通过shell脚本优化Keepalived+Nginx高可用集群

问题描述

Keepalived不容易挂掉，容易挂掉的是Nginx，如果Nginx挂掉了依然可以通过Keepalived访问机器，但是访问不到Nginx服务。所以这里需要借助Keepalived的vrrp_script配置来调用自定义shell脚本，来检测Nginx是否挂掉，如果Nginx挂掉了，就启动它，打开失败就关闭Keepalived启用备用机

实现过程

编写shell脚本

在 / 目录下新建shell目录存放shell脚本文件

1	mkdir /shell

新建 .sh文件，命名为：nginx_check.sh，内容如下：（该脚本的功能为通过 ps -ef|grep -w nginx|grep -v grep|wc -l查看当前有多少个Nginx服务在运行，如果返回0说明Nginx服务没有运行，就启动Nginx，过2秒再查看是否启动成功，启动失败就停止Keepalived启用备用机）

#!/bin/bash

echo 'check Nginx'

count_nginx=`ps -ef|grep -w nginx|grep -v grep|wc -l`

echo $count_nginx

if [ $count_nginx -eq 0 ];then

    systemctl start nginx
    echo 'start Nginx'
    sleep 2

    if [ `ps -ef|grep -w nginx|grep -v grep|wc -l` -eq 0 ];then
        echo 'stop keepalived'
        systemctl stop keepalived
    fi  

fi

修改Keepalived配置

配置文件路径为：/etc/keepalived/keepalived.conf

添加节点：

vrrp_script check_nginx {
	script "/shell/nginx_check.sh"
	nterval 2
	weight -20
}

在vrrp_instance VI_1节点添加：

1
2
3

track_script {
	check_nginx
}

完整keepalived.conf如下：

! Configuration File for keepalived

global_defs {
   notification_email {
     acassen@firewall.loc
     failover@firewall.loc
     sysadmin@firewall.loc
   }
   notification_email_from Alexandre.Cassen@firewall.loc
   smtp_server 192.168.200.1
   smtp_connect_timeout 30
   router_id KEEPALIVED_NGINX_MASTER
   vrrp_skip_check_adv_addr
   # vrrp_strict
   vrrp_garp_interval 0
   vrrp_gna_interval 0
}

vrrp_script check_nginx {
	script "/shell/nginx_check.sh"
	nterval 2
	weight -20
}

vrrp_instance VI_1 {
    state MASTER
    interface ens33
    virtual_router_id 51
    priority 100
    advert_int 1
    authentication {
        auth_type PASS
        auth_pass 1111
    }
    track_script {
	    check_nginx
    }
    virtual_ipaddress {
        192.168.1.99
    }
}