老师布置的作业要求搭建 Hadoop 平台，跟初学 OpenStack 一样，接连出错了好几次才成功，为了方便以后偷懒决定写个脚本。

基于完全分布式模式部署 Hadoop

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
#!/bin/bash

#echo -e "\e[31m需配置好静态IP\e[0m"
echo -e "\e[31m虚拟机可能需要能联网\e[0m"
echo -e "\e[31m把所需压缩包放在hadoop1:/root/\e[0m"
echo -e "\e[31mhadoop-3.3.0.tar.gz jdk-8u241-linux-x64.tar.gz\e[0m"
read -p "没问题就回车执行!!如有误Ctrl+z终止程序!!"
echo " "
echo -e "\e[31m
    /\_____/\\
   /  o   o  \\
  ( ==  ^  == )
   )         (
  (           )
 ( (  )   (  ) )
(__(__)___(__)__)
\e[0m"
echo " "
sleep 5
echo -e "\e[31m输入错误按住Ctrl再点删除\e[0m"

# 基础环境配置
echo "1. 配置hosts解析"
read -p "hadoop1的IP地址: " hadoop1
read -p "hadoop2的IP地址: " hadoop2
read -p "hadoop3的IP地址: " hadoop3
read -p "root密码: " PASSWD


cat >> /etc/hosts << EOF
$hadoop1 hadoop1
$hadoop2 hadoop2
$hadoop3 hadoop3
EOF

# 配置yum源
mkdir /etc/yum.repos.d/bak
mv /etc/yum.repos.d/*.repo /etc/yum.repos.d/bak/
curl -o /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo

mkdir /opt/centos
mount /dev/sr0 /tmp/
cp -rvf /tmp/* /opt/centos/
umount /tmp/

cat > /etc/yum.repos.d/local.repo << EOF
[centos]
name=local
baseurl=file:///opt/centos
gpgcheck=0
EOF

yum install -y expect vim net-tools

echo "2.配置ssh"
expect -c "
spawn ssh hadoop1 'ssh-keygen'
expect \"Are you sure you want to continue connecting (yes/no)? \"
send \"yes\r\"
expect \"root@hadoop1's password: \"
send \"$PASSWD\r\"
expect \"Enter file in which to save the key (/root/.ssh/id_rsa): \"
send \"\r\"
expect \"Enter passphrase (empty for no passphrase): \"
send \"\r\"
expect \"Enter same passphrase again: \"
send \"\r\"
expect \"Are you sure you want to continue connecting (yes/no)? \"
send \"yes\r\"
expect eof
"


expect -c "
spawn ssh hadoop2 'ssh-keygen'
expect \"Are you sure you want to continue connecting (yes/no)? \"
send \"yes\r\"
expect \"root@hadoop2's password: \"
send \"$PASSWD\r\"
expect \"Enter file in which to save the key (/root/.ssh/id_rsa): \"
send \"\r\"
expect \"Enter passphrase (empty for no passphrase): \"
send \"\r\"
expect \"Enter same passphrase again: \"
send \"\r\"
expect eof
"

expect -c "
spawn ssh hadoop3 'ssh-keygen'
expect \"Are you sure you want to continue connecting (yes/no)? \"
send \"yes\r\"
expect \"root@hadoop3's password: \"
send \"$PASSWD\r\"
expect \"Enter file in which to save the key (/root/.ssh/id_rsa): \"
send \"\r\"
expect \"Enter passphrase (empty for no passphrase): \"
send \"\r\"
expect \"Enter same passphrase again: \"
send \"\r\"
expect eof
"



#for i in hadoop{1..3}
#do
#  echo -e "\e[30;41;5m输入yes和$i密码（密码输入看不见正常）\e[0m"
#  echo -e "\e[30;41;5m之后3个回车\e[0m"
#  ssh $i "ssh-keygen"
#  echo -e "\e[30;41;5m再次输入$i密码回车\e[0m"
#  scp /etc/hosts $i:/etc/hosts
#done

expect -c "
spawn ssh-copy-id hadoop1
expect \"root@hadoop1's password: \"
send \"$PASSWD\r\"
expect eof
"
expect -c "
spawn ssh-copy-id hadoop2
expect \"root@hadoop2's password: \"
send \"$PASSWD\r\"
expect eof
"
expect -c "
spawn ssh-copy-id hadoop3
expect \"root@hadoop3's password: \"
send \"$PASSWD\r\"
expect eof
"


for i in hadoop{1..3}
do
  ssh $i "mkdir -p /export/{data,servers,software}"
  ssh $i "systemctl disable --now firewalld"
  ssh $i "hostnamectl set-hostname $i"
done


mv /root/hadoop-3.3.0.tar.gz /export/software
mv /root/jdk-8u241-linux-x64.tar.gz /export/software

#安装JDK和Hadoop
echo "3.安装JDK和Hadoop"

tar xvf /export/software/jdk-8u241-linux-x64.tar.gz -C /export/servers/
tar xvf /export/software/hadoop-3.3.0.tar.gz -C /export/servers/

cat >> /etc/profile << EOF
# JAVA_HOME
export JAVA_HOME=/export/servers/jdk1.8.0_241

# HADOOP_HOME
export HADOOP_HOME=/export/servers/hadoop-3.3.0
export PATH=\$PATH:\$JAVA_HOME/bin:\$HADOOP_HOME/bin
EOF

source /etc/profile
echo "*************************************************************************"
java -version
echo "*************************************************************************"
hadoop version
echo "*************************************************************************"
# read -p "环境变量是否配置正确，无误回车继续！！如有误Ctrl+z终止程序"

# 配置Hadoop
echo "4.修改hadoop配置文件"

cat >> /export/servers/hadoop-3.3.0/etc/hadoop/hadoop-env.sh << EOF
export JAVA_HOME=/export/servers/jdk1.8.0_241
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root
EOF

cat > /export/servers/hadoop-3.3.0/etc/hadoop/core-site.xml << EOF
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
        <property>
                <name>fs.defaultFS</name>
                <value>hdfs://hadoop1:9000</value>
        </property>
        <property>
                <name>hadoop.tmp.dir</name>
                <value>/export/data/hadoop-3.3.0</value>
        </property>
        <property>
                <name>hadoop.http.staticuser.user</name>
                <value>root</value>
        </property>
        <property>
                <name>hadoop.proxyuser.root.hosts</name>
                <value>*</value>
        </property>
        <property>
                <name>hadoop.proxyuser.root.groups</name>
                <value>*</value>
        </property>
        <property>
                <name>fs.trash.interval</name>
                <value>1440</value>
        </property>
</configuration>
EOF

cat > /export/servers/hadoop-3.3.0/etc/hadoop/hdfs-site.xml << EOF
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
        <property>
                <name>dfs.replication</name>
                <value>2</value>
        </property>
        <property>
                <name>dfs.namenode.secondary.http-address</name>
                <value>hadoop2:9868</value>
        </property>
</configuration>
EOF

cat > /export/servers/hadoop-3.3.0/etc/hadoop/mapred-site.xml << EOF
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
        <property>
                <name>mapreduce.framework.name</name>
                <value>yarn</value>
        </property>
        <property>
                <name>mapreduce.jobhistory.address</name>
                <value>hadoop1:10020</value>
        </property>
        <property>
                <name>mapreduce.jobhistory.webapp.address</name>
                <value>hadoop1:19888</value>
        </property>
        <property>
                <name>yarn.app.mapreduce.am.env</name>
                <value>HADOOP_MAPRED_HOME=\${HADOOP_HOME}</value>
        </property>
        <property>
                <name>mapreduce.map.env</name>
                <value>HADOOP_MAPRED_HOME=\${HADOOP_HOME}</value>
        </property>
        <property>
                <name>mapreduce.reduce.env</name>
                <value>HADOOP_MAPRED_HOME=\${HADOOP_HOME}</value>
        </property>
</configuration>
EOF

cat > /export/servers/hadoop-3.3.0/etc/hadoop/yarn-site.xml << EOF
<?xml version="1.0"?>
<configuration>
        <property>
                <name>yarn.resourcemanager.hostname</name>
                <value>hadoop1</value>
        </property>
        <property>
                <name>yarn.nodemanager.aux-services</name>
                <value>mapreduce_shuffle</value>
        </property>
        <property>
                <name>yarn.nodemanager.pmem-check-enabled</name>
                <value>false</value>
        </property>
        <property>
                <name>yarn.nodemanager.vmem-check-enabled</name>
                <value>false</value>
        </property>
        <property>
                <name>yarn.log-aggregation-enable</name>
                <value>true</value>
        </property>
        <property>
                <name>yarn.log.server.url</name>
                <value>http://hadoop1:19888/jobhistory/logs</value>
        </property>
        <property>
                <name>yarn.log-aggregation.retain-seconds</name>
                <value>604800</value>
        </property>
</configuration>
EOF

cat > /export/servers/hadoop-3.3.0/etc/hadoop/workers << EOF
hadoop2
hadoop3
EOF

for i in hadoop{2,3}
do
  scp -r /export/servers/* $i:/export/servers/
  scp -r /etc/profile  $i:/etc/profile
done

for i in hadoop{1..3}
do
  echo -e "\e[30;41;5m$i\e[0m"
  ssh $i "source /etc/profile && java -version && echo '***********************************************' && hadoop version"
done

#read -p "hadoop2,3环境变量是否配置正确，无误回车继续！！如有误Ctrl+z终止程序"


hdfs namenode -format
/export/servers/hadoop-3.3.0/sbin/start-dfs.sh
/export/servers/hadoop-3.3.0/sbin/start-yarn.sh

echo "PS1='\[\e[36;40m\][\[\e[33;40m\]\u\[\e[31;40m\]@\[\e[34;40m\]\h \[\e[35;40m\]\W\[\e[36;40m\]]\]\e[0m\$ '" >> /root/.bashrc
source /root/.bashrc


echo '     _.-- ,.--.' > /etc/motd
echo "   .'   .'    /"  >> /etc/motd
echo "   | @       |'..--------._" >> /etc/motd
echo "  /      \._/              '. "  >> /etc/motd
echo " /  .-.-                     \\" >> /etc/motd
echo "(  /    \                     \\" >> /etc/motd
echo " \\\      '.                  | #" >> /etc/motd
echo "  \\\       \   -.           /" >> /etc/motd
echo "   :\       |    )._____.'   \\" >> /etc/motd
echo '    "       |   /  \  |  \    )' >> /etc/motd
echo "            |   |./'  :__ \.-'" >> /etc/motd
echo "            '--'" >> /etc/motd

cat /etc/motd



echo "浏览器搜索http://$hadoop1:9870和http:$hadoop1:8088"

  • 理解原理

  • 完成作业