From: Christoph Hellwig <hch@infradead.org> To: Wu Fengguang <fengguang.wu@intel.com> Cc: linux-fsdevel@vger.kernel.org, xfs@oss.sgi.com Subject: [PATCH, RFC] writeback: avoid redirtying when ->write_inode failed to clear I_DIRTY Date: Sat, 27 Aug 2011 02:14:09 -0400 [thread overview] Message-ID: <20110827061409.GA6854@infradead.org> (raw) Right now ->write_inode has no way to safely return a EAGAIN without explicitly redirtying the inode, as we would lose the dirty state otherwise. Most filesystems get this wrong, but XFS makes heavy use of it to avoid blocking the flusher thread when ->write_inode hits contentended inode locks. A contended ilock is something XFS can hit very easibly when extending files, as the data I/O completion handler takes the lock to update the size, and the ->write_inode call can race with it fairly easily if writing enough data in one go so that the completion for the first write come in just before we call ->write_inode. Change the handling of this case to use requeue_io for a quick retry instead of redirty_tail, which keeps moving out the dirtied_when data and thus keeps delaying the writeout more and more with every failed attempt to get the lock. Signed-off-by: Christoph Hellwig <hch@lst.de> Index: linux-2.6/fs/fs-writeback.c =================================================================== --- linux-2.6.orig/fs/fs-writeback.c 2011-08-26 14:47:42.137050059 +0200 +++ linux-2.6/fs/fs-writeback.c 2011-08-26 15:06:47.003493601 +0200 @@ -464,8 +464,18 @@ writeback_single_inode(struct inode *ino * operations, such as delayed allocation during * submission or metadata updates after data IO * completion. + * + * For the latter case it is very important to give + * the inode another turn on b_more_io instead of + * redirtying it. Constantly moving dirtied_when + * forward will prevent us from ever writing out + * the metadata dirtied in the I/O completion handler. + * + * For files on XFS that constantly get appended to + * calling redirty_tail means they will never get + * their updated i_size written out. */ - redirty_tail(inode, wb); + requeue_io(inode, wb); } else { /* * The inode is clean. At this point we either have
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@infradead.org> To: Wu Fengguang <fengguang.wu@intel.com> Cc: linux-fsdevel@vger.kernel.org, xfs@oss.sgi.com Subject: [PATCH, RFC] writeback: avoid redirtying when ->write_inode failed to clear I_DIRTY Date: Sat, 27 Aug 2011 02:14:09 -0400 [thread overview] Message-ID: <20110827061409.GA6854@infradead.org> (raw) Right now ->write_inode has no way to safely return a EAGAIN without explicitly redirtying the inode, as we would lose the dirty state otherwise. Most filesystems get this wrong, but XFS makes heavy use of it to avoid blocking the flusher thread when ->write_inode hits contentended inode locks. A contended ilock is something XFS can hit very easibly when extending files, as the data I/O completion handler takes the lock to update the size, and the ->write_inode call can race with it fairly easily if writing enough data in one go so that the completion for the first write come in just before we call ->write_inode. Change the handling of this case to use requeue_io for a quick retry instead of redirty_tail, which keeps moving out the dirtied_when data and thus keeps delaying the writeout more and more with every failed attempt to get the lock. Signed-off-by: Christoph Hellwig <hch@lst.de> Index: linux-2.6/fs/fs-writeback.c =================================================================== --- linux-2.6.orig/fs/fs-writeback.c 2011-08-26 14:47:42.137050059 +0200 +++ linux-2.6/fs/fs-writeback.c 2011-08-26 15:06:47.003493601 +0200 @@ -464,8 +464,18 @@ writeback_single_inode(struct inode *ino * operations, such as delayed allocation during * submission or metadata updates after data IO * completion. + * + * For the latter case it is very important to give + * the inode another turn on b_more_io instead of + * redirtying it. Constantly moving dirtied_when + * forward will prevent us from ever writing out + * the metadata dirtied in the I/O completion handler. + * + * For files on XFS that constantly get appended to + * calling redirty_tail means they will never get + * their updated i_size written out. */ - redirty_tail(inode, wb); + requeue_io(inode, wb); } else { /* * The inode is clean. At this point we either have _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs
next reply other threads:[~2011-08-27 6:14 UTC|newest] Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-08-27 6:14 Christoph Hellwig [this message] 2011-08-27 6:14 ` [PATCH, RFC] writeback: avoid redirtying when ->write_inode failed to clear I_DIRTY Christoph Hellwig 2011-08-27 13:58 ` Wu Fengguang 2011-08-27 13:58 ` Wu Fengguang 2011-09-03 1:13 ` Jan Kara 2011-09-03 1:13 ` Jan Kara 2011-09-03 21:35 ` Wu Fengguang 2011-09-03 21:35 ` Wu Fengguang 2011-09-05 11:11 ` Jan Kara 2011-09-05 11:11 ` Jan Kara 2011-09-05 13:22 ` Wu Fengguang 2011-09-05 13:22 ` Wu Fengguang 2011-09-07 11:52 ` Christoph Hellwig 2011-09-07 11:52 ` Christoph Hellwig 2011-09-07 12:51 ` Wu Fengguang 2011-09-08 0:51 ` Jan Kara 2011-09-08 0:51 ` Jan Kara
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20110827061409.GA6854@infradead.org \ --to=hch@infradead.org \ --cc=fengguang.wu@intel.com \ --cc=linux-fsdevel@vger.kernel.org \ --cc=xfs@oss.sgi.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.