monit 监控并自动重启服务

Monit是一款功能非常丰富的进程、文件、目录和设备的监测软件,用于Unix平台。 它可以自动修复那些已经停止运作的程序,特使适合处理那些由于多种原因导致的软件错误。monit运行于应用层
安装很简单,三部曲
#./configure
#make
#make install
 
复制配置文件
# cp monitrc /etc/monitrc
 
接下来我们根据实际情况来修改这个配置文件
set daemon 120 # Poll at 2-minute intervals//每2分钟检查一次
set logfile /home/monit/log/monit.log          //monit的日志文件
set alert zhouwei@chinabank.com.cn with reminder on 1 cycle  //出现1次错误的时候发报警邮件到指定的邮箱
#set mailserver mail.tildeslash.com, mail.foo.bar port 10025, localhost with tim
eout 15 seconds
set mailserver 10.10.9.109    //设置邮件服务器
set httpd port 2812 and use address 10.10.8.2 //设置http监控页面的端口和ip
    allow localhost   # Allow localhost to connect //允许本机访问
    allow 10.10.8.0/24                                            //允许此IP段访问
    allow admin:nishiwode # Allow Basic Auth   //认证的用户名和密码
# all system                                                         //平均负载.内存使用率,cpu使用率
check system 10.10.8.2
   if loadavg (1min) > 4 then alert
   if loadavg (5min) > 2 then alert
   if memory usage > 75% then alert
   if cpu usage (user) > 70% then alert
   if cpu usage (system) > 30% then alert
   if cpu usage (wait) > 20% then alert
# all disk                                                              //磁盘空间使用率
check device data with path /dev/sda2
   if space usage > 90% then alert
   if inode usage > 85% then alert
check device home with path /dev/sda3
   if space usage > 85% then alert
   if inode usage > 85% then alert
# all rsync
#10.10.8.2
check process sshd with pidfile /var/run/sshd.pid
start program "/etc/init.d/sshd start"
stop program "/etc/init.d/sshd stop"
if failed host 127.0.0.1 port 22 protocol ssh then restart
if 5 restarts within 5 cycles then timeout
//监控ssh服务
check process httpd with pidfile /var/run/httpd.pid
group apache
start program = "/etc/init.d/httpd start"
stop program = "/etc/init.d/httpd stop"
if failed host 127.0.0.1 port 80
protocol http then restart
if 5 restarts within 5 cycles then timeout
//监控http服务

//监控自定义服务
check process web_lb with pidfile /data/v20/server/web_lb/httpd.pid
    start program = "/data/v20/bin/lb.sh"  //启动脚本
    stop  program = "/data/v20/bin/lb_stop.sh" //停止脚本
    if failed host 10.10.8.2 port 16101 proto http then restart
    if failed host 10.10.8.2 port 16101 proto http for 5 times within 5 cycles t
hen exec "/data/v20/bin/lb_pay.sh"
    if failed host 10.10.8.2 port 16102 type TCPSSL proto http then restart
    if failed host 10.10.8.2 port 16102 type TCPSSL proto http for 5 times withi
n 5 cycles then exec "/data/v20/bin/lb_pay.sh

RHEL可以用如下方法启动monit
# vi /etc/inittab
添加:
mo:2345:respawn:/usr/local/bin/monit -Ic /etc/monitrc
Now start monit:
# init -q或者# telinit -q
You can verify that monit is started from /var/log/message log file:
# tail -f /var/log/message
如果正常启动能看到如下输出: 
Nov 21 04:39:21 server monit[8759]: Starting monit daemon
Nov 21 04:39:21 server monit[8759]: Monit started

　　

实际应用：

yum install -y monit

EOF

# add by zhangzizhao
cat > /etc/monitrc << EOF
set daemon 30
set logfile syslog facility log_daemon
set pidfile /var/run/monit.pid
set httpd port 30000
allow 127.0.0.1

check process tangible
        with pidfile /tangible_dev/tangible.pid
        start program  "/tangible_dev/tangible"
        stop program  "/bin/bash -c  '/usr/bin/kill -9 \`/bin/cat /tangible_dev/tangible.pid\`'"

EOF

monit -d 1
monit start tangible