Re: Unkillable and runaway processes

From: Pawel Jakub Dawidek <pjd_at_FreeBSD.org>
Date: Thu, 13 Sep 2007 10:36:35 +0200
On Fri, Sep 07, 2007 at 08:31:09AM +0200, Kenneth Vestergaard Schmidt wrote:
> Pawel Jakub Dawidek <pjd_at_FreeBSD.org> writes:
> 
> > On Wed, Sep 05, 2007 at 05:25:09PM +0200, Kenneth Vestergaard Schmidt wrote:
> >> Pawel Jakub Dawidek <pjd_at_FreeBSD.org> writes:
> >> >> I could use some pointers on what to do - is there some way I can debug
> >> >> this better, maybe give some better info?
> >> >
> >> > Try disabling ZIL. This looks like a bug was already reported by Kris.
> >> > This was already reported to OpenSolaris.
> >> 
> >> We disabled ZIL, but the bug crept up again. I've just now rebooted the
> >> machine with DDB-support, so I can get some more info, per Kris's mail.
> 
> That would be Kip's mail.
> 
> >> The full state of the process hanging is 'zfs:(&tx->tx_quiesce_done_cv)'
> >>  - it cycles between RUN, CPUx and this one.
> >
> > Hmm, this means it didn't deadlock...
> 
> Here's some debugging output. PIDs 14870, 14933 and 12458 are just
> spinning and being useless. Funnily, all three have rename() in their
> backtrace.
> 
> db> ps
[...]
>   360     0     0     0  SL      zfs:(&tq 0xd151877c [zil_clean]
>   359     0     0     0  SL      zfs:(&tq 0xd1518848 [zil_clean]
[...]

Are you sure you disabled ZIL?

-- 
Pawel Jakub Dawidek                       http://www.wheel.pl
pjd_at_FreeBSD.org                           http://www.FreeBSD.org
FreeBSD committer                         Am I Evil? Yes, I Am!

Received on Thu Sep 13 2007 - 06:38:00 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:17 UTC