2009-06-15 07:43:54

by Theodore Ts'o

[permalink] [raw]
Subject: [PATCH] ext4: Don't update ctime for non-extent-mapped inodes

The VFS handles updating ctime, so we don't need to update the inode's
ctime in ext4_splace_branch() to update the direct or indirect blocks.
This was harmless when we did this in ext3, but in ext4, thanks to
delayed allocation, updating the ctime in ext4_splice_branch() can
cause the ctime to mysteriously jump when the blocks are finally

Thanks to Björn Steinbrink for pointing out this problem on the git
mailing list.

Signed-off-by: "Theodore Ts'o" <[email protected]>
fs/ext4/inode.c | 6 +-----
1 files changed, 1 insertions(+), 5 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8d0908a..7c17ae2 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -856,10 +856,6 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,

/* We are done with atomic stuff, now do the rest of housekeeping */
- inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);