zfs discuss - Sep 2012 - Failure to zfs destroy - after interrupting zfs receive

Formerly, if you interrupted a zfs receive, it would leave a clone with a % in
its name, and you could find it via "zdb -d" and then you could
destroy the clone, and then you could destroy the filesystem you had interrupted
receiving.

That was considered a bug, and it was fixed, I think by Sun.  If the lingering
clone was discovered laying around, zfs would automatically destroy it.  But now
I''m encountering a new version of the same problem...

Unfortunately, now I have a filesystem where "zfs receive" was
interrupted, and I can''t destroy the filesystem or the snapshot of the
filesystem on the receiving side.

sudo zfs destroy -R tank/Downloads
cannot destroy ''tank/Downloads at
zfs-auto-snap_hourly-2012-08-31-17h54'': dataset already exists

sudo zfs destroy -R tank/Downloads at zfs-auto-snap_hourly-2012-08-31-17h54
cannot destroy snapshot tank/Downloads at zfs-auto-snap_hourly-2012-08-31-17h54:
snapshot is cloned

sudo zfs list -t all | grep Downloads
tank/Downloads
tank/Downloads at zfs-auto-snap_hourly-2012-08-31-17h54

sudo zdb -d tank/Downloads
Dataset tank/Downloads [ZPL], ID 139, cr_txg 31408, 3.91G, 30 objects
(Notice, I don''t get any clones listed.)

I''m running openindiana 151.1.6 (the latest, fully patched a couple of
weeks ago.)

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20120928/4d58b25c/attachment.html>

I have the same issue as described by Ned in his email.  I had a zfs
recv going that deadlocked against a zfs list; after a day of leaving
them hung I finally had to hard reset the box (shutdown wouldn''t, since
it couldn''t terminate the processes).  When it came back up, I wanted
to
zfs destroy that last snapshot but I got the dreaded

cannot destroy ''export/upload at partial-2012-10-01_08:00:00'':
snapshot is
cloned

but there are no clones:

root at ms8 # zdb -d export/upload | grep ''%''
root at ms8 #

and an attempt to remove what the clone ought to be fails:

zfs destroy export/upload/%partial-2012-10-01_08:00:00
cannot open ''export/upload/%partial-2012-10-01_08:00:00'':
dataset does
not exist

This isn''t opensolaris, it''s SunOS 5.10 Generic_142901-06 from
before
Oracle took it over, but that''s not going to make any difference as to
the bug, I think.  Any ideas?

> From: zfs-discuss-bounces at opensolaris.org [mailto:zfs-discuss-
> bounces at opensolaris.org] On Behalf Of Ariel T. Glenn
> 
> I have the same issue as described by Ned in his email.  I had a zfs
> recv going that deadlocked against a zfs list; after a day of leaving
> them hung I finally had to hard reset the box (shutdown wouldn''t,
since
> it couldn''t terminate the processes).  When it came back up, I
wanted to
> zfs destroy that last snapshot but I got the dreaded
For what it''s worth - that is precisely the behavior I saw.  No
"zfs" or "zpool" commands would return, and eventually the
system hung badly enough I had to power cycle.  And afterward, I was unable to
destroy either the filesystem, the snapshot, or any clones.  I posted here,
didn''t get any response...  And at some point, I "zfs send"
my filesystem somewhere else, destroy & recreate the pool, "zfs
send" the filesystem back.

http://mail.opensolaris.org/pipermail/zfs-discuss/2012-September/052412.html