Eclipse提交任务至Hadoop集群遇到的问题

环境：Windows8.1，Eclipse

用Hadoop自带的wordcount示例

hadoop2.7.0

hadoop-eclipse-plugin-2.7.0.jar //Eclipse的插件，需要对应Hadoop当前版本

基本步骤有很多博客已经提及，就不再赘述

1. 将hadoop-eclipse-plugin-2.7.0.jar放入Eclipse的plugins目录，启动Eclipse

2. 配置Eclipse的Hadoop location信息

3. 新建MapReduce Project

4. 将wordcount的代码拷贝进去

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }

  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
	conf.set("mapred.job.tracker", "192.168.1.150:9001");
	conf.set("yarn.resourcemanager.address", "192.168.1.150:8032");

    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

Main方法的头三行代码，需要自己来配置

5. 将部署好的Hadoop集群中的配置文件拷贝至项目中

log4j.properties必须要配置，不然提交任务至集群时，Console无法显示信息，以下是我的配置

log4j.rootLogger=DEBUG, CA

log4j.appender.CA=org.apache.log4j.ConsoleAppender

log4j.appender.CA.layout=org.apache.log4j.PatternLayout
log4j.appender.CA.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n

6. 右键点击WordCount.java -> Run as -> Run on Hadoop

错误1：

org.apache.hadoop.util.Shell$ExitCodeException: /bin/bash: line 0: fg: no job control

Hadoop读取Windows和Linux系统变量时的引发的问题，有几种解决方案，嫌麻烦不想重新编译整个Hadoop就在本项目中直接重写来解决

在Hadoop的源代码中找到YARNRunner.java，拷贝至项目中，项目中的Package要和Hadoop源代码中的一样，运行时才会覆盖

修改YARNRunner.java

（1）修改读取Windows系统变量的方式

注释掉的代码是原来的代码

（2）新增一个处理Windows系统变量的方法

  private void replaceEnvironment(Map<String, String> environment) {
      String tmpClassPath = environment.get("CLASSPATH");
      tmpClassPath=tmpClassPath.replaceAll(";", ":");
      tmpClassPath=tmpClassPath.replaceAll("%PWD%", "\\$PWD");
      tmpClassPath=tmpClassPath.replaceAll("%HADOOP_MAPRED_HOME%", "\\$HADOOP_MAPRED_HOME");
      tmpClassPath= tmpClassPath.replaceAll("\\\\", "/" );
      environment.put("CLASSPATH",tmpClassPath);
}

　在此处使用

错误2：

exited with exitCode: 1 due to: Exception from container-launch

Diagnostics: Exception from container-launch.

修改项目中的mapred-site.xml，增加以下内容

<property>
<name>mapreduce.application.classpath</name>
<value>
$HADOOP_CONF_DIR,
$HADOOP_COMMON_HOME/share/hadoop/common/*,
$HADOOP_COMMON_HOME/share/hadoop/common/lib/*,
$HADOOP_HDFS_HOME/share/hadoop/hdfs/*,
$HADOOP_HDFS_HOME/share/hadoop/hdfs/lib/*,
$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*,
$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*,
$HADOOP_YARN_HOME/share/hadoop/yarn/*,
$HADOOP_YARN_HOME/share/hadoop/yarn/lib/*
</value>
</property>

ViewCode