shell脚本编程(进阶)

以三台机器搭建的集群为例

1.查看三台机器的进程

[hadoop@hadoop001 hadoop]$ vi jps.sh
#!/bin/bash

echo "-----------------hadoop001 process---------------"
ssh hadoop001 "$JAVA_HOME/bin/jps"
echo "                                                    "


echo "-----------------hadoop002 process---------------"
ssh hadoop002 "$JAVA_HOME/bin/jps"
echo "                                                    "


echo "-----------------hadoop003 process---------------"
ssh  hadoop003 "$JAVA_HOME/bin/jps"
echo "                                                    "
[hadoop@hadoop001 hadoop]$ ./jps.sh
----------hadoop001 process------------
3385 Jps
                                                
----------hadoop002 process------------
2903 Jps
                                                
----------hadoop003 process------------
2611 Jps

2.拷贝文件脚本

[hadoop@hadoop001 hadoop]$ vi sync_hadoop.sh 
#!/bin/bash -x

HADOOP_CONF=/home/hadoop/app/hadoop/etc/hadoop/

cd $HADOOP_CONF

# 此处由于机器少 可以直接一个一个写  如果机器多的话  可以使用for循环
scp hadoop-env.sh core-site.xml hdfs-site.xml mapred-site.xml yarn-site.xml  hadoop002:$HADOOP_CONF
scp hadoop-env.sh core-site.xml hdfs-site.xml mapred-site.xml yarn-site.xml  hadoop003:$HADOOP_CONF

exit 0

3.启动集群shell脚本

3.1 编写启动脚本

[hadoop@hadoop001 hadoop]$ vi start_cluster.sh
#!/bin/bash -x

# 启动zk
ssh hadoop001 "$ZOOKEEPER_HOME/bin/zkServer.sh start"
ssh hadoop002 "$ZOOKEEPER_HOME/bin/zkServer.sh start"
ssh hadoop003 "$ZOOKEEPER_HOME/bin/zkServer.sh start"

# 睡眠5s  zk启动之后不能立马就启动hadoop
sleep 5

#start hdfs+yarn+jobhistory
/home/hadoop/app/hadoop/sbin/start-all.sh

sleep 5s

# 启动hadoop002机器上的resourcemanager historyserver
ssh hadoop002 "/home/hadoop/app/hadoop/sbin/yarn-daemon.sh start resourcemanager"
/home/hadoop/app/hadoop/sbin/mr-jobhistory-daemon.sh start historyserver

# 退出
exit 0

3.2 执行脚本并查看进程

# 执行脚本
[hadoop@hadoop001 hadoop]$ ./start_cluster.sh
# 启动日志如下
+ ssh hadoop001 '/home/hadoop/app/zookeeper/bin/zkServer.sh start'
JMX enabled by default
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
+ ssh hadoop002 '/home/hadoop/app/zookeeper/bin/zkServer.sh start'
JMX enabled by default
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
+ ssh hadoop003 '/home/hadoop/app/zookeeper/bin/zkServer.sh start'
JMX enabled by default
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
+ sleep 5
+ /home/hadoop/app/hadoop/sbin/start-all.sh
This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh
Starting namenodes on [hadoop001 hadoop002]
hadoop001: starting namenode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-namenode-hadoop001.out
hadoop002: starting namenode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-namenode-hadoop002.out
hadoop001: starting datanode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-datanode-hadoop001.out
hadoop002: starting datanode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-datanode-hadoop002.out
hadoop003: starting datanode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-datanode-hadoop003.out
Starting journal nodes [hadoop001 hadoop002 hadoop003]
hadoop001: starting journalnode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-journalnode-hadoop001.out
hadoop003: starting journalnode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-journalnode-hadoop003.out
hadoop002: starting journalnode, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-journalnode-hadoop002.out
Starting ZK Failover Controllers on NN hosts [hadoop001 hadoop002]
hadoop001: starting zkfc, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-zkfc-hadoop001.out
hadoop002: starting zkfc, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/hadoop-hadoop-zkfc-hadoop002.out
starting yarn daemons
starting resourcemanager, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/yarn-hadoop-resourcemanager-hadoop001.out
hadoop003: starting nodemanager, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/yarn-hadoop-nodemanager-hadoop003.out
hadoop002: starting nodemanager, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/yarn-hadoop-nodemanager-hadoop002.out
hadoop001: starting nodemanager, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/yarn-hadoop-nodemanager-hadoop001.out
+ sleep 5s
+ ssh hadoop002 '/home/hadoop/app/hadoop/sbin/yarn-daemon.sh start resourcemanager'
starting resourcemanager, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/yarn-hadoop-resourcemanager-hadoop002.out
+ /home/hadoop/app/hadoop/sbin/mr-jobhistory-daemon.sh start historyserver
starting historyserver, logging to /home/hadoop/app/hadoop-2.6.0-cdh5.15.1/logs/mapred-hadoop-historyserver-hadoop001.out
+ exit 0

# 执行jps.sh 查看下各机器进程情况
[hadoop@hadoop001 hadoop]$ ./jps.sh
----------hadoop001 process------------
3265 Jps
2401 NameNode
3219 JobHistoryServer
2694 JournalNode
2504 DataNode
3066 NodeManager
                                                
----------hadoop002 process------------
2787 ResourceManager
2628 NodeManager
2260 NameNode
2324 DataNode
2427 JournalNode
2829 Jps
                                                
----------hadoop003 process------------
2357 JournalNode
2455 NodeManager
2263 DataNode
2585 Jps
# 查看进程会发现启动有问题 缺少zookeeper  zkfc

3.2.1 排查集群未启动成功问题

3.2.1.1 查看zookeeper进程

# 通过ps -ef | grep zookeeper 查看进程
[hadoop@hadoop001 hadoop]$ ps -ef | grep zookeeper
hadoop    3527  2111  0 15:08 pts/0    00:00:00 grep --color=auto zookeeper
# 未发现zookeeper进程

由于zk没有启动成功，导致zkfc也启动失败

3.2.1.2 查看zk启动日志

# ① 查找zk配置文件 发现没有配置日志目录
[hadoop@hadoop001 conf]$ cat zoo.cfg

# ② 查找conf目录下的log4j.properties文件
[hadoop@hadoop001 conf]$ cat log4j.properties
......
zookeeper.log.dir=.
zookeeper.log.file=zookeeper.log
......
# 但通过给定的路径未找到日志文件 zookeeper.log 

# ③ find /home/hadoop -name 'zookeeper.log'
[hadoop@hadoop001 conf]$ find /home/hadoop -name 'zookeeper.log'
# 没有任何信息打印 说明hadoop用户下不存在
# 用root在根目录下搜索
[root@hadoop001 ~]# find / -name 'zookeeper.log'

# ④ 查看zk启动脚本  zkServer.sh
[hadoop@hadoop001 bin]$ vi zkServer.sh
# 由于是启动  所以只需要看start那一块脚本即可
......
_ZOO_DAEMON_OUT="$ZOO_LOG_DIR/zookeeper.out"

case $1 in
start)
    echo  -n "Starting zookeeper ... "
    if [ -f "$ZOOPIDFILE" ]; then
      if kill -0 `cat "$ZOOPIDFILE"` > /dev/null 2>&1; then
         echo $command already running as process `cat "$ZOOPIDFILE"`.
         exit 0
      fi
    fi
    nohup "$JAVA" "-Dzookeeper.log.dir=${ZOO_LOG_DIR}" "-Dzookeeper.root.logger=${ZOO_LOG4J_PROP}" \
    -cp "$CLASSPATH" $JVMFLAGS $ZOOMAIN "$ZOOCFG" > "$_ZOO_DAEMON_OUT" 2>&1 < /dev/null &
......
# 经查找启动脚本会发现 日志文件的后缀被更改成了zookeeper.out

# ⑤ 全局搜索下 zookeeper.out
[root@hadoop001 ~]# find / -name 'zookeeper.out'
/home/hadoop/app/hadoop-2.6.0-cdh5.15.1/etc/hadoop/zookeeper.out
/home/hadoop/app/zookeeper-3.4.6/conf/zookeeper.out
/home/hadoop/zookeeper.out # 该文件为日志文件
[root@hadoop001 ~]# cat /home/hadoop/zookeeper.out
nohup: failed to run command ‘java’: No such file or directory
# 此时问题找到

# ⑥ 分析错误 直接执行ssh查找java   发现找不到java  但是却可以找到环境变量  且 单独执行which java也是存在的
[hadoop@hadoop001 ~]$ ssh hadoop001 "which java"
which: no java in (/usr/local/bin:/usr/bin)
[hadoop@hadoop001 ~]$ ssh hadoop001 "echo $JAVA_HOME"
/usr/java/jdk1.8.0_40
[hadoop@hadoop001 ~]$ which java
/usr/java/jdk1.8.0_40/bin/java

# ⑦ 继续查看zkServer.sh启动脚本 从头开始看 主要为了找到zkServer.sh脚本中$JAVA在哪里赋值的
# 会发现如下部分
[hadoop@hadoop001 bin]$ vi zkServer.sh
......
if [ -e "$ZOOBIN/../libexec/zkEnv.sh" ]; then
  . "$ZOOBINDIR/../libexec/zkEnv.sh"
else
  . "$ZOOBINDIR/zkEnv.sh"
fi
......
# 查看zkEnv.sh   找到如下赋值
[hadoop@hadoop001 bin]$ vi zkEnv.sh
......
#手动加一句打印  为了查看环境变量是否存在
echo "---------------java: $JAVA_HOME-------------"

if [ "$JAVA_HOME" != "" ]; then
  JAVA="$JAVA_HOME/bin/java"
else
  JAVA=java
fi
......
# 尝试ssh启动zk
[hadoop@hadoop001 bin]$ ssh hadoop001 "$ZOOKEEPER_HOME/bin/zkServer.sh start"
JMX enabled by default
---------------java: -------------
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
# 上面结果显示未读取到环境变量JAVA_HOME  且下面结果中没有zk进程
[hadoop@hadoop001 bin]$ ps -ef | grep zookeeper
hadoop    4284  3989  0 15:58 pts/2    00:00:00 grep --color=auto zookeeper

# ⑧ 解决方案：
# 1.在zkEnv.sh中写死java路径
[hadoop@hadoop001 bin]$ vi zkEnv.sh
if [ "$JAVA_HOME" != "" ]; then
  JAVA="$JAVA_HOME/bin/java"
else
  JAVA=/usr/java/jdk1.8.0_40/bin/java
fi
# 2.将java环境变量配置到hadoop用户的 ~/.bashrc中
[hadoop@hadoop001 bin]$ vi ~/.bashrc
export JAVA_HOME=/usr/java/jdk1.8.0_40
export PATH=$JAVA_HOME/bin:$PATH
# 验证下是可以读取到的
[hadoop@hadoop001 bin]$ ssh hadoop001 "which java"
/usr/java/jdk1.8.0_40/bin/java
[hadoop@hadoop001 bin]$ ssh hadoop001 "$ZOOKEEPER_HOME/bin/zkServer.sh start"
JMX enabled by default
---------------java: /usr/java/jdk1.8.0_40------------- # 可以读取到
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
[hadoop@hadoop001 bin]$ jps
4507 Jps
4478 QuorumPeerMain # zk进程存在

# 对应的将~/.bashrc同步到另两台机器上面
[hadoop@hadoop001 bin]$ scp ~/.bashrc hadoop002:/home/hadoop/
.bashrc                                                 100%  306     0.3KB/s   00:00    
[hadoop@hadoop001 bin]$ scp ~/.bashrc hadoop003:/home/hadoop/
.bashrc                                                 100%  306     0.3KB/s   00:00 

3.2.2 补充ssh知识点

3.2.2.1 ssh执行远程命令和脚本

三种环境变量配置

全局： /etc/profile

个人： ~/.bash_profile 或者 ~/.bashrc

⚠️⚠️⚠️ bash模式：加载环境变量配置文件：个人~/.bashrc

3.3. 再次通过shell脚本启动集群

# 启动前先关闭
[hadoop@hadoop001 hadoop]$ ./stop_cluster.sh 

# 执行启动脚本
[hadoop@hadoop001 hadoop]$ ./start_cluster.sh 

# 执行jps.sh验证下  zk zkfc都已启动成功
[hadoop@hadoop001 hadoop]$ ./jps.sh 
----------hadoop001 process------------
5186 QuorumPeerMain
5330 NameNode
6373 JobHistoryServer
5625 JournalNode
6025 NodeManager
5434 DataNode
5916 ResourceManager
6445 Jps
5805 DFSZKFailoverController
                                                
----------hadoop002 process------------
4496 NodeManager
4659 ResourceManager
4292 JournalNode
4197 DataNode
4123 NameNode
4060 QuorumPeerMain
4413 DFSZKFailoverController
4717 Jps
                                                
----------hadoop003 process------------
3090 JournalNode
3186 NodeManager
2995 DataNode
3319 Jps
2938 QuorumPeerMain

4.关闭集群

[hadoop@hadoop001 hadoop]$ vi stop_cluster.sh 
#!/bin/bash -x

#stop history+yarn+hdfs
/home/hadoop/app/hadoop/sbin/mr-jobhistory-daemon.sh stop historyserver
ssh hadoop002 "/home/hadoop/app/hadoop/sbin/yarn-daemon.sh stop resourcemanager"

/home/hadoop/app/hadoop/sbin/stop-all.sh

#stop zk
ssh hadoop001 "$ZOOKEEPER_HOME/bin/zkServer.sh stop"
ssh hadoop002 "$ZOOKEEPER_HOME/bin/zkServer.sh stop"
ssh hadoop003 "$ZOOKEEPER_HOME/bin/zkServer.sh stop"

# 调用jps.sh脚本 查看进程
./jps.sh

exit 0

# 执行脚本
[hadoop@hadoop001 hadoop]$ ./stop_cluster.sh 
+ /home/hadoop/app/hadoop/sbin/mr-jobhistory-daemon.sh stop historyserver
stopping historyserver
+ ssh hadoop002 '/home/hadoop/app/hadoop/sbin/yarn-daemon.sh stop resourcemanager'
stopping resourcemanager
+ /home/hadoop/app/hadoop/sbin/stop-all.sh
This script is Deprecated. Instead use stop-dfs.sh and stop-yarn.sh
Stopping namenodes on [hadoop001 hadoop002]
hadoop001: stopping namenode
hadoop002: stopping namenode
hadoop001: stopping datanode
hadoop003: stopping datanode
hadoop002: stopping datanode
Stopping journal nodes [hadoop001 hadoop002 hadoop003]
hadoop001: stopping journalnode
hadoop002: stopping journalnode
hadoop003: stopping journalnode
Stopping ZK Failover Controllers on NN hosts [hadoop001 hadoop002]
hadoop002: stopping zkfc
hadoop001: stopping zkfc
stopping yarn daemons
stopping resourcemanager
hadoop002: stopping nodemanager
hadoop003: stopping nodemanager
hadoop001: stopping nodemanager
no proxyserver to stop
+ ssh hadoop001 '/home/hadoop/app/zookeeper/bin/zkServer.sh stop'
JMX enabled by default
---------------java: /usr/java/jdk1.8.0_40-------------
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Stopping zookeeper ... STOPPED
+ ssh hadoop002 '/home/hadoop/app/zookeeper/bin/zkServer.sh stop'
JMX enabled by default
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Stopping zookeeper ... STOPPED
+ ssh hadoop003 '/home/hadoop/app/zookeeper/bin/zkServer.sh stop'
JMX enabled by default
Using config: /home/hadoop/app/zookeeper/bin/../conf/zoo.cfg
Stopping zookeeper ... STOPPED
+ ./jps.sh
----------hadoop001 process------------
7132 Jps
                                                
----------hadoop002 process------------
5142 Jps
                                                
----------hadoop003 process------------
3483 Jps
                                                
+ exit 0