microuptime() ...

Doug White dwhite at gumbysoft.com
Wed Aug 18 18:49:44 PDT 2004


On Wed, 18 Aug 2004, Brian Astill wrote:

> > Because VIA doesn't publish documentaion, and source is not
> > documentation.
>
> I don't quite understand this response.  Are you saying that the Linux
> kernel team are somehow privileged cpw FBSD, so that they can avoid
> that microuptime issue and FBSD can't?  I would have thought that the
> source cpw documentation for VIA chipsets would have been the same for
> all.

What's 'cpw'? Criminal Posession of a Weapon? :)

I can't speak to Linux's timecounter implementation since I haven't read
their code. I suspect they don't have any sort of thing like
microuptime(), using jiffies insteaed which are somewhat lower precision.
They may just ignore the any timecounter disruptions due to CPU clock
adjustments, for all I know.

And it is *very* possible someone inside of VIA or one of their customers
got access to the docs that we can't get to and added the requisite code.
If you can derive the appropriate bits and offer them as a patch then all
the better.  Linux has lots of friends in high places since its Speshul.

-- 
Doug White                    |  FreeBSD: The Power to Serve
dwhite at gumbysoft.com          |  www.FreeBSD.org


More information about the freebsd-stable mailing list