⬛︎ HDFS 환경 구축

$ sudo apt-get install default-jdk
$ sudo update-alternatives --list java
/usr/lib/jvm/java-7-openjdk-amd64/jre/bin/java

$ cd $HOME
$ vi .profile
export JAVA_HOME=/usr/lib/jvm/java-7-openjdk-amd64
export PATH=$HOME/hadoop-2.7.2/bin:$HOME/hadoop-2.7.2/sbin:$PATH
$ source .profile

$ sudo apt-get install ssh
$ sudo apt-get install rsync
$ ssh-keygen -t dsa -P '' -f ~/.ssh/id_dsa
$ cat ~/.ssh/id_dsa.pub >> ~/.ssh/authorized_keys
$ chmod 0600 ~/.ssh/authorized_keys

$ ssh localhost
$ exit

$ wget http://www.apache.org/dist/hadoop/common/hadoop-2.7.2/hadoop-2.7.2.tar.gz
$ tar xfz hadoop-2.7.2.tar.gz
$ cd hadoop-2.7.2/etc/hadoop/

$ vi core-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>fs.default.name</name>
        <value>hdfs://localhost:9000</value>
    </property>
</configuration>

$ vi hdfs-site.xml
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
</configuration>

$ vi hadoop-env.sh
export JAVA_HOME=/usr/lib/jvm/java-7-openjdk-amd64

$ hdfs namenode -format
16/03/04 03:55:40 INFO namenode.NameNode: STARTUP_MSG: 
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG:   host = HDFS/127.0.1.1
STARTUP_MSG:   args = [-format]
STARTUP_MSG:   version = 2.7.2

... (snip)

/************************************************************
SHUTDOWN_MSG: Shutting down NameNode at HDFS/127.0.1.1
************************************************************/

$ start-dfs.sh 
Starting namenodes on [localhost]
localhost: starting namenode, logging to /home/tsubo/hadoop-2.7.2/logs/hadoop-tsubo-namenode-HDFS.out
localhost: starting datanode, logging to /home/tsubo/hadoop-2.7.2/logs/hadoop-tsubo-datanode-HDFS.out
Starting secondary namenodes [0.0.0.0]
0.0.0.0: starting secondarynamenode, logging to /home/tsubo/hadoop-2.7.2/logs/hadoop-tsubo-secondarynamenode-HDFS.out

$ jps
12767 Jps
12656 SecondaryNameNode
12462 DataNode
12302 NameNode

⬛︎ HDFS를 사용해보기

$ hdfs dfs -ls /
$ hdfs dfs -mkdir /foo
$ hdfs dfs -ls /
Found 1 items
drwxr-xr-x   - tsubo supergroup          0 2016-03-04 04:11 /foo

$ cat /home/tsubo/test.txt
test data
$ hdfs dfs -put /home/tsubo/test.txt /foo
@HDFS:~$ hdfs dfs -ls /foo
Found 1 items
-rw-r--r--   1 tsubo supergroup         10 2016-03-04 04:14 /foo/test.txt

$ hdfs dfs -cat /foo/test.txt
test data

웹 브라우저의 관리 화면에서도 확인해보십시오.

$ hdfs dfs -rm /foo/test.txt
16/03/04 04:20:54 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 0 minutes, Emptier interval = 0 minutes.
Deleted /foo/test.txt

$ hdfs dfs -rmdir /foo
$ hdfs dfs -ls /

$ stop-dfs.sh
Stopping namenodes on [localhost]
localhost: stopping namenode
localhost: stopping datanode
Stopping secondary namenodes [0.0.0.0]
0.0.0.0: stopping secondarynamenode