Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763902AbYBURJn (ORCPT ); Thu, 21 Feb 2008 12:09:43 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755046AbYBURJU (ORCPT ); Thu, 21 Feb 2008 12:09:20 -0500 Received: from victor.provo.novell.com ([137.65.250.26]:37761 "EHLO victor.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932392AbYBURJS (ORCPT ); Thu, 21 Feb 2008 12:09:18 -0500 X-Greylist: delayed 305 seconds by postgrey-1.27 at vger.kernel.org; Thu, 21 Feb 2008 12:09:17 EST Subject: Re: [PATCH [RT] 10/14] adjust pi_lock usage in wakeup From: "Peter W. Morreale" To: Steven Rostedt Cc: Gregory Haskins , mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de, linux-rt-users@vger.kernel.org, linux-kernel@vger.kernel.org, bill.huey@gmail.com, kevin@hilman.org, cminyard@mvista.com, dsingleton@mvista.com, dwalker@mvista.com, npiggin@suse.de, dsaxena@plexity.net, ak@suse.de, gregkh@suse.de, sdietrich@novell.com, mkohari@novell.com In-Reply-To: References: <20080221152504.4804.8724.stgit@novell1.haskins.net> <20080221152717.4804.56212.stgit@novell1.haskins.net> Content-Type: text/plain Organization: Linux Solutions Group Date: Thu, 21 Feb 2008 10:09:04 -0700 Message-Id: <1203613744.4232.32.camel@hermosa.morrealenet> Mime-Version: 1.0 X-Mailer: Evolution 2.6.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1290 Lines: 39 On Thu, 2008-02-21 at 11:48 -0500, Steven Rostedt wrote: > On Thu, 21 Feb 2008, Gregory Haskins wrote: > > > From: Peter W.Morreale > > > > In wakeup_next_waiter(), we take the pi_lock, and then find out whether > > we have another waiter to add to the pending owner. We can reduce > > contention on the pi_lock for the pending owner if we first obtain the > > pointer to the next waiter outside of the pi_lock. > > > > This patch adds a measureable increase in throughput. > > I see how this may decrease contention (slightly less time in holding the > pi_lock). But, please, when stating something like: "adds a measurable > increase in throughput", show the benchmark numbers. > > -- Steve > Approximately 3% to the dbench benchmark we used. My "standard" sanity check was to mount a ramfs filesystem and execute: dbench -t 10 30 five times and generate an average from the reported "Throughput" numbers displayed by the runs. dbench was chosen merely because of the contention on dcache_lock. Best, -PWM -- 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/