[PATCH] Increase the upper bound on NR_CPUS.

[PATCH] Increase the upper bound on NR_CPUS.

[Tony Breeds]

Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>

---
why not?

 arch/powerpc/platforms/Kconfig.cputype |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 99684ea..5d70862 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -220,8 +220,8 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-128)"
-	range 2 128
+	int "Maximum number of CPUs (2-1024)"
+	range 2 1024
 	depends on SMP
 	default "32" if PPC64
 	default "4"

Yours Tony

  linux.conf.au        http://linux.conf.au/ || http://lca2008.linux.org.au/
  Jan 28 - Feb 02 2008 The Australian Linux Technical Conference!

Re: [PATCH] Increase the upper bound on NR_CPUS.

[Michael Ellerman]

[-- Attachment #1: Type: text/plain, Size: 455 bytes --]

On Thu, 2007-11-29 at 15:16 +1100, Tony Breeds wrote:
> Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
> 
> ---
> why not?

How big is say a pseries_defconfig with NR_CPUS = 1024 ?

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH] Increase the upper bound on NR_CPUS.

[Tony Breeds]

On Thu, Nov 29, 2007 at 03:17:16PM +1100, Michael Ellerman wrote:
> On Thu, 2007-11-29 at 15:16 +1100, Tony Breeds wrote:
> > Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
> > 
> > ---
> > why not?
> 
> How big is say a pseries_defconfig with NR_CPUS = 1024 ?

This is a ppc64_defconfig, with a couple of extra patches, and
NR_CPUS=1024

tony@Sprygo:~/scratch/working$ size ../working_out/arch/powerpc/boot/zImage.{pmac,pseries,iseries} ../working_out/vmlinux
   text    data     bss      dec     hex filename
3697092    5356   48232  3750680  393b18 ../working_out/arch/powerpc/boot/zImage.pmac
3697092    5356   48232  3750680  393b18 ../working_out/arch/powerpc/boot/zImage.pseries
8101340 4994176  815544 13911060  d44414 ../working_out/arch/powerpc/boot/zImage.iseries
8101340 4994176  815544 13911060  d44414 ../working_out/vmlinux

Yours Tony

  linux.conf.au        http://linux.conf.au/ || http://lca2008.linux.org.au/
  Jan 28 - Feb 02 2008 The Australian Linux Technical Conference!

Re: [PATCH] Increase the upper bound on NR_CPUS.

[Michael Ellerman]

[-- Attachment #1: Type: text/plain, Size: 1516 bytes --]


On Thu, 2007-11-29 at 15:23 +1100, Tony Breeds wrote:
> On Thu, Nov 29, 2007 at 03:17:16PM +1100, Michael Ellerman wrote:
> > On Thu, 2007-11-29 at 15:16 +1100, Tony Breeds wrote:
> > > Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
> > > 
> > > ---
> > > why not?
> > 
> > How big is say a pseries_defconfig with NR_CPUS = 1024 ?
> 
> This is a ppc64_defconfig, with a couple of extra patches, and
> NR_CPUS=1024
> 
> tony@Sprygo:~/scratch/working$ size ../working_out/arch/powerpc/boot/zImage.{pmac,pseries,iseries} ../working_out/vmlinux
>    text    data     bss      dec     hex filename
> 3697092    5356   48232  3750680  393b18 ../working_out/arch/powerpc/boot/zImage.pmac
> 3697092    5356   48232  3750680  393b18 ../working_out/arch/powerpc/boot/zImage.pseries
> 8101340 4994176  815544 13911060  d44414 ../working_out/arch/powerpc/boot/zImage.iseries
> 8101340 4994176  815544 13911060  d44414 ../working_out/vmlinux

OK, not too bad for the zImage, but the vmlinux has grown a bit, we
obviously have lots of foo[NR_CPUS].

NR_CPUS = 32 vs 1024

   text    data     bss     dec     hex filename
7889287 1786256  529248 10204791         9bb677 vmlinux
7901531 4946864  814432 13662827         d07a6b vmlinux

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH] Increase the upper bound on NR_CPUS.

[Stephen Rothwell]

[-- Attachment #1: Type: text/plain, Size: 358 bytes --]

Hi Tony, :-)

On Thu, 29 Nov 2007 15:16:03 +1100 tony@bakeyournoodle.com (Tony Breeds) wrote:
>
> Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>

NAK ... you need to change the static initialisation of the paca
structures to match ...

-- 
Cheers,
Stephen Rothwell                    sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH] Increase the upper bound on NR_CPUS.

[Arnd Bergmann]

On Thursday 29 November 2007, Tony Breeds wrote:
> why not?

In the past I've seen run-time problems because some parts of the
code kmalloc NR_CPUS sized arrays, which can easily grow beyond
the kmalloc limit of 128kb. Have you tried running some tests
on a small machine with the big NR_CPUS?

	Arnd <><