7 |
|
# |
8 |
|
# $Author$ |
9 |
|
# $Id$ |
10 |
+ |
# |
11 |
+ |
############################################################ |
12 |
+ |
#### Configuration Files & Groups |
13 |
+ |
############################################################ |
14 |
|
|
15 |
< |
# FilterManager configuration |
15 |
> |
# for computing machines |
16 |
> |
group.computing=Host.129.12.4.*; |
17 |
> |
config.computing=computing.conf |
18 |
|
|
19 |
+ |
# for library machines |
20 |
+ |
group.library=Host.129.12.58.*; |
21 |
+ |
config.library=library.conf |
22 |
+ |
|
23 |
+ |
# for SSB machines |
24 |
+ |
group.ssb=Host.stue*.ukc.ac.uk; |
25 |
+ |
config.ssb=ssb.conf |
26 |
+ |
|
27 |
+ |
# mySQL configuration |
28 |
+ |
config.mySQL=mySQL.conf |
29 |
+ |
|
30 |
+ |
############################################################ |
31 |
+ |
#### Misc system-wide configuration |
32 |
+ |
############################################################ |
33 |
+ |
|
34 |
+ |
# the time (in seconds) that checks should be made for |
35 |
+ |
# changes in configuration |
36 |
+ |
ConfigurationProxy.updateTime=60 |
37 |
+ |
|
38 |
+ |
# The time interval at which the Queue's should be monitored |
39 |
+ |
Queue.MonitorInterval=15 |
40 |
+ |
# The upper limit for a Queue |
41 |
+ |
Queue.SizeLimit=1000 |
42 |
+ |
# The removal algorithm |
43 |
+ |
Queue.RemoveAlgorithm=FIRST |
44 |
+ |
|
45 |
+ |
|
46 |
+ |
############################################################ |
47 |
+ |
#### FilterManager configuration |
48 |
+ |
############################################################ |
49 |
+ |
|
50 |
|
# The default port to listen for new host connections |
51 |
|
FilterManager.listenPort=4567 |
52 |
|
|
53 |
+ |
|
54 |
+ |
|
55 |
+ |
############################################################ |
56 |
+ |
#### Filter configuration |
57 |
+ |
############################################################ |
58 |
+ |
|
59 |
|
# The default port for Filter's to listen on |
60 |
|
Filter.UDPListenPort=4589 |
61 |
|
Filter.TCPListenPort=4589 |
62 |
|
|
63 |
+ |
# Plugin Information |
64 |
+ |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
65 |
+ |
Filter.Plugins=TypeChecker;EnforceEssentialData |
66 |
+ |
|
67 |
|
# The name for the root filter |
68 |
|
RootFilter.name=root |
69 |
+ |
|
70 |
+ |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
71 |
+ |
Filter.parentFilter=root |
72 |
+ |
|
73 |
+ |
|
74 |
+ |
|
75 |
+ |
############################################################ |
76 |
+ |
#### Root filter interfaces configuration |
77 |
+ |
############################################################ |
78 |
+ |
|
79 |
|
# Comment either of these (or delete them) and |
80 |
|
# that interface won't be started |
81 |
|
RootFilter.realtimeInterfaceName=realtimeclients |
82 |
|
RootFilter.dbInterfaceName=database |
83 |
|
|
84 |
+ |
|
85 |
+ |
|
86 |
+ |
############################################################ |
87 |
+ |
#### Client interface configuration |
88 |
+ |
############################################################ |
89 |
+ |
|
90 |
|
# The port for the client interface to listen on |
91 |
|
ClientInterface.listenPort=4510 |
92 |
|
|
30 |
– |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
31 |
– |
Filter.parentFilter=root |
93 |
|
|
94 |
+ |
|
95 |
+ |
############################################################ |
96 |
+ |
#### Host Configuration |
97 |
+ |
############################################################ |
98 |
+ |
|
99 |
|
# The default filter for a new host |
100 |
< |
Host.filter=filter1 |
100 |
> |
Host.filter=computingFilter; |
101 |
|
|
102 |
|
# The default update times for a new host |
103 |
|
Host.UDPUpdateTime=10 |
104 |
|
Host.TCPUpdateTime=60 |
105 |
+ |
Host.AveragerUpdateTime=5 |
106 |
|
|
40 |
– |
# Plugin Information |
41 |
– |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
42 |
– |
Filter.Plugins=TypeChecker;EnforceEssentialData |
43 |
– |
|
107 |
|
# The services checks to run on a host |
108 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
109 |
< |
Host.serviceChecks=Test;HTTP |
108 |
> |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
109 |
> |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet |
110 |
|
|
111 |
< |
# mySQL Details |
112 |
< |
config.mySQL=mySQL.conf |
111 |
> |
|
112 |
> |
|
113 |
> |
############################################################ |
114 |
> |
#### Monitor Configuration |
115 |
> |
############################################################ |
116 |
> |
|
117 |
> |
# the monitors to run |
118 |
> |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
119 |
> |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
120 |
> |
|
121 |
> |
|
122 |
> |
## CPU monitor configuration |
123 |
> |
# threshold values |
124 |
> |
# |
125 |
> |
# note: if the UPPER threshold is broken, |
126 |
> |
# the alertTimeout values are halved. |
127 |
> |
# This is to escalate the alert quicker. |
128 |
> |
Monitor.CPU.threshold.LOWER=90 |
129 |
> |
Monitor.CPU.threshold.UPPER=99 |
130 |
> |
|
131 |
> |
# timings of the alerts (in seconds) |
132 |
> |
Monitor.CPU.alertTimeout.NOTICE=60 |
133 |
> |
Monitor.CPU.alertTimeout.WARNING=900 |
134 |
> |
Monitor.CPU.alertTimeout.CAUTION=1800 |
135 |
> |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
136 |
> |
|
137 |
> |
|
138 |
> |
## Memory monitor configuration |
139 |
> |
# threshold values |
140 |
> |
# |
141 |
> |
# note: if the UPPER threshold is broken, |
142 |
> |
# the alertTimeout values are halved. |
143 |
> |
# This is to escalate the alert quicker. |
144 |
> |
Monitor.Memory.threshold.LOWER=80 |
145 |
> |
Monitor.Memory.threshold.UPPER=90 |
146 |
> |
|
147 |
> |
# timings of the alerts (in seconds) |
148 |
> |
Monitor.Memory.alertTimeout.NOTICE=60 |
149 |
> |
Monitor.Memory.alertTimeout.WARNING=900 |
150 |
> |
Monitor.Memory.alertTimeout.CAUTION=1800 |
151 |
> |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
152 |
> |
|
153 |
> |
|
154 |
> |
## Swap monitor configuration |
155 |
> |
# threshold values |
156 |
> |
# |
157 |
> |
# note: if the UPPER threshold is broken, |
158 |
> |
# the alertTimeout values are halved. |
159 |
> |
# This is to escalate the alert quicker. |
160 |
> |
Monitor.Swap.threshold.LOWER=80 |
161 |
> |
Monitor.Swap.threshold.UPPER=90 |
162 |
> |
|
163 |
> |
# timings of the alerts (in seconds) |
164 |
> |
Monitor.Swap.alertTimeout.NOTICE=60 |
165 |
> |
Monitor.Swap.alertTimeout.WARNING=900 |
166 |
> |
Monitor.Swap.alertTimeout.CAUTION=1800 |
167 |
> |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
168 |
> |
|
169 |
> |
|
170 |
> |
## Disk monitor configuration |
171 |
> |
# threshold values |
172 |
> |
# |
173 |
> |
# note: if the UPPER threshold is broken, |
174 |
> |
# the alertTimeout values are halved. |
175 |
> |
# This is to escalate the alert quicker. |
176 |
> |
Monitor.Disk.threshold.LOWER=80 |
177 |
> |
Monitor.Disk.threshold.UPPER=90 |
178 |
> |
|
179 |
> |
# timings of the alerts (in seconds) |
180 |
> |
Monitor.Disk.alertTimeout.NOTICE=60 |
181 |
> |
Monitor.Disk.alertTimeout.WARNING=900 |
182 |
> |
Monitor.Disk.alertTimeout.CAUTION=1800 |
183 |
> |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
184 |
> |
|
185 |
> |
|
186 |
> |
## Services monitor configuration |
187 |
> |
# threshold values |
188 |
> |
# |
189 |
> |
# THE SERVICES MONITOR USES A HACK |
190 |
> |
# WHEREBY IT USES THE SERVICE STATUS |
191 |
> |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
192 |
> |
# BE LOOKED AT! |
193 |
> |
# |
194 |
> |
# note: if the UPPER threshold is broken, |
195 |
> |
# the alertTimeout values are halved. |
196 |
> |
# This is to escalate the alert quicker. |
197 |
> |
#Monitor.Services.threshold.LOWER=120 |
198 |
> |
#Monitor.Services.threshold.LOWER=300 |
199 |
> |
|
200 |
> |
# timings of the alerts (in seconds) |
201 |
> |
Monitor.Services.alertTimeout.NOTICE=60 |
202 |
> |
Monitor.Services.alertTimeout.WARNING=900 |
203 |
> |
Monitor.Services.alertTimeout.CAUTION=1800 |
204 |
> |
Monitor.Services.alertTimeout.CRITICAL=3600 |
205 |
> |
|
206 |
> |
# Make sure we shut up eventually |
207 |
> |
Monitor.Services.reachFINALcount=5 |
208 |
> |
|
209 |
> |
|
210 |
> |
## Heartbeat monitor configuration |
211 |
> |
# threshold values |
212 |
> |
# |
213 |
> |
# note: if the UPPER threshold is broken, |
214 |
> |
# the alertTimeout values are halved. |
215 |
> |
# This is to escalate the alert quicker. |
216 |
> |
Monitor.Heartbeat.checkPeriod=50 |
217 |
> |
# these are values in seconds from when the heartbeat |
218 |
> |
# was *expected* to arrive (ie. last + hearbeat period) |
219 |
> |
Monitor.Heartbeat.threshold.LOWER=120 |
220 |
> |
Monitor.Heartbeat.threshold.UPPER=300 |
221 |
> |
|
222 |
> |
# timings of the alerts (in seconds) |
223 |
> |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
224 |
> |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
225 |
> |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
226 |
> |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
227 |
> |
|
228 |
> |
# this means it will reach a FINAL level, |
229 |
> |
# and thus the host will be removed from the monitor list, |
230 |
> |
# if the highest level alert is reached and occours this |
231 |
> |
# number of times. |
232 |
> |
# |
233 |
> |
# int this setup, that means 5 CRITICAL alerts would occour |
234 |
> |
# on a Heartbeat before reaching FINAL. |
235 |
> |
# If this value is wrong or not present, FINAL is never reached |
236 |
> |
# |
237 |
> |
Monitor.Heartbeat.reachFINALcount=5 |
238 |
> |
|
239 |
> |
############################################################ |
240 |
> |
#### Alerter Configuration |
241 |
> |
############################################################ |
242 |
> |
# The following var's are understood by ALL alerters for messages |
243 |
> |
# |
244 |
> |
# %level% - the alert level (eg, WARNING) |
245 |
> |
# %threshold% - the threshold broken (eg, LOWER) |
246 |
> |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
247 |
> |
# %value% - the value reached (eg, 95) |
248 |
> |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
249 |
> |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
250 |
> |
# %timeTillNextAlert% - the time the next alert will be sent out |
251 |
> |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
252 |
> |
# %timeOfFirstAlert% - the time the first alert was sent |
253 |
> |
# |
254 |
> |
|
255 |
> |
# alerters to run |
256 |
> |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
257 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder; |
258 |
> |
|
259 |
> |
# EMail alerter configuration |
260 |
> |
Alerter.EMail.level = WARNING |
261 |
> |
Alerter.EMail.destList = dev@i-scream.org.uk |
262 |
> |
Alerter.EMail.sender = dev@i-scream.org.uk |
263 |
> |
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
264 |
> |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
265 |
> |
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%. |
266 |
> |
|
267 |
> |
|
268 |
> |
# IRC alerter configuration |
269 |
> |
Alerter.IRC.level = OK |
270 |
> |
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
271 |
> |
Alerter.IRC.IRCPort = 6667 |
272 |
> |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
273 |
> |
Alerter.IRC.user = i-scream |
274 |
> |
Alerter.IRC.comment = i-scream alerting bot |
275 |
> |
Alerter.IRC.channel = #i-scream |
276 |
> |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
277 |
> |
Alerter.IRC.reconnectDelay = 30 |
278 |
> |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
279 |
> |
Alerter.IRC.stopCommand = stop alerts |
280 |
> |
Alerter.IRC.startCommand = start alerts |
281 |
> |
Alerter.IRC.lastAlertCommand = last alert |
282 |
> |
Alerter.IRC.joinCommand = join |
283 |
> |
Alerter.IRC.nickChangeCommand = nick |
284 |
> |
Alerter.IRC.statCommand = statistics |
285 |
> |
Alerter.IRC.uptimeCommand = uptime |
286 |
> |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
287 |
> |
Alerter.IRC.versionCommand = version |
288 |
> |
Alerter.IRC.helpCommand = help |
289 |
> |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
290 |
> |
|
291 |
> |
############################################################ |
292 |
> |
#### WebFeeder Configuration |
293 |
> |
############################################################ |
294 |
> |
|
295 |
> |
# Define these (one or both_ to turn on the WebFeeder's, |
296 |
> |
# comment it to turn them off |
297 |
> |
WebFeeder.latestActive = true |
298 |
> |
WebFeeder.alertActive = true |
299 |
> |
|
300 |
> |
# Check period in seconds (for cleaning stale/old alerts) |
301 |
> |
WebFeeder.checkPeriod = 900 |
302 |
> |
|
303 |
> |
# Delete alerts older than this, in seconds. |
304 |
> |
# Files are only check every WebFeeder.checkPeriod seconds. |
305 |
> |
WebFeeder.alertDeleteOlderThan = 1800 |
306 |
> |
|
307 |
> |
# Root Path |
308 |
> |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
309 |
> |
|
310 |
> |
# Latest Data |
311 |
> |
WebFeeder.latestSubDir = latest |
312 |
> |
WebFeeder.latestFileName = latest_data |
313 |
> |
|
314 |
> |
# Alert Data |
315 |
> |
WebFeeder.alertSubDir = alert |
316 |
> |
WebFeeder.alertFileName = alert_data |
317 |
> |
|
318 |
> |
############################################################ |
319 |
> |
|