From: Linus Torvalds <torvalds@linux-foundation.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@infradead.org>, linux-kernel@vger.kernel.org
Subject: Re: upcoming kerneloops.org item: get_page_from_freelist
Date: Wed, 24 Jun 2009 09:52:17 -0700 (PDT) [thread overview]
Message-ID: <alpine.LFD.2.01.0906240948430.3240@localhost.localdomain> (raw)
In-Reply-To: <20090624094622.d0b0fd82.akpm@linux-foundation.org>
On Wed, 24 Jun 2009, Andrew Morton wrote:
>
> Well yes. Using GFP_NOFAIL on a higher-order allocation is bad.
Yes, but your definition of "higher order" is incorrect.
At the very least, we should change the "order > 0" to "order > 1".
As I already mentioned, SLAB uses order-1 allocations in order to not have
excessive fragmentation for small kmalloc/slab's that would otherwise
waste tons of memory.
Think network packets at 1500 bytes each. You can allocate two per page,
or five per 2-pages. That's a 25% memory usage difference!
And getting an order-1 allocation is simply not that much harder than an
order-0 one. It starts getting hard once you get to order-3 or more.
Linus
next prev parent reply other threads:[~2009-06-24 16:52 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-24 15:07 Arjan van de Ven
2009-06-24 16:46 ` Andrew Morton
2009-06-24 16:52 ` Linus Torvalds [this message]
2009-06-24 16:55 ` Pekka Enberg
2009-06-24 16:56 ` Pekka Enberg
2009-06-24 17:00 ` Pekka Enberg
2009-06-24 17:55 ` Andrew Morton
2009-06-24 17:53 ` Pekka Enberg
2009-06-24 18:30 ` Andrew Morton
2009-06-24 18:42 ` Linus Torvalds
2009-06-24 18:44 ` Pekka Enberg
2009-06-24 18:50 ` Linus Torvalds
2009-06-24 19:12 ` Pekka J Enberg
2009-06-24 19:21 ` Linus Torvalds
2009-06-24 19:06 ` Andrew Morton
2009-06-24 19:16 ` Linus Torvalds
2009-06-24 19:36 ` Andrew Morton
2009-06-24 19:46 ` Linus Torvalds
2009-06-24 19:47 ` Linus Torvalds
2009-06-24 20:01 ` Andrew Morton
2009-06-24 20:13 ` Linus Torvalds
2009-06-24 20:40 ` Linus Torvalds
2009-06-24 22:07 ` Andrew Morton
2009-06-25 4:05 ` Nick Piggin
2009-06-25 13:25 ` Theodore Tso
2009-06-25 18:51 ` David Rientjes
2009-06-25 19:38 ` Theodore Tso
2009-06-25 19:44 ` Theodore Tso
2009-06-25 19:55 ` Andrew Morton
2009-06-25 20:11 ` Linus Torvalds
2009-06-25 20:22 ` Linus Torvalds
2009-06-25 20:36 ` David Rientjes
2009-06-25 20:51 ` Linus Torvalds
2009-06-25 22:25 ` David Rientjes
2009-06-26 8:51 ` Nick Piggin
2009-06-25 20:18 ` David Rientjes
2009-06-25 20:37 ` Theodore Tso
2009-06-25 21:05 ` Joel Becker
2009-06-25 21:26 ` Andreas Dilger
2009-06-25 22:05 ` Theodore Tso
2009-06-25 22:11 ` Eric Sandeen
2009-06-26 1:11 ` Theodore Tso
2009-06-26 5:16 ` Pekka J Enberg
2009-06-26 8:56 ` Nick Piggin
2009-06-26 8:58 ` Pekka Enberg
2009-06-26 9:07 ` Nick Piggin
2009-06-29 21:06 ` Christoph Lameter
2009-06-30 7:59 ` Nick Piggin
2009-06-26 14:41 ` Eric Sandeen
2009-06-29 21:15 ` Christoph Lameter
2009-06-29 21:20 ` Eric Sandeen
2009-06-29 22:35 ` Christoph Lameter
2009-06-25 19:55 ` Jens Axboe
2009-06-25 20:08 ` Jens Axboe
2009-06-24 21:56 ` Andrew Morton
2009-06-25 4:14 ` Nick Piggin
2009-06-25 8:21 ` David Rientjes
2009-06-29 15:30 ` Mel Gorman
2009-06-29 19:20 ` Andrew Morton
2009-06-30 11:00 ` Mel Gorman
2009-06-30 19:35 ` David Rientjes
2009-06-30 20:32 ` Mel Gorman
2009-06-30 20:51 ` David Rientjes
2009-07-01 10:22 ` Mel Gorman
2009-06-29 23:35 ` David Rientjes
2009-06-30 7:47 ` Nick Piggin
2009-06-30 8:13 ` David Rientjes
2009-06-30 8:24 ` Nick Piggin
2009-06-30 8:41 ` David Rientjes
2009-06-30 9:09 ` Nick Piggin
2009-06-30 19:47 ` David Rientjes
2009-06-30 6:27 ` Pavel Machek
2009-06-28 10:16 ` Pavel Machek
2009-06-28 18:01 ` Linus Torvalds
2009-06-28 18:27 ` Arjan van de Ven
2009-06-28 18:36 ` Linus Torvalds
2009-06-30 7:35 ` Pavel Machek
2009-06-24 18:43 ` Pekka Enberg
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=alpine.LFD.2.01.0906240948430.3240@localhost.localdomain \
--to=torvalds@linux-foundation.org \
--cc=akpm@linux-foundation.org \
--cc=arjan@infradead.org \
--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
all inboxes | Powered by JetHome®