nilfs2: improve the performance of fdatasync()
Support for fdatasync() has been implemented in NILFS2 for a long time,
but whenever the corresponding inode is dirty the implementation falls
back to a full-flegded sync(). Since every write operation has to
update the modification time of the file, the inode will almost always
be dirty and fdatasync() will fall back to sync() most of the time. But
this fallback is only necessary for a change of the file size and not
for a change of the various timestamps.
This patch adds a new flag NILFS_I_INODE_SYNC to differentiate between
those two situations.
* If it is set the file size was changed and a full sync is necessary.
* If it is not set then only the timestamps were updated and
fdatasync() can go ahead.
There is already a similar flag I_DIRTY_DATASYNC on the VFS layer with
the exact same semantics. Unfortunately it cannot be used directly,
because NILFS2 doesn't implement write_inode() and doesn't clear the VFS
flags when inodes are written out. So the VFS writeback thread can
clear I_DIRTY_DATASYNC at any time without notifying NILFS2. So
I_DIRTY_DATASYNC has to be mapped onto NILFS_I_INODE_SYNC in
nilfs_update_inode().
Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index d071e7f..e1fa69b 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -126,7 +126,7 @@
nilfs_transaction_abort(inode->i_sb);
goto out;
}
- nilfs_mark_inode_dirty(inode);
+ nilfs_mark_inode_dirty_sync(inode);
nilfs_transaction_commit(inode->i_sb); /* never fails */
/* Error handling should be detailed */
set_buffer_new(bh_result);
@@ -672,7 +672,7 @@
for substitutions of appended fields */
}
-void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
+void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
{
ino_t ino = inode->i_ino;
struct nilfs_inode_info *ii = NILFS_I(inode);
@@ -683,7 +683,8 @@
if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
- set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
+ if (flags & I_DIRTY_DATASYNC)
+ set_bit(NILFS_I_INODE_SYNC, &ii->i_state);
nilfs_write_inode_common(inode, raw_inode, 0);
/* XXX: call with has_bmap = 0 is a workaround to avoid
@@ -939,7 +940,7 @@
return 0;
}
-int nilfs_mark_inode_dirty(struct inode *inode)
+int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
{
struct buffer_head *ibh;
int err;
@@ -950,7 +951,7 @@
"failed to reget inode block.\n");
return err;
}
- nilfs_update_inode(inode, ibh);
+ nilfs_update_inode(inode, ibh, flags);
mark_buffer_dirty(ibh);
nilfs_mdt_mark_dirty(NILFS_I(inode)->i_root->ifile);
brelse(ibh);
@@ -983,7 +984,7 @@
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
- nilfs_mark_inode_dirty(inode);
+ __nilfs_mark_inode_dirty(inode, flags);
nilfs_transaction_commit(inode->i_sb); /* never fails */
}