Combiner 会继承Reducer,它是一种mr的优化,用于减少服务器之间网络带宽的压力,它是在map结束后在每台服务器中都算出一个值,再传到shuffle中。适合于求和等每台服务器算出的值对最后结果没有影响的业务中,但是像求平均值等功能会带来误差所以不能使用。Combiner会在map结束后,shuffle开始前进行执行,
package com.it18zhang.day05.flow;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class FlowCountCombiner extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> values,Context context)
throws IOException, InterruptedException {
long sum = 0;
for(LongWritable value: values){
sum += value.get();
}
context.write(key, new LongWritable(sum));
}
}
package com.it18zhang.day05.flow;
import java.io.IOException;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FlowCountDriver {
public static void main(String[] args) throws Exception {
String inPath = "";
String outPath ="";
if(args.length == 2){
inPath = args[0];
outPath = args[1];
}
Configuration conf = new Configuration();
if(!outPath.equals("")){
FileSystem fs = FileSystem.get(new URI("hdfs://192.168.81.201:8020/") , conf, "centos");
Path f = new Path(outPath);
boolean isTrue = fs.delete(f,true);
if(isTrue){
System.out.println("删除成功");
}
}
Job job = Job.getInstance(conf);
//设置主的环境
job.setJarByClass(FlowCountDriver.class);
//设置map和reduce
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
//设置map的输出类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//设置reduce的输出类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
//指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(inPath));
//指定job的输出结果所在目录
FileOutputFormat.setOutputPath(job, new Path(outPath));
//将job中配置的相关参数,以及job所用的java类所在的jar包,提交给yarn去运行
/*job.submit();*/
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}