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 1.46 2001/03/22 02:06:07 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


############################################################
#### 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;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


# 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=90
Monitor.Queue.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.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=120
Monitor.Heartbeat.threshold.UPPER=300
# this is how often we will run a "check" of heartbeats
Monitor.Heartbeat.checkPeriod=30
# 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;


# 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

# Only pass on alerts past this level
WebFeeder.alertLevel = 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:	1.47
Committed:	Thu Mar 22 02:18:05 2001 UTC (23 years, 9 months ago) by tdb
Branch:	MAIN
Changes since 1.46:	+40 -127 lines
Log Message:	Tidied up the Monitor's section. Alert timeouts are stored as defaults, which can be overridden. This saves repeating the same values. Also neatened the layout and comments. More detailed explanation could be given in the user documentation.
#	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	1.47	# $Id: system.conf,v 1.46 2001/03/22 02:06:07 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
101	ajm	1.14
102
103			############################################################
104			#### Host Configuration
105			############################################################
106	tdb	1.2
107			# The default filter for a new host
108	tdb	1.36	Host.filter=computingFilter;
109	tdb	1.13
110	tdb	1.2	# The default update times for a new host
111	tdb	1.7	Host.UDPUpdateTime=10
112	tdb	1.2	Host.TCPUpdateTime=60
113	tdb	1.15	Host.AveragerUpdateTime=5
114	tdb	1.2
115	ajm	1.8	# The services checks to run on a host
116	tdb	1.36	Host.serviceChecksPackage=uk.org.iscream.filter.plugins
117	tdb	1.2
118	ajm	1.14
119	tdb	1.12
120	ajm	1.14	############################################################
121			#### Monitor Configuration
122			############################################################
123
124	tdb	1.47	## The monitors to run
125	tdb	1.36	Monitor.PluginsPackage=uk.org.iscream.client.monitors
126	tdb	1.46	Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;Heartbeat;Queue;WebFeeder;
127	tdb	1.24
128	tdb	1.47	## Default alert timeouts
129			# these can be override on a per-monitor basis
130			# timings of the alerts (in seconds)
131			Monitor.alertTimeout.NOTICE=60
132			Monitor.alertTimeout.WARNING=900
133			Monitor.alertTimeout.CAUTION=1800
134			Monitor.alertTimeout.CRITICAL=3600
135	ajm	1.14
136	tdb	1.47	## Threshold values
137	ajm	1.16	#
138			# note: if the UPPER threshold is broken,
139			# the alertTimeout values are halved.
140			# This is to escalate the alert quicker.
141	tdb	1.47	#
142
143			# CPU monitor threshold values
144	ajm	1.16	Monitor.CPU.threshold.LOWER=90
145			Monitor.CPU.threshold.UPPER=99
146
147	tdb	1.44
148	tdb	1.47	# Load monitor threshold values
149	tdb	1.44	Monitor.Load.threshold.LOWER=10.0
150			Monitor.Load.threshold.UPPER=20.0
151
152
153	tdb	1.47	# Process Count threshold values
154	tdb	1.44	Monitor.Process.threshold.LOWER=1000
155			Monitor.Process.threshold.UPPER=1500
156
157	tdb	1.24
158	tdb	1.47	# Memory monitor threshold values
159	tdb	1.24	Monitor.Memory.threshold.LOWER=80
160			Monitor.Memory.threshold.UPPER=90
161
162
163	tdb	1.47	# Swap monitor threshold values
164	tdb	1.24	Monitor.Swap.threshold.LOWER=80
165			Monitor.Swap.threshold.UPPER=90
166
167	ajm	1.33
168	tdb	1.47	# Disk monitor threshold values
169	tdb	1.42	Monitor.Disk.threshold.LOWER=90
170			Monitor.Disk.threshold.UPPER=95
171	tdb	1.47	# Thresholds given are PERCENTAGE or VALUE
172			# where PERCENTAGE is a percentage of disk in use
173			# and VALUE is an absolute value of space free
174	tdb	1.46	Monitor.Disk.thresholdMeasure=PERCENTAGE
175	ajm	1.33
176	tdb	1.46
177	tdb	1.47	# Disk monitor threshold values
178	tdb	1.46	Monitor.Queue.threshold.LOWER=90
179			Monitor.Queue.threshold.UPPER=95
180	tdb	1.47	# Thresholds given are PERCENTAGE or VALUE
181			# where PERCENTAGE is a percentage of disk in use
182			# and VALUE is an absolute value of space free
183	tdb	1.46	Monitor.Queue.thresholdMeasure=PERCENTAGE
184
185	ajm	1.34
186	tdb	1.47	# Services monitor threshold values
187	ajm	1.34	#
188			# THE SERVICES MONITOR USES A HACK
189			# WHEREBY IT USES THE SERVICE STATUS
190			# AS THE THRESHOLD LEVEL. THIS SHOULD
191			# BE LOOKED AT!
192			#
193	tdb	1.47	# how many times we should be at the highest level before
194			# we go to a FINAL alert
195	tdb	1.38	Monitor.Services.reachFINALcount=5
196
197	ajm	1.14
198	tdb	1.47	# Heartbeat threshold values
199	tdb	1.25	# these are values in seconds from when the heartbeat
200			# was expected to arrive (ie. last + hearbeat period)
201	tdb	1.22	Monitor.Heartbeat.threshold.LOWER=120
202	tdb	1.38	Monitor.Heartbeat.threshold.UPPER=300
203	tdb	1.47	# this is how often we will run a "check" of heartbeats
204			Monitor.Heartbeat.checkPeriod=30
205			# how many times we should be at the highest level before
206			# we go to a FINAL alert
207			Monitor.Heartbeat.reachFINALcount=5
208
209	ajm	1.14
210	ajm	1.23
211	ajm	1.14	############################################################
212			#### Alerter Configuration
213			############################################################
214	ajm	1.23	# The following var's are understood by ALL alerters for messages
215			#
216			# %level% - the alert level (eg, WARNING)
217			# %threshold% - the threshold broken (eg, LOWER)
218			# %source% - the source of the alert (eg, raptor.ukc.ac.uk)
219			# %value% - the value reached (eg, 95)
220			# %thresholdValue% - the value of the threshold broken (eg, 90)
221			# %attributeName% - the attribute that has caused the alert (eg, CPU User)
222			# %timeTillNextAlert% - the time the next alert will be sent out
223			# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem
224			# %timeOfFirstAlert% - the time the first alert was sent
225			#
226	ajm	1.14
227			# alerters to run
228	tdb	1.36	Alerter.PluginsPackage=uk.org.iscream.client.alerters
229	tdb	1.47	Alerter.Plugins=EMail;IRC;WebFeeder;
230
231	ajm	1.14
232			# EMail alerter configuration
233	tdb	1.38	Alerter.EMail.level = WARNING
234			Alerter.EMail.destList = dev@i-scream.org.uk
235	ajm	1.14	Alerter.EMail.sender = dev@i-scream.org.uk
236			Alerter.EMail.smtpServer = mercury.ukc.ac.uk
237	ajm	1.16	Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName%
238	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%.
239
240	ajm	1.14
241			# IRC alerter configuration
242	ajm	1.16	Alerter.IRC.level = OK
243	ajm	1.14	Alerter.IRC.IRCServer = killigrew.ukc.ac.uk
244			Alerter.IRC.IRCPort = 6667
245	tdb	1.19	Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot
246	tdb	1.17	Alerter.IRC.user = i-scream
247			Alerter.IRC.comment = i-scream alerting bot
248	ajm	1.14	Alerter.IRC.channel = #i-scream
249	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%
250	tdb	1.17	Alerter.IRC.reconnectDelay = 30
251			Alerter.IRC.startupNotice = i-scream alerting bot activated
252			Alerter.IRC.stopCommand = stop alerts
253			Alerter.IRC.startCommand = start alerts
254			Alerter.IRC.lastAlertCommand = last alert
255			Alerter.IRC.joinCommand = join
256	tdb	1.18	Alerter.IRC.nickChangeCommand = nick
257			Alerter.IRC.statCommand = statistics
258			Alerter.IRC.uptimeCommand = uptime
259			Alerter.IRC.timeSinceLastAlertCommand = time since last alert
260	tdb	1.19	Alerter.IRC.versionCommand = version
261	tdb	1.17	Alerter.IRC.helpCommand = help
262			Alerter.IRC.rejectMessage = sorry, I don't understand your request
263	tdb	1.29
264	tdb	1.47
265
266	tdb	1.29	############################################################
267			#### WebFeeder Configuration
268			############################################################
269
270	tdb	1.32	# Define these (one or both_ to turn on the WebFeeder's,
271			# comment it to turn them off
272			WebFeeder.latestActive = true
273			WebFeeder.alertActive = true
274	tdb	1.43
275			# Only pass on alerts past this level
276			WebFeeder.alertLevel = OK
277	tdb	1.37
278			# Check period in seconds (for cleaning stale/old alerts)
279	tdb	1.42	WebFeeder.checkPeriod = 120
280	tdb	1.37
281			# Delete alerts older than this, in seconds.
282			# Files are only check every WebFeeder.checkPeriod seconds.
283	tdb	1.42	WebFeeder.alertDeleteOlderThan = 300
284	tdb	1.32
285	tdb	1.29	# Root Path
286			WebFeeder.rootPath = /usr/local/proj/co600_10/webroot
287
288			# Latest Data
289			WebFeeder.latestSubDir = latest
290	tdb	1.31	WebFeeder.latestFileName = latest_data
291	tdb	1.32
292			# Alert Data
293			WebFeeder.alertSubDir = alert
294			WebFeeder.alertFileName = alert_data
295	ajm	1.16
296	tdb	1.47
297	tdb	1.17	############################################################