realtime problem
Mike Silbersack
silby at silby.com
Mon Apr 14 00:31:30 PDT 2003
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
More information about the freebsd-hackers
mailing list