MapReduceJob设置集群运行模式

package cn.coder.mapreduce;

import com.google.common.base.Strings;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class JobMain extends Configured implements Tool {
    //该方法指定一个job任务
    @Override
    public int run(String[] strings) throws Exception {
        //1.创建job任务对象     获取configure对象      任务名
        Job job = Job.getInstance(super.getConf(), "wordcount");

        //2.配置job任务对象

        //第一步:指定文件的读取方式和读取路径
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://hadoop01:8020/wordcount"));

        //第二步:指定Map阶段的处理方式
        job.setMapperClass(WordCountMapper.class);
        //设置map阶段k2的类型
        job.setMapOutputKeyClass(Text.class);

        //设置map阶段v2的类型
        job.setMapOutputValueClass(LongWritable.class);

        //第3,4,5,6  shuffle阶段采用默认的方式

        //第7步:指定Reduce阶段的处理方式和数据类型
        job.setReducerClass(WordCountReduce.class);
        //设置K3的类型
        job.setOutputKeyClass(Text.class);

        //设置V3的类型
        job.setOutputValueClass(LongWritable.class);

        //第8部:设置输出类型
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输出的路径
        TextOutputFormat.setOutputPath(job,new Path("hdfs://hadoop01:8020/wordcount_out"));

        //等待任务结束
        boolean b = job.waitForCompletion(true);
        //0正常1不正常
        return b?0:1;
    }

    public static void main(String[] args) throws Exception {
        //启动job任务    把这个configuration对象给了父类configure
        Configuration conf = new Configuration();
        //集群运行模式  也可以在mapred-site.xml里设置
        conf.set("mapreduce.framework.name","yarn");
        int run = ToolRunner.run(conf, new JobMain(), args);
        System.exit(run);
    }
}