Redis 단계 분석 센티널 센티널 클러스터

[root@Centos7 ~]# hostnamectl set-hostname master
[root@Centos7 ~]# su
[root@master ~]# systemctl stop firewalld
[root@master ~]# setenforce 0
setenforce: SELinux is disabled
[root@master ~]# mount /dev/cdrom /mnt/
mount: /dev/sr0 写保护，将以只读方式挂载
mount: /dev/sr0 已经挂载或 /mnt 忙
       /dev/sr0 已经挂载到 /mnt 上
[root@master ~]# ll
总用量 1928
-rw-------. 1 root root    1264 1月  12 18:27 anaconda-ks.cfg
-rw-r--r--  1 root root 1966337 6月   9 01:16 redis-5.0.4.tar.gz
[root@master ~]# tar xf redis-5.0.4.tar.gz
[root@master ~]# cd redis-5.0.4
[root@master redis-5.0.4]# make
[root@master redis-5.0.4]# mkdir -p /usr/local/redis
[root@master redis-5.0.4]# cp /root/redis-5.0.4/src/redis-server /usr/local/redis/
[root@master redis-5.0.4]# cp /root/redis-5.0.4/src/redis-cli /usr/local/redis/
[root@master redis-5.0.4]# cp /root/redis-5.0.4/redis.conf  /usr/local/redis/ 
[root@master redis-5.0.4]# vim /usr/local/redis/redis.conf   #修改
。。。。。。
  68 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  69 bind 192.168.100.202  #修改为本机地址，如果为127.0.0.1就只能本机访问
  70 
。。。。。。
  87 # are explicitly listed using the "bind" directive.
  88 protected-mode no  #关闭redis的保护模式，如果为yes的话其他客户端就无法连接到此服务器
  89 
。。。。。。
 135 # Note that Redis will write a pid file in /var/run/redis.pid when daemonized.
 136 daemonize yes  #开启redis的后台守护程序，即在redis开启之后是放在后台运行的
 137 
。。。。。。
 262 # Note that you must specify a directory here, not a file name.
 263 dir /usr/local/redis/rdb
 264 
。。。。。。
 506 #
 507 requirepass 123123  #去掉注释，修改redis的密码为123123
 508 
#保存退出
[root@slave2 redis-5.0.4]# mkdir /usr/local/redis/rdb
[root@master redis-5.0.4]# vim /etc/init.d/redis
#!/bin/sh
# chkconfig: 2345 80 90
# description: Start and Stop redis
#PATH=/usr/local/bin:/sbin:/usr/bin:/bin
REDISPORT=6379
EXEC=/usr/local/redis/redis-server
REDIS_CLI=/usr/local/redis/redis-cli
PIDFILE=/var/run/redis_6379.pid
CONF="/usr/local/redis/redis.conf"
AUTH="123123"
LISTEN_IP=$(netstat -utpln |grep redis-server |awk '{print $4}'|awk -F':' '{print $1}')

case "$1" in
    start)
        if [ -f $PIDFILE ]
        then
                echo "$PIDFILE exists, process is already running or crashed"
        else
                echo "Starting Redis server..."
                $EXEC $CONF
        fi
        if [ "$?"="0" ]
        then
              echo "Redis is running..."
        fi
        ;;
    stop)
        if [ ! -f $PIDFILE ]
        then
                echo "$PIDFILE does not exist, process is not running"
        else
                PID=$(cat $PIDFILE)
                echo "Stopping ..."
                $REDIS_CLI -h $LISTEN_IP -p $REDISPORT -a $AUTH SHUTDOWN
                while [ -x ${PIDFILE} ]
               do
                    echo "Waiting for Redis to shutdown ..."
                    sleep 1
                done
                echo "Redis stopped"
        fi
        ;;
   restart|force-reload)
        ${0} stop
        ${0} start
        ;;
  *)
    echo "Usage: /etc/init.d/redis {start|stop|restart|force-reload}" >&2
        exit 1
esac
[root@master redis-5.0.4]# chkconfig --add redis
[root@master redis-5.0.4]# chmod 755 /etc/init.d/redis
[root@master redis-5.0.4]# ln -s /usr/local/redis/* /usr/local/bin/
[root@master redis-5.0.4]# /etc/init.d/redis start 
Starting Redis server...
5233:C 09 Jun 2021 01:25:53.069 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
5233:C 09 Jun 2021 01:25:53.069 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=5233, just started
5233:C 09 Jun 2021 01:25:53.069 # Configuration loaded
Redis is running...
[root@master redis-5.0.4]# netstat -anpt | grep 6379
tcp        0      0 192.168.100.202:6379    0.0.0.0:*               LISTEN      5234/redis-server 1

******（1）Master配置
[root@master redis-5.0.4]# vim /usr/local/redis/redis.conf #修改
。。。。。。
 292 #
 293  masterauth 123123  #配置主服务器密码，哨兵有一个问题，就是当主服务器坏掉，切换到从服务器时，原来的主服务器可以正常运行之后，再次加入集群是加不进去的，因为哨兵没有配置主服务器的密码，所以无法连接，所以在使用哨兵集群时，要把每台的主服务器密码都配置上，每台redis的密码最好都一样
 294 
。。。。。。
 456 #
 457  min-replicas-to-write 1 #设置slave服务器的数量，当slave服务器少于这个数量时，Master主服务器会停止接收客户端的一切写请求
 458  min-replicas-max-lag 10 #设置主服务器和从服务器之间同步数据的超时时间，当超过此时间时，master主服务器会停止客户端的一切写操作，单位为秒
 459 #
。。。。。。
[root@master redis-5.0.4]# /etc/init.d/redis restart   #重启redis
Stopping ...
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
Redis stopped
Starting Redis server...
5291:C 09 Jun 2021 02:04:39.132 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
5291:C 09 Jun 2021 02:04:39.132 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=5291, just started
5291:C 09 Jun 2021 02:04:39.132 # Configuration loaded
Redis is running...

******（2）Slave1配置
[root@slave1 redis-5.0.4]# vim /usr/local/redis/redis.conf 
。。。。。。
 285 #
 286 replicaof 192.168.100.202 6379  #在从服务器上指定主服务器的ip和端口
 287 
。。。。。。
 292 #
 293 masterauth 123123  #指定主服务器上redis的密码
 294
。。。。。。
#保存退出
[root@slave redis-5.0.4]# /etc/init.d/redis restart  #重启服务
Stopping ...
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
Redis stopped
Starting Redis server...
5304:C 09 Jun 2021 02:11:32.241 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
5304:C 09 Jun 2021 02:11:32.241 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=5304, just started
5304:C 09 Jun 2021 02:11:32.241 # Configuration loaded
Redis is running...

******（3）Slave2配置
[root@slave2 redis-5.0.4]# vim /usr/local/redis/redis.conf 
。。。。。。
 286  replicaof 192.168.100.204 6379
 287 
 288 # If the master is password protected (using the "requirepass" configuration
 289 # directive below) it is possible to tell the replica to authenticate before
 290 # starting the replication synchronization process, otherwise the master will
 291 # refuse the replica request.
 292 #
 293  masterauth 123123
 294 
。。。。。。
#保存退出
[root@slave2 redis-5.0.4]# /etc/init.d/redis restart 
Stopping ...
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
Redis stopped
Starting Redis server...
5253:C 09 Jun 2021 17:50:25.680 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
5253:C 09 Jun 2021 17:50:25.680 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=5253, just started
5253:C 09 Jun 2021 17:50:25.680 # Configuration loaded
Redis is running...

******（3）验证主从是否成功
[root@master ~]# redis-cli -h 192.168.100.202 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.202:6379> set aaa bbb
OK
192.168.100.202:6379> set bbb ccc 
OK
192.168.100.202:6379> keys *
1) "aaa"
2) "bbb"

[root@slave1 ~]# redis-cli -h 192.168.100.203 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.203:6379> keys *
1) "bbb"
2) "aaa"
192.168.100.203:6379> set ttt fff
(error) READONLY You can't write against a read only replica.  #从服务器无法写入数据

[root@slave2 redis-5.0.4]# redis-cli -h 192.168.100.204 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.204:6379> keys *
1) "aaa"
2) "bbb"
192.168.100.204:6379> set ggg aaa
(error) READONLY You can't write against a read only replica.

#主从配置完成

******（1）在master上配置sentinel哨兵
[root@master ~]# cp redis-5.0.4/src/redis-sentinel /usr/local/redis/  #复制哨兵启动脚本
[root@master ~]# cp redis-5.0.4/sentinel.conf /usr/local/redis/  #复制哨兵配置文件
[root@master ~]# mkdir -p /var/redis/data  #创建日志文件存放位置	
[root@master ~]# vim /usr/local/redis/sentinel.conf   #修改哨兵配置文件
。。。。。。
 21 port 26379  #指定端口默认为26379
 22 
 23 # By default Redis Sentinel does not run as a daemon. Use 'yes' if you need it.
 24 # Note that Redis will write a pid file in /var/run/redis-sentinel.pid when
 25 # daemonized.
 26 daemonize yes  #yes为放在后台运行，使用no放在前台运行可以看到主从切换时候的信息
 27 
。。。。。。
 64 # unmounting filesystems.
 65 dir /var/redis/data  #指定日志存放位置，就是刚才创建的路径
 66 
。。。。。。
 83 # The valid charset is A-z 0-9 and the three characters ".-_".
 84 sentinel monitor mymaster 192.168.100.202  6379 1  #指定用户为mymaster，ip为202，端口为6379，1表示当有一台master出现故障时，就进行切换
 85 
 86 # sentinel a
。。。。。。
112 # Default is 30 seconds.
113 sentinel down-after-milliseconds mymaster 3000  #指定master的失效时间，单位为毫秒3000为3秒，表示master超过3秒没响应就判定为故障
114 
。。。。。。
145 # Default is 3 minutes.
146 sentinel failover-timeout mymaster 180000  #切换操作完成的超时时间，单位为毫秒180000为180秒，在主从切换超过这个时间就判定为切换失败
147 
148 # SCRIPTS EXE
。。。。。。
102 #
103  sentinel auth-pass mymaster 123123  #连接master和slave的密码
104 sentinel config-epoch mymaster  1  #切换后最多有多少节点可以于新的master进行同步数据
105 
#保存退出
[root@master ~]# /usr/local/redis/redis-sentinel /usr/local/redis/sentinel.conf  #启动哨兵
1118:X 09 Jun 2021 18:09:29.027 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
1118:X 09 Jun 2021 18:09:29.027 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=1118, just started
1118:X 09 Jun 2021 18:09:29.027 # Configuration loaded
[root@master ~]# netstat -anpt | grep 26379
tcp        0      0 0.0.0.0:26379           0.0.0.0:*               LISTEN      1119/redis-sentinel 
tcp6       0      0 :::26379                :::*                    LISTEN      1119/redis-sentinel 
[root@master ~]# kill -9 1119  #先关闭哨兵
[root@master ~]# netstat -anpt | grep 26379
[root@master ~]# sed -i '26s/yes/no/g' /usr/local/redis/sentinel.conf  #修改为前台启动
[root@master ~]# /usr/local/redis/redis-sentinel /usr/local/redis/sentinel.conf  #再次开启哨兵，稍等一段时间会有提示
1129:X 09 Jun 2021 18:11:02.585 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
1129:X 09 Jun 2021 18:11:02.585 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=1129, just started
1129:X 09 Jun 2021 18:11:02.585 # Configuration loaded
1129:X 09 Jun 2021 18:11:02.586 * Increased maximum number of open files to 10032 (it was originally set to 1024).
                _._                                                  
           _.-``__ ''-._                                             
      _.-``    `.  `_.  ''-._           Redis 5.0.4 (00000000/0) 64 bit
  .-`` .-".  "\/    _.,_ ''-._                                   
 (    '      ,       .-`  | `,    )     Running in sentinel mode
 |`-._`-...-` __...-.``-._|'` _.-'|     Port: 26379
 |    `-._   `._    /     _.-'    |     PID: 1129
  `-._    `-._  `-./  _.-'    _.-'                                   
 |`-._`-._    `-.__.-'    _.-'_.-'|                                  
 |    `-._`-._        _.-'_.-'    |           http://redis.io        
  `-._    `-._`-.__.-'_.-'    _.-'                                   
 |`-._`-._    `-.__.-'    _.-'_.-'|                                  
 |    `-._`-._        _.-'_.-'    |                                  
  `-._    `-._`-.__.-'_.-'    _.-'                                   
      `-._    `-.__.-'    _.-'                                       
          `-._        _.-'                                           
              `-.__.-'                                               

1129:X 09 Jun 2021 18:11:02.586 # WARNING: The TCP backlog setting of 511 cannot be enforced because /proc/sys/net/core/somaxconn is set to the lower value of 128.
1129:X 09 Jun 2021 18:11:02.586 # Sentinel ID is fce7776020cf12792fd239f6f9d34f2d3fdef98c
1129:X 09 Jun 2021 18:11:02.586 # +monitor master mymaster 192.168.100.202 6379 quorum 1
1129:X 09 Jun 2021 18:18:04.434 * +reboot slave 192.168.100.204:6379 192.168.100.204 6379 @ mymaster 192.168.100.202 6379  #看到新增两条消息，从服务器增加了203和204主服务器时202
1129:X 09 Jun 2021 18:18:14.478 * +reboot slave 192.168.100.203:6379 192.168.100.203 6379 @ mymaster 192.168.100.202 6379

#哨兵配置完成

******（1）把master服务器在开启一个终端，在新开启的终端中关闭redis，测试是否可以主从切换
[root@master ~]# /etc/init.d/redis stop 
Stopping ...
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
Redis stopped

******（2）切换到开启哨兵的终端，查看新弹出的信息
1129:X 09 Jun 2021 18:20:36.588 # +failover-end master mymaster 192.168.100.202 6379
1129:X 09 Jun 2021 18:20:36.588 # +switch-master mymaster 192.168.100.202 6379 192.168.100.203 6379
1129:X 09 Jun 2021 18:20:36.588 * +slave slave 192.168.100.204:6379 192.168.100.204 6379 @ mymaster 192.168.100.203 6379  #发现主服务器变成了203
1129:X 09 Jun 2021 18:20:36.588 * +slave slave 192.168.100.202:6379 192.168.100.202 6379 @ mymaster 192.168.100.203 6379
1129:X 09 Jun 2021 18:20:39.607 # +sdown slave 192.168.100.202:6379 192.168.100.202 6379 @ mymaster 192.168.100.203 6379‘

******（3）在203上测试主从复制是否可以正常同步
[root@slave1 ~]# redis-cli -h 192.168.100.203 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.203:6379> keys *
1) "aaa"
2) "bbb"
192.168.100.203:6379> set yyy aaa
OK
192.168.100.203:6379> keys *
1) "yyy"
2) "aaa"
3) "bbb"

[root@slave2 redis-5.0.4]# redis-cli -h 192.168.100.204 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.204:6379> keys *  #发现同步成功
1) "yyy"
2) "bbb"
3) "aaa"

******（4）此时重新开启202的redis，并且查看哨兵的提示消息
[root@master ~]# /etc/init.d/redis start 
Starting Redis server...
1167:C 09 Jun 2021 18:23:39.756 # oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo
1167:C 09 Jun 2021 18:23:39.756 # Redis version=5.0.4, bits=64, commit=00000000, modified=0, pid=1167, just started
1167:C 09 Jun 2021 18:23:39.756 # Configuration loaded
Redis is running...

1129:X 09 Jun 2021 18:23:50.324 * +convert-to-slave slave 192.168.100.202:6379 192.168.100.202 6379 @ mymaster 192.168.100.203 6379   #提示增加了一台slave

******（5）在202的新终端上查看redis的数据是否成功同步
[root@master ~]# redis-cli -h 192.168.100.202 -a 123123
Warning: Using a password with '-a' or '-u' option on the command line interface may not be safe.
192.168.100.202:6379> keys *  #发现已经成功同步
1) "bbb"
2) "aaa"
3) "yyy"

#测试故障切换缓存，发现在master主机出现故障然后重新连接到集群后，master角色不会进行转移

#把哨兵放在前台运行时，日志信息会直接输出到终端上，放到后台运行时，日志会写到指定的路径中
+reset-master <instance details>   #当master被重置时.
+slave <instance details>  #当检测到一个slave并添加进slave列表时.
+failover-state-reconf-slaves <instance details> #Failover状态变为reconf-slaves状态时
+failover-detected <instance details> #当failover发生时
+slave-reconf-sent <instance details> #sentinel发送SLAVEOF命令把它重新配置时
+slave-reconf-inprog <instance details> #slave被重新配置为另外一个master的slave，但数据复制还未发生时。
+slave-reconf-done <instance details> #slave被重新配置为另外一个master的slave并且数据复制已经与master同步时。
-dup-sentinel <instance details> #删除指定master上的冗余sentinel时,当一个sentinel重新启动时，可能会发生这个事件
+sentinel <instance details> #当master增加了一个sentinel时。
+sdown <instance details> #进入SDOWN状态时;
-sdown <instance details> #离开SDOWN状态时。
+odown <instance details> #进入ODOWN状态时。
-odown <instance details> #离开ODOWN状态时。
+new-epoch <instance details>  #当前配置版本被更新时。
+try-failover <instance details> #达到failover条件，正等待其他sentinel的选举。
+elected-leader <instance details> #被选举为去执行failover的时候。
+failover-state-select-slave <instance details> #开始要选择一个slave当选新master时。
no-good-slave <instance details> #没有合适的slave来担当新master
selected-slave <instance details> #找到了一个适合的slave来担当新master
failover-state-send-slaveof-noone <instance details> #当把选择为新master的slave的身份进行切换的时候。
failover-end-for-timeout <instance details>   #failover由于超时而失败时。
failover-end <instance details> #failover成功完成时。
switch-master <master name> <oldip> <oldport> <newip> <newport> #当master的地址发生变化时。通常这是客户端最感兴趣的消息了。
+tilt #进入Tilt模式。
-tilt #退出Tilt模式。