| 94 |
|
############################################################ |
| 95 |
|
|
| 96 |
|
# The default filter for a new host |
| 97 |
< |
Host.filter=filter1 |
| 97 |
> |
Host.filter=filter1; |
| 98 |
|
|
| 99 |
|
# The default update times for a new host |
| 100 |
|
Host.UDPUpdateTime=10 |
| 103 |
|
|
| 104 |
|
# The services checks to run on a host |
| 105 |
|
Host.serviceChecksPackage=uk.ac.ukc.iscream.filter.plugins |
| 106 |
< |
Host.serviceChecks=HTTP;SMTP |
| 106 |
> |
Host.serviceChecks=HTTP;SMTP;POP3;SSH;POP3;IMAP |
| 107 |
|
|
| 108 |
|
|
| 109 |
|
|
| 113 |
|
|
| 114 |
|
# the monitors to run |
| 115 |
|
Monitor.PluginsPackage=uk.ac.ukc.iscream.client.monitors |
| 116 |
< |
Monitor.Plugins=CPU; |
| 116 |
> |
Monitor.Plugins=CPU;Memory;Swap;Heartbeat; |
| 117 |
|
|
| 118 |
< |
# CPU monitor configuration |
| 118 |
> |
|
| 119 |
> |
## CPU monitor configuration |
| 120 |
|
# threshold values |
| 121 |
|
# |
| 122 |
|
# note: if the UPPER threshold is broken, |
| 132 |
|
Monitor.CPU.alertTimeout.CRITICAL=3600 |
| 133 |
|
|
| 134 |
|
|
| 135 |
+ |
## Memory monitor configuration |
| 136 |
+ |
# threshold values |
| 137 |
+ |
# |
| 138 |
+ |
# note: if the UPPER threshold is broken, |
| 139 |
+ |
# the alertTimeout values are halved. |
| 140 |
+ |
# This is to escalate the alert quicker. |
| 141 |
+ |
Monitor.Memory.threshold.LOWER=80 |
| 142 |
+ |
Monitor.Memory.threshold.UPPER=90 |
| 143 |
|
|
| 144 |
+ |
# timings of the alerts (in seconds) |
| 145 |
+ |
Monitor.Memory.alertTimeout.NOTICE=60 |
| 146 |
+ |
Monitor.Memory.alertTimeout.WARNING=900 |
| 147 |
+ |
Monitor.Memory.alertTimeout.CAUTION=1800 |
| 148 |
+ |
Monitor.Memory.alertTimeout.CRITICAL=3600 |
| 149 |
+ |
|
| 150 |
+ |
|
| 151 |
+ |
## Swap monitor configuration |
| 152 |
+ |
# threshold values |
| 153 |
+ |
# |
| 154 |
+ |
# note: if the UPPER threshold is broken, |
| 155 |
+ |
# the alertTimeout values are halved. |
| 156 |
+ |
# This is to escalate the alert quicker. |
| 157 |
+ |
Monitor.Swap.threshold.LOWER=80 |
| 158 |
+ |
Monitor.Swap.threshold.UPPER=90 |
| 159 |
+ |
|
| 160 |
+ |
# timings of the alerts (in seconds) |
| 161 |
+ |
Monitor.Swap.alertTimeout.NOTICE=60 |
| 162 |
+ |
Monitor.Swap.alertTimeout.WARNING=900 |
| 163 |
+ |
Monitor.Swap.alertTimeout.CAUTION=1800 |
| 164 |
+ |
Monitor.Swap.alertTimeout.CRITICAL=3600 |
| 165 |
+ |
|
| 166 |
+ |
|
| 167 |
+ |
## Heartbeat monitor configuration |
| 168 |
+ |
# threshold values |
| 169 |
+ |
# |
| 170 |
+ |
# note: if the UPPER threshold is broken, |
| 171 |
+ |
# the alertTimeout values are halved. |
| 172 |
+ |
# This is to escalate the alert quicker. |
| 173 |
+ |
Monitor.Heartbeat.checkPeriod=50 |
| 174 |
+ |
# these are values in seconds from when the heartbeat |
| 175 |
+ |
# was *expected* to arrive (ie. last + hearbeat period) |
| 176 |
+ |
Monitor.Heartbeat.threshold.LOWER=120 |
| 177 |
+ |
Monitor.Heartbeat.threshold.LOWER=300 |
| 178 |
+ |
|
| 179 |
+ |
# timings of the alerts (in seconds) |
| 180 |
+ |
Monitor.Heartbeat.alertTimeout.NOTICE=60 |
| 181 |
+ |
Monitor.Heartbeat.alertTimeout.WARNING=900 |
| 182 |
+ |
Monitor.Heartbeat.alertTimeout.CAUTION=1800 |
| 183 |
+ |
Monitor.Heartbeat.alertTimeout.CRITICAL=3600 |
| 184 |
+ |
|
| 185 |
+ |
# this means it will reach a FINAL level, |
| 186 |
+ |
# and thus the host will be removed from the monitor list, |
| 187 |
+ |
# if the highest level alert is reached and occours this |
| 188 |
+ |
# number of times. |
| 189 |
+ |
# |
| 190 |
+ |
# int this setup, that means 5 CRITICAL alerts would occour |
| 191 |
+ |
# on a Heartbeat before reaching FINAL. |
| 192 |
+ |
# If this value is wrong or not present, FINAL is never reached |
| 193 |
+ |
# |
| 194 |
+ |
Monitor.Heartbeat.reachFINALcount=5 |
| 195 |
+ |
|
| 196 |
|
############################################################ |
| 197 |
|
#### Alerter Configuration |
| 198 |
|
############################################################ |
| 199 |
+ |
# The following var's are understood by ALL alerters for messages |
| 200 |
+ |
# |
| 201 |
+ |
# %level% - the alert level (eg, WARNING) |
| 202 |
+ |
# %threshold% - the threshold broken (eg, LOWER) |
| 203 |
+ |
# %source% - the source of the alert (eg, raptor.ukc.ac.uk) |
| 204 |
+ |
# %value% - the value reached (eg, 95) |
| 205 |
+ |
# %thresholdValue% - the value of the threshold broken (eg, 90) |
| 206 |
+ |
# %attributeName% - the attribute that has caused the alert (eg, CPU User) |
| 207 |
+ |
# %timeTillNextAlert% - the time the next alert will be sent out |
| 208 |
+ |
# %timeSinceFirstAlert% - the time elapsed since the first alert for this problem |
| 209 |
+ |
# %timeOfFirstAlert% - the time the first alert was sent |
| 210 |
+ |
# |
| 211 |
|
|
| 212 |
|
# alerters to run |
| 213 |
|
Alerter.PluginsPackage=uk.ac.ukc.iscream.client.alerters |
| 215 |
|
|
| 216 |
|
# EMail alerter configuration |
| 217 |
|
Alerter.EMail.level = CAUTION |
| 218 |
< |
Alerter.EMail.destList = dev@i-scream.org.uk |
| 218 |
> |
Alerter.EMail.defaultDestList = dev@i-scream.org.uk |
| 219 |
|
Alerter.EMail.sender = dev@i-scream.org.uk |
| 220 |
|
Alerter.EMail.smtpServer = mercury.ukc.ac.uk |
| 221 |
|
Alerter.EMail.subject = i-scream alert: %level% alert on %source% for %attributeName% |
