linux.git/fs/sync.c, branch v2.6.31

sys_sync(): fix 16% performance regression in ffsb create_4k test

2009-07-06T20:57:03+00:00

I run many ffsb test cases on JBODs (typically 13/12 disks).  Comparing
with kernel 2.6.30, 2.6.31-rc1 has about 16% regression with
ffsb_create_4k.  The sub test case creates files continuously for 10
minitues and every file is 1MB.

Bisect located below patch.

5cee5815d1564bbbd505fea86f4550f1efdb5cd0 is first bad commit
commit 5cee5815d1564bbbd505fea86f4550f1efdb5cd0
Author: Jan Kara 
Date:   Mon Apr 27 16:43:51 2009 +0200

    vfs: Make sys_sync() use fsync_super() (version 4)

    It is unnecessarily fragile to have two places (fsync_super() and do_sync())
    doing data integrity sync of the filesystem. Alter __fsync_super() to
    accommodate needs of both callers and use it. So after this patch
    __fsync_super() is the only place where we gather all the calls needed to
    properly send all data on a filesystem to disk.

As a matter of fact, ffsb calls sys_sync in the end to make sure all data
is flushed to disks and the flushing is counted into the result.  vmstat
shows ffsb is blocked when syncing for a long time.  With 2.6.30, ffsb is
blocked for a short time.

I checked the patch and did experiments to recover the original methods.
Eventually, the root cause is the patch deletes the calling to
wakeup_pdflush when syncing, so only ffsb is blocked on disk I/O.
wakeup_pdflush could ask pdflush to write back pages with ffsb at the
same time.

[akpm@linux-foundation.org: restore comment too]
Signed-off-by: Zhang Yanmin 
Cc: Jan Kara 
Cc: Al Viro 
Acked-by: Jens Axboe 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

remove the call to ->write_super in __sync_filesystem

2009-06-12T01:36:17+00:00

Now that all filesystems provide ->sync_fs methods we can change
__sync_filesystem to only call ->sync_fs.

This gives us a clear separation between periodic writeouts which
are driven by ->write_super and data integrity syncs that go
through ->sync_fs. (modulo file_fsync which is also going away)

Signed-off-by: Christoph Hellwig 
Signed-off-by: Al Viro

->write_super lock_super pushdown

2009-06-12T01:36:09+00:00

Push down lock_super into ->write_super instances and remove it from the
caller.

Following filesystem don't need ->s_lock in ->write_super and are skipped:

 * bfs, nilfs2 - no other uses of s_lock and have internal locks in
	->write_super
 * ext2 - uses BKL in ext2_write_super and has internal calls without s_lock
 * reiserfs - no other uses of s_lock as has reiserfs_write_lock (BKL) in
 	->write_super
 * xfs - no other uses of s_lock and uses internal lock (buffer lock on
	superblock buffer) to serialize ->write_super.  Also xfs_fs_write_super
	is superflous and will go away in the next merge window

Signed-off-by: Christoph Hellwig 
Signed-off-by: Al Viro

enforce ->sync_fs is only called for rw superblock

2009-06-12T01:36:06+00:00

Make sure a superblock really is writeable by checking MS_RDONLY
under s_umount.  sync_filesystems needed some re-arragement for
that, but all but one sync_filesystem caller had the correct locking
already so that we could add that check there.  cachefiles grew
s_umount locking.

I've also added a WARN_ON to sync_filesystem to assert this for
future callers.

Signed-off-by: Christoph Hellwig 
Signed-off-by: Al Viro

quota: Introduce writeout_quota_sb() (version 4)

2009-06-12T01:36:04+00:00

Introduce this function which just writes all the quota structures but
avoids all the syncing and cache pruning work to expose quota structures
to userspace. Use this function from __sync_filesystem when wait == 0.

Signed-off-by: Jan Kara 
Signed-off-by: Al Viro

quota: cleanup dquota sync functions (version 4)

2009-06-12T01:36:04+00:00

Currently the VFS calls vfs_dq_sync to sync out disk quotas for a given
superblock.  This is a small wrapper around sync_dquots which for the
case of a non-NULL superblock is a small wrapper around quota_sync_sb.

Just make quota_sync_sb global (rename it to sync_quota_sb) and call it
directly.  Also call it directly for those cases in quota.c that have a
superblock and leave sync_dquots purely an iterator over sync_quota_sb and
remove it's superblock argument.

To make this nicer move the check for the lack of a quota_sync method
from the callers into sync_quota_sb.

[folded build fix from Alexander Beregalov ]

Signed-off-by: Christoph Hellwig 
Signed-off-by: Jan Kara 
Signed-off-by: Al Viro

vfs: Rename fsync_super() to sync_filesystem() (version 4)

2009-06-12T01:36:04+00:00

Rename the function so that it better describe what it really does. Also
remove the unnecessary include of buffer_head.h.

Signed-off-by: Jan Kara 
Signed-off-by: Al Viro

vfs: Move syncing code from super.c to sync.c (version 4)

2009-06-12T01:36:04+00:00

Move sync_filesystems(), __fsync_super(), fsync_super() from
super.c to sync.c where it fits better.

[build fixes folded]

Signed-off-by: Jan Kara 
Signed-off-by: Al Viro

vfs: Make sys_sync() use fsync_super() (version 4)

2009-06-12T01:36:03+00:00

It is unnecessarily fragile to have two places (fsync_super() and do_sync())
doing data integrity sync of the filesystem. Alter __fsync_super() to
accommodate needs of both callers and use it. So after this patch
__fsync_super() is the only place where we gather all the calls needed to
properly send all data on a filesystem to disk.

Nice bonus is that we get a complete livelock avoidance and write_supers()
is now only used for periodic writeback of superblocks.

sync_blockdevs() introduced a couple of patches ago is gone now.

[build fixes folded]

Signed-off-by: Jan Kara 
Signed-off-by: Al Viro

vfs: Fix sys_sync() and fsync_super() reliability (version 4)

2009-06-12T01:36:03+00:00

So far, do_sync() called:
  sync_inodes(0);
  sync_supers();
  sync_filesystems(0);
  sync_filesystems(1);
  sync_inodes(1);

This ordering makes it kind of hard for filesystems as sync_inodes(0) need not
submit all the IO (for example it skips inodes with I_SYNC set) so e.g. forcing
transaction to disk in ->sync_fs() is not really enough. Therefore sys_sync has
not been completely reliable on some filesystems (ext3, ext4, reiserfs, ocfs2
and others are hit by this) when racing e.g. with background writeback. A
similar problem hits also other filesystems (e.g. ext2) because of
write_supers() being called before the sync_inodes(1).

Change the ordering of calls in do_sync() - this requires a new function
sync_blockdevs() to preserve the property that block devices are always synced
after write_super() / sync_fs() call.

The same issue is fixed in __fsync_super() function used on umount /
remount read-only.

[AV: build fixes]

Signed-off-by: Jan Kara 
Signed-off-by: Al Viro