--- projects/cms/source/server/build/etc/system.conf 2000/12/12 19:00:44 1.1.2.1 +++ projects/cms/source/server/build/etc/system.conf 2001/03/22 02:06:07 1.46 @@ -6,38 +6,379 @@ # root of configuration # # $Author: tdb $ -# $Id: system.conf,v 1.1.2.1 2000/12/12 19:00:44 tdb Exp $ +# $Id: system.conf,v 1.46 2001/03/22 02:06:07 tdb Exp $ +# +############################################################ +#### Configuration Files & Groups +############################################################ -# FilterManager configuration +# 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 default parent filter (should almost always be the same as Filter.rootFilter) -Filter.parentFilter=root + +############################################################ +#### Host Configuration +############################################################ + # The default filter for a new host -Host.filter=filter1 +Host.filter=computingFilter; # The default update times for a new host -Host.UDPUpdateTime=5 +Host.UDPUpdateTime=10 Host.TCPUpdateTime=60 +Host.AveragerUpdateTime=5 -# Plugin Information -Filter.PluginsPackage=uk.ac.ukc.iscream.filter.plugins -Filter.Plugins=EnforceEssentialData +# The services checks to run on a host +Host.serviceChecksPackage=uk.org.iscream.filter.plugins -# mySQL Details -config.mySQL=mySQL.conf \ No newline at end of file + + +############################################################ +#### 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; +#Monitor.Plugins=CPU;WebFeeder; +#Monitor.Plugins= + + +## 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 + + +## Load monitor configuration +# threshold values +# +# note: if the UPPER threshold is broken, +# the alertTimeout values are halved. +# This is to escalate the alert quicker. +Monitor.Load.threshold.LOWER=10.0 +Monitor.Load.threshold.UPPER=20.0 + +# timings of the alerts (in seconds) +Monitor.Load.alertTimeout.NOTICE=60 +Monitor.Load.alertTimeout.WARNING=900 +Monitor.Load.alertTimeout.CAUTION=1800 +Monitor.Load.alertTimeout.CRITICAL=3600 + + +## Process Count monitor configuration +# threshold values +# +# note: if the UPPER threshold is broken, +# the alertTimeout values are halved. +# This is to escalate the alert quicker. +Monitor.Process.threshold.LOWER=1000 +Monitor.Process.threshold.UPPER=1500 + +# timings of the alerts (in seconds) +Monitor.Process.alertTimeout.NOTICE=60 +Monitor.Process.alertTimeout.WARNING=900 +Monitor.Process.alertTimeout.CAUTION=1800 +Monitor.Process.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=90 +Monitor.Disk.threshold.UPPER=95 +Monitor.Disk.thresholdMeasure=PERCENTAGE + +# 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 configuration +# threshold values +# +# note: if the UPPER threshold is broken, +# the alertTimeout values are halved. +# This is to escalate the alert quicker. +Monitor.Queue.threshold.LOWER=90 +Monitor.Queue.threshold.UPPER=95 +Monitor.Queue.thresholdMeasure=PERCENTAGE + +# timings of the alerts (in seconds) +Monitor.Queue.alertTimeout.NOTICE=60 +Monitor.Queue.alertTimeout.WARNING=900 +Monitor.Queue.alertTimeout.CAUTION=1800 +Monitor.Queue.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; +Alerter.Plugins=IRC;WebFeeder; +#Alerter.Plugins=WebFeeder; +#Alerter.Plugins= + +# 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 + +############################################################ +