[ntp:questions] refclock on Windows graphs

David J Taylor david-taylor at blueyonder.neither-this-bit.nor-this.co.uk
Wed Mar 18 07:28:19 UTC 2009

Unruh wrote:
> "David J Taylor"
>> Another PC in the same room running a FreeBSD system has about half
>> the jitter, but far less offset - PC Pixie at the top:
>>  http://www.satsignal.eu/mrtg/performance_ntp.php
> That looks much more like the kind of timing I get on my Linux system.
> driven by a PPS from a Garmin 18LVC.
> I assume that the rate is also far more constant on that system.

Not far more constant, no.  On the FreeBSD/Pentium-133 system over the 
last 72 hours the frequncy varied between about -0.6ppm to +0.4ppm from 
the mean, and on the Windows XP system from about -1.4ppm to +1.1ppm from 
the mean.  So about 1ppm variation as opposed to 2.5ppm, about 40% of the 
frequency variation.

As far as I can tell, the NTP offset is more a function of the control 
loop parameters than of the actual hardware (with ~150us offsets and yet 
only 2.5us jitter).

There is another issue - version numbers.  The FreeBSD runs 4.2.0-a from 
May 2005, the Windows 4.2.4.p6 from 2009.  I don't know whether there may 
have been internal changes affecting the offset compared to the jitter.

I have checked for a temperature monitoring SNMP plug-in, but not found a 
compatible one as yet.

Yes, it would be helpful to have more Windows testers.


More information about the questions mailing list