[PATCH] ext3: speed up O_SYNC writes

This is a forward-port of a 2.4 change from Stephen.  The (old) 2.5 code is
forcing a commit on every write by artificially dirtying the inode.

But generic_file_aio_write() has called generic_osync_inode() for us, which
has synced the file data.  There is no need to force the extra commit.

fs/ext3/file.c

@@ -55,29 +55,61 @@ static int ext3_open_file (struct inode * inode, struct file * filp)
 	return 0;
 }
 
-/*
- * ext3_file_write().
- *
- * Most things are done in ext3_prepare_write() and ext3_commit_write().
- */
-
 static ssize_t
 ext3_file_write(struct kiocb *iocb, const char *buf, size_t count, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_dentry->d_inode;
+	int ret, err;
+
+	ret = generic_file_aio_write(iocb, buf, count, pos);
 
 	/*
-	 * Nasty: if the file is subject to synchronous writes then we need
-	 * to force generic_osync_inode() to call ext3_write_inode().
-	 * We do that by marking the inode dirty.  This adds much more
-	 * computational expense than we need, but we're going to sync
-	 * anyway.
+	 * Skip flushing if there was an error, or if nothing was written.
+	 */
+	if (ret <= 0)
+		return ret;
+	
+	/*
+	 * If the inode is IS_SYNC, or is O_SYNC and we are doing data
+	 * journalling then we need to make sure that we force the transaction
+	 * to disk to keep all metadata uptodate synchronously.
 	 */
-	if (IS_SYNC(inode) || (file->f_flags & O_SYNC))
-		mark_inode_dirty(inode);
+	if (file->f_flags & O_SYNC) {
+		/*
+		 * If we are non-data-journaled, then the dirty data has
+		 * already been flushed to backing store by generic_osync_inode,
+		 * and the inode has been flushed too if there have been any
+		 * modifications other than mere timestamp updates.
+		 *
+		 * Open question --- do we care about flushing timestamps too
+		 * if the inode is IS_SYNC?
+		 */
+		if (!ext3_should_journal_data(inode))
+			return ret;
+
+		goto force_commit;
+	}
 
-	return generic_file_aio_write(iocb, buf, count, pos);
+	/*
+	 * So we know that there has been no forced data flush.  If the inode
+	 * is marked IS_SYNC, we need to force one ourselves.
+	 */
+	if (!IS_SYNC(inode))
+		return ret;
+	
+	/*
+	 * Open question #2 --- should we force data to disk here too?  If we
+	 * don't, the only impact is that data=writeback filesystems won't
+	 * flush data to disk automatically on IS_SYNC, only metadata (but
+	 * historically, that is what ext2 has done.)
+	 */
+	
+force_commit:
+	err = ext3_force_commit(inode->i_sb);
+	if (err) 
+		return err;
+	return ret;
 }
 
 struct file_operations ext3_file_operations = {