<% @path = '/etc/monit/monitrc' %> ############################################################################### ## 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 '/'. ## ## Bellow is the example of some frequently used statements. For information ## about the control file, a complete list of statements and options please ## have a look in the monit manual. ## ## ############################################################################### ## Global section ############################################################################### ## ## Start monit in background (run as daemon) and check the services at 2-minute ## intervals. # # set daemon 120 set daemon 60 # # ## Set syslog logging with the 'daemon' facility. If the FACILITY option is ## omited, monit will use 'user' facility by default. You can specify the ## path to the file for monit native logging. # # set logfile syslog facility log_daemon set logfile /var/log/monit.log # # ## Set list of mailservers for alert delivery. Multiple servers may be ## specified using comma separator. By default monit uses port 25 - it is ## possible to override it with the PORT option. # # set mailserver mail.bar.baz, # primary mailserver # backup.bar.baz port 10025, # backup mailserver on port 10025 # localhost # fallback relay # # ## By default monit will drop the event alert, in the case that there is no ## mailserver available. In the case that you want to keep the events for ## later delivery retry, you can use the EVENTQUEUE statement. The base ## directory where undelivered events will be stored is specified by the ## BASEDIR option. You can limit the maximal queue size using the SLOTS ## option (if omited then the queue is limited just by the backend filesystem). # # set eventqueue # basedir /var/monit # set the base directory where events will be stored # slots 100 # optionaly limit the queue size # # ## 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 the alert message format or its parts such as subject ## or sender using the MAIL-FORMAT statement. Macros such as $DATE, etc. ## are expanded on runtime. For example to override the sender: # # set mail-format { from: monit@foo.bar } # # ## You can set the alert recipients here, which will receive the alert for ## each service. The event alerts may be restricted using the list. # # set alert sysadm@foo.bar # receive all alerts # set alert manager@foo.bar only on { timeout } # receive just service- # # timeout alert # excluding instance, changed set alert <%= rubber_env.admin_email %> only on { connection checksum data exec gid icmp invalid nonexist permission resource size timeout timestamp uid } # # ## Monit has an embedded webserver, which can be used to view the ## configuration, actual services parameters or manage the services using the ## web interface. # # 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' # <% tools_server = rubber_instances.for_role('web_tools').first.internal_ip rescue "127.0.0.1" %> set httpd port <%= rubber_env.monit_admin_port %> allow <%= tools_server %> # ############################################################################### ## Services ############################################################################### ## ## Check the general system resources such as load average, cpu and memory ## usage. Each rule specifies the tested resource, the limit and the action ## which will be performed in the case that the test failed. # # check system myhost.mydomain.tld # if loadavg (1min) > 4 then alert # if loadavg (5min) > 2 then alert # if memory usage > 75% then alert # if cpu usage (user) > 70% then alert # if cpu usage (system) > 30% then alert # if cpu usage (wait) > 20% then alert # # ## Check a file for existence, checksum, permissions, uid and gid. In addition ## to the recipients in the global section, customized alert will be send to ## the additional recipient. The service may be grouped using the GROUP option. # # 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, responding on the HTTP and HTTPS request, ## check its resource usage such as cpu and memory, number of childrens. ## In the case that the process is not running, monit will restart it by ## default. In the case that the service was restarted very often and the ## problem remains, it is possible to disable the monitoring using the ## TIMEOUT statement. The service depends on another service (apache_bin) which ## is defined in the monit control file as well. # # check process apache with pidfile /usr/local/apache/logs/httpd.pid # start program = "/etc/init.d/httpd start" # 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 "/monit/doc/next.php" # 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 the device permissions, uid, gid, space and inode usage. Other ## services such as databases may depend on this resource and automatical ## graceful stop may be cascaded to them before the filesystem will become ## full and the data will be lost. # # check device 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: when it becomes older then 15 minutes, the ## file is not updated and something is wrong. In the case that the size ## of the file exceeded given limit, perform the 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" # # ## Check the directory permission, uid and gid. An event is triggered ## if the directory does not belong to the user with the uid 0 and ## the gid 0. In the 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 the remote host network services availability and the response ## content. One of three pings, a successfull connection to a port and ## 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 the configuration or its parts from other files or ## directories. # include /etc/monit/monit.d/*.conf # #