[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20070711092658.645023b9.kjwinchester@gmail.com>
Date: Wed, 11 Jul 2007 09:26:58 -0300
From: Kevin Winchester <kjwinchester@...il.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: "Matthew Hawkins" <darthmdh@...il.com>,
"Con Kolivas" <kernel@...ivas.org>, "ck list" <ck@....kolivas.org>,
"Ingo Molnar" <mingo@...e.hu>, "Paul Jackson" <pj@....com>,
linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [ck] Re: -mm merge plans for 2.6.23
On Tue, 10 Jul 2007 18:14:19 -0700
Andrew Morton <akpm@...ux-foundation.org> wrote:
> On Wed, 11 Jul 2007 11:02:56 +1000 "Matthew Hawkins" <darthmdh@...il.com> wrote:
>
> > We all know swap prefetch has been tested out the wazoo since Moses was a
> > little boy, is compile-time and runtime selectable, and gives an important
> > and quantifiable performance increase to desktop systems.
>
> Always interested. Please provide us more details on your usage and
> testing of that code. Amount of memory, workload, observed results,
> etc?
>
I only have 512 MB of memory on my Athlon64 desktop box, and I switch between -mm and mainline kernels regularly. I have noticed that -mm is always much more responsive, especially first thing in the morning. I believe this has been due to the new schedulers in -mm (because I notice an improvement in mainline now that CFS has been merged), as well as swap prefetch. I haven't tested swap prefetch alone to know for sure, but it seems pretty likely.
My workload is compiling kernels, with sylpheed, pidgin and firefox[1] open, and sometimes MonoDevelop if I want to slow my system to a crawl.
I will be getting another 512 MB of RAM at Christmas time, but from the other reports, it seems that swap prefetch will still be useful.
[1] Is there a graphical browser for linux that doesn't suck huge amounts of RAM?
--
Kevin Winchester
Content of type "application/pgp-signature" skipped
Powered by blists - more mailing lists