[lkml]   [2000]   [Mar]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: new IRQ scalability changes in 2.3.48

(I trimmed the list slightly.)

Linus Torvalds wrote:
> On Sun, 19 Mar 2000, Rogier Wolff wrote:
> >
> > How about making "preemptive kernel" a "default-on" option on 2.4pre
> > and a "default-off" option on the real 2.4 kernel?
> No, it's definitely too experimental - there are places that play games
> with the irq state etc, so there can be things that need quite a lot of
> debugging to get the threaded-UP case working fine.

Won't a "preemtive UP kernel" behave more like a SMP kernel? And aid to
find really nasty SMP bugs?

Rescheduling while not holding locks in UP case, should be equivalent to
a SMP CPU wandering off serving an IRQ at the same place - or am I

All kinds of nasty stuff might happen since CPUs executing in kernel
may PASS each other and they can end up in those "places that play

During pre series would be an excellent time for enabling this feature -
then it can be turned off when entering 2.4. The only problem to do that
is that people might end up liking their preemtive kernels too much :-)

> Maybe during 2.5.x we can back-port the changes to a 2.4.x release, and
> give people a three-way choice: UP, threaded-UP or SMP. But it's not a
> 2.4.x development thing.

But I think you need a quite stable system to start with in the first
place. If you try to add it to an unstable development kernel it would
possibly be blamed for all kinds of unrelated stuff too :-)

As _first_ addition in 2.5 with back porting to 2.4 could be an option.


Home page:

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
Please read the FAQ at

 \ /
  Last update: 2005-03-22 13:57    [W:0.118 / U:7.688 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site