From: Nick Piggin <npiggin@suse.de>
To: Rik van Riel <riel@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Peter Zijlstra <peterz@infradead.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Christoph Lameter <cl@linux-foundation.org>
Subject: Re: [PATCH] vmscan: skip freeing memory from zones with lots free
Date: Wed, 10 Dec 2008 06:09:38 +0100 [thread overview]
Message-ID: <20081210050938.GF8434@wotan.suse.de> (raw)
In-Reply-To: <493D82A6.9070104@redhat.com>
On Mon, Dec 08, 2008 at 03:25:10PM -0500, Rik van Riel wrote:
> KOSAKI Motohiro wrote:
>
> >+ for (o = order; o < MAX_ORDER; o++) {
> >+ if (z->free_area[o].nr_free)
> >+ return 1;
>
> Since page breakup and coalescing always manipulates .nr_free,
> I wonder if it would make sense to pack the nr_free variables
> in their own cache line(s), so we have fewer cache misses when
> going through zone_watermark_ok() ?
For order-0 allocations, they should not be touched at all. For
higher order allocations in performance critical paths, we should
try to fix those to use order-0 ;)
WARNING: multiple messages have this Message-ID (diff)
From: Nick Piggin <npiggin@suse.de>
To: Rik van Riel <riel@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Peter Zijlstra <peterz@infradead.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Christoph Lameter <cl@linux-foundation.org>
Subject: Re: [PATCH] vmscan: skip freeing memory from zones with lots free
Date: Wed, 10 Dec 2008 06:09:38 +0100 [thread overview]
Message-ID: <20081210050938.GF8434@wotan.suse.de> (raw)
In-Reply-To: <493D82A6.9070104@redhat.com>
On Mon, Dec 08, 2008 at 03:25:10PM -0500, Rik van Riel wrote:
> KOSAKI Motohiro wrote:
>
> >+ for (o = order; o < MAX_ORDER; o++) {
> >+ if (z->free_area[o].nr_free)
> >+ return 1;
>
> Since page breakup and coalescing always manipulates .nr_free,
> I wonder if it would make sense to pack the nr_free variables
> in their own cache line(s), so we have fewer cache misses when
> going through zone_watermark_ok() ?
For order-0 allocations, they should not be touched at all. For
higher order allocations in performance critical paths, we should
try to fix those to use order-0 ;)
--
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>
next prev parent reply other threads:[~2008-12-10 5:09 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-28 11:08 [PATCH] vmscan: skip freeing memory from zones with lots free Rik van Riel
2008-11-28 11:08 ` Rik van Riel
2008-11-28 11:30 ` Peter Zijlstra
2008-11-28 11:30 ` Peter Zijlstra
2008-11-28 22:43 ` Johannes Weiner
2008-11-28 22:43 ` Johannes Weiner
2008-11-29 7:19 ` Andrew Morton
2008-11-29 7:19 ` Andrew Morton
2008-11-29 10:55 ` KOSAKI Motohiro
2008-11-29 10:55 ` KOSAKI Motohiro
2008-12-08 13:00 ` KOSAKI Motohiro
2008-12-08 13:00 ` KOSAKI Motohiro
2008-12-08 13:03 ` KOSAKI Motohiro
2008-12-08 13:03 ` KOSAKI Motohiro
2008-12-08 17:48 ` KOSAKI Motohiro
2008-12-08 17:48 ` KOSAKI Motohiro
2008-12-10 5:07 ` Nick Piggin
2008-12-10 5:07 ` Nick Piggin
2008-12-08 20:25 ` Rik van Riel
2008-12-08 20:25 ` Rik van Riel
2008-12-10 5:09 ` Nick Piggin [this message]
2008-12-10 5:09 ` Nick Piggin
2008-12-12 5:50 ` KOSAKI Motohiro
2008-11-29 16:47 ` Rik van Riel
2008-11-29 16:47 ` Rik van Riel
2008-11-29 17:45 ` Andrew Morton
2008-11-29 17:45 ` Andrew Morton
2008-11-29 17:58 ` Rik van Riel
2008-11-29 17:58 ` Rik van Riel
2008-11-29 18:26 ` Andrew Morton
2008-11-29 18:26 ` Andrew Morton
2008-11-29 18:41 ` Rik van Riel
2008-11-29 18:41 ` Rik van Riel
2008-11-29 18:51 ` Andrew Morton
2008-11-29 18:51 ` Andrew Morton
2008-11-29 18:59 ` Rik van Riel
2008-11-29 18:59 ` Rik van Riel
2008-11-29 20:29 ` Andrew Morton
2008-11-29 20:29 ` Andrew Morton
2008-11-29 21:35 ` Rik van Riel
2008-11-29 21:35 ` Rik van Riel
2008-11-29 21:57 ` Andrew Morton
2008-11-29 21:57 ` Andrew Morton
2008-11-29 22:07 ` Rik van Riel
2008-11-29 22:07 ` Rik van Riel
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=20081210050938.GF8434@wotan.suse.de \
--to=npiggin@suse.de \
--cc=akpm@linux-foundation.org \
--cc=cl@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.