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.*; |
97 |
|
|
98 |
|
# The port for the client interface to listen on |
99 |
|
ClientInterface.listenPort=4510 |
100 |
+ |
# The name for the client interface |
101 |
+ |
ClientInterface.name=realtimeclients |
102 |
|
|
103 |
|
|
104 |
|
|
105 |
|
############################################################ |
106 |
+ |
#### Database interface configuration |
107 |
+ |
############################################################ |
108 |
+ |
|
109 |
+ |
# The name for the Database interface |
110 |
+ |
DBInterface.name=database |
111 |
+ |
|
112 |
+ |
|
113 |
+ |
|
114 |
+ |
############################################################ |
115 |
|
#### Host Configuration |
116 |
|
############################################################ |
117 |
|
|
132 |
|
#### Monitor Configuration |
133 |
|
############################################################ |
134 |
|
|
135 |
< |
# the monitors to run |
135 |
> |
## The monitors to run |
136 |
|
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
137 |
< |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
137 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
138 |
> |
Heartbeat;Queue;UserCount;WebFeeder; |
139 |
|
|
140 |
+ |
## Default alert timeouts |
141 |
+ |
# these can be override on a per-monitor basis |
142 |
+ |
# timings of the alerts (in seconds) |
143 |
+ |
Monitor.alertTimeout.NOTICE=60 |
144 |
+ |
Monitor.alertTimeout.WARNING=900 |
145 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
146 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
147 |
|
|
148 |
< |
## CPU monitor configuration |
128 |
< |
# threshold values |
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 |
+ |
# |
154 |
+ |
|
155 |
+ |
# CPU monitor threshold values |
156 |
|
Monitor.CPU.threshold.LOWER=90 |
157 |
|
Monitor.CPU.threshold.UPPER=99 |
158 |
|
|
136 |
– |
# timings of the alerts (in seconds) |
137 |
– |
Monitor.CPU.alertTimeout.NOTICE=60 |
138 |
– |
Monitor.CPU.alertTimeout.WARNING=900 |
139 |
– |
Monitor.CPU.alertTimeout.CAUTION=1800 |
140 |
– |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
159 |
|
|
160 |
+ |
# Load monitor threshold values |
161 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
162 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
163 |
|
|
164 |
< |
## Memory monitor configuration |
165 |
< |
# threshold values |
166 |
< |
# |
167 |
< |
# note: if the UPPER threshold is broken, |
168 |
< |
# the alertTimeout values are halved. |
169 |
< |
# This is to escalate the alert quicker. |
164 |
> |
|
165 |
> |
# Process Count threshold values |
166 |
> |
Monitor.Process.threshold.LOWER=1000 |
167 |
> |
Monitor.Process.threshold.UPPER=1500 |
168 |
> |
|
169 |
> |
|
170 |
> |
# Memory monitor threshold values |
171 |
|
Monitor.Memory.threshold.LOWER=80 |
172 |
|
Monitor.Memory.threshold.UPPER=90 |
173 |
|
|
152 |
– |
# timings of the alerts (in seconds) |
153 |
– |
Monitor.Memory.alertTimeout.NOTICE=60 |
154 |
– |
Monitor.Memory.alertTimeout.WARNING=900 |
155 |
– |
Monitor.Memory.alertTimeout.CAUTION=1800 |
156 |
– |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
174 |
|
|
175 |
< |
|
159 |
< |
## Swap monitor configuration |
160 |
< |
# threshold values |
161 |
< |
# |
162 |
< |
# note: if the UPPER threshold is broken, |
163 |
< |
# the alertTimeout values are halved. |
164 |
< |
# This is to escalate the alert quicker. |
175 |
> |
# Swap monitor threshold values |
176 |
|
Monitor.Swap.threshold.LOWER=80 |
177 |
|
Monitor.Swap.threshold.UPPER=90 |
178 |
|
|
168 |
– |
# timings of the alerts (in seconds) |
169 |
– |
Monitor.Swap.alertTimeout.NOTICE=60 |
170 |
– |
Monitor.Swap.alertTimeout.WARNING=900 |
171 |
– |
Monitor.Swap.alertTimeout.CAUTION=1800 |
172 |
– |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
179 |
|
|
180 |
+ |
# UserCount monitor threshold values |
181 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
182 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
183 |
|
|
175 |
– |
## Disk monitor configuration |
176 |
– |
# threshold values |
177 |
– |
# |
178 |
– |
# note: if the UPPER threshold is broken, |
179 |
– |
# the alertTimeout values are halved. |
180 |
– |
# This is to escalate the alert quicker. |
181 |
– |
Monitor.Disk.threshold.LOWER=80 |
182 |
– |
Monitor.Disk.threshold.UPPER=90 |
184 |
|
|
185 |
< |
# timings of the alerts (in seconds) |
186 |
< |
Monitor.Disk.alertTimeout.NOTICE=60 |
187 |
< |
Monitor.Disk.alertTimeout.WARNING=900 |
188 |
< |
Monitor.Disk.alertTimeout.CAUTION=1800 |
189 |
< |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
185 |
> |
# Disk monitor threshold values |
186 |
> |
Monitor.Disk.threshold.LOWER=90 |
187 |
> |
Monitor.Disk.threshold.UPPER=95 |
188 |
> |
# Thresholds given are PERCENTAGE or VALUE |
189 |
> |
# where PERCENTAGE is a percentage of disk in use |
190 |
> |
# and VALUE is an absolute value of space free |
191 |
> |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
192 |
|
|
193 |
|
|
194 |
< |
## Services monitor configuration |
195 |
< |
# threshold values |
194 |
> |
# Disk monitor threshold values |
195 |
> |
Monitor.Queue.threshold.LOWER=50 |
196 |
> |
Monitor.Queue.threshold.UPPER=80 |
197 |
> |
# Thresholds given are PERCENTAGE or VALUE |
198 |
> |
# where PERCENTAGE is a percentage of disk in use |
199 |
> |
# and VALUE is an absolute value of space free |
200 |
> |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
201 |
> |
|
202 |
> |
|
203 |
> |
# Services monitor threshold values |
204 |
|
# |
205 |
|
# THE SERVICES MONITOR USES A HACK |
206 |
|
# WHEREBY IT USES THE SERVICE STATUS |
207 |
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
208 |
|
# BE LOOKED AT! |
209 |
|
# |
210 |
< |
# note: if the UPPER threshold is broken, |
211 |
< |
# the alertTimeout values are halved. |
201 |
< |
# This is to escalate the alert quicker. |
202 |
< |
#Monitor.Services.threshold.LOWER=120 |
203 |
< |
#Monitor.Services.threshold.LOWER=300 |
204 |
< |
|
205 |
< |
# timings of the alerts (in seconds) |
206 |
< |
Monitor.Services.alertTimeout.NOTICE=60 |
207 |
< |
Monitor.Services.alertTimeout.WARNING=900 |
208 |
< |
Monitor.Services.alertTimeout.CAUTION=1800 |
209 |
< |
Monitor.Services.alertTimeout.CRITICAL=3600 |
210 |
< |
|
211 |
< |
# Make sure we shut up eventually |
210 |
> |
# how many times we should be at the highest level before |
211 |
> |
# we go to a FINAL alert |
212 |
|
Monitor.Services.reachFINALcount=5 |
213 |
|
|
214 |
|
|
215 |
< |
## Heartbeat monitor configuration |
216 |
< |
# threshold values |
217 |
< |
# |
218 |
< |
# note: if the UPPER threshold is broken, |
219 |
< |
# the alertTimeout values are halved. |
220 |
< |
# This is to escalate the alert quicker. |
221 |
< |
Monitor.Heartbeat.checkPeriod=50 |
215 |
> |
# Heartbeat threshold values |
216 |
|
# these are values in seconds from when the heartbeat |
217 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
218 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
218 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
219 |
|
Monitor.Heartbeat.threshold.UPPER=300 |
220 |
+ |
# this is how often we will run a "check" of heartbeats |
221 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
222 |
+ |
# how many times we should be at the highest level before |
223 |
+ |
# we go to a FINAL alert |
224 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
225 |
|
|
227 |
– |
# timings of the alerts (in seconds) |
228 |
– |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
229 |
– |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
230 |
– |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
231 |
– |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
226 |
|
|
233 |
– |
# this means it will reach a FINAL level, |
234 |
– |
# and thus the host will be removed from the monitor list, |
235 |
– |
# if the highest level alert is reached and occours this |
236 |
– |
# number of times. |
237 |
– |
# |
238 |
– |
# int this setup, that means 5 CRITICAL alerts would occour |
239 |
– |
# on a Heartbeat before reaching FINAL. |
240 |
– |
# If this value is wrong or not present, FINAL is never reached |
241 |
– |
# |
242 |
– |
Monitor.Heartbeat.reachFINALcount=5 |
227 |
|
|
228 |
|
############################################################ |
229 |
|
#### Alerter Configuration |
245 |
|
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
246 |
|
Alerter.Plugins=EMail;IRC;WebFeeder; |
247 |
|
|
248 |
+ |
|
249 |
|
# EMail alerter configuration |
250 |
|
Alerter.EMail.level = WARNING |
251 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
278 |
|
Alerter.IRC.helpCommand = help |
279 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
280 |
|
|
281 |
+ |
|
282 |
+ |
|
283 |
|
############################################################ |
284 |
|
#### WebFeeder Configuration |
285 |
|
############################################################ |
289 |
|
WebFeeder.latestActive = true |
290 |
|
WebFeeder.alertActive = true |
291 |
|
|
292 |
+ |
# Only pass on alerts past this level |
293 |
+ |
WebFeeder.alertLevel = OK |
294 |
+ |
|
295 |
|
# Check period in seconds (for cleaning stale/old alerts) |
296 |
< |
WebFeeder.checkPeriod = 900 |
296 |
> |
WebFeeder.checkPeriod = 120 |
297 |
|
|
298 |
|
# Delete alerts older than this, in seconds. |
299 |
|
# Files are only check every WebFeeder.checkPeriod seconds. |
300 |
< |
WebFeeder.alertDeleteOlderThan = 1800 |
300 |
> |
WebFeeder.alertDeleteOlderThan = 300 |
301 |
|
|
302 |
|
# Root Path |
303 |
|
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
310 |
|
WebFeeder.alertSubDir = alert |
311 |
|
WebFeeder.alertFileName = alert_data |
312 |
|
|
323 |
– |
############################################################ |
313 |
|
|
314 |
+ |
############################################################ |