d_delete()) ahome3-MDD:
> error unlinking orphan [0x20001bb76:0xd86e:0x0]: rc = -2) - not sure if this
> could be related to the problem.
>
> We also had one login node locked up with a load of >4000 and many ps
> commands uninterruptible and hung. Again, not sure if this coul
> Mar 17 09:44:46 amds01b kernel: []
> > ptlrpc_main+0xb34/0x1470 [ptlrpc]
> > Mar 17 09:44:46 amds01b kernel: [] ?
> > ptlrpc_register_service+0xf80/0xf80 [ptlrpc]
> > Mar 17 09:44:46 amds01b kernel: [] kthread+0xd1/0xe0
> > Mar 17 09:44:46 amds01b kernel: [] ?
> > i
t_from_fork_nospec_begin+0x7/0x21
> Mar 17 09:44:46 amds01b kernel: [] ?
> insert_kthread_work+0x40/0x40
>
> Has anyone seen similar when using Lustre on ZFS and were you able to recover
> the filesystem to a workable state - I've found a few similar problems in the
> zfs mailing lists over the last
years, but no solutions.
Kind Regards,
Christopher.
From: Mountford, Christopher J. (Dr.)
Sent: 15 March 2023 20:35
To: Colin Faber; Mountford, Christopher J. (Dr.)
Cc: lustre-discuss
Subject: Re: [lustre-discuss] Repeated ZFS panics on MDT
The ZFS scrub
rds,
Christopher.
From: lustre-discuss on behalf of
Mountford, Christopher J. (Dr.) via lustre-discuss
Sent: 15 March 2023 19:21
To: Colin Faber
Cc: lustre-discuss
Subject: Re: [lustre-discuss] Repeated ZFS panics on MDT
***CAUTION:*** This email was s
small ssd based MDT).
Thanks,
Chris
From: Colin Faber
Sent: 15 March 2023 18:41
To: Mountford, Christopher J. (Dr.)
Cc: lustre-discuss
Subject: Re: [lustre-discuss] Repeated ZFS panics on MDT
***CAUTION:*** This email was sent from an EXTERNAL source. Think
Have you tried resilvering the pool?
On Wed, Mar 15, 2023, 11:57 AM Mountford, Christopher J. (Dr.) via
lustre-discuss wrote:
> I'm hoping someone offer some suggestions.
>
> We have a problem on our production Lustre/ZFS filesystem (CentOS 7, ZFS
> 0.7.13, Lustre 2.12.9), so far I've drawn a
I'm hoping someone offer some suggestions.
We have a problem on our production Lustre/ZFS filesystem (CentOS 7, ZFS
0.7.13, Lustre 2.12.9), so far I've drawn a blank trying to track down the
cause of this.
We see the following zfs panic message in the logs (in every case the
VERIFY3/panic