HDFS 的Trash回收站

1）在core-site.xml文件中添加这个配置

在每个节点(不仅仅是主节点)上添加配置 core-site.xml,增加如下内容
<property>
    <name>fs.trash.interval</name>
    <value>1440</value>
</property>

1440表示在文件放入回收站1440分钟之后才会真得彻底的被删除

2）使用命令行删除文件：

//查看HDFS下的根目录
root@Ubuntu-1:/usr/local/hadoop-2.6.0/bin# hadoop fs -ls /
Found 1 items
drwxr-xr-x   - root supergroup          0 2017-05-19 11:02 /test

//删除文件
root@Ubuntu-1:/usr/local/hadoop-2.6.0/bin# hadoop fs -rm -r /test
17/05/22 15:39:00 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
Moved: 'hdfs://Ubuntu-1:9000/test' to trash at: hdfs://Ubuntu-1:9000/user/root/.Trash/Current

//查看回收站的文件：

root@Ubuntu-1:/usr/local/hadoop-2.6.0# bin/hdfs dfs -ls hdfs://Ubuntu-1:9000/user/root/.Trash/Current
Found 1 items
drwxr-xr-x - root supergroup 0 2017-05-19 11:02 hdfs://Ubuntu-1:9000/user/root/.Trash/Current/test

//撤回回收站的文件
root@Ubuntu-1:/usr/local/hadoop-2.6.0# bin/hadoop fs -mv /user/root/.Trash/Current /user/root/test

//文件已撤回
root@Ubuntu-1:/usr/local/hadoop-2.6.0# bin/hadoop fs -ls
Found 2 items
drwx------   - root supergroup          0 2017-05-22 16:12 .Trash
drwx------   - root supergroup          0 2017-05-22 15:39 test

 

3）使用java代码操作HDFS的回收站

import java.io.IOException;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.Trash;

public class RMFile {
    private final static Log log = LogFactory.getLog(RMFile.class);
    private final static Configuration conf = new Configuration();

    /**
     * Delete a file/directory on hdfs
     * 
     * @param path
     * @param recursive
     * @return
     * @throws IOException
     */
    public static boolean rm(FileSystem fs, Path path, boolean recursive)
            throws IOException {
        log.info("rm: " + path + " recursive: " + recursive);
        boolean ret = fs.delete(path, recursive);
        if (ret)
            log.info("rm: " + path);
        return ret;

    }

    /**
     * Delete a file/directory on hdfs,and move a file/directory to Trash
     * @param fs
     * @param path
     * @param recursive
     * @param skipTrash
     * @return
     * @throws IOException
     */
    public static boolean rm(FileSystem fs, Path path, boolean recursive,
            boolean skipTrash) throws IOException {
        log.info("rm: " + path + " recursive: " + recursive+" skipTrash:"+skipTrash);
        if (!skipTrash) {
            Trash trashTmp = new Trash(fs, conf);
            if (trashTmp.moveToTrash(path)) {
                log.info("Moved to trash: " + path);
                return true;
            }
        }
        boolean ret = fs.delete(path, recursive);
        if (ret)
            log.info("rm: " + path);
        return ret;

    }

    public static void main(String[] args) throws IOException {
        conf.set("fs.default.name", "hdfs://data2.kt:8020/");
        FileSystem fs = FileSystem.get(conf);
        RMFile.rm(fs,new Path("hdfs://data2.kt:8020/test/testrm"),true,false);
    }

}