Re: swap cache

Paul R. Wilson (wilson@cs.utexas.edu)
Mon, 21 Dec 1998 14:48:32 -0600


>From alan@lxorguk.ukuu.org.uk Mon Dec 21 10:28:27 1998
>From: alan@lxorguk.ukuu.org.uk (Alan Cox)
>Subject: Re: swap cache
>To: vonbrand@inf.utfsm.cl (Horst von Brand)
>Date: Mon, 21 Dec 1998 17:25:18 +0000 (GMT)
>Cc: wilson@cs.utexas.edu, linux-kernel@vger.rutgers.edu
>
>The interesting thing however is that for a lot of desktop usage, that
>thinking is the correct model.

And it's often true for servers as well, during peak load or when
somebody's doing something unusually memory-intensive and others aren't
doing much.

And it can always turn itself off when it's not helpful.

> There is only one way to find out for definite -
>someone who believes its clearly a win should code it and try it

That's my plan---or in the short term, implementing enough of it
to show the performance issues convincingly.

Any assistance would be welcome, of course, whether it's helping
hack the kernel, or just pointing out easy ways to do things, or
things to *avoid* messing with because they're carefully put together
and I'll mess them up.

-
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.tux.org/lkml/