MapReduce中Combiner方法使用
阿新 • • 發佈:2019-02-01
Combiner 會繼承Reducer,它是一種mr的優化,用於減少伺服器之間網路頻寬的壓力,它是在map結束後在每臺伺服器中都算出一個值,再傳到shuffle中。適合於求和等每臺伺服器算出的值對最後結果沒有影響的業務中,但是像求平均值等功能會帶來誤差所以不能使用。Combiner會在map結束後,shuffle開始前進行執行,
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("刪除成功");
}
}
Job job = Job.getInstance(conf);
//設定主的環境
job.setJarByClass(FlowCountDriver.class);
//設定map和reduce
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
//設定map的輸出型別
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
//設定reduce的輸出型別
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
//指定job的輸入原始檔案所在目錄
FileInputFormat.setInputPaths(job, new Path(inPath));
//指定job的輸出結果所在目錄
FileOutputFormat.setOutputPath(job, new Path(outPath));
//將job中配置的相關引數,以及job所用的java類所在的jar包,提交給yarn去執行
/*job.submit();*/
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}