mirror of
https://github.com/jimeh/skyhook.git
synced 2026-02-19 11:06:38 +00:00
307 lines
11 KiB
Plaintext
307 lines
11 KiB
Plaintext
|
|
|
|
# set polling interval
|
|
set daemon 60
|
|
|
|
|
|
# default log file
|
|
set logfile /var/log/monit/monit.log
|
|
|
|
|
|
# mail server configuration
|
|
set mailserver
|
|
localhost
|
|
|
|
|
|
# set "from" email address
|
|
set mail-format { from: monit@heartb.it }
|
|
|
|
|
|
# default email address to send alerts to
|
|
set alert serverstatus@heartb.it
|
|
|
|
|
|
# event queue configuration
|
|
set eventqueue
|
|
basedir /var/monit/queue
|
|
slots 5000
|
|
|
|
|
|
# web-interface setup
|
|
set httpd port 2812
|
|
allow "admin":"admin"
|
|
|
|
|
|
|
|
# monitor nginx
|
|
check process nginx with pidfile /var/run/nginx.pid
|
|
start = "/etc/init.d/nginx start"
|
|
stop = "/etc/init.d/nginx stop"
|
|
if failed host localhost port 4041 then restart
|
|
if cpu usage > 95% for 3 cycles then restart
|
|
if 5 restarts within 15 cycles then timeout
|
|
group app
|
|
|
|
|
|
# monitor memcahe
|
|
check process memcache with pidfile /var/run/memcached.pid
|
|
start = "/etc/init.d/memcached start"
|
|
stop = "/etc/init.d/memcached stop"
|
|
if totalmem > 90% for 2 cycles then restart
|
|
if 5 restarts within 15 cycles then timeout
|
|
group app
|
|
|
|
|
|
# monitor starling
|
|
check process starling with pidfile /var/run/starling.pid
|
|
start = "/etc/init.d/starling start"
|
|
stop = "/etc/init.d/starling stop"
|
|
if cpu usage > 20% for 2 cycles then alert
|
|
if cpu usage > 75% for 2 cycles then restart
|
|
if totalmem > 50% for 2 cycles then restart
|
|
if 5 restarts within 15 cycles then timeout
|
|
group app
|
|
|
|
|
|
# monitor apache
|
|
# check process apache with pidfile /var/run/apache2.pid
|
|
# start = "/etc/init.d/apache2 start"
|
|
# stop = "/etc/init.d/apache2 stop"
|
|
# if failed host 127.0.0.1 port 81 for 2 cycles then restart
|
|
# if cpu usage > 60% for 2 cycles then alert
|
|
# if cpu usage > 98% for 5 cycles then restart
|
|
# if 5 restarts within 5 cycles then timeout
|
|
# group server
|
|
|
|
|
|
|
|
# monitor main file system
|
|
check device root with path /dev/sda1
|
|
if space usage > 80% for 5 times within 15 cycles then alert
|
|
group server
|
|
|
|
# monitor /mnt file system
|
|
check device mnt with path /dev/sda2
|
|
if space usage > 80% for 5 times within 15 cycles then alert
|
|
group server
|
|
|
|
|
|
|
|
###############################################################################
|
|
## 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, 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) and check services at
|
|
## 2-minute intervals.
|
|
#
|
|
# set daemon 120
|
|
#
|
|
#
|
|
## 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 stand alone log file instead, specify the path to a log file
|
|
#
|
|
# set logfile syslog facility log_daemon
|
|
#
|
|
#
|
|
## Set the list of mail servers for alert delivery. Multiple servers may be
|
|
## specified using comma separator. By default monit uses port 25 - this
|
|
## is possible to override 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 alert events if no mail servers are available.
|
|
## If you want to keep the alerts for a 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 # 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 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:
|
|
#
|
|
# set mail-format { from: monit@foo.bar }
|
|
#
|
|
#
|
|
## You can set alert recipients here 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 sysadm@foo.bar # receive all alerts
|
|
# set alert manager@foo.bar only on { timeout } # receive just service-
|
|
# # timeout alert
|
|
#
|
|
#
|
|
## Monit has an embedded web server which can be used to view status of
|
|
## services monitored, the current configuration, actual services parameters
|
|
## and manage services from a 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'
|
|
#
|
|
#
|
|
###############################################################################
|
|
## 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 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 alert recipients in the global section, customized alert will be sent to
|
|
## additional recipients by specifying a local alert handler. 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, 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 was 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"
|
|
# 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 device 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 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. 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"
|
|
#
|
|
#
|
|
## 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 network services availability using a ping test and
|
|
## check response content from a web server. Up to three pings are sent and
|
|
## connection to a port and a 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/*
|
|
#
|
|
#
|