| 5 |
|
# configuration system has this file as its |
| 6 |
|
# root of configuration |
| 7 |
|
# |
| 8 |
+ |
# This is a working sample configuration, which |
| 9 |
+ |
# aims to provide a working "out of the box" |
| 10 |
+ |
# setup, aswell as a some example configuration. |
| 11 |
+ |
# |
| 12 |
|
# $Author$ |
| 13 |
|
# $Id$ |
| 14 |
|
# |
| 15 |
+ |
# http://www.i-scream.org.uk/ |
| 16 |
+ |
# |
| 17 |
+ |
|
| 18 |
|
############################################################ |
| 19 |
|
#### Configuration Files & Groups |
| 20 |
|
############################################################ |
| 21 |
|
|
| 22 |
< |
# for computing machines |
| 23 |
< |
group.computing=Host.129.12.4.*; |
| 24 |
< |
group.rocks=Host.agate.ukc.ac.uk;Host.arkose.ukc.ac.uk;Host.basalt.ukc.ac.uk;Host.chalk.ukc.ac.uk;\ |
| 25 |
< |
Host.chert.ukc.ac.uk;Host.granite.ukc.ac.uk;Host.jade.ukc.ac.uk;Host.jasper.ukc.ac.uk;\ |
| 26 |
< |
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 |
> |
# All components, such as hosts, will take their configuration |
| 23 |
> |
# as given in this file. Unless, that is, they have an extra |
| 24 |
> |
# configuration file specified here, or they're in a group |
| 25 |
> |
# that has a configuration file. If this is the case the extra |
| 26 |
> |
# configuration will override what is given in this file. |
| 27 |
|
|
| 28 |
< |
config.computing=computing.conf |
| 29 |
< |
config.rocks=rocks.conf |
| 30 |
< |
config.compsoc1=rocks.conf |
| 28 |
> |
# We can define an extra configuration file for any component |
| 29 |
> |
# of the system. This is done by specifying the following: |
| 30 |
> |
# |
| 31 |
> |
# config.component=someconfigfile.conf |
| 32 |
> |
# |
| 33 |
> |
# Component names will be defined in the documentation for |
| 34 |
> |
# the component. An example is that a host component is |
| 35 |
> |
# known by the name "Host.hostname" or "Host.ip". |
| 36 |
> |
# It is also possible to use the wildcard "*" in a |
| 37 |
> |
# hostname or IP address. |
| 38 |
|
|
| 39 |
< |
# for library machines |
| 40 |
< |
group.library=Host.129.12.58.*; |
| 41 |
< |
config.library=library.conf |
| 39 |
> |
# This defines that server.example.com has some extra |
| 40 |
> |
# configuration in the file 'server.conf'. |
| 41 |
> |
config.Host.server.example.com=exserver.conf |
| 42 |
|
|
| 43 |
< |
# for SSB machines |
| 44 |
< |
group.ssb=Host.stue*.ukc.ac.uk; |
| 45 |
< |
config.ssb=ssb.conf |
| 43 |
> |
# All webservers are placed in a group named 'www'. |
| 44 |
> |
group.www=Host.www1.example.com;Host.www2.example.com |
| 45 |
> |
# Then we define some extra config for them. |
| 46 |
> |
config.www=webservers.conf |
| 47 |
|
|
| 48 |
< |
# mySQL configuration |
| 49 |
< |
config.mySQL=mySQL.conf |
| 48 |
> |
# Our workstations are in their own subnet. |
| 49 |
> |
group.workstations=Host.192.168.10.*; |
| 50 |
> |
# They can have their own config too. |
| 51 |
> |
config.workstations=workstations.conf |
| 52 |
|
|
| 53 |
+ |
# Any hosts not specified by now have the default |
| 54 |
+ |
# config as given in this file. |
| 55 |
+ |
|
| 56 |
+ |
|
| 57 |
|
############################################################ |
| 58 |
|
#### Misc system-wide configuration |
| 59 |
|
############################################################ |
| 60 |
|
|
| 61 |
< |
# the time (in seconds) that checks should be made for |
| 62 |
< |
# changes in configuration |
| 61 |
> |
# The ConfigurationProxy caches configuration for various |
| 62 |
> |
# parts of the server. This setting defines how often, in |
| 63 |
> |
# seconds, the proxy will check if the data it contains |
| 64 |
> |
# is still valid. |
| 65 |
|
ConfigurationProxy.updateTime=60 |
| 66 |
|
|
| 67 |
< |
# The time interval at which the Queue's should be monitored |
| 68 |
< |
Queue.MonitorInterval=15 |
| 69 |
< |
# The upper limit for a Queue |
| 67 |
> |
# The internal Queue's can be monitored. This specifies |
| 68 |
> |
# the interval, in seconds, at which their state should |
| 69 |
> |
# be monitored. |
| 70 |
> |
Queue.MonitorInterval=300 |
| 71 |
> |
# The maximum size a Queue can be before items are |
| 72 |
> |
# dropped when new ones arrive. |
| 73 |
|
Queue.SizeLimit=1000 |
| 74 |
< |
# The removal algorithm |
| 74 |
> |
# And which items we should drop when the queue is full |
| 75 |
> |
# and new items arrive. Choices are: |
| 76 |
> |
# RANDOM - drop a random item from the queue |
| 77 |
> |
# FIRST - drop the first item from the queue |
| 78 |
> |
# LAST - drop the last item from the queue |
| 79 |
> |
# DROP - drop the new item from the queue |
| 80 |
|
Queue.RemoveAlgorithm=FIRST |
| 81 |
|
|
| 82 |
+ |
# The XMLCache caches data passing through the system. |
| 83 |
+ |
# This setting specifies the time, in seconds, at which |
| 84 |
+ |
# the caches contents will be rotated. In real terms |
| 85 |
+ |
# this means the minimum age at which an XMLPacket can |
| 86 |
+ |
# be before it is up for deletion from the cache. |
| 87 |
+ |
XMLCache.cleanupPeriod=30 |
| 88 |
|
|
| 89 |
+ |
|
| 90 |
|
############################################################ |
| 91 |
|
#### FilterManager configuration |
| 92 |
|
############################################################ |
| 93 |
|
|
| 94 |
< |
# The default port to listen for new host connections |
| 94 |
> |
# The FilterManager accepts connections from hosts |
| 95 |
> |
# upon startup. It provides them with configuration |
| 96 |
> |
# and details of which filter to talk to. This setting |
| 97 |
> |
# specifies which port (TCP) it listens on. |
| 98 |
|
FilterManager.listenPort=4567 |
| 99 |
|
|
| 100 |
+ |
# An Access Control List for the FilterManager. One |
| 101 |
+ |
# might consider something like this: |
| 102 |
+ |
# |
| 103 |
+ |
# FilterManager.ACL=DEFAULT:DENY;*.example.com:ALLOW |
| 104 |
+ |
FilterManager.ACL=DEFAULT:ALLOW |
| 105 |
|
|
| 106 |
|
|
| 107 |
|
############################################################ |
| 108 |
|
#### Filter configuration |
| 109 |
|
############################################################ |
| 110 |
|
|
| 111 |
< |
# The default port for Filter's to listen on |
| 111 |
> |
# A Filter accepts data from hosts on a UDP port. It is |
| 112 |
> |
# specified here. |
| 113 |
|
Filter.UDPListenPort=4589 |
| 69 |
– |
Filter.TCPListenPort=4589 |
| 114 |
|
|
| 115 |
< |
# Plugin Information |
| 116 |
< |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
| 117 |
< |
Filter.Plugins=TypeChecker;EnforceEssentialData |
| 115 |
> |
# Filters contain plugins for checking the data passing |
| 116 |
> |
# through them. This plugins do the job of "filtering". |
| 117 |
> |
# This setting specifies the java package they're |
| 118 |
> |
# contained in. |
| 119 |
> |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
| 120 |
> |
# And the names of the plugins to be loaded. |
| 121 |
> |
Filter.Plugins=TypeChecker;EnforceEssentialData;SourceChecker |
| 122 |
|
|
| 123 |
< |
# The name for the root filter |
| 124 |
< |
RootFilter.name=root |
| 125 |
< |
|
| 126 |
< |
# The default parent filter (should almost always be the same as Filter.rootFilter) |
| 123 |
> |
# Every Filter, except the root, needs a parent to |
| 124 |
> |
# send their data to. This is usually the root filter, |
| 125 |
> |
# although in more complex setups it might be another |
| 126 |
> |
# filter - giving a tree structure. |
| 127 |
|
Filter.parentFilter=root |
| 128 |
|
|
| 129 |
+ |
# A Filter can accept data through UDP, or from |
| 130 |
+ |
# an upstream Filter (CORBA). These methods can be |
| 131 |
+ |
# individually turned of on a filter. The default |
| 132 |
+ |
# is to have them all on. |
| 133 |
+ |
# (comment or set to 0 to disable) |
| 134 |
+ |
Filter.ActivateUDPReader=1 |
| 135 |
+ |
Filter.ActivateCORBAReader=1 |
| 136 |
|
|
| 137 |
+ |
# We can also specify Access Control Lists for the |
| 138 |
+ |
# UDP input of the Filters. One might want something |
| 139 |
+ |
# restrictive like this: |
| 140 |
+ |
# |
| 141 |
+ |
# Filter.UDPACL=DEFAULT:DENY;*.example.com:ALLOW |
| 142 |
+ |
Filter.UDPACL=DEFAULT:ALLOW |
| 143 |
|
|
| 144 |
+ |
# A Filter plugin called the SourceChecker verifies |
| 145 |
+ |
# that packets come from permitted hosts. It is |
| 146 |
+ |
# given an ACL to check the hosts against. A possible |
| 147 |
+ |
# ACL might be: |
| 148 |
+ |
# |
| 149 |
+ |
# Filter.SourceCheckerPluginACL=DEFAULT:DENY;*.example.com:ALLOW |
| 150 |
+ |
Filter.SourceCheckerPluginACL=DEFAULT:ALLOW |
| 151 |
+ |
|
| 152 |
+ |
|
| 153 |
|
############################################################ |
| 154 |
< |
#### Root filter interfaces configuration |
| 154 |
> |
#### Root filter configuration |
| 155 |
|
############################################################ |
| 156 |
|
|
| 157 |
< |
# Comment either of these (or delete them) and |
| 158 |
< |
# that interface won't be started |
| 159 |
< |
RootFilter.realtimeInterfaceName=realtimeclients |
| 90 |
< |
RootFilter.dbInterfaceName=database |
| 157 |
> |
# The special filter known as the "Root Filter" needs |
| 158 |
> |
# a name within the system. |
| 159 |
> |
RootFilter.name=root |
| 160 |
|
|
| 161 |
|
|
| 93 |
– |
|
| 162 |
|
############################################################ |
| 163 |
|
#### Client interface configuration |
| 164 |
|
############################################################ |
| 165 |
|
|
| 166 |
< |
# The port for the client interface to listen on |
| 166 |
> |
# The client interface listens for connections from clients |
| 167 |
> |
# on a TCP port. It is specified here. |
| 168 |
|
ClientInterface.listenPort=4510 |
| 169 |
|
|
| 170 |
+ |
# The client interface needs to connect to another one to |
| 171 |
+ |
# receive data. There is a special client interface in the |
| 172 |
+ |
# root filter which is the top of the tree. |
| 173 |
+ |
ClientInterface.parent=root |
| 174 |
|
|
| 175 |
+ |
# The Client Interface has two channels, control and data. |
| 176 |
+ |
# Each of these can have an ACL for allowing connections. |
| 177 |
+ |
# As per previous examples in this configuration file they |
| 178 |
+ |
# could be set restrictively, but we'll leave them open |
| 179 |
+ |
# by default |
| 180 |
+ |
ClientInterface.TCPControlChannelACL=DEFAULT:ALLOW |
| 181 |
+ |
ClientInterface.TCPDataChannelACL=DEFAULT:ALLOW |
| 182 |
|
|
| 183 |
+ |
|
| 184 |
|
############################################################ |
| 185 |
+ |
#### LocalClient Configuration |
| 186 |
+ |
############################################################ |
| 187 |
+ |
|
| 188 |
+ |
# The parent for the Local Client |
| 189 |
+ |
Client.parent=clientinterface1 |
| 190 |
+ |
|
| 191 |
+ |
|
| 192 |
+ |
############################################################ |
| 193 |
|
#### Host Configuration |
| 194 |
|
############################################################ |
| 195 |
|
|
| 196 |
< |
# The default filter for a new host |
| 197 |
< |
Host.filter=computingFilter; |
| 196 |
> |
# A host can use any filter. We'll set the default filter |
| 197 |
> |
# for all hosts to be 'filter1'. This can be a list. |
| 198 |
> |
Host.filter=filter1; |
| 199 |
|
|
| 200 |
< |
# The default update times for a new host |
| 201 |
< |
Host.UDPUpdateTime=10 |
| 112 |
< |
Host.TCPUpdateTime=60 |
| 113 |
< |
Host.AveragerUpdateTime=5 |
| 200 |
> |
# Hosts send data every UDPUpdateTime, in seconds. |
| 201 |
> |
Host.UDPUpdateTime=60 |
| 202 |
|
|
| 203 |
< |
# The services checks to run on a host |
| 204 |
< |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
| 203 |
> |
# How long a hosts config is valid for (a TTL effectively) |
| 204 |
> |
# after this time, in seconds, has passed a host should |
| 205 |
> |
# consider it's configuration invalid and check for a new |
| 206 |
> |
# configuration as soon as it can. |
| 207 |
> |
Host.ConfigTTL=3600 |
| 208 |
|
|
| 209 |
+ |
# We can run service checks on a host. The java package |
| 210 |
+ |
# which contains them is specified here. |
| 211 |
+ |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
| 212 |
|
|
| 213 |
|
|
| 214 |
|
############################################################ |
| 215 |
|
#### Monitor Configuration |
| 216 |
|
############################################################ |
| 217 |
|
|
| 218 |
< |
# the monitors to run |
| 219 |
< |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
| 220 |
< |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
| 221 |
< |
#Monitor.Plugins=CPU;WebFeeder; |
| 222 |
< |
#Monitor.Plugins= |
| 218 |
> |
# Monitors allow data to be watched for possible problems. |
| 219 |
> |
# This setting specifies which java package they're in. |
| 220 |
> |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
| 221 |
> |
# And which ones should be loaded. |
| 222 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
| 223 |
> |
Heartbeat;Queue;UserCount;WebFeeder;DiskIO;\ |
| 224 |
> |
NetIO;Paging; |
| 225 |
|
|
| 226 |
+ |
# Alerts timeout after a given time in seconds and go up |
| 227 |
+ |
# to the next level. These can be overridden for monitors |
| 228 |
+ |
# on an individual basis. |
| 229 |
+ |
Monitor.alertTimeout.NOTICE=60 |
| 230 |
+ |
Monitor.alertTimeout.WARNING=900 |
| 231 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
| 232 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
| 233 |
|
|
| 234 |
< |
## CPU monitor configuration |
| 235 |
< |
# threshold values |
| 236 |
< |
# |
| 237 |
< |
# note: if the UPPER threshold is broken, |
| 238 |
< |
# the alertTimeout values are halved. |
| 239 |
< |
# This is to escalate the alert quicker. |
| 234 |
> |
## Threshold values |
| 235 |
> |
# |
| 236 |
> |
# Here we specify the threshold for each monitor. When |
| 237 |
> |
# a threshold is broken an alert is raised. If the |
| 238 |
> |
# UPPER threshold is broken the alertTimeout values |
| 239 |
> |
# given above are halved to make the alert escalate |
| 240 |
> |
# quicker. |
| 241 |
> |
|
| 242 |
> |
# CPU monitor threshold values |
| 243 |
|
Monitor.CPU.threshold.LOWER=90 |
| 244 |
< |
Monitor.CPU.threshold.UPPER=99 |
| 244 |
> |
Monitor.CPU.threshold.UPPER=95 |
| 245 |
|
|
| 246 |
< |
# timings of the alerts (in seconds) |
| 247 |
< |
Monitor.CPU.alertTimeout.NOTICE=60 |
| 248 |
< |
Monitor.CPU.alertTimeout.WARNING=900 |
| 143 |
< |
Monitor.CPU.alertTimeout.CAUTION=1800 |
| 144 |
< |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
| 246 |
> |
# Load monitor threshold values |
| 247 |
> |
Monitor.Load.threshold.LOWER=10.0 |
| 248 |
> |
Monitor.Load.threshold.UPPER=20.0 |
| 249 |
|
|
| 250 |
+ |
# Paging monitor threshold values |
| 251 |
+ |
Monitor.Paging.threshold.LOWER=1000 |
| 252 |
+ |
Monitor.Paging.threshold.UPPER=5000 |
| 253 |
|
|
| 254 |
< |
## Memory monitor configuration |
| 255 |
< |
# threshold values |
| 256 |
< |
# |
| 257 |
< |
# note: if the UPPER threshold is broken, |
| 258 |
< |
# the alertTimeout values are halved. |
| 152 |
< |
# This is to escalate the alert quicker. |
| 254 |
> |
# Process Count threshold values |
| 255 |
> |
Monitor.Process.threshold.LOWER=500 |
| 256 |
> |
Monitor.Process.threshold.UPPER=1000 |
| 257 |
> |
|
| 258 |
> |
# Memory monitor threshold values |
| 259 |
|
Monitor.Memory.threshold.LOWER=80 |
| 260 |
|
Monitor.Memory.threshold.UPPER=90 |
| 261 |
+ |
# Whether to include 'cache' in the 'free' value |
| 262 |
+ |
# (1 is true, anything else is false) |
| 263 |
+ |
Monitor.Memory.useCacheAsFree=1 |
| 264 |
|
|
| 265 |
< |
# timings of the alerts (in seconds) |
| 157 |
< |
Monitor.Memory.alertTimeout.NOTICE=60 |
| 158 |
< |
Monitor.Memory.alertTimeout.WARNING=900 |
| 159 |
< |
Monitor.Memory.alertTimeout.CAUTION=1800 |
| 160 |
< |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
| 161 |
< |
|
| 162 |
< |
|
| 163 |
< |
## Swap monitor configuration |
| 164 |
< |
# threshold values |
| 165 |
< |
# |
| 166 |
< |
# note: if the UPPER threshold is broken, |
| 167 |
< |
# the alertTimeout values are halved. |
| 168 |
< |
# This is to escalate the alert quicker. |
| 265 |
> |
# Swap monitor threshold values |
| 266 |
|
Monitor.Swap.threshold.LOWER=80 |
| 267 |
|
Monitor.Swap.threshold.UPPER=90 |
| 268 |
|
|
| 269 |
< |
# timings of the alerts (in seconds) |
| 270 |
< |
Monitor.Swap.alertTimeout.NOTICE=60 |
| 271 |
< |
Monitor.Swap.alertTimeout.WARNING=900 |
| 175 |
< |
Monitor.Swap.alertTimeout.CAUTION=1800 |
| 176 |
< |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
| 269 |
> |
# UserCount monitor threshold values |
| 270 |
> |
Monitor.UserCount.threshold.LOWER=100 |
| 271 |
> |
Monitor.UserCount.threshold.UPPER=200 |
| 272 |
|
|
| 273 |
< |
|
| 179 |
< |
## Disk monitor configuration |
| 180 |
< |
# threshold values |
| 181 |
< |
# |
| 182 |
< |
# note: if the UPPER threshold is broken, |
| 183 |
< |
# the alertTimeout values are halved. |
| 184 |
< |
# This is to escalate the alert quicker. |
| 273 |
> |
# Disk monitor threshold values |
| 274 |
|
Monitor.Disk.threshold.LOWER=90 |
| 275 |
|
Monitor.Disk.threshold.UPPER=95 |
| 276 |
+ |
Monitor.DiskInode.threshold.LOWER=90 |
| 277 |
+ |
Monitor.DiskInode.threshold.UPPER=95 |
| 278 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
| 279 |
+ |
# where PERCENTAGE is a percentage of disk in use |
| 280 |
+ |
# and VALUE is an absolute value of space free |
| 281 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
| 282 |
+ |
Monitor.DiskInode.thresholdMeasure=PERCENTAGE |
| 283 |
|
|
| 284 |
< |
# timings of the alerts (in seconds) |
| 285 |
< |
Monitor.Disk.alertTimeout.NOTICE=60 |
| 286 |
< |
Monitor.Disk.alertTimeout.WARNING=900 |
| 287 |
< |
Monitor.Disk.alertTimeout.CAUTION=1800 |
| 288 |
< |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
| 284 |
> |
# DiskIO monitor threshold values (in bytes) |
| 285 |
> |
Monitor.DiskIO.rbytes.threshold.LOWER=10000000 |
| 286 |
> |
Monitor.DiskIO.rbytes.threshold.UPPER=50000000 |
| 287 |
> |
Monitor.DiskIO.wbytes.threshold.LOWER=10000000 |
| 288 |
> |
Monitor.DiskIO.wbytes.threshold.UPPER=50000000 |
| 289 |
|
|
| 290 |
+ |
# NetIO monitor threshold values (in bytes) |
| 291 |
+ |
Monitor.NetIO.rxbytes.threshold.LOWER=10000000 |
| 292 |
+ |
Monitor.NetIO.rxbytes.threshold.UPPER=50000000 |
| 293 |
+ |
Monitor.NetIO.txbytes.threshold.LOWER=10000000 |
| 294 |
+ |
Monitor.NetIO.txbytes.threshold.UPPER=50000000 |
| 295 |
|
|
| 296 |
< |
## Services monitor configuration |
| 297 |
< |
# threshold values |
| 296 |
> |
# Queue monitor threshold values |
| 297 |
> |
Monitor.Queue.threshold.LOWER=50 |
| 298 |
> |
Monitor.Queue.threshold.UPPER=80 |
| 299 |
> |
# Thresholds given are PERCENTAGE or VALUE |
| 300 |
> |
# where PERCENTAGE is a percentage of the queue in use |
| 301 |
> |
# and VALUE is an absolute value of free space |
| 302 |
> |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
| 303 |
> |
|
| 304 |
> |
# Services monitor threshold values |
| 305 |
|
# |
| 306 |
|
# THE SERVICES MONITOR USES A HACK |
| 307 |
|
# WHEREBY IT USES THE SERVICE STATUS |
| 308 |
< |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
| 308 |
> |
# AS THE THRESHOLD LEVEL. THIS SHOULD |
| 309 |
|
# BE LOOKED AT! |
| 310 |
|
# |
| 311 |
< |
# note: if the UPPER threshold is broken, |
| 312 |
< |
# the alertTimeout values are halved. |
| 205 |
< |
# This is to escalate the alert quicker. |
| 206 |
< |
#Monitor.Services.threshold.LOWER=120 |
| 207 |
< |
#Monitor.Services.threshold.LOWER=300 |
| 208 |
< |
|
| 209 |
< |
# timings of the alerts (in seconds) |
| 210 |
< |
Monitor.Services.alertTimeout.NOTICE=60 |
| 211 |
< |
Monitor.Services.alertTimeout.WARNING=900 |
| 212 |
< |
Monitor.Services.alertTimeout.CAUTION=1800 |
| 213 |
< |
Monitor.Services.alertTimeout.CRITICAL=3600 |
| 214 |
< |
|
| 215 |
< |
# Make sure we shut up eventually |
| 311 |
> |
# how many times we should be at the highest level before |
| 312 |
> |
# we go to a FINAL alert |
| 313 |
|
Monitor.Services.reachFINALcount=5 |
| 314 |
|
|
| 315 |
< |
|
| 219 |
< |
## Heartbeat monitor configuration |
| 220 |
< |
# threshold values |
| 221 |
< |
# |
| 222 |
< |
# note: if the UPPER threshold is broken, |
| 223 |
< |
# the alertTimeout values are halved. |
| 224 |
< |
# This is to escalate the alert quicker. |
| 225 |
< |
Monitor.Heartbeat.checkPeriod=50 |
| 315 |
> |
# Heartbeat threshold values |
| 316 |
|
# these are values in seconds from when the heartbeat |
| 317 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
| 318 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
| 318 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
| 319 |
|
Monitor.Heartbeat.threshold.UPPER=300 |
| 320 |
< |
|
| 321 |
< |
# timings of the alerts (in seconds) |
| 322 |
< |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
| 323 |
< |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
| 234 |
< |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
| 235 |
< |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
| 236 |
< |
|
| 237 |
< |
# this means it will reach a FINAL level, |
| 238 |
< |
# and thus the host will be removed from the monitor list, |
| 239 |
< |
# if the highest level alert is reached and occours this |
| 240 |
< |
# number of times. |
| 241 |
< |
# |
| 242 |
< |
# int this setup, that means 5 CRITICAL alerts would occour |
| 243 |
< |
# on a Heartbeat before reaching FINAL. |
| 244 |
< |
# If this value is wrong or not present, FINAL is never reached |
| 245 |
< |
# |
| 320 |
> |
# this is how often we will run a "check" of heartbeats |
| 321 |
> |
Monitor.Heartbeat.checkPeriod=50 |
| 322 |
> |
# how many times we should be at the highest level before |
| 323 |
> |
# we go to a FINAL alert |
| 324 |
|
Monitor.Heartbeat.reachFINALcount=5 |
| 325 |
+ |
# list of hosts we expect to have at startup |
| 326 |
+ |
# this ensures we notice hosts that aren't running, not |
| 327 |
+ |
# just those that have gone down recently. |
| 328 |
+ |
#Monitor.Heartbeat.initialHosts=importantserver.example.com;myserver.example.com |
| 329 |
|
|
| 330 |
+ |
|
| 331 |
|
############################################################ |
| 332 |
|
#### Alerter Configuration |
| 333 |
|
############################################################ |
| 334 |
< |
# The following var's are understood by ALL alerters for messages |
| 334 |
> |
# The following variables are understood by ALL alerters |
| 335 |
> |
# for messages. They will be substituted for their |
| 336 |
> |
# appropriate value. |
| 337 |
|
# |
| 338 |
|
# %level% - the alert level (eg, WARNING) |
| 339 |
|
# %threshold% - the threshold broken (eg, LOWER) |
| 346 |
|
# %timeOfFirstAlert% - the time the first alert was sent |
| 347 |
|
# |
| 348 |
|
|
| 349 |
< |
# alerters to run |
| 350 |
< |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
| 351 |
< |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
| 352 |
< |
Alerter.Plugins=IRC;WebFeeder; |
| 353 |
< |
#Alerter.Plugins=WebFeeder; |
| 354 |
< |
#Alerter.Plugins= |
| 349 |
> |
# The java package containing the alerters |
| 350 |
> |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
| 351 |
> |
# And the names of the ones to activate |
| 352 |
> |
# You might want to turn them all on, but we only activate |
| 353 |
> |
# two basic ones by default. |
| 354 |
> |
# Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
| 355 |
> |
Alerter.Plugins=WebFeeder;Logging; |
| 356 |
|
|
| 357 |
< |
# EMail alerter configuration |
| 357 |
> |
# Configuration for the EMail alerter |
| 358 |
> |
# The level alerts have to bypass to be e-mailed out |
| 359 |
|
Alerter.EMail.level = WARNING |
| 360 |
< |
Alerter.EMail.destList = dev@i-scream.org.uk |
| 361 |
< |
Alerter.EMail.sender = dev@i-scream.org.uk |
| 362 |
< |
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
| 360 |
> |
# A list of people to send alerts to |
| 361 |
> |
Alerter.EMail.destList = me@example.com |
| 362 |
> |
# The sender of the e-mail |
| 363 |
> |
Alerter.EMail.sender = me@example.com |
| 364 |
> |
# The SMTP server to send alerts to |
| 365 |
> |
Alerter.EMail.smtpServer = smtp.example.com |
| 366 |
> |
# The subject line of the e-mail |
| 367 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
| 368 |
+ |
# The message in the e-mail |
| 369 |
|
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%. |
| 370 |
|
|
| 371 |
< |
|
| 372 |
< |
# IRC alerter configuration |
| 371 |
> |
# Configuration for the IRC alerter |
| 372 |
> |
# The level alerts have to bypass to be sent |
| 373 |
|
Alerter.IRC.level = OK |
| 374 |
< |
Alerter.IRC.IRCServer = killigrew.ukc.ac.uk |
| 374 |
> |
# The IRC server name |
| 375 |
> |
Alerter.IRC.IRCServer = irc.example.com |
| 376 |
> |
# and it's port |
| 377 |
|
Alerter.IRC.IRCPort = 6667 |
| 378 |
+ |
# A list of nicks to try and be |
| 379 |
|
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
| 380 |
+ |
# Username to be |
| 381 |
|
Alerter.IRC.user = i-scream |
| 382 |
< |
Alerter.IRC.comment = i-scream alerting bot |
| 382 |
> |
# Responses to CTCP prods |
| 383 |
> |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
| 384 |
> |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
| 385 |
> |
# Channel to join |
| 386 |
|
Alerter.IRC.channel = #i-scream |
| 387 |
+ |
# Message to use when sending an alert |
| 388 |
|
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
| 389 |
+ |
# How long to wait before reconnecting |
| 390 |
|
Alerter.IRC.reconnectDelay = 30 |
| 391 |
+ |
# Notice to send when starting up |
| 392 |
|
Alerter.IRC.startupNotice = i-scream alerting bot activated |
| 393 |
+ |
# Commands the bot will recognise |
| 394 |
|
Alerter.IRC.stopCommand = stop alerts |
| 395 |
|
Alerter.IRC.startCommand = start alerts |
| 396 |
|
Alerter.IRC.lastAlertCommand = last alert |
| 401 |
|
Alerter.IRC.timeSinceLastAlertCommand = time since last alert |
| 402 |
|
Alerter.IRC.versionCommand = version |
| 403 |
|
Alerter.IRC.helpCommand = help |
| 404 |
+ |
# Message to send when the bot is addressed and |
| 405 |
+ |
# doesn't understand the command |
| 406 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
| 407 |
|
|
| 408 |
+ |
# Configuration for the Logging Alerter |
| 409 |
+ |
# This alerter writes alerts to the i-scream logfile. |
| 410 |
+ |
# The level alerts have to bypass to be logged |
| 411 |
+ |
Alerter.Logging.level = WARNING |
| 412 |
+ |
# The message to use when logging the alert |
| 413 |
+ |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
| 414 |
+ |
|
| 415 |
+ |
|
| 416 |
|
############################################################ |
| 417 |
|
#### WebFeeder Configuration |
| 418 |
|
############################################################ |
| 419 |
|
|
| 420 |
< |
# Define these (one or both_ to turn on the WebFeeder's, |
| 421 |
< |
# comment it to turn them off |
| 420 |
> |
# The WebFeeder drops alerts and latest data in to a |
| 421 |
> |
# directory for the web interface to use. It is essentially |
| 422 |
> |
# the link between the web interface and the server. |
| 423 |
> |
|
| 424 |
> |
# Set these to something to tell the WebFeeder to drop |
| 425 |
> |
# latest data, alerts, or both. Comment themt o disable. |
| 426 |
|
WebFeeder.latestActive = true |
| 427 |
|
WebFeeder.alertActive = true |
| 428 |
|
|
| 429 |
< |
# Only pass on alerts past this level |
| 430 |
< |
WebFeeder.alertLevel = OK |
| 429 |
> |
# We can make the WebFeeder only drop alerts that go |
| 430 |
> |
# past a certain level. The default is "OK", which makes |
| 431 |
> |
# all alerts get passed on. |
| 432 |
> |
Alerter.WebFeeder.level = OK |
| 433 |
|
|
| 434 |
< |
# Check period in seconds (for cleaning stale/old alerts) |
| 434 |
> |
# The WebFeeder cleans out old and stale alerts when it |
| 435 |
> |
# performs a check. This setting is the period, in seconds, |
| 436 |
> |
# at which a check happens. |
| 437 |
|
WebFeeder.checkPeriod = 120 |
| 438 |
|
|
| 439 |
|
# Delete alerts older than this, in seconds. |
| 319 |
– |
# Files are only check every WebFeeder.checkPeriod seconds. |
| 440 |
|
WebFeeder.alertDeleteOlderThan = 300 |
| 441 |
|
|
| 442 |
< |
# Root Path |
| 443 |
< |
WebFeeder.rootPath = /usr/local/proj/co600_10/webroot |
| 442 |
> |
# Data will be dropped to a subdirectory (specified |
| 443 |
> |
# below) of this directory. |
| 444 |
> |
WebFeeder.rootPath = /web/i-scream |
| 445 |
|
|
| 446 |
< |
# Latest Data |
| 446 |
> |
# SubDir is the directory below rootPath which latest |
| 447 |
> |
# data will be placed in. Below that a directory will |
| 448 |
> |
# be created with the machine name, and a file named |
| 449 |
> |
# FileName (specified here) will be created containg |
| 450 |
> |
# the data. |
| 451 |
|
WebFeeder.latestSubDir = latest |
| 452 |
|
WebFeeder.latestFileName = latest_data |
| 453 |
|
|
| 454 |
< |
# Alert Data |
| 454 |
> |
# As above, but for the alerts. |
| 455 |
|
WebFeeder.alertSubDir = alert |
| 456 |
|
WebFeeder.alertFileName = alert_data |
| 457 |
|
|
| 333 |
– |
############################################################ |
| 458 |
|
|
| 459 |
+ |
############################################################ |
