|
| 1 | +############################################################################### |
| 2 | +## Monit control file |
| 3 | +############################################################################### |
| 4 | +## |
| 5 | +## Comments begin with a '#' and extend through the end of the line. Keywords |
| 6 | +## are case insensitive. All path's MUST BE FULLY QUALIFIED, starting with '/'. |
| 7 | +## |
| 8 | +## Below you will find examples of some frequently used statements. For |
| 9 | +## information about the control file and a complete list of statements and |
| 10 | +## options, please have a look in the Monit manual. |
| 11 | +## |
| 12 | +## |
| 13 | +############################################################################### |
| 14 | +## Global section |
| 15 | +############################################################################### |
| 16 | +## |
| 17 | +## Start Monit in the background (run as a daemon): |
| 18 | +# |
| 19 | +set daemon 30 # check services at 30 seconds intervals |
| 20 | +# with start delay 240 # optional: delay the first check by 4-minutes (by |
| 21 | +# # default Monit check immediately after Monit start) |
| 22 | +# |
| 23 | +# |
| 24 | +## Set syslog logging. If you want to log to a standalone log file instead, |
| 25 | +## specify the full path to the log file |
| 26 | +# |
| 27 | +set log syslog |
| 28 | + |
| 29 | +# |
| 30 | +# |
| 31 | +## Set the location of the Monit lock file which stores the process id of the |
| 32 | +## running Monit instance. By default this file is stored in $HOME/.monit.pid |
| 33 | +# |
| 34 | +# set pidfile /var/run/monit.pid |
| 35 | +# |
| 36 | +## Set the location of the Monit id file which stores the unique id for the |
| 37 | +## Monit instance. The id is generated and stored on first Monit start. By |
| 38 | +## default the file is placed in $HOME/.monit.id. |
| 39 | +# |
| 40 | +# set idfile /var/.monit.id |
| 41 | +# |
| 42 | +## Set the location of the Monit state file which saves monitoring states |
| 43 | +## on each cycle. By default the file is placed in $HOME/.monit.state. If |
| 44 | +## the state file is stored on a persistent filesystem, Monit will recover |
| 45 | +## the monitoring state across reboots. If it is on temporary filesystem, the |
| 46 | +## state will be lost on reboot which may be convenient in some situations. |
| 47 | +# |
| 48 | +# set statefile /var/.monit.state |
| 49 | +# |
| 50 | +# |
| 51 | + |
| 52 | +## Set limits for various tests. The following example shows the default values: |
| 53 | +## |
| 54 | +# set limits { |
| 55 | +# programOutput: 512 B, # check program's output truncate limit |
| 56 | +# sendExpectBuffer: 256 B, # limit for send/expect protocol test |
| 57 | +# fileContentBuffer: 512 B, # limit for file content test |
| 58 | +# httpContentBuffer: 1 MB, # limit for HTTP content test |
| 59 | +# networkTimeout: 5 seconds # timeout for network I/O |
| 60 | +# programTimeout: 300 seconds # timeout for check program |
| 61 | +# stopTimeout: 30 seconds # timeout for service stop |
| 62 | +# startTimeout: 30 seconds # timeout for service start |
| 63 | +# restartTimeout: 30 seconds # timeout for service restart |
| 64 | +# } |
| 65 | + |
| 66 | +## Set global SSL options (just most common options showed, see manual for |
| 67 | +## full list). |
| 68 | +# |
| 69 | +# set ssl { |
| 70 | +# verify : enable, # verify SSL certificates (disabled by default but STRONGLY RECOMMENDED) |
| 71 | +# selfsigned : allow # allow self signed SSL certificates (reject by default) |
| 72 | +# } |
| 73 | +# |
| 74 | +# |
| 75 | +## Set the list of mail servers for alert delivery. Multiple servers may be |
| 76 | +## specified using a comma separator. If the first mail server fails, Monit |
| 77 | +## will use the second mail server in the list and so on. By default Monit uses |
| 78 | +## port 25 - it is possible to override this with the PORT option. |
| 79 | +# |
| 80 | +# set mailserver mail.bar.baz, # primary mailserver |
| 81 | +# backup.bar.baz port 10025, # backup mailserver on port 10025 |
| 82 | +# localhost # fallback relay |
| 83 | +# |
| 84 | +# |
| 85 | +## By default Monit will drop alert events if no mail servers are available. |
| 86 | +## If you want to keep the alerts for later delivery retry, you can use the |
| 87 | +## EVENTQUEUE statement. The base directory where undelivered alerts will be |
| 88 | +## stored is specified by the BASEDIR option. You can limit the queue size |
| 89 | +## by using the SLOTS option (if omitted, the queue is limited by space |
| 90 | +## available in the back end filesystem). |
| 91 | +# |
| 92 | +# set eventqueue |
| 93 | +# basedir /var/monit # set the base directory where events will be stored |
| 94 | +# slots 100 # optionally limit the queue size |
| 95 | +# |
| 96 | +# |
| 97 | +## Send status and events to M/Monit (for more information about M/Monit |
| 98 | +## see https://mmonit.com/). By default Monit registers credentials with |
| 99 | +## M/Monit so M/Monit can smoothly communicate back to Monit and you don't |
| 100 | +## have to register Monit credentials manually in M/Monit. It is possible to |
| 101 | +## disable credential registration using the commented out option below. |
| 102 | +## Though, if safety is a concern we recommend instead using https when |
| 103 | +## communicating with M/Monit and send credentials encrypted. The password |
| 104 | +## should be URL encoded if it contains URL-significant characters like |
| 105 | +## ":", "?", "@". Default timeout is 5 seconds, you can customize it by |
| 106 | +## adding the timeout option. |
| 107 | +# |
| 108 | +# set mmonit http://monit:monit@192.168.1.10:8080/collector |
| 109 | +# # with timeout 30 seconds # Default timeout is 5 seconds |
| 110 | +# # and register without credentials # Don't register credentials |
| 111 | +# |
| 112 | +# |
| 113 | +## Monit by default uses the following format for alerts if the mail-format |
| 114 | +## statement is missing:: |
| 115 | +## --8<-- |
| 116 | +## set mail-format { |
| 117 | +## from: Monit <monit@$HOST> |
| 118 | +## subject: monit alert -- $EVENT $SERVICE |
| 119 | +## message: $EVENT Service $SERVICE |
| 120 | +## Date: $DATE |
| 121 | +## Action: $ACTION |
| 122 | +## Host: $HOST |
| 123 | +## Description: $DESCRIPTION |
| 124 | +## |
| 125 | +## Your faithful employee, |
| 126 | +## Monit |
| 127 | +## } |
| 128 | +## --8<-- |
| 129 | +## |
| 130 | +## You can override this message format or parts of it, such as subject |
| 131 | +## or sender using the MAIL-FORMAT statement. Macros such as $DATE, etc. |
| 132 | +## are expanded at runtime. For example, to override the sender, use: |
| 133 | +# |
| 134 | +# set mail-format { from: monit@foo.bar } |
| 135 | +# |
| 136 | +# |
| 137 | +## You can set alert recipients whom will receive alerts if/when a |
| 138 | +## service defined in this file has errors. Alerts may be restricted on |
| 139 | +## events by using a filter as in the second example below. |
| 140 | +# |
| 141 | +# set alert sysadm@foo.bar # receive all alerts |
| 142 | +# |
| 143 | +## Do not alert when Monit starts, stops or performs a user initiated action. |
| 144 | +## This filter is recommended to avoid getting alerts for trivial cases. |
| 145 | +# |
| 146 | +# set alert your-name@your.domain not on { instance, action } |
| 147 | +# |
| 148 | +# |
| 149 | +## Monit has an embedded HTTP interface which can be used to view status of |
| 150 | +## services monitored and manage services from a web interface. The HTTP |
| 151 | +## interface is also required if you want to issue Monit commands from the |
| 152 | +## command line, such as 'monit status' or 'monit restart service' The reason |
| 153 | +## for this is that the Monit client uses the HTTP interface to send these |
| 154 | +## commands to a running Monit daemon. See the Monit Wiki if you want to |
| 155 | +## enable SSL for the HTTP interface. |
| 156 | +# |
| 157 | +set httpd port 2812 and |
| 158 | + use address localhost # only accept connection from localhost (drop if you use M/Monit) |
| 159 | + allow localhost # allow localhost to connect to the server and |
| 160 | + allow admin:monit # require user 'admin' with password 'monit' |
| 161 | + #with ssl { # enable SSL/TLS and set path to server certificate |
| 162 | + # pemfile: /etc/ssl/certs/monit.pem |
| 163 | + #} |
| 164 | +# |
| 165 | +## Monit can perform act differently regarding services previous state when |
| 166 | +## going back in duty. By default, Monit will 'start' all services. Monit can |
| 167 | +## also takes no action to start services in 'nostart' mode. Monit can try to |
| 168 | +## restore the 'laststate' of the service when Monit was shutdown. |
| 169 | +# set onreboot start # start, nostart, laststart |
| 170 | + |
| 171 | +############################################################################### |
| 172 | +## Services |
| 173 | +############################################################################### |
| 174 | +## |
| 175 | +## Check general system resources such as load average, cpu and memory |
| 176 | +## usage. Each test specifies a resource, conditions and the action to be |
| 177 | +## performed should a test fail. |
| 178 | +# |
| 179 | +# check system $HOST |
| 180 | +# if loadavg (1min) per core > 2 for 5 cycles then alert |
| 181 | +# if loadavg (5min) per core > 1.5 for 10 cycles then alert |
| 182 | +# if cpu usage > 95% for 10 cycles then alert |
| 183 | +# if memory usage > 75% then alert |
| 184 | +# if swap usage > 25% then alert |
| 185 | +# |
| 186 | +# |
| 187 | +## Check if a file exists, checksum, permissions, uid and gid. In addition |
| 188 | +## to alert recipients in the global section, customized alert can be sent to |
| 189 | +## additional recipients by specifying a local alert handler. The service may |
| 190 | +## be grouped using the GROUP option. More than one group can be specified by |
| 191 | +## repeating the 'group name' statement. |
| 192 | +# |
| 193 | +# check file apache_bin with path /usr/local/apache/bin/httpd |
| 194 | +# if failed checksum and |
| 195 | +# expect the sum 8f7f419955cefa0b33a2ba316cba3659 then unmonitor |
| 196 | +# if failed permission 755 then unmonitor |
| 197 | +# if failed uid "root" then unmonitor |
| 198 | +# if failed gid "root" then unmonitor |
| 199 | +# alert security@foo.bar on { |
| 200 | +# checksum, permission, uid, gid, unmonitor |
| 201 | +# } with the mail-format { subject: Alarm! } |
| 202 | +# group server |
| 203 | +# |
| 204 | +# |
| 205 | +## Check that a process is running, in this case Apache, and that it respond |
| 206 | +## to HTTP and HTTPS requests. Check its resource usage such as cpu and memory, |
| 207 | +## and number of children. If the process is not running, Monit will restart |
| 208 | +## it by default. In case the service is restarted very often and the |
| 209 | +## problem remains, it is possible to disable monitoring using the TIMEOUT |
| 210 | +## statement. This service depends on another service (apache_bin) which |
| 211 | +## is defined above. |
| 212 | +# |
| 213 | +# check process apache with pidfile /usr/local/apache/logs/httpd.pid |
| 214 | +# start program = "/etc/init.d/httpd start" with timeout 60 seconds |
| 215 | +# stop program = "/etc/init.d/httpd stop" |
| 216 | +# if cpu > 60% for 2 cycles then alert |
| 217 | +# if cpu > 80% for 5 cycles then restart |
| 218 | +# if totalmem > 200.0 MB for 5 cycles then restart |
| 219 | +# if children > 250 then restart |
| 220 | +# if disk read > 500 kb/s for 10 cycles then alert |
| 221 | +# if disk write > 500 kb/s for 10 cycles then alert |
| 222 | +# if failed host www.tildeslash.com port 80 protocol http and request "/somefile.html" then restart |
| 223 | +# if failed port 443 protocol https with timeout 15 seconds then restart |
| 224 | +# if 3 restarts within 5 cycles then unmonitor |
| 225 | +# depends on apache_bin |
| 226 | +# group server |
| 227 | +# |
| 228 | +# |
| 229 | +## Check filesystem permissions, uid, gid, space usage, inode usage and disk I/O. |
| 230 | +## Other services, such as databases, may depend on this resource and an automatically |
| 231 | +## graceful stop may be cascaded to them before the filesystem will become full and data |
| 232 | +## lost. |
| 233 | +# |
| 234 | +# check filesystem datafs with path /dev/sdb1 |
| 235 | +# start program = "/bin/mount /data" |
| 236 | +# stop program = "/bin/umount /data" |
| 237 | +# if failed permission 660 then unmonitor |
| 238 | +# if failed uid "root" then unmonitor |
| 239 | +# if failed gid "disk" then unmonitor |
| 240 | +# if space usage > 80% for 5 times within 15 cycles then alert |
| 241 | +# if space usage > 99% then stop |
| 242 | +# if inode usage > 30000 then alert |
| 243 | +# if inode usage > 99% then stop |
| 244 | +# if read rate > 1 MB/s for 5 cycles then alert |
| 245 | +# if read rate > 500 operations/s for 5 cycles then alert |
| 246 | +# if write rate > 1 MB/s for 5 cycles then alert |
| 247 | +# if write rate > 500 operations/s for 5 cycles then alert |
| 248 | +# if service time > 10 milliseconds for 3 times within 5 cycles then alert |
| 249 | +# group server |
| 250 | +# |
| 251 | +# |
| 252 | +## Check a file's timestamp. In this example, we test if a file is older |
| 253 | +## than 15 minutes and assume something is wrong if its not updated. Also, |
| 254 | +## if the file size exceed a given limit, execute a script |
| 255 | +# |
| 256 | +# check file database with path /data/mydatabase.db |
| 257 | +# if failed permission 700 then alert |
| 258 | +# if failed uid "data" then alert |
| 259 | +# if failed gid "data" then alert |
| 260 | +# if timestamp > 15 minutes then alert |
| 261 | +# if size > 100 MB then exec "/my/cleanup/script" as uid dba and gid dba |
| 262 | +# |
| 263 | +# |
| 264 | +## Check directory permission, uid and gid. An event is triggered if the |
| 265 | +## directory does not belong to the user with uid 0 and gid 0. In addition, |
| 266 | +## the permissions have to match the octal description of 755 (see chmod(1)). |
| 267 | +# |
| 268 | +# check directory bin with path /bin |
| 269 | +# if failed permission 755 then unmonitor |
| 270 | +# if failed uid 0 then unmonitor |
| 271 | +# if failed gid 0 then unmonitor |
| 272 | +# |
| 273 | +# |
| 274 | +## Check a remote host availability by issuing a ping test and check the |
| 275 | +## content of a response from a web server. Up to three pings are sent and |
| 276 | +## connection to a port and an application level network check is performed. |
| 277 | +# |
| 278 | +# check host myserver with address 192.168.1.1 |
| 279 | +# if failed ping then alert |
| 280 | +# if failed port 3306 protocol mysql with timeout 15 seconds then alert |
| 281 | +# if failed port 80 protocol http |
| 282 | +# and request /some/path with content = "a string" |
| 283 | +# then alert |
| 284 | +# |
| 285 | +# |
| 286 | +## Check a network link status (up/down), link capacity changes, saturation |
| 287 | +## and bandwidth usage. |
| 288 | +# |
| 289 | +# check network public with interface eth0 |
| 290 | +# if link down then alert |
| 291 | +# if changed link then alert |
| 292 | +# if saturation > 90% then alert |
| 293 | +# if download > 10 MB/s then alert |
| 294 | +# if total uploaded > 1 GB in last hour then alert |
| 295 | +# |
| 296 | +# |
| 297 | +## Check custom program status output. |
| 298 | +# |
| 299 | +# check program myscript with path /usr/local/bin/myscript.sh |
| 300 | +# if status != 0 then alert |
| 301 | +# |
| 302 | +# |
| 303 | +############################################################################### |
| 304 | +## Includes |
| 305 | +############################################################################### |
| 306 | +## |
| 307 | +## It is possible to include additional configuration parts from other files or |
| 308 | +## directories. |
| 309 | +# |
| 310 | +# include /etc/monit.d/* |
| 311 | +# |
0 commit comments