From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:17024 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751005AbaIJAmg (ORCPT ); Tue, 9 Sep 2014 20:42:36 -0400 Message-ID: <540F9E77.3080701@fb.com> Date: Tue, 9 Sep 2014 20:42:31 -0400 From: Chris Mason MIME-Version: 1.0 To: Morten Stevens , Subject: Re: btrfs 3.16.2 system crash References: <540E3858.8060904@fb.com> In-Reply-To: <540E3858.8060904@fb.com> Content-Type: text/plain; charset="UTF-8" Sender: linux-btrfs-owner@vger.kernel.org List-ID: On 09/08/2014 07:14 PM, Chris Mason wrote: > > > On 09/08/2014 06:51 PM, Morten Stevens wrote: >> Hi, >> >> After some testing with the latest stable 3.16.2 kernel on my Fedora >> 20 test-vm and a small filesystem >> test with btrfs causes the system to crash. >> >> Kernel: 3.16.2 >> Mount options: rw,seclabel,relatime,compress=lzo,space_cache >> >> The test is really simple: only writing 16 GB files on the disk with dd >> # dd if=/dev/zero of=ddfile bs=8k count=2000000 >> >> You need to run it multiple times, after some time the host gets into >> a non-responsive >> state. > > Hi Morten, > > I haven't seen that one, and I ran an overnight stress before sending > out the stable patches. But, let me try here. I ran the dd's overnight and some other tests without trouble. But that doesn't mean its not a btrfs bug, I'll try again tonight. -chris