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 |
+ |
# the time (in seconds) at which the XMLCache's contents |
54 |
+ |
# will be rotated. in real terms, this means the minimum |
55 |
+ |
# age at which an XMLPacket can be before it is deleted |
56 |
+ |
# from the cache. |
57 |
+ |
XMLCache.cleanupPeriod=30 |
58 |
|
|
42 |
– |
|
59 |
|
############################################################ |
60 |
|
#### FilterManager configuration |
61 |
|
############################################################ |
63 |
|
# The default port to listen for new host connections |
64 |
|
FilterManager.listenPort=4567 |
65 |
|
|
66 |
+ |
# Access control list |
67 |
+ |
FilterManager.ACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
68 |
|
|
69 |
|
|
70 |
+ |
|
71 |
|
############################################################ |
72 |
|
#### Filter configuration |
73 |
|
############################################################ |
77 |
|
Filter.TCPListenPort=4589 |
78 |
|
|
79 |
|
# Plugin Information |
80 |
< |
Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins |
81 |
< |
Filter.Plugins=TypeChecker;EnforceEssentialData |
80 |
> |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
81 |
> |
Filter.Plugins=TypeChecker;EnforceEssentialData;SourceChecker;KeyChecker |
82 |
|
|
83 |
|
# The name for the root filter |
84 |
|
RootFilter.name=root |
86 |
|
# The default parent filter (should almost always be the same as Filter.rootFilter) |
87 |
|
Filter.parentFilter=root |
88 |
|
|
89 |
+ |
# The input methods to activate |
90 |
+ |
# (comment or set to 0 to disable) |
91 |
+ |
Filter.ActivateTCPReader=1 |
92 |
+ |
Filter.ActivateUDPReader=1 |
93 |
+ |
Filter.ActivateCORBAReader=1 |
94 |
|
|
95 |
+ |
# Access control list for the TCP and UDP inputs |
96 |
+ |
Filter.TCPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
97 |
+ |
Filter.UDPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
98 |
|
|
99 |
+ |
# Access control list for the SourceChecker plugin |
100 |
+ |
# - packets not permitted by this ACL will be filtered |
101 |
+ |
Filter.SourceCheckerPluginACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
102 |
+ |
|
103 |
+ |
# Enforce host authentication? |
104 |
+ |
# (comment or set to 0 to disable) |
105 |
+ |
Filter.EnforceHostAuth=1 |
106 |
+ |
|
107 |
+ |
# Length of keys to use in authentication |
108 |
+ |
Filter.KeyLength=15 |
109 |
+ |
|
110 |
+ |
|
111 |
+ |
|
112 |
|
############################################################ |
113 |
|
#### Root filter interfaces configuration |
114 |
|
############################################################ |
126 |
|
|
127 |
|
# The port for the client interface to listen on |
128 |
|
ClientInterface.listenPort=4510 |
129 |
+ |
# The name for the client interface |
130 |
+ |
ClientInterface.name=realtimeclients |
131 |
|
|
132 |
+ |
# Access Control List for TCP Clients |
133 |
+ |
ClientInterface.TCPControlChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
134 |
+ |
ClientInterface.TCPDataChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
135 |
|
|
136 |
|
|
137 |
+ |
|
138 |
|
############################################################ |
139 |
+ |
#### Database interface configuration |
140 |
+ |
############################################################ |
141 |
+ |
|
142 |
+ |
# The name for the Database interface |
143 |
+ |
DBInterface.name=database |
144 |
+ |
|
145 |
+ |
|
146 |
+ |
|
147 |
+ |
############################################################ |
148 |
|
#### Host Configuration |
149 |
|
############################################################ |
150 |
|
|
151 |
|
# The default filter for a new host |
152 |
< |
Host.filter=filter1; |
152 |
> |
Host.filter=computingFilter; |
153 |
|
|
154 |
|
# The default update times for a new host |
155 |
|
Host.UDPUpdateTime=10 |
156 |
|
Host.TCPUpdateTime=60 |
102 |
– |
Host.AveragerUpdateTime=5 |
157 |
|
|
158 |
|
# The services checks to run on a host |
159 |
< |
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
106 |
< |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet |
159 |
> |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
160 |
|
|
161 |
|
|
162 |
|
|
164 |
|
#### Monitor Configuration |
165 |
|
############################################################ |
166 |
|
|
167 |
< |
# the monitors to run |
168 |
< |
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
169 |
< |
Monitor.Plugins=CPU;Memory;Swap;Heartbeat;WebFeeder; |
167 |
> |
## The monitors to run |
168 |
> |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
169 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
170 |
> |
Heartbeat;Queue;UserCount;WebFeeder; |
171 |
|
|
172 |
+ |
## Default alert timeouts |
173 |
+ |
# these can be override on a per-monitor basis |
174 |
+ |
# timings of the alerts (in seconds) |
175 |
+ |
Monitor.alertTimeout.NOTICE=60 |
176 |
+ |
Monitor.alertTimeout.WARNING=900 |
177 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
178 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
179 |
|
|
180 |
< |
## CPU monitor configuration |
120 |
< |
# threshold values |
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 |
+ |
# |
186 |
+ |
|
187 |
+ |
# CPU monitor threshold values |
188 |
|
Monitor.CPU.threshold.LOWER=90 |
189 |
|
Monitor.CPU.threshold.UPPER=99 |
190 |
|
|
128 |
– |
# timings of the alerts (in seconds) |
129 |
– |
Monitor.CPU.alertTimeout.NOTICE=60 |
130 |
– |
Monitor.CPU.alertTimeout.WARNING=900 |
131 |
– |
Monitor.CPU.alertTimeout.CAUTION=1800 |
132 |
– |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
191 |
|
|
192 |
+ |
# Load monitor threshold values |
193 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
194 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
195 |
|
|
196 |
< |
## Memory monitor configuration |
197 |
< |
# threshold values |
198 |
< |
# |
199 |
< |
# note: if the UPPER threshold is broken, |
200 |
< |
# the alertTimeout values are halved. |
201 |
< |
# This is to escalate the alert quicker. |
196 |
> |
|
197 |
> |
# Process Count threshold values |
198 |
> |
Monitor.Process.threshold.LOWER=1000 |
199 |
> |
Monitor.Process.threshold.UPPER=1500 |
200 |
> |
|
201 |
> |
|
202 |
> |
# Memory monitor threshold values |
203 |
|
Monitor.Memory.threshold.LOWER=80 |
204 |
|
Monitor.Memory.threshold.UPPER=90 |
205 |
+ |
# Whether to include 'cache' in the 'free' value |
206 |
+ |
# (1 is true, anything else is false) |
207 |
+ |
Monitor.Memory.useCacheAsFree=1 |
208 |
|
|
144 |
– |
# timings of the alerts (in seconds) |
145 |
– |
Monitor.Memory.alertTimeout.NOTICE=60 |
146 |
– |
Monitor.Memory.alertTimeout.WARNING=900 |
147 |
– |
Monitor.Memory.alertTimeout.CAUTION=1800 |
148 |
– |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
209 |
|
|
210 |
< |
|
151 |
< |
## Swap monitor configuration |
152 |
< |
# threshold values |
153 |
< |
# |
154 |
< |
# note: if the UPPER threshold is broken, |
155 |
< |
# the alertTimeout values are halved. |
156 |
< |
# This is to escalate the alert quicker. |
210 |
> |
# Swap monitor threshold values |
211 |
|
Monitor.Swap.threshold.LOWER=80 |
212 |
|
Monitor.Swap.threshold.UPPER=90 |
213 |
|
|
160 |
– |
# timings of the alerts (in seconds) |
161 |
– |
Monitor.Swap.alertTimeout.NOTICE=60 |
162 |
– |
Monitor.Swap.alertTimeout.WARNING=900 |
163 |
– |
Monitor.Swap.alertTimeout.CAUTION=1800 |
164 |
– |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
214 |
|
|
215 |
+ |
# UserCount monitor threshold values |
216 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
217 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
218 |
|
|
219 |
< |
## Heartbeat monitor configuration |
220 |
< |
# threshold values |
219 |
> |
|
220 |
> |
# Disk monitor threshold values |
221 |
> |
Monitor.Disk.threshold.LOWER=90 |
222 |
> |
Monitor.Disk.threshold.UPPER=95 |
223 |
> |
# Thresholds given are PERCENTAGE or VALUE |
224 |
> |
# where PERCENTAGE is a percentage of disk in use |
225 |
> |
# and VALUE is an absolute value of space free |
226 |
> |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
227 |
> |
|
228 |
> |
|
229 |
> |
# Queue monitor threshold values |
230 |
> |
Monitor.Queue.threshold.LOWER=50 |
231 |
> |
Monitor.Queue.threshold.UPPER=80 |
232 |
> |
# Thresholds given are PERCENTAGE or VALUE |
233 |
> |
# where PERCENTAGE is a percentage of disk in use |
234 |
> |
# and VALUE is an absolute value of space free |
235 |
> |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
236 |
> |
|
237 |
> |
|
238 |
> |
# Services monitor threshold values |
239 |
|
# |
240 |
< |
# note: if the UPPER threshold is broken, |
241 |
< |
# the alertTimeout values are halved. |
242 |
< |
# This is to escalate the alert quicker. |
243 |
< |
Monitor.Heartbeat.checkPeriod=50 |
240 |
> |
# THE SERVICES MONITOR USES A HACK |
241 |
> |
# WHEREBY IT USES THE SERVICE STATUS |
242 |
> |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
243 |
> |
# BE LOOKED AT! |
244 |
> |
# |
245 |
> |
# how many times we should be at the highest level before |
246 |
> |
# we go to a FINAL alert |
247 |
> |
Monitor.Services.reachFINALcount=5 |
248 |
> |
|
249 |
> |
|
250 |
> |
# Heartbeat threshold values |
251 |
|
# these are values in seconds from when the heartbeat |
252 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
253 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
254 |
< |
Monitor.Heartbeat.threshold.LOWER=300 |
253 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
254 |
> |
Monitor.Heartbeat.threshold.UPPER=300 |
255 |
> |
# this is how often we will run a "check" of heartbeats |
256 |
> |
Monitor.Heartbeat.checkPeriod=50 |
257 |
> |
# how many times we should be at the highest level before |
258 |
> |
# we go to a FINAL alert |
259 |
> |
Monitor.Heartbeat.reachFINALcount=5 |
260 |
> |
# list of hosts we expect to have at startup |
261 |
> |
# this ensures we notice hosts that aren't running, not |
262 |
> |
# just those that have gone down recently. |
263 |
> |
Monitor.Heartbeat.initialHosts=raptor.ukc.ac.uk;myrtle.ukc.ac.uk;kestrel.ukc.ac.uk |
264 |
|
|
179 |
– |
# timings of the alerts (in seconds) |
180 |
– |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
181 |
– |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
182 |
– |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
183 |
– |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
265 |
|
|
185 |
– |
# this means it will reach a FINAL level, |
186 |
– |
# and thus the host will be removed from the monitor list, |
187 |
– |
# if the highest level alert is reached and occours this |
188 |
– |
# number of times. |
189 |
– |
# |
190 |
– |
# int this setup, that means 5 CRITICAL alerts would occour |
191 |
– |
# on a Heartbeat before reaching FINAL. |
192 |
– |
# If this value is wrong or not present, FINAL is never reached |
193 |
– |
# |
194 |
– |
Monitor.Heartbeat.reachFINALcount=5 |
266 |
|
|
267 |
|
############################################################ |
268 |
|
#### Alerter Configuration |
281 |
|
# |
282 |
|
|
283 |
|
# alerters to run |
284 |
< |
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
285 |
< |
Alerter.Plugins=EMail;IRC;WebFeeder; |
284 |
> |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
285 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
286 |
|
|
287 |
+ |
|
288 |
|
# EMail alerter configuration |
289 |
< |
Alerter.EMail.level = CAUTION |
290 |
< |
Alerter.EMail.defaultDestList = dev@i-scream.org.uk |
289 |
> |
Alerter.EMail.level = WARNING |
290 |
> |
Alerter.EMail.destList = dev@i-scream.org.uk |
291 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
292 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
293 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
294 |
< |
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%. |
294 |
> |
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%. |
295 |
|
|
296 |
+ |
|
297 |
|
# IRC alerter configuration |
298 |
|
Alerter.IRC.level = OK |
299 |
|
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
300 |
|
Alerter.IRC.IRCPort = 6667 |
301 |
|
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
302 |
|
Alerter.IRC.user = i-scream |
303 |
< |
Alerter.IRC.comment = i-scream alerting bot |
303 |
> |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
304 |
> |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
305 |
|
Alerter.IRC.channel = #i-scream |
306 |
|
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
307 |
|
Alerter.IRC.reconnectDelay = 30 |
318 |
|
Alerter.IRC.helpCommand = help |
319 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
320 |
|
|
321 |
+ |
|
322 |
+ |
# Logging alerter configuration |
323 |
+ |
Alerter.Logging.level = WARNING |
324 |
+ |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
325 |
+ |
|
326 |
+ |
|
327 |
+ |
|
328 |
|
############################################################ |
329 |
|
#### WebFeeder Configuration |
330 |
|
############################################################ |
331 |
|
|
332 |
+ |
# Define these (one or both_ to turn on the WebFeeder's, |
333 |
+ |
# comment it to turn them off |
334 |
+ |
WebFeeder.latestActive = true |
335 |
+ |
WebFeeder.alertActive = true |
336 |
+ |
|
337 |
+ |
# Only pass on alerts past this level |
338 |
+ |
Alerter.WebFeeder.level = OK |
339 |
+ |
|
340 |
+ |
# Check period in seconds (for cleaning stale/old alerts) |
341 |
+ |
WebFeeder.checkPeriod = 120 |
342 |
+ |
|
343 |
+ |
# Delete alerts older than this, in seconds. |
344 |
+ |
# Files are only check every WebFeeder.checkPeriod seconds. |
345 |
+ |
WebFeeder.alertDeleteOlderThan = 300 |
346 |
+ |
|
347 |
|
# Root Path |
348 |
|
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
349 |
|
|
351 |
|
WebFeeder.latestSubDir = latest |
352 |
|
WebFeeder.latestFileName = latest_data |
353 |
|
|
354 |
< |
############################################################ |
354 |
> |
# Alert Data |
355 |
> |
WebFeeder.alertSubDir = alert |
356 |
> |
WebFeeder.alertFileName = alert_data |
357 |
|
|
358 |
+ |
|
359 |
+ |
############################################################ |