94 |
|
############################################################ |
95 |
|
|
96 |
|
# The default filter for a new host |
97 |
< |
Host.filter=filter1 |
97 |
> |
Host.filter=filter1; |
98 |
|
|
99 |
|
# The default update times for a new host |
100 |
|
Host.UDPUpdateTime=10 |
103 |
|
|
104 |
|
# The services checks to run on a host |
105 |
|
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
106 |
< |
Host.serviceChecks=HTTP;SMTP |
106 |
> |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet |
107 |
|
|
108 |
|
|
109 |
|
|
113 |
|
|
114 |
|
# the monitors to run |
115 |
|
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
116 |
< |
Monitor.Plugins=CPU; |
116 |
> |
Monitor.Plugins=CPU;Disk;Memory;Swap;Heartbeat;WebFeeder; |
117 |
|
|
118 |
< |
# CPU monitor configuration |
118 |
> |
|
119 |
> |
## CPU monitor configuration |
120 |
|
# threshold values |
121 |
|
# |
122 |
|
# note: if the UPPER threshold is broken, |
132 |
|
Monitor.CPU.alertTimeout.CRITICAL=3600 |
133 |
|
|
134 |
|
|
135 |
+ |
## Memory monitor configuration |
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 |
+ |
Monitor.Memory.threshold.LOWER=80 |
142 |
+ |
Monitor.Memory.threshold.UPPER=90 |
143 |
|
|
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 |
149 |
+ |
|
150 |
+ |
|
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. |
157 |
+ |
Monitor.Swap.threshold.LOWER=80 |
158 |
+ |
Monitor.Swap.threshold.UPPER=90 |
159 |
+ |
|
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 |
165 |
+ |
|
166 |
+ |
|
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 |
175 |
+ |
|
176 |
+ |
# timings of the alerts (in seconds) |
177 |
+ |
Monitor.Disk.alertTimeout.NOTICE=60 |
178 |
+ |
Monitor.Disk.alertTimeout.WARNING=900 |
179 |
+ |
Monitor.Disk.alertTimeout.CAUTION=1800 |
180 |
+ |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
181 |
+ |
|
182 |
+ |
|
183 |
+ |
## Services monitor configuration |
184 |
+ |
# threshold values |
185 |
+ |
# |
186 |
+ |
# THE SERVICES MONITOR USES A HACK |
187 |
+ |
# WHEREBY IT USES THE SERVICE STATUS |
188 |
+ |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
189 |
+ |
# BE LOOKED AT! |
190 |
+ |
# |
191 |
+ |
# note: if the UPPER threshold is broken, |
192 |
+ |
# the alertTimeout values are halved. |
193 |
+ |
# This is to escalate the alert quicker. |
194 |
+ |
#Monitor.Services.threshold.LOWER=120 |
195 |
+ |
#Monitor.Services.threshold.LOWER=300 |
196 |
+ |
|
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 |
211 |
+ |
# these are values in seconds from when the heartbeat |
212 |
+ |
# was *expected* to arrive (ie. last + hearbeat period) |
213 |
+ |
Monitor.Heartbeat.threshold.LOWER=120 |
214 |
+ |
Monitor.Heartbeat.threshold.LOWER=300 |
215 |
+ |
|
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 |
221 |
+ |
|
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 |
232 |
+ |
|
233 |
|
############################################################ |
234 |
|
#### Alerter Configuration |
235 |
|
############################################################ |
236 |
+ |
# The following var's are understood by ALL alerters for messages |
237 |
+ |
# |
238 |
+ |
# %level% - the alert level (eg, WARNING) |
239 |
+ |
# %threshold% - the threshold broken (eg, LOWER) |
240 |
+ |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
241 |
+ |
# %value% - the value reached (eg, 95) |
242 |
+ |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
243 |
+ |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
244 |
+ |
# %timeTillNextAlert% - the time the next alert will be sent out |
245 |
+ |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
246 |
+ |
# %timeOfFirstAlert% - the time the first alert was sent |
247 |
+ |
# |
248 |
|
|
249 |
|
# alerters to run |
250 |
|
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
251 |
< |
Alerter.Plugins=EMail;IRC; |
251 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder; |
252 |
|
|
253 |
|
# EMail alerter configuration |
254 |
|
Alerter.EMail.level = CAUTION |
255 |
< |
Alerter.EMail.destList = dev@i-scream.org.uk |
255 |
> |
Alerter.EMail.defaultDestList = dev@i-scream.org.uk |
256 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
257 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
258 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
262 |
|
Alerter.IRC.level = OK |
263 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
264 |
|
Alerter.IRC.IRCPort = 6667 |
265 |
< |
Alerter.IRC.nickList = iscreamBot;i-screamBot;_iscreamBot |
265 |
> |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
266 |
|
Alerter.IRC.user = i-scream |
267 |
|
Alerter.IRC.comment = i-scream alerting bot |
268 |
|
Alerter.IRC.channel = #i-scream |
273 |
|
Alerter.IRC.startCommand = start alerts |
274 |
|
Alerter.IRC.lastAlertCommand = last alert |
275 |
|
Alerter.IRC.joinCommand = join |
276 |
+ |
Alerter.IRC.nickChangeCommand = nick |
277 |
+ |
Alerter.IRC.statCommand = statistics |
278 |
+ |
Alerter.IRC.uptimeCommand = uptime |
279 |
+ |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
280 |
+ |
Alerter.IRC.versionCommand = version |
281 |
|
Alerter.IRC.helpCommand = help |
282 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
283 |
+ |
|
284 |
+ |
############################################################ |
285 |
+ |
#### WebFeeder Configuration |
286 |
+ |
############################################################ |
287 |
+ |
|
288 |
+ |
# Define these (one or both_ to turn on the WebFeeder's, |
289 |
+ |
# comment it to turn them off |
290 |
+ |
WebFeeder.latestActive = true |
291 |
+ |
WebFeeder.alertActive = true |
292 |
+ |
|
293 |
+ |
# Root Path |
294 |
+ |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
295 |
+ |
|
296 |
+ |
# Latest Data |
297 |
+ |
WebFeeder.latestSubDir = latest |
298 |
+ |
WebFeeder.latestFileName = latest_data |
299 |
+ |
|
300 |
+ |
# Alert Data |
301 |
+ |
WebFeeder.alertSubDir = alert |
302 |
+ |
WebFeeder.alertFileName = alert_data |
303 |
|
|
304 |
|
############################################################ |
305 |
|
|