Yo Achim!

On Thu, 23 Mar 2017 20:43:22 +0100
Achim Gratz <[email protected]> wrote:

> Gary E. Miller writes:
> > Hmm, very interesting data point.  That GigE is not clearly better
> > than the 100BaseT is a surprise to me.  
> 
> Why do you think it should be "clearly" better?  The point of the GbE
> is that even when you move data around (which none of my time boxes
> do on a regular basis, at least not yet) the line will be blocked for
> shorter periods of time.

Which, paradxically, is why GigE is usually better than 100Base-T.  At
the same total amount of data per second the latency could be cut by
a factor of ten.

And less latency would hopefully lead to less jitter.

> > Can the TikerBoard GigE do hardware PTP?  
> 
> I don't think so and ethtool only report software timestamping
> capabilities.

That nail that coffin shut.  Sad, it would be a nice feeature.


> There's an RTC device, part of the PMIC.  Unfortunately the 32kHz XO
> does not seem to be populated, not is there any option to power it via
> battery.  It might have an internal (awful) oscillator.

Even a really bad RTC is better than any RasPi.

> It does also have an integrated GPS baseband block, interestingly
> enough.

That would be cool, prolly left over from its cell phone heritage.

> One nice thing is that it actually can be powered off from Linux.  The
> rasPi shuts down, but still consumes around 110mA.

Luckily I do nothing requiring really low power.  And NTP prefers always
on, and on high speed.

When you have real performance numbers, send them on so we can share.

RGDS
GARY
---------------------------------------------------------------------------
Gary E. Miller Rellim 109 NW Wilmington Ave., Suite E, Bend, OR 97703
        [email protected]  Tel:+1 541 382 8588

            Veritas liberabit vos. -- Quid est veritas?
    "If you can’t measure it, you can’t improve it." - Lord Kelvin

Attachment: pgpGzamQOoCjG.pgp
Description: OpenPGP digital signature

_______________________________________________
devel mailing list
[email protected]
http://lists.ntpsec.org/mailman/listinfo/devel

Reply via email to