linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jan Kara <jack@suse.cz>
To: Al Viro <viro@ZenIV.linux.org.uk>
Cc: <linux-fsdevel@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Curt Wohlgemuth <curtw@google.com>,
	Christoph Hellwig <hch@infradead.org>, Jan Kara <jack@suse.cz>
Subject: [PATCH 7/8] vfs: Remove unnecessary flushing of block devices
Date: Tue,  3 Jul 2012 16:45:33 +0200	[thread overview]
Message-ID: <1341326734-29881-8-git-send-email-jack@suse.cz> (raw)
In-Reply-To: <1341326734-29881-1-git-send-email-jack@suse.cz>

It is not necessary to write block devices twice. The reason why we first did
flush and then proper sync is that
  for_each_bdev() {
    write_bdev()
    wait_for_completion()
  }
is much slower than
  for_each_bdev()
    write_bdev()
  for_each_bdev()
    wait_for_completion()
when there is bigger amount of data. But as is seen in the above, there's no real
need to scan pages and submit them twice. We just need to separate the submission
and waiting part. This patch does that.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/sync.c |   16 ++++++++--------
 1 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c
index ea6e818..6d177d1 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -85,14 +85,14 @@ static void sync_fs_one_sb(struct super_block *sb, void *arg)
 		sb->s_op->sync_fs(sb, *(int *)arg);
 }
 
-static void flush_one_bdev(struct block_device *bdev, void *arg)
+static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
 {
-	__sync_blockdev(bdev, 0);
+	filemap_fdatawrite(bdev->bd_inode->i_mapping);
 }
 
-static void sync_one_bdev(struct block_device *bdev, void *arg)
+static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
 {
-	sync_blockdev(bdev);
+	filemap_fdatawait(bdev->bd_inode->i_mapping);
 }
 
 /*
@@ -106,10 +106,10 @@ SYSCALL_DEFINE0(sync)
 	wakeup_flusher_threads(0, WB_REASON_SYNC);
 	iterate_supers(writeback_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_bdevs(flush_one_bdev, NULL);
 	iterate_supers(sync_inodes_one_sb, NULL);
 	iterate_supers(sync_fs_one_sb, &wait);
-	iterate_bdevs(sync_one_bdev, NULL);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
+	iterate_bdevs(fdatawait_one_bdev, NULL);
 	if (unlikely(laptop_mode))
 		laptop_sync_completion();
 	return 0;
@@ -125,10 +125,10 @@ static void do_sync_work(struct work_struct *work)
 	 */
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_bdevs(flush_one_bdev, NULL);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
 	iterate_supers(sync_inodes_one_sb, &nowait);
 	iterate_supers(sync_fs_one_sb, &nowait);
-	iterate_bdevs(flush_one_bdev, NULL);
+	iterate_bdevs(fdatawrite_one_bdev, NULL);
 	printk("Emergency Sync complete\n");
 	kfree(work);
 }
-- 
1.7.1

  parent reply	other threads:[~2012-07-03 14:45 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-07-03 14:45 [PATCH 0/8 v4] Flush all block devices on sync(2) and cleanup the code Jan Kara
2012-07-03 14:45 ` [PATCH 1/8] vfs: Move noop_backing_dev_info check from sync into writeback Jan Kara
2012-07-03 14:45 ` [PATCH 2/8] quota: Split dquot_quota_sync() to writeback and cache flushing part Jan Kara
2012-07-03 14:45 ` [PATCH 3/8] quota: Move quota syncing to ->sync_fs method Jan Kara
2012-07-03 14:45 ` [PATCH 4/8] vfs: Reorder operations during sys_sync Jan Kara
2012-07-03 14:45 ` [PATCH 5/8] vfs: Create function for iterating over block devices Jan Kara
2012-07-03 14:45 ` [PATCH 6/8] vfs: Make sys_sync writeout also block device inodes Jan Kara
2012-07-17  6:27   ` Fengguang Wu
2012-07-20  2:21     ` Fengguang Wu
2012-07-03 14:45 ` Jan Kara [this message]
2012-07-03 14:45 ` [PATCH 8/8] vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes Jan Kara
  -- strict thread matches above, loose matches on Subject: below --
2012-01-05 23:46 [PATCH 0/8 RESEND] Cleanup and improve sync (v4) Jan Kara
2012-01-05 23:46 ` [PATCH 7/8] vfs: Remove unnecessary flushing of block devices Jan Kara
2011-11-09 17:44 [PATCH 0/8] Cleanup and improve sync (v4) Jan Kara
2011-11-09 17:45 ` [PATCH 7/8] vfs: Remove unnecessary flushing of block devices 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=1341326734-29881-8-git-send-email-jack@suse.cz \
    --to=jack@suse.cz \
    --cc=curtw@google.com \
    --cc=hch@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=viro@ZenIV.linux.org.uk \
    /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: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).