Date: Thu, 19 Mar 2009 18:02:51 +0200 From: Kostik Belousov <kostikbel@gmail.com> To: John Baldwin <jhb@freebsd.org> Cc: freebsd-stable@freebsd.org Subject: Re: in recent 7-STABLE: VOP_WRITE...is not exclusive locked but should be Message-ID: <20090319160251.GJ7716@deviant.kiev.zoral.com.ua> In-Reply-To: <200903191001.44491.jhb@freebsd.org> References: <alpine.LFD.2.00.0903190639450.9228@cardinal> <200903191001.44491.jhb@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--XigHxYirkHk2Kxsx
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Thu, Mar 19, 2009 at 10:01:44AM -0400, John Baldwin wrote:
> On Thursday 19 March 2009 8:05:34 am Tim Chase wrote:
> > Hello,
> >=20
> > I have a system that had been running quite well with an oldish 7-STABLE
> > (from around August 7, 2008) but has started deadlocking within the past
> > week or so.
> >=20
> > I updated the kernel to a newer 7-STABLE (Mar 15, 2009) and enabled
> > INVARIANTS, INVARIANT_SUPPORT, WITNESS, DEBUG_LOCKS DEBUG_VFS_LOCKS and
> > DIAGNOSTIC and the message indicated in the subject line has now appear=
ed
> > 3 times as shown below. Is this something to be terribly concerned abo=
ut?
> > Is there anything I can to to further track down the cause? Since the
> > system is a production mail server, I have it set to not drop into DDB
> > when this happens.
> >=20
> > The machine is a 4-core Xeon X5450 with 8G of RAM running FreeBSD
> > amd64 and in userland it's pretty much just cyrus imapd and apache/php.
> > The file systems are all ZFS on a bunch of SAS drives connected to a
> > LSI Logic 1068 controller.
> >=20
> > As to the deadlock that started this exercise, if the machine follows i=
ts
> > recent pattern, that should happen within the next 2-4 hours.
>=20
> Err, the vn_write() routine should be using an exclusive vnode lock:
>=20
> vn_write()
> {
>=20
> ...
> vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, td);
> if ((flags & FOF_OFFSET) =3D=3D 0)
> uio->uio_offset =3D fp->f_offset;
> ioflag |=3D sequential_heuristic(uio, fp);
> #ifdef MAC
> error =3D mac_check_vnode_write(active_cred, fp->f_cred, vp);
> if (error =3D=3D 0)
> #endif
> error =3D VOP_WRITE(vp, uio, ioflag, fp->f_cred);
> ...
> }
>=20
> Can you check your /sys/kern/vfs_vnops.c and verify that LK_EXCLUSIVE is=
=20
> present in your vn_write() routine? If so, then perhaps run memtest?
Note that this happens on the ZFS. Might be, ZFS unlocks the vnode and
then relocks it with some invalid flags ?
--XigHxYirkHk2Kxsx
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (FreeBSD)
iEYEARECAAYFAknCbKoACgkQC3+MBN1Mb4hjlgCaAp+sXu+hS5igKIyZar0Gl0oi
YOMAoNne2paSwO+3Yb2ul98wSxAbu6+q
=0vTG
-----END PGP SIGNATURE-----
--XigHxYirkHk2Kxsx--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20090319160251.GJ7716>