Keepalived+lvs实现高可用负载均衡双主模式

Keepalived一开始就是为lvs设计的,解决了单点服务器的故障问题,能保证服务不中断、稳定运行。(《keepalived在前一篇博客Nginx+keepalived实现高可用负载均衡的主从模式》http://legehappy.blog.51cto.com/13251607/1974468就已经介绍过了,这里不多介绍了)

Lvs是一种集群(Cluster)技术:采用IP负载均衡技术和基于内容请求分发技术。调度器具有很好的吞吐率,将请求均衡地转移到不同的服务器上执行,且调度器自动屏蔽掉服务器的故障,从而将一组服务器构成一个高性能的、高可用的虚拟服务器。整个服务器集群的结构对客户是透明的,而且无需修改客户端和服务器端的程序。工作在四层,在内核空间工作,基于ipvs模块,不占用流量。

 

双机高可用方法目前分为两种:
1)双机主从模式即前端使用两台服务器,一台主服务器和一台热备服务器,正常情况下,主服务器绑定一个公网虚拟IP,提供负载均衡服务,热备服务器处于空闲状态;当主服务器发生故障时,热备服务器接管主服务器的公网虚拟IP,提供负载均衡服务;但是热备服务器在主机器不出现故障的时候,永远处于浪费状态,对于服务器不多的网站,该方案不经济实惠。
2)双机主主模式这种模式的效果很强大,即前端使用两台负载均衡服务器,互为主备,且都处于活动状态(这样达到不浪费服务器),同时各自绑定一个公网虚拟IP,提供负载均衡服务;当其中一台发生故障时,另一台接管发生故障服务器的公网虚拟IP(这时由非故障机器一台负担所有的请求)。这种方案,经济实惠,非常适合于当前架构环境。

                            461e1f29339195b10d775f72b633a048.png-wh_

一、环境介绍:

操作系统:

[root@centos-4 ~]# cat /etc/redhat-release

CentOS release 6.9 (Final)

服务器对应关系:

KA1:192.168.5.129 centos-1

KA2:192.168.5.128 centos-4

Vip1:192.168.5.200  129master/128backup

VIP2:192.168.5.210  128master/129backup

Web1:192.168.5.131 centos-2

Web2:192.168.5.132 centos-3

Client:192.168.5.140centos-5

二、环境安装:

安装依赖:

(在KA1和KA2机器上执行以下步骤)

[root@centos-4 ~]# yum -y install gcc pcre-devel zlib-devel openssl-devel
[root@centos-4~]# cd /usr/local/src/
[root@centos-4 src]# wget http://nginx.org/download/nginx-1.9.7.tar.gz


安装nginx

[root@centos-4 src]# tar -zvxfnginx-1.9.7.tar.gz 
[root@centos-4 src]# cd nginx-1.9.7
[root@centos-4 nginx-1.9.7]#./configure --prefix=/usr/local/nginx --user=nginx --group=nginx--with-http_ssl_module --with-http_flv_module --with-http_stub_status_module--with-http_gzip_static_module --with-pcre
[root@centos-4 nginx-1.9.7]# make &&make install
[root@centos-1 ~]# yum install -y keepalived
[root@centos-1 ~]# yum install –y ipvsadm

 

       (在web1服务器和web2服务器上安装nginx)

[root@centos-2~]# yum -y install gcc pcre-devel zlib-devel openssl-devel
[root@centos-2~]# cd /usr/local/src/
[root@centos-2 src]# wget http://nginx.org/download/nginx-1.9.7.tar.gz


安装nginx

[root@centos-2 src]# tar -zvxfnginx-1.9.7.tar.gz 
[root@centos-2 src]# cd nginx-1.9.7
[root@centos-2 nginx-1.9.7]# ./configure --prefix=/usr/local/nginx --user=nginx --group=nginx--with-http_ssl_module --with-http_flv_module --with-http_stub_status_module--with-http_gzip_static_module --with-pcre
[root@centos-2 nginx-1.9.7]# make &&make install


三、配置服务:

(所以服务器上配置)

[root@centos-1 ~]# cat/etc/sysconfig/selinux
SELINUX=disabled
[root@centos-1 ~]# getenforce
Disabled
[root@centos-1 ~]# service iptables stop

1、配置keepalived:

(KA1上操作)

[root@centos-1 ~]#cat /etc/keepalived/keepalived.conf
! Configuration File forkeepalived  
  
global_defs {  
   notification_email {  
     acassen@firewall.loc  
     #failover@firewall.loc  
     #sysadmin@firewall.loc  
   }  
   router_id LVS_DEVEL  
}  
 vrrp_script chk_http_port {        
    script "/opt/check_nginx.sh"   
    interval 2                     
    weight -5                       
    fall 2                   
    rise 1                  
}  
vrrp_instance VI_1{  
    state MASTER
    interface eth0  
    virtual_router_id 51  
    priority 100  
    advert_int 1  
    authentication {  
        auth_type PASS  
        auth_pass 1111  
    }  
    virtual_ipaddress {  
        192.168.5.200  
    }  
} 
 
vrrp_instance VI_2{  
    state BACKUP
    interface eth0
    virtual_router_id 50
    priority 90
    advert_int 1  
    authentication {  
        auth_type PASS
        auth_pass 1111  
    }
    virtual_ipaddress {
        192.168.5.210
    }
}
 
track_script {                     
   chk_http_port                 
}
}
virtual_server192.168.5.200 80 {       # 定义转移ip端口80的集群服务
    delay_loop 3
    lb_algo rr
    lb_kind DR
    protocol TCP
 sorry_server 127.0.0.1 80
    real_server 192.168.5.131 80 {      # 定义集群服务包含的RS 1
         weight 1                     # 权重为1
     HTTP_GET {                   # 定义RS1的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
    real_server 192.168.5.132 80 {      # 定义集群服务包含的RS 2
         weight 1                      # 权重为1
     HTTP_GET {                    # 定义RS2的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
}
virtual_server 192.168.5.21080 {       # 定义转移ip端口80的集群服务
    delay_loop 3
    lb_algo rr
    lb_kind DR
    protocol TCP
 sorry_server 127.0.0.1 80
    real_server 192.168.5.131 80 {      # 定义集群服务包含的RS 1
         weight 1                     # 权重为1
     HTTP_GET {                   # 定义RS1的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
    real_server 192.168.5.132 80 {      # 定义集群服务包含的RS 2
         weight 1                      # 权重为1
     HTTP_GET {                    # 定义RS2的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
}


(KA2上操作)

[root@centos-2 ~]# cat/etc/keepalived/keepalived.conf
! Configuration File forkeepalived  
  
global_defs {  
   notification_email {  
     acassen@firewall.loc  
     #failover@firewall.loc  
     #sysadmin@firewall.loc  
   }  
   router_id LVS_DEVEL  
}  
 vrrp_script chk_http_port {        
    script "/opt/check_nginx.sh"   
    interval 2                      
    weight -5                       
    fall 2                   
    rise 1                  
}  
vrrp_instance VI_1{  
    state BACKUP
    interface eth0  
    virtual_router_id 51  
    priority 100  
    advert_int 1  
    authentication {  
        auth_type PASS  
        auth_pass 1111  
    }  
    virtual_ipaddress {  
        192.168.5.200  
    }  
} 
 
vrrp_instance VI_2{  
    state MASTER
    interface eth0
    virtual_router_id 50
    priority 90
    advert_int 1  
    authentication {  
        auth_type PASS
        auth_pass 1111  
    }
    virtual_ipaddress {
        192.168.5.210
    }
}
 
track_script {                     
   chk_http_port                 
}
}
virtual_server192.168.5.200 80 {       # 定义转移ip端口80的集群服务
    delay_loop 3
    lb_algo rr
    lb_kind DR
    protocol TCP
 sorry_server 127.0.0.1 80
    real_server 192.168.5.131 80 {      # 定义集群服务包含的RS 1
         weight 1                     # 权重为1
     HTTP_GET {                   # 定义RS1的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
    real_server 192.168.5.132 80 {      # 定义集群服务包含的RS 2
         weight 1                      # 权重为1
     HTTP_GET {                    # 定义RS2的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
}
virtual_server192.168.5.210 80 {       # 定义转移ip端口80的集群服务
    delay_loop 3
    lb_algo rr
    lb_kind DR
    protocol TCP
 sorry_server 127.0.0.1 80
    real_server 192.168.5.131 80 {      # 定义集群服务包含的RS 1
         weight 1                     # 权重为1
     HTTP_GET {                   # 定义RS1的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
    real_server 192.168.5.132 80 {      # 定义集群服务包含的RS 2
         weight 1                      # 权重为1
     HTTP_GET {                    # 定义RS2的健康状态检测
         url {
           path /
           status_code 200
         }
         connect_timeout 1
         nb_get_retry 3
         delay_before_retry 1
      }
    }
}


 

编写一个监控nginx的脚本:

需要注意的是,要判断本机nginx是否正常,如果发现nginx不正常,重启之后,等待三秒在校验,任然失败则不尝试,关闭keepalived,发送邮件,其他主机此时接管VIP;

[root@centos-4~]# cat /opt/check_nginx.sh
#!/bin/bash
check=$(ps -C nginx --no-heading | wc -l)
IP=`ip addr | grep ens32 | awk  'NR==2{print $2}'| awk -F '/' '{print $1}'`
if [ "${check}" = "2" ]; then
        /usr/local/nginx/sbin/nginx
        sleep 2
        counter=$(ps -C nginx --no-heading|wc -l)
        if [ "${counter}" = "2" ]; then
        /etc/init.d/keepalived stop
       echo "check $IP nginx is down"| mail -s "check keepalived nginx" *********@qq.com
        fi
fi

(KA1一样的监控脚本)

 

2、在后端两台web服务器上配置vip默认路由和配置两台服务器的nginx(这就不演示怎样配置nginx了。):

(考虑到方便执行就编写了一个脚本:在web1和web2服务器上配置。)

[root@centos-2 ~]# cat lvs.sh
#!/bin/bash
#realserver config vip config route arp
#legehappy
Vip1=192.168.5.200
Vip2=192.168.5.210
source /etc/rc.d/init.d/functions
case $1 in
start)
        echo "config vip route arp" > /tmp/lvs1.txt
        /sbin/ifconfig lo:0 $Vip1 broadcast $Vip1 netmask 255.255.255.255 up
        /sbin/ifconfig lo:1 $Vip2 broadcast $Vip2 netmask 255.255.255.255 up
 
        echo "1" > /proc/sys/net/ipv4/conf/lo/arp_ignore
        echo "2" > /proc/sys/net/ipv4/conf/lo/arp_announce
        echo "1" > /proc/sys/net/ipv4/conf/all/arp_ignore
        echo "2" > /proc/sys/net/ipv4/conf/all/arp_announce
       route add -host $Vip1 dev lo:0
       route add -host $Vip2 dev lo:1
;;
stop)
        echo "deletevip route arp" > /tmp/lvs2.txt
       /sbin/ifconfig lo:0 down
        echo"0" > /proc/sys/net/ipv4/conf/lo/arp_ignore
        echo"0" > /proc/sys/net/ipv4/conf/lo/arp_announce
        echo"0" > /proc/sys/net/ipv4/conf/all/arp_ignore
        echo"0" > /proc/sys/net/ipv4/conf/all/arp_announce
       route del -host $Vip1 dev lo:0
       route del -host $Vip2 dev lo:1
 
;;
*)
        echo"Usage: $0 (start | stop)"
exit 1
esac

(两台后端配置web服务nginx的页面信息)

[root@centos-2 ~]# curl 192.168.5.131

10.2

[root@centos-3 ~]# curl 192.168.5.132

10.3

3、在两台前端服务器上启动keepalived服务,对于192.168.5.200的vip centos-1是master/192.168.5.210的vip centos-1是backup。

[root@centos-1 ~]#service keepalived start
[root@centos-4 ~]# service keepalived start

查看日志文件:

[root@centos-1 ~]# cat /var/log/messages

Oct 19 22:00:22 centos-1 Keepalived_vrrp[46184]: VRRP_Instance(VI_2)Sending gratuitous ARPs on eth0 for 192.168.5.210

Oct 19 22:00:22 centos-1 Keepalived_healthcheckers[46183]: Netlinkreflector reports IP 192.168.5.210 added

Oct 19 22:00:24 centos-1 Keepalived_vrrp[46184]: VRRP_Instance(VI_1)Sending gratuitous ARPs on eth0 for 192.168.5.200

Oct 19 22:00:27 centos-1 Keepalived_vrrp[46184]: VRRP_Instance(VI_2)Sending gratuitous ARPs on eth0 for 192.168.5.210

(因为KA1先启动keepalived服务所以两个vip都会在KA1上,但第二台keepaliver服务起来后vip2就会被KA2抢占回来。)

[root@centos-4 ~]# cat /var/log/messages

Oct 19 22:01:38 centos-4 Keepalived_healthcheckers[15009]: Netlinkreflector reports IP 192.168.5.210 added

Oct 19 22:01:38 centos-4 avahi-daemon[1513]: Registering new addre***ecord for 192.168.5.210 on eth0.IPv4.

Oct 19 22:01:38 centos-4 Keepalived_vrrp[15010]: VRRP_Instance(VI_2)Sending gratuitous ARPs on eth0 for 192.168.5.210

Oct 19 22:01:43 centos-4 Keepalived_vrrp[15010]: VRRP_Instance(VI_2)Sending gratuitous ARPs on eth0 for 192.168.5.210

查看ip addr:

[root@centos-1 keepalived]# ip add

2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdiscpfifo_fast state UP qlen 1000

    link/ether00:0c:29:0d:f3:5d brd ff:ff:ff:ff:ff:ff

    inet 192.168.5.129/24 brd192.168.5.255 scope global eth0

    inet 192.168.5.200/32scope global eth0

 

 [root@centos-4 keepalived]#ip addr

2: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdiscpfifo_fast state UP qlen 1000

    link/ether00:50:56:3a:84:30 brd ff:ff:ff:ff:ff:ff

    inet 192.168.5.128/24 brd192.168.5.255 scope global eth0

         inet 192.168.5.210/32 scope global eth0

(两台KA1和KA2服务器重启nginx、keepalived服务)

[root@centos-1~]# /usr/local/nginx/sbin/nginx -t
nginx:the configuration file /usr/local/nginx/conf/nginx.conf syntax is ok
nginx:configuration file /usr/local/nginx/conf/nginx.conf test is successful ###检查配置文件没问题后再执行重启nginx。
[root@centos-1~]# /usr/local/nginx/sbin/nginx -s reload
 
[root@centos-4~]# /usr/local/nginx/sbin/nginx -t
nginx:the configuration file /usr/local/nginx/conf/nginx.conf syntax is ok
nginx:configuration file /usr/local/nginx/conf/nginx.conf test is successful
[root@centos-4~]# /usr/local/nginx/sbin/nginx -s reload
[root@centos-1~]# service keepalived restart
停止keepalived:                                          [确定]
正在启动keepalived:                                      [确定]
[root@centos-4~]# service keepalived restart
停止keepalived:                                         [确定]
正在启动keepalived:                                      [确定]

 

四、测试:

验证方法(保证从负载均衡器本机到后端真实服务器之间能正常通信)

(1)、先测试完成后的效果访问vip1、vip2

Vip1:

[root@centos-5~]# curl 192.168.5.200

10.2

[root@centos-5~]# curl 192.168.5.200

10.3

[root@centos-5~]# curl 192.168.5.200

10.2

[root@centos-5~]# curl 192.168.5.200

10.3

Vip2:

[root@centos-5~]# curl 192.168.5.210

10.3

[root@centos-5~]# curl 192.168.5.210

10.2

[root@centos-5~]# curl 192.168.5.210

10.3

[root@centos-5~]# curl 192.168.5.210

10.2

 

(2)、把KA1keepalived stop掉(模拟KA1主机的keepalived故障)

[root@centos-1 ~]# service keepalived stop

停止 keepalived:

[root@centos-1 ~]# ip addr

2: eth0:<BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen1000

   link/ether 00:0c:29:0d:f3:5d brd ff:ff:ff:ff:ff:ff

   inet 192.168.5.129/24 brd 192.168.5.255 scope global eth0

   inet6 fe80::20c:29ff:fe0d:f35d/64 scope link

      valid_lft forever preferred_lft forever

(KA1主机上查看ip addr已经没有vip了。)

在KA2主机上查看日志文件

[root@centos-4 ~]# cat /var/log/messages

Oct 19 23:20:46 centos-4Keepalived_vrrp[15412]: VRRP_Instance(VI_1) Sending gratuitous ARPs on eth0 for192.168.5.200

Oct 19 23:20:46 centos-4avahi-daemon[1513]: Registering new address record for 192.168.5.200 oneth0.IPv4.

Oct 19 23:20:46 centos-4Keepalived_healthcheckers[15411]: Netlink reflector reports IP 192.168.5.200added

Oct 19 23:20:51 centos-4Keepalived_vrrp[15412]: VRRP_Instance(VI_1) Sending gratuitous ARPs on eth0 for192.168.5.200

(日志文件显示已经把vip:192.168.5.200接管了)

查看KA2主机的ip addr

[root@centos-4 ~]# ip addr

2: eth0:<BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen1000

   link/ether 00:50:56:3a:84:30 brd ff:ff:ff:ff:ff:ff

   inet 192.168.5.128/24 brd 192.168.5.255 scope global eth0

   inet 192.168.5.210/32 scope global eth0

   inet 192.168.5.200/32 scope global eth0

 (可以看到已经有两个vip

检查nginx服务是否被KA2接管且不中断

[root@centos-5~]# curl 192.168.5.200

10.3

[root@centos-5~]# curl 192.168.5.200

10.2

[root@centos-5~]# curl 192.168.5.210

10.3

[root@centos-5~]# curl 192.168.5.210

10.2


注意:

假如你开启keepalived的时候防火墙多了一条drop规则的时候:

[root@13cml2 ~]# iptables -L

Chain INPUT (policy ACCEPT)

target     prot opt source               destination         

DROP       all  --  anywhere             anywhere             match-set keepalived dst


Chain FORWARD (policy ACCEPT)

target     prot opt source               destination         


Chain OUTPUT (policy ACCEPT)

target     prot opt source               destination  

去掉配置文件中的
vrrp_strict

重启keeplived(可能要加上改成单播的方式),就能访问和ping通了