Re: [PATCH] per-cpu change

[William Lee Irwin III]

In message <[e-mail]> you write:
>>  - On NUMA, you want to allocate the per-CPU areas in node-local memory.

On Sat, May 03, 2003 at 02:40:57PM +1000, Rusty Russell wrote:
> Thanks: I'd forgotten about this.  Even "big smp" machines often have
> different memory latencies.

I have already a patch to do this for ia32 NUMA systems (which present
issues not present on sane architectures).

I also didn't notice the lack of an override; #undef'ing the macro
__GENERIC_PER_CPU appeared to suffice for me.

-- wli