1 |
# 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 |
# This is a working sample configuration, which |
9 |
# aims to provide a working "out of the box" |
10 |
# setup, aswell as a some example configuration. |
11 |
# |
12 |
# $Author: tdb $ |
13 |
# $Id: system.conf,v 1.78 2006/11/27 10:51:54 tdb Exp $ |
14 |
# |
15 |
# http://www.i-scream.org/ |
16 |
# |
17 |
|
18 |
############################################################ |
19 |
#### Configuration Files & Groups |
20 |
############################################################ |
21 |
|
22 |
# All components, such as hosts, will take their configuration |
23 |
# as given in this file. Unless, that is, they have an extra |
24 |
# configuration file specified here, or they're in a group |
25 |
# that has a configuration file. If this is the case the extra |
26 |
# configuration will override what is given in this file. |
27 |
|
28 |
# We can define an extra configuration file for any component |
29 |
# of the system. This is done by specifying the following: |
30 |
# |
31 |
# config.component=someconfigfile.conf |
32 |
# |
33 |
# Component names will be defined in the documentation for |
34 |
# the component. An example is that a host component is |
35 |
# known by the name "Host.hostname" or "Host.ip". |
36 |
# It is also possible to use the wildcard "*" in a |
37 |
# hostname or IP address. |
38 |
|
39 |
# This defines that server.example.com has some extra |
40 |
# configuration in the file 'server.conf'. |
41 |
config.Host.server.example.com=exserver.conf |
42 |
|
43 |
# All webservers are placed in a group named 'www'. |
44 |
group.www=Host.www1.example.com;Host.www2.example.com |
45 |
# Then we define some extra config for them. |
46 |
config.www=webservers.conf |
47 |
|
48 |
# Our workstations are in their own subnet. |
49 |
group.workstations=Host.192.168.10.*; |
50 |
# They can have their own config too. |
51 |
config.workstations=workstations.conf |
52 |
|
53 |
# Any hosts not specified by now have the default |
54 |
# config as given in this file. |
55 |
|
56 |
|
57 |
############################################################ |
58 |
#### Misc system-wide configuration |
59 |
############################################################ |
60 |
|
61 |
# The ConfigurationProxy caches configuration for various |
62 |
# parts of the server. This setting defines how often, in |
63 |
# seconds, the proxy will check if the data it contains |
64 |
# is still valid. |
65 |
ConfigurationProxy.updateTime=60 |
66 |
|
67 |
# The internal Queue's can be monitored. This specifies |
68 |
# the interval, in seconds, at which their state should |
69 |
# be monitored. |
70 |
Queue.MonitorInterval=300 |
71 |
# The maximum size a Queue can be before items are |
72 |
# dropped when new ones arrive. |
73 |
Queue.SizeLimit=1000 |
74 |
# And which items we should drop when the queue is full |
75 |
# and new items arrive. Choices are: |
76 |
# RANDOM - drop a random item from the queue |
77 |
# FIRST - drop the first item from the queue |
78 |
# LAST - drop the last item from the queue |
79 |
# DROP - drop the new item from the queue |
80 |
Queue.RemoveAlgorithm=FIRST |
81 |
|
82 |
# The XMLCache caches data passing through the system. |
83 |
# This setting specifies the time, in seconds, at which |
84 |
# the caches contents will be rotated. In real terms |
85 |
# this means the minimum age at which an XMLPacket can |
86 |
# be before it is up for deletion from the cache. |
87 |
XMLCache.cleanupPeriod=30 |
88 |
|
89 |
|
90 |
############################################################ |
91 |
#### FilterManager configuration |
92 |
############################################################ |
93 |
|
94 |
# The FilterManager accepts connections from hosts |
95 |
# upon startup. It provides them with configuration |
96 |
# and details of which filter to talk to. This setting |
97 |
# specifies which port (TCP) it listens on. |
98 |
FilterManager.listenPort=4567 |
99 |
|
100 |
# An Access Control List for the FilterManager. One |
101 |
# might consider something like this: |
102 |
# |
103 |
# FilterManager.ACL=DEFAULT:DENY;*.example.com:ALLOW |
104 |
FilterManager.ACL=DEFAULT:ALLOW |
105 |
|
106 |
|
107 |
############################################################ |
108 |
#### Filter configuration |
109 |
############################################################ |
110 |
|
111 |
# A Filter accepts data from hosts on a UDP port. It is |
112 |
# specified here. |
113 |
Filter.UDPListenPort=4589 |
114 |
|
115 |
# Filters contain plugins for checking the data passing |
116 |
# through them. This plugins do the job of "filtering". |
117 |
# This setting specifies the java package they're |
118 |
# contained in. |
119 |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
120 |
# And the names of the plugins to be loaded. |
121 |
Filter.Plugins=TypeChecker;EnforceEssentialData;SourceChecker |
122 |
|
123 |
# Every Filter, except the root, needs a parent to |
124 |
# send their data to. This is usually the root filter, |
125 |
# although in more complex setups it might be another |
126 |
# filter - giving a tree structure. |
127 |
Filter.parentFilter=root |
128 |
|
129 |
# A Filter can accept data through UDP, or from |
130 |
# an upstream Filter (CORBA). These methods can be |
131 |
# individually turned of on a filter. The default |
132 |
# is to have them all on. |
133 |
# (comment or set to 0 to disable) |
134 |
Filter.ActivateUDPReader=1 |
135 |
Filter.ActivateCORBAReader=1 |
136 |
|
137 |
# We can also specify Access Control Lists for the |
138 |
# UDP input of the Filters. One might want something |
139 |
# restrictive like this: |
140 |
# |
141 |
# Filter.UDPACL=DEFAULT:DENY;*.example.com:ALLOW |
142 |
Filter.UDPACL=DEFAULT:ALLOW |
143 |
|
144 |
# A Filter plugin called the SourceChecker verifies |
145 |
# that packets come from permitted hosts. It is |
146 |
# given an ACL to check the hosts against. A possible |
147 |
# ACL might be: |
148 |
# |
149 |
# Filter.SourceCheckerPluginACL=DEFAULT:DENY;*.example.com:ALLOW |
150 |
Filter.SourceCheckerPluginACL=DEFAULT:ALLOW |
151 |
|
152 |
|
153 |
############################################################ |
154 |
#### Root filter configuration |
155 |
############################################################ |
156 |
|
157 |
# The special filter known as the "Root Filter" needs |
158 |
# a name within the system. |
159 |
RootFilter.name=root |
160 |
|
161 |
|
162 |
############################################################ |
163 |
#### Client interface configuration |
164 |
############################################################ |
165 |
|
166 |
# The client interface listens for connections from clients |
167 |
# on a TCP port. It is specified here. |
168 |
ClientInterface.listenPort=4510 |
169 |
|
170 |
# The client interface needs to connect to another one to |
171 |
# receive data. There is a special client interface in the |
172 |
# root filter which is the top of the tree. |
173 |
ClientInterface.parent=root |
174 |
|
175 |
# The Client Interface has two channels, control and data. |
176 |
# Each of these can have an ACL for allowing connections. |
177 |
# As per previous examples in this configuration file they |
178 |
# could be set restrictively, but we'll leave them open |
179 |
# by default |
180 |
ClientInterface.TCPControlChannelACL=DEFAULT:ALLOW |
181 |
ClientInterface.TCPDataChannelACL=DEFAULT:ALLOW |
182 |
|
183 |
|
184 |
############################################################ |
185 |
#### LocalClient Configuration |
186 |
############################################################ |
187 |
|
188 |
# The parent for the Local Client |
189 |
Client.parent=clientinterface1 |
190 |
|
191 |
|
192 |
############################################################ |
193 |
#### Host Configuration |
194 |
############################################################ |
195 |
|
196 |
# A host can use any filter. We'll set the default filter |
197 |
# for all hosts to be 'filter1'. This can be a list. |
198 |
Host.filter=filter1; |
199 |
|
200 |
# Hosts send data every UDPUpdateTime, in seconds. |
201 |
Host.UDPUpdateTime=60 |
202 |
|
203 |
# How long a hosts config is valid for (a TTL effectively) |
204 |
# after this time, in seconds, has passed a host should |
205 |
# consider it's configuration invalid and check for a new |
206 |
# configuration as soon as it can. |
207 |
Host.ConfigTTL=3600 |
208 |
|
209 |
# We can run service checks on a host. The java package |
210 |
# which contains them is specified here. |
211 |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
212 |
|
213 |
|
214 |
############################################################ |
215 |
#### Monitor Configuration |
216 |
############################################################ |
217 |
|
218 |
# Monitors allow data to be watched for possible problems. |
219 |
# This setting specifies which java package they're in. |
220 |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
221 |
# And which ones should be loaded. |
222 |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
223 |
Heartbeat;Queue;UserCount;WebFeeder;DiskIO;\ |
224 |
NetIO;Paging;MailQ; |
225 |
|
226 |
# Alerts timeout after a given time in seconds and go up |
227 |
# to the next level. These can be overridden for monitors |
228 |
# on an individual basis. |
229 |
Monitor.alertTimeout.NOTICE=60 |
230 |
Monitor.alertTimeout.WARNING=900 |
231 |
Monitor.alertTimeout.CAUTION=1800 |
232 |
Monitor.alertTimeout.CRITICAL=3600 |
233 |
|
234 |
# Is monitoring enabled? (comment or set to 0 to disable) |
235 |
Monitor.enable=1 |
236 |
|
237 |
## Threshold values |
238 |
# |
239 |
# Here we specify the threshold for each monitor. When |
240 |
# a threshold is broken an alert is raised. If the |
241 |
# UPPER threshold is broken the alertTimeout values |
242 |
# given above are halved to make the alert escalate |
243 |
# quicker. |
244 |
|
245 |
# CPU monitor threshold values |
246 |
Monitor.CPU.threshold.LOWER=90 |
247 |
Monitor.CPU.threshold.UPPER=95 |
248 |
# enable this monitor (comment or set to 0 to disable) |
249 |
Monitor.CPU.enable=1 |
250 |
|
251 |
# Load monitor threshold values |
252 |
Monitor.Load.threshold.LOWER=10.0 |
253 |
Monitor.Load.threshold.UPPER=20.0 |
254 |
# enable this monitor (comment or set to 0 to disable) |
255 |
Monitor.Load.enable=1 |
256 |
|
257 |
# Paging monitor threshold values |
258 |
Monitor.Paging.threshold.LOWER=1000 |
259 |
Monitor.Paging.threshold.UPPER=5000 |
260 |
# enable this monitor (comment or set to 0 to disable) |
261 |
Monitor.Paging.enable=1 |
262 |
|
263 |
# Process Count threshold values |
264 |
Monitor.Process.threshold.LOWER=500 |
265 |
Monitor.Process.threshold.UPPER=1000 |
266 |
# enable this monitor (comment or set to 0 to disable) |
267 |
Monitor.Process.enable=1 |
268 |
|
269 |
# Memory monitor threshold values |
270 |
Monitor.Memory.threshold.LOWER=80 |
271 |
Monitor.Memory.threshold.UPPER=90 |
272 |
# Whether to include 'cache' in the 'free' value |
273 |
# (1 is true, anything else is false) |
274 |
Monitor.Memory.useCacheAsFree=1 |
275 |
# enable this monitor (comment or set to 0 to disable) |
276 |
Monitor.Memory.enable=1 |
277 |
|
278 |
# Swap monitor threshold values |
279 |
Monitor.Swap.threshold.LOWER=80 |
280 |
Monitor.Swap.threshold.UPPER=90 |
281 |
# enable this monitor (comment or set to 0 to disable) |
282 |
Monitor.Swap.enable=1 |
283 |
|
284 |
# UserCount monitor threshold values |
285 |
Monitor.UserCount.threshold.LOWER=100 |
286 |
Monitor.UserCount.threshold.UPPER=200 |
287 |
# enable this monitor (comment or set to 0 to disable) |
288 |
Monitor.UserCount.enable=1 |
289 |
|
290 |
# Disk monitor threshold values |
291 |
Monitor.Disk.threshold.LOWER=90 |
292 |
Monitor.Disk.threshold.UPPER=95 |
293 |
Monitor.DiskInode.threshold.LOWER=90 |
294 |
Monitor.DiskInode.threshold.UPPER=95 |
295 |
# Thresholds given are PERCENTAGE or VALUE |
296 |
# where PERCENTAGE is a percentage of disk in use |
297 |
# and VALUE is an absolute value of space free |
298 |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
299 |
Monitor.DiskInode.thresholdMeasure=PERCENTAGE |
300 |
# enable this monitor (comment or set to 0 to disable) |
301 |
Monitor.Disk.enable=1 |
302 |
Monitor.DiskInode.enable=1 |
303 |
|
304 |
# DiskIO monitor threshold values (in bytes) |
305 |
Monitor.DiskIO.rbytes.threshold.LOWER=10000000 |
306 |
Monitor.DiskIO.rbytes.threshold.UPPER=50000000 |
307 |
Monitor.DiskIO.wbytes.threshold.LOWER=10000000 |
308 |
Monitor.DiskIO.wbytes.threshold.UPPER=50000000 |
309 |
# enable this monitor (comment or set to 0 to disable) |
310 |
Monitor.DiskIO.enable=1 |
311 |
|
312 |
# NetIO monitor threshold values (in bytes) |
313 |
Monitor.NetIO.rxbytes.threshold.LOWER=10000000 |
314 |
Monitor.NetIO.rxbytes.threshold.UPPER=50000000 |
315 |
Monitor.NetIO.txbytes.threshold.LOWER=10000000 |
316 |
Monitor.NetIO.txbytes.threshold.UPPER=50000000 |
317 |
# enable this monitor (comment or set to 0 to disable) |
318 |
Monitor.NetIO.enable=1 |
319 |
|
320 |
# Queue monitor threshold values |
321 |
Monitor.Queue.threshold.LOWER=50 |
322 |
Monitor.Queue.threshold.UPPER=80 |
323 |
# Thresholds given are PERCENTAGE or VALUE |
324 |
# where PERCENTAGE is a percentage of the queue in use |
325 |
# and VALUE is an absolute value of free space |
326 |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
327 |
# enable this monitor (comment or set to 0 to disable) |
328 |
Monitor.Queue.enable=1 |
329 |
|
330 |
# Services monitor threshold values |
331 |
# |
332 |
# THE SERVICES MONITOR USES A HACK |
333 |
# WHEREBY IT USES THE SERVICE STATUS |
334 |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
335 |
# BE LOOKED AT! |
336 |
# |
337 |
# how many times we should be at the highest level before |
338 |
# we go to a FINAL alert |
339 |
Monitor.Services.reachFINALcount=5 |
340 |
|
341 |
# Heartbeat threshold values |
342 |
# these are values in seconds from when the heartbeat |
343 |
# was *expected* to arrive (ie. last + hearbeat period) |
344 |
Monitor.Heartbeat.threshold.LOWER=180 |
345 |
Monitor.Heartbeat.threshold.UPPER=300 |
346 |
# this is how often we will run a "check" of heartbeats |
347 |
Monitor.Heartbeat.checkPeriod=50 |
348 |
# how many times we should be at the highest level before |
349 |
# we go to a FINAL alert |
350 |
Monitor.Heartbeat.reachFINALcount=5 |
351 |
# list of hosts we expect to have at startup |
352 |
# this ensures we notice hosts that aren't running, not |
353 |
# just those that have gone down recently. |
354 |
#Monitor.Heartbeat.initialHosts=importantserver.example.com;myserver.example.com |
355 |
# enable this monitor (comment or set to 0 to disable) |
356 |
Monitor.Heartbeat.enable=1 |
357 |
|
358 |
# MailQ monitor threshold values |
359 |
Monitor.MailQ.size.threshold.LOWER=100 |
360 |
Monitor.MailQ.size.threshold.UPPER=1000 |
361 |
# enable this monitor (comment or set to 0 to disable) |
362 |
Monitor.MailQ.enable=1 |
363 |
|
364 |
|
365 |
############################################################ |
366 |
#### Alerter Configuration |
367 |
############################################################ |
368 |
# The following variables are understood by ALL alerters |
369 |
# for messages. They will be substituted for their |
370 |
# appropriate value. |
371 |
# |
372 |
# %level% - the alert level (eg, WARNING) |
373 |
# %threshold% - the threshold broken (eg, LOWER) |
374 |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
375 |
# %value% - the value reached (eg, 95) |
376 |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
377 |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
378 |
# %timeTillNextAlert% - the time the next alert will be sent out |
379 |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
380 |
# %timeOfFirstAlert% - the time the first alert was sent |
381 |
# |
382 |
|
383 |
# The java package containing the alerters |
384 |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
385 |
# And the names of the ones to activate |
386 |
# You might want to turn them all on, but we only activate |
387 |
# two basic ones by default. |
388 |
# Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
389 |
Alerter.Plugins=WebFeeder;Logging; |
390 |
|
391 |
# Configuration for the EMail alerter |
392 |
# The level alerts have to bypass to be e-mailed out |
393 |
Alerter.EMail.level = WARNING |
394 |
# A list of people to send alerts to |
395 |
Alerter.EMail.destList = me@example.com |
396 |
# The sender of the e-mail |
397 |
Alerter.EMail.sender = me@example.com |
398 |
# The SMTP server to send alerts to |
399 |
Alerter.EMail.smtpServer = smtp.example.com |
400 |
# The subject line of the e-mail |
401 |
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
402 |
# The message in the e-mail |
403 |
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%. |
404 |
|
405 |
# Configuration for the IRC alerter |
406 |
# The level alerts have to bypass to be sent |
407 |
Alerter.IRC.level = OK |
408 |
# The IRC server name |
409 |
Alerter.IRC.IRCServer = irc.example.com |
410 |
# and it's port |
411 |
Alerter.IRC.IRCPort = 6667 |
412 |
# A list of nicks to try and be |
413 |
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
414 |
# Username to be |
415 |
Alerter.IRC.user = i-scream |
416 |
# Responses to CTCP prods |
417 |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
418 |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
419 |
# Channel to join |
420 |
Alerter.IRC.channel = #i-scream |
421 |
# Message to use when sending an alert |
422 |
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
423 |
# How long to wait before reconnecting |
424 |
Alerter.IRC.reconnectDelay = 30 |
425 |
# Notice to send when starting up |
426 |
Alerter.IRC.startupNotice = i-scream alerting bot activated |
427 |
# Commands the bot will recognise |
428 |
Alerter.IRC.stopCommand = stop alerts |
429 |
Alerter.IRC.startCommand = start alerts |
430 |
Alerter.IRC.lastAlertCommand = last alert |
431 |
Alerter.IRC.joinCommand = join |
432 |
Alerter.IRC.nickChangeCommand = nick |
433 |
Alerter.IRC.statCommand = statistics |
434 |
Alerter.IRC.uptimeCommand = uptime |
435 |
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
436 |
Alerter.IRC.versionCommand = version |
437 |
Alerter.IRC.helpCommand = help |
438 |
# Message to send when the bot is addressed and |
439 |
# doesn't understand the command |
440 |
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
441 |
|
442 |
# Configuration for the Logging Alerter |
443 |
# This alerter writes alerts to the i-scream logfile. |
444 |
# The level alerts have to bypass to be logged |
445 |
Alerter.Logging.level = WARNING |
446 |
# The message to use when logging the alert |
447 |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
448 |
|
449 |
|
450 |
############################################################ |
451 |
#### WebFeeder Configuration |
452 |
############################################################ |
453 |
|
454 |
# The WebFeeder drops alerts and latest data in to a |
455 |
# directory for the web interface to use. It is essentially |
456 |
# the link between the web interface and the server. |
457 |
|
458 |
# Set these to something to tell the WebFeeder to drop |
459 |
# latest data, alerts, or both. Comment themt o disable. |
460 |
WebFeeder.latestActive = true |
461 |
WebFeeder.alertActive = true |
462 |
|
463 |
# We can make the WebFeeder only drop alerts that go |
464 |
# past a certain level. The default is "OK", which makes |
465 |
# all alerts get passed on. |
466 |
Alerter.WebFeeder.level = OK |
467 |
|
468 |
# The WebFeeder cleans out old and stale alerts when it |
469 |
# performs a check. This setting is the period, in seconds, |
470 |
# at which a check happens. |
471 |
WebFeeder.checkPeriod = 120 |
472 |
|
473 |
# Delete alerts older than this, in seconds. |
474 |
WebFeeder.alertDeleteOlderThan = 300 |
475 |
|
476 |
# Data will be dropped to a subdirectory (specified |
477 |
# below) of this directory. |
478 |
WebFeeder.rootPath = /web/i-scream |
479 |
|
480 |
# SubDir is the directory below rootPath which latest |
481 |
# data will be placed in. Below that a directory will |
482 |
# be created with the machine name, and a file named |
483 |
# FileName (specified here) will be created containg |
484 |
# the data. |
485 |
WebFeeder.latestSubDir = latest |
486 |
WebFeeder.latestFileName = latest_data |
487 |
|
488 |
# As above, but for the alerts. |
489 |
WebFeeder.alertSubDir = alert |
490 |
WebFeeder.alertFileName = alert_data |
491 |
|
492 |
|
493 |
############################################################ |