From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757291Ab3KYTw3 (ORCPT ); Mon, 25 Nov 2013 14:52:29 -0500 Received: from www.linutronix.de ([62.245.132.108]:57046 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754033Ab3KYTw2 (ORCPT ); Mon, 25 Nov 2013 14:52:28 -0500 Date: Mon, 25 Nov 2013 20:52:23 +0100 (CET) From: Thomas Gleixner To: Davidlohr Bueso cc: Peter Zijlstra , Linus Torvalds , Linux Kernel Mailing List , Ingo Molnar , Darren Hart , Mike Galbraith , Jeff Mahoney , "Norton, Scott J" , tom.vaden@hp.com, "Chandramouleeswaran, Aswin" , Waiman Long , Jason Low , "Paul E. McKenney" Subject: Re: [PATCH 4/5] futex: Avoid taking hb lock if nothing to wakeup In-Reply-To: <1385405723.15768.3.camel@buesod1.americas.hpqcorp.net> Message-ID: References: <1385168197-8612-1-git-send-email-davidlohr@hp.com> <1385168197-8612-5-git-send-email-davidlohr@hp.com> <1385176773.5402.14.camel@buesod1.americas.hpqcorp.net> <20131125163627.GC10022@twins.programming.kicks-ass.net> <1385405723.15768.3.camel@buesod1.americas.hpqcorp.net> User-Agent: Alpine 2.02 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Linutronix-Spam-Score: -1.0 X-Linutronix-Spam-Level: - X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required, ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 25 Nov 2013, Davidlohr Bueso wrote: > On Mon, 2013-11-25 at 18:32 +0100, Thomas Gleixner wrote: > > If the smp_mb() is heavy weight, then it will hurt massivly in the > > case where the hash bucket is not empty, because we add the price for > > the smp_mb() just for no gain. > > > > In that context it would also be helpful to measure the overhead on > > x86 for the !empty case. > > Absolutely, I will add these comparisons. If we do notice that we end up > hurting the !empty case, would the current patch using atomic ops still > be considered? We have made sure that none of the changes in this set > affects performance on other workloads/smaller systems. Please read my last reply to the atomic ops approach. Aside of that we need numbers for a significant range of !x86. Thanks, tglx