// Setting up the cache for the application

     1. Copy the requisite files to the FileSystem:

     $ bin/hadoop fs -copyFromLocal lookup.dat /myapp/lookup.dat
     $ bin/hadoop fs -copyFromLocal map.zip /myapp/map.zip
     $ bin/hadoop fs -copyFromLocal mylib.jar /myapp/mylib.jar
     $ bin/hadoop fs -copyFromLocal mytar.tar /myapp/mytar.tar
     $ bin/hadoop fs -copyFromLocal mytgz.tgz /myapp/mytgz.tgz
     $ bin/hadoop fs -copyFromLocal mytargz.tar.gz /myapp/mytargz.tar.gz

     2. Setup the application's JobConf:

     JobConf job = new JobConf();　　  //　#lookup.dat 表示给前面的这个文件取一个别名，类似sql里面的as别名一样     DistributedCache.addCacheFile(new URI("/myapp/lookup.dat#lookup.dat"),
                                   job);
     DistributedCache.addCacheArchive(new URI("/myapp/map.zip", job);
     DistributedCache.addFileToClassPath(new Path("/myapp/mylib.jar"), job);
     DistributedCache.addCacheArchive(new URI("/myapp/mytar.tar", job);
     DistributedCache.addCacheArchive(new URI("/myapp/mytgz.tgz", job);
     DistributedCache.addCacheArchive(new URI("/myapp/mytargz.tar.gz", job);
 
     3. Use the cached files in the Mapper
     or Reducer:

     public static class MapClass extends MapReduceBase
     implements Mapper<K, V, K, V> {

       private Path[] localArchives;
       private Path[] localFiles;

       public void configure(JobConf job) {
         // Get the cached archives/files
         localArchives = DistributedCache.getLocalCacheArchives(job);
         localFiles = DistributedCache.getLocalCacheFiles(job);
       }

       public void map(K key, V value,
                       OutputCollector<K, V> output, Reporter reporter)
       throws IOException {
         // Use data from the cached archives/files here
         // ...
         // ...
         output.collect(k, v);
       }
     }

　　查看代码了才知道其实它根本不是什么缓存，它只不过是在配置文件中的指定属性记录下相应的值，然后在mapreduce的时候，调用配置文件里面的属性值，然后取得需要的文件盒jar包。