why did Ubuntu turn off kernel preemption in Edgy?

[Ben Collins]

On Mon, 2006-11-27 at 00:57 +0000, Rui Tiago Cação Matos wrote:
> On Dom, 2006-11-26 at 19:11 -0500, Ben Collins wrote:
> > Because a lot of laptops didn't like this setup. It caused an increase
> > in timer related interrupts, which resulted in a significant decrease in
> > batter life.
> 
> And why not have a laptop-battery-friendly kernel version then? What do
> the likes of Fedora and openSuSE do about this issue? Why not fix those
> timer related interrupt problems instead? Are the lkml hackers aware of
> this?

It was a few of those very hackers that told me PREEMPT was a red
herring, and 1000HZ was not suggested. It's not a bug that 1000 timer
interrupts a second causes extra CPU load. Think of it this way: 1000HZ
is 10 times more interrupts than 100HZ. That's 10 times more CPU load
from just that functionality.

> > For feisty, I'm considering a low latency targeted kernel for audio
> > users. However, I'm a little reluctant, mainly because I never hear from
> > any of the multimedia users (like you) who are interested in this sort
> > of functionality until after we release, which for me means I wont get
> > any testing on these kernels until after it's too late to fix things.
> 
> Even though I'm not what I think you consider an 'audio user' I notice
> hickups on rhythmbox's output everytime my disk is hit more often. This
> is unacceptable, we are in 2006 and this is not rocket science nor does
> it need 'secret' hardware specs to get working. So, to answer you, yes
> you'll have testers. I'm actually already running feisty with 2.6.19.

Hickups from rhythmbox during disk access is an entirely different
issue. Try switching IO schedulers, see if one works better for you.

Also, I'll refrain from further correspondence with you until your tone
improves. You want answers? That's fine. You want improvement? Great, so
do I. However, in return, I want to be addressed with the same respect I
give you.