From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932718Ab1EYUrq (ORCPT ); Wed, 25 May 2011 16:47:46 -0400 Received: from e2.ny.us.ibm.com ([32.97.182.142]:45806 "EHLO e2.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932237Ab1EYUrn (ORCPT ); Wed, 25 May 2011 16:47:43 -0400 Date: Wed, 25 May 2011 13:47:39 -0700 From: "Paul E. McKenney" To: Ingo Molnar Cc: Yinghai Lu , linux-kernel@vger.kernel.org, mingo@redhat.com, hpa@zytor.com, tglx@linutronix.de Subject: Re: [tip:core/rcu] Revert "rcu: Decrease memory-barrier usage based on semi-formal proof" Message-ID: <20110525204739.GJ2341@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <4DDAD934.9010603@kernel.org> <4DDAE5FA.2030303@kernel.org> <4DDAE6A5.6060701@kernel.org> <20110524011824.GL7428@linux.vnet.ibm.com> <4DDB093F.2060601@kernel.org> <20110524013523.GO7428@linux.vnet.ibm.com> <4DDC21E1.1070502@kernel.org> <4DDC48E3.1060108@kernel.org> <20110525045253.GB2262@linux.vnet.ibm.com> <20110525072742.GI429@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110525072742.GI429@elte.hu> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, May 25, 2011 at 09:27:42AM +0200, Ingo Molnar wrote: > > * Paul E. McKenney wrote: > > > On Tue, May 24, 2011 at 05:10:11PM -0700, Yinghai Lu wrote: > > > On 05/24/2011 02:23 PM, Yinghai Lu wrote: > > > > On 05/23/2011 06:35 PM, Paul E. McKenney wrote: > > > >> On Mon, May 23, 2011 at 06:26:23PM -0700, Yinghai Lu wrote: > > > >>> On 05/23/2011 06:18 PM, Paul E. McKenney wrote: > > > >>> > > > >>>> OK, so it looks like I need to get this out of the way in order to track > > > >>>> down the delays. Or does reverting PeterZ's patch get you a stable > > > >>>> system, but with the longish delays in memory_dev_init()? If the latter, > > > >>>> it might be more productive to handle the two problems separately. > > > >>>> > > > >>>> For whatever it is worth, I do see about 5% increase in grace-period > > > >>>> duration when switching to kthreads. This is acceptable -- your > > > >>>> 30x increase clearly is completely unacceptable and must be fixed. > > > >>>> Other than that, the main thing that affects grace period duration is > > > >>>> the setting of CONFIG_HZ -- the smaller the HZ value, the longer the > > > >>>> grace-period duration. > > > >>> > > > >>> for my 1024g system when memory hotadd is enabled in kernel config: > > > >>> 1. current linus tree + tip tree: memory_dev_init will take about 100s. > > > >>> 2. current linus tree + tip tree + your tree - Peterz patch: > > > >>> a. on fedora 14 gcc: will cost about 4s: like old times > > > >>> b. on opensuse 11.3 gcc: will cost about 10s. > > > >> > > > >> So some patch in my tree that is not yet in tip makes things better? > > > >> > > > >> If so, could you please see which one? Maybe that would give me a hint > > > >> that could make things better on opensuse 11.3 as well. > > > > > > > > today's tip: > > > > > > > > [ 31.795597] cpu_dev_init done > > > > [ 40.930202] memory_dev_init done > > > > > > > > > > another boot from tip got: > > > > > > [ 35.211927] cpu_dev_init done > > > [ 136.053698] memory_dev_init done > > > > > > wonder if you can have clean revert for > > > > > > commit a26ac2455ffcf3be5c6ef92bc6df7182700f2114 > > > > Author: Paul E. McKenney > > > > Date: Wed Jan 12 14:10:23 2011 -0800 > > > > > > > > rcu: move TREE_RCU from softirq to kthread > > > > > > > > If RCU priority boosting is to be meaningful, callback invocation must > > > > be boosted in addition to preempted RCU readers. Otherwise, in presence > > > > of CPU real-time threads, the grace period ends, but the callbacks don't > > > > get invoked. If the callbacks don't get invoked, the associated memory > > > > doesn't get freed, so the system is still subject to OOM. > > > > > > > > But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit > > > > moves the callback invocations to a kthread, which can be boosted easily. > > > > > > > > Also add comments and properly synchronized all accesses to > > > > rcu_cpu_kthread_task, as suggested by Lai Jiangshan. > > > > > > > > Signed-off-by: Paul E. McKenney > > > > Signed-off-by: Paul E. McKenney > > > > Reviewed-by: Josh Triplett > > > > There is a new branch yinghai.2011.05.24a on: > > > > git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git > > > > Or will be as soon as kernel.org updates its mirrors. > > > > I am not sure I could call this "clean", but it does revert that commit > > and 11 of the subsequent commits that depend on it. It does build, > > and I will test it once my currently running tests complete. > > Given that this is about a 1-2 minute delays with 1 *terabyte* of RAM, the per > gigabyte delay is like 60-120 msecs, right? > > So it's not a regression we are absolutely forced to address via a quick > revert, debugging it would be nicer. There's something we don't understand and > that's arguably worse than having unresolved non-fatal bugs :-) And my attempted revert results in test failures in any case. :-( > We already fixed the worst problem via a revert, the semi-hang: so i don't > think there's pressure to do other reverts - other than for diagnostic > purposes, of course. Given that I have to debug in any case, I am happier debugging in the forward direction rather than in the backwards direction. ;-) Thanx, Paul