[Hadoop] 50030/jobtracker.jsp监控不到eclipse提交的作业

搭建好eclipse hadoop开发环境后，一般会用hadoop自带的WordCount做个测试，其自带的WordCount.java如下：

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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.log4j.PropertyConfigurator;

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();

//set inpath,outpath
Path inpath=new Path("/test/input/file1");
Path outpath=new Path("/test/output/output4");

Job job = new Job(conf, "mango");
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
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, inpath);
FileOutputFormat.setOutputPath(job,outpath);
System.out.println("开始执行");
System.exit(job.waitForCompletion(true) ? 0 : 1);

}
}

如果此时你run java aplication,你的程序只会在eclipse中虚拟的一个云环境中运行，而不会跑上云端去运行，所以无法再master:50070/jobtracker.jsp页面中监控到该作业；需要在main方法中添加几行代码，代码附录如下：

//在你的文件地址前自动添加：hdfs://master:9000/
conf.set("fs.default.name", "hdfs://master:9000/");
conf.set("hadoop.job.user","mango");
//指定jobtracker的ip和端口号，master在/etc/hosts中可以配置
conf.set("mapred.job.tracker","master:9001");