Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758538AbZASS4g (ORCPT ); Mon, 19 Jan 2009 13:56:36 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753318AbZASS41 (ORCPT ); Mon, 19 Jan 2009 13:56:27 -0500 Received: from rcsinet13.oracle.com ([148.87.113.125]:60800 "EHLO rgminet13.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752680AbZASS40 (ORCPT ); Mon, 19 Jan 2009 13:56:26 -0500 Subject: RE: Mainline kernel OLTP performance update From: Chris Mason To: Steven Rostedt Cc: "Ma, Chinang" , Andrew Morton , Matthew Wilcox , "Wilcox, Matthew R" , "linux-kernel@vger.kernel.org" , "Tripathi, Sharad C" , "arjan@linux.intel.com" , "Kleen, Andi" , "Siddha, Suresh B" , "Chilukuri, Harita" , "Styner, Douglas W" , "Wang, Peter Xihong" , "Nueckel, Hubert" , "linux-scsi@vger.kernel.org" , Andrew Vasquez , Anirban Chakraborty , Ingo Molnar , Thomas Gleixner , Peter Zijlstra , Gregory Haskins , Rusty Russell In-Reply-To: <1232390259.25783.5.camel@localhost.localdomain> References: <20090114163557.11e097f2.akpm@linux-foundation.org> <20090115012147.GW29283@parisc-linux.org> <20090114180431.f4a96543.akpm@linux-foundation.org> <1231986439.21980.54.camel@localhost.localdomain> <1232388291.6521.140.camel@think.oraclecorp.com> <1232390259.25783.5.camel@localhost.localdomain> Content-Type: text/plain Date: Mon, 19 Jan 2009 13:55:05 -0500 Message-Id: <1232391305.6521.146.camel@think.oraclecorp.com> Mime-Version: 1.0 X-Mailer: Evolution 2.24.1 Content-Transfer-Encoding: 7bit X-Source-IP: acsmt705.oracle.com [141.146.40.83] X-Auth-Type: Internal IP X-CT-RefId: str=0001.0A090201.4974CC90.0066:SCFSTAT928724,ss=1,fgs=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1866 Lines: 59 On Mon, 2009-01-19 at 13:37 -0500, Steven Rostedt wrote: > (added Rusty) > > On Mon, 2009-01-19 at 13:04 -0500, Chris Mason wrote: > > > > I think the -rt version of check_preempt_equal_prio has gotten much more > > expensive since 2.6.24. > > > > I'm sure these changes were made for good reasons, and this workload may > > not be a good reason to change it back. But, what does the patch below > > do to performance on 2.6.29-rcX? > > > > -chris > > > > diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c > > index 954e1a8..bbe3492 100644 > > --- a/kernel/sched_rt.c > > +++ b/kernel/sched_rt.c > > @@ -842,6 +842,7 @@ static void check_preempt_curr_rt(struct rq *rq, > > struct task_struct *p, int sync > > resched_task(rq->curr); > > return; > > } > > + return; > > > > #ifdef CONFIG_SMP > > /* > > That should not cause much of a problem if the scheduling task is not > pinned to an CPU. But!!!!! > > A recent change makes it expensive: > + if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) > return; > check_preempt_equal_prio is in a scheduling hot path!!!!! > > WTF are we allocating there for? I wasn't actually looking at the cost of the checks, even though they do look higher (if they are using CONFIG_CPUMASK_OFFSTACK anyway). The 2.6.24 code would trigger a rescheduling interrupt only when the prio of the inbound task was higher than the running task. This workload has a large number of equal priority rt tasks that are not bound to a single CPU, and so I think it should trigger more preempts/reschedules with the today's check_preempt_equal_prio(). -chris -- 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/