From owner-freebsd-current@FreeBSD.ORG Sun Oct 8 22:55:46 2006 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 38F0616A417 for ; Sun, 8 Oct 2006 22:55:46 +0000 (UTC) (envelope-from kmacy@fsmware.com) Received: from demos.bsdclusters.com (demos.bsdclusters.com [69.55.225.36]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4DB3A43D95 for ; Sun, 8 Oct 2006 22:55:25 +0000 (GMT) (envelope-from kmacy@fsmware.com) Received: from demos.bsdclusters.com (demos [69.55.225.36]) by demos.bsdclusters.com (8.12.8p1/8.12.8) with ESMTP id k98MtLlZ030599; Sun, 8 Oct 2006 15:55:21 -0700 (PDT) (envelope-from kmacy@fsmware.com) Received: from localhost (kmacy@localhost) by demos.bsdclusters.com (8.12.8p1/8.12.8/Submit) with ESMTP id k98MtLnn030596; Sun, 8 Oct 2006 15:55:21 -0700 (PDT) X-Authentication-Warning: demos.bsdclusters.com: kmacy owned process doing -bs Date: Sun, 8 Oct 2006 15:55:20 -0700 (PDT) From: Kip Macy X-X-Sender: kmacy@demos.bsdclusters.com To: Ivan Voras In-Reply-To: <4529667D.8070108@fer.hr> Message-ID: <20061008155350.L29803@demos.bsdclusters.com> References: <2fd864e0610080423q7ba6bdeal656a223e662a5d@mail.gmail.com> <2006 10082011.53649.davidxu@freebsd.org> <20061008135031.G83537@demos.bsdclusters.com> <4529667D.8070108@fer.hr> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-current@freebsd.org Subject: Re: [PATCH] MAXCPU alterable in kernel config - needs testers X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 08 Oct 2006 22:55:46 -0000 > Any word on how will they handle migration of threads across sockets (or > will it be OS's job)? Judging from T1 architecture, I think such event > would create a very large performance penalty, but I'm not an expert. It is the job of the OS to take locality into account in thread scheduling. Moving between chips You'll just lose the L2 cache locality just as you would on a normal SMP. -Kip