From: Eric Sandeen Subject: Re: [PATCH RFC] Insure direct IO writes do not use the page cache Date: Wed, 29 Jul 2009 12:41:40 -0500 Message-ID: <4A7089D4.3030809@redhat.com> References: <6601abe90907281728h22be79fenc68a16b578e28a91@mail.gmail.com> <6601abe90907290910x7cf1122cwac689d1f106326d3@mail.gmail.com> <4A708451.4060908@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: ext4 development To: Curt Wohlgemuth Return-path: Received: from mx2.redhat.com ([66.187.237.31]:37065 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750780AbZG2Rlo (ORCPT ); Wed, 29 Jul 2009 13:41:44 -0400 In-Reply-To: <4A708451.4060908@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: Eric Sandeen wrote: ... > I haven't replied to the first mail yet because I have a lot of > remembering to do about xfs first, but I'm fairly certain that at least > your use of blockdev_direct_IO_own_locking() is not correct. See for > example all the comments around __blockdev_direct_IO about i_mutex, and > all the xfs_ilock/xfs_iolock calls in xfs_read/xfs_write. Oh and i_alloc_sem too, forgot about that one :) -Eric