Insight into soft lockup related to XFS?

[Galen Charlton]

Hi,

On Tue, Nov 25, 2014 at 11:27 AM, Brian Foster <bfoster at redhat.com> wrote:
> Do you reproduce this often or is this a one-off occurrence?

So far, just a one-off after a couple hundred days of uptime.

> FYI, the output below is line-wrapped and difficult to read. It's best
> to try and post log content so your mailer doesn't munge it (or also
> attach it unformatted so it's easier to parse).

Gah, sorry about that.

> Anyways, this looks like it could be the lock recursion problem fixed by
> the following commits:
>
> 5337fe9b xfs: recheck buffer pinned status after push trylock failure
> fa5566e4 xfs: remove log force from xfs_buf_trylock()
>
> ... which were introduced around v3.9. On a quick search, I don't see
> these commits in stable trees before that so the v3.10 stable tree would
> be the first where they are available.

Thanks!

Regards,

Galen
-- 
Galen Charlton
Manager of Implementation
Equinox Software, Inc. / The Open Source Experts
email:  gmc at esilibrary.com
direct: +1 770-709-5581
cell:   +1 404-984-4366
skype:  gmcharlt
web:    http://www.esilibrary.com/
Supporting Koha and Evergreen: http://koha-community.org &
http://evergreen-ils.org