Suresh wrote:
hi,
So in case of uml, if all the interrupts are being handled in the
processor 0, hence
softirq and tasklets are going to be handled in processor 0. If this is
the case,
then don't you think that smp functionality is lost here. Kindly tell
me, is that the case
even in 2.4.20 kerne
At 06:52 PM 4/26/2005, Vincent Guffens wrote:
Suresh wrote:
hi,
So in case of uml, if all the interrupts are being handled in the
processor 0, hence
softirq and tasklets are going to be handled in processor 0. If this is
the case,
then don't you think that smp functionality is lost here. Kindly t
hi,
So in case of uml, if all the interrupts are being handled in the processor
0, hence
softirq and tasklets are going to be handled in processor 0. If this is the
case,
then don't you think that smp functionality is lost here. Kindly tell me,
is that the case
even in 2.4.20 kernel. In the dair
hi,
with uml smp support, only processor 0 is processing interrupts. This is
described there:
http://user-mode-linux.sourceforge.net/diary.html (25 Jul 2002)
It is quite old but I tried not so long ago and I could see in
/proc/interrupt that is was indeed the case.
cheers,
Suresh wrote:
Hi
I
Hi
I brought up uml with smp support. I used the vanilla kernel 2.4.20 and
the patch uml-patch-2.4.20-1.bz2.
I wrote a small kernel module.
This module registers to netfilter hooks. and the netfilter callback
function has the following callback functionality.
if(smp_processor_id() == 0)
spin_lock
