[request-for-test] [patch 0/3] [IA64] Allow DISCONTIGMEM without NUMA

[request-for-test] [patch 0/3] [IA64] Allow DISCONTIGMEM without NUMA

[Simon Horman]

The following patches relate to allowing DISCONTIG memory to compile
(and hopefully work) without NUMA. I've tested that they boot, but not much
beyond that.

The first two patches are minor cleanups in files related to this change.
The third patch is the real change.

-- 
Horms
  H: http://www.vergenet.net/~horms/
  W: http://www.valinux.co.jp/en/

Re: [request-for-test] [patch 0/3] [IA64] Allow DISCONTIGMEM without NUMA

[Christoph Hellwig]

On Thu, May 10, 2007 at 07:19:45PM +0900, Simon Horman wrote:
> The following patches relate to allowing DISCONTIG memory to compile
> (and hopefully work) without NUMA. I've tested that they boot, but not much
> beyond that.

Why?  I though we wanted to use virtual mem_map and sparsemem for
holes inside a single node?

Re: [request-for-test] [patch 0/3] [IA64] Allow DISCONTIGMEM without NUMA

[Simon Horman]

On Thu, May 10, 2007 at 12:45:48PM +0100, Christoph Hellwig wrote:
> On Thu, May 10, 2007 at 07:19:45PM +0900, Simon Horman wrote:
> > The following patches relate to allowing DISCONTIG memory to compile
> > (and hopefully work) without NUMA. I've tested that they boot, but not much
> > beyond that.
> 
> Why?  I though we wanted to use virtual mem_map and sparsemem for
> holes inside a single node?

There was a breif dicusion on linux-ia64 which I interpated as Tony
saying it was a good idea.

http://thread.gmane.org/gmane.linux.ports.ia64/16325/focus\x16327

With regards to sparse, the current code needs most if
not all these fixes in order to use arch/ia64/mm/discontig.c.
Is the idea to rework that?

-- 
Horms
  H: http://www.vergenet.net/~horms/
  W: http://www.valinux.co.jp/en/