|
ge. Each test specifies a resource, conditions and the action to be ## performed should a test fail. # # check system $HOST # if loadavg (1min) > 4 then alert # if loadavg (5min) > 2 then alert # if cpu usage > 95% for 10 cycles then alert # if memory usage > 75% then alert # if swap usage > 25% then alert # # ## Check if a file exists, checksum, permissions, uid and gid. In addition ## to alert recipients in the global section, customized alert can be sent to ## additional recipients by specifying a local alert handler. The service may ## be grouped using the GROUP option. More than one group can be specified by ## repeating the 'group name' statement. # # check file apache_bin with path /usr/local/apache/bin/httpd # if failed checksum and # expect the sum 8f7f419955cefa0b33a2ba316cba3659 then unmonitor # if failed permission 755 then unmonitor # if failed uid root then unmonitor # if failed gid root then unmonitor # alert security@foo.bar on { # checksum, permission, uid, gid, unmonitor # } with the mail-format { subject: Alarm! } # group server # # ## Check that a process is running, in this case Apache, and that it respond ## to HTTP and HTTPS requests. Check its resource usage such as cpu and memory, ## and number of children. If the process is not running, Monit will restart ## it by default. In case the service is restarted very often and the ## problem remains, it is possible to disable monitoring using the TIMEOUT ## statement. This service depends on another service (apache_bin) which ## is defined above. # # check process apache with pidfile /usr/local/apache/logs/httpd.pid # start program = "/etc/init.d/httpd start" with timeout 60 seconds # stop program = "/etc/init.d/httpd stop" # if cpu > 60% for 2 cycles then alert # if cpu > 80% for 5 cycles then restart # if totalmem > 200.0 MB for 5 cycles then restart # if children > 250 then restart # if loadavg(5min) greater than 10 for 8 cycles then stop # if failed host www.tildeslash.com port 80 protocol http # and request "/somefile.html" # then restart # if failed port 443 type tcpssl protocol http # with timeout 15 seconds # then restart # if 3 restarts within 5 cycles then unmonitor # depends on apache_bin # group server #
# 监控进程可以通过上面监控pid文件的方式，当没有pid文件时，可以通过MATCHING正则表达式来匹配进程。
# 测试一个进程是否匹配来自命令行使用的模式monit procmatch "regex-pattern"，这将列出匹配或不匹配的所有进程，regex模式。
# 我们这里监控了包含shop-pad-server字段的进程，并指明了启动以及停止的命令，这样在进程因故断掉后，Monit会自动重启进程。
# 同时若进程ID变动，会发送邮件通知到之前指定的收件人。
check process shop-pad-server with MATCHING shop-pad-server start program = "/usr/bin/nohup /home/azureuser/pad-server/run.sh > /home/azureuser/pad-server/nohup.out 2>&1 &" stop program = "/usr/bin/ps -ef | /usr/bin/grep shop-pad| /usr/bin/grep -v grep | /usr/bin/awk '{print $2}' | xargs kill" if changed pid then alert
# ## Check filesystem permissions, uid, gid, space and inode usage. Other services, ## such as databases, may depend on this resource and an automatically graceful ## stop may be cascaded to them before the filesystem will become full and data ## lost. # # check filesystem datafs with path /dev/sdb1 # start program = "/bin/mount /data" # stop program = "/bin/umount /data" # if failed permission 660 then unmonitor # if failed uid root then unmonitor # if failed gid disk then unmonitor # if space usage > 80% for 5 times within 15 cycles then alert # if space usage > 99% then stop # if inode usage > 30000 then alert # if inode usage > 99% then stop |