[PlanetCCRMA] Re: [linux-audio-user] Re: Recent LKML discussion on preempt/latency in 2.6 kernels

Ross Vandegrift ross@willow.seitz.com
Wed Mar 24 09:48:00 2004

On Tue, Mar 23, 2004 at 05:17:46PM -0800, Fernando Pablo Lopez-Lezcano wrote:
> On Tue, 2004-03-23 at 06:13, Ross Vandegrift wrote:
> > Has anyone tried audio work with 2.6 and preempt *off*?
> I just did and it does make a significant different in my tests (I have
> not tested yet compiling performance). Here are some results.

Oh wow.  Very interesting - it appears that my performance problems are
almost certainly due to something else.  It seems evident to me that
preempt does in general make the situation better in 2.6, though Andrea and
others have argued it's not the best approach.  I'm loading the DRI
modules - I'll have to try again without those. (well, once my network
card starts working in 2.6 again)

I'll try some without preemption (compiled a kernel for it last night),
but it looks like I'm barking up the wrong tree.

Ross Vandegrift

A Pope has a Water Cannon.                               It is a Water Cannon.
He fires Holy-Water from it.                        It is a Holy-Water Cannon.
He Blesses it.                                 It is a Holy Holy-Water Cannon.
He Blesses the Hell out of it.          It is a Wholly Holy Holy-Water Cannon.
He has it pierced.                It is a Holey Wholly Holy Holy-Water Cannon.
He makes it official.       It is a Canon Holey Wholly Holy Holy-Water Cannon.
Batman and Robin arrive.                                       He shoots them.