From owner-freebsd-smp@FreeBSD.ORG Mon Sep 27 16:32:00 2004 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 16E4816A4CE for ; Mon, 27 Sep 2004 16:32:00 +0000 (GMT) Received: from cs.columbia.edu (cs.columbia.edu [128.59.16.20]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6B23343D2D for ; Mon, 27 Sep 2004 16:31:59 +0000 (GMT) (envelope-from mre2007@cs.columbia.edu) Received: from hydra.cs.columbia.edu (IDENT:RhCZNJvS+zCNuYmrjXBJJxFEXauvQOos@hydra.cs.columbia.edu [128.59.16.129]) by cs.columbia.edu (8.12.10/8.12.10) with ESMTP id i8RGVowG029795 verify=NOT); Mon, 27 Sep 2004 12:31:55 -0400 (EDT) Received: from webmail.cs.columbia.edu (IDENT:TxSqIM1yBY/yOySOWwln8cNM0l38b0Z9@localhost [127.0.0.1]) i8RGVnAr029072; Mon, 27 Sep 2004 12:31:49 -0400 Received: from 148.104.5.33 (SquirrelMail authenticated user mre2007) by webmail.cs.columbia.edu with HTTP; Mon, 27 Sep 2004 12:31:50 -0400 (EDT) Message-ID: <15450.148.104.5.33.1096302710.squirrel@webmail.cs.columbia.edu> In-Reply-To: References: Date: Mon, 27 Sep 2004 12:31:50 -0400 (EDT) From: mre2007@cs.columbia.edu To: "Dave Dolson" User-Agent: SquirrelMail/1.4.2 MIME-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Priority: 3 Importance: Normal X-PMX-Version: 4.7.0.111621, Antispam-Engine: 2.0.1.0, Antispam-Data: 2004.9.26.0 X-PerlMx-Spam: Gauge=X, Probability=10%, Report='PRIORITY_NO_NAME 0.716, NO_REAL_NAME 0, __CT 0, __CTE 0, __CT_TEXT_PLAIN 0, __HAS_MSGID 0, __HAS_X_PRIORITY 0, __MIME_VERSION 0, __SANE_MSGID 0' cc: freebsd-smp@freebsd.org Subject: RE: "Kernel Hacking"/Developing on a HT CPU versus "physical" CPUs X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 27 Sep 2004 16:32:00 -0000 Dave: yes this makes sense! So, does the scheduler take this into consideration? -Marc > Here is one example: > If you have dual HT processors, this looks like 4 CPUs to the O/S. > For performance reasons, the scheduler should not treat them equally. > If there are two threads to run, they should be put on different physical > processors (vs. two hyperthreads of the same processor). > > > David Dolson (ddolson@sandvine.com, www.sandvine.com) > > >> -----Original Message----- >> From: owner-freebsd-smp@freebsd.org >> [mailto:owner-freebsd-smp@freebsd.org]On Behalf Of >> mre2007@cs.columbia.edu >> Sent: Saturday, September 25, 2004 10:48 AM >> To: freebsd-smp@freebsd.org >> Subject: "Kernel Hacking"/Developing on a HT CPU versus >> "physical" CPUs >> >> >> Hey, I was wondering if from a developing/"kernel hacking" >> standpoint, are >> hyperthreading and two "physical" CPUs any different? At what >> point do the >> differences have to be taken into consideration when working on the >> FreeBSD kernel/scheduler/etc? I'm looking to start contributing to the >> FreeBSD project and am trying to get some hardware set aside. >> >> Thanks! >> -Marc >> _______________________________________________ >> freebsd-smp@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-smp >> To unsubscribe, send any mail to "freebsd-smp-unsubscribe@freebsd.org" >> >