Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 7 Dec 2012 10:21:01 -0800
From:      Garrett Cooper <yanegomi@gmail.com>
To:        Fabian Keil <freebsd-listen@fabiankeil.de>
Cc:        "freebsd-fs@freebsd.org" <freebsd-fs@freebsd.org>
Subject:   Re: ZFS hang
Message-ID:  <79E03100-A019-4579-8762-50FBB82DD356@gmail.com>
In-Reply-To: <20121207172240.037306e1@fabiankeil.de>
References:  <50C1CB34.3000308@icritical.com> <50C1DDE8.9030503@icritical.com> <20121207172240.037306e1@fabiankeil.de>

next in thread | previous in thread | raw e-mail | index | archive | help
On Dec 7, 2012, at 8:22 AM, Fabian Keil <freebsd-listen@fabiankeil.de> wrote=
:

> Matt Burke <mattblists@icritical.com> wrote:
>=20
>> Obviously, the cause of my problems would seem to be a hosed disk. Howeve=
r
>> the kernel msgbuf shows no complaints from the drive before reboot.
>>=20
>> da8 is a 60GB OCZ Agility 3 SSD (purchased prior to realising just how
>> unreliable they are). According to the SMART data, it's had just 146GB of=

>> reads and 278GB writes over 3 power cycles with only 3 months power on
>> time, similar to the others that have failed (~60% failure rate for ours)=

>>=20
>> I can understand the drive failing, I just can't understand how it hung t=
he
>> system. I have had a similar thing happen on one of these machines before=

>> (with GENERIC and no dumpdev, so no debugging) with one of these disks on=

>> an Areca HBA.
>=20
> In CURRENT, parts of the cam layer can silently hang under certain
> circumstances and this can negatively affect various other subsystems
> including ZFS:
> http://lists.freebsd.org/pipermail/freebsd-current/2012-October/037413.htm=
l
>=20
> I suppose this regression is old enough to have trickled down
> to the stable branches by now.
>=20
> I'm not saying that this is definitively the problem you are
> seeing, but I think it would explain the symptoms.
>=20
>> Could there be a problem with ATA devices on SCSI controllers which is
>> causing failures to be silently dropped? Is ZFS lacking a timeout on IO c=
alls?
>=20
> I believe ZFS is designed with the expectation that timeouts are
> handled by the layers below it, so technically it doesn't "lack"
> the timeouts for IO calls ...

I've noticed hangs on reboot as well recently (in the last 2-3 months) with m=
y ata single disk pools and my mfi pool. All storage disks seem healthy... T=
he pools were running v28 with the zfs features upgrade.

Thanks,
-Garrett=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?79E03100-A019-4579-8762-50FBB82DD356>