From: Andi Kleen <ak@suse.de>
To: Eric Dumazet <dada1@cosmosbay.com>
Cc: Christoph Lameter <clameter@sgi.com>,
William Lee Irwin III <wli@holomorphy.com>,
Nick Piggin <npiggin@suse.de>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Linux Memory Management List <linux-mm@kvack.org>,
linux-arch@vger.kernel.org
Subject: Re: [rfc] increase struct page size?!
Date: Sun, 20 May 2007 14:56:25 +0200 [thread overview]
Message-ID: <200705201456.26283.ak@suse.de> (raw)
In-Reply-To: <464FCA28.9040009@cosmosbay.com>
On Sunday 20 May 2007 06:10:16 Eric Dumazet wrote:
> Christoph Lameter a ecrit :
> > On Sat, 19 May 2007, William Lee Irwin III wrote:
> >
> >> However, there are numerous optimizations and features made possible
> >> with flag bits, which might as could be made cheap by padding struct
> >> page up to the next highest power of 2 bytes with space for flag bits.
> >
> > Well the last time I tried to get this by Andi we became a bit concerned
> > when we realized that the memory map would grow by 14% in size. Given
> > that 4k page size challenged platforms have a huge amount of page structs
> > that growth is significant. I think it would be fine to do it for IA64
> > with 16k page size but not for x86_64.
>
> This reminds me Andi attempted in the past to convert 'flags' to a 32 bits field :
>
> http://marc.info/?l=linux-kernel&m=107903527523739&w=2
>
> I wonder why this idea was not taken, saving 2MB per GB of memory is nice :)
It made sense in 2.4, but in 2.6 it doesn't actually save any memory because
there is no field to put into the freed padding.
Besides with the scarcity of pageflags it might make sense to do "64 bit only"
flags at some point.
-Andi
--
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:[~2007-05-20 12:56 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-05-18 4:08 Nick Piggin
2007-05-18 4:47 ` David Miller, Nick Piggin
2007-05-18 5:12 ` Nick Piggin
2007-05-18 5:22 ` David Miller, Nick Piggin
2007-05-18 5:31 ` Nick Piggin
2007-05-18 18:15 ` Christoph Lameter
2007-05-18 7:19 ` Andrew Morton
2007-05-18 7:32 ` Nick Piggin
2007-05-18 7:43 ` Andrew Morton
2007-05-18 7:59 ` Nick Piggin
2007-05-18 9:42 ` David Howells
2007-05-19 1:30 ` Nick Piggin
2007-05-18 12:06 ` Andi Kleen
2007-05-18 15:42 ` Hugh Dickins
2007-05-19 1:22 ` Nick Piggin
2007-05-19 17:53 ` William Lee Irwin III
2007-05-20 22:50 ` Matthew Wilcox
2007-05-18 18:14 ` Christoph Lameter
2007-05-18 20:37 ` Luck, Tony
2007-05-21 6:28 ` KAMEZAWA Hiroyuki
2007-05-19 1:25 ` Nick Piggin
2007-05-19 2:03 ` [rfc] increase struct page size?! (now sparsemem vmemmap) Christoph Lameter
2007-05-19 15:43 ` Andy Whitcroft
2007-05-19 18:15 ` [rfc] increase struct page size?! William Lee Irwin III
2007-05-19 18:25 ` Christoph Lameter
2007-05-20 4:10 ` Eric Dumazet
2007-05-20 12:56 ` Andi Kleen [this message]
2007-05-21 17:08 ` Christoph Lameter
2007-05-22 0:30 ` KAMEZAWA Hiroyuki
2007-05-22 0:38 ` Christoph Lameter
2007-05-22 0:58 ` KAMEZAWA Hiroyuki
2007-05-22 9:44 ` Geert Uytterhoeven
2007-05-19 22:09 ` Andrew Morton
2007-05-20 7:26 ` William Lee Irwin III
2007-05-21 9:12 ` Helge Hafting
2007-05-21 9:45 ` Nick Piggin
2007-05-20 5:22 ` Nick Piggin
2007-05-20 8:46 ` William Lee Irwin III
2007-05-20 9:25 ` Nick Piggin
2007-05-21 8:08 ` William Lee Irwin III
2007-05-21 9:27 ` Nick Piggin
2007-05-21 11:26 ` William Lee Irwin III
2007-05-22 0:52 ` Nick Piggin
2007-05-21 22:43 ` Matt Mackall
2007-05-22 1:08 ` Nick Piggin
2007-05-22 1:13 ` Christoph Lameter
2007-05-22 1:39 ` William Lee Irwin III
2007-05-22 1:57 ` Nick Piggin
2007-05-22 5:04 ` William Lee Irwin III
2007-05-22 6:24 ` Nick Piggin
2007-05-22 10:59 ` William Lee Irwin III
2007-05-21 9:31 ` Eric Dumazet
2007-05-21 17:06 ` Christoph Lameter
2007-05-20 17:13 ` Andrea Arcangeli
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=200705201456.26283.ak@suse.de \
--to=ak@suse.de \
--cc=clameter@sgi.com \
--cc=dada1@cosmosbay.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=npiggin@suse.de \
--cc=wli@holomorphy.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox