From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from alpha.arachsys.com ([91.203.57.7]:40192 "EHLO alpha.arachsys.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754371AbaDPR6k (ORCPT ); Wed, 16 Apr 2014 13:58:40 -0400 Date: Wed, 16 Apr 2014 18:58:37 +0100 From: Richard Davies To: cgroups@vger.kernel.org, linux-mm@kvack.org, linux-btrfs@vger.kernel.org Subject: Re: Kernel crash triggered by dd to file with memcg, worst on btrfs Message-ID: <20140416175837.GA9412@alpha.arachsys.com> References: <20140416174210.GA11486@alpha.arachsys.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20140416174210.GA11486@alpha.arachsys.com> Sender: linux-btrfs-owner@vger.kernel.org List-ID: Richard Davies wrote: > I have a test case in which I can often crash an entire machine by running > dd to a file with a memcg with relatively generous limits. This is > simplified from real world problems with heavy disk i/o inside containers. > > The crashes are easy to trigger when dding to create a file on btrfs. On > ext3, typically there is just an error in the kernel log, although > occasionally it also crashes. A further note - the ext3 SLUB errors occur when dding into a ext3 file alone. The few ext3 crashes occurred when dding into a btrfs file for a while without a crash, then switching to dding into an ext3 file. So the "ext3 crashes" could actually be due to btrfs cached data still in memory - i.e. all crashes could be due to btrfs use. Richard.