? ? ?通過" FileSystem.getFileBlockLocation（FileStatus file，long start，long len） "可查找指定文件在HDFS集群上的位置，其中file為文件的完整路徑，start和len來標(biāo)識(shí)查找文件的路徑。

以下是java代碼的實(shí)現(xiàn)：

package com.njupt.hadoop;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.BlockLocation;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.DistributedFileSystem;
import org.apache.hadoop.hdfs.protocol.DatanodeInfo;


public class FindFileOnHDFS {


public static void main(String[] args) throws Exception{
getHDFSNodes();
getFileLocal();
}


public static void getFileLocal() throws Exception {


Configuration conf = new Configuration();
FileSystem hdfs = FileSystem.get(conf);
Path fpath = new Path("/user/root/20120722/word.txt");

FileStatus fileStatus = hdfs.getFileStatus(fpath);
? ?BlockLocation[] blkLocations = hdfs.getFileBlockLocations(fileStatus, 0, fileStatus.getLen());

? ?int blockLen = blkLocations.length;
? ?
? ?for(int i = 0 ; i < blockLen ; ++i ){
? ?String[] hosts = blkLocations[i].getHosts();
? ?System.out.println("block_"+i + "_location:" + hosts[i]);
? ?}
}


public static void getHDFSNodes() throws Exception{
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
DistributedFileSystem hdfs = (DistributedFileSystem)fs;
DatanodeInfo[] dataNodeStats = hdfs.getDataNodeStats();

for( int i = 0 ; i < dataNodeStats.length ; ++i ){
System.out.println("DataNode_" + i + "_Node:" + dataNodeStats[i].getHostName());
}
}
}

?

查找某個(gè)文件在HDFS集群中的位置