Re: isolcpus weirdness

[Emmanuel Pacaud <emmanuel.pacaud@univ-poitiers.fr>]

Le jeudi 23 février 2006 à 21:00 +1100, Con Kolivas a écrit :
> On Thursday 23 February 2006 20:55, Emmanuel Pacaud wrote:
> > Le mercredi 22 février 2006 à 22:18 +0100, Frederik Deweerdt a écrit :
> > > On Wed, Feb 22, 2006 at 02:21:27PM +0100, Emmanuel Pacaud wrote:
> > > > What's wrong ?
> > >
> > > Are you able to reproduce the same behaviour after disabling HT in
> > > the kernel config?
> >
> > I think HT is disabled in kernel config, since I only see 2 cpus.
> >
> > In fact, I've tried to enable HT, but did'nt succeed. HT is enabled in
> > BIOS, but I'm not sure about exact things I must set at kernel config
> > level for hyperthreading. I've tried to set/unset CONFIG_SCHED_SMT, but
> > that changes nothing (no hyperthreading, isolated cpu is always cpu0).
> >
> > Here's attached my config file.
> 
> CONFIG_ACPI is not set
> 
> You need ACPI to enumerate hyperthread siblings. That's why HT never gets 
> enabled for you.

Following your advice, I've set CONFIG_ACPI, and now, isolcpus works
fine, when hyperthreading is activated.

But, I'm trying to build a real time system where hyperthreading is not
desired. So, I've tried to disable HT in BIOS, and the result is the
same as when ACPI is not enabled in kernel config: isolated cpu is
always cpu0.

On the same machine, which is originally a Scientific Linux 4, I've
tried with distribution supplied kernel (a customized 2.6.9 with smp/HT
enabled): isolcpus works fine, even with HT disabled at BIOS level.

It seems there's a regression between 2.6.9 and 2.6.15. 

I've attached config file of scientific linux 4.

Regards,

	Emmanuel.

Attachment: config-2.6.9-5.0.5.ELsmp.gz
Description: GNU Zip compressed data