CONFIG_X86_TSC_DISABLE question

CONFIG_X86_TSC_DISABLE question

[uaca]

Hi all

I would like to know if in wich degree the issue of unsynced TSCs also applies 
on x86 SMP.

Thanks

	Ulisses

                Debian GNU/Linux: a dream come true
-----------------------------------------------------------------------------
"Computers are useless. They can only give answers."            Pablo Picasso

--->	Visita http://www.valux.org/ para saber acerca de la	<---
--->	Asociación Valenciana de Usuarios de Linux		<---
 

Re: CONFIG_X86_TSC_DISABLE question

[Martin J. Bligh]

Depends on your box. Most standard SMP boxes are all clocked off the
same clock, so it's not an issue.

--On Thursday, January 02, 2003 15:44:09 +0100 uaca@alumni.uv.es wrote:

> Hi all
>
> I would like to know if in wich degree the issue of unsynced TSCs also
> applies  on x86 SMP.
>
> Thanks
>
> 	Ulisses
>
>                 Debian GNU/Linux: a dream come true
> -------------------------------------------------------------------------
> ---- "Computers are useless. They can only give answers."
> Pablo Picasso
>
> --->	Visita http://www.valux.org/ para saber acerca de la	<---
> --->	Asociación Valenciana de Usuarios de Linux		<---
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
>
>

Re: CONFIG_X86_TSC_DISABLE question

[uaca]

On Thu, Jan 02, 2003 at 09:39:40AM -0800, Martin J. Bligh wrote:
> Depends on your box. Most standard SMP boxes are all clocked off the
> same clock, so it's not an issue.

Hi Martin

Thanks for your reply

Is there a way to verify this? or must I contact the motherboard maker and
ask for it? how I should ask it?


Ulisses

> 
> --On Thursday, January 02, 2003 15:44:09 +0100 uaca@alumni.uv.es wrote:
> 
> >Hi all
> >
> >I would like to know if in wich degree the issue of unsynced TSCs also
> >applies  on x86 SMP.
> >
> >Thanks
> >
> >	Ulisses
> >
> >                Debian GNU/Linux: a dream come true
> >-------------------------------------------------------------------------
> >---- "Computers are useless. They can only give answers."
> >Pablo Picasso
> >
> >--->	Visita http://www.valux.org/ para saber acerca de la	<---
> >--->	Asociación Valenciana de Usuarios de Linux		<---
> >
> >-
> >To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> >the body of a message to majordomo@vger.kernel.org
> >More majordomo info at  http://vger.kernel.org/majordomo-info.html
> >Please read the FAQ at  http://www.tux.org/lkml/
> >
> >
> 
> 
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

-- 
                Debian GNU/Linux: a dream come true
-----------------------------------------------------------------------------
"Computers are useless. They can only give answers."            Pablo Picasso

--->	Visita http://www.valux.org/ para saber acerca de la	<---
--->	Asociación Valenciana de Usuarios de Linux		<---
 

Re: CONFIG_X86_TSC_DISABLE question

[Martin J. Bligh]

> Is there a way to verify this? or must I contact the motherboard maker and
> ask for it? how I should ask it?

I'd just assume that it works unless you have > 4 CPUs. Boxes (like mine)
where it doesn't work tend to be arcane NUMA things with large CPU counts.

M.

Re: CONFIG_X86_TSC_DISABLE question

[uaca]

On Fri, Jan 03, 2003 at 05:52:55PM -0500, Mark Hahn wrote:

Hi Mark

> > > Depends on your box. Most standard SMP boxes are all clocked off the
> > > same clock, so it's not an issue.
> > 
> > Hi Martin
> > 
> > Thanks for your reply
> > 
> > Is there a way to verify this? or must I contact the motherboard maker and
> > ask for it? how I should ask it?
> 
> any SMP less than $50k is using a single clock to drive the CPUs,
> and therefore has TSC's in sync.  if you owned a numa/clustered
> SMP, you'd know it - they're the only ones that need something special.

Thanks for your reply

I think that CONFIG_X86_TSC_DISABLE should be more informative on this

Ulisses


                Debian GNU/Linux: a dream come true
-----------------------------------------------------------------------------
"Computers are useless. They can only give answers."            Pablo Picasso

--->	Visita http://www.valux.org/ para saber acerca de la	<---
--->	Asociación Valenciana de Usuarios de Linux		<---

Re: CONFIG_X86_TSC_DISABLE question

[uaca]

On Fri, Jan 03, 2003 at 06:01:13PM -0500, Mark Hahn wrote:
> > I think that CONFIG_X86_TSC_DISABLE should be more informative on this
> 
> at most, it should say "don't worry about this unless you need to.
> and you'll know it if you need to".


And It should say that the kernel test TSCs are syncroniced across CPUS at
boot time, which I've just have found:

The message is the following in a 2.4.19-pre6 kernel

checking TSC synchronization across CPUs: passed.


I hope this helps somebody


	Ulisses

                Debian GNU/Linux: a dream come true
-----------------------------------------------------------------------------
"Computers are useless. They can only give answers."            Pablo Picasso

--->	Visita http://www.valux.org/ para saber acerca de la	<---
--->	Asociación Valenciana de Usuarios de Linux		<---