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;Load;Process;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
127 |
< |
#Monitor.Plugins=CPU;WebFeeder; |
128 |
< |
#Monitor.Plugins= |
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 |
132 |
< |
# 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 |
|
|
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 |
147 |
|
|
148 |
< |
|
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. |
148 |
> |
# Load monitor threshold values |
149 |
|
Monitor.Load.threshold.LOWER=10.0 |
150 |
|
Monitor.Load.threshold.UPPER=20.0 |
151 |
|
|
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 |
152 |
|
|
153 |
< |
|
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. |
153 |
> |
# Process Count threshold values |
154 |
|
Monitor.Process.threshold.LOWER=1000 |
155 |
|
Monitor.Process.threshold.UPPER=1500 |
156 |
|
|
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 |
157 |
|
|
158 |
< |
|
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. |
158 |
> |
# Memory monitor threshold values |
159 |
|
Monitor.Memory.threshold.LOWER=80 |
160 |
|
Monitor.Memory.threshold.UPPER=90 |
161 |
|
|
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 |
162 |
|
|
163 |
< |
|
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. |
163 |
> |
# Swap monitor threshold values |
164 |
|
Monitor.Swap.threshold.LOWER=80 |
165 |
|
Monitor.Swap.threshold.UPPER=90 |
166 |
|
|
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 |
167 |
|
|
168 |
< |
|
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. |
168 |
> |
# Disk monitor threshold values |
169 |
|
Monitor.Disk.threshold.LOWER=90 |
170 |
|
Monitor.Disk.threshold.UPPER=95 |
171 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
172 |
+ |
# where PERCENTAGE is a percentage of disk in use |
173 |
+ |
# and VALUE is an absolute value of space free |
174 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
175 |
|
|
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 |
176 |
|
|
177 |
+ |
# Disk monitor threshold values |
178 |
+ |
Monitor.Queue.threshold.LOWER=50 |
179 |
+ |
Monitor.Queue.threshold.UPPER=80 |
180 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
181 |
+ |
# where PERCENTAGE is a percentage of disk in use |
182 |
+ |
# and VALUE is an absolute value of space free |
183 |
+ |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
184 |
|
|
185 |
< |
## Services monitor configuration |
186 |
< |
# threshold values |
185 |
> |
|
186 |
> |
# Services monitor threshold values |
187 |
|
# |
188 |
|
# THE SERVICES MONITOR USES A HACK |
189 |
|
# WHEREBY IT USES THE SERVICE STATUS |
190 |
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
191 |
|
# BE LOOKED AT! |
192 |
|
# |
193 |
< |
# note: if the UPPER threshold is broken, |
194 |
< |
# 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 |
193 |
> |
# how many times we should be at the highest level before |
194 |
> |
# we go to a FINAL alert |
195 |
|
Monitor.Services.reachFINALcount=5 |
196 |
|
|
197 |
|
|
198 |
< |
## 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 |
198 |
> |
# Heartbeat threshold values |
199 |
|
# these are values in seconds from when the heartbeat |
200 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
201 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
201 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
202 |
|
Monitor.Heartbeat.threshold.UPPER=300 |
203 |
+ |
# this is how often we will run a "check" of heartbeats |
204 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
205 |
+ |
# how many times we should be at the highest level before |
206 |
+ |
# we go to a FINAL alert |
207 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
208 |
|
|
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 |
209 |
|
|
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 |
210 |
|
|
211 |
|
############################################################ |
212 |
|
#### Alerter Configuration |
226 |
|
|
227 |
|
# alerters to run |
228 |
|
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
229 |
< |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
299 |
< |
Alerter.Plugins=IRC;WebFeeder; |
300 |
< |
#Alerter.Plugins=WebFeeder; |
301 |
< |
#Alerter.Plugins= |
229 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder; |
230 |
|
|
231 |
+ |
|
232 |
|
# EMail alerter configuration |
233 |
|
Alerter.EMail.level = WARNING |
234 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
261 |
|
Alerter.IRC.helpCommand = help |
262 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
263 |
|
|
264 |
+ |
|
265 |
+ |
|
266 |
|
############################################################ |
267 |
|
#### WebFeeder Configuration |
268 |
|
############################################################ |
293 |
|
WebFeeder.alertSubDir = alert |
294 |
|
WebFeeder.alertFileName = alert_data |
295 |
|
|
365 |
– |
############################################################ |
296 |
|
|
297 |
+ |
############################################################ |