From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sebastian Andrzej Siewior Subject: Re: Bisect results for 4.4.1-rt[4,5] Date: Thu, 25 Feb 2016 15:06:27 +0100 Message-ID: <56CF0A63.7010203@linutronix.de> References: <20150816135630.GE7004@linutronix.de> <1614199.PesBpXyHut@dabox> <56BDA0EF.7090503@linutronix.de> <6333508.b5IKNpgbEX@dabox> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: linux-rt-users , LKML , Thomas Gleixner , rostedt@goodmis.org, John Kacur To: Tim Sander Return-path: Received: from www.linutronix.de ([62.245.132.108]:53506 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759993AbcBYOGd (ORCPT ); Thu, 25 Feb 2016 09:06:33 -0500 In-Reply-To: <6333508.b5IKNpgbEX@dabox> Sender: linux-rt-users-owner@vger.kernel.org List-ID: On 02/17/2016 09:14 AM, Tim Sander wrote: > Hi Sebastian Hi Tim, > I have done a bisect run, its a rather innocent looking on liner whic= h seems=20 > to cause the problems. The numbers where reasonably stable so i am pr= etty=20 > confident that this is the patch giving ~26=B5s additional latency on= the Altera > SOC plattform: >=20 > eec2bf477ac674583a7d73b9d00f47c528b7266d is the first bad commit > commit eec2bf477ac674583a7d73b9d00f47c528b7266d > Author: Sebastian Andrzej Siewior > Date: Thu Feb 4 16:38:10 2016 +0100 >=20 > kernel/perf: mark perf_cpu_context's timer as irqsafe > =20 > Otherwise we get a WARN_ON() backtrace and some events are report= ed as > "not counted". > =20 > Cc: stable-rt@vger.kernel.org > Reported-by: Yang Shi > Signed-off-by: Sebastian Andrzej Siewior Seriously? That patch? I played a little and I doubt seriously that this patch has something to do with it. So before that patch you would have a warn_on spotted and complained if that timer would fire. So that is one reason why I doubt that this patch is in charge of the 25us. If I add a printk() to that timer I don't see it under "normal" circumstances. However I do perf_4.3 stat -e branches,branch-misses,bus-cycles,cache-misses,cache-references,cycles,= instructions apt-get update then I see them fire. > Best Regards > Tim Sebastian -- To unsubscribe from this list: send the line "unsubscribe linux-rt-user= s" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760434AbcBYOGe (ORCPT ); Thu, 25 Feb 2016 09:06:34 -0500 Received: from www.linutronix.de ([62.245.132.108]:53506 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759993AbcBYOGd (ORCPT ); Thu, 25 Feb 2016 09:06:33 -0500 Subject: Re: Bisect results for 4.4.1-rt[4,5] To: Tim Sander References: <20150816135630.GE7004@linutronix.de> <1614199.PesBpXyHut@dabox> <56BDA0EF.7090503@linutronix.de> <6333508.b5IKNpgbEX@dabox> Cc: linux-rt-users , LKML , Thomas Gleixner , rostedt@goodmis.org, John Kacur From: Sebastian Andrzej Siewior X-Enigmail-Draft-Status: N1110 Message-ID: <56CF0A63.7010203@linutronix.de> Date: Thu, 25 Feb 2016 15:06:27 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Icedove/38.5.0 MIME-Version: 1.0 In-Reply-To: <6333508.b5IKNpgbEX@dabox> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 8bit X-Linutronix-Spam-Score: -1.0 X-Linutronix-Spam-Level: - X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required, ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001,URIBL_BLOCKED=0.001 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/17/2016 09:14 AM, Tim Sander wrote: > Hi Sebastian Hi Tim, > I have done a bisect run, its a rather innocent looking on liner which seems > to cause the problems. The numbers where reasonably stable so i am pretty > confident that this is the patch giving ~26µs additional latency on the Altera > SOC plattform: > > eec2bf477ac674583a7d73b9d00f47c528b7266d is the first bad commit > commit eec2bf477ac674583a7d73b9d00f47c528b7266d > Author: Sebastian Andrzej Siewior > Date: Thu Feb 4 16:38:10 2016 +0100 > > kernel/perf: mark perf_cpu_context's timer as irqsafe > > Otherwise we get a WARN_ON() backtrace and some events are reported as > "not counted". > > Cc: stable-rt@vger.kernel.org > Reported-by: Yang Shi > Signed-off-by: Sebastian Andrzej Siewior Seriously? That patch? I played a little and I doubt seriously that this patch has something to do with it. So before that patch you would have a warn_on spotted and complained if that timer would fire. So that is one reason why I doubt that this patch is in charge of the 25us. If I add a printk() to that timer I don't see it under "normal" circumstances. However I do perf_4.3 stat -e branches,branch-misses,bus-cycles,cache-misses,cache-references,cycles,instructions apt-get update then I see them fire. > Best Regards > Tim Sebastian