| 7 |
|
# |
| 8 |
|
# $Author$ |
| 9 |
|
# $Id$ |
| 10 |
+ |
# |
| 11 |
+ |
############################################################ |
| 12 |
+ |
#### Configuration Files & Groups |
| 13 |
+ |
############################################################ |
| 14 |
|
|
| 15 |
< |
# FilterManager configuration |
| 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.*; |
| 29 |
+ |
config.library=library.conf |
| 30 |
+ |
|
| 31 |
+ |
# for SSB machines |
| 32 |
+ |
group.ssb=Host.stue*.ukc.ac.uk; |
| 33 |
+ |
config.ssb=ssb.conf |
| 34 |
+ |
|
| 35 |
+ |
# mySQL configuration |
| 36 |
+ |
config.mySQL=mySQL.conf |
| 37 |
+ |
|
| 38 |
+ |
############################################################ |
| 39 |
+ |
#### Misc system-wide configuration |
| 40 |
+ |
############################################################ |
| 41 |
+ |
|
| 42 |
+ |
# the time (in seconds) that checks should be made for |
| 43 |
+ |
# changes in configuration |
| 44 |
+ |
ConfigurationProxy.updateTime=60 |
| 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 |
+ |
|
| 54 |
+ |
############################################################ |
| 55 |
+ |
#### FilterManager configuration |
| 56 |
+ |
############################################################ |
| 57 |
+ |
|
| 58 |
|
# The default port to listen for new host connections |
| 59 |
|
FilterManager.listenPort=4567 |
| 60 |
|
|
| 61 |
+ |
|
| 62 |
+ |
|
| 63 |
+ |
############################################################ |
| 64 |
+ |
#### Filter configuration |
| 65 |
+ |
############################################################ |
| 66 |
+ |
|
| 67 |
|
# The default port for Filter's to listen on |
| 68 |
|
Filter.UDPListenPort=4589 |
| 69 |
|
Filter.TCPListenPort=4589 |
| 70 |
|
|
| 71 |
+ |
# Plugin Information |
| 72 |
+ |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
| 73 |
+ |
Filter.Plugins=TypeChecker;EnforceEssentialData |
| 74 |
+ |
|
| 75 |
|
# The name for the root filter |
| 76 |
|
RootFilter.name=root |
| 77 |
+ |
|
| 78 |
+ |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
| 79 |
+ |
Filter.parentFilter=root |
| 80 |
+ |
|
| 81 |
+ |
|
| 82 |
+ |
|
| 83 |
+ |
############################################################ |
| 84 |
+ |
#### Root filter interfaces configuration |
| 85 |
+ |
############################################################ |
| 86 |
+ |
|
| 87 |
+ |
# Comment either of these (or delete them) and |
| 88 |
+ |
# that interface won't be started |
| 89 |
|
RootFilter.realtimeInterfaceName=realtimeclients |
| 90 |
|
RootFilter.dbInterfaceName=database |
| 91 |
|
|
| 92 |
+ |
|
| 93 |
+ |
|
| 94 |
+ |
############################################################ |
| 95 |
+ |
#### Client interface configuration |
| 96 |
+ |
############################################################ |
| 97 |
+ |
|
| 98 |
|
# The port for the client interface to listen on |
| 99 |
|
ClientInterface.listenPort=4510 |
| 100 |
|
|
| 28 |
– |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
| 29 |
– |
Filter.parentFilter=root |
| 101 |
|
|
| 102 |
+ |
|
| 103 |
+ |
############################################################ |
| 104 |
+ |
#### Host Configuration |
| 105 |
+ |
############################################################ |
| 106 |
+ |
|
| 107 |
|
# The default filter for a new host |
| 108 |
< |
Host.filter=filter1 |
| 108 |
> |
Host.filter=computingFilter; |
| 109 |
|
|
| 110 |
|
# The default update times for a new host |
| 111 |
< |
Host.UDPUpdateTime=5 |
| 111 |
> |
Host.UDPUpdateTime=10 |
| 112 |
|
Host.TCPUpdateTime=60 |
| 113 |
+ |
Host.AveragerUpdateTime=5 |
| 114 |
|
|
| 115 |
< |
# Plugin Information |
| 116 |
< |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
| 40 |
< |
Filter.Plugins=EnforceEssentialData |
| 115 |
> |
# The services checks to run on a host |
| 116 |
> |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
| 117 |
|
|
| 118 |
< |
# mySQL Details |
| 119 |
< |
config.mySQL=mySQL.conf |
| 118 |
> |
|
| 119 |
> |
|
| 120 |
> |
############################################################ |
| 121 |
> |
#### Monitor Configuration |
| 122 |
> |
############################################################ |
| 123 |
> |
|
| 124 |
> |
# the monitors to run |
| 125 |
> |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
| 126 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
| 127 |
> |
#Monitor.Plugins=CPU;WebFeeder; |
| 128 |
> |
#Monitor.Plugins= |
| 129 |
> |
|
| 130 |
> |
|
| 131 |
> |
## CPU monitor configuration |
| 132 |
> |
# threshold values |
| 133 |
> |
# |
| 134 |
> |
# note: if the UPPER threshold is broken, |
| 135 |
> |
# the alertTimeout values are halved. |
| 136 |
> |
# This is to escalate the alert quicker. |
| 137 |
> |
Monitor.CPU.threshold.LOWER=90 |
| 138 |
> |
Monitor.CPU.threshold.UPPER=99 |
| 139 |
> |
|
| 140 |
> |
# timings of the alerts (in seconds) |
| 141 |
> |
Monitor.CPU.alertTimeout.NOTICE=60 |
| 142 |
> |
Monitor.CPU.alertTimeout.WARNING=900 |
| 143 |
> |
Monitor.CPU.alertTimeout.CAUTION=1800 |
| 144 |
> |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
| 145 |
> |
|
| 146 |
> |
|
| 147 |
> |
## Load monitor configuration |
| 148 |
> |
# threshold values |
| 149 |
> |
# |
| 150 |
> |
# note: if the UPPER threshold is broken, |
| 151 |
> |
# the alertTimeout values are halved. |
| 152 |
> |
# This is to escalate the alert quicker. |
| 153 |
> |
Monitor.Load.threshold.LOWER=10.0 |
| 154 |
> |
Monitor.Load.threshold.UPPER=20.0 |
| 155 |
> |
|
| 156 |
> |
# timings of the alerts (in seconds) |
| 157 |
> |
Monitor.Load.alertTimeout.NOTICE=60 |
| 158 |
> |
Monitor.Load.alertTimeout.WARNING=900 |
| 159 |
> |
Monitor.Load.alertTimeout.CAUTION=1800 |
| 160 |
> |
Monitor.Load.alertTimeout.CRITICAL=3600 |
| 161 |
> |
|
| 162 |
> |
|
| 163 |
> |
## Process Count monitor configuration |
| 164 |
> |
# threshold values |
| 165 |
> |
# |
| 166 |
> |
# note: if the UPPER threshold is broken, |
| 167 |
> |
# the alertTimeout values are halved. |
| 168 |
> |
# This is to escalate the alert quicker. |
| 169 |
> |
Monitor.Process.threshold.LOWER=1000 |
| 170 |
> |
Monitor.Process.threshold.UPPER=1500 |
| 171 |
> |
|
| 172 |
> |
# timings of the alerts (in seconds) |
| 173 |
> |
Monitor.Process.alertTimeout.NOTICE=60 |
| 174 |
> |
Monitor.Process.alertTimeout.WARNING=900 |
| 175 |
> |
Monitor.Process.alertTimeout.CAUTION=1800 |
| 176 |
> |
Monitor.Process.alertTimeout.CRITICAL=3600 |
| 177 |
> |
|
| 178 |
> |
|
| 179 |
> |
## Memory monitor configuration |
| 180 |
> |
# threshold values |
| 181 |
> |
# |
| 182 |
> |
# note: if the UPPER threshold is broken, |
| 183 |
> |
# the alertTimeout values are halved. |
| 184 |
> |
# This is to escalate the alert quicker. |
| 185 |
> |
Monitor.Memory.threshold.LOWER=80 |
| 186 |
> |
Monitor.Memory.threshold.UPPER=90 |
| 187 |
> |
|
| 188 |
> |
# timings of the alerts (in seconds) |
| 189 |
> |
Monitor.Memory.alertTimeout.NOTICE=60 |
| 190 |
> |
Monitor.Memory.alertTimeout.WARNING=900 |
| 191 |
> |
Monitor.Memory.alertTimeout.CAUTION=1800 |
| 192 |
> |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
| 193 |
> |
|
| 194 |
> |
|
| 195 |
> |
## Swap monitor configuration |
| 196 |
> |
# threshold values |
| 197 |
> |
# |
| 198 |
> |
# note: if the UPPER threshold is broken, |
| 199 |
> |
# the alertTimeout values are halved. |
| 200 |
> |
# This is to escalate the alert quicker. |
| 201 |
> |
Monitor.Swap.threshold.LOWER=80 |
| 202 |
> |
Monitor.Swap.threshold.UPPER=90 |
| 203 |
> |
|
| 204 |
> |
# timings of the alerts (in seconds) |
| 205 |
> |
Monitor.Swap.alertTimeout.NOTICE=60 |
| 206 |
> |
Monitor.Swap.alertTimeout.WARNING=900 |
| 207 |
> |
Monitor.Swap.alertTimeout.CAUTION=1800 |
| 208 |
> |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
| 209 |
> |
|
| 210 |
> |
|
| 211 |
> |
## Disk monitor configuration |
| 212 |
> |
# threshold values |
| 213 |
> |
# |
| 214 |
> |
# note: if the UPPER threshold is broken, |
| 215 |
> |
# the alertTimeout values are halved. |
| 216 |
> |
# This is to escalate the alert quicker. |
| 217 |
> |
Monitor.Disk.threshold.LOWER=90 |
| 218 |
> |
Monitor.Disk.threshold.UPPER=95 |
| 219 |
> |
|
| 220 |
> |
# timings of the alerts (in seconds) |
| 221 |
> |
Monitor.Disk.alertTimeout.NOTICE=60 |
| 222 |
> |
Monitor.Disk.alertTimeout.WARNING=900 |
| 223 |
> |
Monitor.Disk.alertTimeout.CAUTION=1800 |
| 224 |
> |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
| 225 |
> |
|
| 226 |
> |
|
| 227 |
> |
## Services monitor configuration |
| 228 |
> |
# threshold values |
| 229 |
> |
# |
| 230 |
> |
# THE SERVICES MONITOR USES A HACK |
| 231 |
> |
# WHEREBY IT USES THE SERVICE STATUS |
| 232 |
> |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
| 233 |
> |
# BE LOOKED AT! |
| 234 |
> |
# |
| 235 |
> |
# note: if the UPPER threshold is broken, |
| 236 |
> |
# the alertTimeout values are halved. |
| 237 |
> |
# This is to escalate the alert quicker. |
| 238 |
> |
#Monitor.Services.threshold.LOWER=120 |
| 239 |
> |
#Monitor.Services.threshold.LOWER=300 |
| 240 |
> |
|
| 241 |
> |
# timings of the alerts (in seconds) |
| 242 |
> |
Monitor.Services.alertTimeout.NOTICE=60 |
| 243 |
> |
Monitor.Services.alertTimeout.WARNING=900 |
| 244 |
> |
Monitor.Services.alertTimeout.CAUTION=1800 |
| 245 |
> |
Monitor.Services.alertTimeout.CRITICAL=3600 |
| 246 |
> |
|
| 247 |
> |
# Make sure we shut up eventually |
| 248 |
> |
Monitor.Services.reachFINALcount=5 |
| 249 |
> |
|
| 250 |
> |
|
| 251 |
> |
## Heartbeat monitor configuration |
| 252 |
> |
# threshold values |
| 253 |
> |
# |
| 254 |
> |
# note: if the UPPER threshold is broken, |
| 255 |
> |
# the alertTimeout values are halved. |
| 256 |
> |
# This is to escalate the alert quicker. |
| 257 |
> |
Monitor.Heartbeat.checkPeriod=50 |
| 258 |
> |
# these are values in seconds from when the heartbeat |
| 259 |
> |
# was *expected* to arrive (ie. last + hearbeat period) |
| 260 |
> |
Monitor.Heartbeat.threshold.LOWER=120 |
| 261 |
> |
Monitor.Heartbeat.threshold.UPPER=300 |
| 262 |
> |
|
| 263 |
> |
# timings of the alerts (in seconds) |
| 264 |
> |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
| 265 |
> |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
| 266 |
> |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
| 267 |
> |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
| 268 |
> |
|
| 269 |
> |
# this means it will reach a FINAL level, |
| 270 |
> |
# and thus the host will be removed from the monitor list, |
| 271 |
> |
# if the highest level alert is reached and occours this |
| 272 |
> |
# number of times. |
| 273 |
> |
# |
| 274 |
> |
# int this setup, that means 5 CRITICAL alerts would occour |
| 275 |
> |
# on a Heartbeat before reaching FINAL. |
| 276 |
> |
# If this value is wrong or not present, FINAL is never reached |
| 277 |
> |
# |
| 278 |
> |
Monitor.Heartbeat.reachFINALcount=5 |
| 279 |
> |
|
| 280 |
> |
############################################################ |
| 281 |
> |
#### Alerter Configuration |
| 282 |
> |
############################################################ |
| 283 |
> |
# The following var's are understood by ALL alerters for messages |
| 284 |
> |
# |
| 285 |
> |
# %level% - the alert level (eg, WARNING) |
| 286 |
> |
# %threshold% - the threshold broken (eg, LOWER) |
| 287 |
> |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
| 288 |
> |
# %value% - the value reached (eg, 95) |
| 289 |
> |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
| 290 |
> |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
| 291 |
> |
# %timeTillNextAlert% - the time the next alert will be sent out |
| 292 |
> |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
| 293 |
> |
# %timeOfFirstAlert% - the time the first alert was sent |
| 294 |
> |
# |
| 295 |
> |
|
| 296 |
> |
# alerters to run |
| 297 |
> |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
| 298 |
> |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
| 299 |
> |
Alerter.Plugins=IRC;WebFeeder; |
| 300 |
> |
#Alerter.Plugins=WebFeeder; |
| 301 |
> |
#Alerter.Plugins= |
| 302 |
> |
|
| 303 |
> |
# EMail alerter configuration |
| 304 |
> |
Alerter.EMail.level = WARNING |
| 305 |
> |
Alerter.EMail.destList = dev@i-scream.org.uk |
| 306 |
> |
Alerter.EMail.sender = dev@i-scream.org.uk |
| 307 |
> |
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
| 308 |
> |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
| 309 |
> |
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%. |
| 310 |
> |
|
| 311 |
> |
|
| 312 |
> |
# IRC alerter configuration |
| 313 |
> |
Alerter.IRC.level = OK |
| 314 |
> |
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
| 315 |
> |
Alerter.IRC.IRCPort = 6667 |
| 316 |
> |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
| 317 |
> |
Alerter.IRC.user = i-scream |
| 318 |
> |
Alerter.IRC.comment = i-scream alerting bot |
| 319 |
> |
Alerter.IRC.channel = #i-scream |
| 320 |
> |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
| 321 |
> |
Alerter.IRC.reconnectDelay = 30 |
| 322 |
> |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
| 323 |
> |
Alerter.IRC.stopCommand = stop alerts |
| 324 |
> |
Alerter.IRC.startCommand = start alerts |
| 325 |
> |
Alerter.IRC.lastAlertCommand = last alert |
| 326 |
> |
Alerter.IRC.joinCommand = join |
| 327 |
> |
Alerter.IRC.nickChangeCommand = nick |
| 328 |
> |
Alerter.IRC.statCommand = statistics |
| 329 |
> |
Alerter.IRC.uptimeCommand = uptime |
| 330 |
> |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
| 331 |
> |
Alerter.IRC.versionCommand = version |
| 332 |
> |
Alerter.IRC.helpCommand = help |
| 333 |
> |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
| 334 |
> |
|
| 335 |
> |
############################################################ |
| 336 |
> |
#### WebFeeder Configuration |
| 337 |
> |
############################################################ |
| 338 |
> |
|
| 339 |
> |
# Define these (one or both_ to turn on the WebFeeder's, |
| 340 |
> |
# comment it to turn them off |
| 341 |
> |
WebFeeder.latestActive = true |
| 342 |
> |
WebFeeder.alertActive = true |
| 343 |
> |
|
| 344 |
> |
# Only pass on alerts past this level |
| 345 |
> |
WebFeeder.alertLevel = OK |
| 346 |
> |
|
| 347 |
> |
# Check period in seconds (for cleaning stale/old alerts) |
| 348 |
> |
WebFeeder.checkPeriod = 120 |
| 349 |
> |
|
| 350 |
> |
# Delete alerts older than this, in seconds. |
| 351 |
> |
# Files are only check every WebFeeder.checkPeriod seconds. |
| 352 |
> |
WebFeeder.alertDeleteOlderThan = 300 |
| 353 |
> |
|
| 354 |
> |
# Root Path |
| 355 |
> |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
| 356 |
> |
|
| 357 |
> |
# Latest Data |
| 358 |
> |
WebFeeder.latestSubDir = latest |
| 359 |
> |
WebFeeder.latestFileName = latest_data |
| 360 |
> |
|
| 361 |
> |
# Alert Data |
| 362 |
> |
WebFeeder.alertSubDir = alert |
| 363 |
> |
WebFeeder.alertFileName = alert_data |
| 364 |
> |
|
| 365 |
> |
############################################################ |
| 366 |
> |
|
