[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [microblaze-uclinux] Re: [PATCH 6/6] Add support for __read_mostly to linux/cache.h
- To: Christoph Lameter <cl@xxxxxxxxx>
- Subject: Re: [microblaze-uclinux] Re: [PATCH 6/6] Add support for __read_mostly to linux/cache.h
- From: "Edgar E. Iglesias" <edgar.iglesias@xxxxxxxxx>
- Date: Fri, 1 May 2009 23:47:13 +0200
- Cc: Sam Ravnborg <sam@xxxxxxxxxxxx>, Tim Abbott <tabbott@xxxxxxx>, Anders Kaseorg <andersk@xxxxxxx>, Waseem Daher <wdaher@xxxxxxx>, Denys Vlasenko <vda.linux@xxxxxxxxxxxxxx>, Jeff Arnold <jbarnold@xxxxxxx>, Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>, Bryan Wu <cooloney@xxxxxxxxxx>, Chris Zankel <chris@xxxxxxxxxx>, Cyrill Gorcunov <gorcunov@xxxxxxxxxx>, David Howells <dhowells@xxxxxxxxxx>, "David S. Miller" <davem@xxxxxxxxxxxxx>, dev-etrax@xxxxxxxx, Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>, Greg Ungerer <gerg@xxxxxxxxxxx>, Haavard Skinnemoen <hskinnemoen@xxxxxxxxx>, Heiko Carstens <heiko.carstens@xxxxxxxxxx>, Helge Deller <deller@xxxxxx>, Hirokazu Takata <takata@xxxxxxxxxxxxxx>, "H. Peter Anvin" <hpa@xxxxxxxxx>, Ingo Molnar <mingo@xxxxxxxxxx>, Jeff Dike <jdike@xxxxxxxxxxx>, Jesper Nilsson <jesper.nilsson@xxxxxxxx>, Kyle McMartin <kyle@xxxxxxxxxxx>, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, linux-alpha@xxxxxxxxxxxxxxx, linux-am33-list@xxxxxxxxxx, linux-arm-kernel@xxxxxxxxxxxxxxxxxxxxxx, linux-ia64@xxxxxxxxxxxxxxx, linux-m32r@xxxxxxxxxxxxxxxxx, linux-m68k@xxxxxxxxxxxxxxx, linux-mips@xxxxxxxxxxxxxx, linux-parisc@xxxxxxxxxxxxxxx, linuxppc-dev@xxxxxxxxxx, linux-s390@xxxxxxxxxxxxxxx, linux-sh@xxxxxxxxxxxxxxx, Martin Schwidefsky <schwidefsky@xxxxxxxxxx>, Michal Simek <monstr@xxxxxxxxx>, microblaze-uclinux@xxxxxxxxxxxxxx, Mikael Starvik <starvik@xxxxxxxx>, Paul Mackerras <paulus@xxxxxxxxx>, Paul Mundt <lethal@xxxxxxxxxxxx>, Ralf Baechle <ralf@xxxxxxxxxxxxxx>, Richard Henderson <rth@xxxxxxxxxxx>, Roman Zippel <zippel@xxxxxxxxxxxxxx>, Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>, sparclinux@xxxxxxxxxxxxxxx, Thomas Gleixner <tglx@xxxxxxxxxxxxx>, Tony Luck <tony.luck@xxxxxxxxx>, uclinux-dist-devel@xxxxxxxxxxxxxxxxxxxx, user-mode-linux-devel@xxxxxxxxxxxxxxxxxxxxx, Yoshinori Sato <ysato@xxxxxxxxxxxxxxxxxxxx>
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:received:date:from:to:cc :subject:message-id:references:mime-version:content-type :content-disposition:in-reply-to:user-agent; bh=mng4vw6dm21qh7/q+QJctc3NV+qYTC1IRY7MqV61E1U=; b=yBhjkmWl83f7r+hD4ofFb3pGwHcUU/Rw8QFdmScKLpm4U4JnEiUC5QRpAZ3DO9iTsY FeIat+TiehhbxDJdQJ/8GsRMR3f2fqLUqaiOC9A9PFgCUVLOSDXxqzx5Q0AC7FdRgDIB y4ZRBrHTKPsXMwEjTCbPD7S/yEmR3zDWjPae0=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=date:from:to:cc:subject:message-id:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; b=IaXKigzjNJmm/l6CdDsX1aytbuDHM/BA52TPzXQC4HWXmLGDqD0NdT3qPNgDO2WtBB 5HdwBiXncwZy/foVhIUgYzpMhY7wzdZJpgHaJ4RMi6/A6aletBE/QnK2BcYr1Ogfl0Ks uGE64q2Ltz1wdIGipZExqsVIovu0Sq0yUNf4o=
- In-reply-to: <alpine.DEB.1.10.0905010948140.18324@xxxxxxxxx>
- References: <1241119956-31453-1-git-send-email-tabbott@xxxxxxx> <1241119956-31453-2-git-send-email-tabbott@xxxxxxx> <1241119956-31453-3-git-send-email-tabbott@xxxxxxx> <1241119956-31453-4-git-send-email-tabbott@xxxxxxx> <1241119956-31453-5-git-send-email-tabbott@xxxxxxx> <1241119956-31453-6-git-send-email-tabbott@xxxxxxx> <1241119956-31453-7-git-send-email-tabbott@xxxxxxx> <20090501094407.GD18326@xxxxxxxxxxxxxxxxxxx> <alpine.DEB.1.10.0905010948140.18324@xxxxxxxxx>
- Reply-to: microblaze-uclinux@xxxxxxxxxxxxxx
- Sender: owner-microblaze-uclinux@xxxxxxxxxxxxxxxxxxxx
- User-agent: Mutt/1.5.16 (2007-06-09)
On Fri, May 01, 2009 at 09:52:18AM -0400, Christoph Lameter wrote:
> On Fri, 1 May 2009, Sam Ravnborg wrote:
>
> > Are there any specific reason why we do not support read_mostly on all
> > architectures?
>
> Not that I know of.
>
> > read_mostly is about grouping rarely written data together
> > so what is needed is to introduce this section in the remaining
> > archtectures.
> >
> > Christoph - git log says you did the inital implmentation.
> > Do you agree?
>
> Yes.
>
> There is some concern that __read_mostly is needlessly applied to
> numerous variables that are not used in hot code paths. This may make
> __read_mostly ineffective and actually increase the cache footprint of a
> function since global variables are no longer in the same cacheline. If
> such a function is called and the caches are cold then two cacheline
> fetches have to be done instead of one.
FWIW I think that's a valid concern. Also, I think one can question the
value of __read_mostly for write-through caches, given the mentioned
concern it probably makes things worse for those. IMO there should be
a way to turn it off for arch's that know it's no good for them.
Cheers
___________________________
microblaze-uclinux mailing list
microblaze-uclinux@xxxxxxxxxxxxxx
Project Home Page : http://www.itee.uq.edu.au/~jwilliams/mblaze-uclinux
Mailing List Archive : http://www.itee.uq.edu.au/~listarch/microblaze-uclinux/