Re: [PATCH] SPARSEMEM + NUMA can't handle unaligned memory regions?

From: Andy Whitcroft
Date: Tue May 09 2006 - 12:14:34 EST


mike kravetz wrote:
> On Tue, May 09, 2006 at 02:34:51PM +0100, Andy Whitcroft wrote:
>
>>3) record the nid -- when we record the memory present in the system we
>>are passed the nid.
>>
>>Somehow the last of these seems the most logical given we have the
>>correct information at the time we record that we need to instantiate
>>the section. So I had a quick go at something which seems to have come
>>out pretty clean. Attached is a completly untested patch to show what I
>>am proposing.
>
>
> Looks sane to me. I've always wanted to encode the nid in the section.
> But, never had a compelling reason to do so.
>
> With this code in place, we could optimize the pfn_to_nid() routines to
> now obtain the nid from the section (rather than page struct). However,
> I'm not sure this is worth the effort.

Well its only in there temporarily during init, its not in there once we
have allocated the section mem_map.

-apw
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/