From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gerrit Binnenmars Subject: Re: CONFIG_CRITICAL_IRQSOFF_TIMING Date: Wed, 31 Oct 2007 20:53:25 +0100 (CET) Message-ID: <14294538.1772991193860405373.JavaMail.www@wwinf6002> Reply-To: gerritbinnenmars@wanadoo.nl Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Daniel Walker , linux-rt-users@vger.kernel.org To: Steven Rostedt Return-path: Received: from smtp-1.orange.nl ([193.252.22.241]:13527 "EHLO smtp-1.orange.nl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753782AbXJaTx3 convert rfc822-to-8bit (ORCPT ); Wed, 31 Oct 2007 15:53:29 -0400 Received: from me-wanadoo.net (localhost [127.0.0.1]) by mwinf6007.orange.nl (SMTP Server) with ESMTP id 669AC7000094 for ; Wed, 31 Oct 2007 20:53:25 +0100 (CET) Sender: linux-rt-users-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org > Datum: 31/10/07 01:17 AM > Van: "Steven Rostedt"=20 > Aan: "Gerrit Binnenmars"=20 > CC: linux-rt-users@vger.kernel.org > Onderwerp : Re: CONFIG_CRITICAL_IRQSOFF_TIMING >=20 >=20 > -- > On Tue, 30 Oct 2007, Gerrit Binnenmars wrote: >=20 > > > Datum: 29/10/07 02:09 PM > > > Van: "Steven Rostedt" > > > Aan: "Gerrit Binnenmars" > > > CC: linux-rt-users@vger.kernel.org > > > Onderwerp : Re: CONFIG_CRITICAL_IRQSOFF_TIMING > > > > > > > > > -- > > > On Sun, 28 Oct 2007, Gerrit Binnenmars wrote: > > > > > > > Hello, > > > > > > > > Can someone send me a .config file that shows the options neede= d to get the interrupt off > > > > timing values in preempt_max_latency, please. I only see a valu= e of 0 in this file > > > > I am using kernel 2.6.22.1 with the corresponding rt patch. > > > > > > > > Thanks in advance, > > > > > > Make sure you have event trace and latency tracing as well as > > > "Interrupts-off critical section latency timing". > > > > > > Then you need to echo 0 > /proc/sys/kernel/preempt_max_latency. > > > > > Hello Steve, > > > > Thanks for your quick response, but the preempt_max_latency remains= 0. Also the latency_hist shows no samples taken. > > Can you or someone else have a look at the corresponding CONFIG opt= ions? > > > > CONFIG_LTT_PROBE_LOCKING=3Dm > > # CONFIG_LTT_PROBE_STACK is not set > > > > # > > # Kernel hacking > > # >=20 > [...] >=20 > > CONFIG_INTERRUPT_OFF_HIST=3Dy > > CONFIG_CRITICAL_LATENCY_HIST=3Dy > > CONFIG_LATENCY_HIST=3Dy >=20 > Turn off all histograms. They will kill any measurements you are taki= ng. > And yes, you will not get the output from latency_trace that you are > after. Steven and Daniel, I tried your suggestion with the following resulsts: CRITICAL_IRQSOFF_TIMING: preempt_max_latency remains 0 even under load,= =20 cyclictest -b is able to store a trace in /pro= c/latency_trace CRITICAL_PREEMPT_TIMING: kernel won=C2=B4t start at all (vmlinuz is rea= d from tftp server but nothing afterwards) WAKEUP_TIMING: is working as expected. So switching off the histograms is an improvement. For the moment, I ca= n live with this situation=20 (especially the cyclictest -b option is very useful), but I wonder if anyone else has the same problems? Regards, Gerrit >=20 > -- Steve >=20 > - > To unsubscribe from this list: send the line "unsubscribe linux-rt-us= ers" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html >=20 >