How Monit

moint-how-to.conf

###############################################################################
#操作系统CentOS 5
#1：#yum –y install monit
#2:修改主配置文件
#vi /etc/monit.conf
#################################################################### ##########
#黄色部分是上次修改过的，根据实际情况配置
###############################################################################
## 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  30 start delay 60        //设置monit为后台进程，每30秒为一个检查周期，首次启动后4分钟开始第一次检查
# 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    //设置系统日志，这是默认设定，可以手动配置指定日志文件                  
#
#
### 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 /etc/rc.d/init.d/monit   //设置monit对象实例，这里的对象是指本机
#
### 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    //设置状态报告文件
#
## 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         mail.surfront.com              # primary mailserver  //设置邮件服务器，通过它来发送邮件告警
#                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
//设置事件报告，每个事件对应的文件最大大小为100KB
#
#
## 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:[email protected]: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: [email protected] }
#
#
## 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    //设置告警要发往的邮箱
set alert [email protected] only on { timeout }  # receive just service-     //当发送失败后，发送的另外一个备用邮箱
#                                                # 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 localhost  //设定http访问端口，只允许本机访问
    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'//登录用户和密码
    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.
#检查负载
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 [email protected] 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 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
 
check process mysqld with pidfile /var/run/mysqld/mysqld.pid
   group database
   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
 
check process surfront with pidfile /var/run/surfront.pid
   start program = "/etc/init.d/surfd start"
   stop program = "/etc/init.d/surfd stop"
   if failed host 127.0.0.1 port 15902 then restart
   if 5 restarts within 5 cycles then timeout
 
check process surfadmin with pidfile /var/run/admin.pid
   start program = "/etc/init.d/surfd start"
   stop program = "/etc/init.d/surfd stop"
   if failed host 127.0.0.1 port 15919 then restart
   if 5 restarts within 5 cycles then timeout
 
check process surfguard with pidfile /var/run/surfguard.pid
   start program = "/etc/init.d/watchdog start"
   stop program = "/etc/init.d/watchdog stop"
   if failed host 127.0.0.1 port 16217 then restart
   if 5 restarts within 5 cycles then timeout
 
check process crond with pidfile /var/run/crond.pid
   start program = "/etc/init.d/crond start"
   stop program = "/etc/init.d/crond stop"
   if failed host 127.0.0.1 port 18973 then restart
   if 5 restarts within 5 cycles then timeout
 
#check process nginx with pidfile /var/run/nginx.pid
#    start program = "/etc/init.d/nginx start"
#    stop program  = "/etc/init.d/nginx stop"
#    if failed host 127.0.0.1 port 80 then restart
#    if 5 restarts within 5 cycles then timeout
 
#check process php_cgi with pidfile /var/run/php_cgi.pid
#    start program = "/etc/init.d/php_cgi start"
#    stop program  = "/etc/init.d/php_cgi stop"
#    if failed host 127.0.0.1 port 9000 then restart
#    if 5 restarts within 5 cycles then timeout
#   
## 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:[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/*
#
#