Jonathan Stone said on 2000-05-12:

> In message <x766sjwqgv.fsf@capsicum.wsrcc.com>Wolfgang Rupprecht writes
> 
> >I'm concerned that most of the advantage of using a GPS with a few
> >10's of nS of noise on it PPS line will be lost if the kernel proceeds
> >to timestamp things with only 1uS of resolution.
> 
> It still helps. Dave Mills has nearly a decade of experience with Suns
> using microsecond-resolution clocks. Unfortunatley the MI timekeeping
> in NetBSD still uses microseconds.  I've suggested changes to that,
> but there was a lack of consensus about formats and inkernel APIs:
> other people focusing on different uses of timing proposed rather
> different APIs.

Dave Mills has done an excellent job in terms of syncronization...

     remote           local      st poll reach  delay   offset    disp
=======================================================================
*GPS_NMEA(0)     127.0.0.1        0   64  377 0.00000  0.000044 0.00095
.gnomon.cc.colum 216.33.34.145    1   64  377 0.02582 -0.000985 0.00119

And this is without hardpps()... it works pretty darn well, and I'm
expecting that once we get over this hurdle, it will improve a small bit,
too.  This is using one of Dave Schwartz's GPSClock 200's (no affiliation
at all with him, but it's a very nice low cost unit for NTP purposes).

-yubyub
----------------------------------------------------------------
croquette - n.  A small cake of minced | SMTP: yubyub@yubyub.net
 food, such as poultry, vegetables, or | http://www.yubyub.net
 fish, that is usually coated with     | NetBSD on Sparc, Alpha
 bread crumbs and fried in _deep fat_. |  i386, Mac68k, VAX