Gary E. Miller gem at rellim.com
Mon Nov 7 19:16:10 UTC 2016

Yo Achim!

On Mon, 07 Nov 2016 20:01:46 +0100
Achim Gratz <Stromeko at nexgo.de> wrote:

> Gary E. Miller writes:
> > Hard to control the power dissipation on a PC serving the
> > internet.  
> We weren't talking about a PC, or at least I was not.  The only
> subject I'm discussing is a rasPi and more specifically the 2B, which
> has multiple cores to play with.

I consider RasPi's to be PCs, powerfull little machines.  I use my 
RasPi's exactly as I use my other 'PC's.

> >> 99% of all
> >> PPS timestamps over the last day stay within ±10µs, 75% within ±1µs
> >> and slightly less than half within ±500ns.  
> >
> > Odd that I get much better numbers without all that work:  
> Read again what I wrote, please.

Yeah, I still arrive at tthe same opinion.

>  This data was for 86400 raw PPS
> timestamps (which you are seemingly not recording), you are talking
> the loopstats.

Correct.  I care about the end result.  But when I look attt my raw
data I actually see worse results in the unaveraged data.

> So in fact I do get
> better numbers than yours at least at the tail ends of the
> distribution.

Facts not in evidence.  Please post ntpviz graphs and stats.  I'm not
gonna go rouund and round with vague assertions instead of data.  Here
are many of mine:


> The skew seems to originate from the aging transient (especially the
> initial part, see below),

Yuu think you are seeing xtal aging in 24 hours?  I seriously doubt it
and you'll need a lot longer data collection to prove it.  There may
be 'initial' aging just after you cut a crystal, but not it sees
a small transient, what you are seeing is loop convergence.  Aging is
by definition irreversible.

Gary E. Miller Rellim 109 NW Wilmington Ave., Suite E, Bend, OR 97703
	gem at rellim.com  Tel:+1 541 382 8588
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 455 bytes
Desc: OpenPGP digital signature
URL: <http://lists.ntpsec.org/pipermail/devel/attachments/20161107/cd8abab9/attachment.bin>

More information about the devel mailing list