realtime problem

[Mike Silbersack]

On Fri, 11 Apr 2003, Harti Brandt wrote:

> So, of course, it never takes the early return. When I remove the first
> assignment it seems to work. In this case I get a mean time for
> xl_status_update of 205usec which is ok I suppose.

That sounds like what I was seeing back when I was playing with the code.
Not perfect, but a heck of a lot better than how it was before.

If the logic in the patch is munged, it's probably because I took a
snapshot of my work in an non-optimal state... nonetheless, the idea is
clear, and should apply to all PHYs equally well.  I encourage you to
investigate further. :)

I would take another look at the code, but I'm bound and determined to
finish my mbuf testing / finding that if_xl-related panic before I get
sidetracked again.  (And I already have a great diversion planned for
myself once this gets done.)

Good luck,

Mike "Silby" Silbersack