Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756132Ab1EDXmo (ORCPT ); Wed, 4 May 2011 19:42:44 -0400 Received: from one.firstfloor.org ([213.235.205.2]:51365 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755987Ab1EDXmn (ORCPT ); Wed, 4 May 2011 19:42:43 -0400 Date: Thu, 5 May 2011 01:42:41 +0200 From: Andi Kleen To: Thomas Gleixner Cc: Andi Kleen , Dave Kleikamp , Chris Mason , Peter Zijlstra , Tim Chen , linux-kernel@vger.kernel.org, lenb@kernel.org, paulmck@us.ibm.com Subject: Re: idle issues running sembench on 128 cpus Message-ID: <20110504234241.GD2925@one.firstfloor.org> References: <4DC1C95B.4040706@gmail.com> <20110504230349.GC2925@one.firstfloor.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.2i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2663 Lines: 81 On Thu, May 05, 2011 at 01:29:49AM +0200, Thomas Gleixner wrote: > > > hierarchical about that. It all boils down on _ONE_ single functional > > > > The mask can be used to see if another thread on this core is still > > running. If yes you don't need that. Right now Linux doesn't > > know that, but it could be taught. The only problem is that once > > the other guy goes idle too their timeouts have to be merged. > > > > This would cut contention in half. > > That makes sense, but merging the timeouts race free will be a real > PITA. For this case one could actually use a spinlock between the siblings. That shouldn't be a problem as long as it's not a global spinlock. > > > Also if it's HPET you could actually use multiple independent HPET channels. > > I remember us discussing this a long time ago... Not sure if it's worth > > it, but it may be a small relief. > > Multiple broadcast devices. That sounds still horrible :) It would cut contention in half or more at least. Not great, but sometimes you take everything you can get. > Might be worth a try. Need some sleep to remember why I discarded that > idea long ago. Ok. Here's a new patch without the raw. Boots on my Westmere. --- From: Andi Kleen Subject: [PATCH] Move C3 stop test outside lock Avoid taking locks in the idle path for systems where the timer doesn't stop in C3. Signed-off-by: Andi Kleen diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index da800ff..9cf0415 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -456,23 +456,22 @@ void tick_broadcast_oneshot_control(unsigned long reason) unsigned long flags; int cpu; - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - /* * Periodic mode does not care about the enter/exit of power * states */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - goto out; + return; + cpu = raw_smp_processor_id(); bc = tick_broadcast_device.evtdev; - cpu = smp_processor_id(); td = &per_cpu(tick_cpu_device, cpu); dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - goto out; + return; + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) { cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask()); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/