From: Jens Axboe <axboe@suse.de>
To: Con Kolivas <kernel@kolivas.org>
Cc: ck@vds.kolivas.org, "Ryan M." <kubisuro@att.net>,
linux-kernel@vger.kernel.org
Subject: Re: [ck] Re: -mm merge plans
Date: Thu, 23 Mar 2006 13:12:36 +0100 [thread overview]
Message-ID: <20060323121236.GY4285@suse.de> (raw)
In-Reply-To: <cone.1143104848.990946.31285.501@kolivas.org>
On Thu, Mar 23 2006, Con Kolivas wrote:
> Jens Axboe writes:
>
> >It's a heuristic, and sometimes that will work well and sometimes it
> >will not. What if during this period of inactivity, you start bringing
> >everything in from swap again, only to page it right out because the
> >next memory hog starts running? From a logical standpoint, swap prefetch
> >and the vm must work closely together to avoid paging in things which
> >really aren't needed.
>
> If the system is idle it doesn't cost anything to bring those pages in
> (laptop mode disables any prefetching if you're thinking about power
> consumption on laptops). And if the system wants the ram that has been
> filled with prefetched pages wrongly, the prefetched pages are at the tail
> end of the inactive LRU list with a copy on backing store so if they're not
> accessed they'll be the first thing dropped in preference to anything
> else, without any I/O.
I missed the fact that you left these pages on backing store for easy
dropping in the future. I guess if you didn't, it could coarsely be
handled in user space easily.
--
Jens Axboe
next prev parent reply other threads:[~2006-03-23 12:12 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-03-23 4:53 -mm merge plans Andrew Morton
2006-03-23 7:04 ` swap prefetching " Con Kolivas
2006-03-23 7:56 ` [ck] " Grzegorz Kulewski
2006-03-23 8:01 ` jos poortvliet
2006-03-23 8:22 ` Nick Piggin
2006-03-23 9:09 ` Con Kolivas
2006-03-23 9:24 ` Con Kolivas
2006-03-23 13:23 ` Martin J. Bligh
2006-03-23 8:33 ` Thomas Kuther
2006-03-23 11:19 ` Jesper Juhl
2006-03-23 11:24 ` [ck] " André Goddard Rosa
2006-03-23 11:57 ` Spike
2006-03-23 12:03 ` Spike
2006-03-23 12:16 ` Spike
2006-03-23 11:58 ` Lenar Lõhmus
2006-03-23 13:58 ` Francesco Biscani
2006-03-23 15:37 ` James Rayner
2006-03-23 15:34 ` [ck] " Radoslaw Szkodzinski
2006-03-23 18:35 ` Mattia Dongili
2006-03-23 18:40 ` Rafael J. Wysocki
2006-03-25 14:37 ` Jan Engelhardt
2006-03-25 15:24 ` Nick Piggin
2006-03-25 23:44 ` Con Kolivas
2006-03-26 5:54 ` Mike Galbraith
2006-03-26 8:08 ` Con Kolivas
2006-03-26 7:42 ` Mike Galbraith
2006-03-26 9:34 ` Con Kolivas
2006-03-27 15:37 ` [ck] " André Goddard Rosa
2006-03-27 22:19 ` Con Kolivas
2006-03-26 9:20 ` Jan Engelhardt
2006-03-28 6:16 ` [ck] " Chase Venters
2006-03-23 7:59 ` -mm " Ryan M.
2006-03-23 8:09 ` [ck] " Jens Axboe
2006-03-23 9:07 ` Con Kolivas
2006-03-23 12:12 ` Jens Axboe [this message]
2006-03-23 10:39 ` Takashi Iwai
2006-03-23 12:33 ` Christoph Hellwig
2006-03-23 12:49 ` [PATCH] remove pps support Roman Zippel
2006-03-23 13:43 ` -mm merge plans Michal Piotrowski
2006-03-24 23:33 ` Eric W. Biederman
2006-03-24 23:53 ` Andrew Morton
2006-03-25 0:50 ` Eric W. Biederman
2006-03-25 1:53 ` Arthur Othieno
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20060323121236.GY4285@suse.de \
--to=axboe@suse.de \
--cc=ck@vds.kolivas.org \
--cc=kernel@kolivas.org \
--cc=kubisuro@att.net \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox