MapReduce使用记录之Combiner

MapReduce中Combiner的作用和用法

作用：

①每一个map可能会产生大量的输出，Combiner的作用就是在map端对输出先做一次合并，以减少传输到reducer的数据量。
②Combiner最基本是实现本地key的归并，Combiner具有类似本地的reduce功能。

优点：

如果不用Combiner，那么，所有的结果都是reduce完成，效率会相对低下。 使用Combiner，先完成的map会在本地聚合，提升速度。 

注意：Combiner的输出是Reducer的输入，如果Combiner是可插拔的，添加Combiner绝不能改变最终的计算结果。所以Combiner只应该用于那种Reduce的输入key/value与输出key/value类型完全一致，且不影响最终结果的场景。比如累加，最大值等。

*（单词统计）代码节段：

public class WordCount {

public static void main(String[] args) throws Exception {

if (args.length < 2) {
System.exit(2);
}

String inputPath = args[0];
Path outputPath = new Path(args[1]);

//1配置
Configuration conf = new Configuration();
URI uri = new URI("hdfs://192.168.0.200:9000");
FileSystem fileSystem = FileSystem.get(uri, conf);

if (fileSystem.exists(outputPath)) {
boolean b = fileSystem.delete(outputPath, true);
System.out.println("已存在目录删除："+b);
}

//2.建立job
Job job = Job.getInstance(conf, WordCount.class.getName());
job.setJarByClass(WordCount.class);

//3.输入文件
FileInputFormat.setInputPaths(job, new Path(inputPath));

//4.格式化输入文件
job.setInputFormatClass(TextInputFormat.class);

//5.map
job.setMapperClass(MapWordCountTask.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

//6.reduce
job.setReducerClass(ReduceWordCountTask.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

/**指定本job使用combiner组件，组件所用的类为ReduceWordCountTask**/
job.setCombinerClass(ReduceWordCountTask.class);

//7.输出文件
FileOutputFormat.setOutputPath(job, outputPath);

//8.输出文件格式化
job.setOutputFormatClass(TextOutputFormat.class);

//9.提交给集群执行
job.waitForCompletion(true);

}

public static class MapWordCountTask extends Mapper<LongWritable, Text, Text, LongWritable> {

private Text k2 = new Text();
private LongWritable v2 = new LongWritable();

@Override
protected void map(LongWritable key, Text value, Context context) throws Exception {
String content = value.toString();
StringTokenizer st = new StringTokenizer(content);
while (st.hasMoreElements()) {
k2.set(st.nextToken());
v2.set(1L);
context.write(k2, v2);
}
}
}

public static class ReduceWordCountTask extends Reducer<Text, LongWritable, Text, LongWritable> {

private LongWritable v3 = new LongWritable();

@Override
protected void reduce(Text k2, Iterable<LongWritable> v2s,Context context) throws Exception {
long sum = 0;
for (LongWritable longWritable : v2s) {
sum += longWritable.get();
v3.set(sum);
}
context.write(k2, v3);
}
}
}