On 07-Feb-02 Ulf Zimmermann wrote: > On Sun, Jan 20, 2002 at 11:23:49AM +0000, Josef Karthauser wrote: >> On Sat, Jan 19, 2002 at 05:39:56PM -0800, Duane H. Hesser wrote: >> > >> > I can confirm the problem, and point you to a message in the "current" >> > archives (Dec 15) which contains a simple 3 or 4 line patch to uhui.c. >> > The message, authored by Andrew Gordon, may be found at >> > >> > >http://www.FreeBSD.org/cgi/getmsg.cgi?fetch=775757+780830+/usr/local/www/db/text/2001/freebsd-current/20011216.freebsd-c >> > urren >> > t >> >> Hmm. :) Looking at the NetBSD code, they made a major commit to fix the >> same issue: >> >> uhci.c revision 1.123 >> date: 2000/08/13 16:18:09; author: augustss; state: Exp; lines: +136 -31 >> Implement what in Intel-speech is known as "bandwidth reclamation". >> It means that we continously poll USB devices that have a pending transfer >> instead of polling just once every ms. This speeds up some transfers >> at the expense of using more PCI bandwidth. >> >> I'm looking at what is necessary to port that change over. >> >> Joe > > I was wondering if this has been ported over and if so, how about a -stable > version. > > -- > Regards, Ulf. >
Josef Karthauser has reported that the NetBSD changes to address this problem are much more complex than the patch above; he is working on importing them to -current, but it may be a while before they reach -stable. In the meantime, the Gordon patch is working well for me (although I have not monitored increases in cpu time during transfers), with about a four-fold increase in tranfer rate. It's a simple change, and I plan to move it forward to 4.5 when I upgrade. -------------- Duane H. Hesser [EMAIL PROTECTED] To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
