Re: xntpd - VERY old folks, how about updating? :-)

[Poul-Henning Kamp]

In message <[EMAIL PROTECTED]>, Karl Denninger writes:
>On Sun, Jan 02, 2000 at 03:32:00PM -0700, Warner Losh wrote:
>> In message <[EMAIL PROTECTED]> Karl Denninger writes:
>> : Why spend twice what Mr. Schwartz seems to want to charge?
>> 
>> Because we need a PPS that is < 10nS from the true start of second for 
>> our application?  1uS is really really bad for the timing geeks in the 
>> audience.
>> 
>> Warner
>
>And on what hardware do you think you can obtain 10ns resolution RELIABLY 
>at the software level in the Unix environment and under FreeBSD?
>
>Answer: NONE!
>
>The actual usable resolution of a timing source is determined by the 
>maximum slop in ANY part of the complete system.
>
>I challenge you to get actual REPEATABLE 10ns results while a multi-tasking
>anything is running on the recipient of that data.

What rides on this challenge ?  What is the prize ?  
I would use some cash, and this will be like picking cherries...

--
Poul-Henning Kamp             FreeBSD coreteam member
[EMAIL PROTECTED]               "Real hackers run -current on their laptop."
FreeBSD -- It will take a long time before progress goes too far!


To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message