linux 系统 eclipse提交job到hadoop集群上的一些坑

自从学习hadoop开始，一直就想找到一个办法，能提交一个job到hadoop集群上，而不是export jar包，然后在hadoop集群上执行命令 hadoop jar

今天算是被我找到了，顺带还发现一个local模式

先上hadoop的经典的wordcount代码，这个代码是从官网上摘来的

package com.hit.hadoop;
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;


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();
    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);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

之后就是一个一个tool的代码，具体如下

package com.hit.hadoop;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


import com.hit.hadoop.WordCount.IntSumReducer;
import com.hit.hadoop.WordCount.TokenizerMapper;


public class World extends Configured implements Tool {


@Override
public int run(String[] args) throws Exception {
   Job job = Job.getInstance(getConf(), "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);
   FileInputFormat.addInputPath(job, new Path(args[0]));
   FileOutputFormat.setOutputPath(job, new Path(args[1]));
   System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}


public static void main(String[] args)throws Exception {
String a[] = new String[]{"/zhonghui/input","/zhonghui/output"};
Configuration conf = new Configuration();
conf.addResource("core-site.xml");
conf.addResource("hdfs-site.xml");
conf.addResource("yarn-site.xml");
conf.addResource("mapred-site.xml");
ToolRunner.run(conf, new World(), a);
}



}

上面代码中的core-site.xml,hdfs-site.xml,yarn-site.xml,mapred-site.xml是从集群上拷贝过来的。

但是就这么整，你的代码一般都会出现各种问题，比如能提交job到yarn上，但是报class not found错误

解决办法

在yarn-site.xml配置文件中添加

<property><name>yarn.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_YARN_HOME/share/hadoop/yarn/*, $HADOOP_YARN_HOME/share/hadoop/yarn/lib/*
</value></property>

这个的意思，请自己查看官方文档http://hadoop.apache.org/docs/r2.5.2/hadoop-yarn/hadoop-yarn-common/yarn-default.xml

在mapred-site.xml配置文件中添加

<property><name>mapreduce.application.classpath</name><value>
$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*, $HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*
</value></property>

写上这两个在你自己eclipse工程中的配置文件。就可以提交任务成功了。

另外说一个本地模式，本地模式，可以避免一些jar包问题，或者测试比较方便。

开启的方式是，在mapred-site.xml中添加

<property><name>mapreduce.framework.name</name><value>local</value></property>

即可