Re: new IRQ scalability changes in 2.3.48

From: Andrea Arcangeli (andrea@suse.de)
Date: Mon Mar 27 2000 - 17:00:06 EST


On Sun, 19 Mar 2000, Rogier Wolff wrote:

>How about making "preemptive kernel" a "default-on" option on 2.4pre [..]

preemptive kernel is not obvious patch at all. Just to show a very subtle
example you can't preempt the mmx clear-page or the FPU state will get
screwed up. An explicit preempt_lock() is necessary around the mmx stuff.

I'm not convinced having the kernel preemptable will be worthy even on UP
where we don't have the per-cpu data structure locking troubles. It looks
more fascinating stuff than real life stuff.

The other way around (the patch to allow some section of code to be
preemptible) was quite obviously right instead.

Andrea

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Fri Mar 31 2000 - 21:00:21 EST