From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765900AbZAOXqe (ORCPT ); Thu, 15 Jan 2009 18:46:34 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1763704AbZAOXpt (ORCPT ); Thu, 15 Jan 2009 18:45:49 -0500 Received: from styx.suse.cz ([82.119.242.94]:34262 "EHLO mail.suse.cz" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S935536AbZAOXpq (ORCPT ); Thu, 15 Jan 2009 18:45:46 -0500 Date: Fri, 16 Jan 2009 00:45:44 +0100 From: Jan Kara To: Fernando Luis =?iso-8859-1?Q?V=E1zquez?= Cao Cc: Theodore Tso , Jan Kara , Alan Cox , Pavel Machek , kernel list , Jens Axboe , sandeen@redhat.com Subject: Re: ext2 + -osync: not as easy as it seems Message-ID: <20090115234544.GA7579@duck.suse.cz> References: <20090113140347.GD17664@mit.edu> <20090113143011.GB10064@duck.suse.cz> <1231904239.11640.38.camel@sebastian.kern.oss.ntt.co.jp> <20090114103532.GA18834@duck.suse.cz> <20090114132146.GC6222@mit.edu> <20090114140532.GC19950@duck.suse.cz> <20090114141204.GD6222@mit.edu> <20090114143756.GF19950@duck.suse.cz> <20090114165952.GH6222@mit.edu> <1232021211.14626.19.camel@sebastian.kern.oss.ntt.co.jp> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <1232021211.14626.19.camel@sebastian.kern.oss.ntt.co.jp> User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu 15-01-09 21:06:51, Fernando Luis Vázquez Cao wrote: > On Wed, 2009-01-14 at 11:59 -0500, Theodore Tso wrote: > > On Wed, Jan 14, 2009 at 03:37:56PM +0100, Jan Kara wrote: > > > > Um, we have that already; the sync_inode() followed by > > > > blkdev_issue_flush() is the path taken by fdatasync(), I do believe. > > > > > > Maybe ext4-patch-queue changes that area but in Linus's tree I see: > > > > > > if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) > > > goto out; > > > > > > So if we just overwrite some data, we send them to disk via fdatawrite() > > > and then we quickly bail out from ext4_sync_file() without doing > > > blkdev_issue_flush(). > > > > So you're thinking about fdatawrite() being called by some code path > > other than ext4_sync_file() before we call fsync()? Yeah, that could > > happen.... I think that will only happen if the file is opened > > O_SYNC, but that raises another issue, which is that we're not forcing > > a flush for writes when the file is opened O_SYNC. > > Hi Jan, Ted > > Is something like the patch below what you had in mind? > > -- > > From: Fernando Luis Vazquez Cao > Subject: ext3: call blkdev_issue_flush on fsync > > To ensure that bits are truly on-disk after an fsync or fdatasync, we > should call blkdev_issue_flush if barriers are supported. > > Signed-off-by: Fernando Luis Vazquez Cao > --- > > --- linux-2.6.29-rc1-orig/fs/ext4/fsync.c 2008-12-25 08:26:37.000000000 +0900 > +++ linux-2.6.29-rc1/fs/ext4/fsync.c 2009-01-15 21:03:19.000000000 +0900 > @@ -48,6 +48,7 @@ int ext4_sync_file(struct file *file, st > { > struct inode *inode = dentry->d_inode; > journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; > + unsigned long i_state = inode->i_state; > int ret = 0; > > J_ASSERT(ext4_journal_current_handle() == NULL); > @@ -79,22 +80,35 @@ int ext4_sync_file(struct file *file, st > goto out; > } > > - if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) > - goto out; > + if (datasync && !(i_state & I_DIRTY_DATASYNC)) > + goto flush_blkdev; > > /* > * The VFS has written the file data. If the inode is unaltered > * then we need not start a commit. > */ > - if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) { > + if (i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) { > struct writeback_control wbc = { > .sync_mode = WB_SYNC_ALL, > .nr_to_write = 0, /* sys_fsync did this */ > }; > ret = sync_inode(inode, &wbc); > - if (journal && (journal->j_flags & JBD2_BARRIER)) > - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); > + /* > + * When there are no blocks attached to the journal transaction > + * some optimizations are possible, but if there were dirty > + * pages sync_inode() should have ensured that all data gets > + * actually written to disk. Thus, we can skip > + * blkdev_issue_flush() below. > + */ > + if (!(i_state & I_DIRTY_PAGES)) > + goto flush_blkdev; Uh. Here I don't get it. When we did sync_inode(), blkdev_issue_flush() is needed only if the journal does not do barriers. So I'd expect here: if (!(journal->j_flags & JBD2_BARRIER)) goto flush_blkdev; goto out; > } > + > + goto out; But here we might need to issue a flush if there are some data written. So I'd have here: if (!(i_state & I_DIRTY_PAGES)) goto out; > + > +flush_blkdev: > + if (journal && (journal->j_flags & JBD2_BARRIER)) > + blkdev_issue_flush(inode->i_sb->s_bdev, NULL); > out: > return ret; > } Honza -- Jan Kara SUSE Labs, CR