Re: [PATCH] Export symbol ksize()

[Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>]

On Sun, 15 Feb 2009, Matt Mackall wrote:
> On Sun, 2009-02-15 at 17:00 -0800, Andrew Morton wrote:
> > On Sun, 15 Feb 2009 17:49:41 -0600 Matt Mackall <mpm@selenic.com> wrote:
> 
> > The whole concept is quite hacky and nasty, isn't it?.
> 
> It is, which is part of why we were trying to kill it. The primary users
> were thing growing buffers ala realloc. So we were pushing to change the
> callers to just do a realloc. But IPSEC doesn't fit well into that mold.
> 
> The fundamental problem here for networking is that 1500 is not very
> close to a power of two and just about everything in the VM wants it to
> be. If we could get SKBs fitting more nicely in memory, I think it would
> cease to be a concern.

Does it help to remind that 4 KiB - 2 * 1500 = 1096 \approx 1024?
(hmm, the difference is 72 \approx 64)?

If 1500 is so common as an allocation size, it may make sense to start
special-casing it...

With kind regards,

Geert Uytterhoeven
Software Architect

Sony Techsoft Centre Europe
The Corporate Village . Da Vincilaan 7-D1 . B-1935 Zaventem . Belgium

Phone:    +32 (0)2 700 8453
Fax:      +32 (0)2 700 8622
E-mail:   Geert.Uytterhoeven@sonycom.com
Internet: http://www.sony-europe.com/

A division of Sony Europe (Belgium) N.V.
VAT BE 0413.825.160 . RPR Brussels
Fortis . BIC GEBABEBB . IBAN BE41293037680010

--
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>