目錄一、什麼是哨兵模式1、為什麼需要哨兵機制2、哨兵架構拓撲3、Redis Sentinel的功能：二、搭建哨兵架構1、涉及主機2、拓撲結構3、設置一主兩從4、master伺服器狀態5、編輯哨兵的配置文件6、啟動哨兵7、驗證哨兵埠8、查看哨兵日誌9、驗證當前sentinel狀態三、故障轉移1、re ...
目錄
一、什麼是哨兵模式
Redis Sentinel 是一個分散式系統，為Redis提供高可用性解決方案。可以在一個架構中運行多個 Sentinel 進程(progress)， 這些進程使用流言協議 (gossip protocols) 來接收關於主伺服器是否下線的信息， 並使用投票協議(agreement protocols)來決定是否執行自動故障遷移，以及選擇哪個從伺服器作為新的主伺服器。
1、為什麼需要哨兵機制
在沒有哨兵機制的情況下，Redis主從集群中若主節點發生故障，需要運維人員手動介入，識別故障、選擇合適的從節點提升為主節點，並更新所有客戶端的連接配置，使其指向新的主節點。這一過程既繁瑣又耗時，尤其是在緊急情況下可能導致服務長時間不可用。
2、哨兵架構拓撲
3、Redis Sentinel的功能：
- 對Redis節點進行監控
- 故障判斷
- 故障轉移
- 故障通知
二、搭建哨兵架構
1、涉及主機
| 角色 | 主機名 | IP地址 |
|---|---|---|
| 主節點 | master | 192.168.112.40 |
| 從節點 | slave2 | 192.168.112.50 |
| 從節點 | slave1 | 192.168.112.60 |
2、拓撲結構
3、設置一主兩從
所有節點：
[root@master ~]# vim /apps/redis/etc/redis.conf
bind 0.0.0.0
masterauth centos
requirepass centos
[root@master ~]# echo -e "net.core.somaxconn = 1024\nvm.overcommit_memory = 1" >> /etc/sysctl.conf
[root@master ~]# sysctl -p
net.core.somaxconn = 1024
vm.overcommit_memory = 1
net.core.somaxconn = 1024
vm.overcommit_memory = 1
[root@master ~]# echo never > /sys/kernel/mm/transparent_hugepage/enabled
[root@master ~]# echo "echo never > /sys/kernel/mm/transparent_hugepage/enabled" >> /etc/rc.d/rc.local
[root@master ~]# chmod +x /etc/rc.d/rc.local
[root@master ~]# systemctl restart redis
slave節點：
[root@slave1 ~]# echo "replicaof 192.168.112.40 6379" >> /apps/redis/etc/redis.conf
[root@slave1 ~]# systemctl restart redis
[root@slave2 ~]# echo "replicaof 192.168.112.40 6379" >> /apps/redis/etc/redis.conf
[root@slave2 ~]# systemctl restart redis
4、master伺服器狀態
[root@master ~]# redis-cli -a centos --no-auth-warning
127.0.0.1:6379> info replication
# Replication
role:master
connected_slaves:2
slave0:ip=192.168.112.60,port=6379,state=online,offset=518,lag=0
slave1:ip=192.168.112.50,port=6379,state=online,offset=518,lag=0
master_replid:4f28bb9953f9850a433ae73a943fa02e607f691f
master_replid2:0000000000000000000000000000000000000000
master_repl_offset:518
second_repl_offset:-1
repl_backlog_active:1
repl_backlog_size:1048576
repl_backlog_first_byte_offset:1
repl_backlog_histlen:518
5、編輯哨兵的配置文件
Sentinel實際上是一個特殊的redis伺服器,有些redis指令支持,但很多指令並不支持.預設監聽在26379/tcp埠
哨兵可以不和Redis伺服器部署在一起，但一般部署在一起，所有redis節點使用相同的配置文件
如果是編譯安裝，在源碼目錄有sentinel.conf，複製到安裝目錄即可
master節點：
[root@master ~]# cp redis-5.0.9/sentinel.conf /apps/redis/etc/
[root@master ~]# egrep -v "^#|^$" /apps/redis/etc/sentinel.conf
port 26379
daemonize no
pidfile /var/run/redis-sentinel.pid
logfile ""
dir /tmp #工作目錄
sentinel monitor mymaster 127.0.0.1 6379 2
#指定當前mymaster集群中master伺服器的地址和埠
#2為法定人數限制(quorum)，即有幾個sentinel認為master down了就進行故障轉移，一般此值是所有sentinel節點(一般總數是>=3的 奇數,如:3,5,7等)的一半以上的整數值，比如，總數是3，即3/2=1.5，取整為2,是master的ODOWN客觀下線的依據
sentinel auth-pass <master-name> <password>
#mymaster集群中master的密碼，註意此行要在上面行的下麵
sentinel down-after-milliseconds mymaster 30000
#(SDOWN)判斷mymaster集群中所有節點的主觀下線的時間，單位：毫秒，建議30000
sentinel parallel-syncs mymaster 1
#發生故障轉移後，同時向新master同步數據的slave數量，數字越小總同步時間越長，但可以減輕新master的負載壓力
sentinel failover-timeout mymaster 180000
#所有slaves指向新的master所需的超時時間，單位：毫秒
sentinel deny-scripts-reconfig yes
#禁止修改腳本
修改所有的哨兵伺服器配置文件
修改配置文件前記得備份
#所有的哨兵伺服器都是如下配置，以master為例
[root@master ~]# egrep -v "^#|^$" /apps/redis/etc/sentinel.conf
port 26379
daemonize no
pidfile /apps/redis/run/redis-sentinel.pid
logfile "/apps/redis/log/sentinel.log"
dir /tmp
sentinel monitor mymaster 192.168.112.40 6379 2
sentinel auth-pass mymaster centos
sentinel down-after-milliseconds mymaster 30000
sentinel parallel-syncs mymaster 1
sentinel failover-timeout mymaster 180000
sentinel deny-scripts-reconfig yes
6、啟動哨兵
所有主機
#添加哨兵服務
cat << EOF > /lib/systemd/system/redis-sentinel.service
[Unit]
Description=Redis Sentinel
After=network.target
After=network-online.target
Wants=network-online.target
[Service]
ExecStart=/apps/redis/bin/redis-sentinel /apps/redis/etc/sentinel.conf --supervised systemd
ExecStop=/usr/libexec/redis-shutdown redis-sentinel
Type=notify
User=redis
Group=redis
RuntimeDirectory=redis
RuntimeDirectoryMode=0755
[Install]
WantedBy=multi-user.target
EOF
[root@master ~]# chown redis.redis /apps/redis/etc/sentinel.conf
#重載配置文件
[root@master ~]# systemctl daemon-reload
# 確保每個哨兵主機myid不同
#在master上
[root@master ~]# systemctl daemon-reload
[root@master ~]# systemctl enable --now redis-sentinel
Created symlink from /etc/systemd/system/multi-user.target.wants/redis-sentinel.service to /usr/lib/systemd/system/redis-sentinel.service.
[root@master ~]# grep myid /apps/redis/etc/sentinel.conf
sentinel myid 331200834d2dbc801dfe3714051861683517b037
#在slave1上
[root@slave1 tmp]# systemctl daemon-reload
[root@slave1 tmp]# systemctl enable --now redis-sentinel
Created symlink from /etc/systemd/system/multi-user.target.wants/redis-sentinel.service to /usr/lib/systemd/system/redis-sentinel.service.
[root@slave1 tmp]# grep myid /apps/redis/etc/sentinel.conf
sentinel myid d67683381ceb20bf91fc965540bd88a76594b7f5
#在slave2上
[root@slave2 tmp]# systemctl daemon-reload
[root@slave2 tmp]# systemctl enable --now redis-sentinel
Created symlink from /etc/systemd/system/multi-user.target.wants/redis-sentinel.service to /usr/lib/systemd/system/redis-sentinel.service.
[root@slave2 tmp]# grep myid /apps/redis/etc/sentinel.conf
sentinel myid 4223fba33129fa40e8af93590900b2f3e5a8f81f
7、驗證哨兵埠
ss -tnl
8、查看哨兵日誌
[root@master ~]# tail /apps/redis/log/sentinel.log
1628:X 16 Apr 2024 09:43:19.697 # You requested maxclients of 10000 requiring at least 10032 max file descriptors.
1628:X 16 Apr 2024 09:43:19.697 # Server can't set maximum open files to 10032 because of OS error: Operation not permitted.
1628:X 16 Apr 2024 09:43:19.697 # Current maximum open files is 4096. maxclients has been reduced to 4064 to compensate for low ulimit. If you need higher maxclients increase 'ulimit -n'.
1628:X 16 Apr 2024 09:43:19.698 * Running mode=sentinel, port=26379.
1628:X 16 Apr 2024 09:43:19.702 # Sentinel ID is 331200834d2dbc801dfe3714051861683517b037
1628:X 16 Apr 2024 09:43:19.702 # +monitor master mymaster 192.168.112.40 6379 quorum 2
1628:X 16 Apr 2024 09:43:19.703 * +slave slave 192.168.112.50:6379 192.168.112.50 6379 @ mymaster 192.168.112.40 6379
1628:X 16 Apr 2024 09:43:19.703 * +slave slave 192.168.112.60:6379 192.168.112.60 6379 @ mymaster 192.168.112.40 6379
1628:X 16 Apr 2024 09:44:54.907 * +sentinel sentinel d67683381ceb20bf91fc965540bd88a76594b7f5 192.168.112.50 26379 @ mymaster 192.168.112.40 6379
1628:X 16 Apr 2024 09:45:47.791 * +sentinel sentinel 4223fba33129fa40e8af93590900b2f3e5a8f81f 192.168.112.60 26379 @ mymaster 192.168.112.40 6379
9、驗證當前sentinel狀態
master節點：
[root@master ~]# redis-cli -p 26379
127.0.0.1:26379> info sentinel
# Sentinel
sentinel_masters:1
sentinel_tilt:0
sentinel_running_scripts:0
sentinel_scripts_queue_length:0
sentinel_simulate_failure_flags:0
master0:name=mymaster,status=ok,address=192.168.112.40:6379,slaves=2,sentinels=3
在sentinel狀態中尤其是最後一行，涉及到masterIP是多少，有幾個slave，有幾個sentinels，必須是符合全部伺服器數量
三、故障轉移
1、redis sentinel故障轉移的步驟：
1.當某個master發生故障，多個sentinel會監控到這個異常，這些sentinel會按照一定規則從多個slave中選中一個做為新的master,並通知別的slave從新的master中同步數據
2.當某個slave轉換為新的master，sentinel會記錄新的master的地址信息和slave的地址信息，通知Redis cli
3.Redis cli接收到新的master和slave的信息，就會向新的master寫入數據，從slave中讀取數據
4.等到原來的master重啟之後，會變成新的master的slave,並從新的master同步數據
2、停止redis master
yum install -y psmisc
[root@master ~]# killall redis-server
3、查看各個節點哨兵信息
slave1：
[root@slave1 ~]# redis-cli -p 26379
127.0.0.1:26379> info sentinel
# Sentinel
sentinel_masters:1
sentinel_tilt:0
sentinel_running_scripts:0
sentinel_scripts_queue_length:0
sentinel_simulate_failure_flags:0
master0:name=mymaster,status=ok,address=192.168.112.60:6379,slaves=2,sentinels=3
slave2：
[root@slave2 ~]# redis-cli -p 26379
127.0.0.1:26379> info sentinel
# Sentinel
sentinel_masters:1
sentinel_tilt:0
sentinel_running_scripts:0
sentinel_scripts_queue_length:0
sentinel_simulate_failure_flags:0
master0:name=mymaster,status=ok,address=192.168.112.60:6379,slaves=2,sentinels=3
4、查看redis配置文件
[root@slave1 ~]# grep "^replicaof" /apps/redis/etc/redis.conf
replicaof 192.168.112.60 6379
[root@slave1 ~]# grep monitor /apps/redis/etc/sentinel.conf
sentinel monitor mymaster 192.168.112.60 6379 2
5、查看新master狀態
[root@slave2 ~]# redis-cli -a centos --no-auth-warning
127.0.0.1:6379> info replication
# Replication
role:master
connected_slaves:1
slave0:ip=192.168.112.50,port=6379,state=online,offset=392291,lag=1
master_replid:c647c550c9394542e4f43b5538b1bfc1f7d5fedd
master_replid2:b54e20a0f991557145e9df7367777e1da8256a6f
master_repl_offset:392434
second_repl_offset:238694
repl_backlog_active:1
repl_backlog_size:1048576
repl_backlog_first_byte_offset:1
repl_backlog_histlen:392434
6、恢復故障的原master重新加入redis集群
[root@master ~]# systemctl restart redis
[root@master ~]# ss -tnl
State Recv-Q Send-Q Local Address:Port Peer Address:Port
LISTEN 0 128 *:22 *:*
LISTEN 0 100 127.0.0.1:25 *:*
LISTEN 0 511 *:6379 *:*
LISTEN 0 511 *:26379 *:*
LISTEN 0 128 [::]:22 [::]:*
LISTEN 0 100 [::1]:25 [::]:*
LISTEN 0 511 [::]:26379 [::]:*
[root@master ~]# grep "^replicaof" /apps/redis/etc/redis.conf
replicaof 192.168.112.60 6379
[root@master ~]# redis-cli -a centos --no-auth-warning
127.0.0.1:6379> info replication
# Replication
role:slave
master_host:192.168.112.60
master_port:6379
master_link_status:up
master_last_io_seconds_ago:0
master_sync_in_progress:0
slave_repl_offset:446146
slave_priority:100
slave_read_only:1
connected_slaves:0
master_replid:c647c550c9394542e4f43b5538b1bfc1f7d5fedd
master_replid2:0000000000000000000000000000000000000000
master_repl_offset:446146
second_repl_offset:-1
repl_backlog_active:1
repl_backlog_size:1048576
repl_backlog_first_byte_offset:438489
repl_backlog_histlen:7658
四、sentinel運維
1、手動讓主節點下線
# 指定優先順序,值越小sentinel會優先將之選為新的master,默為值為100
[root@master ~]# vim /apps/redis/etc/redis.conf
replica-priority 10
[root@master ~]# systemctl restart redis
[root@master ~]# redis-cli -p 26379
127.0.0.1:26379> sentinel failover mymaster #手動發起哨兵切換
OK
127.0.0.1:26379> info sentinel
# Sentinel
sentinel_masters:1
sentinel_tilt:0
sentinel_running_scripts:0
sentinel_scripts_queue_length:0
sentinel_simulate_failure_flags:0
master0:name=mymaster,status=ok,address=192.168.112.40:6379,slaves=2,sentinels=3
