kern/151648: [zfs] disk wait bug

[Pawel Jakub Dawidek]

On Sun, Oct 24, 2010 at 08:20:13AM +0000, Andriy Gapon wrote:
> The following reply was made to PR kern/151648; it has been noted by GNATS.
> 
> From: Andriy Gapon <avg at freebsd.org>
> To: Bartosz Nowicki <b.nowicki at admin.net.pl>
> Cc: bug-followup at freebsd.org
> Subject: Re: kern/151648: [zfs] disk wait bug
> Date: Sun, 24 Oct 2010 11:12:59 +0300
> 
>  -----BEGIN PGP SIGNED MESSAGE-----
>  Hash: SHA1
>  
>  on 23/10/2010 18:43 Bartosz Nowicki said the following:
>  > Dnia 23-10-2010 o 10:58:59 Andriy Gapon <avg at icyb.net.ua> napisał(a):
>  > 
>  >> Please provide procstat -kk -a output.
>  > 
>  > I would rather not reveal all processes (production OS, many user accounts), but
>  > discovered that it's not only when using nginx.
>  [snip]
>  > If it isn't enough I will send full output.
>  
>  I believe that the threads you showed so far are "secondary victims".
>  I think that there should be a primary victim that got stuck while holding some
>  locks and now other threads get stuck on those locks.

I agree. First we need to find what the thread which holds this vnode
lock is doing. The best way to do that is recompiling the kernel with
WITNESS and use DDB to figure this out.

-- 
Pawel Jakub Dawidek                       http://www.wheelsystems.com
pjd at FreeBSD.org                           http://www.FreeBSD.org
FreeBSD committer                         Am I Evil? Yes, I Am!
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 196 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/freebsd-fs/attachments/20101024/0dd522de/attachment.pgp