共计 6711 个字符，预计需要花费 17 分钟才能阅读完成。
高可用是个老生常谈的问题了，开源的高可用软件已经做的相当成熟了，之前也在 debian 下做过 lvs+heartbeat 的 4 层 LB，一直很稳定（可惜流量不大啊委屈），现在由于业务的需要，做一个基于 keepalived+nginx 的高可用 7 层负载均衡。
拓扑结构也比较简单，就不画拓扑图了：2 个节点上分别安装配置 keepalived 和 nginx，配置 nginx 反向代理后端的 real server
比较关键的几个点：
1、为避免同一个局域网中有多个 keepalived 组中的多播相互响应，采用单播通信
2、状态切换的过程触发邮件通知、短信通知、web 通知、log 记录，便于通过各种途径了解主备工作状态
3、nginx 的检测脚本采用了轻量级的方式：”killall -0 nginx”，还可以使用 pidof nginx 的方式或者调用其他自定义检测脚本的方式
4、特别要注意优先级的大小及检测到异常时权重的变化
5、了解免费 ARP 的工作机制
6、了解 VRRP 协议的适用范围：局域网，第一跳网关冗余
7、单个 vrrp 实例工作在主备模式，为最大程度的利用 2 个节点的资源，可以做多个 vrrp 实例，实现高可用和负载均衡
为便于软件包的管理，采用 CentOS 自带的 keepalived，nginx1.8.0 采用 nginx 官方源，整体安装也比较简单。
#yum install keepalived nginx -y
设置关键服务的开机启动
#chkconfig nginx on
#chkconfig keepalived on
查看 keepalived 包安装了那些文件（文档一定好好看）：
#rpm -ql keepalived
/etc/keepalived
/etc/keepalived/keepalived.conf
/etc/rc.d/init.d/keepalived
/etc/sysconfig/keepalived
/usr/bin/genhash
/usr/libexec/keepalived
/usr/sbin/keepalived
/usr/share/doc/keepalived-1.2.13
/usr/share/doc/keepalived-1.2.13/AUTHOR
………
keepalived 的主配置文件，2 台机器的配置文件略有区别，具体请看配置文件中注释
[root@proxy101 ~]# more /etc/keepalived/keepalived.conf
####Configuration File for keepalived
#### 内部 API 网关 keepalived HA 配置
#### laijingli 20151213
global_defs {
notification_email {
xxxx@qq.com
}
notification_email_from yn_alert@xxx.me
smtp_server 127.0.0.1
smtp_connect_timeout 30
router_id proxy101 ## proxy101 on master101 , proxy102 on backup102
}
###simple check with killall -0 which is less expensive than pidof to verify that nginx is running
vrrp_script chk_nginx {
script “killall -0 nginx”
interval 1
weight 2
fall 2
rise 1
}
vrrp_instance YN_API_GATEWAY {
state MASTER ## MASTER on master101 , BACKUP on backup102
interface em1
virtual_router_id 101
priority 200 ## 200 on master101 , 199 on backup102
advert_int 1
### 采用单播通信，避免同一个局域网中多个 keepalived 组之间的相互影响
unicast_src_ip 192.168.0.101 ## 本机 ip
unicast_peer {
192.168.0.102 ## 对端 ip
}
authentication {
auth_type PASS
auth_pass testpass
}
virtual_ipaddress {
192.168.0.105 ## VIP
}
### 如果只有一块网卡的话监控网络接口就没有必要了
#track_interface {
# em1
#}
track_script {
chk_nginx
}
### 状态切换是发送邮件通知，本机记录 log，后期会触发短信通知
notify_master /usr/local/bin/keepalived_notify.sh notify_master
notify_backup /usr/local/bin/keepalived_notify.sh notify_backup
notify_fault /usr/local/bin/keepalived_notify.sh notify_fault
notify /usr/local/bin/keepalived_notify.sh notify
smtp_alert
}
VRRP 实例组节点状态切换触发邮件通知、短信通知、log 记录的脚本
# more /usr/local/bin/keepalived_notify.sh
#!/bin/bash
###keepalived notify script for record ha state transtion to log files
### 将将状态转换过程记录到 log，便于排错
logfile=/var/log/keepalived.notify.log
echo ————— >> $logfile
echo `date` [`hostname`] keepalived HA role state transition: $1 $2 $3 $4 $5 $6 >> $logfile
### 将状态转换记录到 nginx 的文件，便于通过 web 查看 ha 状态（一定注意不要开放到公网）
echo `date` `hostname` $1 $2 $3 $4 $5 $6 > /usr/share/nginx/html/index.html
nginx 的部分配置文件，仅供参考
# more /etc/nginx/nginx.conf
### 运维管理用途: 用于区别 vip 跑在那台服务器上
server {
listen 80;
server_name localhost;
location / {
root /usr/share/nginx/html;
index index.html index.htm;
}
## nginx monitor use only
###add by lai monitor nginx status
location /server-status {
stub_status on;
allow 127.0.0.1;
allow 192.168.0.0/24;
}
}
通过启停 keepalived 和 nginx 来模拟故障，测试 vrrp 实例的状态切换过程（即 VIP 的漂移）：
/etc/init.d/keepalived start/stop
/etc/init.d/nginx stop start/stop
通过启停 em1 内网网卡、em2 公网网卡来模拟故障，测试 vrrp 实例的状态切换过程（即 VIP 的漂移）
ifdown em1
ifdown em2
查看 VIP 跑在那台服务器上：
# ip addr show|grep 192.168
inet 192.168.0.101/24 brd 192.168.0.255 scope global em1
inet 192.168.0.105/32 scope global em1
测试：
[root@test28 ~]$ curl 192.168.0.101
Mon Dec 14 16:27:10 CST 2015 proxy101 INSTANCE YN_API_GATEWAY MASTER 202
[root@test28 ~]$ curl 192.168.0.102
Mon Dec 14 16:34:40 CST 2015 proxy102 INSTANCE YN_API_GATEWAY BACKUP 199
[root@test28 ~]$ curl 192.168.0.105
Mon Dec 14 16:27:10 CST 2015 proxy101 INSTANCE YN_API_GATEWAY MASTER 202
# tail /var/log/keepalived.notify.log
Mon Dec 14 16:25:13 CST 2015 [proxy101] keepalived HA role state transition:
Mon Dec 14 16:25:13 CST 2015 [proxy101] keepalived HA role state transition: INSTANCE YN_API_GATEWAY MASTER 202
—————
—————
Mon Dec 14 16:26:34 CST 2015 [proxy101] keepalived HA role state transition:
Mon Dec 14 16:26:34 CST 2015 [proxy101] keepalived HA role state transition: INSTANCE YN_API_GATEWAY BACKUP 200
—————
—————
Mon Dec 14 16:27:10 CST 2015 [proxy101] keepalived HA role state transition:
Mon Dec 14 16:27:10 CST 2015 [proxy101] keepalived HA role state transition: INSTANCE YN_API_GATEWAY MASTER 202
# tail /var/log/messages
Dec 14 16:27:08 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) forcing a new MASTER election
Dec 14 16:27:08 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) forcing a new MASTER election
Dec 14 16:27:09 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) Transition to MASTER STATE
Dec 14 16:27:10 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) Entering MASTER STATE
Dec 14 16:27:10 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) setting protocol VIPs.
Dec 14 16:27:10 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) Sending gratuitous ARPs on em1 for 192.168.0.105
Dec 14 16:27:10 localhost Keepalived_healthcheckers[74307]: Netlink reflector reports IP 192.168.0.105 added
Dec 14 16:27:10 localhost Keepalived_vrrp[74308]: Remote SMTP server [127.0.0.1]:25 connected.
Dec 14 16:27:10 localhost Keepalived_vrrp[74308]: SMTP alert successfully sent.
Dec 14 16:27:15 localhost Keepalived_vrrp[74308]: VRRP_Instance(YN_API_GATEWAY) Sending gratuitous ARPs on em1 for 192.168.0.105
主备状态转换通知邮件：
通过抓包查看来了解详细的工作过程：
# tcpdump -ni em1 vrrp
tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on em1, link-type EN10MB (Ethernet), capture size 65535 bytes
17:36:47.098225 IP 192.168.0.101 > 192.168.0.102: VRRPv2, Advertisement, vrid 101, prio 202, authtype simple, intvl 1s, length 20
17:36:47.388540 IP 192.168.0.22 > 224.0.0.18: VRRPv2, Advertisement, vrid 51, prio 120, authtype simple, intvl 1s, length 20
17:36:48.099409 IP 192.168.0.101 > 192.168.0.102: VRRPv2, Advertisement, vrid 101, prio 202, authtype simple, intvl 1s, length 20
17:36:48.389504 IP 192.168.0.22 > 224.0.0.18: VRRPv2, Advertisement, vrid 51, prio 120, authtype simple, intvl 1s, length 20
17:36:49.100544 IP 192.168.0.101 > 192.168.0.102: VRRPv2, Advertisement, vrid 101, prio 202, authtype simple, intvl 1s, length 20
17:36:49.390487 IP 192.168.0.22 > 224.0.0.18: VRRPv2, Advertisement, vrid 51, prio 120, authtype simple, intvl 1s, length 20
17:36:50.101713 IP 192.168.0.101 > 192.168.0.102: VRRPv2, Advertisement, vrid 101, prio 202, authtype simple, intvl 1s, length 20
17:36:50.391453 IP 192.168.0.22 > 224.0.0.18: VRRPv2, Advertisement, vrid 51, prio 120, authtype simple, intvl 1s, length 20
《Keepalived 权威指南》下载见 http://www.linuxidc.com/Linux/2012-05/60951.htm
Nginx+Keepalived 实现站点高可用 http://www.linuxidc.com/Linux/2016-12/137883.htm
Nginx+Keepalived 实现站点高可用 (负载均衡) http://www.linuxidc.com/Linux/2016-12/138221.htm
构建高可用集群 Keepalived+Haproxy 负载均衡 http://www.linuxidc.com/Linux/2016-12/138917.htm
CentOS6.5 下 Keepalived 高可用服务单实例配置 http://www.linuxidc.com/Linux/2016-12/138110.htm
Keepalived+Nginx 实现高可用（HA）http://www.linuxidc.com/Linux/2017-02/140422.htm
本文永久更新链接地址 ：http://www.linuxidc.com/Linux/2017-02/141084.htm
