69 |
|
Filter.TCPListenPort=4589 |
70 |
|
|
71 |
|
# Plugin Information |
72 |
< |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
72 |
> |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
73 |
|
Filter.Plugins=TypeChecker;EnforceEssentialData |
74 |
|
|
75 |
|
# The name for the root filter |
78 |
|
# The default parent filter (should almost always be the same as Filter.rootFilter) |
79 |
|
Filter.parentFilter=root |
80 |
|
|
81 |
+ |
# The input methods to activate |
82 |
+ |
# (comment or set to 0 to disable) |
83 |
+ |
Filter.ActivateTCPReader=1 |
84 |
+ |
Filter.ActivateUDPReader=1 |
85 |
+ |
Filter.ActivateCORBAReader=1 |
86 |
|
|
87 |
+ |
# Access control list for the TCP and UDP inputs |
88 |
+ |
Filter.TCPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
89 |
+ |
Filter.UDPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
90 |
|
|
91 |
+ |
|
92 |
+ |
|
93 |
|
############################################################ |
94 |
|
#### Root filter interfaces configuration |
95 |
|
############################################################ |
107 |
|
|
108 |
|
# The port for the client interface to listen on |
109 |
|
ClientInterface.listenPort=4510 |
110 |
+ |
# The name for the client interface |
111 |
+ |
ClientInterface.name=realtimeclients |
112 |
|
|
113 |
|
|
114 |
|
|
115 |
|
############################################################ |
116 |
+ |
#### Database interface configuration |
117 |
+ |
############################################################ |
118 |
+ |
|
119 |
+ |
# The name for the Database interface |
120 |
+ |
DBInterface.name=database |
121 |
+ |
|
122 |
+ |
|
123 |
+ |
|
124 |
+ |
############################################################ |
125 |
|
#### Host Configuration |
126 |
|
############################################################ |
127 |
|
|
131 |
|
# The default update times for a new host |
132 |
|
Host.UDPUpdateTime=10 |
133 |
|
Host.TCPUpdateTime=60 |
113 |
– |
Host.AveragerUpdateTime=5 |
134 |
|
|
135 |
|
# The services checks to run on a host |
136 |
< |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
136 |
> |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
137 |
|
|
138 |
|
|
139 |
|
|
141 |
|
#### Monitor Configuration |
142 |
|
############################################################ |
143 |
|
|
144 |
< |
# the monitors to run |
145 |
< |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
146 |
< |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
147 |
< |
#Monitor.Plugins=CPU;WebFeeder; |
128 |
< |
#Monitor.Plugins= |
144 |
> |
## The monitors to run |
145 |
> |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
146 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
147 |
> |
Heartbeat;Queue;UserCount;WebFeeder; |
148 |
|
|
149 |
+ |
## Default alert timeouts |
150 |
+ |
# these can be override on a per-monitor basis |
151 |
+ |
# timings of the alerts (in seconds) |
152 |
+ |
Monitor.alertTimeout.NOTICE=60 |
153 |
+ |
Monitor.alertTimeout.WARNING=900 |
154 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
155 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
156 |
|
|
157 |
< |
## CPU monitor configuration |
132 |
< |
# threshold values |
157 |
> |
## Threshold values |
158 |
|
# |
159 |
|
# note: if the UPPER threshold is broken, |
160 |
|
# the alertTimeout values are halved. |
161 |
|
# This is to escalate the alert quicker. |
162 |
+ |
# |
163 |
+ |
|
164 |
+ |
# CPU monitor threshold values |
165 |
|
Monitor.CPU.threshold.LOWER=90 |
166 |
|
Monitor.CPU.threshold.UPPER=99 |
167 |
|
|
140 |
– |
# timings of the alerts (in seconds) |
141 |
– |
Monitor.CPU.alertTimeout.NOTICE=60 |
142 |
– |
Monitor.CPU.alertTimeout.WARNING=900 |
143 |
– |
Monitor.CPU.alertTimeout.CAUTION=1800 |
144 |
– |
Monitor.CPU.alertTimeout.CRITICAL=3600 |
168 |
|
|
169 |
< |
|
147 |
< |
## Load monitor configuration |
148 |
< |
# threshold values |
149 |
< |
# |
150 |
< |
# note: if the UPPER threshold is broken, |
151 |
< |
# the alertTimeout values are halved. |
152 |
< |
# This is to escalate the alert quicker. |
169 |
> |
# Load monitor threshold values |
170 |
|
Monitor.Load.threshold.LOWER=10.0 |
171 |
|
Monitor.Load.threshold.UPPER=20.0 |
172 |
|
|
156 |
– |
# timings of the alerts (in seconds) |
157 |
– |
Monitor.Load.alertTimeout.NOTICE=60 |
158 |
– |
Monitor.Load.alertTimeout.WARNING=900 |
159 |
– |
Monitor.Load.alertTimeout.CAUTION=1800 |
160 |
– |
Monitor.Load.alertTimeout.CRITICAL=3600 |
173 |
|
|
174 |
< |
|
163 |
< |
## Process Count 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. |
174 |
> |
# Process Count threshold values |
175 |
|
Monitor.Process.threshold.LOWER=1000 |
176 |
|
Monitor.Process.threshold.UPPER=1500 |
177 |
|
|
172 |
– |
# timings of the alerts (in seconds) |
173 |
– |
Monitor.Process.alertTimeout.NOTICE=60 |
174 |
– |
Monitor.Process.alertTimeout.WARNING=900 |
175 |
– |
Monitor.Process.alertTimeout.CAUTION=1800 |
176 |
– |
Monitor.Process.alertTimeout.CRITICAL=3600 |
178 |
|
|
179 |
< |
|
179 |
< |
## Memory 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. |
179 |
> |
# Memory monitor threshold values |
180 |
|
Monitor.Memory.threshold.LOWER=80 |
181 |
|
Monitor.Memory.threshold.UPPER=90 |
182 |
|
|
188 |
– |
# timings of the alerts (in seconds) |
189 |
– |
Monitor.Memory.alertTimeout.NOTICE=60 |
190 |
– |
Monitor.Memory.alertTimeout.WARNING=900 |
191 |
– |
Monitor.Memory.alertTimeout.CAUTION=1800 |
192 |
– |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
183 |
|
|
184 |
< |
|
195 |
< |
## Swap monitor configuration |
196 |
< |
# threshold values |
197 |
< |
# |
198 |
< |
# note: if the UPPER threshold is broken, |
199 |
< |
# the alertTimeout values are halved. |
200 |
< |
# This is to escalate the alert quicker. |
184 |
> |
# Swap monitor threshold values |
185 |
|
Monitor.Swap.threshold.LOWER=80 |
186 |
|
Monitor.Swap.threshold.UPPER=90 |
187 |
|
|
204 |
– |
# timings of the alerts (in seconds) |
205 |
– |
Monitor.Swap.alertTimeout.NOTICE=60 |
206 |
– |
Monitor.Swap.alertTimeout.WARNING=900 |
207 |
– |
Monitor.Swap.alertTimeout.CAUTION=1800 |
208 |
– |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
188 |
|
|
189 |
+ |
# UserCount monitor threshold values |
190 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
191 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
192 |
|
|
193 |
< |
## Disk monitor configuration |
194 |
< |
# threshold values |
213 |
< |
# |
214 |
< |
# note: if the UPPER threshold is broken, |
215 |
< |
# the alertTimeout values are halved. |
216 |
< |
# This is to escalate the alert quicker. |
193 |
> |
|
194 |
> |
# Disk monitor threshold values |
195 |
|
Monitor.Disk.threshold.LOWER=90 |
196 |
|
Monitor.Disk.threshold.UPPER=95 |
197 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
198 |
+ |
# where PERCENTAGE is a percentage of disk in use |
199 |
+ |
# and VALUE is an absolute value of space free |
200 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
201 |
|
|
220 |
– |
# timings of the alerts (in seconds) |
221 |
– |
Monitor.Disk.alertTimeout.NOTICE=60 |
222 |
– |
Monitor.Disk.alertTimeout.WARNING=900 |
223 |
– |
Monitor.Disk.alertTimeout.CAUTION=1800 |
224 |
– |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
202 |
|
|
203 |
+ |
# Queue monitor threshold values |
204 |
+ |
Monitor.Queue.threshold.LOWER=50 |
205 |
+ |
Monitor.Queue.threshold.UPPER=80 |
206 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
207 |
+ |
# where PERCENTAGE is a percentage of disk in use |
208 |
+ |
# and VALUE is an absolute value of space free |
209 |
+ |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
210 |
|
|
211 |
< |
## Services monitor configuration |
212 |
< |
# threshold values |
211 |
> |
|
212 |
> |
# Services monitor threshold values |
213 |
|
# |
214 |
|
# THE SERVICES MONITOR USES A HACK |
215 |
|
# WHEREBY IT USES THE SERVICE STATUS |
216 |
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
217 |
|
# BE LOOKED AT! |
218 |
|
# |
219 |
< |
# note: if the UPPER threshold is broken, |
220 |
< |
# the alertTimeout values are halved. |
237 |
< |
# This is to escalate the alert quicker. |
238 |
< |
#Monitor.Services.threshold.LOWER=120 |
239 |
< |
#Monitor.Services.threshold.LOWER=300 |
240 |
< |
|
241 |
< |
# timings of the alerts (in seconds) |
242 |
< |
Monitor.Services.alertTimeout.NOTICE=60 |
243 |
< |
Monitor.Services.alertTimeout.WARNING=900 |
244 |
< |
Monitor.Services.alertTimeout.CAUTION=1800 |
245 |
< |
Monitor.Services.alertTimeout.CRITICAL=3600 |
246 |
< |
|
247 |
< |
# Make sure we shut up eventually |
219 |
> |
# how many times we should be at the highest level before |
220 |
> |
# we go to a FINAL alert |
221 |
|
Monitor.Services.reachFINALcount=5 |
222 |
|
|
223 |
|
|
224 |
< |
## Heartbeat monitor configuration |
252 |
< |
# threshold values |
253 |
< |
# |
254 |
< |
# note: if the UPPER threshold is broken, |
255 |
< |
# the alertTimeout values are halved. |
256 |
< |
# This is to escalate the alert quicker. |
257 |
< |
Monitor.Heartbeat.checkPeriod=50 |
224 |
> |
# Heartbeat threshold values |
225 |
|
# these are values in seconds from when the heartbeat |
226 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
227 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
227 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
228 |
|
Monitor.Heartbeat.threshold.UPPER=300 |
229 |
+ |
# this is how often we will run a "check" of heartbeats |
230 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
231 |
+ |
# how many times we should be at the highest level before |
232 |
+ |
# we go to a FINAL alert |
233 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
234 |
+ |
# list of hosts we expect to have at startup |
235 |
+ |
# this ensures we notice hosts that aren't running, not |
236 |
+ |
# just those that have gone down recently. |
237 |
+ |
Monitor.Heartbeat.initialHosts=raptor.ukc.ac.uk;myrtle.ukc.ac.uk;kestrel.ukc.ac.uk |
238 |
|
|
263 |
– |
# timings of the alerts (in seconds) |
264 |
– |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
265 |
– |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
266 |
– |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
267 |
– |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
239 |
|
|
269 |
– |
# this means it will reach a FINAL level, |
270 |
– |
# and thus the host will be removed from the monitor list, |
271 |
– |
# if the highest level alert is reached and occours this |
272 |
– |
# number of times. |
273 |
– |
# |
274 |
– |
# int this setup, that means 5 CRITICAL alerts would occour |
275 |
– |
# on a Heartbeat before reaching FINAL. |
276 |
– |
# If this value is wrong or not present, FINAL is never reached |
277 |
– |
# |
278 |
– |
Monitor.Heartbeat.reachFINALcount=5 |
240 |
|
|
241 |
|
############################################################ |
242 |
|
#### Alerter Configuration |
255 |
|
# |
256 |
|
|
257 |
|
# alerters to run |
258 |
< |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
259 |
< |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
299 |
< |
Alerter.Plugins=IRC;WebFeeder; |
300 |
< |
#Alerter.Plugins=WebFeeder; |
301 |
< |
#Alerter.Plugins= |
258 |
> |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
259 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
260 |
|
|
261 |
+ |
|
262 |
|
# EMail alerter configuration |
263 |
|
Alerter.EMail.level = WARNING |
264 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
274 |
|
Alerter.IRC.IRCPort = 6667 |
275 |
|
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
276 |
|
Alerter.IRC.user = i-scream |
277 |
< |
Alerter.IRC.comment = i-scream alerting bot |
277 |
> |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
278 |
> |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
279 |
|
Alerter.IRC.channel = #i-scream |
280 |
|
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
281 |
|
Alerter.IRC.reconnectDelay = 30 |
292 |
|
Alerter.IRC.helpCommand = help |
293 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
294 |
|
|
295 |
+ |
|
296 |
+ |
# Logging alerter configuration |
297 |
+ |
Alerter.Logging.level = WARNING |
298 |
+ |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
299 |
+ |
|
300 |
+ |
|
301 |
+ |
|
302 |
|
############################################################ |
303 |
|
#### WebFeeder Configuration |
304 |
|
############################################################ |
309 |
|
WebFeeder.alertActive = true |
310 |
|
|
311 |
|
# Only pass on alerts past this level |
312 |
< |
WebFeeder.alertLevel = OK |
312 |
> |
Alerter.WebFeeder.level = OK |
313 |
|
|
314 |
|
# Check period in seconds (for cleaning stale/old alerts) |
315 |
|
WebFeeder.checkPeriod = 120 |
329 |
|
WebFeeder.alertSubDir = alert |
330 |
|
WebFeeder.alertFileName = alert_data |
331 |
|
|
365 |
– |
############################################################ |
332 |
|
|
333 |
+ |
############################################################ |