aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/disk-io.c
diff options
context:
space:
mode:
authorChris Mason <chris.mason@oracle.com>2009-03-31 13:27:11 -0400
committerChris Mason <chris.mason@oracle.com>2009-03-31 14:27:58 -0400
commit5a3f23d515a2ebf0c750db80579ca57b28cbce6d (patch)
treee0ffb43dd35f1c3def9a74ec7a6f4470902c9761 /fs/btrfs/disk-io.c
parent1a81af4d1d9c60d4313309f937a1fc5567205a87 (diff)
Btrfs: add extra flushing for renames and truncates
Renames and truncates are both common ways to replace old data with new data. The filesystem can make an effort to make sure the new data is on disk before actually replacing the old data. This is especially important for rename, which many application use as though it were atomic for both the data and the metadata involved. The current btrfs code will happily replace a file that is fully on disk with one that was just created and still has pending IO. If we crash after transaction commit but before the IO is done, we'll end up replacing a good file with a zero length file. The solution used here is to create a list of inodes that need special ordering and force them to disk before the commit is done. This is similar to the ext3 style data=ordering, except it is only done on selected files. Btrfs is able to get away with this because it does not wait on commits very often, even for fsync (which use a sub-commit). For renames, we order the file when it wasn't already on disk and when it is replacing an existing file. Larger files are sent to filemap_flush right away (before the transaction handle is opened). For truncates, we order if the file goes from non-zero size down to zero size. This is a little different, because at the time of the truncate the file has no dirty bytes to order. But, we flag the inode so that it is added to the ordered list on close (via release method). We also immediately add it to the ordered list of the current transaction so that we can try to flush down any writes the application sneaks in before commit. Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r--fs/btrfs/disk-io.c2
1 files changed, 2 insertions, 0 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9244cd7313d4..1747dfd18654 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1572,6 +1572,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
1572 INIT_LIST_HEAD(&fs_info->dead_roots); 1572 INIT_LIST_HEAD(&fs_info->dead_roots);
1573 INIT_LIST_HEAD(&fs_info->hashers); 1573 INIT_LIST_HEAD(&fs_info->hashers);
1574 INIT_LIST_HEAD(&fs_info->delalloc_inodes); 1574 INIT_LIST_HEAD(&fs_info->delalloc_inodes);
1575 INIT_LIST_HEAD(&fs_info->ordered_operations);
1575 spin_lock_init(&fs_info->delalloc_lock); 1576 spin_lock_init(&fs_info->delalloc_lock);
1576 spin_lock_init(&fs_info->new_trans_lock); 1577 spin_lock_init(&fs_info->new_trans_lock);
1577 spin_lock_init(&fs_info->ref_cache_lock); 1578 spin_lock_init(&fs_info->ref_cache_lock);
@@ -1643,6 +1644,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
1643 insert_inode_hash(fs_info->btree_inode); 1644 insert_inode_hash(fs_info->btree_inode);
1644 1645
1645 mutex_init(&fs_info->trans_mutex); 1646 mutex_init(&fs_info->trans_mutex);
1647 mutex_init(&fs_info->ordered_operations_mutex);
1646 mutex_init(&fs_info->tree_log_mutex); 1648 mutex_init(&fs_info->tree_log_mutex);
1647 mutex_init(&fs_info->drop_mutex); 1649 mutex_init(&fs_info->drop_mutex);
1648 mutex_init(&fs_info->pinned_mutex); 1650 mutex_init(&fs_info->pinned_mutex);