13 |
|
############################################################ |
14 |
|
|
15 |
|
# for computing machines |
16 |
< |
group.computing=Host.raptor.ukc.ac.uk;Host.slate.ukc.ac.uk;Host.granite.ukc.ac.uk; |
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.killigrew.ukc.ac.uk; |
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 |
|
############################################################ |
69 |
|
Filter.TCPListenPort=4589 |
70 |
|
|
71 |
|
# Plugin Information |
72 |
< |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
72 |
> |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
73 |
|
Filter.Plugins=TypeChecker;EnforceEssentialData |
74 |
|
|
75 |
|
# The name for the root filter |
105 |
|
############################################################ |
106 |
|
|
107 |
|
# The default filter for a new host |
108 |
< |
Host.filter=computingFilter |
108 |
> |
Host.filter=computingFilter; |
109 |
|
|
110 |
|
# The default update times for a new host |
111 |
|
Host.UDPUpdateTime=10 |
112 |
|
Host.TCPUpdateTime=60 |
113 |
+ |
Host.AveragerUpdateTime=5 |
114 |
|
|
115 |
|
# The services checks to run on a host |
116 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
90 |
< |
Host.serviceChecks=HTTP;SMTP |
116 |
> |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
117 |
|
|
118 |
|
|
119 |
|
|
94 |
– |
# The time interval at which the Queue's should be monitored |
95 |
– |
Queue.MonitorInterval=15 |
96 |
– |
|
97 |
– |
|
98 |
– |
|
120 |
|
############################################################ |
121 |
|
#### Monitor Configuration |
122 |
|
############################################################ |
123 |
|
|
124 |
|
# the monitors to run |
125 |
< |
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
126 |
< |
Monitor.Plugins=CPU; |
125 |
> |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
126 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;Heartbeat;Queue;WebFeeder; |
127 |
> |
#Monitor.Plugins=CPU;WebFeeder; |
128 |
> |
#Monitor.Plugins= |
129 |
|
|
107 |
– |
# CPU monitor configuration |
108 |
– |
Monitor.CPU.level.1=90 |
109 |
– |
Monitor.CPU.level.2=95 |
110 |
– |
Monitor.CPU.level.3=100 |
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 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
220 |
+ |
|
221 |
+ |
# timings of the alerts (in seconds) |
222 |
+ |
Monitor.Disk.alertTimeout.NOTICE=60 |
223 |
+ |
Monitor.Disk.alertTimeout.WARNING=900 |
224 |
+ |
Monitor.Disk.alertTimeout.CAUTION=1800 |
225 |
+ |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
226 |
+ |
|
227 |
+ |
|
228 |
+ |
## Disk monitor configuration |
229 |
+ |
# threshold values |
230 |
+ |
# |
231 |
+ |
# note: if the UPPER threshold is broken, |
232 |
+ |
# the alertTimeout values are halved. |
233 |
+ |
# This is to escalate the alert quicker. |
234 |
+ |
Monitor.Queue.threshold.LOWER=90 |
235 |
+ |
Monitor.Queue.threshold.UPPER=95 |
236 |
+ |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
237 |
+ |
|
238 |
+ |
# timings of the alerts (in seconds) |
239 |
+ |
Monitor.Queue.alertTimeout.NOTICE=60 |
240 |
+ |
Monitor.Queue.alertTimeout.WARNING=900 |
241 |
+ |
Monitor.Queue.alertTimeout.CAUTION=1800 |
242 |
+ |
Monitor.Queue.alertTimeout.CRITICAL=3600 |
243 |
+ |
|
244 |
+ |
|
245 |
+ |
## Services monitor configuration |
246 |
+ |
# threshold values |
247 |
+ |
# |
248 |
+ |
# THE SERVICES MONITOR USES A HACK |
249 |
+ |
# WHEREBY IT USES THE SERVICE STATUS |
250 |
+ |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
251 |
+ |
# BE LOOKED AT! |
252 |
+ |
# |
253 |
+ |
# note: if the UPPER threshold is broken, |
254 |
+ |
# the alertTimeout values are halved. |
255 |
+ |
# This is to escalate the alert quicker. |
256 |
+ |
#Monitor.Services.threshold.LOWER=120 |
257 |
+ |
#Monitor.Services.threshold.LOWER=300 |
258 |
+ |
|
259 |
+ |
# timings of the alerts (in seconds) |
260 |
+ |
Monitor.Services.alertTimeout.NOTICE=60 |
261 |
+ |
Monitor.Services.alertTimeout.WARNING=900 |
262 |
+ |
Monitor.Services.alertTimeout.CAUTION=1800 |
263 |
+ |
Monitor.Services.alertTimeout.CRITICAL=3600 |
264 |
+ |
|
265 |
+ |
# Make sure we shut up eventually |
266 |
+ |
Monitor.Services.reachFINALcount=5 |
267 |
+ |
|
268 |
+ |
|
269 |
+ |
## Heartbeat monitor configuration |
270 |
+ |
# threshold values |
271 |
+ |
# |
272 |
+ |
# note: if the UPPER threshold is broken, |
273 |
+ |
# the alertTimeout values are halved. |
274 |
+ |
# This is to escalate the alert quicker. |
275 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
276 |
+ |
# these are values in seconds from when the heartbeat |
277 |
+ |
# was *expected* to arrive (ie. last + hearbeat period) |
278 |
+ |
Monitor.Heartbeat.threshold.LOWER=120 |
279 |
+ |
Monitor.Heartbeat.threshold.UPPER=300 |
280 |
+ |
|
281 |
+ |
# timings of the alerts (in seconds) |
282 |
+ |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
283 |
+ |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
284 |
+ |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
285 |
+ |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
286 |
+ |
|
287 |
+ |
# this means it will reach a FINAL level, |
288 |
+ |
# and thus the host will be removed from the monitor list, |
289 |
+ |
# if the highest level alert is reached and occours this |
290 |
+ |
# number of times. |
291 |
+ |
# |
292 |
+ |
# int this setup, that means 5 CRITICAL alerts would occour |
293 |
+ |
# on a Heartbeat before reaching FINAL. |
294 |
+ |
# If this value is wrong or not present, FINAL is never reached |
295 |
+ |
# |
296 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
297 |
+ |
|
298 |
|
############################################################ |
299 |
|
#### Alerter Configuration |
300 |
|
############################################################ |
301 |
+ |
# The following var's are understood by ALL alerters for messages |
302 |
+ |
# |
303 |
+ |
# %level% - the alert level (eg, WARNING) |
304 |
+ |
# %threshold% - the threshold broken (eg, LOWER) |
305 |
+ |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
306 |
+ |
# %value% - the value reached (eg, 95) |
307 |
+ |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
308 |
+ |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
309 |
+ |
# %timeTillNextAlert% - the time the next alert will be sent out |
310 |
+ |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
311 |
+ |
# %timeOfFirstAlert% - the time the first alert was sent |
312 |
+ |
# |
313 |
|
|
314 |
|
# alerters to run |
315 |
< |
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
316 |
< |
Alerter.Plugins=EMail;IRC; |
315 |
> |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
316 |
> |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
317 |
> |
Alerter.Plugins=IRC;WebFeeder; |
318 |
> |
#Alerter.Plugins=WebFeeder; |
319 |
> |
#Alerter.Plugins= |
320 |
|
|
321 |
|
# EMail alerter configuration |
322 |
< |
Alerter.EMail.level = 2 |
322 |
> |
Alerter.EMail.level = WARNING |
323 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
324 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
325 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
326 |
< |
Alerter.EMail.subject = i-scream alert: level %level% alert on %source for %attributeName% |
327 |
< |
Alerter.EMail.message = The i-scream distributed central monitoring system has\nraised a level %level% alert for the host %source%.\n\nThe value for %attributeName% of %value% has exceeded the\nthreshold value of %thresholdValue%. |
326 |
> |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
327 |
> |
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%. |
328 |
|
|
329 |
+ |
|
330 |
|
# IRC alerter configuration |
331 |
< |
Alerter.IRC.level = 1 |
331 |
> |
Alerter.IRC.level = OK |
332 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
333 |
|
Alerter.IRC.IRCPort = 6667 |
334 |
< |
Alerter.IRC.nick = iscreamBot |
334 |
> |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
335 |
> |
Alerter.IRC.user = i-scream |
336 |
> |
Alerter.IRC.comment = i-scream alerting bot |
337 |
|
Alerter.IRC.channel = #i-scream |
338 |
< |
Alerter.IRC.message = level %level%: %attributeName% on %source% has reached %value% |
338 |
> |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
339 |
> |
Alerter.IRC.reconnectDelay = 30 |
340 |
> |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
341 |
> |
Alerter.IRC.stopCommand = stop alerts |
342 |
> |
Alerter.IRC.startCommand = start alerts |
343 |
> |
Alerter.IRC.lastAlertCommand = last alert |
344 |
> |
Alerter.IRC.joinCommand = join |
345 |
> |
Alerter.IRC.nickChangeCommand = nick |
346 |
> |
Alerter.IRC.statCommand = statistics |
347 |
> |
Alerter.IRC.uptimeCommand = uptime |
348 |
> |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
349 |
> |
Alerter.IRC.versionCommand = version |
350 |
> |
Alerter.IRC.helpCommand = help |
351 |
> |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
352 |
|
|
353 |
< |
############################################################ |
353 |
> |
############################################################ |
354 |
> |
#### WebFeeder Configuration |
355 |
> |
############################################################ |
356 |
> |
|
357 |
> |
# Define these (one or both_ to turn on the WebFeeder's, |
358 |
> |
# comment it to turn them off |
359 |
> |
WebFeeder.latestActive = true |
360 |
> |
WebFeeder.alertActive = true |
361 |
> |
|
362 |
> |
# Only pass on alerts past this level |
363 |
> |
WebFeeder.alertLevel = OK |
364 |
> |
|
365 |
> |
# Check period in seconds (for cleaning stale/old alerts) |
366 |
> |
WebFeeder.checkPeriod = 120 |
367 |
> |
|
368 |
> |
# Delete alerts older than this, in seconds. |
369 |
> |
# Files are only check every WebFeeder.checkPeriod seconds. |
370 |
> |
WebFeeder.alertDeleteOlderThan = 300 |
371 |
> |
|
372 |
> |
# Root Path |
373 |
> |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
374 |
> |
|
375 |
> |
# Latest Data |
376 |
> |
WebFeeder.latestSubDir = latest |
377 |
> |
WebFeeder.latestFileName = latest_data |
378 |
> |
|
379 |
> |
# Alert Data |
380 |
> |
WebFeeder.alertSubDir = alert |
381 |
> |
WebFeeder.alertFileName = alert_data |
382 |
> |
|
383 |
> |
############################################################ |
384 |
> |
|