From: Matt Mackall <mpm@selenic.com>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Pekka Enberg <penberg@cs.helsinki.fi>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
Christoph Lameter <cl@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-crypto@vger.kernel.org, Geert.Uytterhoeven@sonycom.com
Subject: Re: [PATCH] Export symbol ksize()
Date: Sun, 15 Feb 2009 19:28:46 -0600 [thread overview]
Message-ID: <1234747726.5669.215.camel@calx> (raw)
In-Reply-To: <20090216012110.GA13575@gondor.apana.org.au>
On Mon, 2009-02-16 at 09:21 +0800, Herbert Xu wrote:
> On Sun, Feb 15, 2009 at 05:00:52PM -0800, Andrew Morton wrote:
> >
> > But kmem_cache_size() would tell you how much extra secret memory there
> > is available after the object?
> >
> > How that gets along with redzoning is a bit of a mystery though.
> >
> > The whole concept is quite hacky and nasty, isn't it?. Does
> > networking/crypto actually show any gain from pulling this stunt?
>
> I see no point in calling ksize on memory that's not kmalloced.
> So no there is nothing to be gained from having kmem_cache_ksize.
>
> However, for kmalloced memory we're wasting hundreds of bytes
> for the standard 1500 byte allocation without ksize which means
> that we're doing reallocations (and sometimes copying) when it
> isn't necessary.
Yeah. That sucks. We should probably stick in an skb-friendly slab size
and see what happens on network benchmarks.
--
http://selenic.com : development and support for Mercurial and Linux
WARNING: multiple messages have this Message-ID (diff)
From: Matt Mackall <mpm@selenic.com>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Pekka Enberg <penberg@cs.helsinki.fi>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
Christoph Lameter <cl@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-crypto@vger.kernel.org, Geert.Uytterhoeven@sonycom.com
Subject: Re: [PATCH] Export symbol ksize()
Date: Sun, 15 Feb 2009 19:28:46 -0600 [thread overview]
Message-ID: <1234747726.5669.215.camel@calx> (raw)
In-Reply-To: <20090216012110.GA13575@gondor.apana.org.au>
On Mon, 2009-02-16 at 09:21 +0800, Herbert Xu wrote:
> On Sun, Feb 15, 2009 at 05:00:52PM -0800, Andrew Morton wrote:
> >
> > But kmem_cache_size() would tell you how much extra secret memory there
> > is available after the object?
> >
> > How that gets along with redzoning is a bit of a mystery though.
> >
> > The whole concept is quite hacky and nasty, isn't it?. Does
> > networking/crypto actually show any gain from pulling this stunt?
>
> I see no point in calling ksize on memory that's not kmalloced.
> So no there is nothing to be gained from having kmem_cache_ksize.
>
> However, for kmalloced memory we're wasting hundreds of bytes
> for the standard 1500 byte allocation without ksize which means
> that we're doing reallocations (and sometimes copying) when it
> isn't necessary.
Yeah. That sucks. We should probably stick in an skb-friendly slab size
and see what happens on network benchmarks.
--
http://selenic.com : development and support for Mercurial and Linux
--
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:[~2009-02-16 1:29 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-10 13:21 [PATCH] Export symbol ksize() Kirill A. Shutemov
2009-02-10 13:21 ` Kirill A. Shutemov
2009-02-10 13:35 ` Pekka Enberg
2009-02-10 13:35 ` Pekka Enberg
2009-02-10 13:46 ` Kirill A. Shutemov
2009-02-10 14:06 ` Pekka J Enberg
2009-02-10 14:06 ` Pekka J Enberg
2009-02-10 14:06 ` Pekka J Enberg
2009-02-12 10:43 ` Herbert Xu
2009-02-12 10:43 ` Herbert Xu
2009-02-12 10:45 ` Pekka Enberg
2009-02-12 10:45 ` Pekka Enberg
2009-02-12 10:50 ` Herbert Xu
2009-02-12 10:50 ` Herbert Xu
2009-02-12 13:10 ` Nick Piggin
2009-02-12 13:10 ` Nick Piggin
2009-02-12 23:09 ` Herbert Xu
2009-02-12 23:09 ` Herbert Xu
2009-02-12 23:37 ` Matt Mackall
2009-02-12 23:37 ` Matt Mackall
2009-02-13 13:20 ` Nick Piggin
2009-02-13 13:20 ` Nick Piggin
2009-02-13 16:57 ` Kyle Moffett
2009-02-13 16:57 ` Kyle Moffett
2009-02-12 15:55 ` Pekka Enberg
2009-02-12 15:55 ` Pekka Enberg
2009-02-12 23:09 ` Herbert Xu
2009-02-12 23:09 ` Herbert Xu
2009-02-15 21:36 ` Andrew Morton
2009-02-15 21:36 ` Andrew Morton
2009-02-15 21:43 ` Matt Mackall
2009-02-15 21:43 ` Matt Mackall
2009-02-15 21:55 ` Andrew Morton
2009-02-15 21:55 ` Andrew Morton
2009-02-15 23:49 ` Matt Mackall
2009-02-15 23:49 ` Matt Mackall
2009-02-16 1:00 ` Andrew Morton
2009-02-16 1:00 ` Andrew Morton
2009-02-16 1:21 ` Herbert Xu
2009-02-16 1:21 ` Herbert Xu
2009-02-16 1:28 ` Matt Mackall [this message]
2009-02-16 1:28 ` Matt Mackall
2009-02-16 1:52 ` Herbert Xu
2009-02-16 1:52 ` Herbert Xu
2009-02-16 1:54 ` Matt Mackall
2009-02-16 1:54 ` Matt Mackall
2009-02-16 1:57 ` Herbert Xu
2009-02-16 1:57 ` Herbert Xu
2009-02-16 1:38 ` Matt Mackall
2009-02-16 1:38 ` Matt Mackall
2009-02-17 8:43 ` Geert Uytterhoeven
2009-02-17 8:43 ` Geert Uytterhoeven
2009-02-17 8:43 ` Geert Uytterhoeven
2009-02-17 16:17 ` Christoph Lameter
2009-02-17 16:17 ` Christoph Lameter
2009-02-17 17:03 ` Pekka Enberg
2009-02-17 17:03 ` Pekka Enberg
2009-02-17 17:06 ` Christoph Lameter
2009-02-17 17:06 ` Christoph Lameter
2009-02-16 13:56 ` Johannes Weiner
2009-02-16 13:56 ` Johannes Weiner
2009-02-16 14:09 ` Pekka Enberg
2009-02-16 14:09 ` Pekka Enberg
2009-02-16 16:32 ` Joe Perches
2009-02-16 16:32 ` Joe Perches
2009-02-16 17:29 ` Pekka Enberg
2009-02-16 17:29 ` 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=1234747726.5669.215.camel@calx \
--to=mpm@selenic.com \
--cc=Geert.Uytterhoeven@sonycom.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux-foundation.org \
--cc=herbert@gondor.apana.org.au \
--cc=kirill@shutemov.name \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=penberg@cs.helsinki.fi \
/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.