From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from homie.mail.dreamhost.com ([208.97.132.208]:36763 "EHLO homiemail-a3.g.dreamhost.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753722AbaJQUIV (ORCPT ); Fri, 17 Oct 2014 16:08:21 -0400 Message-ID: <1413576485.22256.5.camel@linux-t7sj.site> Subject: Re: btrfs soft lockups: locks gone crazy From: Davidlohr Bueso To: Josef Bacik Cc: LKML , linux-btrfs@vger.kernel.org Date: Fri, 17 Oct 2014 13:08:05 -0700 In-Reply-To: <54416EF6.1050403@fb.com> References: <1413271664.27233.13.camel@linux-t7sj.site> <54416EF6.1050403@fb.com> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Sender: linux-btrfs-owner@vger.kernel.org List-ID: On Fri, 2014-10-17 at 15:33 -0400, Josef Bacik wrote: > On 10/14/2014 03:27 AM, Davidlohr Bueso wrote: > > Hello, > > > > I'm getting massive amounts of cpu soft lockups in Linus's tree for > > today. This occurs almost immediately and is very reproducible in aim7 > > disk workloads using btrfs: > > > > I'm trying to reproduce but it's not popping for me. What is the setup > of your fs? mkfs options, mount options etc. And how are you running > aim7? I'm using reaim with the default reaim.config and workfile,disk, > is this what you are using? If not please attach your config and > workfile so I can be sure to be doing the same thing as you. Thanks, The steps I used are: Download mmtests: https://github.com/gormanm/mmtests.git cp configs/config-global-dhp__reaim-io config edit the new config and just leave 'workfile.shared workfile.disk' workloads as the REAIM_WORKFILES parameter. ./run-mmtests --no-monitor testname Just a few mins into the test you should start getting the lockups. fwiw I have not had the time to try other setups of reaim that are not bundled with mmtests. Thanks, Davidlohr