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 1.53 2001/05/13 01:52:45 tdb1 Exp $
#
############################################################
#### Configuration Files & Groups
############################################################

# for computing machines
group.computing=Host.129.12.4.*;
group.rocks=Host.agate.ukc.ac.uk;Host.arkose.ukc.ac.uk;Host.basalt.ukc.ac.uk;Host.chalk.ukc.ac.uk;\
            Host.chert.ukc.ac.uk;Host.granite.ukc.ac.uk;Host.jade.ukc.ac.uk;Host.jasper.ukc.ac.uk;\
            Host.magnetite.ukc.ac.uk;Host.obsidian.ukc.ac.uk;Host.pumice.ukc.ac.uk;\
            Host.pyrite.ukc.ac.uk;Host.slate.ukc.ac.uk;Host.topaz.ukc.ac.uk;
group.compsoc=Host.compsoc1.ukc.ac.uk

config.computing=computing.conf
config.rocks=rocks.conf
config.compsoc1=rocks.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
# The upper limit for a Queue
Queue.SizeLimit=1000
# The removal algorithm
Queue.RemoveAlgorithm=FIRST


############################################################
#### 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
# The name for the client interface
ClientInterface.name=realtimeclients


############################################################
#### Database interface configuration
############################################################

# The name for the Database interface
DBInterface.name=database


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


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

## The monitors to run
Monitor.PluginsPackage=uk.org.iscream.client.monitors
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\
                Heartbeat;Queue;UserCount;WebFeeder;

## Default alert timeouts
# these can be override on a per-monitor basis
# timings of the alerts (in seconds)
Monitor.alertTimeout.NOTICE=60
Monitor.alertTimeout.WARNING=900
Monitor.alertTimeout.CAUTION=1800
Monitor.alertTimeout.CRITICAL=3600

## Threshold values
# 
# note: if the UPPER threshold is broken,
# the alertTimeout values are halved.
# This is to escalate the alert quicker.
#

# CPU monitor threshold values
Monitor.CPU.threshold.LOWER=90
Monitor.CPU.threshold.UPPER=99


# Load monitor threshold values
Monitor.Load.threshold.LOWER=10.0
Monitor.Load.threshold.UPPER=20.0


# Process Count threshold values
Monitor.Process.threshold.LOWER=1000
Monitor.Process.threshold.UPPER=1500


# Memory monitor threshold values
Monitor.Memory.threshold.LOWER=80
Monitor.Memory.threshold.UPPER=90


# Swap monitor threshold values
Monitor.Swap.threshold.LOWER=80
Monitor.Swap.threshold.UPPER=90


# UserCount monitor threshold values
Monitor.UserCount.threshold.LOWER=100
Monitor.UserCount.threshold.UPPER=200


# Disk monitor threshold values
Monitor.Disk.threshold.LOWER=90
Monitor.Disk.threshold.UPPER=95
# Thresholds given are PERCENTAGE or VALUE
# where PERCENTAGE is a percentage of disk in use
# and VALUE is an absolute value of space free
Monitor.Disk.thresholdMeasure=PERCENTAGE


# Disk monitor threshold values
Monitor.Queue.threshold.LOWER=50
Monitor.Queue.threshold.UPPER=80
# Thresholds given are PERCENTAGE or VALUE
# where PERCENTAGE is a percentage of disk in use
# and VALUE is an absolute value of space free
Monitor.Queue.thresholdMeasure=PERCENTAGE


# Services monitor threshold values
# 
# THE SERVICES MONITOR USES A HACK
# WHEREBY IT USES THE SERVICE STATUS
# AS THE THRESHOLD LEVEL.  THIS SHOULD
# BE LOOKED AT!
#
# how many times we should be at the highest level before
# we go to a FINAL alert
Monitor.Services.reachFINALcount=5


# Heartbeat threshold values
# these are values in seconds from when the heartbeat
# was *expected* to arrive (ie. last + hearbeat period)
Monitor.Heartbeat.threshold.LOWER=180
Monitor.Heartbeat.threshold.UPPER=300
# this is how often we will run a "check" of heartbeats
Monitor.Heartbeat.checkPeriod=50
# how many times we should be at the highest level before
# we go to a FINAL alert
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;Logging;


# 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


# Logging alerter configuration
Alerter.Logging.level = WARNING
Alerter.EMail.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value%


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

# Only pass on alerts past this level
Alerter.WebFeeder.level = OK

# Check period in seconds (for cleaning stale/old alerts)
WebFeeder.checkPeriod = 120

# Delete alerts older than this, in seconds.
# Files are only check every WebFeeder.checkPeriod seconds.
WebFeeder.alertDeleteOlderThan = 300

# 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:	1.54
Committed:	Thu May 24 14:11:32 2001 UTC (23 years, 6 months ago) by tdb
Branch:	MAIN
Changes since 1.53:	+7 -2 lines
Log Message:	A new alerter that writes alerts to the system logfile, thus keeping a permanent record should the need arise to see "what happened" at some point in the past. It currently logs at DEBUG level, although I propose a new level be introduced. This will be discussed.
#	User	Rev	Content
1	tdb	1.2	# 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	tdb	1.36	# $Author: tdb1 $
9	tdb	1.54	# $Id: system.conf,v 1.53 2001/05/13 01:52:45 tdb1 Exp $
10	ajm	1.14	#
11			############################################################
12			#### Configuration Files & Groups
13			############################################################
14
15			# for computing machines
16	tdb	1.15	group.computing=Host.129.12.4.*;
17	tdb	1.41	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	tdb	1.42	group.compsoc=Host.compsoc1.ukc.ac.uk
22	tdb	1.41
23	tdb	1.15	config.computing=computing.conf
24	tdb	1.41	config.rocks=rocks.conf
25	tdb	1.42	config.compsoc1=rocks.conf
26	ajm	1.14
27			# for library machines
28	tdb	1.15	group.library=Host.129.12.58.*;
29	ajm	1.14	config.library=library.conf
30
31	tdb	1.15	# for SSB machines
32			group.ssb=Host.stue*.ukc.ac.uk;
33			config.ssb=ssb.conf
34
35	ajm	1.14	# mySQL configuration
36			config.mySQL=mySQL.conf
37
38	ajm	1.16	############################################################
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	tdb	1.40	# The upper limit for a Queue
49			Queue.SizeLimit=1000
50			# The removal algorithm
51			Queue.RemoveAlgorithm=FIRST
52	tdb	1.2
53	ajm	1.14
54			############################################################
55			#### FilterManager configuration
56			############################################################
57	tdb	1.2
58			# The default port to listen for new host connections
59			FilterManager.listenPort=4567
60
61	ajm	1.14
62
63			############################################################
64			#### Filter configuration
65			############################################################
66
67	tdb	1.2	# The default port for Filter's to listen on
68			Filter.UDPListenPort=4589
69			Filter.TCPListenPort=4589
70
71	ajm	1.14	# Plugin Information
72	tdb	1.36	Filter.PluginsPackage=uk.org.iscream.filter.plugins
73	ajm	1.14	Filter.Plugins=TypeChecker;EnforceEssentialData
74
75	tdb	1.2	# The name for the root filter
76			RootFilter.name=root
77	ajm	1.14
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	tdb	1.2	# Comment either of these (or delete them) and
88			# that interface won't be started
89			RootFilter.realtimeInterfaceName=realtimeclients
90	tdb	1.6	RootFilter.dbInterfaceName=database
91	tdb	1.2
92	ajm	1.14
93
94			############################################################
95			#### Client interface configuration
96			############################################################
97
98	tdb	1.2	# The port for the client interface to listen on
99			ClientInterface.listenPort=4510
100	tdb	1.52	# The name for the client interface
101			ClientInterface.name=realtimeclients
102
103
104
105			############################################################
106			#### Database interface configuration
107			############################################################
108
109			# The name for the Database interface
110			DBInterface.name=database
111	tdb	1.2
112	ajm	1.14
113
114			############################################################
115			#### Host Configuration
116			############################################################
117	tdb	1.2
118			# The default filter for a new host
119	tdb	1.36	Host.filter=computingFilter;
120	tdb	1.13
121	tdb	1.2	# The default update times for a new host
122	tdb	1.7	Host.UDPUpdateTime=10
123	tdb	1.2	Host.TCPUpdateTime=60
124	tdb	1.15	Host.AveragerUpdateTime=5
125	tdb	1.2
126	ajm	1.8	# The services checks to run on a host
127	tdb	1.36	Host.serviceChecksPackage=uk.org.iscream.filter.plugins
128	tdb	1.2
129	ajm	1.14
130	tdb	1.12
131	ajm	1.14	############################################################
132			#### Monitor Configuration
133			############################################################
134
135	tdb	1.47	## The monitors to run
136	tdb	1.36	Monitor.PluginsPackage=uk.org.iscream.client.monitors
137	tdb	1.51	Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\
138			Heartbeat;Queue;UserCount;WebFeeder;
139	tdb	1.24
140	tdb	1.47	## 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	ajm	1.14
148	tdb	1.47	## Threshold values
149	ajm	1.16	#
150			# note: if the UPPER threshold is broken,
151			# the alertTimeout values are halved.
152			# This is to escalate the alert quicker.
153	tdb	1.47	#
154
155			# CPU monitor threshold values
156	ajm	1.16	Monitor.CPU.threshold.LOWER=90
157			Monitor.CPU.threshold.UPPER=99
158
159	tdb	1.44
160	tdb	1.47	# Load monitor threshold values
161	tdb	1.44	Monitor.Load.threshold.LOWER=10.0
162			Monitor.Load.threshold.UPPER=20.0
163
164
165	tdb	1.47	# Process Count threshold values
166	tdb	1.44	Monitor.Process.threshold.LOWER=1000
167			Monitor.Process.threshold.UPPER=1500
168
169	tdb	1.24
170	tdb	1.47	# Memory monitor threshold values
171	tdb	1.24	Monitor.Memory.threshold.LOWER=80
172			Monitor.Memory.threshold.UPPER=90
173
174
175	tdb	1.47	# Swap monitor threshold values
176	tdb	1.24	Monitor.Swap.threshold.LOWER=80
177			Monitor.Swap.threshold.UPPER=90
178	tdb	1.50
179
180			# UserCount monitor threshold values
181			Monitor.UserCount.threshold.LOWER=100
182			Monitor.UserCount.threshold.UPPER=200
183	tdb	1.24
184	ajm	1.33
185	tdb	1.47	# Disk monitor threshold values
186	tdb	1.42	Monitor.Disk.threshold.LOWER=90
187			Monitor.Disk.threshold.UPPER=95
188	tdb	1.47	# 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	tdb	1.46	Monitor.Disk.thresholdMeasure=PERCENTAGE
192	ajm	1.33
193	tdb	1.46
194	tdb	1.47	# Disk monitor threshold values
195	tdb	1.49	Monitor.Queue.threshold.LOWER=50
196			Monitor.Queue.threshold.UPPER=80
197	tdb	1.47	# 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	tdb	1.46	Monitor.Queue.thresholdMeasure=PERCENTAGE
201
202	ajm	1.34
203	tdb	1.47	# Services monitor threshold values
204	ajm	1.34	#
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	tdb	1.47	# how many times we should be at the highest level before
211			# we go to a FINAL alert
212	tdb	1.38	Monitor.Services.reachFINALcount=5
213
214	ajm	1.14
215	tdb	1.47	# Heartbeat threshold values
216	tdb	1.25	# these are values in seconds from when the heartbeat
217			# was expected to arrive (ie. last + hearbeat period)
218	tdb	1.48	Monitor.Heartbeat.threshold.LOWER=180
219	tdb	1.38	Monitor.Heartbeat.threshold.UPPER=300
220	tdb	1.47	# this is how often we will run a "check" of heartbeats
221	tdb	1.48	Monitor.Heartbeat.checkPeriod=50
222	tdb	1.47	# 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	ajm	1.14
227	ajm	1.23
228	ajm	1.14	############################################################
229			#### Alerter Configuration
230			############################################################
231	ajm	1.23	# 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	ajm	1.14
244			# alerters to run
245	tdb	1.36	Alerter.PluginsPackage=uk.org.iscream.client.alerters
246	tdb	1.54	Alerter.Plugins=EMail;IRC;WebFeeder;Logging;
247	tdb	1.47
248	ajm	1.14
249			# EMail alerter configuration
250	tdb	1.38	Alerter.EMail.level = WARNING
251			Alerter.EMail.destList = dev@i-scream.org.uk
252	ajm	1.14	Alerter.EMail.sender = dev@i-scream.org.uk
253			Alerter.EMail.smtpServer = mercury.ukc.ac.uk
254	ajm	1.16	Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName%
255	tdb	1.38	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	ajm	1.14
258			# IRC alerter configuration
259	ajm	1.16	Alerter.IRC.level = OK
260	ajm	1.14	Alerter.IRC.IRCServer = killigrew.ukc.ac.uk
261			Alerter.IRC.IRCPort = 6667
262	tdb	1.19	Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot
263	tdb	1.17	Alerter.IRC.user = i-scream
264			Alerter.IRC.comment = i-scream alerting bot
265	ajm	1.14	Alerter.IRC.channel = #i-scream
266	ajm	1.16	Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert%
267	tdb	1.17	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	tdb	1.18	Alerter.IRC.nickChangeCommand = nick
274			Alerter.IRC.statCommand = statistics
275			Alerter.IRC.uptimeCommand = uptime
276			Alerter.IRC.timeSinceLastAlertCommand = time since last alert
277	tdb	1.19	Alerter.IRC.versionCommand = version
278	tdb	1.17	Alerter.IRC.helpCommand = help
279			Alerter.IRC.rejectMessage = sorry, I don't understand your request
280	tdb	1.54
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	tdb	1.29
286	tdb	1.47
287
288	tdb	1.29	############################################################
289			#### WebFeeder Configuration
290			############################################################
291
292	tdb	1.32	# 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	tdb	1.43
297			# Only pass on alerts past this level
298	tdb	1.53	Alerter.WebFeeder.level = OK
299	tdb	1.37
300			# Check period in seconds (for cleaning stale/old alerts)
301	tdb	1.42	WebFeeder.checkPeriod = 120
302	tdb	1.37
303			# Delete alerts older than this, in seconds.
304			# Files are only check every WebFeeder.checkPeriod seconds.
305	tdb	1.42	WebFeeder.alertDeleteOlderThan = 300
306	tdb	1.32
307	tdb	1.29	# Root Path
308			WebFeeder.rootPath = /usr/local/proj/co600_10/webroot
309
310			# Latest Data
311			WebFeeder.latestSubDir = latest
312	tdb	1.31	WebFeeder.latestFileName = latest_data
313	tdb	1.32
314			# Alert Data
315			WebFeeder.alertSubDir = alert
316			WebFeeder.alertFileName = alert_data
317	ajm	1.16
318	tdb	1.47
319	tdb	1.17	############################################################