On Mon, Dec 17, 2012 at 12:24:53AM -0700, Miao Xie wrote:

On 	fri, 14 Dec 2012 12:51:06 -0500, Josef Bacik wrote:

quoted

On Mon, Nov 26, 2012 at 02:28:13AM -0700, Miao Xie wrote:

quoted

If we remount the fs to close the auto defragment or make the fs R/O, we should
stop the auto defragment.

Signed-off-by: Miao Xie <redacted>

I'm dropping this patch, it causes a deadlock since defrag will need to reserve
metadata which could call writeback_sb_nr_if_idle which does a
down_read(&sb->s_umount).  Figure out another way to fix this and I'll apply it.
Thanks,

Hi, Josef

I forget to point out this patch is based on my patches:
	[PATCH 1/2 RESEND] vfs: re-implement writeback_inodes_sb(_nr)_if_idle() and rename them
	[PATCH 2/2 RESEND] Btrfs: flush all the dirty pages if try_to_writeback_inodes_sb_nr() fails

But I found you implemented a new writeback_sb_nr_if_idle()(Btrfs: fix autodefrag and umount lockup),
with this new function, my patch(Btrfs: fix remount vs autodefrag) also can wrok well.

Yeah I'll pull them on now.  Once Al takes the vfs patch we can drop my local
function, so when that happens send a patch to remove it please.  Thanks,

Josef