最近发现了一个蛮有意思的监控软件Monit,它的功能远比zabbix要强大,而且要灵活得多,更重要的是它可以监控到的参数比较多。
Monit的安装比较简单,在这里就不做介绍了,我主要说一下在我们的生产环境上需要配置的东西
不过这个配置目前也是在实验阶段还没敢真机上上手
下面是配置文件/etc/monitrc
# set daemon 120 # check services at 2-minute intervals
# with start delay 240 # optional: delay the first check by 4-minutes (by
# # default Monit check immediately after Monit start)
set daemon 90 #设置monit进程检查的时间间隔是90秒
# set logfile syslog facility log_daemon
set logfile /var/log/monit.log #设置日志文件的路径
# set idfile /var/.monit.id
# set statefile /var/.monit.state
# set mailserver mail.bar.baz, # primary mailserver
# backup.bar.baz port 10025, # backup mailserver on port 10025
# localhost # fallback relay
#
set mailserver 119.254.72.233 #设置发邮件的邮件服务器,如果没有该项设置,那么monit将不会发出警告
## By default Monit will drop alert events if no mail servers are available.
## If you want to keep the alerts for later delivery retry, you can use the
## EVENTQUEUE statement. The base directory where undelivered alerts will be
## stored is specified by the BASEDIR option. You can limit the maximal queue
## size using the SLOTS option (if omitted, the queue is limited by space
## available in the back end filesystem).
#
# set eventqueue
# basedir /var/monit # set the base directory where events will be stored
# slots 100 # optionally limit the queue size
#
#
## Send status and events to M/Monit (for more informations about M/Monit
## see http://mmonit.com/).
#
# set mmonit http://monit:[email protected]:8080/collector
#set mmonit http://119.254.72.248:8080/collector
#
#
## Monit by default uses the following alert mail format:
##
## --8<--
#From: monit@$HOST # sender
#Subject: monit alert -- $HOST $EVENT $SERVICE # subject
##
##$EVENT Service $SERVICE #
## #
## Date: $DATE #
## Action: $ACTION #
## Host: $HOST # body
## Description: $DESCRIPTION #
## #
## Your faithful employee, #
## Monit #
## --8<--
##
## You can override this message format or parts of it, such as subject
## or sender using the MAIL-FORMAT statement. Macros such as $DATE, etc.
## are expanded at runtime. For example, to override the sender, use:
#
# set mail-format { from: [email protected] }
set mail-format { from: [email protected] } #设置报警发件人
set mail-format { Subject: alert $HOST $SERVICE $DESCRIPTION } #设置报警邮件的格式
#
## You can set alert recipients whom will receive alerts if/when a
## service defined in this file has errors. Alerts may be restricted on
## events by using a filter as in the second example below.
#
# set alert [email protected] # receive all alerts
# set alert [email protected] only on { timeout } # receive just service-
# # timeout alert
#
set alert [email protected] # 接收报警邮件地址(接收所有)
#
## Monit has an embedded web server which can be used to view status of
## services monitored and manage services from a web interface. See the
## Monit Wiki if you want to enable SSL for the web server.
#
# set httpd port 2812 and
# use address localhost # only accept connection from localhost
# allow localhost # allow localhost to connect to the server and
# allow admin:monit # 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
#
#
#监控apache服务器
set httpd port 2812 and #设置apache监听端口为2812
use address 119.254.72.248 #设置监听apache的monit服务器IP
allow localhost #允许本机访问apache
allow 203.86.46.224/29 #允许该IP段访问apache
allow 203.86.63.133 #允许该IP访问apache
allow sysadmin:monit12114 #设置以用户名sysadmin和对应的密码访问apache
###############################################################################
## Services
###############################################################################
##
## Check general system resources such as load average, cpu and memory
## usage. Each test specifies a resource, conditions and the action to be
## performed should a test fail.
#监控系统负载 CPU 内存使用情况
check system 119.254.72.248
if loadavg (1min) > 4 then alert #如果一分钟之内的平均负载大于4则报警
if loadavg (5min) > 2 then alert #如果五分钟之内的平均负载大于2则报警
if memory usage > 75% then alert #如果CPU使用率超过75%则报警
if cpu usage (user) > 70% then alert #如果用户占用内存超过70%则报警
if cpu usage (system) > 30% then alert #如果系统占用内存超过30%则报警
if cpu usage (wait) > 20% then alert 如果等待进程占用内存超过20%则报警
#
# 检测文件 是否存在 校验和 权限 UID GID
## Check a file for existence, 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 [email protected] on {
# checksum, permission, uid, gid, unmonitor
# } with the mail-format { subject: Alarm! }
# group server
#
# 检查apache运行状态,monit会自动回应apache的请求,检测apache占用的系统资源情况以及子进程数量。如果apache down了,monit会自动将apache重启,如果重启的频率过高的话,将会有可能停止monit并使用timeout
## 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 timeout
# depends on apache_bin
# group server
#
check process apache with pidfile /usr/local/apache/logs/httpd.pid
start program = "/usr/local/apache/bin/apachectl start" with timeout 60 seconds
stop program = "/usr/local/apache/bin/apachectl stop"
if failed host 119.254.72.248 port 80 protocol http then restart
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 > 140 then restart
# if loadavg(5min) greater than 10 for 8 cycles then stop
#
check process httpd with pidfile /usr/local/http_post/logs/httpd.pid
start program = "/usr/local/http_post/bin/apachectl start" with timeout 60 seconds
stop program = "/usr/local/http_post/bin/apachectl stop"
if failed host 119.254.72.248 port 8080 protocol http then restart
#
###
#检查Nginx服务进程
check process nginx with pidfile /usr/local/nginx/logs/nginx.pid
start program = "/usr/local/nginx/bin/nginx start" with timeout 60 seconds
stop program = "/usr/local/nginx/bin/nginx stop"
if failed host 119.254.72.248 port 81 protocol http then restart
## 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
#检查系统磁盘空间使用情况并根据不同的设置来报警,一般情况下分两个级别,磁盘使用率达到70%和85%时,分别报警。主要是针对 root home usr var 四个磁盘空间,尤其是home是邮件目录,占用磁盘空间比较大,磁盘空间上涨很快
check filesystem root with path /
if space usage > 70% then alert
if inode usage > 85% then alert
check filesystem home with path /home
if space usage > 50% for 5 times within 15 cycles then alert
if inode usage > 85% then alert
check filesystem usr with path /usr
if space usage > 70% then alert
if inode usage > 85% then alert
check filesystem var with path /var
if space usage > 70% then alert
if inode usage > 85% then alert
# 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 > 50% 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
# group server
#
#
## Check a file's timestamp. In this example, we test if a file is older
## than 15 minutes and assume something is wrong if its not updated. Also,
## if the file size exceed a given limit, execute a script
#
# check file database with path /data/mydatabase.db
# if failed permission 700 then alert
# if failed uid data then alert
# if failed gid data then alert
# if timestamp > 15 minutes then alert
# if size > 100 MB then exec "/my/cleanup/script" as uid dba and gid dba
#
#
## Check directory permission, uid and gid. An event is triggered if the
## directory does not belong to the user with uid 0 and gid 0. In addition,
## the permissions have to match the octal description of 755 (see chmod(1)).
#
# check directory bin with path /bin
# if failed permission 755 then unmonitor
# if failed uid 0 then unmonitor
# if failed gid 0 then unmonitor
#
#
## Check a remote host availability by issuing a ping test and check the
## content of a response from a web server. Up to three pings are sent and
## connection to a port and an application level network check is performed.
#
# check host myserver with address 192.168.1.1
# if failed icmp type echo count 3 with timeout 3 seconds then alert
# if failed port 3306 protocol mysql with timeout 15 seconds then alert
# if failed url http://user:[email protected]:8080/?querystring
# and content == 'action="j_security_check"'
# then alert
#
#
###############################################################################
## Includes
###############################################################################
##
## It is possible to include additional configuration parts from other files or
## directories.
#
# include /etc/monit.d/*
#
未完 待续。。。。。。。