nt-guide - The Windows NT Guide to MRTG 2.9.17
Installing MRTG on an Windows NT or Windows 2000 box is not quite as click and point as some might want it to be. But then again it is not all that difficult if you follow the instructions below.
To get MRTG to work on Windows NT you need the following:
I suggest you do the following from the machine that will be running MRTG, which, in this case is also a web server. All examples are for doing things to a LOCAL machine.
C:\Perl\bin;%SystemRoot%\system32;%SystemRoot%;...
You can manually check this by going to [Control Panel]->[System]->[Environment]
To see if everything is installed properly you can open a Command Shell and go into c:\mrtg-2.9.17\bin. Type:
perl mrtg
This should give you a friendly error message complaining about the missing mrtg configuration file. Now, you have successfully installed mrtg and perl.
Now it is time to walk create a configuration for mrtg. But before we begin you need to know a few things, take an opportunity to gather the following information:
For the rest of this document we will be using device 10.10.10.1 ( a CISCO Catalyst 5000) with Community string public. We are interested in monitoring traffic, and the CPU Load. Let's begin.
The first thing we do in setting up mrtg is by making a default config file. Get to a cmd prompt and change to the c:\mrtg-2.9.17\bin directory. Type the following command:
perl cfgmaker public@10.10.10.1 --global "WorkDir: c:\www\mrtg" --output mrtg.cfg
This creates an initial MRTG config file for you. Note that in this file all interfaces of your router will be stored by number. Unfortunately these numbers are likely to change when ever you reconfigure your router. So in order to work around this you can get cfgmaker to produce a configuration which is based on Ip numbers, or even Interface Descriptions. Check the cfgmaker manpage
If you get an error message complaining about no such name or no response, your community name is probably wrong.
Now, lets take a look at the mrtg.cfg file that was created.
In Perl a #
is a comment, synonymous with REM
in DOS.
Add the following to the top of the mrtg.cfg file:
WorkDir: D:\InetPub\wwwroot\MRTG
This is where the web pages are created, usually a web root.
###################################################################### # Description: LCP SUWGB # Contact: Administrator # System Name: LC-Bridge # Location: Here #.....................................................................
TargetDevice's IP Address:Interface Number:Community:IP Address
Target[10.10.10.1.1]: 1:public@10.10.10.1
This is the interface speed (Default is 10 megabits; for 100Mbit devices use 12500000 and so on...)
MaxBytes[10.10.10.1.1]: 1250000
Title[10.10.10.1.1]: LC-Bridge (sample.device): ether0
This section determines how the web page headers will look
PageTop[10.10.10.1.1]: <H1>Traffic Analysis for ether0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ether0(1)</TD></TR> <TR><TD>IP:</TD><TD>sample.device(10.10.10.1)</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
Target[10.10.10.1.2]: 2:public@10.10.10.1 MaxBytes[10.10.10.1.2]: 1250000 Title[10.10.10.1.2]: LC-Bridge (): ulink0 PageTop[10.10.10.1.2]: <H1>Traffic Analysis for ulink0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ulink0(2)</TD></TR> <TR><TD>IP:</TD><TD>()</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
#---------------------------------------------------------------
And that is a very basic mrtg config file. You can run this and see your results by going into the c:\mrtg-2.9.17\bin directory and typing:
perl mrtg mrtg.cfg
It is normal to get errors for the first two times you run this command. The errors will alert you about the fact that there have not been any log files in existnace before.
If you take a look at those web pages they are not real exciting, yet. You need to have the mrtg files run every five minutes to produce the desired results. Just run it again after a few minutes. You should now be able to see the first lines in your graphs.
Starting mrtg by hand every time you want to run it is not going to make you happy I guess.
There is a special option you can set in the mrtg configuration file so so that mrtg will not terminate after it was started. Instead it will wait for 5 minutes and then run again.
Add the option
RunAsDaemon: yes
to your mrtg.cfg file and start it with:
start /Dc:\mrtg-2.9.17\bin wperl mrtg --logging=eventlog mrtg.cfg
If you use wperl instead of perl, no console window will show. MRTG is now running in the background. If it runns into problems it will tell you so over the EventLog. To stop MRTG, open the taskmanager and terminate the wperl.exe process. If mrtg has anything to tell you these messages can be found in the eventlog.
If you put a shortcut with
Target: wperl mrtg --logging=eventlog mrtg.cfg Start in: c:\mrtg-2.9.17\bin
into your startup folder, mrtg will now start whever you login to your NT box.
If you do not want to log into your NT box just to start mrtg. Have a look at http://www.firedaemon.com/mrtg-howto.html which describes a free tool to start any program as a Service. The pages gives specific instructions for mrtg users.
Now lets look at a config file to monitor what we wanted to on our mythical Cisco Cat 5000 -- utilization on ports 3, 5, 10, and 24, and the CPU Load, which will show us nonstandard mrtg configurations as well as more options..
WorkDir: D:\InetPub\wwwroot\MRTG
###################################################################### # Description: LCP SUWGB # Contact: Administrator # System Name: LC-Bridge # Location: Here #.....................................................................
Target[10.10.10.1.1]: 3:public@10.10.10.1 MaxBytes[10.10.10.1.1]: 1250000 Title[10.10.10.1.1]: LC-Bridge (sample-device): ether0 PageTop[10.10.10.1.1]: <H1>Traffic Analysis for ether0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ether0(3)</TD></TR> <TR><TD>IP:</TD><TD>sample-device(10.10.10.1)</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
#---------------------------------------------------------------
Target[10.10.10.1.2]: 5:public@10.10.10.1 MaxBytes[10.10.10.1.2]: 1250000 Title[10.10.10.1.2]: LC-Bridge (): ulink0 PageTop[10.10.10.1.2]: <H1>Traffic Analysis for ulink0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ulink0(5)</TD></TR> <TR><TD>IP:</TD><TD>()</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
#---------------------------------------------------------------
Target[10.10.10.1.1]: 10:public@10.10.10.1 MaxBytes[10.10.10.1.1]: 1250000 Title[10.10.10.1.1]: LC-Bridge (sample-device): ether0 PageTop[10.10.10.1.1]: <H1>Traffic Analysis for ether0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ether0(10)</TD></TR> <TR><TD>IP:</TD><TD>sample-device(10.10.10.1)</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
#---------------------------------------------------------------
Target[10.10.10.1.2]: 24:public@10.10.10.1 MaxBytes[10.10.10.1.2]: 1250000 Title[10.10.10.1.2]: LC-Bridge (): ulink0 PageTop[10.10.10.1.2]: <H1>Traffic Analysis for ulink0</H1> <TABLE> <TR><TD>System:</TD><TD>LC-Bridge inAndover</TD></TR> <TR><TD>Maintainer:</TD><TD>Administrator</TD></TR> <TR><TD>Interface:</TD><TD>ulink0(24)</TD></TR> <TR><TD>IP:</TD><TD>()</TD></TR> <TR><TD>Max Speed:</TD> <TD>1250.0 kBytes/s (ethernetCsmacd)</TD></TR> </TABLE>
#---------------------------------------------------------------
# Router CPU load % Target[cpu.1]:1.3.6.1.4.1.9.2.1.58.0&1.3.6.1.4.1.9.2.1.58.0:public@10.10.10.1 RouterUptime[cpu.1]: public@10.10.10.1 MaxBytes[cpu.1]: 100 Title[cpu.1]: CPU LOAD PageTop[cpu.1]: <H1>CPU Load %</H1> Unscaled[cpu.1]: ymwd ShortLegend[cpu.1]: % XSize[cpu.1]: 380 YSize[cpu.1]: 100 YLegend[cpu.1]: CPU Utilization Legend1[cpu.1]: CPU Utilization in % (Load) Legend2[cpu.1]: CPU Utilization in % (Load) Legend3[cpu.1]: Legend4[cpu.1]: LegendI[cpu.1]: LegendO[cpu.1]: Usage Options[cpu.1]: gauge
This is a nice example of how to monitor any SNMP device if you know what OID you want to use. Once again, For an explanation of the more advance features of mrtg, please see Tobias's documentation.
David S. Divins <ddivins@moon.jic.com>, Steve Pierce <MRTG@HDL.com>, Tobi Oeitker <oetiker@ee.ethz.ch>