From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ryusuke Konishi Subject: Re: Deadlocks! help, please! Date: Tue, 22 Jan 2008 12:02:00 +0900 Message-ID: <1200970920.2844.59.camel@localhost.localdomain> References: <20080117183302.275d051d@vosztok> <1200628693.2931.54.camel@localhost.localdomain> <1200651072.2931.112.camel@localhost.localdomain> <20080121.140129.01311807.ryusuke@osrg.net> <20080122000052.215084db@vosztok> Reply-To: NILFS Users mailing list Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <20080122000052.215084db@vosztok> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: users-bounces-JrjvKiOkagjYtjvyW6yDsg@public.gmane.org Errors-To: users-bounces-JrjvKiOkagjYtjvyW6yDsg@public.gmane.org Content-Type: text/plain; charset="iso-8859-1" To: NILFS Users mailing list Hi, On Tue, 2008-01-22 at 00:00 +0100, Gergely G=E1bor wrote: > > Here I attach a test patch to fix the problem. > > Could you try the patch ? > >=20 > > So, if rtorrent (or something else) hang again, then > > send me a copy of /proc/slabinfo, please. > It hang again, Ugh! OK, I'll continue to work on it. > but i have to note, that i had to respin kernel,=20 > as I used SLUB before (some make oldconfig possibly=20 > defaulted to that or suggested that), and had no /proc/slabinfo. > With SLUB even with the patch in place, the machine froze, > and with SLAB i did a fine ~6 hour uptime, and was just telling > a friend that nilfs is just right now, when it stuck :) > the hang occured when epiphany ( based on gecko. memleaker :( )=20 > eat up a lot of ram, and I was just about to close it.=20 > some massive swapping happened, and the fs hang. > I attach many stuff, might they help: a log with call trace,=20 > a copy of slabinfo and the kernel config, might that be of any use. Thanks a lot for providing various information. Actually I have a machine with a SLUB configured kernel, but it's not so problematic. I wonder why NILFS hangs so offten=20 in your environment :) Joking aside, one of key differences that my colleague=20 pointed out, is that your kernel is non-smp one. We'll try your config to get better environment to debug. Best regards, --=20 Ryusuke Konishi NILFS team NTT http://www.nilfs.org/