From owner-freebsd-hardware@FreeBSD.ORG Sat Oct 4 17:05:44 2003 Return-Path: Delivered-To: freebsd-hardware@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D119216A4B3 for ; Sat, 4 Oct 2003 17:05:44 -0700 (PDT) Received: from maelstrom.waterspout.com (rrcs-ma-24-56-74-54.biz.rr.com [24.56.74.54]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9DC0244003 for ; Sat, 4 Oct 2003 17:05:43 -0700 (PDT) (envelope-from csg@waterspout.com) Received: from maelstrom.waterspout.com (localhost [127.0.0.1]) h9505aPH043687; Sat, 4 Oct 2003 19:05:36 -0500 (CDT) (envelope-from csg@waterspout.com) Received: (from csg@localhost)h9505ZNI043686; Sat, 4 Oct 2003 19:05:35 -0500 (CDT) X-Authentication-Warning: maelstrom.waterspout.com: csg set sender to csg@waterspout.com using -f Date: Sat, 4 Oct 2003 19:05:35 -0500 From: "C. Stephen Gunn" To: "Marc G. Fournier" Message-ID: <20031005000535.GA40750@waterspout.com> References: <200310021105.10872.john@johnrshannon.com> <20031002170952.GF15256@sentex.net> <20031002141921.K25730@ganymede.hub.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20031002141921.K25730@ganymede.hub.org> User-Agent: Mutt/1.4.1i cc: Damian Gerow cc: hardware@freebsd.org Subject: Re: Hyperthreading Kernel Configuration - 5.1 X-BeenThere: freebsd-hardware@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: General discussion of FreeBSD hardware List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 05 Oct 2003 00:05:44 -0000 Marc G. Fournier (scrappy@hub.org) likely uttered: > My understanding is that the speed improvements (or degradation) depend on > the use of the machine ... for instance, I've heard that a high I/O server > will be slower with HTT enabled, and, from my experience with one such, it > is so ... I'm not sure what circumstances would show improvements though Most likly the other end of the spectrum. I've seem some transactional loads that require modest compute (say .2 seconds) that seem to do quite well on a Hyperthread box. - Steve