Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 12 Apr 2007 15:40:48 +0100 (BST)
From:      Robert Watson <rwatson@FreeBSD.org>
To:        Dag-Erling =?iso-8859-1?Q?Sm=F8rgrav?= <des@des.no>
Cc:        Randall Stewart <rrs@cisco.com>, freebsd-current@freebsd.org, Ivan Voras <ivoras@fer.hr>, Brad Penoff <penoff@cs.ubc.ca>, Janardhan Iyengar <iyengar@conncoll.edu>
Subject:   Re: CPU utilization
Message-ID:  <20070412153930.A99718@fledge.watson.org>
In-Reply-To: <86d529zxci.fsf@dwp.des.no>
References:  <461E0078.3050001@cisco.com> <evl00c$89j$1@sea.gmane.org> <461E092B.4080001@cisco.com> <86d529zxci.fsf@dwp.des.no>

next in thread | previous in thread | raw e-mail | index | archive | help
  This message is in MIME format.  The first part should be readable text,
  while the remaining parts are likely unreadable without MIME-aware tools.

--0-1967887432-1176388848=:99718
Content-Type: TEXT/PLAIN; charset=iso-8859-1; format=flowed
Content-Transfer-Encoding: QUOTED-PRINTABLE


On Thu, 12 Apr 2007, Dag-Erling Sm=F8rgrav wrote:

> Randall Stewart <rrs@cisco.com> writes:
>> machdep.hyperthreading_allowed: 0
>
> Note that enabling hyperthreading is more likely to harm performance than=
 to=20
> help it.  You should just disable it in the BIOS, and run a UP kernel.

Historically this has been true, but some more recent results I've seen=20
suggest that both hyperthreading hardware has improved, and the efficiency =
of=20
our SMP implementation and scheduler has lead to it being more effective us=
ed.=20
I would reevaluate this on more modern hardware and using a more recent ker=
nel=20
before assuming this remains true for your application.

Robert N M Watson
Computer Laboratory
University of Cambridge
--0-1967887432-1176388848=:99718--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070412153930.A99718>