From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757340AbbAIQZM (ORCPT ); Fri, 9 Jan 2015 11:25:12 -0500 Received: from smtprelay0151.hostedemail.com ([216.40.44.151]:37881 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751659AbbAIQZL (ORCPT ); Fri, 9 Jan 2015 11:25:11 -0500 X-Session-Marker: 6E657665747340676F6F646D69732E6F7267 X-Spam-Summary: 2,0,0,,d41d8cd98f00b204,rostedt@goodmis.org,:::::::::::,RULES_HIT:41:355:379:541:599:800:960:973:988:989:1260:1277:1311:1313:1314:1345:1359:1437:1515:1516:1518:1534:1541:1593:1594:1711:1730:1747:1777:1792:2393:2553:2559:2562:2892:3138:3139:3140:3141:3142:3353:3622:3865:3866:3867:3868:3870:3871:3872:3873:3874:5007:6119:6248:6261:7514:7774:7875:7903:8829:10004:10400:10848:10967:11232:11639:11658:11914:12043:12517:12519:12663:12740:13069:13161:13229:13311:13357:13618:14096:14097:21060:21080,0,RBL:none,CacheIP:none,Bayesian:0.5,0.5,0.5,Netcheck:none,DomainCache:0,MSF:not bulk,SPF:fn,MSBL:0,DNSBL:none,Custom_rules:0:0:0 X-HE-Tag: nail57_66d3facf40616 X-Filterd-Recvd-Size: 2256 Date: Fri, 9 Jan 2015 11:25:05 -0500 From: Steven Rostedt To: Vaibhav Shinde Cc: Peter Zijlstra , linux-kernel@vger.kernel.org, Andrew Morton , tj@kernel.org, Davidlohr Bueso Subject: Re: Preemptionirqsoff latency issue Message-ID: <20150109112505.4ed9de41@gandalf.local.home> In-Reply-To: References: <20150109095603.GB22386@worktop.programming.kicks-ass.net> X-Mailer: Claws Mail 3.11.1 (GTK+ 2.24.25; x86_64-pc-linux-gnu) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 9 Jan 2015 20:19:51 +0530 Vaibhav Shinde wrote: > Hi Peter, > > Thanks for you reply. > > I am interested in scheduling latency, and using ftrace I see for my > application suffering from it, that's why I am digging in preemption/irq > disable time which might cause the latency. > > My app runs on cpu0, while other cpus looks idle; as per my understanding > from your comment owner of the mutex is on the cpu other than cpu0, and > which is causing wait spin on cpu0. > Can this be the reason why latency is caused ? > If so, then I think I need to take care of the mutex lock which is called > from my code. > If you download and install the latest trace-cmd, you may be able to get more information with its new command "profile". # trace-cmd profile -o file workload Then look at the output in file. To limit the running to tracing only the workload: # trace-cmd profile -o file -F -c workload You'll need to use the latest that's in my repo. Use the master branch, as it has all the above features. git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git -- Steve