wget http://www.mmonit.org/monit/dist/monit-5.2.1.tar.gz
tar -zxvf monit-5.2.1.tar.gz
yum install flex
yum install bioson
yum install byacc
./configure –prefix=/usr/local/monit –without-ssl
cp /home/whw/monit-5.2.1/monitrc /etc/
/etc/monitrc
set daemon 120 # 设置monit作为守护进程运行，并且每2分钟监视一次
set logfile /var/log/monit.log # 设置日志文件的位置
set httpd port 2812 and use address 192.168.1.184 # monit内置了一个用于查看被监视服务状态的http服务器,注意在防火墙中开启
allow localhost # 允许本地访问
allow 192.168.1.1/255.255.255.0 # 允许内网访问
allow admin:monit11 # 设置使用用户名admin和密码monit11
set mailserver localhost
set alert yourname@mailaddress
要打开2812端口
/sbin/iptables -A INPUT -i eth0 -p tcp --dport 2812 -j ACCEPT
/sbin/service iptables save
打开catalina.sh文件,在开头处加入CATALINA_PID=/var/run/catalina.pid,因为tomcat进程默认是不使用pid文件的
# 下面设置监视tomcat
check process tomcat2 with pidfile /var/run/catalina.pid
start program = "/etc/init.d/tomcat start" #设置启动命令
stop program = "/etc/init.d/tomcat stop" #设置停止命令
if 9 restarts within 10 cycles then timeout #设置在10个监视周期内重
#启了9次则超时,不再监视
#这个服务。
if cpu usage > 90% for 5 cycles then alert #如果在5个周期内该服务的cpu使用率都超过90%则提示
# 若连续5个周期打开url都失败（120秒超时，超时认为也失败）则重启服务
if failed url http://127.0.0.1:4000/ timeout 120 seconds for 5 cycles then restart
if failed url http://127.0.0.1:5000/ timeout 120 seconds for 5 cycles then restart
如果要监视其它服务，可以加入更多的监视逻辑，例如要监视mysql服务，可以：
check process mysql with pidfile /var/run/mysqld/mysqld.pid
start program = /etc/init.d/mysqld start"
stop program = "/etc/init.d/mysqld stop"
if failed host 127.0.0.1 port 3306 then restart
if 5 restarts within 5 cycles then timeout
监视ssh服务：
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 port 22 protocol SSH then restart
if 5 restarts within 5 cycles then timeout
如果监视的服务比较多,可以将各个服务的监视逻辑放在不同的文件,然后使用include命令包含进来,使配置文件更加清晰。
include /etc/monit/includes/mysqld
可以设置monit随系统启动,在/etc/inittab文件的最后加入
# Run monit in standard run-levels
mo:2345:respawn:/usr/local/bin/monit -Ic /etc/monitrc
更新init
telinit q
注意：由于将monit设置成为了守护进程,并且在inittab中加入了随系统启动的设置,则monit进程如果停止,init进程会将其重启,而monit又监视着其它的服务,这意味着monit所监视的服务不能使用一般的方法来停止,因为一停止,monit又会将其启动.要停止monit所监视的服务,应该使用monit stop name这样的命令,例如要停止tomcat: monit stop tomcat
要停止全部monit所监视的服务可以使用monit stop all.
要启动某个服务可以用monit stop name这样的命令,启动全部则是monit start all.
对于monit配置进行更新，需要使用monit quit进行重新加载
附：我的配置文件
/////////////////////////////////////////////
###############################################################################
## Monit control file
###############################################################################
##
## Comments begin with a ‘#’ and extend through the end of the line. Keywords
## are case insensitive. All path’s MUST BE FULLY QUALIFIED, starting with ‘/’.
##
## Below you will find examples of some frequently used statements. For
## information about the control file and a complete list of statements and
## options, please have a look in the Monit manual.
##
##
###############################################################################
## Global section
###############################################################################
##
## Start Monit in the background (run as a daemon):
#
set daemon 12 # 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 syslog logging with the ‘daemon’ facility. If the FACILITY option is
## omitted, Monit will use ‘user’ facility by default. If you want to log to
## a standalone log file instead, specify the full path to the log file
#
set logfile syslog facility log_daemon
set logfile /usr/local/monit/monit.log
#
#
### Set the location of the Monit id file which stores the unique id for the
### Monit instance. The id is generated and stored on first Monit start. By
### default the file is placed in $HOME/.monit.id.
#
set idfile /var/.monit.id
#
### Set the location of the Monit state file which saves monitoring states
### on each cycle. By default the file is placed in $HOME/.monit.state. If
### the state file is stored on a persistent filesystem, Monit will recover
### the monitoring state across reboots. If it is on temporary filesystem, the
### state will be lost on reboot which may be convenient in some situations.
#
# set statefile /var/.monit.state
#
## Set the list of mail servers for alert delivery. Multiple servers may be
## specified using a comma separator. By default Monit uses port 25 – it is
## possible to override this with the PORT option.
#
set mailserver localhost, # primary mailserver
# backup.bar.baz port 10025, # backup mailserver on port 10025
# localhost # fallback relay
#
#
## By default Monit will drop alert events if no mail servers are available.
## If you want to keep the alerts for later delivery retry, you can use the
## EVENTQUEUE statement. The base directory where undelivered alerts will be
## stored is specified by the BASEDIR option. You can limit the maximal queue
## size using the SLOTS option (if omitted, the queue is limited by space
## available in the back end filesystem).
#
# set eventqueue
# basedir /var/monit # set the base directory where events will be stored
# slots 100 # optionally limit the queue size
#
#
## Send status and events to M/Monit (for more informations about M/Monit
## see http://mmonit.com/). By default Monit registers credentials with
## M/Monit so M/Monit can smoothly communicate back to Monit and you don’t
## have to register Monit credentials manually in M/Monit. It is possible to
## disable credential registration using the commented out option below.
## Though, if safety is a concern we recommend instead using https when
## communicating with M/Monit and send credentials encrypted.
#
# set mmonit http://monit:monit@192.168.1.10:8080/collector
# # and register without credentials # Don’t register credentials
#
#
#
## Monit by default uses the following alert mail format:
##
## –8<–
## From: monit@$HOST # sender
## Subject: monit alert — $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: whw@ninhao.com }
#
#
## 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 569108268@qq.com # receive all alerts
set alert 569108268@qq.com only on { timeout } # receive just service-
# # timeout alert
#
#
## 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 172.16.1.201 # only accept connection from localhost
allow 172.16.1.1/255.255.255.0 # 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
#
#
###############################################################################
## 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.
#
# check system myhost.mydomain.tld
# if loadavg (1min) > 4 then alert
# if loadavg (5min) > 2 then alert
# if memory usage > 75% then alert
# if swap usage > 25% then alert
# if cpu usage (user) > 70% then alert
# if cpu usage (system) > 30% then alert
# if cpu usage (wait) > 20% 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 timeout
# depends on apache_bin
# group server
#
#
## 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
# 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:password@www.foo.bar: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/*
#
#apache//////////////////////////////
check process apache 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
#nginx///////////////////////////////
check process nginx with pidfile /usr/local/nginx/nginx.pid
group nobody
start program = “/usr/local/nginx/sbin/nginx”
stop program = “/bin/bash -c ‘/bin/kill `cat /usr/local/nginx/nginx.pid`’”
#if failed url http://172.16.1.201:8383 then restart
if failed host 172.16.1.201 port 8383 protocol http then restart
#if 5 restarts within 5 cycles then timeout
#mysql ////////////////////////////
check process mysql with pidfile /usr/local/mysql/var/localhost.pid
group database
start program = “/etc/init.d/mysqld start”
stop program = “/etc/init.d/mysqld stop”
if failed host localhost port 3306 protocol mysql then restart
/////////////////////////////////////////////
