[ntp:questions] General ntp architecture question

Miroslav Lichvar mlichvar at redhat.com
Mon Aug 16 13:40:37 UTC 2010

On Mon, Aug 16, 2010 at 08:42:02AM -0400, Richard B. Gilbert wrote:
> If you require accuracy at the microsecond level, put your equipment
> in a controlled environment!  If the temperature in the room where
> the equipment resides is an unvarying 68 degrees F or 20 degrees C
> you will get a better and more stable time.  This may not be easy to
> do but it's essential for the very best time.  Actually just about
> any temperature that will not damage the hardware will work equally
> well as long as it does not vary minute to minute or hour to hour.

That may not be enough unless the CPU load is constant or the computer
case is well designed and the temperature of the oscillator is not
affected by other components. In my tests fully loading CPU can change
the frequency by tenths of ppm in less than minute and 1us lock will
be far from PLL's reach even with the minimum poll 3.

Miroslav Lichvar

More information about the questions mailing list