Monit config files

_etc_monit.d_mysql

check process mysql
  with pidfile /var/run/mysqld/mysqld.pid
  start program = "/usr/sbin/service mysql start" with timeout 60 seconds
  stop program = "/usr/sbin/service mysql stop" with timeout 60 seconds
  if totalmem > 400 MB for 5 cycles then alert
  if totalmem > 600 MB for 5 cycles then restart
  if cpu > 50% for 5 cycles then alert
  if cpu > 90% for 5 cycles then restart
  if 3 restarts within 5 cycles then timeout

_etc_monit.d_system

check system wp01
  if loadavg(5min) > 1 then alert
  if memory usage > 90% for 5 cycles then alert
  if cpu usage (user) > 90% for 5 cycles then alert

_etc_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 '/'.
##
## 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 20

## 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 /var/log/monit.log

## Set the location of the Monit lock file which stores the process id of the
## running Monit instance. By default this file is stored in $HOME/.monit.pid
set pidfile /var/run/monit.pid

## 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/lib/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/lib/monit/state

## Set the list of mail servers for alert delivery. Multiple servers may be
## specified using a comma separator. If the first mail server fails, Monit
# will use the second mail server in the list and so on. By default Monit uses
# port 25 - it is possible to override this with the PORT option.
set mailserver smtp.mailgun.org
  port 587
  username "[email protected]"
  password "secret"
  with timeout 60 seconds

## 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 queue size
## by using the SLOTS option (if omitted, the queue is limited by space
## available in the back end filesystem).
set eventqueue
  basedir /var/lib/monit/events
  slots 100

## 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 format for alerts if the the mail-format
## statement is missing::
## --8<--
## set mail-format {
##      from: monit@$HOST
##   subject: monit alert --  $EVENT $SERVICE
##   message: $EVENT Service $SERVICE
##                 Date:        $DATE
##                 Action:      $ACTION
##                 Host:        $HOST
##                 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]
  subject: [Monit] $HOST - $SERVICE - $ACTION - $EVENT
  message: $DESCRIPTION
}

## 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] NOT ON { action, instance }

## Monit has an embedded HTTP interface which can be used to view status of
## services monitored and manage services from a web interface. The HTTP
## interface is also required if you want to issue Monit commands from the
## command line, such as 'monit status' or 'monit restart service' The reason
## for this is that the Monit client uses the HTTP interface to send these
## commands to a running Monit daemon. See the Monit Wiki if you want to
## enable SSL for the web server.
set httpd port 2812
  allow chief:"secret"

###############################################################################
## 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 [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 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 ping then alert
#    if failed port 3306 protocol mysql with timeout 15 seconds then alert
#    if failed port 80 protocol http
#       and request /some/path with content = "a string"
#    then alert
#
#
###############################################################################
## Includes
###############################################################################
##
## It is possible to include additional configuration parts from other files or
## directories.

include /etc/monit.d/system
include /etc/monit.d/mysql