From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756735AbZBKA5U (ORCPT ); Tue, 10 Feb 2009 19:57:20 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753143AbZBKA5H (ORCPT ); Tue, 10 Feb 2009 19:57:07 -0500 Received: from tomts43.bellnexxia.net ([209.226.175.110]:57497 "EHLO tomts43-srv.bellnexxia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752351AbZBKA5F (ORCPT ); Tue, 10 Feb 2009 19:57:05 -0500 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: ArEEACyxkUlMQWt2/2dsb2JhbACBbtIMhBoG Date: Tue, 10 Feb 2009 19:57:01 -0500 From: Mathieu Desnoyers To: "Paul E. McKenney" 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: <20090211005701.GA550@Krystal> References: <20090208224419.GA19512@Krystal> <20090209041153.GR7120@linux.vnet.ibm.com> <20090209045352.GA28653@Krystal> <20090209051737.GA29254@Krystal> <20090209070317.GA31583@Krystal> <20090209153305.GA6802@linux.vnet.ibm.com> <20090210191731.GA20867@Krystal> <20090210211643.GL6742@linux.vnet.ibm.com> <20090210212833.GA27578@Krystal> <20090210222115.GN6742@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline In-Reply-To: <20090210222115.GN6742@linux.vnet.ibm.com> X-Editor: vi X-Info: http://krystal.dyndns.org:8080 X-Operating-System: Linux/2.6.21.3-grsec (i686) X-Uptime: 19:48:56 up 41 days, 47 min, 4 users, load average: 0.62, 0.73, 0.60 User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Paul E. McKenney (paulmck@linux.vnet.ibm.com) wrote: > On Tue, Feb 10, 2009 at 04:28:33PM -0500, Mathieu Desnoyers wrote: > > * Paul E. McKenney (paulmck@linux.vnet.ibm.com) wrote: > > > On Tue, Feb 10, 2009 at 02:17:31PM -0500, Mathieu Desnoyers wrote: > > > > * Paul E. McKenney (paulmck@linux.vnet.ibm.com) wrote: > > > > > 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(). > > > > > > > > > > > > > I just did a mb() version of the urcu : > > > > > > > > (uncomment CFLAGS=+-DDEBUG_FULL_MB in the Makefile) > > > > > > > > Time per read : 48.4086 cycles > > > > (about 6-7 times slower, as expected) > > > > > > > > This will be useful especially to increase the chance to trigger races. > > > > > > > > I tried removing the second parity switch from the writer. The rcu > > > > torture test did not find the problem yet (maybe I am not using the > > > > correct parameters ? It does not run for more than 5 seconds). > > > > > > > > So I added a "-n" option to test_urcu, so it can make the usleep(1) > > > > between the writes optional. I also changed the yield for a usleep with > > > > random delay. I also now use a circular buffer rather than malloc so we > > > > are sure the memory is not quickly reused by the writer and stays longer > > > > in an invalid state. > > > > > > > > So what really make the problem appear quickly is to add a delay between > > > > the rcu_dereference and the assertion on the data validity in thr_reader. > > > > > > > > It now appears after just a few seconds when running > > > > ./test_urcu_yield 20 -r -n > > > > Compiled with CFLAGS=+-DDEBUG_FULL_MB > > > > > > > > It seem to be much harder to trigger with the signal-based version. It's > > > > expected, because the writer takes about 50 times longer to execute than > > > > with the -DDEBUG_FULL_MB version. > > > > > > > > So I'll let the ./test_urcu_yield NN -r -n run for a while on the > > > > correct version (with DEBUG_FULL_MB) and see what it gives. > > > > > > Hmmm... I had worse luck this time, took three 10-second tries to > > > see a failure: > > > > > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ ./rcu_nest32 1 stress > > > n_reads: 44682055 n_updates: 9609503 n_mberror: 0 > > > rcu_stress_count: 44679377 2678 0 0 0 0 0 0 0 0 0 > > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ !! > > > ./rcu_nest32 1 stress > > > n_reads: 42281884 n_updates: 9870129 n_mberror: 0 > > > rcu_stress_count: 42277756 4128 0 0 0 0 0 0 0 0 0 > > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ !! > > > ./rcu_nest32 1 stress > > > n_reads: 41384304 n_updates: 10040805 n_mberror: 0 > > > rcu_stress_count: 41380075 4228 1 0 0 0 0 0 0 0 0 > > > paulmck@paulmck-laptop:~/paper/perfbook/CodeSamples/defer$ > > > > > > This is my prototype version, with read-side memory barriers, no > > > signals, and without your initialization-value speedup. > > > > > > > It would be interesting to re-sync our trees, or if you can point me to > > a current version of your prototype, I could review it. > > Look at: > > CodeSamples/defer/rcu_nest32.[hc] > > In the git archive: > > git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/perfbook.git > flip_counter_and_wait : yours do rcu_gp_ctr += RCU_GP_CTR_BOTTOM_BIT mine : rcu_gp_ctr ^= RCU_GP_CTR_BOTTOM_BIT. Another major difference between our tree is the lack of smp_mb() at the end of flip_counter_and_wait() (in your tree). Your code does : smp_mb() switch parity smp_mb() wait for each thread ongoing old gp <<<<<<< ---- missing smp_mb. switch parity smp_mb() wait for each thread ongoing old gp smp_mb() I also wonder why you have a smp_mb() after spin_unlock() in your synchronize_rcu() -> if you follow the Linux kernel semantics for spinlocks, the smp_mb() should be implied. (but I have not looked at your spin_lock/unlock primitives yet). Mathieu > Thanx, Paul > > _______________________________________________ > ltt-dev mailing list > ltt-dev@lists.casi.polymtl.ca > http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev > -- Mathieu Desnoyers OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68