Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 18 Jan 2007 21:01:41 +1100 (EST)
From:      Bruce Evans <bde@zeta.org.au>
To:        Suleiman Souhlal <ssouhlal@FreeBSD.org>
Cc:        Maxim Sobolev <sobomax@FreeBSD.org>, Ivan Voras <ivoras@fer.hr>, Attilio Rao <attilio@FreeBSD.org>, freebsd-current@FreeBSD.org, freebsd-arch@FreeBSD.org
Subject:   Re: [PATCH] Mantaining turnstile aligned to 128 bytes in i386 CPUs
Message-ID:  <20070118204641.M3613@besplex.bde.org>
In-Reply-To: <45AF23DE.6030801@FreeBSD.org>
References:  <3bbf2fe10607250813w8ff9e34pc505bf290e71758@mail.gmail.com> <3bbf2fe10607281004o6727e976h19ee7e054876f914@mail.gmail.com> <3bbf2fe10701160851r79b04464m2cbdbb7f644b22b6@mail.gmail.com> <20070116154258.568e1aaf@pleiades.nextvenue.com> <b1fa29170701161355lc021b90o35fa5f9acb5749d@mail.gmail.com> <eoji7s$cit$2@sea.gmane.org> <b1fa29170701161425n7bcfe1e5m1b8c671caf3758db@mail.gmail.com> <eojlnb$qje$1@sea.gmane.org> <3bbf2fe10701161525j6ad9292y93502b8df0f67aa9@mail.gmail.com> <45AD6DFA.6030808@FreeBSD.org> <3bbf2fe10701161655p5e686b52n7340b3100ecfab93@mail.gmail.com> <200701172022.l0HKMYV8053837@apollo.backplane.com> <20070118113831.A11834@delplex.bde.org> <45AF23DE.6030801@FreeBSD.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 17 Jan 2007, Suleiman Souhlal wrote:

> Bruce Evans wrote:
>> I haven't tried this, but have seen and partly worked sensitivity to
>> linear KVA maps not being physically (non)linear enough.  Some CPUs
>> and/or memory systems are remarkably sensitive to bank interleave.
>> FreeBSD's page coloring doesn't know anything about banks, ...
>
> About page coloring: Don't amd64 CPUs have virtually indexed, physically
> tagged caches? If so, wouldn't it make sense to turn off page coloring,
> since it's useless for virtually indexed caches (and probably hurts things
> a bit)?

I think superpages will soon turn off coloring.  Not sure if this is
right.  How is copying and zeroing a whole superpage at a time avoided?

IIRC, my benchmarks (and LMbench) show some small positive benefits for
page coloring on amd64.  I don't remember exactly what they are, just
that they are smaller than on AthlonXP.

Bruce



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070118204641.M3613>