高可用keepalived

什么是高可用:

“高可用性”（High Availability）通常来描述一个系统经过专门的设计，从而减少停工时间，而保持其服务的高度可用性。（目的：减少停工时间）。

• 负载均衡服务器的高可用：

为了屏蔽负载均衡服务器的失效，需要建立一个备份机。主服务器和备份机上都运行High Availability监控程序，通过传送诸如“I am alive”这样的信息来监控对方的运行状况。当备份机不能在一定的时间内收到这样的信息时，它就接管主服务器的服务IP并继续提供服务

高可用集群：

• keepalived
• slb

对谁高可用？

对关键性业务做高可用（如lvs的调度器，主从数据库的主数据库）

keepalived

概念

起初是专为LVS负载均衡设计用来监控LVS各集群节点状态，后来加入VRRP协议。通过VRRP（Virtual Router RedundancyProtocol）虚拟路由器冗余协议，来保证个别节点宕机时，整个网络服务不间断运行。

功能

• 管理LVS负载均衡软件
• 实现LVS集群节点的健康检查
• 作为系统网络服务的高可用性（failover）

原理

基于keepalived的nginx负载均衡高可用实现

环境说明

系统	主机名	ip
rhel8	master	192.168.94.141
rhel8	slave	192.168.94.143

//主备防火墙selinux关闭，安装keepalived和nginx的包
systemctl stop firewalld.service 
setenforce 0
yum -y install keepalived nginx

//主备各修改网页内容，方便查看效果,设置开机自启
systemctl enable --now nginx
[root@master ~]# echo 'master'> /usr/share/nginx/html/index.html 
[root@slave ~]# echo 'slave'> /usr/share/nginx/html/index.html 

keepalived配置

master端配置

//编写脚本
[root@master ~]# mkdir /script/
[root@node1 script]# cd
[root@node1 ~]# cd /script/
[root@node1 script]# cat Ngchcek.sh 
#!/bin/bash
nginx_status=$(ps -ef|grep -Ev "grep|$0"|grep 'nginx'|wc -l)		#定义一个变量用于检测nginx进程数
if [ $nginx_status -lt 1 ];then	#判断进程数是否<1，是则停止keep
    systemctl stop keepalived
fi

[root@node1 script]# cat notify.sh 
#!/bin/bash
VIP=$2		#定义VIP变量为外部传进来的第二个参数
sendmail (){	#定义一个sendmail函数
	subject="${VIP}'s server keepalived state is translate"
	content="`date +'%F %T'`: `hostname`'s state change to master"	#定义主题，内容
	echo $content | mail -s "$subject" 1@2.com	#发送给指定邮箱
}
case "$1" in	#分支选择
  master)	#如果第一个参数是master
        nginx_status=$(ps -ef|grep -Ev "grep|$0"|grep 'nginx'|wc -l)
	if [ $nginx_status -lt 1 ];then	#判断进程数是否小于1
	systemctl start nginx	#成立则启动nginx
	fi
	sendmail	#调用sendmail函数
  ;;
  backup)	#第一个参数是备份的情况
        nginx_status=$(ps -ef|grep -Ev "grep|$0"|grep 'nginx'|wc -l)
	if [ $nginx_status -gt 0 ];then	#判断进程是否大于0
	    systemctl stop nginx	#成立则停止进程
	fi
  ;;
  *)
	  echo "Usage:$0 master|backup VIP"	#其他参数则输出正确语法
  ;;
esac

[root@master ~]# cat /etc/keepalived/keepalived.conf 
! Configuration File for keepalived

global_defs {
   router_id lb01 #全局定义路由id为lb01
}

vrrp_script nginx_check {	#VRRP脚本
    script "/script/check_n.sh"
    interval 10		#设置脚本检测间隔（秒）
    weight -20
}


vrrp_instance VI_1 {	#VRRP实例
    state MASTER	#状态为主（master）
    interface ens160	#本机网卡名
    virtual_router_id 51	#虚拟路由id
    priority 100	#优先级100
    advert_int 10	 #检查间隔,默认1秒 VRRP心跳包的发送周期	
    authentication { 	#认证
        auth_type PASS	#类型为密码
        auth_pass fxx	#设置密码
    }
    virtual_ipaddress {	#vip设置
        192.168.94.250
    }
    track_script {
        nginx_check
    }
   A notify_master "/script/notify.sh master 192.168.94.141"
    notify_backup "/script/notify.sh backup 192.168.94.143"

}

virtual_server 192.168.94.250 80 { #虚拟服务器设置
    delay_loop 6	#延迟回路6次
    lb_algo rr	#轮询
    lb_kind DR	#工作模式DR
    persistence_timeout 50	#持久性超时
    protocol TCP	#协议TCP

    real_server 192.168.94.141 80 {	#真实服务器设置
        weight 1	#权重1
	TCP_CHECK {
            connect_port 80	#访问端口80
            connect_timeout 3	#超时连接3次
            nb_get_retry 3	
            delay_before_retry 3
        }
    }
    real_server 192.168.94.143 80 {
        weight 1
	TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
        }
    }
}

//令keepalived服务开机自启
[root@master ~]# systemctl enable --now keepalived.service

//查看ip
[root@master ~]# ip a |grep ens160
2: ens160: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP group default qlen 1000
    inet 192.168.94.141/24 brd 192.168.94.255 scope global dynamic noprefixroute ens160
    inet 192.168.94.250/32 scope global ens160 #vip启动了

slave端配置

[root@slave ~]# cat /etc/keepalived/keepalived.conf
! Configuration File for keepalived
global_defs {
   router_id lb02	#路由id lb02
}

vrrp_instance VI_1 {
    state BACKUP
    interface ens160
    virtual_router_id 51
    priority 90
    nopreemt
    advert_int 10	 #检查间隔,默认1秒 VRRP心跳包的发送周期
    authentication {
        auth_type PASS
        auth_pass fxx
    }
    virtual_ipaddress {
        192.168.94.250
    }
    notify_master "/script/notify.sh master 192.168.94.141"
    notify_backup "/script/notify.sh backup 192.168.94.143"
}

virtual_server 192.168.94.250 80 {
    delay_loop 6
    lb_algo rr
    lb_kind DR
    persistence_timeout 50
    protocol TCP

    real_server 192.168.94.141 80 {
        weight 1
        TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
        }
    }

    real_server 192.168.94.143 80 {
        weight 1
        TCP_CHECK {
            connect_port 80
            connect_timeout 3
            nb_get_retry 3
            delay_before_retry 3
        }
    }
}

[root@slave ~]# mkdir /script
[root@master script]# scp /script/notify.sh root@node2:/script
notify.sh                  100%  583   562.4KB/s   00:00 
[root@slave ~]# systemctl enable --now keepalived.service 

测试验证

//保证salve端keep运行，nginx停止
[root@slave ~]# systemctl status keepalived.service |grep running
   Active: active (running) since Thu 2021-05-20 21:41:24 CST; 19min ago
[root@slave ~]# systemctl status nginx.service |grep dead
   Active: inactive (dead)

//保证master上二者都是启动的
[root@master ~]# systemctl status keepalived.service |grep running
   Active: active (running) since Thu 2021-05-20 21:41:24 CST; 19min ago
[root@master ~]# systemctl status nginx.service |grep running   
   Active: active (running) since Thu 2021-05-20 21:41:28 CST; 19min ago

访问vip

//模拟主nginx挂了
[root@master ~]# pkill nginx
[root@master ~]# systemctl status nginx.service 
● nginx.service - The nginx HTTP and reverse proxy server
   Loaded: loaded (/usr/lib/systemd/system/nginx.service; di>
   Active: inactive (dead)
   
//脚本检测没有nginx进程，触发条件停止keep
[root@master ~]# systemctl status keepalived.service 
● keepalived.service - LVS and VRRP High Availability Monitor
   Loaded: loaded (/usr/lib/systemd/system/keepalived.service;>
   Active: inactive (dead) since Thu 2021-05-20 22:04:55 CST; >
  Process: 1616 ExecStart=/usr/sbin/keepalived $KEEPALIVED_OPT>
 Main PID: 1617 (code=exited, status=0/SUCCESS)

再次访问vip

//查看从端发现nginx启动。
[root@slave ~]# systemctl status nginx.service 
● nginx.service - The nginx HTTP and reverse proxy server
   Loaded: loaded (/usr/lib/systemd/system/nginx.service; disabled; vendor p>
   Active: active (running) since Thu 2021-05-20 22:04:55 CST; 3min 53s ago

主恢复的情况

//启动主ngin和keep
[root@master ~]# systemctl start nginx.service 
[root@master ~]# systemctl start keepalived.service 

//发现从nginx挂了
[root@slave ~]# systemctl status nginx.service 
● nginx.service - The nginx HTTP and reverse proxy server
   Loaded: loaded (/usr/lib/systemd/system/nginx.service; disabled; vendor p>
   Active: failed (Result: timeout) since Thu 2021-05-20 22:13:05 CST; 1min >

访问vip