Keepalived+HAProxy实现MySQL高可用负载均衡的配置

Keepalived
由于在生产环境使用了mysqlcluster,需要实现高可用负载均衡,这里提供了keepalived+haproxy来实现.
      keepalived主要功能是实现真实机器的故障隔离及负载均衡器间的失败切换.可在第3,4,5层交换.它通过VRRPv2（Virtual Router Redundancy Protocol） stack实现的.
      Layer3:Keepalived会定期向服务器群中的服务器.发送一个ICMP的数据包（既我们平时用的Ping程序）,如果发现某台服务的IP地址没有激活，Keepalived便报告这台服务器失效，并将它从服务器群中剔除，这种情况的典型例子是某台服务器被非法关机。Layer3的方式是以服务器的IP地址是否有效作为服务器工作正常与否的标准。
     Layer4:主要以TCP端口的状态来决定服务器工作正常与否。如web server的服务端口一般是80，如果Keepalived检测到80端口没有启动，则Keepalived将把这台服务器从服务器群中剔除。
     Layer5:在网络上占用的带宽也要大一些。Keepalived将根据用户的设定检查服务器程序的运行是否正常，如果与用户的设定不相符，则Keepalived将把服务器从服务器群中剔除。
Software Design

2016228164756604.jpg （597×381）

keepalived启动后会有单个进程

8352 ?Ss 0:00 /usr/sbin/keepalived8353 ?S 0:00 \_ /usr/sbin/keepalived8356 ?S 0:01 \_ /usr/sbin/keepalived

父进程:内存管理,子进程管理等等
子进程:VRRP子进程
子进程:Healthchecking 子进程
实例
2台mysqlcluster 10.1.6.203 master 10.1.6.205 backup
vip 10.1.6.173
目的访问10.1.6.173 3366端口分别轮询通过haproxy转发到10.1.6.203 3306 和10.1.6.205 3306
mysqlcluster搭建参照之前博客,这里在2台机上安装keepalived

root@10.1.6.203:~# apt-get install keepalivedroot@10.1.6.203:~# cat /etc/keepalived/keepalived.conf vrrp_script chk_haproxy {script "killall -0 haproxy"# verify the pid existanceinterval 2# check every 2 secondsweight -2# add 2 points of prio if OK} vrrp_instance VI_1 {interface eth1# interface to monitorstate MASTER virtual_router_id 51 # Assign one ID for this routepriority 101 # 101 on master, 100 on backupnopreemptdebug virtual_ipaddress {10.1.6.173} track_script {#注意大括号空格chk_haproxy} notify_master /etc/keepalived/scripts/start_haproxy.sh #表示当切换到master状态时,要执行的脚本notify_fault /etc/keepalived/scripts/stop_keepalived.sh #故障时执行的脚本notify_stop/etc/keepalived/scripts/stop_haproxy.sh #keepalived停止运行前运行notify_stop指定的脚本 }

VRRPD配置包括三个类:

VRRP同步组（synchroization group）
VRRP实例（VRRP Instance）
VRRP脚本

这里使用了 VRRP实例, VRRP脚本
注意配置选项:
stat:指定instance（Initial）的初始状态，就是说在配置好后，这台服务器的初始状态就是这里指定的，但这里指定的不算，还是得要通过竞选通过优先级来确定，里如果这里设置为master，但如若他的优先级不及另外一台，那么这台在发送通告时，会发送自己的优先级，另外一台发现优先级不如自己的高，那么他会就回抢占为master

interface：实例绑定的网卡，因为在配置虚拟IP的时候必须是在已有的网卡上添加的
priority 101：设置本节点的优先级，优先级高的为master
debug：debug级别
nopreempt:设置为不抢占

vrrp_script chk_haproxy {script "killall -0 haproxy"# verify the pid existanceinterval 2# check every 2 seconds 脚本执行间隔weight -2# add 2 points of prio if OK 脚本结果导致的优先级变更：2表示优先级+2；-2则表示优先级-2}

然后在实例（vrrp_instance）里面引用，有点类似脚本里面的函数引用一样：先定义，后引用函数名

track_script {chk_haproxy}

注意：VRRP脚本（vrrp_script）和VRRP实例（vrrp_instance）属于同一个级别

root@10.1.6.203:scripts# cat start_haproxy.sh #！/bin/bash sleep 5get=`ip addr |grep 10.1.6.173 |wc -l`echo $get >> /etc/keepalived/scripts/start_ha.log if [ $get -eq 1 ]thenecho "`date +%c` success to get vip" >> /etc/keepalived/scripts/start_ha.log/usr/local/sbin/haproxy -f /etc/haproxy/haproxy.cfgelseecho "`date +%c` can not get vip" >> /etc/keepalived/scripts/start_ha.logfiroot@10.1.6.203:scripts# cat stop_keepalived.sh #！/bin/bash pid=`pidof keepalived`if [ $pid == "" ]thenecho "`date +%c` no keepalived process id" >> /etc/keepalived/scripts/stop_keep.logelseecho "`date +%c` will stop keepalived " >> /etc/keepalived/scripts/stop_keep.log/etc/init.d/keepalived stopfi /etc/init.d/keepalived stop root@10.1.6.203:scripts# cat stop_haproxy.sh #！/bin/bash pid=`pidof haproxy`echo "`date +%c` stop haproxy" >> /etc/keepalived/scripts/stop_ha.logkill -9 $pid

同理配置10.1.6.205

root@10.1.6.205:~# cat /etc/keepalived/keepalived.conf vrrp_script chk_haproxy {script "killall -0 haproxy"# verify the pid existanceinterval 2# check every 2 secondsweight 2 # add 2 points of prio if OK} vrrp_instance VI_1 {interface eth1# interface to monitorstate BACKUPvirtual_router_id 51 # Assign one ID for this routepriority 100 # 101 on master, 100 on backupvirtual_ipaddress {10.1.6.173} track_script {chk_haproxy} notify_master /etc/keepalived/scripts/start_haproxy.shnotify_fault /etc/keepalived/scripts/stop_keepalived.shnotify_stop /etc/keepalived/scripts/stop_haproxy.sh }

HAProxy
下面再介绍下haproxy
HAProxy是一款基于TCP（第四层）和HTTP（第七层）应用的代理软件,它也可作为负载均衡器.可以支持数以万计的并发连接.同时可以保护服务器不暴露到网络上,通过端口映射.它还自带监控服务器状态的页面.
安装haproxy

wget -O/tmp/haproxy-1.4.22.tar.gz http://haproxy.1wt.eu/download/1.4/src/haproxy-1.4.22.tar.gztar xvfz /tmp/haproxy-1.4.22.tar.gz -C /tmp/cd /tmp/haproxy-1.4.22make TARGET=linux26make install

haproxy需要对每一个mysqlcluster服务器进行健康检查
1.在2台主机分别配置haproxy.cfg

root@10.1.6.203:scripts# cat /etc/haproxy/haproxy.cfg globalmaxconn 51200 #默认最大连接数 #uid 99#gid 99daemon#以后台形式运行haproxy#quietnbproc 1 #进程数量（可以设置多个进程提高性能） pidfile /etc/haproxy/haproxy.pid #haproxy的pid存放路径,启动进程的用户必须有权限访问此文件defaultsmode tcp#所处理的类别 （#7层 http;4层tcp ） option redispatch#serverId对应的服务器挂掉后,强制定向到其他健康的服务器 option abortonclose #当服务器负载很高的时候，自动结束掉当前队列处理比较久的连接 timeout connect 5000s#连接超时timeout client 50000s #客户端超时timeout server 50000s#服务器超时log 127.0.0.1 local0#错误日志记录balance roundrobin#默认的负载均衡的方式,轮询方式listen proxybind 10.1.6.173:3366#监听端口 mode tcp#http的7层模式option httpchk#心跳检测的文件server db1 10.1.6.203:3306 weight 1 check port 9222 inter 12000 rise 3 fall 3 #服务器定义,check inter 12000是检测心跳频率 rise 3是3次正确认为服务器可用， fall 3是3次失败认为服务器不可用，weight代表权重 server db2 10.1.6.205:3306 weight 1 check port 9222 inter 12000 rise 3 fall 3 listen haproxy_statsmode httpbind 10.1.6.173:8888option httplogstats refresh 5sstats uri /status #网站健康检测URL，用来检测HAProxy管理的网站是否可以用，正常返回200，不正常返回503 stats realm Haproxy Managerstats auth admin:p@a1SZs24 #账号密码root@10.1.6.205:~$ cat /etc/haproxy/haproxy.cfg globalmaxconn 51200#uid 99#gid 99daemon#quietnbproc 1pidfile /etc/haproxy/haproxy.pid defaultsmode tcpoption redispatchoption abortonclosetimeout connect 5000stimeout client 50000stimeout server 50000slog 127.0.0.1 local0balance roundrobinlisten proxybind 10.1.6.173:3366mode tcpoption httpchkserver db1 10.1.6.203:3306 weight 1 check port 9222 inter 12000 rise 3 fall 3server db2 10.1.6.205:3306 weight 1 check port 9222 inter 12000 rise 3 fall 3 listen haproxy_statsmode httpbind 10.1.6.173:8888option httplogstats refresh 5sstats uri /status stats realm Haproxy Managerstats auth admin:p@a1SZs24

2.安装xinetd

root@10.1.6.203:~# apt-get install xinetd

3.在每个节点添加xinetd服务脚本和mysqlchk端口号

root@10.1.6.203:~# vim /etc/xinetd.d/mysqlchk # default: on# description: mysqlchkservice mysqlchk #需要在servive定义{flags= REUSEsocket_type = streamport= 9222wait= nouser= nobodyserver = /opt/mysqlchk log_on_failure += USERIDdisable = noper_source = UNLIMITEDbind= 10.1.6.173} root@10.1.6.203:~# vim /etc/services mysqlchk9222/tcp# mysqlchk

4.编写mysqlchk监控服务脚本

root@10.1.6.203:~# ls -l /opt/mysqlchk -rwxr--r-- 1 nobody root 1994 2013-09-17 11:27 /opt/mysqlchkroot@10.1.6.203:~# cat /opt/mysqlchk #！/bin/bash## This script checks if a mysql server is healthy running on localhost. It will# return:# "HTTP/1.x 200 OK
" （if mysql is running smoothly）# - OR -# "HTTP/1.x 500 Internal Server Error
" （else）## The purpose of this script is make haproxy capable of monitoring mysql properly# MYSQL_HOST="localhost"MYSQL_SOCKET="/var/run/mysqld/mysqld.sock"MYSQL_USERNAME="mysqlchkusr" #该账户密码需要在mysql里添加MYSQL_PASSWORD="secret"MYSQL_OPTS="-N -q -A"TMP_FILE="/dev/shm/mysqlchk.$$.out"ERR_FILE="/dev/shm/mysqlchk.$$.err"FORCE_FAIL="/dev/shm/proxyoff"MYSQL_BIN="/opt/mysqlcluster/mysql-cluster-gpl-7.2.6-linux2.6-x86_64/bin/mysql"CHECK_QUERY="select 1" preflight_check（）{for I in "$TMP_FILE" "$ERR_FILE"; doif [ -f "$I" ]; thenif [ ！ -w $I ]; thenecho -e "HTTP/1.1 503 Service Unavailable
"echo -e "Content-Type: Content-Type: text/plain
"echo -e "
"echo -e "Cannot write to $I
"echo -e "
"exit 1fifidone} return_ok（）{echo -e "HTTP/1.1 200 OK
"echo -e "Content-Type: text/html
"echo -e "Content-Length: 43
"echo -e "
"echo -e "<html><body>MySQL is running.</body></html>
"echo -e "
"rm $ERR_FILE $TMP_FILEexit 0}return_fail（）{echo -e "HTTP/1.1 503 Service Unavailable
"echo -e "Content-Type: text/html
"echo -e "Content-Length: 42
"echo -e "
"echo -e "<html><body>MySQL is *down*.</body></html>
"sed -e "s/
$/
/" $ERR_FILEecho -e "
"rm $ERR_FILE $TMP_FILEexit 1}preflight_checkif [ -f "$FORCE_FAIL" ]; thenecho "$FORCE_FAIL found" > $ERR_FILEreturn_fail;fi$MYSQL_BIN $MYSQL_OPTS --host=$MYSQL_HOST --socket=$MYSQL_SOCKET --user=$MYSQL_USERNAME --password=$MYSQL_PASSWORD -e "$CHECK_QUERY" > $TMP_FILE 2> $ERR_FILEif [ $? -ne 0 ]; thenreturn_fail;fireturn_ok;

测试
2个节点开启keepalived（主节点会获得vip,自动拉起haproxy）,xinetd

root@10.1.6.203:~# ip add1: lo: <LOOPBACK,UP,LOWER_UP> mtu 16436 qdisc noqueue state UNKNOWN link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00inet 127.0.0.1/8 scope host lo2: eth0: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN qlen 1000link/ether 00:26:b9:36:0f:81 brd ff:ff:ff:ff:ff:ffinet 211.151.105.186/26 brd 211.151.105.191 scope global eth03: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state UP qlen 1000link/ether 00:26:b9:36:0f:83 brd ff:ff:ff:ff:ff:ffinet 10.1.6.203/24 brd 10.1.6.255 scope global eth1inet 10.1.6.173/32 scope global eth14: eth2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN qlen 1000link/ether 00:26:b9:36:0f:85 brd ff:ff:ff:ff:ff:ff5: eth3: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN qlen 1000link/ether 00:26:b9:36:0f:87 brd ff:ff:ff:ff:ff:ffroot@10.1.6.203:~# netstat -tunlp | grep hatcp0 0 10.1.6.173:3366 0.0.0.0:*LISTEN 1042/haproxytcp0 0 10.1.6.203:8888 0.0.0.0:*LISTEN 1042/haproxyudp0 0 0.0.0.0:565620.0.0.0:*1042/haproxyroot@10.1.6.203:~# netstat -tunlp | grep xinetcp0 0 10.1.6.203:9222 0.0.0.0:*LISTEN 30897/xinetdroot@10.1.6.203:~# ps -ef | grep haproxyroot 1042 1 0 Sep17 ?00:00:00 /usr/local/sbin/haproxy -f /etc/haproxy/haproxy.cfg

测试:
通过vip10.1.6.173 3366访问cluster数据库（注意账户dave权限需要加3个ip10.1.6.203,10.1.6.205,10.1.6.173）

root@10.1.6.203:mgm# mysql -udave -p -h 10.1.6.173 -P 3366Enter password: Welcome to the MySQL monitor. Commands end with ; or g.Your MySQL connection id is 1344316Server version: 5.5.22-ndb-7.2.6-gpl-log MySQL Cluster Community Server （GPL） Type "help;" or "h" for help. Type "c" to clear the buffer. mysql> show databases;+--------------------+| Database|+--------------------+| information_schema | | dave | | test| +--------------------+3 rows in set （0.01 sec） mysql>

手动分别使keepalive,haproxy,数据库挂掉.vip10.1.6.173会自动漂到10.1.6.205从上，并不影响vip的访问
通过vip,haproxy查看各节点状态
http://10.1.6.173:8888/status

2016228164844383.jpg （1158×481）