build/etc/system.conf

# This is the default system configuration file
# used by all components of the i-scream system
#
# ALL configuration that uses the centralised
# configuration system has this file as its 
# root of configuration
#
# $Author: tdb1 $
# $Id: system.conf,v 1.38 2001/03/16 05:28:00 tdb1 Exp $
#
############################################################
#### Configuration Files & Groups
############################################################

# for computing machines
group.computing=Host.129.12.4.*;
config.computing=computing.conf

# for library machines
group.library=Host.129.12.58.*;
config.library=library.conf

# for SSB machines
group.ssb=Host.stue*.ukc.ac.uk;
config.ssb=ssb.conf

# mySQL configuration
config.mySQL=mySQL.conf

############################################################
#### Misc system-wide configuration
############################################################

# the time (in seconds) that checks should be made for
# changes in configuration
ConfigurationProxy.updateTime=60

# The time interval at which the Queue's should be monitored
Queue.MonitorInterval=15


############################################################
#### FilterManager configuration
############################################################

# The default port to listen for new host connections
FilterManager.listenPort=4567


############################################################
#### Filter configuration
############################################################

# The default port for Filter's to listen on
Filter.UDPListenPort=4589
Filter.TCPListenPort=4589

# Plugin Information
Filter.PluginsPackage=uk.org.iscream.filter.plugins
Filter.Plugins=TypeChecker;EnforceEssentialData

# The name for the root filter
RootFilter.name=root

# The default parent filter (should almost always be the same as Filter.rootFilter)
Filter.parentFilter=root


############################################################
#### Root filter interfaces configuration
############################################################

# Comment either of these (or delete them) and
# that interface won't be started
RootFilter.realtimeInterfaceName=realtimeclients
RootFilter.dbInterfaceName=database


############################################################
#### Client interface configuration
############################################################

# The port for the client interface to listen on
ClientInterface.listenPort=4510


############################################################
#### Host Configuration
############################################################

# The default filter for a new host
Host.filter=computingFilter;

# The default update times for a new host
Host.UDPUpdateTime=10
Host.TCPUpdateTime=60
Host.AveragerUpdateTime=5

# The services checks to run on a host
Host.serviceChecksPackage=uk.org.iscream.filter.plugins
Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet


############################################################
#### Monitor Configuration
############################################################

# the monitors to run
Monitor.PluginsPackage=uk.org.iscream.client.monitors
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder;


## CPU monitor configuration
# threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
Monitor.CPU.threshold.LOWER=90
Monitor.CPU.threshold.UPPER=99

# timings of the alerts (in seconds)
Monitor.CPU.alertTimeout.NOTICE=60
Monitor.CPU.alertTimeout.WARNING=900
Monitor.CPU.alertTimeout.CAUTION=1800
Monitor.CPU.alertTimeout.CRITICAL=3600


## Memory monitor configuration
# threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
Monitor.Memory.threshold.LOWER=80
Monitor.Memory.threshold.UPPER=90

# timings of the alerts (in seconds)
Monitor.Memory.alertTimeout.NOTICE=60
Monitor.Memory.alertTimeout.WARNING=900
Monitor.Memory.alertTimeout.CAUTION=1800
Monitor.Memory.alertTimeout.CRITICAL=3600


## Swap monitor configuration
# threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
Monitor.Swap.threshold.LOWER=80
Monitor.Swap.threshold.UPPER=90

# timings of the alerts (in seconds)
Monitor.Swap.alertTimeout.NOTICE=60
Monitor.Swap.alertTimeout.WARNING=900
Monitor.Swap.alertTimeout.CAUTION=1800
Monitor.Swap.alertTimeout.CRITICAL=3600


## Disk monitor configuration
# threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
Monitor.Disk.threshold.LOWER=80
Monitor.Disk.threshold.UPPER=90

# timings of the alerts (in seconds)
Monitor.Disk.alertTimeout.NOTICE=60
Monitor.Disk.alertTimeout.WARNING=900
Monitor.Disk.alertTimeout.CAUTION=1800
Monitor.Disk.alertTimeout.CRITICAL=3600


## Services monitor configuration
# threshold values
# 
# THE SERVICES MONITOR USES A HACK
# WHEREBY IT USES THE SERVICE STATUS
# AS THE THRESHOLD LEVEL.  THIS SHOULD
# BE LOOKED AT!
#
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
#Monitor.Services.threshold.LOWER=120
#Monitor.Services.threshold.LOWER=300

# timings of the alerts (in seconds)
Monitor.Services.alertTimeout.NOTICE=60
Monitor.Services.alertTimeout.WARNING=900
Monitor.Services.alertTimeout.CAUTION=1800
Monitor.Services.alertTimeout.CRITICAL=3600

# Make sure we shut up eventually
Monitor.Services.reachFINALcount=5


## Heartbeat monitor configuration
# threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
Monitor.Heartbeat.checkPeriod=50
# these are values in seconds from when the heartbeat
# was *expected* to arrive (ie. last + hearbeat period)
Monitor.Heartbeat.threshold.LOWER=120
Monitor.Heartbeat.threshold.UPPER=300

# timings of the alerts (in seconds)
Monitor.Heartbeat.alertTimeout.NOTICE=60
Monitor.Heartbeat.alertTimeout.WARNING=900
Monitor.Heartbeat.alertTimeout.CAUTION=1800
Monitor.Heartbeat.alertTimeout.CRITICAL=3600

# this means it will reach a FINAL level,
# and thus the host will be removed from the monitor list,
# if the highest level alert is reached and occours this
# number of times.
#
# int this setup, that means 5 CRITICAL alerts would occour
# on a Heartbeat before reaching FINAL.
# If this value is wrong or not present, FINAL is never reached
#
Monitor.Heartbeat.reachFINALcount=5

############################################################
#### Alerter Configuration
############################################################
# The following var's are understood by ALL alerters for messages
#
# %level%               - the alert level (eg, WARNING)
# %threshold%           - the threshold broken (eg, LOWER)
# %source%              - the source of the alert (eg, raptor.ukc.ac.uk)
# %value%               - the value reached (eg, 95)
# %thresholdValue%      - the value of the threshold broken (eg, 90)
# %attributeName%       - the attribute that has caused the alert (eg, CPU User)
# %timeTillNextAlert%   - the time the next alert will be sent out
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem
# %timeOfFirstAlert%    - the time the first alert was sent
#

# alerters to run
Alerter.PluginsPackage=uk.org.iscream.client.alerters
Alerter.Plugins=EMail;IRC;WebFeeder;

# EMail alerter configuration
Alerter.EMail.level = WARNING
Alerter.EMail.destList = dev@i-scream.org.uk
Alerter.EMail.sender = dev@i-scream.org.uk
Alerter.EMail.smtpServer = mercury.ukc.ac.uk
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName%
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%.


# IRC alerter configuration
Alerter.IRC.level = OK
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk
Alerter.IRC.IRCPort = 6667
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot
Alerter.IRC.user = i-scream
Alerter.IRC.comment = i-scream alerting bot
Alerter.IRC.channel = #i-scream
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert%
Alerter.IRC.reconnectDelay = 30
Alerter.IRC.startupNotice = i-scream alerting bot activated 
Alerter.IRC.stopCommand = stop alerts
Alerter.IRC.startCommand = start alerts
Alerter.IRC.lastAlertCommand = last alert
Alerter.IRC.joinCommand = join
Alerter.IRC.nickChangeCommand = nick
Alerter.IRC.statCommand = statistics
Alerter.IRC.uptimeCommand = uptime
Alerter.IRC.timeSinceLastAlertCommand = time since last alert
Alerter.IRC.versionCommand = version
Alerter.IRC.helpCommand = help
Alerter.IRC.rejectMessage = sorry, I don't understand your request

############################################################
#### WebFeeder Configuration
############################################################

# Define these (one or both_ to turn on the WebFeeder's,
# comment it to turn them off
WebFeeder.latestActive = true
WebFeeder.alertActive = true

# Check period in seconds (for cleaning stale/old alerts)
WebFeeder.checkPeriod = 900

# Delete alerts older than this, in seconds.
# Files are only check every WebFeeder.checkPeriod seconds.
WebFeeder.alertDeleteOlderThan = 1800

# Root Path
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot

# Latest Data
WebFeeder.latestSubDir = latest
WebFeeder.latestFileName = latest_data

# Alert Data
WebFeeder.alertSubDir = alert
WebFeeder.alertFileName = alert_data

############################################################

Revision:	1.39
Committed:	Fri Mar 16 05:54:23 2001 UTC (23 years, 6 months ago) by tdb
Branch:	MAIN
Changes since 1.38:	+3 -3 lines
Log Message:	Halfed the OK/FINAL timeout periods. It's a bit hard to test with such long intervals to wait :)
#	Content
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	# $Author: tdb1 $
9	# $Id: system.conf,v 1.38 2001/03/16 05:28:00 tdb1 Exp $
10	#
11	############################################################
12	#### Configuration Files & Groups
13	############################################################
14
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
41
42
43	############################################################
44	#### FilterManager configuration
45	############################################################
46
47	# The default port to listen for new host connections
48	FilterManager.listenPort=4567
49
50
51
52	############################################################
53	#### Filter configuration
54	############################################################
55
56	# The default port for Filter's to listen on
57	Filter.UDPListenPort=4589
58	Filter.TCPListenPort=4589
59
60	# Plugin Information
61	Filter.PluginsPackage=uk.org.iscream.filter.plugins
62	Filter.Plugins=TypeChecker;EnforceEssentialData
63
64	# The name for the root filter
65	RootFilter.name=root
66
67	# The default parent filter (should almost always be the same as Filter.rootFilter)
68	Filter.parentFilter=root
69
70
71
72	############################################################
73	#### Root filter interfaces configuration
74	############################################################
75
76	# Comment either of these (or delete them) and
77	# that interface won't be started
78	RootFilter.realtimeInterfaceName=realtimeclients
79	RootFilter.dbInterfaceName=database
80
81
82
83	############################################################
84	#### Client interface configuration
85	############################################################
86
87	# The port for the client interface to listen on
88	ClientInterface.listenPort=4510
89
90
91
92	############################################################
93	#### Host Configuration
94	############################################################
95
96	# The default filter for a new host
97	Host.filter=computingFilter;
98
99	# The default update times for a new host
100	Host.UDPUpdateTime=10
101	Host.TCPUpdateTime=60
102	Host.AveragerUpdateTime=5
103
104	# The services checks to run on a host
105	Host.serviceChecksPackage=uk.org.iscream.filter.plugins
106	Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet
107
108
109
110	############################################################
111	#### Monitor Configuration
112	############################################################
113
114	# the monitors to run
115	Monitor.PluginsPackage=uk.org.iscream.client.monitors
116	Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder;
117
118
119	## CPU monitor configuration
120	# threshold values
121	#
122	# note: if the UPPER threshold is broken,
123	# the alertTimeout values are halved.
124	# This is to escalate the alert quicker.
125	Monitor.CPU.threshold.LOWER=90
126	Monitor.CPU.threshold.UPPER=99
127
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
133
134
135	## Memory monitor configuration
136	# threshold values
137	#
138	# note: if the UPPER threshold is broken,
139	# the alertTimeout values are halved.
140	# This is to escalate the alert quicker.
141	Monitor.Memory.threshold.LOWER=80
142	Monitor.Memory.threshold.UPPER=90
143
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
149
150
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.
157	Monitor.Swap.threshold.LOWER=80
158	Monitor.Swap.threshold.UPPER=90
159
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
165
166
167	## Disk monitor configuration
168	# threshold values
169	#
170	# note: if the UPPER threshold is broken,
171	# the alertTimeout values are halved.
172	# This is to escalate the alert quicker.
173	Monitor.Disk.threshold.LOWER=80
174	Monitor.Disk.threshold.UPPER=90
175
176	# timings of the alerts (in seconds)
177	Monitor.Disk.alertTimeout.NOTICE=60
178	Monitor.Disk.alertTimeout.WARNING=900
179	Monitor.Disk.alertTimeout.CAUTION=1800
180	Monitor.Disk.alertTimeout.CRITICAL=3600
181
182
183	## Services monitor configuration
184	# threshold values
185	#
186	# THE SERVICES MONITOR USES A HACK
187	# WHEREBY IT USES THE SERVICE STATUS
188	# AS THE THRESHOLD LEVEL. THIS SHOULD
189	# BE LOOKED AT!
190	#
191	# note: if the UPPER threshold is broken,
192	# the alertTimeout values are halved.
193	# This is to escalate the alert quicker.
194	#Monitor.Services.threshold.LOWER=120
195	#Monitor.Services.threshold.LOWER=300
196
197	# timings of the alerts (in seconds)
198	Monitor.Services.alertTimeout.NOTICE=60
199	Monitor.Services.alertTimeout.WARNING=900
200	Monitor.Services.alertTimeout.CAUTION=1800
201	Monitor.Services.alertTimeout.CRITICAL=3600
202
203	# Make sure we shut up eventually
204	Monitor.Services.reachFINALcount=5
205
206
207	## Heartbeat monitor configuration
208	# threshold values
209	#
210	# note: if the UPPER threshold is broken,
211	# the alertTimeout values are halved.
212	# This is to escalate the alert quicker.
213	Monitor.Heartbeat.checkPeriod=50
214	# these are values in seconds from when the heartbeat
215	# was expected to arrive (ie. last + hearbeat period)
216	Monitor.Heartbeat.threshold.LOWER=120
217	Monitor.Heartbeat.threshold.UPPER=300
218
219	# timings of the alerts (in seconds)
220	Monitor.Heartbeat.alertTimeout.NOTICE=60
221	Monitor.Heartbeat.alertTimeout.WARNING=900
222	Monitor.Heartbeat.alertTimeout.CAUTION=1800
223	Monitor.Heartbeat.alertTimeout.CRITICAL=3600
224
225	# this means it will reach a FINAL level,
226	# and thus the host will be removed from the monitor list,
227	# if the highest level alert is reached and occours this
228	# number of times.
229	#
230	# int this setup, that means 5 CRITICAL alerts would occour
231	# on a Heartbeat before reaching FINAL.
232	# If this value is wrong or not present, FINAL is never reached
233	#
234	Monitor.Heartbeat.reachFINALcount=5
235
236	############################################################
237	#### Alerter Configuration
238	############################################################
239	# The following var's are understood by ALL alerters for messages
240	#
241	# %level% - the alert level (eg, WARNING)
242	# %threshold% - the threshold broken (eg, LOWER)
243	# %source% - the source of the alert (eg, raptor.ukc.ac.uk)
244	# %value% - the value reached (eg, 95)
245	# %thresholdValue% - the value of the threshold broken (eg, 90)
246	# %attributeName% - the attribute that has caused the alert (eg, CPU User)
247	# %timeTillNextAlert% - the time the next alert will be sent out
248	# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem
249	# %timeOfFirstAlert% - the time the first alert was sent
250	#
251
252	# alerters to run
253	Alerter.PluginsPackage=uk.org.iscream.client.alerters
254	Alerter.Plugins=EMail;IRC;WebFeeder;
255
256	# EMail alerter configuration
257	Alerter.EMail.level = WARNING
258	Alerter.EMail.destList = dev@i-scream.org.uk
259	Alerter.EMail.sender = dev@i-scream.org.uk
260	Alerter.EMail.smtpServer = mercury.ukc.ac.uk
261	Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName%
262	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%.
263
264
265	# IRC alerter configuration
266	Alerter.IRC.level = OK
267	Alerter.IRC.IRCServer = killigrew.ukc.ac.uk
268	Alerter.IRC.IRCPort = 6667
269	Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot
270	Alerter.IRC.user = i-scream
271	Alerter.IRC.comment = i-scream alerting bot
272	Alerter.IRC.channel = #i-scream
273	Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert%
274	Alerter.IRC.reconnectDelay = 30
275	Alerter.IRC.startupNotice = i-scream alerting bot activated
276	Alerter.IRC.stopCommand = stop alerts
277	Alerter.IRC.startCommand = start alerts
278	Alerter.IRC.lastAlertCommand = last alert
279	Alerter.IRC.joinCommand = join
280	Alerter.IRC.nickChangeCommand = nick
281	Alerter.IRC.statCommand = statistics
282	Alerter.IRC.uptimeCommand = uptime
283	Alerter.IRC.timeSinceLastAlertCommand = time since last alert
284	Alerter.IRC.versionCommand = version
285	Alerter.IRC.helpCommand = help
286	Alerter.IRC.rejectMessage = sorry, I don't understand your request
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	# Check period in seconds (for cleaning stale/old alerts)
298	WebFeeder.checkPeriod = 900
299
300	# Delete alerts older than this, in seconds.
301	# Files are only check every WebFeeder.checkPeriod seconds.
302	WebFeeder.alertDeleteOlderThan = 1800
303
304	# Root Path
305	WebFeeder.rootPath = /usr/local/proj/co600_10/webroot
306
307	# Latest Data
308	WebFeeder.latestSubDir = latest
309	WebFeeder.latestFileName = latest_data
310
311	# Alert Data
312	WebFeeder.alertSubDir = alert
313	WebFeeder.alertFileName = alert_data
314
315	############################################################
316