From: Jens Axboe Subject: Re: Test generic/299 stalling forever Date: Wed, 19 Oct 2016 11:49:12 -0600 Message-ID: <30fef8cd-67cc-da49-77d9-9d1a833f8a48@fb.com> References: <20150618155337.GA10439@thunk.org> <20150618233430.GK20262@dastard> <20160929043722.ypf3tnxsl6ovt653@thunk.org> <20161012211407.GL23194@dastard> <20161013021552.l6afs2k5tjcsfp2k@thunk.org> <20161013231923.j2fidfbtzdp66x3t@thunk.org> <20161018180107.fscbfm66yidwhey4@thunk.org> <7856791a-0795-9183-6057-6ce8fd0e3d58@fb.com> Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Cc: Dave Chinner , , , To: "Theodore Ts'o" Return-path: In-Reply-To: <7856791a-0795-9183-6057-6ce8fd0e3d58@fb.com> Sender: fstests-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On 10/19/2016 08:06 AM, Jens Axboe wrote: > On 10/18/2016 12:01 PM, Theodore Ts'o wrote: >> Jens, ping? >> >> Have you had a chance to take a look at the stack traces? Is there >> any other debugging information I can get for you? > > I'll take a look today. I agree, this definitely looks like a fio > bug. But not related to the mutex issue for the stat part, all verifier > threads are waiting to be woken up, but the main thread is done. > > I'll see if I can reproduce. If not, I may ask you to dump more info > from the hung processes. Been running for 4 hours now, in a loop, with bs=1k. I haven't been able to reproduce. Before I go through the hassle of doing the google compute engine thing, can you give me some details of the hardware? Number of cores/nodes? Memory size? Rough speed and size of the device? Any special mkfs options? And whatever else might be relevant. -- Jens Axboe