--- projects/cms/source/server/build/etc/system.conf	2001/03/15 14:29:09	1.37
+++ projects/cms/source/server/build/etc/system.conf	2001/03/22 17:33:10	1.49
@@ -6,7 +6,7 @@
 # root of configuration
 #
 # $Author: tdb $
-# $Id: system.conf,v 1.37 2001/03/15 14:29:09 tdb Exp $
+# $Id: system.conf,v 1.49 2001/03/22 17:33:10 tdb Exp $
 #
 ############################################################
 #### Configuration Files & Groups
@@ -14,7 +14,15 @@
 
 # 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.*;
@@ -37,9 +45,12 @@ 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
 ############################################################
@@ -103,7 +114,6 @@ 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
 
 
 
@@ -111,124 +121,92 @@ Host.serviceChecks=HTTP;SMTP;POP3;SSH;FTP;IMAP;Telnet
 #### Monitor Configuration
 ############################################################
 
-# the monitors to run
+## The monitors to run
 Monitor.PluginsPackage=uk.org.iscream.client.monitors
-Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder;
+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
 
-## CPU monitor configuration
-# threshold values
+## 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
 
-# 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
 
+# Load monitor threshold values
+Monitor.Load.threshold.LOWER=10.0
+Monitor.Load.threshold.UPPER=20.0
 
-## Memory monitor configuration
-# threshold values
-# 
-# note: if the UPPER threshold is broken,
-# the alertTimeout values are halved.
-# This is to escalate the alert quicker.
+
+# 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
 
-# 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.
+# Swap monitor threshold values
 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 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 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
+# 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 configuration
-# threshold values
+# 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!
 #
-# 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
+# how many times we should be at the highest level before
+# we go to a FINAL alert
+Monitor.Services.reachFINALcount=5
 
-# 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
 
-
-## 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
+# 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.LOWER=300
+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
 
-# 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
@@ -250,14 +228,16 @@ Monitor.Heartbeat.reachFINALcount=5
 Alerter.PluginsPackage=uk.org.iscream.client.alerters
 Alerter.Plugins=EMail;IRC;WebFeeder;
 
+
 # EMail alerter configuration
-Alerter.EMail.level = CAUTION
-Alerter.EMail.defaultDestList = dev@i-scream.org.uk
+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\nThe next alert (should one occur) will be sent in %timeTillNextAlert%.
+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
@@ -281,6 +261,8 @@ Alerter.IRC.versionCommand = version
 Alerter.IRC.helpCommand = help
 Alerter.IRC.rejectMessage = sorry, I don't understand your request
 
+
+
 ############################################################
 #### WebFeeder Configuration
 ############################################################
@@ -290,12 +272,15 @@ Alerter.IRC.rejectMessage = sorry, I don't understand 
 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 = 1800
+WebFeeder.checkPeriod = 120
 
 # Delete alerts older than this, in seconds.
 # Files are only check every WebFeeder.checkPeriod seconds.
-WebFeeder.alertDeleteOlderThan = 3600
+WebFeeder.alertDeleteOlderThan = 300
 
 # Root Path
 WebFeeder.rootPath = /usr/local/proj/co600_10/webroot
@@ -308,5 +293,5 @@ WebFeeder.latestFileName = latest_data
 WebFeeder.alertSubDir = alert
 WebFeeder.alertFileName = alert_data
 
-############################################################
 
+############################################################