Keepalived搭建双机热备监控Nginx实战

一、Keepalived、Nginx服务安装搭建

Keepalived高可用集群、安装

运维之道 | 企业级Nginx环境搭建

二、双机热备监控Nginx

配置Keepalived

• 配置Keepalived-Master服务器文件

! Configuration File for keepalived

global_defs {
        router_id NodeA 
}

vrrp_instance VI_1 {
    state Master
    interface ens33
    virtual_router_id 51
    priority 100
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 1111
    }
    virtual_ipaddress {
        192.168.182.111/24
    }
}

• 配置Keepalived-BACKUP服务器文件

! Configuration File for keepalived

global_defs {
        router_id NodeB
}

vrrp_instance VI_1 {
    state BACKUP
    interface ens33
    virtual_router_id 51
    priority 90
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 1111
    }
    virtual_ipaddress {
        192.168.182.111/24
    }
}

Keepalived服务

• 启动Master节点和BACKUP节点Keepalived服务

[root@localhost ~]# systemctl start keepalived

• 通过ip a 命令可以看到192.168.182.111/24绑定到了Master 节点ens33上

[root@localhost sh]# ip a | grep ens33
2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000
    inet 192.168.182.131/24 brd 192.168.182.255 scope global noprefixroute ens33
    inet 192.168.182.111/24 scope global secondary ens33

• 查看Master节点日志（会广播ARRP消息）

[root@localhost ~]# tail -fn 10 /var/log/messages

Jan  5 16:06:54 localhost Keepalived_vrrp[16718]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:06:54 localhost Keepalived_vrrp[16718]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:06:54 localhost Keepalived_vrrp[16718]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:06:54 localhost Keepalived_vrrp[16718]: Sending gratuitous ARP on ens33 for 192.168.182.111

• 查看BACKUP节点日志（会广播ARRP消息）

Jan  5 16:02:19 localhost Keepalived_vrrp[15610]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:02:19 localhost Keepalived_vrrp[15610]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:02:19 localhost Keepalived_vrrp[15610]: Sending gratuitous ARP on ens33 for 192.168.182.111
Jan  5 16:10:01 localhost systemd: Started Session 45 of user root.

监控Nginx服务

• 编写Master节点测试页面

[root@localhost ~]# echo "I am RealServer1 192.168.182.130" > /var/www/html/index.html

• 编写BACKUP节点测试页面

[root@localhost ~]# echo "I am RealServer2 192.168.182.131" > /var/www/html/index.html

• 重启Master、BACKUP节点Nginx服务

[root@localhost ~]# systemctl restart nginx

测试1：开启Master节点Keepalived服务，此时外界访问测试界面则为Master节点测试页面

[root@Master ~]# systemctl start keepalived

[root@Master ~]# ip a |grep ens33
2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000
    inet 192.168.182.130/24 brd 192.168.182.255 scope global noprefixroute ens33
    inet 192.168.182.111/24 scope global secondary ens33

测试2：开启BACKUP节点Keepalived服务，关闭Master节点，此时外界访问测试界面则为BACKUP节点测试页面

[root@BACKUP ~]# systemctl start keepalived

[root@BACKUP ~]# ip a |grep ens33
2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000
    inet 192.168.182.131/24 brd 192.168.182.255 scope global noprefixroute ens33
    inet 192.168.182.111/24 scope global secondary ens33

三、WEB池（脚本故障自动转移服务器）

• Master节点服务器配置WEB池

在原有的命令配置下继续添加以下内容：

virtual_server 192.168.182.111 80 {    #虚拟服务器VIP地址和端口
    delay_loop 6                       #健康检查的间隔时间（秒）
    lb_algo rr                         #轮询调度算法
    lb_kind DR                         #直接路由群集工作模式
    persistence_timeout 50             #连接保持时间（秒）不启动在前面加（！）即可
    protocol TCP                       #采用TCP协议
 
real_server 192.168.182.130 80 {       #第一个WEB节点地址和端口
        weight 1                       #节点权重
        TCP_CHECK {                    #健康检查方式
            connect_port 80            #检查的目录端口
            connect_timeout 3          #连接超时（秒）
            nb_get_retry 3             #重试次数
            delay_before_retry 3       #重试间隔（秒）
        } 
      }
      
real_server 192.168.182.132 80 {       #第二个web节点的地址、端口和部分信息
        weight 1
        TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
      }
    }
  }

• BACKUP节点服务器配置WEB池

在原有的命令配置下继续添加以下内容：

virtual_server 192.168.182.111 80 {
    delay_loop 6
    lb_algo rr
    lb_kind DR
    persistence_timeout 50
    protocol TCP
 
real_server 192.168.182.133 80 {
        weight 1
        TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
        } 
      }
      
real_server 192.168.182.134 80 {
        weight 1
        TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
      }
    }
  }

• 主服务上编写脚本，实现全自动化主从故障切换

[root@localhost ~]#vim /etc/keepalived/keepalived.sh

#!/bin/bash
counter=$(ps -C Nginx --no-heading | wc -l )
if [ "${counter}"="0" ];then
systemctl start Nginx
sleep 5
counter=$(ps -C Nginx --no-heading | wc -l )
if [ "${counter}"="0" ];then
systemctl stop keepalived
  fi
fi

#脚本意思是检测Nginx服务，如果等于0，那么就直接把keepalived停止掉

[root@localhost ~]#chmod +x /etc/keepalived/keepalived.sh

• 把脚本应用到主服务器的keepalived配置文件里

.............
global_defs {
   router_id LVS_DEVEL_R1
}
 
vrrp_script chk_port {                #应用脚本
    script "/etc/keepalived/keepalived.sh"
    interval 2
    weight 2
}
 
.............
   authentication {
        auth_type PASS
        auth_pass 1111
    }
 
track_script {                         #跟踪脚本
chk_port
 }
.............