{{{
#!html
<div style="text-align: center;"><big
 style="font-weight: bold;"><big><big>實作二： HDFS Shell操作練習</big></big></big></div>
}}}
[[PageOutline]]

 == 前言 ==

 * 此部份接續實做一
    
 = Content 1. HDFS Shell基本操作 =
 == 1.1 瀏覽你HDFS目錄 == 

{{{
/opt/hadoop$ bin/hadoop fs -ls
}}}

 == 1.2 上傳資料到HDFS目錄 == 
 * 上傳

{{{
/opt/hadoop$ bin/hadoop fs -put conf input
}}} 

 * 檢查

{{{
/opt/hadoop$ bin/hadoop fs -ls
/opt/hadoop$ bin/hadoop fs -ls input
}}}
 
 == 1.3 下載HDFS的資料到本地目錄 == 

 * 下載

{{{
/opt/hadoop$ bin/hadoop fs -get input fromHDFS
}}} 

 * 檢查

{{{
/opt/hadoop$ ls -al | grep fromHDFS
/opt/hadoop$ ls -al fromHDFS
}}}  

 == 1.4 刪除檔案 ==

{{{
/opt/hadoop$ bin/hadoop fs -ls input
/opt/hadoop$ bin/hadoop fs -rm input/masters
}}} 

 == 1.5 直接看檔案 ==

{{{
/opt/hadoop$ bin/hadoop fs -ls input
/opt/hadoop$ bin/hadoop fs -cat input/slaves
}}} 

 == 1.6 更多指令操作 ==

{{{
hadooper@vPro:/opt/hadoop$ bin/hadoop fs 

Usage: java FsShell
           [-ls <path>]
           [-lsr <path>]
           [-du <path>]
           [-dus <path>]
           [-count[-q] <path>]
           [-mv <src> <dst>]
           [-cp <src> <dst>]
           [-rm <path>]
           [-rmr <path>]
           [-expunge]
           [-put <localsrc> ... <dst>]
           [-copyFromLocal <localsrc> ... <dst>]
           [-moveFromLocal <localsrc> ... <dst>]
           [-get [-ignoreCrc] [-crc] <src> <localdst>]
           [-getmerge <src> <localdst> [addnl]]
           [-cat <src>]
           [-text <src>]
           [-copyToLocal [-ignoreCrc] [-crc] <src> <localdst>]
           [-moveToLocal [-crc] <src> <localdst>]
           [-mkdir <path>]
           [-setrep [-R] [-w] <rep> <path/file>]
           [-touchz <path>]
           [-test -[ezd] <path>]
           [-stat [format] <path>]
           [-tail [-f] <file>]
           [-chmod [-R] <MODE[,MODE]... | OCTALMODE> PATH...]
           [-chown [-R] [OWNER][:[GROUP]] PATH...]
           [-chgrp [-R] GROUP PATH...]
           [-help [cmd]]

Generic options supported are
-conf <configuration file>     specify an application configuration file
-D <property=value>            use value for given property
-fs <local|namenode:port>      specify a namenode
-jt <local|jobtracker:port>    specify a job tracker
-files <comma separated list of files>    specify comma separated files to be copied to the map reduce cluster
-libjars <comma separated list of jars>    specify comma separated jar files to include in the classpath.
-archives <comma separated list of archives>    specify comma separated archives to be unarchived on the compute machines.
The general command line syntax is
bin/hadoop command [genericOptions] [commandOptions]

}}}  
 
  
 
 = Content 2. 使用網頁Gui瀏覽資訊 =
 
 * [http://localhost:50030 Map/Reduce Administration]
 * [http://localhost:50070 NameNode ]
 
 = Content 3. 更多HDFS shell 的用法 = 
 
 * bin/hadoop fs <args> ，下面則列出 <args> 的用法
 * 以下操作預設的目錄在 /user/<$username>/ 下
{{{
$ bin/hadoop fs -ls input
Found 4 items
-rw-r--r--   2 hadooper supergroup  115045564 2009-04-02 11:51 /user/hadooper/input/1.txt
-rw-r--r--   2 hadooper supergroup     987864 2009-04-02 11:51 /user/hadooper/input/2.txt
-rw-r--r--   2 hadooper supergroup    1573048 2009-04-02 11:51 /user/hadooper/input/3.txt
-rw-r--r--   2 hadooper supergroup   25844527 2009-04-02 11:51 /user/hadooper/input/4.txt
}}}
 * 完整的路徑則是 '''hdfs://node:port/path''' 如：
{{{
$ bin/hadoop fs -ls hdfs://gm1.nchc.org.tw:9000/user/hadooper/input
Found 4 items
-rw-r--r--   2 hadooper supergroup  115045564 2009-04-02 11:51 /user/hadooper/input/1.txt
-rw-r--r--   2 hadooper supergroup     987864 2009-04-02 11:51 /user/hadooper/input/2.txt
-rw-r--r--   2 hadooper supergroup    1573048 2009-04-02 11:51 /user/hadooper/input/3.txt
-rw-r--r--   2 hadooper supergroup   25844527 2009-04-02 11:51 /user/hadooper/input/4.txt
}}}

  == -cat  == 
 * 將路徑指定文件的內容輸出到stdout
{{{
$ bin/hadoop fs -cat quota/hadoop-env.sh
}}} 
 ==  -chgrp  == 
 * 改變文件所屬的組
{{{
$ bin/hadoop fs -chgrp -R hadooper own
}}}
  == -chmod == 
 * 改變文件的權限
{{{
$ bin/hadoop fs -chmod -R 755 own
}}}
  == -chown == 
 * 改變文件的擁有者
{{{
$ bin/hadoop fs -chown -R hadooper own
}}}
  == -copyFromLocal, -put == 
 * 從local放檔案到hdfs
{{{
$ bin/hadoop fs -put input dfs_input
}}}
 == -copyToLocal, -get == 
 * 把hdfs上得檔案下載到 local
{{{
$ bin/hadoop fs -get dfs_input input1
}}}
 == -cp == 
 * 將文件從hdfs原本路徑複製到hdfs目標路徑
{{{
$ bin/hadoop fs -cp own hadooper
}}}
 == -du == 
 * 顯示目錄中所有文件的大小
{{{
$ bin/hadoop fs -du input

Found 4 items
115045564   hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/1.txt
987864      hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/2.txt
1573048     hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/3.txt
25844527    hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/4.txt
}}}
 == -dus == 
 * 顯示該目錄/文件的總大小
{{{
$ bin/hadoop fs -dus input

hdfs://gm1.nchc.org.tw:9000/user/hadooper/input	143451003
}}}
 == -expunge == 
 * 清空垃圾桶
{{{
$ bin/hadoop fs -expunge
}}}
 == -getmerge == 
 * 將來源目錄<src>下所有的文件都集合到本地端一個<localdst>檔案內
 * bin/hadoop fs -getmerge <src> <localdst> 
{{{
$ echo "this is one; " >> in1/input
$ echo "this is two; " >> in1/input2
$ bin/hadoop fs -put in1 in1
$ bin/hadoop fs -getmerge in1 merge.txt
$ cat ./merge.txt
}}}

 == -ls == 
 * 列出文件或目錄的資訊
 * 文件名 <副本數> 文件大小 修改日期 修改時間 權限 用戶ID 組ID 
 * 目錄名 <dir> 修改日期 修改時間 權限 用戶ID 組ID 
{{{
$ bin/hadoop fs -ls
}}}
 == -lsr == 
 * ls命令的遞迴版本
{{{
$ bin/hadoop fs -lsr /
}}}
 == -mkdir == 
 * 建立資料夾
{{{
$ bin/hadoop fs -mkdir a b c
}}}
 == -moveFromLocal == 
 * 將local端的資料夾剪下移動到hdfs上
{{{
$ bin/hadoop fs -moveFromLocal in1 in2
}}}
 == -mv == 
 * 更改資料的名稱
{{{
$ bin/hadoop fs -mv in2 in3
}}}
 == -rm == 
 * 刪除指定的檔案（不可資料夾）
{{{
$ bin/hadoop fs -rm in1/input
}}}
 == -rmr == 
 * 遞迴刪除資料夾（包含在內的所有檔案）
{{{
$ bin/hadoop fs -rmr in1
}}}
 == -setrep == 
 * 設定副本係數
 * bin/hadoop fs -setrep [-R] [-w] <rep> <path/file>
{{{
$ bin/hadoop fs -setrep -w 2 -R input 
Replication 2 set: hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/1.txt
Replication 2 set: hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/2.txt
Replication 2 set: hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/3.txt
Replication 2 set: hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/4.txt
Waiting for hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/1.txt ... done
Waiting for hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/2.txt ... done
Waiting for hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/3.txt ... done
Waiting for hdfs://gm1.nchc.org.tw:9000/user/hadooper/input/4.txt ... done
}}}
 == -stat == 
 * 印出時間資訊
{{{
$ bin/hadoop fs -stat input
2009-04-02 03:51:29
}}}
 == -tail == 
 * 將文件的最後1k內容輸出
 * 用法 ： bin/hadoop fs -tail [-f] 檔案 (-f 參數用來顯示如果檔案增大，則秀出被append上得內容)
{{{
$ bin/hadoop fs -tail input/1.txt
}}}
 == -test == 
 * 測試檔案， -e 檢查文件是否存在(1=存在, 0＝否)， -z 檢查文件是否為空(1=空, 0＝不為空)， -d 檢查是否為目錄(1=存在, 0＝否)
   * 要用echo $? 來看回傳值為 0 or 1
 * 用法： bin/hadoop fs -test -[ezd] URI
 
{{{
$ bin/hadoop fs -test -e /user/hadooper/input/5.txt
$ bin/hadoop fs -test -z /user/hadooper/input/5.txt
test: File does not exist: /user/hadooper/input/5.txt
$ bin/hadoop fs -test -d /user/hadooper/input/5.txt

test: File does not exist: /user/hadooper/input/5.txt
}}}
 == -text == 
 * 將檔案（如壓縮檔, textrecordinputstream）輸出為純文字格式
 * hadoop fs -text <src>
{{{
$ hadoop fs -text macadr-eth1.txt.gz
00:1b:fc:61:75:b1
00:1b:fc:58:9c:23
}}}
 * ps : 目前沒支援zip的函式庫
{{{
$ bin/hadoop fs -text b/a.txt.zip
PK
���:��H{
        a.txtUT	b��Ib��IUx��sssss
test
PK

���:��H{

��a.txtUTb��IUxPK

@C
}}}
 == -touchz == 
 * 建立一個空文件
{{{
$ bin/hadoop fs -touchz b/kk
$ bin/hadoop fs -test -z b/kk
$ echo $?
1
$ bin/hadoop fs -test -z b/a.txt.zip
$ echo $?
0
}}}