IOException, InterruptedException {
		int count = 0;
		
		Iterator iterator = values.iterator();
		while(iterator.hasNext()){
			IntWritable value = iterator.next();
			count += value.get();
		}
		context.write(key,new IntWritable(count));
	}

}

JobSubmitter.java

package cn.edu360.mr.wc;

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
/**
 * 用来提交maprejduce job的客户端程序
 * 主要的功能有两个：
 * 	1：封装本次job运行时所需要的必要的参数
 * 	2：跟yarn进行交互，将mapreduce的程序成功的启动，运行
 * @author LENOVO
 *
 */
public class JobSubmitter {
	public static void main(String[] args) throws Exception {
		
		//在代码中设置JVM系统的参数，用于给job对象来获取访问hdfs的用户身份
		System.setProperty("HADOOP_USER_NAME", "root");
		
		Configuration conf = new Configuration();
		//1：设置job运行是要访问的默认文件系统
		conf.set("fs.defaultFS","hdfs://master:9000");
		//2:设置job提交到哪去运行
		conf.set("mapreduce.framework.name", "yarn");//如果是"local"说明则是在本地的模拟器上运行
		//告诉他resourcemanager在那个地方
		conf.set("yarn.resourcemanager.hostname","master");
		//在运行的时候的参数配置带jvm中 去：                 -DHADOOP_USER_NAME=root
		
		//3：如果要从windows系统中运行这个job提交客户端的程序，则需要加这个跨平台提交的参数
		conf.set("mapreduce.app-submission.cross-platform","true");
		
		Job job = Job.getInstance(conf);
		
		//1：封装参数：jar包所在的位置上
		job.setJar("d:/wc.jar");
//		job.setJarByClass(JobSubmitter.class);
		
		//2：封装参数：本次job的所要调用的Mapper实现类
		job.setMapperClass(WordcountMapper.class);
		job.setReducerClass(WordcountReduce.class);
		
		//3:封装参数本次job的mapper实现类,和reduce的实现类  产生的结果数据的key  value类型 
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		Path output = new Path("/wordcount/output");
		FileSystem fs = FileSystem.get(new URI("hdfs://master:9000"),conf,"root");
		if(fs.exists(output)){
			fs.delete(output, true);
		}
		
		// 4、封装参数：本次job要处理的输入数据集所在路径、最终结果的输出路径
		FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
		FileOutputFormat.setOutputPath(job, output);  // 注意：输出路径必须不存在
		
		
		// 5、封装参数：想要启动的reduce task的数量
		job.setNumReduceTasks(2);
		
		// 6、提交job给yarn
		boolean res = job.waitForCompletion(true);
		
		System.exit(res?0:-1);
	}
}

控制台结果：

[WARN ] 2018-07-17 20:41:55,118 method:org.apache.hadoop.util.Shell.(Shell.java:673)
Did not find winutils.exe: java.io.FileNotFoundException: java.io.FileNotFoundException: HADOOP_HOME and hadoop.home.dir are unset. -see https://wiki.apache.org/hadoop/WindowsProblems
[INFO ] 2018-07-17 20:41:56,623 method:org.apache.hadoop.yarn.client.RMProxy.createRMProxy(RMProxy.java:123)
Connecting to ResourceManager at master/192.168.51.247:8032
[WARN ] 2018-07-17 20:41:57,185 method:org.apache.hadoop.mapreduce.JobResourceUploader.uploadFiles(JobResourceUploader.java:64)
Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
[INFO ] 2018-07-17 20:41:57,500 method:org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:289)
Total input files to process : 3
[INFO ] 2018-07-17 20:41:57,654 method:org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:200)
number of splits:3
[INFO ] 2018-07-17 20:41:57,845 method:org.apache.hadoop.mapreduce.JobSubmitter.printTokens(JobSubmitter.java:289)
Submitting tokens for job: job_1531823680410_0008
[INFO ] 2018-07-17 20:41:58,050 method:org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.submitApplication(YarnClientImpl.java:296)
Submitted application application_1531823680410_0008
[INFO ] 2018-07-17 20:41:58,080 method:org.apache.hadoop.mapreduce.Job.submit(Job.java:1345)
The url to track the job: http://master:8088/proxy/application_1531823680410_0008/
[INFO ] 2018-07-17 20:41:58,080 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1390)
Running job: job_1531823680410_0008
[INFO ] 2018-07-17 20:42:05,247 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1411)
Job job_1531823680410_0008 running in uber mode : false
[INFO ] 2018-07-17 20:42:05,248 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1418)
 map 0% reduce 0%
[INFO ] 2018-07-17 20:42:10,325 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1418)
 map 100% reduce 0%
[INFO ] 2018-07-17 20:42:16,398 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1418)
 map 100% reduce 100%
[INFO ] 2018-07-17 20:42:16,426 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1429)
Job job_1531823680410_0008 completed successfully
[INFO ] 2018-07-17 20:42:16,552 method:org.apache.hadoop.mapreduce.Job.monitorAndPrintJob(Job.java:1436)
Counters: 49
	File System Counters
		FILE: Number of bytes read=918
		FILE: Number of bytes written=682817
		FILE: Number of read operations=0
		FILE: Number of large read operations=0
		FILE: Number of write operations=0
		HDFS: Number of bytes read=753
		HDFS: Number of bytes written=103
		HDFS: Number of read operations=15
		HDFS: Number of large read operations=0
		HDFS: Number of write operations=4
	Job Counters 
		Launched map tasks=3
		Launched reduce tasks=2
		Data-local map tasks=3
		Total time spent by all maps in occupied slots (ms)=9265
		Total time spent by all reduces in occupied slots (ms)=6533
		Total time spent by all map tasks (ms)=9265
		Total time spent by all reduce tasks (ms)=6533
		Total vcore-milliseconds taken by all map tasks=9265
		Total vcore-milliseconds taken by all reduce tasks=6533
		Total megabyte-milliseconds taken by all map tasks=9487360
		Total megabyte-milliseconds taken by all reduce tasks=6689792
	Map-Reduce Framework
		Map input records=39
		Map output records=78
		Map output bytes=750
		Map output materialized bytes=942
		Input split bytes=315
		Combine input records=0
		Combine output records=0
		Reduce input groups=14
		Reduce shuffle bytes=942
		Reduce input records=78
		Reduce output records=14
		Spilled Records=156
		Shuffled Maps =6
		Failed Shuffles=0
		Merged Map outputs=6
		GC time elapsed (ms)=434
		CPU time spent (ms)=3950
		Physical memory (bytes) snapshot=1207812096
		Virtual memory (bytes) snapshot=10917920768
		Total committed heap usage (bytes)=896008192
	Shuffle Errors
		BAD_ID=0
		CONNECTION=0
		IO_ERROR=0
		WRONG_LENGTH=0
		WRONG_MAP=0
		WRONG_REDUCE=0
	File Input Format Counters 
		Bytes Read=438
	File Output Format Counters 
		Bytes Written=103