14 |
|
|
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.*; |
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 |
|
|
42 |
– |
|
54 |
|
############################################################ |
55 |
|
#### FilterManager configuration |
56 |
|
############################################################ |
58 |
|
# The default port to listen for new host connections |
59 |
|
FilterManager.listenPort=4567 |
60 |
|
|
61 |
+ |
# Access control list |
62 |
+ |
FilterManager.ACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
63 |
|
|
64 |
|
|
65 |
+ |
|
66 |
|
############################################################ |
67 |
|
#### Filter configuration |
68 |
|
############################################################ |
72 |
|
Filter.TCPListenPort=4589 |
73 |
|
|
74 |
|
# Plugin Information |
75 |
< |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
75 |
> |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
76 |
|
Filter.Plugins=TypeChecker;EnforceEssentialData |
77 |
|
|
78 |
|
# The name for the root filter |
81 |
|
# The default parent filter (should almost always be the same as Filter.rootFilter) |
82 |
|
Filter.parentFilter=root |
83 |
|
|
84 |
+ |
# The input methods to activate |
85 |
+ |
# (comment or set to 0 to disable) |
86 |
+ |
Filter.ActivateTCPReader=1 |
87 |
+ |
Filter.ActivateUDPReader=1 |
88 |
+ |
Filter.ActivateCORBAReader=1 |
89 |
|
|
90 |
+ |
# Access control list for the TCP and UDP inputs |
91 |
+ |
Filter.TCPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
92 |
+ |
Filter.UDPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
93 |
|
|
94 |
+ |
|
95 |
+ |
|
96 |
|
############################################################ |
97 |
|
#### Root filter interfaces configuration |
98 |
|
############################################################ |
110 |
|
|
111 |
|
# The port for the client interface to listen on |
112 |
|
ClientInterface.listenPort=4510 |
113 |
+ |
# The name for the client interface |
114 |
+ |
ClientInterface.name=realtimeclients |
115 |
|
|
116 |
+ |
# Access Control List for TCP Clients |
117 |
+ |
ClientInterface.TCPControlChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
118 |
+ |
ClientInterface.TCPDataChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
119 |
|
|
120 |
|
|
121 |
+ |
|
122 |
|
############################################################ |
123 |
+ |
#### Database interface configuration |
124 |
+ |
############################################################ |
125 |
+ |
|
126 |
+ |
# The name for the Database interface |
127 |
+ |
DBInterface.name=database |
128 |
+ |
|
129 |
+ |
|
130 |
+ |
|
131 |
+ |
############################################################ |
132 |
|
#### Host Configuration |
133 |
|
############################################################ |
134 |
|
|
135 |
|
# The default filter for a new host |
136 |
< |
Host.filter=filter1 |
136 |
> |
Host.filter=computingFilter; |
137 |
|
|
138 |
|
# The default update times for a new host |
139 |
|
Host.UDPUpdateTime=10 |
140 |
|
Host.TCPUpdateTime=60 |
102 |
– |
Host.AveragerUpdateTime=5 |
141 |
|
|
142 |
|
# The services checks to run on a host |
143 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
106 |
< |
Host.serviceChecks=HTTP;SMTP |
143 |
> |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
144 |
|
|
145 |
|
|
146 |
|
|
148 |
|
#### Monitor Configuration |
149 |
|
############################################################ |
150 |
|
|
151 |
< |
# the monitors to run |
152 |
< |
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
153 |
< |
Monitor.Plugins=CPU; |
151 |
> |
## The monitors to run |
152 |
> |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
153 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
154 |
> |
Heartbeat;Queue;UserCount;WebFeeder; |
155 |
|
|
156 |
< |
# CPU monitor configuration |
157 |
< |
# threshold values |
156 |
> |
## Default alert timeouts |
157 |
> |
# these can be override on a per-monitor basis |
158 |
> |
# timings of the alerts (in seconds) |
159 |
> |
Monitor.alertTimeout.NOTICE=60 |
160 |
> |
Monitor.alertTimeout.WARNING=900 |
161 |
> |
Monitor.alertTimeout.CAUTION=1800 |
162 |
> |
Monitor.alertTimeout.CRITICAL=3600 |
163 |
> |
|
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 |
+ |
# |
170 |
+ |
|
171 |
+ |
# CPU monitor threshold values |
172 |
|
Monitor.CPU.threshold.LOWER=90 |
173 |
|
Monitor.CPU.threshold.UPPER=99 |
174 |
|
|
127 |
– |
# timings of the alerts (in seconds) |
128 |
– |
Monitor.CPU.alertTimeout.NOTICE=60 |
129 |
– |
Monitor.CPU.alertTimeout.WARNING=900 |
130 |
– |
Monitor.CPU.alertTimeout.CAUTION=1800 |
131 |
– |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
175 |
|
|
176 |
+ |
# Load monitor threshold values |
177 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
178 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
179 |
|
|
180 |
|
|
181 |
+ |
# Process Count threshold values |
182 |
+ |
Monitor.Process.threshold.LOWER=1000 |
183 |
+ |
Monitor.Process.threshold.UPPER=1500 |
184 |
+ |
|
185 |
+ |
|
186 |
+ |
# Memory monitor threshold values |
187 |
+ |
Monitor.Memory.threshold.LOWER=80 |
188 |
+ |
Monitor.Memory.threshold.UPPER=90 |
189 |
+ |
|
190 |
+ |
|
191 |
+ |
# Swap monitor threshold values |
192 |
+ |
Monitor.Swap.threshold.LOWER=80 |
193 |
+ |
Monitor.Swap.threshold.UPPER=90 |
194 |
+ |
|
195 |
+ |
|
196 |
+ |
# UserCount monitor threshold values |
197 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
198 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
199 |
+ |
|
200 |
+ |
|
201 |
+ |
# Disk monitor threshold values |
202 |
+ |
Monitor.Disk.threshold.LOWER=90 |
203 |
+ |
Monitor.Disk.threshold.UPPER=95 |
204 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
205 |
+ |
# where PERCENTAGE is a percentage of disk in use |
206 |
+ |
# and VALUE is an absolute value of space free |
207 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
208 |
+ |
|
209 |
+ |
|
210 |
+ |
# Queue monitor threshold values |
211 |
+ |
Monitor.Queue.threshold.LOWER=50 |
212 |
+ |
Monitor.Queue.threshold.UPPER=80 |
213 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
214 |
+ |
# where PERCENTAGE is a percentage of disk in use |
215 |
+ |
# and VALUE is an absolute value of space free |
216 |
+ |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
217 |
+ |
|
218 |
+ |
|
219 |
+ |
# Services monitor threshold values |
220 |
+ |
# |
221 |
+ |
# THE SERVICES MONITOR USES A HACK |
222 |
+ |
# WHEREBY IT USES THE SERVICE STATUS |
223 |
+ |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
224 |
+ |
# BE LOOKED AT! |
225 |
+ |
# |
226 |
+ |
# how many times we should be at the highest level before |
227 |
+ |
# we go to a FINAL alert |
228 |
+ |
Monitor.Services.reachFINALcount=5 |
229 |
+ |
|
230 |
+ |
|
231 |
+ |
# Heartbeat threshold values |
232 |
+ |
# these are values in seconds from when the heartbeat |
233 |
+ |
# was *expected* to arrive (ie. last + hearbeat period) |
234 |
+ |
Monitor.Heartbeat.threshold.LOWER=180 |
235 |
+ |
Monitor.Heartbeat.threshold.UPPER=300 |
236 |
+ |
# this is how often we will run a "check" of heartbeats |
237 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
238 |
+ |
# how many times we should be at the highest level before |
239 |
+ |
# we go to a FINAL alert |
240 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
241 |
+ |
# list of hosts we expect to have at startup |
242 |
+ |
# this ensures we notice hosts that aren't running, not |
243 |
+ |
# just those that have gone down recently. |
244 |
+ |
Monitor.Heartbeat.initialHosts=raptor.ukc.ac.uk;myrtle.ukc.ac.uk;kestrel.ukc.ac.uk |
245 |
+ |
|
246 |
+ |
|
247 |
+ |
|
248 |
|
############################################################ |
249 |
|
#### Alerter Configuration |
250 |
|
############################################################ |
251 |
+ |
# 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 |
|
|
264 |
|
# alerters to run |
265 |
< |
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
266 |
< |
Alerter.Plugins=EMail;IRC; |
265 |
> |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
266 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
267 |
|
|
268 |
+ |
|
269 |
|
# EMail alerter configuration |
270 |
< |
Alerter.EMail.level = CAUTION |
270 |
> |
Alerter.EMail.level = WARNING |
271 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
272 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
273 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
274 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
275 |
< |
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\nThe next alert (should one occur) will be sent in %timeTillNextAlert%. |
275 |
> |
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%. |
276 |
|
|
277 |
+ |
|
278 |
|
# IRC alerter configuration |
279 |
|
Alerter.IRC.level = OK |
280 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
154 |
– |
|
281 |
|
Alerter.IRC.IRCPort = 6667 |
282 |
< |
Alerter.IRC.nick = iscreamBot |
282 |
> |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
283 |
> |
Alerter.IRC.user = i-scream |
284 |
> |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
285 |
> |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
286 |
|
Alerter.IRC.channel = #i-scream |
287 |
|
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
288 |
+ |
Alerter.IRC.reconnectDelay = 30 |
289 |
+ |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
290 |
+ |
Alerter.IRC.stopCommand = stop alerts |
291 |
+ |
Alerter.IRC.startCommand = start alerts |
292 |
+ |
Alerter.IRC.lastAlertCommand = last alert |
293 |
+ |
Alerter.IRC.joinCommand = join |
294 |
+ |
Alerter.IRC.nickChangeCommand = nick |
295 |
+ |
Alerter.IRC.statCommand = statistics |
296 |
+ |
Alerter.IRC.uptimeCommand = uptime |
297 |
+ |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
298 |
+ |
Alerter.IRC.versionCommand = version |
299 |
+ |
Alerter.IRC.helpCommand = help |
300 |
+ |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
301 |
|
|
302 |
+ |
|
303 |
+ |
# Logging alerter configuration |
304 |
+ |
Alerter.Logging.level = WARNING |
305 |
+ |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
306 |
+ |
|
307 |
+ |
|
308 |
+ |
|
309 |
+ |
############################################################ |
310 |
+ |
#### WebFeeder Configuration |
311 |
+ |
############################################################ |
312 |
+ |
|
313 |
+ |
# Define these (one or both_ to turn on the WebFeeder's, |
314 |
+ |
# comment it to turn them off |
315 |
+ |
WebFeeder.latestActive = true |
316 |
+ |
WebFeeder.alertActive = true |
317 |
+ |
|
318 |
+ |
# Only pass on alerts past this level |
319 |
+ |
Alerter.WebFeeder.level = OK |
320 |
+ |
|
321 |
+ |
# Check period in seconds (for cleaning stale/old alerts) |
322 |
+ |
WebFeeder.checkPeriod = 120 |
323 |
+ |
|
324 |
+ |
# Delete alerts older than this, in seconds. |
325 |
+ |
# Files are only check every WebFeeder.checkPeriod seconds. |
326 |
+ |
WebFeeder.alertDeleteOlderThan = 300 |
327 |
+ |
|
328 |
+ |
# Root Path |
329 |
+ |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
330 |
+ |
|
331 |
+ |
# Latest Data |
332 |
+ |
WebFeeder.latestSubDir = latest |
333 |
+ |
WebFeeder.latestFileName = latest_data |
334 |
+ |
|
335 |
+ |
# Alert Data |
336 |
+ |
WebFeeder.alertSubDir = alert |
337 |
+ |
WebFeeder.alertFileName = alert_data |
338 |
|
|
339 |
|
|
340 |
|
############################################################ |