58 |
|
# The default port to listen for new host connections |
59 |
|
FilterManager.listenPort=4567 |
60 |
|
|
61 |
+ |
# Access control list |
62 |
+ |
FilterManager.ACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
63 |
|
|
64 |
|
|
65 |
+ |
|
66 |
|
############################################################ |
67 |
|
#### Filter configuration |
68 |
|
############################################################ |
72 |
|
Filter.TCPListenPort=4589 |
73 |
|
|
74 |
|
# Plugin Information |
75 |
< |
Filter.PluginsPackage=uk.org.iscream.filter.plugins |
75 |
> |
Filter.PluginsPackage=uk.org.iscream.cms.server.filter.plugins |
76 |
|
Filter.Plugins=TypeChecker;EnforceEssentialData |
77 |
|
|
78 |
|
# The name for the root filter |
81 |
|
# The default parent filter (should almost always be the same as Filter.rootFilter) |
82 |
|
Filter.parentFilter=root |
83 |
|
|
84 |
+ |
# The input methods to activate |
85 |
+ |
# (comment or set to 0 to disable) |
86 |
+ |
Filter.ActivateTCPReader=1 |
87 |
+ |
Filter.ActivateUDPReader=1 |
88 |
+ |
Filter.ActivateCORBAReader=1 |
89 |
|
|
90 |
+ |
# Access control list for the TCP and UDP inputs |
91 |
+ |
Filter.TCPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
92 |
+ |
Filter.UDPACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
93 |
|
|
94 |
+ |
|
95 |
+ |
|
96 |
|
############################################################ |
97 |
|
#### Root filter interfaces configuration |
98 |
|
############################################################ |
110 |
|
|
111 |
|
# The port for the client interface to listen on |
112 |
|
ClientInterface.listenPort=4510 |
113 |
+ |
# The name for the client interface |
114 |
+ |
ClientInterface.name=realtimeclients |
115 |
|
|
116 |
+ |
# Access Control List for TCP Clients |
117 |
+ |
ClientInterface.TCPControlChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
118 |
+ |
ClientInterface.TCPDataChannelACL=DEFAULT:DENY;*.ukc.ac.uk:ALLOW;129.12.*:ALLOW |
119 |
|
|
120 |
|
|
121 |
+ |
|
122 |
|
############################################################ |
123 |
+ |
#### Database interface configuration |
124 |
+ |
############################################################ |
125 |
+ |
|
126 |
+ |
# The name for the Database interface |
127 |
+ |
DBInterface.name=database |
128 |
+ |
|
129 |
+ |
|
130 |
+ |
|
131 |
+ |
############################################################ |
132 |
|
#### Host Configuration |
133 |
|
############################################################ |
134 |
|
|
138 |
|
# The default update times for a new host |
139 |
|
Host.UDPUpdateTime=10 |
140 |
|
Host.TCPUpdateTime=60 |
113 |
– |
Host.AveragerUpdateTime=5 |
141 |
|
|
142 |
|
# The services checks to run on a host |
143 |
< |
Host.serviceChecksPackage=uk.org.iscream.filter.plugins |
143 |
> |
Host.serviceChecksPackage=uk.org.iscream.cms.server.filter.plugins |
144 |
|
|
145 |
|
|
146 |
|
|
148 |
|
#### Monitor Configuration |
149 |
|
############################################################ |
150 |
|
|
151 |
< |
# the monitors to run |
152 |
< |
Monitor.PluginsPackage=uk.org.iscream.client.monitors |
153 |
< |
Monitor.Plugins=CPU;Disk;Memory;Swap;Services;Heartbeat;WebFeeder; |
154 |
< |
#Monitor.Plugins=CPU;WebFeeder; |
128 |
< |
#Monitor.Plugins= |
151 |
> |
## The monitors to run |
152 |
> |
Monitor.PluginsPackage=uk.org.iscream.cms.server.client.monitors |
153 |
> |
Monitor.Plugins=CPU;Load;Process;Disk;Memory;Swap;Services;\ |
154 |
> |
Heartbeat;Queue;UserCount;WebFeeder; |
155 |
|
|
156 |
+ |
## Default alert timeouts |
157 |
+ |
# these can be override on a per-monitor basis |
158 |
+ |
# timings of the alerts (in seconds) |
159 |
+ |
Monitor.alertTimeout.NOTICE=60 |
160 |
+ |
Monitor.alertTimeout.WARNING=900 |
161 |
+ |
Monitor.alertTimeout.CAUTION=1800 |
162 |
+ |
Monitor.alertTimeout.CRITICAL=3600 |
163 |
|
|
164 |
< |
## CPU monitor configuration |
132 |
< |
# threshold values |
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. |
169 |
+ |
# |
170 |
+ |
|
171 |
+ |
# CPU monitor threshold values |
172 |
|
Monitor.CPU.threshold.LOWER=90 |
173 |
|
Monitor.CPU.threshold.UPPER=99 |
174 |
|
|
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 |
175 |
|
|
176 |
+ |
# Load monitor threshold values |
177 |
+ |
Monitor.Load.threshold.LOWER=10.0 |
178 |
+ |
Monitor.Load.threshold.UPPER=20.0 |
179 |
|
|
180 |
< |
## Memory monitor configuration |
181 |
< |
# threshold values |
182 |
< |
# |
183 |
< |
# note: if the UPPER threshold is broken, |
184 |
< |
# the alertTimeout values are halved. |
185 |
< |
# This is to escalate the alert quicker. |
180 |
> |
|
181 |
> |
# Process Count threshold values |
182 |
> |
Monitor.Process.threshold.LOWER=1000 |
183 |
> |
Monitor.Process.threshold.UPPER=1500 |
184 |
> |
|
185 |
> |
|
186 |
> |
# Memory monitor threshold values |
187 |
|
Monitor.Memory.threshold.LOWER=80 |
188 |
|
Monitor.Memory.threshold.UPPER=90 |
189 |
|
|
156 |
– |
# 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 |
190 |
|
|
191 |
< |
|
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. |
191 |
> |
# Swap monitor threshold values |
192 |
|
Monitor.Swap.threshold.LOWER=80 |
193 |
|
Monitor.Swap.threshold.UPPER=90 |
194 |
|
|
172 |
– |
# timings of the alerts (in seconds) |
173 |
– |
Monitor.Swap.alertTimeout.NOTICE=60 |
174 |
– |
Monitor.Swap.alertTimeout.WARNING=900 |
175 |
– |
Monitor.Swap.alertTimeout.CAUTION=1800 |
176 |
– |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
195 |
|
|
196 |
+ |
# UserCount monitor threshold values |
197 |
+ |
Monitor.UserCount.threshold.LOWER=100 |
198 |
+ |
Monitor.UserCount.threshold.UPPER=200 |
199 |
|
|
200 |
< |
## Disk monitor configuration |
201 |
< |
# 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. |
200 |
> |
|
201 |
> |
# Disk monitor threshold values |
202 |
|
Monitor.Disk.threshold.LOWER=90 |
203 |
|
Monitor.Disk.threshold.UPPER=95 |
204 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
205 |
+ |
# where PERCENTAGE is a percentage of disk in use |
206 |
+ |
# and VALUE is an absolute value of space free |
207 |
+ |
Monitor.Disk.thresholdMeasure=PERCENTAGE |
208 |
|
|
188 |
– |
# timings of the alerts (in seconds) |
189 |
– |
Monitor.Disk.alertTimeout.NOTICE=60 |
190 |
– |
Monitor.Disk.alertTimeout.WARNING=900 |
191 |
– |
Monitor.Disk.alertTimeout.CAUTION=1800 |
192 |
– |
Monitor.Disk.alertTimeout.CRITICAL=3600 |
209 |
|
|
210 |
+ |
# Queue monitor threshold values |
211 |
+ |
Monitor.Queue.threshold.LOWER=50 |
212 |
+ |
Monitor.Queue.threshold.UPPER=80 |
213 |
+ |
# Thresholds given are PERCENTAGE or VALUE |
214 |
+ |
# where PERCENTAGE is a percentage of disk in use |
215 |
+ |
# and VALUE is an absolute value of space free |
216 |
+ |
Monitor.Queue.thresholdMeasure=PERCENTAGE |
217 |
|
|
218 |
< |
## Services monitor configuration |
219 |
< |
# threshold values |
218 |
> |
|
219 |
> |
# Services monitor threshold values |
220 |
|
# |
221 |
|
# THE SERVICES MONITOR USES A HACK |
222 |
|
# WHEREBY IT USES THE SERVICE STATUS |
223 |
|
# AS THE THRESHOLD LEVEL. THIS SHOULD |
224 |
|
# BE LOOKED AT! |
225 |
|
# |
226 |
< |
# note: if the UPPER threshold is broken, |
227 |
< |
# 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 |
226 |
> |
# how many times we should be at the highest level before |
227 |
> |
# we go to a FINAL alert |
228 |
|
Monitor.Services.reachFINALcount=5 |
229 |
|
|
230 |
|
|
231 |
< |
## 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 |
231 |
> |
# Heartbeat threshold values |
232 |
|
# these are values in seconds from when the heartbeat |
233 |
|
# was *expected* to arrive (ie. last + hearbeat period) |
234 |
< |
Monitor.Heartbeat.threshold.LOWER=120 |
234 |
> |
Monitor.Heartbeat.threshold.LOWER=180 |
235 |
|
Monitor.Heartbeat.threshold.UPPER=300 |
236 |
+ |
# this is how often we will run a "check" of heartbeats |
237 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
238 |
+ |
# how many times we should be at the highest level before |
239 |
+ |
# we go to a FINAL alert |
240 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
241 |
+ |
# list of hosts we expect to have at startup |
242 |
+ |
# this ensures we notice hosts that aren't running, not |
243 |
+ |
# just those that have gone down recently. |
244 |
+ |
Monitor.Heartbeat.initialHosts=raptor.ukc.ac.uk;myrtle.ukc.ac.uk;kestrel.ukc.ac.uk |
245 |
|
|
231 |
– |
# timings of the alerts (in seconds) |
232 |
– |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
233 |
– |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
234 |
– |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
235 |
– |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
246 |
|
|
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 |
– |
# |
246 |
– |
Monitor.Heartbeat.reachFINALcount=5 |
247 |
|
|
248 |
|
############################################################ |
249 |
|
#### Alerter Configuration |
262 |
|
# |
263 |
|
|
264 |
|
# alerters to run |
265 |
< |
Alerter.PluginsPackage=uk.org.iscream.client.alerters |
266 |
< |
#Alerter.Plugins=EMail;IRC;WebFeeder; |
267 |
< |
Alerter.Plugins=IRC;WebFeeder; |
268 |
< |
#Alerter.Plugins=WebFeeder; |
269 |
< |
#Alerter.Plugins= |
265 |
> |
Alerter.PluginsPackage=uk.org.iscream.cms.server.client.alerters |
266 |
> |
Alerter.Plugins=EMail;IRC;WebFeeder;Logging; |
267 |
|
|
268 |
+ |
|
269 |
|
# EMail alerter configuration |
270 |
|
Alerter.EMail.level = WARNING |
271 |
|
Alerter.EMail.destList = dev@i-scream.org.uk |
281 |
|
Alerter.IRC.IRCPort = 6667 |
282 |
|
Alerter.IRC.nickList = iscreamBot;_iscreamBot;i-screamBot |
283 |
|
Alerter.IRC.user = i-scream |
284 |
< |
Alerter.IRC.comment = i-scream alerting bot |
284 |
> |
Alerter.IRC.comment = i-scream alerting bot (based on PircBot) |
285 |
> |
Alerter.IRC.finger = i-scream alerting bot (based on PircBot) |
286 |
|
Alerter.IRC.channel = #i-scream |
287 |
|
Alerter.IRC.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% - time till next alert (should one occur), %timeTillNextAlert% |
288 |
|
Alerter.IRC.reconnectDelay = 30 |
299 |
|
Alerter.IRC.helpCommand = help |
300 |
|
Alerter.IRC.rejectMessage = sorry, I don't understand your request |
301 |
|
|
302 |
+ |
|
303 |
+ |
# Logging alerter configuration |
304 |
+ |
Alerter.Logging.level = WARNING |
305 |
+ |
Alerter.Logging.message = %level%: %attributeName% on %source% has passed %threshold%(%thresholdValue%) threshold with %value% |
306 |
+ |
|
307 |
+ |
|
308 |
+ |
|
309 |
|
############################################################ |
310 |
|
#### WebFeeder Configuration |
311 |
|
############################################################ |
315 |
|
WebFeeder.latestActive = true |
316 |
|
WebFeeder.alertActive = true |
317 |
|
|
318 |
+ |
# Only pass on alerts past this level |
319 |
+ |
Alerter.WebFeeder.level = OK |
320 |
+ |
|
321 |
|
# Check period in seconds (for cleaning stale/old alerts) |
322 |
|
WebFeeder.checkPeriod = 120 |
323 |
|
|
336 |
|
WebFeeder.alertSubDir = alert |
337 |
|
WebFeeder.alertFileName = alert_data |
338 |
|
|
330 |
– |
############################################################ |
339 |
|
|
340 |
+ |
############################################################ |