Hadoop 简明教程

$ su
   password:
# useradd hadoop
# passwd hadoop
   New passwd:
   Retype new passwd

$ cd Downloads/
$ ls
jdk-7u71-linux-x64.gz

$ tar zxf jdk-7u71-linux-x64.gz
$ ls
jdk1.7.0_71   jdk-7u71-linux-x64.gz

$ su
password:
# mv jdk1.7.0_71 /usr/local/
# exit

export JAVA_HOME=/usr/local/jdk1.7.0_71
export PATH=$PATH:$JAVA_HOME/bin

$ source ~/.bashrc

# alternatives --install /usr/bin/java java usr/local/java/bin/java 2
# alternatives --install /usr/bin/javac javac usr/local/java/bin/javac 2
# alternatives --install /usr/bin/jar jar usr/local/java/bin/jar 2

# alternatives --set java usr/local/java/bin/java
# alternatives --set javac usr/local/java/bin/javac
# alternatives --set jar usr/local/java/bin/jar

export HADOOP_HOME=/usr/local/hadoop

$ hadoop version

Hadoop 2.4.1
Subversion https://svn.apache.org/repos/asf/hadoop/common -r 1529768
Compiled by hortonmu on 2013-10-07T06:28Z
Compiled with protoc 2.5.0
From source with checksum 79e53ce7994d1628b240f09af91e1af4

$HADOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.2.0.jar

$ hadoop jar $HADOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduceexamples-2.2.0.jar

$ mkdir input
$ cp $HADOOP_HOME/*.txt input
$ ls -l input

total 24
-rw-r--r-- 1 root root 15164 Feb 21 10:14 LICENSE.txt
-rw-r--r-- 1 root root   101 Feb 21 10:14 NOTICE.txt
-rw-r--r-- 1 root root  1366 Feb 21 10:14 README.txt

$ hadoop jar $HADOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduceexamples-2.2.0.jar  wordcount input output

$cat output/*

"AS      4
"Contribution" 1
"Contributor" 1
"Derivative 1
"Legal 1
"License"      1
"License");     1
"Licensor"      1
"NOTICE”        1
"Not      1
"Object"        1
"Source”        1
"Work”    1
"You"     1
"Your")   1
"[]"      1
"control"       1
"printed        1
"submitted"     1
(50%)     1
(BIS),    1
(C)       1
(Don't)   1
(ECCN)    1
(INCLUDING      2
(INCLUDING,     2
.............

export HADOOP_HOME=/usr/local/hadoop
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME

export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin
export HADOOP_INSTALL=$HADOOP_HOME

$ source ~/.bashrc

$ cd $HADOOP_HOME/etc/hadoop

export JAVA_HOME=/usr/local/jdk1.7.0_71

<configuration>
   <property>
      <name>fs.default.name</name>
      <value>hdfs://localhost:9000</value>
   </property>
</configuration>

dfs.replication (data replication value) = 1

(In the below given path /hadoop/ is the user name.
hadoopinfra/hdfs/namenode is the directory created by hdfs file system.)
namenode path = //home/hadoop/hadoopinfra/hdfs/namenode

(hadoopinfra/hdfs/datanode is the directory created by hdfs file system.)
datanode path = //home/hadoop/hadoopinfra/hdfs/datanode

<configuration>
   <property>
      <name>dfs.replication</name>
      <value>1</value>
   </property>

   <property>
      <name>dfs.name.dir</name>
      <value>file:///home/hadoop/hadoopinfra/hdfs/namenode </value>
   </property>

   <property>
      <name>dfs.data.dir</name>
      <value>file:///home/hadoop/hadoopinfra/hdfs/datanode </value>
   </property>
</configuration>

<configuration>
   <property>
      <name>yarn.nodemanager.aux-services</name>
      <value>mapreduce_shuffle</value>
   </property>
</configuration>

$ cp mapred-site.xml.template mapred-site.xml

<configuration>
   <property>
      <name>mapreduce.framework.name</name>
      <value>yarn</value>
   </property>
</configuration>

$ cd ~
$ hdfs namenode -format

10/24/14 21:30:55 INFO namenode.NameNode: STARTUP_MSG:
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG:   host = localhost/192.168.1.11
STARTUP_MSG:   args = [-format]
STARTUP_MSG:   version = 2.4.1
...
...
10/24/14 21:30:56 INFO common.Storage: Storage directory
/home/hadoop/hadoopinfra/hdfs/namenode has been successfully formatted.
10/24/14 21:30:56 INFO namenode.NNStorageRetentionManager: Going to
retain 1 images with txid >= 0
10/24/14 21:30:56 INFO util.ExitUtil: Exiting with status 0
10/24/14 21:30:56 INFO namenode.NameNode: SHUTDOWN_MSG:
/************************************************************
SHUTDOWN_MSG: Shutting down NameNode at localhost/192.168.1.11
************************************************************/

$ start-dfs.sh

10/24/14 21:37:56
Starting namenodes on [localhost]
localhost: starting namenode, logging to /home/hadoop/hadoop
2.4.1/logs/hadoop-hadoop-namenode-localhost.out
localhost: starting datanode, logging to /home/hadoop/hadoop
2.4.1/logs/hadoop-hadoop-datanode-localhost.out
Starting secondary namenodes [0.0.0.0]

$ start-yarn.sh

starting yarn daemons
starting resourcemanager, logging to /home/hadoop/hadoop
2.4.1/logs/yarn-hadoop-resourcemanager-localhost.out
localhost: starting nodemanager, logging to /home/hadoop/hadoop
2.4.1/logs/yarn-hadoop-nodemanager-localhost.out

http://localhost:50070/

http://localhost:8088/

$ $HADOOP_HOME/bin/hadoop fs -mkdir /user/input

$ $HADOOP_HOME/bin/hadoop fs -put /home/file.txt /user/input

$ $HADOOP_HOME/bin/hadoop fs -ls /user/input

$ $HADOOP_HOME/bin/hadoop fs -cat /user/output/outfile

$ $HADOOP_HOME/bin/hadoop fs -get /user/output/ /home/hadoop_tp/

1979   23   23   2   43   24   25   26   26   26   26   25   26  25
1980   26   27   28  28   28   30   31   31   31   30   30   30  29
1981   31   32   32  32   33   34   35   36   36   34   34   34  34
1984   39   38   39  39   39   41   42   43   40   39   38   38  40
1985   38   39   39  39   39   41   41   41   00   40   39   39  45

package hadoop;

import java.util.*;

import java.io.IOException;
import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class ProcessUnits {
   //Mapper class
   public static class E_EMapper extends MapReduceBase implements
   Mapper<LongWritable ,/*Input key Type */
   Text,                /*Input value Type*/
   Text,                /*Output key Type*/
   IntWritable>        /*Output value Type*/
   {
      //Map function
      public void map(LongWritable key, Text value,
      OutputCollector<Text, IntWritable> output,

      Reporter reporter) throws IOException {
         String line = value.toString();
         String lasttoken = null;
         StringTokenizer s = new StringTokenizer(line,"\t");
         String year = s.nextToken();

         while(s.hasMoreTokens()) {
            lasttoken = s.nextToken();
         }
         int avgprice = Integer.parseInt(lasttoken);
         output.collect(new Text(year), new IntWritable(avgprice));
      }
   }

   //Reducer class
   public static class E_EReduce extends MapReduceBase implements Reducer< Text, IntWritable, Text, IntWritable > {

      //Reduce function
      public void reduce( Text key, Iterator <IntWritable> values,
      OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
         int maxavg = 30;
         int val = Integer.MIN_VALUE;

         while (values.hasNext()) {
            if((val = values.next().get())>maxavg) {
               output.collect(key, new IntWritable(val));
            }
         }
      }
   }

   //Main function
   public static void main(String args[])throws Exception {
      JobConf conf = new JobConf(ProcessUnits.class);

      conf.setJobName("max_eletricityunits");
      conf.setOutputKeyClass(Text.class);
      conf.setOutputValueClass(IntWritable.class);
      conf.setMapperClass(E_EMapper.class);
      conf.setCombinerClass(E_EReduce.class);
      conf.setReducerClass(E_EReduce.class);
      conf.setInputFormat(TextInputFormat.class);
      conf.setOutputFormat(TextOutputFormat.class);

      FileInputFormat.setInputPaths(conf, new Path(args[0]));
      FileOutputFormat.setOutputPath(conf, new Path(args[1]));

      JobClient.runJob(conf);
   }
}

$ mkdir units

$ javac -classpath hadoop-core-1.2.1.jar -d units ProcessUnits.java
$ jar -cvf units.jar -C units/ .

$HADOOP_HOME/bin/hadoop fs -mkdir input_dir

$HADOOP_HOME/bin/hadoop fs -put /home/hadoop/sample.txt input_dir

$HADOOP_HOME/bin/hadoop fs -ls input_dir/

$HADOOP_HOME/bin/hadoop jar units.jar hadoop.ProcessUnits input_dir output_dir

INFO mapreduce.Job: Job job_1414748220717_0002
completed successfully
14/10/31 06:02:52
INFO mapreduce.Job: Counters: 49
   File System Counters

FILE: Number of bytes read = 61
FILE: Number of bytes written = 279400
FILE: Number of read operations = 0
FILE: Number of large read operations = 0
FILE: Number of write operations = 0
HDFS: Number of bytes read = 546
HDFS: Number of bytes written = 40
HDFS: Number of read operations = 9
HDFS: Number of large read operations = 0
HDFS: Number of write operations = 2 Job Counters


   Launched map tasks = 2
   Launched reduce tasks = 1
   Data-local map tasks = 2
   Total time spent by all maps in occupied slots (ms) = 146137
   Total time spent by all reduces in occupied slots (ms) = 441
   Total time spent by all map tasks (ms) = 14613
   Total time spent by all reduce tasks (ms) = 44120
   Total vcore-seconds taken by all map tasks = 146137
   Total vcore-seconds taken by all reduce tasks = 44120
   Total megabyte-seconds taken by all map tasks = 149644288
   Total megabyte-seconds taken by all reduce tasks = 45178880

Map-Reduce Framework

   Map input records = 5
   Map output records = 5
   Map output bytes = 45
   Map output materialized bytes = 67
   Input split bytes = 208
   Combine input records = 5
   Combine output records = 5
   Reduce input groups = 5
   Reduce shuffle bytes = 6
   Reduce input records = 5
   Reduce output records = 5
   Spilled Records = 10
   Shuffled Maps  = 2
   Failed Shuffles = 0
   Merged Map outputs = 2
   GC time elapsed (ms) = 948
   CPU time spent (ms) = 5160
   Physical memory (bytes) snapshot = 47749120
   Virtual memory (bytes) snapshot = 2899349504
   Total committed heap usage (bytes) = 277684224

File Output Format Counters

   Bytes Written = 40

$HADOOP_HOME/bin/hadoop fs -ls output_dir/

$HADOOP_HOME/bin/hadoop fs -cat output_dir/part-00000

1981    34
1984    40
1985    45

$HADOOP_HOME/bin/hadoop fs -cat output_dir/part-00000/bin/hadoop dfs get output_dir /home/hadoop

$ $HADOOP_HOME/bin/hadoop job -status <JOB-ID>
e.g.
$ $HADOOP_HOME/bin/hadoop job -status job_201310191043_0004

$ $HADOOP_HOME/bin/hadoop job -history <DIR-NAME>
e.g.
$ $HADOOP_HOME/bin/hadoop job -history /user/expert/output

$ $HADOOP_HOME/bin/hadoop job -kill <JOB-ID>
e.g.
$ $HADOOP_HOME/bin/hadoop job -kill job_201310191043_0004

!/usr/bin/python

import sys

# Input takes from standard input for myline in sys.stdin:
   # Remove whitespace either side
   myline = myline.strip()

   # Break the line into words
   words = myline.split()

   # Iterate the words list
   for myword in words:
      # Write the results to standard output
      print '%s\t%s' % (myword, 1)

#!/usr/bin/python

from operator import itemgetter
import sys

current_word = ""
current_count = 0
word = ""

# Input takes from standard input for myline in sys.stdin:
   # Remove whitespace either side
   myline = myline.strip()

   # Split the input we got from mapper.py word,
   count = myline.split('\t', 1)

   # Convert count variable to integer
   try:
      count = int(count)

   except ValueError:
      # Count was not a number, so silently ignore this line continue

   if current_word == word:
   current_count += count
   else:
      if current_word:
         # Write result to standard output print '%s\t%s' % (current_word, current_count)

      current_count = count
      current_word = word

# Do not forget to output the last word if needed!
if current_word == word:
   print '%s\t%s' % (current_word, current_count)

./bin/hadoop jar contrib/streaming/hadoop-streaming-1.2.1.jar -input myinput -output myoutput -mapper /home/expert/hadoop-1.2.1/mapper.py -reducer /home/expert/hadoop-1.2.1/reducer.py

$ cd Downloads/
$ ls
jdk-7u71-Linux-x64.gz

$ tar zxf jdk-7u71-Linux-x64.gz
$ ls
jdk1.7.0_71 jdk-7u71-Linux-x64.gz

$ su
password:
# mv jdk1.7.0_71 /usr/local/
# exit

export JAVA_HOME=/usr/local/jdk1.7.0_71
export PATH=PATH:$JAVA_HOME/bin

<configuration>
   <property>
      <name>fs.default.name</name>
      <value>hdfs://hadoop-master:9000/</value>
   </property>
   <property>
      <name>dfs.permissions</name>
      <value>false</value>
   </property>
</configuration>

<configuration>
   <property>
      <name>dfs.data.dir</name>
      <value>/opt/hadoop/hadoop/dfs/name/data</value>
      <final>true</final>
   </property>

   <property>
      <name>dfs.name.dir</name>
      <value>/opt/hadoop/hadoop/dfs/name</value>
      <final>true</final>
   </property>

   <property>
      <name>dfs.replication</name>
      <value>1</value>
   </property>
</configuration>

<configuration>
   <property>
      <name>mapred.job.tracker</name>
      <value>hadoop-master:9001</value>
   </property>
</configuration>

export JAVA_HOME=/opt/jdk1.7.0_17
export HADOOP_OPTS=-Djava.net.preferIPv4Stack=true
export HADOOP_CONF_DIR=/opt/hadoop/hadoop/conf

$ vi etc/hadoop/masters

hadoop-master

$ vi etc/hadoop/slaves

hadoop-slave-1
hadoop-slave-2

# su hadoop
$ cd /opt/hadoop/hadoop
$ bin/hadoop namenode –format
11/10/14 10:58:07 INFO namenode.NameNode: STARTUP_MSG:
/************************************************************
STARTUP_MSG: Starting NameNode
STARTUP_MSG: host = hadoop-master/192.168.1.109
STARTUP_MSG: args = [-format]
STARTUP_MSG: version = 1.2.0
STARTUP_MSG: build = https://svn.apache.org/repos/asf/hadoop/common/branches/branch-1.2 -r 1479473;
compiled by 'hortonfo' on Mon May 6 06:59:37 UTC 2013
STARTUP_MSG: java = 1.7.0_71

************************************************************/
11/10/14 10:58:08 INFO util.GSet: Computing capacity for map BlocksMap
editlog=/opt/hadoop/hadoop/dfs/name/current/edits
………………………………………………….
………………………………………………….
………………………………………………….
11/10/14 10:58:08 INFO common.Storage: Storage directory
/opt/hadoop/hadoop/dfs/name has been successfully formatted.
11/10/14 10:58:08 INFO namenode.NameNode:
SHUTDOWN_MSG:
/************************************************************
SHUTDOWN_MSG: Shutting down NameNode at hadoop-master/192.168.1.15
************************************************************/

IP address : 192.168.1.103
netmask : 255.255.255.0
hostname : slave3.in

useradd hadoop
passwd hadoop

mkdir -p $HOME/.ssh
chmod 700 $HOME/.ssh
ssh-keygen -t rsa -P '' -f $HOME/.ssh/id_rsa
cat $HOME/.ssh/id_rsa.pub >> $HOME/.ssh/authorized_keys
chmod 644 $HOME/.ssh/authorized_keys
Copy the public key to new slave node in hadoop user $HOME directory
scp $HOME/.ssh/id_rsa.pub hadoop@192.168.1.103:/home/hadoop/

su hadoop ssh -X hadoop@192.168.1.103

cd $HOME
mkdir -p $HOME/.ssh
chmod 700 $HOME/.ssh
cat id_rsa.pub >>$HOME/.ssh/authorized_keys
chmod 644 $HOME/.ssh/authorized_keys

ssh hadoop@192.168.1.103 or hadoop@slave3

su hadoop or ssh -X hadoop@192.168.1.103

./bin/hadoop-daemon.sh start datanode

$ jps
7141 DataNode
10312 Jps

$ su hadoop

<property>
   <name>dfs.hosts.exclude</name>
   <value>/home/hadoop/hadoop-1.2.1/hdfs_exclude.txt</value>
   <description>DFS exclude</description>
</property>

slave2.in

$ $HADOOP_HOME/bin/hadoop dfsadmin -refreshNodes

$ $HADOOP_HOME/bin/hadoop dfsadmin -report

$ $HADOOP_HOME/bin/hadoop-daemon.sh stop tasktracker
$HADOOP_HOME/bin/hadoop-daemon.sh start tasktracker