| 14 |
|
|
| 15 |
|
# for computing machines |
| 16 |
|
group.computing=Host.129.12.4.*; |
| 17 |
+ |
group.rocks=Host.agate.ukc.ac.uk;Host.arkose.ukc.ac.uk;Host.basalt.ukc.ac.uk;Host.chalk.ukc.ac.uk;\ |
| 18 |
+ |
Host.chert.ukc.ac.uk;Host.granite.ukc.ac.uk;Host.jade.ukc.ac.uk;Host.jasper.ukc.ac.uk;\ |
| 19 |
+ |
Host.magnetite.ukc.ac.uk;Host.obsidian.ukc.ac.uk;Host.pumice.ukc.ac.uk;\ |
| 20 |
+ |
Host.pyrite.ukc.ac.uk;Host.slate.ukc.ac.uk;Host.topaz.ukc.ac.uk; |
| 21 |
+ |
group.compsoc=Host.compsoc1.ukc.ac.uk |
| 22 |
+ |
|
| 23 |
|
config.computing=computing.conf |
| 24 |
+ |
config.rocks=rocks.conf |
| 25 |
+ |
config.compsoc1=rocks.conf |
| 26 |
|
|
| 27 |
|
# for library machines |
| 28 |
|
group.library=Host.129.12.58.*; |
| 45 |
|
|
| 46 |
|
# The time interval at which the Queue's should be monitored |
| 47 |
|
Queue.MonitorInterval=15 |
| 48 |
+ |
# The upper limit for a Queue |
| 49 |
+ |
Queue.SizeLimit=1000 |
| 50 |
+ |
# The removal algorithm |
| 51 |
+ |
Queue.RemoveAlgorithm=FIRST |
| 52 |
|
|
| 53 |
|
|
| 42 |
– |
|
| 54 |
|
############################################################ |
| 55 |
|
#### FilterManager configuration |
| 56 |
|
############################################################ |
| 114 |
|
|
| 115 |
|
# The services checks to run on a host |
| 116 |
|
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
| 106 |
– |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet |
| 117 |
|
|
| 118 |
|
|
| 119 |
|
|
| 121 |
|
#### Monitor Configuration |
| 122 |
|
############################################################ |
| 123 |
|
|
| 124 |
< |
# the monitors to run |
| 124 |
> |
## The monitors to run |
| 125 |
|
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
| 126 |
< |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
| 126 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;Heartbeat;Queue;WebFeeder; |
| 127 |
|
|
| 128 |
+ |
## Default alert timeouts |
| 129 |
+ |
# these can be override on a per-monitor basis |
| 130 |
+ |
# timings of the alerts (in seconds) |
| 131 |
+ |
Monitor.alertTimeout.NOTICE=60 |
| 132 |
+ |
Monitor.alertTimeout.WARNING=900 |
| 133 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
| 134 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
| 135 |
|
|
| 136 |
< |
## CPU monitor configuration |
| 120 |
< |
# threshold values |
| 136 |
> |
## Threshold values |
| 137 |
|
# |
| 138 |
|
# note: if the UPPER threshold is broken, |
| 139 |
|
# the alertTimeout values are halved. |
| 140 |
|
# This is to escalate the alert quicker. |
| 141 |
+ |
# |
| 142 |
+ |
|
| 143 |
+ |
# CPU monitor threshold values |
| 144 |
|
Monitor.CPU.threshold.LOWER=90 |
| 145 |
|
Monitor.CPU.threshold.UPPER=99 |
| 146 |
|
|
| 128 |
– |
# timings of the alerts (in seconds) |
| 129 |
– |
Monitor.CPU.alertTimeout.NOTICE=60 |
| 130 |
– |
Monitor.CPU.alertTimeout.WARNING=900 |
| 131 |
– |
Monitor.CPU.alertTimeout.CAUTION=1800 |
| 132 |
– |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
| 147 |
|
|
| 148 |
+ |
# Load monitor threshold values |
| 149 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
| 150 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
| 151 |
|
|
| 152 |
< |
## Memory monitor configuration |
| 153 |
< |
# threshold values |
| 154 |
< |
# |
| 155 |
< |
# note: if the UPPER threshold is broken, |
| 156 |
< |
# the alertTimeout values are halved. |
| 157 |
< |
# This is to escalate the alert quicker. |
| 152 |
> |
|
| 153 |
> |
# Process Count threshold values |
| 154 |
> |
Monitor.Process.threshold.LOWER=1000 |
| 155 |
> |
Monitor.Process.threshold.UPPER=1500 |
| 156 |
> |
|
| 157 |
> |
|
| 158 |
> |
# Memory monitor threshold values |
| 159 |
|
Monitor.Memory.threshold.LOWER=80 |
| 160 |
|
Monitor.Memory.threshold.UPPER=90 |
| 161 |
|
|
| 144 |
– |
# timings of the alerts (in seconds) |
| 145 |
– |
Monitor.Memory.alertTimeout.NOTICE=60 |
| 146 |
– |
Monitor.Memory.alertTimeout.WARNING=900 |
| 147 |
– |
Monitor.Memory.alertTimeout.CAUTION=1800 |
| 148 |
– |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
| 162 |
|
|
| 163 |
< |
|
| 151 |
< |
## Swap monitor configuration |
| 152 |
< |
# threshold values |
| 153 |
< |
# |
| 154 |
< |
# note: if the UPPER threshold is broken, |
| 155 |
< |
# the alertTimeout values are halved. |
| 156 |
< |
# This is to escalate the alert quicker. |
| 163 |
> |
# Swap monitor threshold values |
| 164 |
|
Monitor.Swap.threshold.LOWER=80 |
| 165 |
|
Monitor.Swap.threshold.UPPER=90 |
| 166 |
|
|
| 160 |
– |
# timings of the alerts (in seconds) |
| 161 |
– |
Monitor.Swap.alertTimeout.NOTICE=60 |
| 162 |
– |
Monitor.Swap.alertTimeout.WARNING=900 |
| 163 |
– |
Monitor.Swap.alertTimeout.CAUTION=1800 |
| 164 |
– |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
| 167 |
|
|
| 168 |
+ |
# UserCount monitor threshold values |
| 169 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
| 170 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
| 171 |
|
|
| 167 |
– |
## Disk monitor configuration |
| 168 |
– |
# threshold values |
| 169 |
– |
# |
| 170 |
– |
# note: if the UPPER threshold is broken, |
| 171 |
– |
# the alertTimeout values are halved. |
| 172 |
– |
# This is to escalate the alert quicker. |
| 173 |
– |
Monitor.Disk.threshold.LOWER=80 |
| 174 |
– |
Monitor.Disk.threshold.UPPER=90 |
| 172 |
|
|
| 173 |
< |
# timings of the alerts (in seconds) |
| 174 |
< |
Monitor.Disk.alertTimeout.NOTICE=60 |
| 175 |
< |
Monitor.Disk.alertTimeout.WARNING=900 |
| 176 |
< |
Monitor.Disk.alertTimeout.CAUTION=1800 |
| 177 |
< |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
| 173 |
> |
# Disk monitor threshold values |
| 174 |
> |
Monitor.Disk.threshold.LOWER=90 |
| 175 |
> |
Monitor.Disk.threshold.UPPER=95 |
| 176 |
> |
# Thresholds given are PERCENTAGE or VALUE |
| 177 |
> |
# where PERCENTAGE is a percentage of disk in use |
| 178 |
> |
# and VALUE is an absolute value of space free |
| 179 |
> |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
| 180 |
|
|
| 181 |
|
|
| 182 |
< |
## Services monitor configuration |
| 183 |
< |
# threshold values |
| 182 |
> |
# Disk monitor threshold values |
| 183 |
> |
Monitor.Queue.threshold.LOWER=50 |
| 184 |
> |
Monitor.Queue.threshold.UPPER=80 |
| 185 |
> |
# Thresholds given are PERCENTAGE or VALUE |
| 186 |
> |
# where PERCENTAGE is a percentage of disk in use |
| 187 |
> |
# and VALUE is an absolute value of space free |
| 188 |
> |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
| 189 |
> |
|
| 190 |
> |
|
| 191 |
> |
# Services monitor threshold values |
| 192 |
|
# |
| 193 |
|
# THE SERVICES MONITOR USES A HACK |
| 194 |
|
# WHEREBY IT USES THE SERVICE STATUS |
| 195 |
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
| 196 |
|
# BE LOOKED AT! |
| 197 |
|
# |
| 198 |
< |
# note: if the UPPER threshold is broken, |
| 199 |
< |
# the alertTimeout values are halved. |
| 200 |
< |
# This is to escalate the alert quicker. |
| 194 |
< |
#Monitor.Services.threshold.LOWER=120 |
| 195 |
< |
#Monitor.Services.threshold.LOWER=300 |
| 198 |
> |
# how many times we should be at the highest level before |
| 199 |
> |
# we go to a FINAL alert |
| 200 |
> |
Monitor.Services.reachFINALcount=5 |
| 201 |
|
|
| 197 |
– |
# timings of the alerts (in seconds) |
| 198 |
– |
Monitor.Services.alertTimeout.NOTICE=60 |
| 199 |
– |
Monitor.Services.alertTimeout.WARNING=900 |
| 200 |
– |
Monitor.Services.alertTimeout.CAUTION=1800 |
| 201 |
– |
Monitor.Services.alertTimeout.CRITICAL=3600 |
| 202 |
|
|
| 203 |
< |
|
| 204 |
< |
## Heartbeat monitor configuration |
| 205 |
< |
# threshold values |
| 206 |
< |
# |
| 207 |
< |
# note: if the UPPER threshold is broken, |
| 208 |
< |
# the alertTimeout values are halved. |
| 209 |
< |
# This is to escalate the alert quicker. |
| 210 |
< |
Monitor.Heartbeat.checkPeriod=50 |
| 203 |
> |
# Heartbeat threshold values |
| 204 |
|
# these are values in seconds from when the heartbeat |
| 205 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
| 206 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
| 207 |
< |
Monitor.Heartbeat.threshold.LOWER=300 |
| 206 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
| 207 |
> |
Monitor.Heartbeat.threshold.UPPER=300 |
| 208 |
> |
# this is how often we will run a "check" of heartbeats |
| 209 |
> |
Monitor.Heartbeat.checkPeriod=50 |
| 210 |
> |
# how many times we should be at the highest level before |
| 211 |
> |
# we go to a FINAL alert |
| 212 |
> |
Monitor.Heartbeat.reachFINALcount=5 |
| 213 |
|
|
| 216 |
– |
# timings of the alerts (in seconds) |
| 217 |
– |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
| 218 |
– |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
| 219 |
– |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
| 220 |
– |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
| 214 |
|
|
| 222 |
– |
# this means it will reach a FINAL level, |
| 223 |
– |
# and thus the host will be removed from the monitor list, |
| 224 |
– |
# if the highest level alert is reached and occours this |
| 225 |
– |
# number of times. |
| 226 |
– |
# |
| 227 |
– |
# int this setup, that means 5 CRITICAL alerts would occour |
| 228 |
– |
# on a Heartbeat before reaching FINAL. |
| 229 |
– |
# If this value is wrong or not present, FINAL is never reached |
| 230 |
– |
# |
| 231 |
– |
Monitor.Heartbeat.reachFINALcount=5 |
| 215 |
|
|
| 216 |
|
############################################################ |
| 217 |
|
#### Alerter Configuration |
| 233 |
|
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
| 234 |
|
Alerter.Plugins=EMail;IRC;WebFeeder; |
| 235 |
|
|
| 236 |
+ |
|
| 237 |
|
# EMail alerter configuration |
| 238 |
< |
Alerter.EMail.level = CAUTION |
| 239 |
< |
Alerter.EMail.defaultDestList = dev@i-scream.org.uk |
| 238 |
> |
Alerter.EMail.level = WARNING |
| 239 |
> |
Alerter.EMail.destList = dev@i-scream.org.uk |
| 240 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
| 241 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
| 242 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
| 243 |
< |
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%. |
| 243 |
> |
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%. |
| 244 |
|
|
| 245 |
+ |
|
| 246 |
|
# IRC alerter configuration |
| 247 |
|
Alerter.IRC.level = OK |
| 248 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
| 266 |
|
Alerter.IRC.helpCommand = help |
| 267 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
| 268 |
|
|
| 269 |
+ |
|
| 270 |
+ |
|
| 271 |
|
############################################################ |
| 272 |
|
#### WebFeeder Configuration |
| 273 |
|
############################################################ |
| 277 |
|
WebFeeder.latestActive = true |
| 278 |
|
WebFeeder.alertActive = true |
| 279 |
|
|
| 280 |
+ |
# Only pass on alerts past this level |
| 281 |
+ |
WebFeeder.alertLevel = OK |
| 282 |
+ |
|
| 283 |
+ |
# Check period in seconds (for cleaning stale/old alerts) |
| 284 |
+ |
WebFeeder.checkPeriod = 120 |
| 285 |
+ |
|
| 286 |
+ |
# Delete alerts older than this, in seconds. |
| 287 |
+ |
# Files are only check every WebFeeder.checkPeriod seconds. |
| 288 |
+ |
WebFeeder.alertDeleteOlderThan = 300 |
| 289 |
+ |
|
| 290 |
|
# Root Path |
| 291 |
|
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
| 292 |
|
|
| 298 |
|
WebFeeder.alertSubDir = alert |
| 299 |
|
WebFeeder.alertFileName = alert_data |
| 300 |
|
|
| 304 |
– |
############################################################ |
| 301 |
|
|
| 302 |
+ |
############################################################ |
