From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754081Ab1CYPtl (ORCPT ); Fri, 25 Mar 2011 11:49:41 -0400 Received: from hrndva-omtalb.mail.rr.com ([71.74.56.123]:52641 "EHLO hrndva-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751088Ab1CYPtj (ORCPT ); Fri, 25 Mar 2011 11:49:39 -0400 X-Authority-Analysis: v=1.1 cv=pN6kzQkhXdmdOr6Akjoh3kGBD/S3UyPMKQp53EJY+ro= c=1 sm=0 a=PNp5keGnr-sA:10 a=Q9fys5e9bTEA:10 a=OPBmh+XkhLl+Enan7BmTLg==:17 a=FP58Ms26AAAA:8 a=wuBOXYkujozFg8MotWoA:9 a=I14lvYSmDetFdoJopmkgDUdwzDoA:4 a=PUjeQqilurYA:10 a=OPBmh+XkhLl+Enan7BmTLg==:117 X-Cloudmark-Score: 0 X-Originating-IP: 67.242.120.143 Subject: Re: [PATCHv3] tracing - avoid soft lockup in trace_pipe From: Steven Rostedt To: Jiri Olsa Cc: Oleg Nesterov , fweisbec@gmail.com, mingo@redhat.com, linux-kernel@vger.kernel.org In-Reply-To: <20110325110518.GC1922@jolsa.brq.redhat.com> References: <20110313145811.GA30558@redhat.com> <1300111651.9910.87.camel@gandalf.stny.rr.com> <20110314141853.GB1936@jolsa.brq.redhat.com> <1300112926.9910.100.camel@gandalf.stny.rr.com> <20110314150746.GA4453@jolsa.brq.redhat.com> <1300116057.9910.106.camel@gandalf.stny.rr.com> <20110314180621.GA5987@jolsa.brq.redhat.com> <20110321121008.GA1979@jolsa.brq.redhat.com> <1301019798.14261.159.camel@gandalf.stny.rr.com> <1301022889.14261.167.camel@gandalf.stny.rr.com> <20110325110518.GC1922@jolsa.brq.redhat.com> Content-Type: text/plain; charset="ISO-8859-15" Date: Fri, 25 Mar 2011 11:49:37 -0400 Message-ID: <1301068177.14261.192.camel@gandalf.stny.rr.com> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2011-03-25 at 12:05 +0100, Jiri Olsa wrote: > right, I'm now able to trigger the issue when running setting the tracing > as said in the patch and plus running this in few instacies: > > (while [ 1 ]; do find / > /dev/null ; done) & That didn't work for me either. But if I run hackbench 50 on the box, then the trace does hang while it is running. > > It's strange I did not need this last time.. not sure why :) > > > anyway, the original reproducer I picked this issue from is ltp suite: > http://sourceforge.net/projects/ltp/files/LTP%20Source/ltp-20100131/ltp-full-20100131.tgz/download > > and running following test: > ltp-full-20101031/testcases/kernel/tracing/ftrace_stress_test/ftrace_stress_test.sh > > reproduces the issue all the time for me, and the patch fixies it. > Attaching patch rebased to the current master with changed comment. Thanks, I'll queue it up for 2.6.40, as I do not think this is that critical of a bug. -- Steve