一般是指2台机器启动着完全相同的业务系统,当有一台机器down机了,另外一台服务器就能快速的接管,对于访问的用户是无感知的。
keepalived高可用只是用在企业内部的,主要用来解决单点故障问题
#硬件通常使用 F5
#软件通常使用 keepalived
keepalived软件是基于VRRP协议实现的,VRRP是虚拟路由冗余协议,主要用于解决单点故障问题
如何才能做到出现故障自动转移,此时VRRP就出现了,我们的VRRP其实是通过软件或者硬件的形式在Master和Backup外面增加一个虚拟的MAC地址(VMAC)与虚拟IP地址(VIP),那么在这种情况下,PC请求VIP的时候,无论是Master处理还是Backup处理,PC仅会在ARP缓存表中记录VMAC与VIP的信息。
1、如何确定谁是主节点谁是备节点(选举投票,优先级)
2、如果Master故障,Backup自动接管,那么Master恢复后会夺权吗(抢占试、非抢占式)
3、如果两台服务器都认为自己是Master会出现什么问题(脑裂)
[root@lb01 conf.d]# scp -r /etc/nginx/ssl_key 172.16.1.5:/etc/nginx/
[root@lb01 conf.d]# scp ./* 172.16.1.5:/etc/nginx/conf.d/
[root@lb01 ~]# yum install -y keepalived
[root@lb02 ~]# yum install -y keepalived
#查看配置文件
[root@lb01 ~]# rpm -qc keepalived
/etc/keepalived/keepalived.conf
/etc/sysconfig/keepalived
[root@lb01 ~]# vim /etc/keepalived/keepalived.conf
global_defs {
router_id lb01
}
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 {
192.168.1.3
}
}
[root@lb02 ~]# rpm -qc keepalived
/etc/keepalived/keepalived.conf
/etc/sysconfig/keepalived
[root@lb02 ~]# vim /etc/keepalived/keepalived.conf
global_defs {
router_id lb02
}
vrrp_instance VI_1 {
state BACKUP
interface eth0
virtual_router_id 51
priority 90
advert_int 1
authentication {
auth_type PASS
auth_pass 1111
}
virtual_ipaddress {
192.168.1.3
}
}
#查看配置文件
[root@lb01 ~]# rpm -qc keepalived
/etc/keepalived/keepalived.conf
/etc/sysconfig/keepalived
#配置主节点配置文件
[root@lb01 ~]# vim /etc/keepalived/keepalived.conf
global_defs {
#全局配置
router_id lb01 #身份验证
}
vrrp_instance VI_1 {
state MASTER #状态,只有MASTER和BACKUP,MASTER是主,BACKUP是备
interface eth0 #网卡绑定,心跳检测
virtual_router_id 51 #虚拟路由标识,组id,把master和backup判断为一组
priority 100 #优先级(真正判断是主是从的条件)(值越大优先级越高)
advert_int 3 #检测状态间隔时间(单位是秒)
authentication {
#认证
auth_type PASS #认证方式
auth_pass 1111 #认证密码指定
}
virtual_ipaddress {
192.168.1.3 #虚拟的VIP地址
}
}
#启动时查看日志
[root@lb02 ~]# tail -f /var/log/messages
#先启动从
[root@lb02 ~]# systemctl start keepalived
#启动时查看日志
[root@lb01 ~]# tail -f /var/log/messages
#再启动主
[root@lb01 ~]# systemctl start keepalived
一、修改 /etc/sysconfig/keepalived
把KEEPALIVED_OPTIONS="-D" 修改为KEEPALIVED_OPTIONS="-D -d -S 0"
#其中-S指定syslog的facility
二、重启服务
service keepalived restart
三、设置syslog,修改/etc/syslog.conf,添加内容如下
# keepalived -S 0
local0.* /var/log/keepalived.log
注意:local0是l是字符L的小写
#由于节点1的优先级高于节点2,所以VIP在节点1上面
[root@lb01 ~]# ip addr | grep 10.0.0.3
inet 10.0.0.3/32 scope global eth0
[root@lb01 ~]# systemctl stop keepalived
#节点2检测不到节点1的心跳,主动接管VIP
[root@lb02 ~]# ip addr | grep 10.0.0.3
inet 10.0.0.3/32 scope global eth0
[root@lb01 ~]# systemctl start keepalived
[root@lb01 ~]# ip addr | grep 10.0.0.3
inet 10.0.0.3/32 scope global eth0
所以keepalived默认是抢占式的创建VIP,
1.修改节点状态,两边状态都必须是BACKUP
2.两个节点都要加上 nopreempt
3.优先级仍保持不同
4.如果配置非抢占式VIP,keepalived主机状态必须一致
#从节点配置
vrrp_instance VI_1 {
state BACKUP
interface eth0
nopreempt
... ...
}
#主节点配置
vrrp_instance VI_1 {
state BACKUP
interface eth0
nopreempt
... ...
}
#查看VIP在节点1上面
[root@lb01 ~]# ip addr | grep 10.0.0.3
inet 10.0.0.3/32 scope global eth0
#windows查看mac地址
C:\Users\admin> arp -a
#将节点1的keepalived停止
[root@lb01 ~]# systemctl stop keepalived
#节点2查看VIP
[root@lb02 ~]# ip addr | grep 10.0.0.3
inet 10.0.0.3/32 scope global eth0
#再次查看MAC地址
C:\Users\admin> arp -a
6.测试页面访问
#配置hosts
10.0.0.3 blog.linux.com
由于某些原因,导致两台keepalived高可用服务器在指定时间内,无法检测到对方是否存活,各自去调用资源,分配工作,而此时两台服务器都还活着并且在工作。
1.服务器网线松动,网络故障
2.服务器硬件发生损坏,硬件故障
3.主备服务器之间开启了防火墙
[root@lb01 ~]# systemctl start firewalld
[root@lb02 ~]# systemctl start firewalld
#访问浏览器因为开启防火墙,所以访问不了站点,需要配置开启http服务
[root@lb02 ~]# firewall-cmd --add-service=http
[root@lb02 ~]# firewall-cmd --add-service=https
#干掉一台服务
[root@lb02 ~]# systemctl stop keepalived
#判断是否有脑裂现象
先做信任,免密登录
[root@lb01 ~]# vim check_naolie.sh
#!/bin/bash
# 做免密
VIP="192.168.15.3"
MASTERIP="172.16.1.6"
BACKUPIP="172.16.1.5"
while true; do
# 探测VIP
PROBE='ip a | grep "${VIP}"'
ssh ${MASTERIP} "${PROBE}" > /dev/null
MASTER_STATU=$?
ssh ${BACKUPIP} "${PROBE}" > /dev/null
BACKUP_STATU=$?
if [[ $MASTER_STATU -eq 0 && $BACKUP_STATU -eq 0 ]];then
ssh ${BACKUPIP} "systemctl stop keepalived.service"
fi
sleep 2
done
-eq 等于
-ne 不等于
-ge 大于等于
-gt 大于
-le 小于等于
-lt 小于
1.nginx默认监听所有IP
#如果nginx宕机,用户请求页面会失败,但是keepalive没有关闭,VIP仍然在nginx挂掉了的机器上,导致影响业务;
#我们应该编写一个脚本,判断nginx状态,如果nginx挂掉,先尝试重启nginx,如果启动不了则关掉keepalived
[root@lb01 ~]# vim check_web.sh
#!/bin/bash
nginxnum=`ps -ef | grep [n]ginx | wc -l`
if [ $nginxnum -eq 0 ];then
systemctl start nginx
sleep 3
nginxnum=`ps -ef | grep [n]ginx | wc -l`
if [ $nginxnum -eq 0 ];then
systemctl stop keepalived.service
fi
fi
[root@lb01 ~]# vim /server/scripts/check_web.sh
#!/bin/sh
nginxpid=$(ps -C nginx --no-header|wc -l)
#1.判断Nginx是否存活,如果不存活则尝试启动Nginx
if [ $nginxpid -eq 0 ];then
systemctl start nginx
sleep 3
#2.等待3秒后再次获取一次Nginx状态
nginxpid=$(ps -C nginx --no-header|wc -l)
#3.再次进行判断, 如Nginx还不存活则停止Keepalived,让地址进行漂移,并退出脚本
if [ $nginxpid -eq 0 ];then
systemctl stop keepalived
fi
fi
[root@lb01 ~]# vim /etc/keepalived/keepalived.conf
global_defs {
router_id lb01
}
#每5秒执行一次脚本,脚本执行完成时间不能超过5秒,否则会重新执行脚本,死循环
vrrp_script check_web {
script "/root/check_web.sh"
interval 5
}
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 {
10.0.0.3
}
#调用计划脚本
track_script {
check_web
}
}
#给脚本添加执行权限
[root@lb01 ~]# chmod +x check_web.sh