hadoop linux 集群提交任务

将这三个文件打成jar包,然后放在集群里用hadoop jar命令来运行hadoop jar wc.jar wc.LinuxS
hadoop jar命令会自动调取本地依赖和配置文件

jobcommit

package wc;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.BasicConfigurator;

public class LinuxS {

    public static void main(String[] args) throws Exception {
        BasicConfigurator.configure(); //自动快速地使用缺省Log4j环境。
        System.setProperty("HADOOP_USER_NAME","root");//配置jvm变量
        Configuration conf = new Configuration();

        // 在hdfs上运行
        conf.set("fs.defaultFS", "hdfs://master:9000");
        conf.set("mapreduce.framework.name", "yarn");//默认linux单机运行local
        conf.set("yarn.resourcemanager.hostname","master");
        conf.set("mapreduce.app-submission.cross-platform","true");//兼容win
        conf.set("yarn.app.mapreduce.am.resource.mb", "500");// 防止虚拟机内存报错

        Job job = Job.getInstance(conf);

        //mapper,reducer,submitter三个类
        job.setJarByClass(LinuxS.class);  //在hadoop集群里提交jar包,可以用这个方法,免去设置jar包
//        job.setJar("d:/wc.jar");  //在idea里提交,需要指明jar包所在位置
        job.setMapperClass(CountMapper.class);
        job.setReducerClass(CountReducer.class);
        //mapper,reducer输出key和value的类型
        job.setMapOutputKeyClass(Text.class);//mapper
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);//reducer
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path("/input"));
        FileOutputFormat.setOutputPath(job, new Path("/output"));

        job.setNumReduceTasks(2);
        boolean res = job.waitForCompletion(true);
        System.exit(res?0:1);
    }
}

mapper

package wc;

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

import java.io.IOException;

/**
 * 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，java原生的数据类型会很慢,
 * 所以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
 *
 */
public class CountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
    //KEYIN ：是map task读取到的一行的起始偏移量Long,hadoop中新建了LongWritable类型来替代
    //VALUEIN:是map task读取到的该行的内容,类型是String,hadoop中用Text来表示
    //KEYOUT：返回的key,用Text,既字母
    //VALUEOUT:返回的value,用Integer,既字母的个数
    @Override
    protected void map(LongWritable key, Text value, Context context)//Context既输出的key-value的容器,可以看成是一个大的字典
            throws IOException, InterruptedException {
        String line = value.toString(); //将一行Text数据转换为String
        String[] words = line.split(" ");//分割单词
        for(String word:words){//将分割的每一个单词写入到字典
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

reducer

package wc;


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

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

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

相关资料:
Linux提交hadoop任务