From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755894Ab1AaSl7 (ORCPT ); Mon, 31 Jan 2011 13:41:59 -0500 Received: from e23smtp08.au.ibm.com ([202.81.31.141]:44377 "EHLO e23smtp08.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752143Ab1AaSl6 (ORCPT ); Mon, 31 Jan 2011 13:41:58 -0500 From: "Aneesh Kumar K. V" To: Miklos Szeredi Cc: v9fs-developer@lists.sourceforge.net, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [RFC PATCH -V1 0/7] Buffered write and writeable mmap support for 9P In-Reply-To: References: <1296329186-23807-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com> User-Agent: Notmuch/0.5-64-gc3ae51d (http://notmuchmail.org) Emacs/23.1.1 (i486-pc-linux-gnu) Date: Tue, 01 Feb 2011 00:11:51 +0530 Message-ID: <877hdk9aq8.fsf@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 31 Jan 2011 10:38:10 +0100, Miklos Szeredi wrote: > On Sun, 30 Jan 2011, Aneesh Kumar K.V wrote: > > The patch series implement buffered write and writeable mmap for 9P > > P9 is supposed to work with servers on the local machine, right? Yes > > In that case you need to think about various deadlock scenarios. An > example: the P9 server needs a large order allocation while serving > the buffered write request. That may trigger the page reclaim and go > into synchronous writeback, possibly waiting on the exact page which > the P9 server is just trying to finish writing out. > > This is not easy to deal with, see commit 3be5a52b for the fuse > solution. I'm not saying it's the only way, there may be a better > one. > Thanks for the commit info. I will look at the details and see how best we can solve this in 9P -aneesh