1 |
tdb |
1.2 |
# This is the default system configuration file |
2 |
|
|
# used by all components of the i-scream system |
3 |
|
|
# |
4 |
|
|
# ALL configuration that uses the centralised |
5 |
|
|
# configuration system has this file as its |
6 |
|
|
# root of configuration |
7 |
|
|
# |
8 |
tdb |
1.36 |
# $Author: tdb1 $ |
9 |
tdb |
1.43 |
# $Id: system.conf,v 1.42 2001/03/19 20:57:41 tdb1 Exp $ |
10 |
ajm |
1.14 |
# |
11 |
|
|
############################################################ |
12 |
|
|
#### Configuration Files & Groups |
13 |
|
|
############################################################ |
14 |
|
|
|
15 |
|
|
# for computing machines |
16 |
tdb |
1.15 |
group.computing=Host.129.12.4.*; |
17 |
tdb |
1.41 |
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 |
tdb |
1.42 |
group.compsoc=Host.compsoc1.ukc.ac.uk |
22 |
tdb |
1.41 |
|
23 |
tdb |
1.15 |
config.computing=computing.conf |
24 |
tdb |
1.41 |
config.rocks=rocks.conf |
25 |
tdb |
1.42 |
config.compsoc1=rocks.conf |
26 |
ajm |
1.14 |
|
27 |
|
|
# for library machines |
28 |
tdb |
1.15 |
group.library=Host.129.12.58.*; |
29 |
ajm |
1.14 |
config.library=library.conf |
30 |
|
|
|
31 |
tdb |
1.15 |
# for SSB machines |
32 |
|
|
group.ssb=Host.stue*.ukc.ac.uk; |
33 |
|
|
config.ssb=ssb.conf |
34 |
|
|
|
35 |
ajm |
1.14 |
# mySQL configuration |
36 |
|
|
config.mySQL=mySQL.conf |
37 |
|
|
|
38 |
ajm |
1.16 |
############################################################ |
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 |
tdb |
1.40 |
# The upper limit for a Queue |
49 |
|
|
Queue.SizeLimit=1000 |
50 |
|
|
# The removal algorithm |
51 |
|
|
Queue.RemoveAlgorithm=FIRST |
52 |
tdb |
1.2 |
|
53 |
ajm |
1.14 |
|
54 |
|
|
############################################################ |
55 |
|
|
#### FilterManager configuration |
56 |
|
|
############################################################ |
57 |
tdb |
1.2 |
|
58 |
|
|
# The default port to listen for new host connections |
59 |
|
|
FilterManager.listenPort=4567 |
60 |
|
|
|
61 |
ajm |
1.14 |
|
62 |
|
|
|
63 |
|
|
############################################################ |
64 |
|
|
#### Filter configuration |
65 |
|
|
############################################################ |
66 |
|
|
|
67 |
tdb |
1.2 |
# The default port for Filter's to listen on |
68 |
|
|
Filter.UDPListenPort=4589 |
69 |
|
|
Filter.TCPListenPort=4589 |
70 |
|
|
|
71 |
ajm |
1.14 |
# Plugin Information |
72 |
tdb |
1.36 |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
73 |
ajm |
1.14 |
Filter.Plugins=TypeChecker;EnforceEssentialData |
74 |
|
|
|
75 |
tdb |
1.2 |
# The name for the root filter |
76 |
|
|
RootFilter.name=root |
77 |
ajm |
1.14 |
|
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 |
tdb |
1.2 |
# Comment either of these (or delete them) and |
88 |
|
|
# that interface won't be started |
89 |
|
|
RootFilter.realtimeInterfaceName=realtimeclients |
90 |
tdb |
1.6 |
RootFilter.dbInterfaceName=database |
91 |
tdb |
1.2 |
|
92 |
ajm |
1.14 |
|
93 |
|
|
|
94 |
|
|
############################################################ |
95 |
|
|
#### Client interface configuration |
96 |
|
|
############################################################ |
97 |
|
|
|
98 |
tdb |
1.2 |
# The port for the client interface to listen on |
99 |
|
|
ClientInterface.listenPort=4510 |
100 |
|
|
|
101 |
ajm |
1.14 |
|
102 |
|
|
|
103 |
|
|
############################################################ |
104 |
|
|
#### Host Configuration |
105 |
|
|
############################################################ |
106 |
tdb |
1.2 |
|
107 |
|
|
# The default filter for a new host |
108 |
tdb |
1.36 |
Host.filter=computingFilter; |
109 |
tdb |
1.13 |
|
110 |
tdb |
1.2 |
# The default update times for a new host |
111 |
tdb |
1.7 |
Host.UDPUpdateTime=10 |
112 |
tdb |
1.2 |
Host.TCPUpdateTime=60 |
113 |
tdb |
1.15 |
Host.AveragerUpdateTime=5 |
114 |
tdb |
1.2 |
|
115 |
ajm |
1.8 |
# The services checks to run on a host |
116 |
tdb |
1.36 |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
117 |
tdb |
1.2 |
|
118 |
ajm |
1.14 |
|
119 |
tdb |
1.12 |
|
120 |
ajm |
1.14 |
############################################################ |
121 |
|
|
#### Monitor Configuration |
122 |
|
|
############################################################ |
123 |
|
|
|
124 |
|
|
# the monitors to run |
125 |
tdb |
1.36 |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
126 |
tdb |
1.35 |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
127 |
tdb |
1.42 |
#Monitor.Plugins=CPU;WebFeeder; |
128 |
|
|
#Monitor.Plugins= |
129 |
tdb |
1.24 |
|
130 |
ajm |
1.14 |
|
131 |
tdb |
1.22 |
## CPU monitor configuration |
132 |
ajm |
1.16 |
# 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 |
tdb |
1.24 |
|
146 |
|
|
|
147 |
|
|
## Memory 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.Memory.threshold.LOWER=80 |
154 |
|
|
Monitor.Memory.threshold.UPPER=90 |
155 |
|
|
|
156 |
|
|
# timings of the alerts (in seconds) |
157 |
|
|
Monitor.Memory.alertTimeout.NOTICE=60 |
158 |
|
|
Monitor.Memory.alertTimeout.WARNING=900 |
159 |
|
|
Monitor.Memory.alertTimeout.CAUTION=1800 |
160 |
|
|
Monitor.Memory.alertTimeout.CRITICAL=3600 |
161 |
|
|
|
162 |
|
|
|
163 |
|
|
## Swap 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.Swap.threshold.LOWER=80 |
170 |
|
|
Monitor.Swap.threshold.UPPER=90 |
171 |
|
|
|
172 |
|
|
# timings of the alerts (in seconds) |
173 |
|
|
Monitor.Swap.alertTimeout.NOTICE=60 |
174 |
|
|
Monitor.Swap.alertTimeout.WARNING=900 |
175 |
|
|
Monitor.Swap.alertTimeout.CAUTION=1800 |
176 |
|
|
Monitor.Swap.alertTimeout.CRITICAL=3600 |
177 |
ajm |
1.33 |
|
178 |
|
|
|
179 |
|
|
## Disk 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 |
tdb |
1.42 |
Monitor.Disk.threshold.LOWER=90 |
186 |
|
|
Monitor.Disk.threshold.UPPER=95 |
187 |
ajm |
1.33 |
|
188 |
|
|
# timings of the alerts (in seconds) |
189 |
|
|
Monitor.Disk.alertTimeout.NOTICE=60 |
190 |
|
|
Monitor.Disk.alertTimeout.WARNING=900 |
191 |
|
|
Monitor.Disk.alertTimeout.CAUTION=1800 |
192 |
|
|
Monitor.Disk.alertTimeout.CRITICAL=3600 |
193 |
ajm |
1.34 |
|
194 |
|
|
|
195 |
|
|
## Services monitor configuration |
196 |
|
|
# threshold values |
197 |
|
|
# |
198 |
|
|
# THE SERVICES MONITOR USES A HACK |
199 |
|
|
# WHEREBY IT USES THE SERVICE STATUS |
200 |
|
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
201 |
|
|
# BE LOOKED AT! |
202 |
|
|
# |
203 |
|
|
# note: if the UPPER threshold is broken, |
204 |
|
|
# the alertTimeout values are halved. |
205 |
|
|
# This is to escalate the alert quicker. |
206 |
|
|
#Monitor.Services.threshold.LOWER=120 |
207 |
|
|
#Monitor.Services.threshold.LOWER=300 |
208 |
|
|
|
209 |
|
|
# timings of the alerts (in seconds) |
210 |
|
|
Monitor.Services.alertTimeout.NOTICE=60 |
211 |
|
|
Monitor.Services.alertTimeout.WARNING=900 |
212 |
|
|
Monitor.Services.alertTimeout.CAUTION=1800 |
213 |
|
|
Monitor.Services.alertTimeout.CRITICAL=3600 |
214 |
tdb |
1.24 |
|
215 |
tdb |
1.38 |
# Make sure we shut up eventually |
216 |
|
|
Monitor.Services.reachFINALcount=5 |
217 |
|
|
|
218 |
ajm |
1.14 |
|
219 |
tdb |
1.22 |
## Heartbeat monitor configuration |
220 |
|
|
# threshold values |
221 |
|
|
# |
222 |
|
|
# note: if the UPPER threshold is broken, |
223 |
|
|
# the alertTimeout values are halved. |
224 |
|
|
# This is to escalate the alert quicker. |
225 |
|
|
Monitor.Heartbeat.checkPeriod=50 |
226 |
tdb |
1.25 |
# these are values in seconds from when the heartbeat |
227 |
|
|
# was *expected* to arrive (ie. last + hearbeat period) |
228 |
tdb |
1.22 |
Monitor.Heartbeat.threshold.LOWER=120 |
229 |
tdb |
1.38 |
Monitor.Heartbeat.threshold.UPPER=300 |
230 |
ajm |
1.14 |
|
231 |
tdb |
1.22 |
# timings of the alerts (in seconds) |
232 |
|
|
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
233 |
|
|
Monitor.Heartbeat.alertTimeout.WARNING=900 |
234 |
|
|
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
235 |
|
|
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
236 |
ajm |
1.14 |
|
237 |
ajm |
1.23 |
# this means it will reach a FINAL level, |
238 |
|
|
# and thus the host will be removed from the monitor list, |
239 |
|
|
# if the highest level alert is reached and occours this |
240 |
|
|
# number of times. |
241 |
|
|
# |
242 |
|
|
# int this setup, that means 5 CRITICAL alerts would occour |
243 |
|
|
# on a Heartbeat before reaching FINAL. |
244 |
|
|
# If this value is wrong or not present, FINAL is never reached |
245 |
|
|
# |
246 |
|
|
Monitor.Heartbeat.reachFINALcount=5 |
247 |
|
|
|
248 |
ajm |
1.14 |
############################################################ |
249 |
|
|
#### Alerter Configuration |
250 |
|
|
############################################################ |
251 |
ajm |
1.23 |
# The following var's are understood by ALL alerters for messages |
252 |
|
|
# |
253 |
|
|
# %level% - the alert level (eg, WARNING) |
254 |
|
|
# %threshold% - the threshold broken (eg, LOWER) |
255 |
|
|
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
256 |
|
|
# %value% - the value reached (eg, 95) |
257 |
|
|
# %thresholdValue% - the value of the threshold broken (eg, 90) |
258 |
|
|
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
259 |
|
|
# %timeTillNextAlert% - the time the next alert will be sent out |
260 |
|
|
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
261 |
|
|
# %timeOfFirstAlert% - the time the first alert was sent |
262 |
|
|
# |
263 |
ajm |
1.14 |
|
264 |
|
|
# alerters to run |
265 |
tdb |
1.36 |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
266 |
tdb |
1.42 |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
267 |
|
|
Alerter.Plugins=IRC;WebFeeder; |
268 |
|
|
#Alerter.Plugins=WebFeeder; |
269 |
|
|
#Alerter.Plugins= |
270 |
ajm |
1.14 |
|
271 |
|
|
# EMail alerter configuration |
272 |
tdb |
1.38 |
Alerter.EMail.level = WARNING |
273 |
|
|
Alerter.EMail.destList = dev@i-scream.org.uk |
274 |
ajm |
1.14 |
Alerter.EMail.sender = dev@i-scream.org.uk |
275 |
|
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
276 |
ajm |
1.16 |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
277 |
tdb |
1.38 |
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%. |
278 |
|
|
|
279 |
ajm |
1.14 |
|
280 |
|
|
# IRC alerter configuration |
281 |
ajm |
1.16 |
Alerter.IRC.level = OK |
282 |
ajm |
1.14 |
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
283 |
|
|
Alerter.IRC.IRCPort = 6667 |
284 |
tdb |
1.19 |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
285 |
tdb |
1.17 |
Alerter.IRC.user = i-scream |
286 |
|
|
Alerter.IRC.comment = i-scream alerting bot |
287 |
ajm |
1.14 |
Alerter.IRC.channel = #i-scream |
288 |
ajm |
1.16 |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
289 |
tdb |
1.17 |
Alerter.IRC.reconnectDelay = 30 |
290 |
|
|
Alerter.IRC.startupNotice = i-scream alerting bot activated |
291 |
|
|
Alerter.IRC.stopCommand = stop alerts |
292 |
|
|
Alerter.IRC.startCommand = start alerts |
293 |
|
|
Alerter.IRC.lastAlertCommand = last alert |
294 |
|
|
Alerter.IRC.joinCommand = join |
295 |
tdb |
1.18 |
Alerter.IRC.nickChangeCommand = nick |
296 |
|
|
Alerter.IRC.statCommand = statistics |
297 |
|
|
Alerter.IRC.uptimeCommand = uptime |
298 |
|
|
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
299 |
tdb |
1.19 |
Alerter.IRC.versionCommand = version |
300 |
tdb |
1.17 |
Alerter.IRC.helpCommand = help |
301 |
|
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
302 |
tdb |
1.29 |
|
303 |
|
|
############################################################ |
304 |
|
|
#### WebFeeder Configuration |
305 |
|
|
############################################################ |
306 |
|
|
|
307 |
tdb |
1.32 |
# Define these (one or both_ to turn on the WebFeeder's, |
308 |
|
|
# comment it to turn them off |
309 |
|
|
WebFeeder.latestActive = true |
310 |
|
|
WebFeeder.alertActive = true |
311 |
tdb |
1.43 |
|
312 |
|
|
# Only pass on alerts past this level |
313 |
|
|
WebFeeder.alertLevel = OK |
314 |
tdb |
1.37 |
|
315 |
|
|
# Check period in seconds (for cleaning stale/old alerts) |
316 |
tdb |
1.42 |
WebFeeder.checkPeriod = 120 |
317 |
tdb |
1.37 |
|
318 |
|
|
# Delete alerts older than this, in seconds. |
319 |
|
|
# Files are only check every WebFeeder.checkPeriod seconds. |
320 |
tdb |
1.42 |
WebFeeder.alertDeleteOlderThan = 300 |
321 |
tdb |
1.32 |
|
322 |
tdb |
1.29 |
# Root Path |
323 |
|
|
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
324 |
|
|
|
325 |
|
|
# Latest Data |
326 |
|
|
WebFeeder.latestSubDir = latest |
327 |
tdb |
1.31 |
WebFeeder.latestFileName = latest_data |
328 |
tdb |
1.32 |
|
329 |
|
|
# Alert Data |
330 |
|
|
WebFeeder.alertSubDir = alert |
331 |
|
|
WebFeeder.alertFileName = alert_data |
332 |
ajm |
1.16 |
|
333 |
tdb |
1.17 |
############################################################ |
334 |
ajm |
1.16 |
|