Re: [gpsd-dev] Mysteriously vanishing bugs don't make me happy

[Miroslav Lichvar]

On Mon, Nov 04, 2013 at 06:22:15PM -0800, Gary E. Miller wrote:
> On Mon, 04 Nov 2013 21:05:42 -0500
> Greg Troxel <address@hidden> wrote:
> > > Yes.  I now see +/- 400 nSec jitter on chrony socket.  I could do
> > > better on a dedicated time server.  Best I can do with SHM is
> > > currently about +/- 2 uSec.
> > 
> > I don't follow why this is different.  Isn't it all about
> > sample-to-sample repeatability of obtaining the system clock
> > (timecounter) at the edge?  WHy does it matter how it's conveyed to
> > chronyd?
> 
> The SOCK interface is in nSec, the SHM interface is in uSec.

Another difference is that the SOCK samples are received shortly after
they were sent. The SHM samples are delayed by up to 1 second (can be
configured with the dpoll option), which adds a small error to the
chrony's "cooked" offset, because in won't include the phase
adjustment applied by the kernel to system clock in that interval. I'm
not sure if that can explain the 400ns vs 2us difference though.

As for how much the nanosecond resolution actually improves the
accuracy of the system clock, see this graph (from clknetsim
simulations) of clock error vs refclock jitter:

http://mlichvar.fedorapeople.org/tmp/refclock_shm_res.png

-- 
Miroslav Lichvar