From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1422790AbXCWLCo (ORCPT ); Fri, 23 Mar 2007 07:02:44 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1422791AbXCWLCo (ORCPT ); Fri, 23 Mar 2007 07:02:44 -0400 Received: from holomorphy.com ([66.93.40.71]:39770 "EHLO holomorphy.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1422790AbXCWLCn (ORCPT ); Fri, 23 Mar 2007 07:02:43 -0400 Date: Fri, 23 Mar 2007 04:02:24 -0700 From: William Lee Irwin III To: Nick Piggin Cc: Ingo Molnar , Linux Kernel Mailing List , Ravikiran G Thirumalai Subject: Re: [rfc][patch] queued spinlocks (i386) Message-ID: <20070323110224.GP2986@holomorphy.com> References: <20070323085910.GA11577@wotan.suse.de> <20070323100418.GA30740@elte.hu> <20070323103243.GE11577@wotan.suse.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070323103243.GE11577@wotan.suse.de> Organization: The Domain of Holomorphy User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Mar 23, 2007 at 11:04:18AM +0100, Ingo Molnar wrote: >> isnt this patented by MS? (which might not worry you SuSE/Novell guys, >> but it might be a worry for the rest of the world ;-) On Fri, Mar 23, 2007 at 11:32:44AM +0100, Nick Piggin wrote: > Hmm, it looks like they have implemented a system where the spinning > cpu sleeps on a per-CPU variable rather than the lock itself, and > the releasing cpu writes to that variable to wake it. They do this > so that spinners don't continually perform exclusive->shared > transitions on the lock cacheline. They call these things queued > spinlocks. They don't seem to be very patent worthy either, but > maybe it is what you're thinking of? Those exclusive-to-shared transitions are among the cacheline transfers typically accounted to the algorithms in their complexity analyses. -- wli