1.keepalived高可用裂脑
由于某些原因，导致两台keepalived高可用服务器在指定时间内，无法检测到对方的心跳消息，各自取得资源及服务的所有权，而此时的两台高可用服务器又都还或者。
导致裂脑的原因：
1.服务器网线松动等网络故障
2.服务器硬件故障发生损坏现象而崩溃
3.主备都开启firewalld防火墙
4.Nginx服务器死掉
2.模拟裂脑案例1-防火墙
双方都开启防火墙
lb01 [root@localhost ~]# systemctl start firewalld.service [root@localhost ~]# ip add show dev ens33 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000 link/ether 00:0c:29:55:83:b7 brd ff:ff:ff:ff:ff:ff inet 192.168.81.210/24 brd 192.168.81.255 scope global ens33 valid_lft forever preferred_lft forever inet 192.168.81.100/32 scope global ens33 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fe55:83b7/64 scope link valid_lft forever preferred_lft forever lb02 [root@jxl ~]# systemctl start firewalld.service [root@jxl ~]# ip add show dev ens33 2: ens33: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP group default qlen 1000 link/ether 00:0c:29:46:66:34 brd ff:ff:ff:ff:ff:ff inet 192.168.81.220/24 brd 192.168.81.255 scope global ens33 valid_lft forever preferred_lft forever inet 192.168.81.100/32 scope global ens33 valid_lft forever preferred_lft forever inet6 fe80::20c:29ff:fe46:6634/64 scope link valid_lft forever preferred_lft forever
到此会发现双方都抢占了虚拟ip
用wireshare抓包也可以看到，都在争宠
3.解决由于防火墙裂脑的脚本
在备上编写检测脚本，测试如能ping通并且备节点还有VIP的话则认为产生了裂脑
[root@jxl ~]# vim check_keepalived.sh lb01=192.168.81.210 vip=192.168.81.100 while true;do vip_count=`ip add | grep ${vip} | wc -l` ping -c 2 -W 3 $lb01 &>/dev/null if [ $? -eq 0 -a $vip_count -eq 1 ];then echo -e "\033[31mkeepalived is split brain.waringing...\033[0m" else echo -e "\033[32mkeepalived is ok....\033[0m" fi sleep 5s done
4.模拟故障案例2-nginx
在master上停掉nginx即可
5.解决nginx异常而导致主备不能切换
主节点的nginx宕掉后，网页无法打开，虚拟ip也不会漂移 这时我们就需要编写一个检测nginx状态的脚本，并在keepalived中引入 主备keepalive服务器都需要操作 1.编写脚本 [root@localhost ~]# vim check_nginx.sh #/bin/bash #检查nginx while true;do nginx_proc_count=`ps -C nginx --no-header | wc -l` if [ $nginx_proc_count -eq 0 ];then systemctl restart nginx if [ $? -eq 0 ];then echo -e "\033[33mnginx starting....\033[0m" fi sleep 5 nginx_proc_count=`ps -C nginx --no-header | wc -l` if [ $nginx_proc_count -eq 0 ];then systemctl stop keepalived echo -e "\033[33mnginx is error,stop keepalived....\033[0m" exit 1 fi fi sleep 5 done 2.在keepalived中引入脚本 主备keepalive服务器都需要操作 [root@jxl ~]# vim /etc/keepalived/keepalived.con global_defs { router_id lb02 } vrrp_script check_web { script "/root/check_nginx.sh" } vrrp_instance VI_1 { state BACKUP interface ens33 virtual_router_id 51 priority 100 advert_int 1 authentication { auth_type PASS auth_pass 1111 } virtual_ipaddress { 192.168.81.100 } track_script { check_web } } [root@localhost keepalived]# systemctl restart keepalived
