| 37 |
|
|
| 38 |
|
# The time interval at which the Queue's should be monitored |
| 39 |
|
Queue.MonitorInterval=15 |
| 40 |
+ |
# The upper limit for a Queue |
| 41 |
+ |
Queue.SizeLimit=1000 |
| 42 |
+ |
# The removal algorithm |
| 43 |
+ |
Queue.RemoveAlgorithm=FIRST |
| 44 |
|
|
| 45 |
|
|
| 42 |
– |
|
| 46 |
|
############################################################ |
| 47 |
|
#### FilterManager configuration |
| 48 |
|
############################################################ |
| 61 |
|
Filter.TCPListenPort=4589 |
| 62 |
|
|
| 63 |
|
# Plugin Information |
| 64 |
< |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
| 64 |
> |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
| 65 |
|
Filter.Plugins=TypeChecker;EnforceEssentialData |
| 66 |
|
|
| 67 |
|
# The name for the root filter |
| 97 |
|
############################################################ |
| 98 |
|
|
| 99 |
|
# The default filter for a new host |
| 100 |
< |
Host.filter=filter1; |
| 100 |
> |
Host.filter=computingFilter; |
| 101 |
|
|
| 102 |
|
# The default update times for a new host |
| 103 |
|
Host.UDPUpdateTime=10 |
| 105 |
|
Host.AveragerUpdateTime=5 |
| 106 |
|
|
| 107 |
|
# The services checks to run on a host |
| 108 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
| 109 |
< |
Host.serviceChecks=HTTP;SMTP |
| 108 |
> |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
| 109 |
> |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet |
| 110 |
|
|
| 111 |
|
|
| 112 |
|
|
| 115 |
|
############################################################ |
| 116 |
|
|
| 117 |
|
# the monitors to run |
| 118 |
< |
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
| 119 |
< |
Monitor.Plugins=CPU;Memory;Swap;Heartbeat; |
| 118 |
> |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
| 119 |
> |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
| 120 |
|
|
| 121 |
|
|
| 122 |
|
## CPU monitor configuration |
| 167 |
|
Monitor.Swap.alertTimeout.CRITICAL=3600 |
| 168 |
|
|
| 169 |
|
|
| 170 |
+ |
## Disk monitor configuration |
| 171 |
+ |
# threshold values |
| 172 |
+ |
# |
| 173 |
+ |
# note: if the UPPER threshold is broken, |
| 174 |
+ |
# the alertTimeout values are halved. |
| 175 |
+ |
# This is to escalate the alert quicker. |
| 176 |
+ |
Monitor.Disk.threshold.LOWER=80 |
| 177 |
+ |
Monitor.Disk.threshold.UPPER=90 |
| 178 |
+ |
|
| 179 |
+ |
# timings of the alerts (in seconds) |
| 180 |
+ |
Monitor.Disk.alertTimeout.NOTICE=60 |
| 181 |
+ |
Monitor.Disk.alertTimeout.WARNING=900 |
| 182 |
+ |
Monitor.Disk.alertTimeout.CAUTION=1800 |
| 183 |
+ |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
| 184 |
+ |
|
| 185 |
+ |
|
| 186 |
+ |
## Services monitor configuration |
| 187 |
+ |
# threshold values |
| 188 |
+ |
# |
| 189 |
+ |
# THE SERVICES MONITOR USES A HACK |
| 190 |
+ |
# WHEREBY IT USES THE SERVICE STATUS |
| 191 |
+ |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
| 192 |
+ |
# BE LOOKED AT! |
| 193 |
+ |
# |
| 194 |
+ |
# note: if the UPPER threshold is broken, |
| 195 |
+ |
# the alertTimeout values are halved. |
| 196 |
+ |
# This is to escalate the alert quicker. |
| 197 |
+ |
#Monitor.Services.threshold.LOWER=120 |
| 198 |
+ |
#Monitor.Services.threshold.LOWER=300 |
| 199 |
+ |
|
| 200 |
+ |
# timings of the alerts (in seconds) |
| 201 |
+ |
Monitor.Services.alertTimeout.NOTICE=60 |
| 202 |
+ |
Monitor.Services.alertTimeout.WARNING=900 |
| 203 |
+ |
Monitor.Services.alertTimeout.CAUTION=1800 |
| 204 |
+ |
Monitor.Services.alertTimeout.CRITICAL=3600 |
| 205 |
+ |
|
| 206 |
+ |
# Make sure we shut up eventually |
| 207 |
+ |
Monitor.Services.reachFINALcount=5 |
| 208 |
+ |
|
| 209 |
+ |
|
| 210 |
|
## Heartbeat monitor configuration |
| 211 |
|
# threshold values |
| 212 |
|
# |
| 214 |
|
# the alertTimeout values are halved. |
| 215 |
|
# This is to escalate the alert quicker. |
| 216 |
|
Monitor.Heartbeat.checkPeriod=50 |
| 217 |
+ |
# these are values in seconds from when the heartbeat |
| 218 |
+ |
# was *expected* to arrive (ie. last + hearbeat period) |
| 219 |
|
Monitor.Heartbeat.threshold.LOWER=120 |
| 220 |
< |
Monitor.Heartbeat.threshold.LOWER=300 |
| 220 |
> |
Monitor.Heartbeat.threshold.UPPER=300 |
| 221 |
|
|
| 222 |
|
# timings of the alerts (in seconds) |
| 223 |
|
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
| 253 |
|
# |
| 254 |
|
|
| 255 |
|
# alerters to run |
| 256 |
< |
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
| 257 |
< |
Alerter.Plugins=EMail;IRC; |
| 256 |
> |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
| 257 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder; |
| 258 |
|
|
| 259 |
|
# EMail alerter configuration |
| 260 |
< |
Alerter.EMail.level = CAUTION |
| 261 |
< |
Alerter.EMail.defaultDestList = dev@i-scream.org.uk |
| 260 |
> |
Alerter.EMail.level = WARNING |
| 261 |
> |
Alerter.EMail.destList = dev@i-scream.org.uk |
| 262 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
| 263 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
| 264 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
| 265 |
< |
Alerter.EMail.message = The i-scream distributed central monitoring system has\nraised a %level% alert for the host %source%.\n\nThe value for %attributeName% of %value% has exceeded the\n%threshold% threshold value of %thresholdValue%.\n\nThe next alert (should one occur) will be sent in %timeTillNextAlert%. |
| 265 |
> |
Alerter.EMail.message = The i-scream distributed central monitoring system has\nraised a %level% alert for the host %source%.\n\nThe value for %attributeName% of %value% has exceeded the\n%threshold% threshold value of %thresholdValue%.\n\nThis alert was originally raised at %timeOfFirstAlert%,\nwhich was %timeSinceFirstAlert% ago.\n\nThe next alert (should one occur) will be sent in %timeTillNextAlert%. |
| 266 |
|
|
| 267 |
+ |
|
| 268 |
|
# IRC alerter configuration |
| 269 |
|
Alerter.IRC.level = OK |
| 270 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
| 287 |
|
Alerter.IRC.versionCommand = version |
| 288 |
|
Alerter.IRC.helpCommand = help |
| 289 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
| 290 |
+ |
|
| 291 |
+ |
############################################################ |
| 292 |
+ |
#### WebFeeder Configuration |
| 293 |
+ |
############################################################ |
| 294 |
+ |
|
| 295 |
+ |
# Define these (one or both_ to turn on the WebFeeder's, |
| 296 |
+ |
# comment it to turn them off |
| 297 |
+ |
WebFeeder.latestActive = true |
| 298 |
+ |
WebFeeder.alertActive = true |
| 299 |
+ |
|
| 300 |
+ |
# Check period in seconds (for cleaning stale/old alerts) |
| 301 |
+ |
WebFeeder.checkPeriod = 900 |
| 302 |
+ |
|
| 303 |
+ |
# Delete alerts older than this, in seconds. |
| 304 |
+ |
# Files are only check every WebFeeder.checkPeriod seconds. |
| 305 |
+ |
WebFeeder.alertDeleteOlderThan = 1800 |
| 306 |
+ |
|
| 307 |
+ |
# Root Path |
| 308 |
+ |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
| 309 |
+ |
|
| 310 |
+ |
# Latest Data |
| 311 |
+ |
WebFeeder.latestSubDir = latest |
| 312 |
+ |
WebFeeder.latestFileName = latest_data |
| 313 |
+ |
|
| 314 |
+ |
# Alert Data |
| 315 |
+ |
WebFeeder.alertSubDir = alert |
| 316 |
+ |
WebFeeder.alertFileName = alert_data |
| 317 |
|
|
| 318 |
|
############################################################ |
| 319 |
|
|
