Re: mm fragmentation patch

Raul Miller (rdm@test.legislate.com)
Thu, 16 Jul 1998 14:18:08 -0400

Colin Plumb <colin@nyx.net> wrote:
> The answer might be applicable to the Linux kernel page allocator.
> Using LIFO order increases fragmentation *drastically*, to the point
> where the larger size of the arena has bad cache effects.

On the other hand, doesn't LIFO give some advantage for cache management?

How about a two-queue mechanism? keep around a few entries because they
have a decent chance of being in cache, but when they're gone revert to
FIFO.

[Or am I chasing phantoms here?]

-- 
Raul


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html