Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 13 Feb 2013 18:54:28 -0500 (EST)
From:      Rick Macklem <rmacklem@uoguelph.ca>
To:        "Marc G. Fournier" <scrappy@hub.org>
Cc:        Konstantin Belousov <kostikbel@gmail.com>, freebsd-stable@freebsd.org, Kostik Belousov <kib@freebsd.org>, John Baldwin <jhb@freebsd.org>
Subject:   Re: 9-STABLE -> NFS -> NetAPP:
Message-ID:  <426187631.3000937.1360799668107.JavaMail.root@erie.cs.uoguelph.ca>
In-Reply-To: <F4BD60BB-6F5F-4E67-BA6D-B4EBC5E3E5BE@hub.org>

next in thread | previous in thread | raw e-mail | index | archive | help
Marc Fournier wrote:
> On 2013-02-13, at 14:50 , Rick Macklem <rmacklem@uoguelph.ca> wrote:
>=20
> > He does get the odd error reported by nfs_getpages() and I don't
> > think we've isolated why yet. The error is 13 (EACCES), but jhb@
> > thought it might be because of the bug he fixed where the krpc
> > reported EACCES for the EINTR case. I don't think we've heard
> > back from Marc w.r.t. whether he has gotten any more of these
> > erros logged since applying jhb@'s patch and whether or not
> > the errno has changed to EINTR?
>=20
> As mentioned previously, it doesn't happen all that often =E2=80=A6 this
> latest one was after 21 days of uptime (or so) =E2=80=A6 I just upgraded =
the
> kernel on that machine to take into consideration changes to hfs
> *since* the last upgrade, so it might be another 20-30 days before it
> happens again *if* that last patch didn't' fix it =E2=80=A6
>=20
> I have several servers that do have fully operational remote consoles
> though =E2=80=A6 to save time if/when it happens next, what do I all need=
 to
> run?
>=20
> ps auxlH
> procstat -kk <pid> (for which process? =E2=80=A6 all part of that "group"=
, or
> just one of the apparently hung processes?)
The pid that is in "T" state for the "ps auxlH".

> sysctl debug.kdb.break_to_debugger=3D1 (shell)
> <ctl><alt><esc> (from console)
>=20
Then the commands described in:
http://www.freebsd.org/doc/en_US.ISO8859-1/book/developers-handbook/kerneld=
ebug-deadlocks.html
"show alllocks" and "show lockedvnods" may be the most useful, I think
you can also
"show sleepchain <pid>"
"show lockchain <pid>"
using the <pid> that is in "T" state.

If you haven't built your kernel with "options WITNESS", this won't work we=
ll.

> now, is there a way of forcing it to do a dump core so that I can run
> the various commands from a shell *after* its rebooted?
No idea. Someone familiar with what you can do to core dump and how to
get your system to make will have to answer this.

> Not
> particularly easy to redirect console output to a file (or is it?), so
> anything that scrolls off the screen is pretty much lost =E2=80=A6 I'm us=
ing a
> DRAC card in most cases, no serial consoles or anything like that that
> I can run within a script session =E2=80=A6 a 'ps' listing is >500 lines =
long,
> just to give an idea ...
>=20
>=20
> _______________________________________________
> freebsd-stable@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
> To unsubscribe, send any mail to
> "freebsd-stable-unsubscribe@freebsd.org"



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?426187631.3000937.1360799668107.JavaMail.root>