系统监控monit
公司的tomcat服务器java虚拟机运行不稳定，为了安全考虑，安装monit自监控。
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。服务能“死而复生”。
官网 http://mmonit.com/monit/documentation/monit.html
一、安装
#tar -zxvf monit-5.8.1.tar.gz
#cd monit-5.8.1
#./configure --prefix=/usr/local/monit \
--without-pam \
--sysconfdir=/usr/local/monit/etc
#make&make install
#cp -a monit-5.8.1/monitrc /usr/local/monit/etc
#chmod 700 /usr/local/monit/etc/monitrc
二、配置文件
#vim /urs/local/monit/etc/monitrc
set daemon 300 #设置多少时间监测一次，单位为秒
set logfile /usr/local/monit/log/monit.log #设置日志文件位置
set mailserver smtp.xxxxx.com USERNAME "" PASSWORD "" #设置报警邮箱
set mail-format { from: 任意取名@域名 } #设置报警邮件格式，则收到的报警都是来自任 意取名@域名 这个邮箱
set alert 接收报警邮件的邮箱 #设置接收报警邮件的邮箱、有多个的话相同格式另取一行。
set httpd port 2812 and
use address 本机ip # only accept connection from localhost
allow ip（能访问的ip） # allow localhost to connect to the server
allow admin:ccmonit # require user 'admin' with password 'monit'
allow @monit # allow users of group 'monit' to connect (rw)
allow @users readonly # allow users of group 'users' to connect readonly
#自监控tomcat
check host tomcat with address ip（本机ip）
start program = "/usr/local/tomcat/bin/catalina.sh start"
stop program = "/usr/local/tomcat/bin/shutdown.sh"
if failed
port 80
protocol http
request "/test/time.jsp" #时间测试页面
then restart
if 4 restarts within 4 cycles then unmonitor #如果连续重启4次都不能启动tmcat则停止重启
三、测试页
#cd /usr/local/tomcat/webapps/
#mkdir test
#cd test
#vim time.jsp （显示系统当前时间）
<HTML>
<HEAD>
<SCRIPT LANGUAGE="JavaScript">
function gettime(){
var d = new Date();
document.getElementById("t").innerHTML =d;
window.setTimeout("gettime()",1000);
}
window.onload = gettime;
</SCRIPT>
</HEAD>
<BODY>
<div id="t">
</div>
</BODY>
</HTML>
访问http：//ip/test/time.jsp验证
四、monit init脚本
#!/bin/bash
#
# Init file for Monit
#
#
# chkconfig: - 80 20
# description: monit daemon
#
# processname: monit
source /etc/rc.d/init.d/functions
### Default variables
CONFIG="/usr/local/monit/etc/monitrc"
[ -x /usr/local/monit/bin/monit ] || exit 1
[ -r "$CONFIG" ] || exit 1
bin_path=/usr/local/monit/bin
RETVAL=0
prog="monit"
desc="Monit daemon"
start() {
echo -n $"Starting $desc ($prog): "
daemon $bin_path/$prog -c "$CONFIG"
RETVAL=$?
echo
[ $RETVAL -eq 0 ] && touch /var/lock/subsys/$prog
return $RETVAL
}
stop() {
echo -n $"Shutting down $desc ($prog): "
killproc $prog
RETVAL=$?
echo
[ $RETVAL -eq 0 ] && rm -f /var/lock/subsys/$prog
return $RETVAL
}
restart() {
stop
start
}
reload() {
echo -n $"Reloading $desc ($prog): "
killproc $prog -HUP
RETVAL=$?
echo
return $RETVAL
}
case "$1" in
start)
start
;;
stop)
stop
;;
restart)
restart
;;
reload)
reload
;;
condrestart)
[ -e /var/lock/subsys/$prog ] && restart
RETVAL=$?
;;
status)
#status $prog
$bin_path/$prog status
RETVAL=$?
;;
*)
echo $"Usage: $0 {start|stop|restart|reload|condrestart|status}"
RETVAL=1
esac
exit $RETV
五、管理进程
#service monit monitor name|all 启动对某服务|所有服务的监控
#service monit unmonitor name|all 关闭对某服务|所有服务的监控
#service monit start name|all 启动某服务|所有服务
#service monit stop name|all 关闭某服务|所有服务
#service monit status 显示监控的服务状态
本文出自 “不莱梅乐队” 博客，谢绝转载！