ext4: Don't update ctime for non-extent-mapped inodes (41591750) · Commits · 戴 / test

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 allocated. Thanks to Björn Steinbrink for pointing out this problem on the git mailing list. Signed-off-by:

"Theodore Ts'o" <tytso@mit.edu>

fs/ext4/inode.c

+1 −5

Original line number	Diff line number	Diff line
		@@ -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);

		/* had we spliced it onto indirect block? */
		if (where->bh) {
		/*
		@@ -878,8 +874,8 @@ static int ext4_splice_branch(handle_t handle, struct inode inode,
		} else {
		/*
		* OK, we spliced it into the inode itself on a direct block.
		* Inode was dirtied above.
		*/
		ext4_mark_inode_dirty(handle, inode);
		jbd_debug(5, "splicing direct\n");
		}
		return err;

Admin message