realtime problem

[Harti Brandt]

On Wed, 9 Apr 2003, Luigi Rizzo wrote:

LR>On Wed, Apr 09, 2003 at 12:00:44PM -0700, John Polstra wrote:
LR>...
LR>> Huh?  I'm not aware of any hz-related botches in the mii code.
LR>> Could you give me a specific example?  I'd like to fix it if I can
LR>> find it.
LR>
LR>it is not hz-related, the fact is that some PHY events are
LR>handled by busy-waiting in the interrupt service routine
LR>thus causing unpredictable latencies in the response to
LR>interrupts.

Well, in this case it is not exacly what one would call an 'event'. It's
the periodcally called status update routine and this routine botches
the callout timing because it cannot generate the minimum timing that MII
requires.

harti
-- 
harti brandt,
http://www.fokus.fraunhofer.de/research/cc/cats/employees/hartmut.brandt/private
brandt at fokus.fraunhofer.de, harti at freebsd.org