Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 41591750 authored by Theodore Ts'o's avatar Theodore Ts'o
Browse files

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
allocated.

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

Signed-off-by: default avatar"Theodore Ts'o" <tytso@mit.edu>
parent de9a55b8

fs/ext4/inode.c

+1 −5
Original line number Original line 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 */

	/* 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? */

	/* had we spliced it onto indirect block? */

	if (where->bh) {

	if (where->bh) {

		/*

		/*
@@ -878,8 +874,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode, 
	} else {

	} else {

		/*

		/*

		 * OK, we spliced it into the inode itself on a direct block.

		 * 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");

		jbd_debug(5, "splicing direct\n");

	}

	}

	return err;

	return err;