realtime problem

[Harti Brandt]

On Thu, 10 Apr 2003, Mike Silbersack wrote:

MS>
MS>On Thu, 10 Apr 2003, Mike Silbersack wrote:
MS>
MS>>
MS>> On Thu, 10 Apr 2003, Harti Brandt wrote:
MS>>
MS>> > MS>Harti, you're more than welcome to investigate and see if those changes
MS>> > MS>reduce delay for you. :)
MS>> >
MS>> > With this patch I get the following timing:
MS>>
MS>> The patch I posted was not all inclusive, and did not touch all of the mii
MS>> code.  You should doublecheck to see if the PHY type of your NIC was
MS>> patched or not.
MS>>
MS>> Mike "Silby" Silbersack
MS>
MS>Hm, wait, the patch I sent should have affected exphy, which is why newer
MS>3Coms use...
MS>
MS>What were your timing results before the change vs after?

This is a 3com and has an exphy, which in turn uses ukphy_status.

The timing is the same (960usec), because it never takes the first return.
Should it?

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