ViewVC Help
View File | Revision Log | Show Annotations | Revision Graph | Root Listing
root/i-scream/projects/cms/source/server/build/etc/system.conf
(Generate patch)

Comparing projects/cms/source/server/build/etc/system.conf (file contents):
Revision 1.37 by tdb, Thu Mar 15 14:29:09 2001 UTC vs.
Revision 1.51 by tdb, Fri Mar 23 02:31:54 2001 UTC

# Line 14 | Line 14
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.*;
# Line 37 | Line 45 | ConfigurationProxy.updateTime=60
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  
42
54   ############################################################
55   #### FilterManager configuration
56   ############################################################
# Line 103 | Line 114 | Host.AveragerUpdateTime=5
114  
115   # The services checks to run on a host
116   Host.serviceChecksPackage=uk.org.iscream.filter.plugins
106 Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet
117  
118  
119  
# Line 111 | Line 121 | Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet
121   #### Monitor Configuration
122   ############################################################
123  
124 < # the monitors to run
124 > ## The monitors to run
125   Monitor.PluginsPackage=uk.org.iscream.client.monitors
126 < Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder;
126 > Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\
127 >                Heartbeat;Queue;UserCount;WebFeeder;
128  
129 + ## Default alert timeouts
130 + # these can be override on a per-monitor basis
131 + # timings of the alerts (in seconds)
132 + Monitor.alertTimeout.NOTICE=60
133 + Monitor.alertTimeout.WARNING=900
134 + Monitor.alertTimeout.CAUTION=1800
135 + Monitor.alertTimeout.CRITICAL=3600
136  
137 < ## CPU monitor configuration
120 < # threshold values
137 > ## Threshold values
138   #
139   # note: if the UPPER threshold is broken,
140   # the alertTimeout values are halved.
141   # This is to escalate the alert quicker.
142 + #
143 +
144 + # CPU monitor threshold values
145   Monitor.CPU.threshold.LOWER=90
146   Monitor.CPU.threshold.UPPER=99
147  
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
148  
149 + # Load monitor threshold values
150 + Monitor.Load.threshold.LOWER=10.0
151 + Monitor.Load.threshold.UPPER=20.0
152  
153 < ## Memory monitor configuration
154 < # threshold values
155 < #
156 < # note: if the UPPER threshold is broken,
157 < # the alertTimeout values are halved.
158 < # This is to escalate the alert quicker.
153 >
154 > # Process Count threshold values
155 > Monitor.Process.threshold.LOWER=1000
156 > Monitor.Process.threshold.UPPER=1500
157 >
158 >
159 > # Memory monitor threshold values
160   Monitor.Memory.threshold.LOWER=80
161   Monitor.Memory.threshold.UPPER=90
162  
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
163  
164 <
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.
164 > # Swap monitor threshold values
165   Monitor.Swap.threshold.LOWER=80
166   Monitor.Swap.threshold.UPPER=90
167  
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
168  
169 + # UserCount monitor threshold values
170 + Monitor.UserCount.threshold.LOWER=100
171 + Monitor.UserCount.threshold.UPPER=200
172  
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
173  
174 < # timings of the alerts (in seconds)
175 < Monitor.Disk.alertTimeout.NOTICE=60
176 < Monitor.Disk.alertTimeout.WARNING=900
177 < Monitor.Disk.alertTimeout.CAUTION=1800
178 < Monitor.Disk.alertTimeout.CRITICAL=3600
174 > # Disk monitor threshold values
175 > Monitor.Disk.threshold.LOWER=90
176 > Monitor.Disk.threshold.UPPER=95
177 > # Thresholds given are PERCENTAGE or VALUE
178 > # where PERCENTAGE is a percentage of disk in use
179 > # and VALUE is an absolute value of space free
180 > Monitor.Disk.thresholdMeasure=PERCENTAGE
181  
182  
183 < ## Services monitor configuration
184 < # threshold values
183 > # Disk monitor threshold values
184 > Monitor.Queue.threshold.LOWER=50
185 > Monitor.Queue.threshold.UPPER=80
186 > # Thresholds given are PERCENTAGE or VALUE
187 > # where PERCENTAGE is a percentage of disk in use
188 > # and VALUE is an absolute value of space free
189 > Monitor.Queue.thresholdMeasure=PERCENTAGE
190 >
191 >
192 > # Services monitor threshold values
193   #
194   # THE SERVICES MONITOR USES A HACK
195   # WHEREBY IT USES THE SERVICE STATUS
196   # AS THE THRESHOLD LEVEL.  THIS SHOULD
197   # BE LOOKED AT!
198   #
199 < # note: if the UPPER threshold is broken,
200 < # the alertTimeout values are halved.
201 < # This is to escalate the alert quicker.
194 < #Monitor.Services.threshold.LOWER=120
195 < #Monitor.Services.threshold.LOWER=300
199 > # how many times we should be at the highest level before
200 > # we go to a FINAL alert
201 > Monitor.Services.reachFINALcount=5
202  
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
203  
204 <
204 < ## Heartbeat monitor configuration
205 < # threshold values
206 < #
207 < # note: if the UPPER threshold is broken,
208 < # the alertTimeout values are halved.
209 < # This is to escalate the alert quicker.
210 < Monitor.Heartbeat.checkPeriod=50
204 > # Heartbeat threshold values
205   # these are values in seconds from when the heartbeat
206   # was *expected* to arrive (ie. last + hearbeat period)
207 < Monitor.Heartbeat.threshold.LOWER=120
208 < Monitor.Heartbeat.threshold.LOWER=300
207 > Monitor.Heartbeat.threshold.LOWER=180
208 > Monitor.Heartbeat.threshold.UPPER=300
209 > # this is how often we will run a "check" of heartbeats
210 > Monitor.Heartbeat.checkPeriod=50
211 > # how many times we should be at the highest level before
212 > # we go to a FINAL alert
213 > Monitor.Heartbeat.reachFINALcount=5
214  
216 # timings of the alerts (in seconds)
217 Monitor.Heartbeat.alertTimeout.NOTICE=60
218 Monitor.Heartbeat.alertTimeout.WARNING=900
219 Monitor.Heartbeat.alertTimeout.CAUTION=1800
220 Monitor.Heartbeat.alertTimeout.CRITICAL=3600
215  
222 # this means it will reach a FINAL level,
223 # and thus the host will be removed from the monitor list,
224 # if the highest level alert is reached and occours this
225 # number of times.
226 #
227 # int this setup, that means 5 CRITICAL alerts would occour
228 # on a Heartbeat before reaching FINAL.
229 # If this value is wrong or not present, FINAL is never reached
230 #
231 Monitor.Heartbeat.reachFINALcount=5
216  
217   ############################################################
218   #### Alerter Configuration
# Line 250 | Line 234 | Monitor.Heartbeat.reachFINALcount=5
234   Alerter.PluginsPackage=uk.org.iscream.client.alerters
235   Alerter.Plugins=EMail;IRC;WebFeeder;
236  
237 +
238   # EMail alerter configuration
239 < Alerter.EMail.level = CAUTION
240 < Alerter.EMail.defaultDestList = dev@i-scream.org.uk
239 > Alerter.EMail.level = WARNING
240 > Alerter.EMail.destList = dev@i-scream.org.uk
241   Alerter.EMail.sender = dev@i-scream.org.uk
242   Alerter.EMail.smtpServer = mercury.ukc.ac.uk
243   Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName%
244 < 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%.
244 > 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%.
245  
246 +
247   # IRC alerter configuration
248   Alerter.IRC.level = OK
249   Alerter.IRC.IRCServer = killigrew.ukc.ac.uk
# Line 281 | Line 267 | Alerter.IRC.versionCommand = version
267   Alerter.IRC.helpCommand = help
268   Alerter.IRC.rejectMessage = sorry, I don't understand your request
269  
270 +
271 +
272   ############################################################
273   #### WebFeeder Configuration
274   ############################################################
# Line 290 | Line 278 | Alerter.IRC.rejectMessage = sorry, I don't understand
278   WebFeeder.latestActive = true
279   WebFeeder.alertActive = true
280  
281 + # Only pass on alerts past this level
282 + WebFeeder.alertLevel = OK
283 +
284   # Check period in seconds (for cleaning stale/old alerts)
285 < WebFeeder.checkPeriod = 1800
285 > WebFeeder.checkPeriod = 120
286  
287   # Delete alerts older than this, in seconds.
288   # Files are only check every WebFeeder.checkPeriod seconds.
289 < WebFeeder.alertDeleteOlderThan = 3600
289 > WebFeeder.alertDeleteOlderThan = 300
290  
291   # Root Path
292   WebFeeder.rootPath = /usr/local/proj/co600_10/webroot
# Line 308 | Line 299 | WebFeeder.latestFileName = latest_data
299   WebFeeder.alertSubDir = alert
300   WebFeeder.alertFileName = alert_data
301  
311 ############################################################
302  
303 + ############################################################

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines