From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755524AbZBIPdS (ORCPT ); Mon, 9 Feb 2009 10:33:18 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754520AbZBIPdJ (ORCPT ); Mon, 9 Feb 2009 10:33:09 -0500 Received: from e2.ny.us.ibm.com ([32.97.182.142]:36810 "EHLO e2.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754132AbZBIPdI (ORCPT ); Mon, 9 Feb 2009 10:33:08 -0500 Date: Mon, 9 Feb 2009 07:33:05 -0800 From: "Paul E. McKenney" To: Mathieu Desnoyers Cc: ltt-dev@lists.casi.polymtl.ca, linux-kernel@vger.kernel.org Subject: Re: [ltt-dev] [RFC git tree] Userspace RCU (urcu) for Linux (repost) Message-ID: <20090209153305.GA6802@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20090206030543.GB8560@Krystal> <20090206045841.GA12995@Krystal> <20090206130640.GB10918@linux.vnet.ibm.com> <20090206163432.GF10918@linux.vnet.ibm.com> <20090208224419.GA19512@Krystal> <20090209041153.GR7120@linux.vnet.ibm.com> <20090209045352.GA28653@Krystal> <20090209051737.GA29254@Krystal> <20090209070317.GA31583@Krystal> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090209070317.GA31583@Krystal> User-Agent: Mutt/1.5.15+20070412 (2007-04-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Feb 09, 2009 at 02:03:17AM -0500, Mathieu Desnoyers wrote: [ . . . ] > I just added modified rcutorture.h and api.h from your git tree > specifically for an urcutorture program to the repository. Some results : > > 8-way x86_64 > E5405 @2 GHZ > > ./urcutorture 8 perf > n_reads: 1937650000 n_updates: 3 nreaders: 8 nupdaters: 1 duration: 1 > ns/read: 4.12871 ns/update: 3.33333e+08 > > ./urcutorture 8 uperf > n_reads: 0 n_updates: 4413892 nreaders: 0 nupdaters: 8 duration: 1 > ns/read: nan ns/update: 1812.46 > > n_reads: 98844204 n_updates: 10 n_mberror: 0 > rcu_stress_count: 98844171 33 0 0 0 0 0 0 0 0 0 > > However, I've tried removing the second switch_qparity() call, and the > rcutorture test did not detect anything wrong. I also did a variation > which calls the "sched_yield" version of the urcu, "urcutorture-yield". My confusion -- I was testing my old approach where the memory barriers are in rcu_read_lock() and rcu_read_unlock(). To force the failures in your signal-handler-memory-barrier approach, I suspect that you are going to need a bigger hammer. In this case, one such bigger hammer would be: o Just before exit from the signal handler, do a pthread_cond_wait() under a pthread_mutex(). o In force_mb_all_threads(), refrain from sending a signal to self. Then it should be safe in force_mb_all_threads() to do a pthread_cond_broadcast() under the same pthread_mutex(). This should raise the probability of seeing the failure in the case where there is a single switch_qparity(). Thanx, Paul