高可用部署 Hadoop

先chmod +x dep-hadoop.sh给脚本增加执行权限

再bash dep-hadoop.sh运行（dep-hadoop.sh为下面的脚本名）

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
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
#!/bin/bash

# 检查软件包是否存在当前目录
[ ! -e hadoop-3.3.0.tar.gz ] && echo -e  "\e[1;5;$[ $[RANDOM%7]+31 ]mNot Found hadoop-3.3.0.tar.gz\e[0m" && exit 1
[ ! -e jdk-8u241-linux-x64.tar.gz ] && echo -e  "\e[1;5;$[ $[RANDOM%7]+31 ]mNot Found jdk-8u241-linux-x64.tar.gz\e[0m" && exit 1
[ ! -e apache-zookeeper-3.7.2-bin.tar.gz ] && echo -e  "\e[1;5;$[ $[RANDOM%7]+31 ]mNot Found apache-zookeeper-3.7.2-bin.tar.gz\e[0m" && exit 1

#  配置hosts解析
hadoop1="192.168.1.11"
hadoop2="192.168.1.12"
hadoop3="192.168.1.13"
PASSWD="000000"

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

# 配置yum源
rm -rf /etc/yum.repos.d/*.repo
curl -o /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo
yum install -y expect vim net-tools bash-completion tree lrzsz man-pages zip unzip wget lsof rsync ftp tcpdump tar

# 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
"



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
"

# 初始化环境
for i in {1..3}
do
  ssh hadoop$i "mkdir -p /export/{data/zookeeper/zkdata,servers/hadoop-HA,software}"
  ssh hadoop$i "systemctl disable --now firewalld"
  ssh hadoop$i "hostnamectl set-hostname hadoop${i}"
  ssh hadoop$i "echo $i > /export/data/zookeeper/zkdata/myid"
  ssh hadoop$i "setenforce 0"
  ssh hadoop$i "sed -i '/^SELINUX/s/SELINUX=.*/SELINUX=disabled/g' /etc/selinux/config"
done

# 把文件放入指定目录下
cp -r *.gz /export/software


# 解压包
tar xf /export/software/hadoop-3.3.0.tar.gz -C /export/servers/hadoop-HA/
tar xf /export/software/jdk-8u241-linux-x64.tar.gz -C /export/servers/
tar xf /export/software/apache-zookeeper-3.7.2-bin.tar.gz -C /export/servers/

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

# ZK_HOME
export ZK_HOME=/export/servers/zookeeper-3.7.2

# HADOOP_HOME
export HADOOP_HOME=/export/servers/hadoop-HA/hadoop-3.3.0

export PATH=\$ZK_HOME/bin:\$JAVA_HOME/bin:\$HADOOP_HOME/bin:\$HADOOP_HOME/sbin:\$PATH
EOF

source /etc/profile


# 配置zookeeper集群
mv /export/servers/apache-zookeeper-3.7.2-bin /export/servers/zookeeper-3.7.2
cat > /export/servers/zookeeper-3.7.2/conf/zoo.cfg << EOF
tickTime=2000
initLimit=10
syncLimit=5
dataDir=/export/data/zookeeper/zkdata
clientPort=2181
server.1=hadoop1:2888:3888
server.2=hadoop2:2888:3888
server.3=hadoop3:2888:3888
EOF

# 配置hadoop高可用
cat >> /export/servers/hadoop-HA/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_JOURNALNODE_USER=root
export HDFS_ZKFC_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root
EOF

cp /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/core-site.xml{,.bak}

cat > /export/servers/hadoop-HA/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://ns1</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/export/data/hadoop-HA/hadooop/</value>
    </property>
    <property>
        <name>ha.zookeeper.quorum</name>
        <value>hadoop1:2181,hadoop2:2181,hadoop3:2181</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>
</configuration>
EOF

cp /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/hdfs-site.xml{,.bak}

cat > /export/servers/hadoop-HA/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>3</value>
    </property>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>/export/data/hadoop/namenode</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>/export/data/hadoop/datanode</value>
    </property>
    <property>
        <name>dfs.nameservices</name>
        <value>ns1</value>
    </property>
    <property>
        <name>dfs.ha.namenodes.ns1</name>
        <value>nn1,nn2</value>
    </property>
    <property>
        <name>dfs.namenode.rpc-address.ns1.nn1</name>
        <value>hadoop1:9000</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.ns1.nn1</name>
        <value>hadoop1:9870</value> 
    </property>
    <property>
        <name>dfs.namenode.rpc-address.ns1.nn2</name>
        <value>hadoop2:9000</value>
    </property>
    <property>
        <name>dfs.namenode.http-address.ns1.nn2</name>
        <value>hadoop2:9870</value>
    </property>
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://hadoop1:8485;hadoop2:8485;hadoop3:8485/ns1</value>
    </property>
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/export/data/journaldata</value>
    </property>
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>dfs.client.failover.proxy.provider.ns1</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    <property>
        <name>dfs.permissions.enable</name>
        <value>false</value>
    </property>
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>
           sshfence
           shell(/bin/true)
        </value>
    </property>
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/root/.ssh/id_rsa</value>
    </property>
    <property>
        <name>dfs.ha.fencing.ssh.connect-timeout</name>
        <value>30000</value>
    </property>
</configuration>
EOF


cp /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/mapred-site.xml{,.bak}

cat > /export/servers/hadoop-HA/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

cp /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/yarn-site.xml{,.bak}

cat > /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/yarn-site.xml << EOF
<?xml version="1.0"?>
<configuration>
    <property>
        <name>yarn.resourcemanager.ha.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>jyarn</value>
    </property>
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>hadoop1</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>hadoop2</value>
    </property>
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>86400</value>
    </property>
    <property>
        <name>yarn.resourcemanager.recovery.enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.resourcemanager.store.class</name>
        <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm1</name>
        <value>hadoop1:8188</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address.rm1</name>
        <value>hadoop1:8130</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address.rm2</name>
        <value>hadoop2:8188</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address.rm2</name>
        <value>hadoop2:8130</value>
    </property>
</configuration>
EOF

cat > /export/servers/hadoop-HA/hadoop-3.3.0/etc/hadoop/workers << EOF
hadoop1
hadoop2
hadoop3
EOF


# 将文件copy给hadoop2、3
for i in hadoop{2,3}
do
  ssh $i "rm -rf  /etc/yum.repos.d/*.repo" 
  ssh $i "curl -o /etc/yum.repos.d/CentOS-Base.repo https://mirrors.aliyun.com/repo/Centos-7.repo"
  ssh $i "yum install -y tar expect vim net-tools bash-completion tree lrzsz man-pages zip unzip wget lsof rsync ftp tcpdump"
  scp -r /export/servers $i:/export
  scp -r /etc/hosts $i:/etc/hosts
  scp -r /etc/profile $i:/etc/profile
done


# 启动zookeeper
for i in hadoop{1..3}
do
  ssh $i "source /etc/profile && /export/servers/zookeeper-3.7.2/bin/zkServer.sh start"
done

# 查看状态
for i in hadoop{1..3}
do
  ssh $i "source /etc/profile && /export/servers/zookeeper-3.7.2/bin/zkServer.sh status" 
  ssh $i "sleep 3"
  ssh $i "source /etc/profile && hdfs --daemon start journalnode"
done

# 格式化
source /etc/profile && hdfs namenode -format

sleep 3

ssh hadoop2 "mkdir -p /export/data/hadoop/namenode"

scp -r /export/data/hadoop/namenode/* hadoop2:/export/data/hadoop/namenode/

sleep 3

source /etc/profile && hdfs zkfc -formatZK

source /etc/profile && start-dfs.sh

source /etc/profile && start-yarn.sh
echo
echo
echo
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m查看NomaNode\e[0m"
echo
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m$hadoop1:9870\e[0m"
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m$hadoop2:9870\e[0m"
echo
echo
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m查看ResourceManager\e[0m"
echo
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m$hadoop1:8188/cluster/cluster\e[0m"
echo -e  "\e[1;$[ $[RANDOM%7]+31 ]m$hadoop2:8188/cluster/cluster\e[0m"
# rm -rf /export
# rm -rf .ssh/*
# vim /etc/hosts
# vim /etc/profile