Return-Path: Received: from minas.ics.muni.cz ([147.251.4.40]:58692 "EHLO minas.ics.muni.cz" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757004Ab0EYOXG (ORCPT ); Tue, 25 May 2010 10:23:06 -0400 Date: Tue, 25 May 2010 16:07:42 +0200 From: Zdenek Salvet To: Trond Myklebust Cc: Lukas Hejtmanek , Pavel Machek , linux-nfs@vger.kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, salvet@ics.muni.cz Subject: Re: Deadlock in NFSv4 in all kernels Message-ID: <20100525140742.GM12852@horn.ics.muni.cz> Reply-To: salvet@ics.muni.cz References: <20100507153920.GP28167@ics.muni.cz> <20100524212422.GA1286@ucw.cz> <1274790520.2949.20.camel@heimdal.trondhjem.org> <20100525125833.GB9731@ics.muni.cz> <1274794765.5377.43.camel@heimdal.trondhjem.org> Content-Type: text/plain; charset=us-ascii In-Reply-To: <1274794765.5377.43.camel@heimdal.trondhjem.org> Sender: linux-nfs-owner@vger.kernel.org List-ID: MIME-Version: 1.0 On Tue, May 25, 2010 at 09:39:25AM -0400, Trond Myklebust wrote: > The schemes I'm talking about typically had special memory pools > preallocated for use by daemons, and would label the daemons using some > equivalent of the PF_MEMALLOC flag to prevent recursion into the > filesystem. Yes. In my opinion, proper solution has to be careful at three points: - daemons must be carefully written not to require much memory - daemons should 'inherit' PF_MEMALLOC while processing upcalls - FS should try to flush fast enough (what W. Adamson wrote) and delay new allocations when it cannot Regards, Zdenek Salvet salvet@ics.muni.cz Institute of Computer Science of Masaryk University, Brno, Czech Republic and CESNET, z.s.p.o., Prague, Czech Republic Phone: ++420-549 49 6534 Fax: ++420-541 212 747 ---------------------------------------------------------------------------- Teamwork is essential -- it allows you to blame someone else.