package cn.jecn.hadoop.hdfs.com;

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();
	}
     
	
	//查找某个文件在HDFS集群的位置
	public static void getFileLocal() throws Exception {

		Configuration conf = new Configuration();
		FileSystem hdfs = FileSystem.get(conf);
		Path fpath = new Path("/user/root/20120722/word.txt");
        
		//获取文件系统里面的文件信息
		FileStatus fileStatus = hdfs.getFileStatus(fpath);
		//获取文件的块信息
		BlockLocation[] blkLocations = hdfs.getFileBlockLocations(fileStatus, 0, fileStatus.getLen());

		int blockLen = blkLocations.length;
        
		//循环打印
		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{
		//HDFS集群点数
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		
		//获取分布式文件系统
		DistributedFileSystem hdfs = (DistributedFileSystem)fs;
		
		//获取所有的节点数
		DatanodeInfo[] dataNodeStats = hdfs.getDataNodeStats();
        
		//循环打印
		for( int i = 0 ; i < dataNodeStats.length ; ++i ){
			System.out.println("DataNode_" + i + "_Node:" + dataNodeStats[i].getHostName());
		}
	}
}