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 |
> |
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 |
> |
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.*; |
29 |
+ |
config.library=library.conf |
30 |
+ |
|
31 |
+ |
# for SSB machines |
32 |
+ |
group.ssb=Host.stue*.ukc.ac.uk; |
33 |
+ |
config.ssb=ssb.conf |
34 |
+ |
|
35 |
+ |
# mySQL configuration |
36 |
+ |
config.mySQL=mySQL.conf |
37 |
+ |
|
38 |
+ |
############################################################ |
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 |
+ |
# The upper limit for a Queue |
49 |
+ |
Queue.SizeLimit=1000 |
50 |
+ |
# The removal algorithm |
51 |
+ |
Queue.RemoveAlgorithm=FIRST |
52 |
+ |
|
53 |
+ |
|
54 |
+ |
############################################################ |
55 |
+ |
#### FilterManager configuration |
56 |
+ |
############################################################ |
57 |
+ |
|
58 |
|
# The default port to listen for new host connections |
59 |
|
FilterManager.listenPort=4567 |
60 |
|
|
61 |
+ |
|
62 |
+ |
|
63 |
+ |
############################################################ |
64 |
+ |
#### Filter configuration |
65 |
+ |
############################################################ |
66 |
+ |
|
67 |
|
# The default port for Filter's to listen on |
68 |
|
Filter.UDPListenPort=4589 |
69 |
|
Filter.TCPListenPort=4589 |
70 |
|
|
71 |
+ |
# Plugin Information |
72 |
+ |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
73 |
+ |
Filter.Plugins=TypeChecker;EnforceEssentialData |
74 |
+ |
|
75 |
|
# The name for the root filter |
76 |
|
RootFilter.name=root |
77 |
+ |
|
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 |
|
# Comment either of these (or delete them) and |
88 |
|
# that interface won't be started |
89 |
|
RootFilter.realtimeInterfaceName=realtimeclients |
90 |
|
RootFilter.dbInterfaceName=database |
91 |
|
|
92 |
+ |
|
93 |
+ |
|
94 |
+ |
############################################################ |
95 |
+ |
#### Client interface configuration |
96 |
+ |
############################################################ |
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 |
|
|
30 |
– |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
31 |
– |
Filter.parentFilter=root |
103 |
|
|
33 |
– |
# The default filter for a new host |
34 |
– |
Host.filter=computingFilter |
104 |
|
|
105 |
< |
config.Host.killigrew.ukc.ac.uk=killigrew.conf |
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 |
+ |
|
118 |
+ |
# The default filter for a new host |
119 |
+ |
Host.filter=computingFilter; |
120 |
+ |
|
121 |
|
# The default update times for a new host |
122 |
|
Host.UDPUpdateTime=10 |
123 |
|
Host.TCPUpdateTime=60 |
124 |
+ |
Host.AveragerUpdateTime=5 |
125 |
|
|
42 |
– |
# Plugin Information |
43 |
– |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
44 |
– |
Filter.Plugins=TypeChecker;EnforceEssentialData |
45 |
– |
|
126 |
|
# The services checks to run on a host |
127 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
48 |
< |
Host.serviceChecks=HTTP;SMTP |
127 |
> |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
128 |
|
|
50 |
– |
# mySQL Details |
51 |
– |
config.mySQL=mySQL.conf |
129 |
|
|
53 |
– |
# The time interval at which the Queue's should be monitored |
54 |
– |
Queue.MonitorInterval=15 |
130 |
|
|
131 |
< |
group.rocks=Host.slate.ukc.ac.uk |
132 |
< |
config.rocks=rocks.conf |
131 |
> |
############################################################ |
132 |
> |
#### Monitor Configuration |
133 |
> |
############################################################ |
134 |
|
|
135 |
+ |
## The monitors to run |
136 |
+ |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
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 |
+ |
## 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 |
+ |
|
159 |
+ |
|
160 |
+ |
# Load monitor threshold values |
161 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
162 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
163 |
+ |
|
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 |
+ |
|
174 |
+ |
|
175 |
+ |
# Swap monitor threshold values |
176 |
+ |
Monitor.Swap.threshold.LOWER=80 |
177 |
+ |
Monitor.Swap.threshold.UPPER=90 |
178 |
+ |
|
179 |
+ |
|
180 |
+ |
# UserCount monitor threshold values |
181 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
182 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
183 |
+ |
|
184 |
+ |
|
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 |
+ |
# 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 |
+ |
# 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 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=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 |
+ |
|
226 |
+ |
|
227 |
+ |
|
228 |
+ |
############################################################ |
229 |
+ |
#### Alerter Configuration |
230 |
+ |
############################################################ |
231 |
+ |
# The following var's are understood by ALL alerters for messages |
232 |
+ |
# |
233 |
+ |
# %level% - the alert level (eg, WARNING) |
234 |
+ |
# %threshold% - the threshold broken (eg, LOWER) |
235 |
+ |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
236 |
+ |
# %value% - the value reached (eg, 95) |
237 |
+ |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
238 |
+ |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
239 |
+ |
# %timeTillNextAlert% - the time the next alert will be sent out |
240 |
+ |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
241 |
+ |
# %timeOfFirstAlert% - the time the first alert was sent |
242 |
+ |
# |
243 |
+ |
|
244 |
+ |
# alerters to run |
245 |
+ |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
246 |
+ |
Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
247 |
+ |
|
248 |
+ |
|
249 |
+ |
# EMail alerter configuration |
250 |
+ |
Alerter.EMail.level = WARNING |
251 |
+ |
Alerter.EMail.destList = dev@i-scream.org.uk |
252 |
+ |
Alerter.EMail.sender = dev@i-scream.org.uk |
253 |
+ |
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
254 |
+ |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
255 |
+ |
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%. |
256 |
+ |
|
257 |
+ |
|
258 |
+ |
# IRC alerter configuration |
259 |
+ |
Alerter.IRC.level = OK |
260 |
+ |
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
261 |
+ |
Alerter.IRC.IRCPort = 6667 |
262 |
+ |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
263 |
+ |
Alerter.IRC.user = i-scream |
264 |
+ |
Alerter.IRC.comment = i-scream alerting bot |
265 |
+ |
Alerter.IRC.channel = #i-scream |
266 |
+ |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
267 |
+ |
Alerter.IRC.reconnectDelay = 30 |
268 |
+ |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
269 |
+ |
Alerter.IRC.stopCommand = stop alerts |
270 |
+ |
Alerter.IRC.startCommand = start alerts |
271 |
+ |
Alerter.IRC.lastAlertCommand = last alert |
272 |
+ |
Alerter.IRC.joinCommand = join |
273 |
+ |
Alerter.IRC.nickChangeCommand = nick |
274 |
+ |
Alerter.IRC.statCommand = statistics |
275 |
+ |
Alerter.IRC.uptimeCommand = uptime |
276 |
+ |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
277 |
+ |
Alerter.IRC.versionCommand = version |
278 |
+ |
Alerter.IRC.helpCommand = help |
279 |
+ |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
280 |
+ |
|
281 |
+ |
|
282 |
+ |
# Logging alerter configuration |
283 |
+ |
Alerter.Logging.level = WARNING |
284 |
+ |
Alerter.EMail.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
285 |
+ |
|
286 |
+ |
|
287 |
+ |
|
288 |
+ |
############################################################ |
289 |
+ |
#### WebFeeder Configuration |
290 |
+ |
############################################################ |
291 |
+ |
|
292 |
+ |
# Define these (one or both_ to turn on the WebFeeder's, |
293 |
+ |
# comment it to turn them off |
294 |
+ |
WebFeeder.latestActive = true |
295 |
+ |
WebFeeder.alertActive = true |
296 |
+ |
|
297 |
+ |
# Only pass on alerts past this level |
298 |
+ |
Alerter.WebFeeder.level = OK |
299 |
+ |
|
300 |
+ |
# Check period in seconds (for cleaning stale/old alerts) |
301 |
+ |
WebFeeder.checkPeriod = 120 |
302 |
+ |
|
303 |
+ |
# Delete alerts older than this, in seconds. |
304 |
+ |
# Files are only check every WebFeeder.checkPeriod seconds. |
305 |
+ |
WebFeeder.alertDeleteOlderThan = 300 |
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 |
+ |
############################################################ |