linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Mel Gorman <mel@csn.ul.ie>
Cc: clameter@sgi.com, Andy Whitcroft <apw@shadowen.org>,
	Linux Memory Management List <linux-mm@kvack.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] Add __GFP_MOVABLE for callers to flag allocations that may be migrated
Date: Mon, 4 Dec 2006 14:34:35 -0800	[thread overview]
Message-ID: <20061204143435.6ab587db.akpm@osdl.org> (raw)
In-Reply-To: <Pine.LNX.4.64.0612041946460.26428@skynet.skynet.ie>

On Mon, 4 Dec 2006 20:34:29 +0000 (GMT)
Mel Gorman <mel@csn.ul.ie> wrote:

> > IOW: big-picture where-do-we-go-from-here stuff.
> >
> 
> Start with lumpy reclaim,

I had lumpy-reclaim in my todo-queue but it seems to have gone away.  I
think I need a lumpy-reclaim resend, please.

> then I'd like to merge page clustering piece by 
> piece, ideally with one of the people with e1000 problems testing to see 
> does it make a difference.
> 
> Assuming they are shown to help, where we'd go from there would be stuff 
> like;
> 
> 1. Keep non-movable and reapable allocations at the lower PFNs as much as
>     possible. This is so DIMMS for higher PFNs can be removed (doesn't
>     exist)

"as much as possible" won't suffice, I suspect.  If there's any chance at
all that a non-moveable page can land in a hot-unpluggable region then
there will be failure scenarios.  Easy-to-hit ones, I suspect.

> 2. Use page migration to compact memory rather than depending solely on
>     reclaim (doesn't exist)

Yup.

> 3. Introduce a mechanism for marking a group of pages as being offlined so
>     that they are not reallocated (code that does something like this
>     exists)

yup.

> 4. Resurrect the hotplug-remove code (exists, but probably very stale)

I don't even remember what that looks like.

> 5. Allow allocations for hugepages outside of the pool as long as the
>     process remains with it's locked_vm limits (patches were posted to
>     libhugetlbfs last Friday. will post to linux-mm tomorrow).

hm.


I'm not saying that we need to do memory hot-unplug immediately.  But the
overlaps between this and anti-frag and lumpiness are sufficient that I do
think that we need to work out how we'll implement hot-unplug, so we don't
screw ourselves up later on.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2006-12-04 22:34 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-30 17:07 Mel Gorman
2006-12-01  1:31 ` Andrew Morton
2006-12-01  9:54   ` Mel Gorman
2006-12-01 19:01     ` Andrew Morton
2006-12-04 14:07       ` Mel Gorman
2006-12-04 19:30         ` Andrew Morton
2006-12-04 19:41           ` Christoph Lameter
2006-12-04 20:06             ` Andrew Morton
2006-12-04 20:17               ` Christoph Lameter
2006-12-04 21:19                 ` Andrew Morton
2006-12-04 21:43                   ` Christoph Lameter
2006-12-04 22:22                     ` Andrew Morton
2006-12-05 16:00                       ` Christoph Lameter
2006-12-05 19:25                         ` Andrew Morton
2006-12-05 20:01                           ` Christoph Lameter
2006-12-05 21:47                             ` Mel Gorman
2006-12-05 23:33                               ` Christoph Lameter
2006-12-06  9:31                                 ` Mel Gorman
2006-12-06 17:31                                   ` Christoph Lameter
2006-12-08  1:21                                     ` Jeremy Fitzhardinge
2006-12-08  2:20                                       ` Christoph Lameter
2006-12-08  6:11                                         ` Jeremy Fitzhardinge
2006-12-05 18:10                       ` Mel Gorman
2006-12-04 20:34           ` Mel Gorman
2006-12-04 22:34             ` Andrew Morton [this message]
2006-12-04 23:45               ` Mel Gorman
2006-12-05  1:16                 ` KAMEZAWA Hiroyuki
2006-12-05 10:03                   ` Mel Gorman
2006-12-05 16:05                     ` Christoph Lameter
2006-12-05 18:26                       ` Andrew Morton
2006-12-05 19:59                         ` Christoph Lameter
2006-12-05 16:14                 ` Christoph Lameter
2006-12-05 17:17                   ` Mel Gorman
2006-12-05 19:54                     ` Christoph Lameter
2006-12-05 15:52               ` Andy Whitcroft
2006-12-05 15:48             ` Andy Whitcroft
2006-12-04 20:37           ` Peter Zijlstra
2006-12-06 14:18             ` Andy Whitcroft

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=20061204143435.6ab587db.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=apw@shadowen.org \
    --cc=clameter@sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    /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