Re: Inclusion of zoned inactive/free shortage patch

[Linus Torvalds <torvalds@transmeta.com>]

On Wed, 18 Jul 2001, Marcelo Tosatti wrote:
>
> Ok, I understand and I agree with doing _unconditional_
> "zone_inactive_plenty()" instead of conditional
> "zone_inactive_shortage()".
>
> This way we do not get _strict_ zoned behaviour (with strict I mean only
> doing scanning for zones which have a shortage), making the shortage
> handling smoother and doing "fair" aging in cases where there are not
> specific zones under pressure.

Cool.

Willing to write a patch and give it some preliminary testing? I also
agree with the patch Rik sent in about GFP_HIGHUSER, that's orthogonal
though (even if I suspect it could also have made the problem _appear_
much much more clearly).

I'd like to do a real pre7 one of these days (it's already growing big
enough, thank you), but I'd love to have this issue put at least somewhat
to rest.

		Linus