Regression in device ath between BETA5 and RC1?

[M. Warner Losh]

In message: <20051020232308.GA77950 at xor.obsecurity.org>
            Kris Kennaway <kris at obsecurity.org> writes:
: On Thu, Oct 20, 2005 at 05:46:52PM -0500, Doug Poland wrote:
: > Kris Kennaway wrote:
: > >On Thu, Oct 20, 2005 at 05:11:41PM -0500, Doug Poland wrote:
: > >
: > >
: > >>I was seeing this behavior a lot on 5.2.1, 5.3, and, IIRC, 5.4.
: > >>Responsiveness was so poor as to make remote SSH sessions unusable.
: > >>When I installed -CURRENT then RELENG_6, then the NIC started performing
: > >>beautifully.  Very stable and consistent.  Now, with yesterday's cvsup'd
: > >>to RC1, the NIC/driver is performing poorly again.
: > >
: > >
: > >Go back to the previous version to verify it's not environmental or
: > >some other problem than a regression in FreeBSD.
: > >
: > Sure, can you tell me what tag to use in my supfile?  Right now I have:
: > 
: >   *default release=cvs tag=RELENG_6
: 
: Use a date instead of a tag (see the cvsup docs).

*default release=cvs date=2005.10.10.12.23.45

and try to find where, since June, the divergence of performance was.
We branched RELENG_6 in June, and there's been much merged from head
back into RELENG_6.

Warner