Re: [2.6.20][PATCH] fix mempolicy error check on a system with memory-less-node

[Andi Kleen <ak@suse.de>]

On Wednesday 07 February 2007 11:37, KAMEZAWA Hiroyuki wrote:
> On Wed, 7 Feb 2007 11:19:02 +0100
> Andi Kleen <ak@suse.de> wrote:
> 
> > 
> > > AFAIK, ia64 creates nodes just depends on SRAT's possible resource information.
> > > Then, ia64 can create cpu-memory-less-node(node with no available resource.).
> > > (*)I don't like this.
> > > 
> > > If we don't allow memory-less-node, we may have to add several codes for cpu-hot-add.
> > > cpus should be moved to nearby node at hotadd .
> > > And node-hot-add have to care that cpus mustn't be added before memory, cpu-driven 
> > > node-hot-add will never occur. (ACPI's 'container' device spec can't guaranntee this.)
> > 
> > You can also alias node numbers to solve this: just point multiple node numbers 
> > to the same pgdat. For a memory less node this would be a nearby one.
> > 
> Hmm, interesting...the 'alias' means follwing ?

Yes.

> NODE_DATA(A) = pgdat_for_A
> NODE_DATA(B) = pgdat_for_A // B is memory-less.
> - NODE_DATA(B) is valid but B is not online.

Well it is online because A is. For all practical purposes
it is A, just under a different name.

> ==
> looks complicated..and we have to care /sys/devices/system/node handling.

x86-64 used to do that when it still only did 1:1 cpu<->memory mappings.
I don't remember any problems with it.

-Andi