Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 7 Dec 2012 12:15:36 +0000
From:      Matt Burke <mattblists@icritical.com>
To:        <freebsd-fs@freebsd.org>
Subject:   Re: ZFS hang
Message-ID:  <50C1DDE8.9030503@icritical.com>
In-Reply-To: <50C1CB34.3000308@icritical.com>
References:  <50C1CB34.3000308@icritical.com>

next in thread | previous in thread | raw e-mail | index | archive | help
After rebooting the box, I've just seen this on the console (after 'Setting
hostid'):

(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 53 8 0 1 0 0
(da8:isci0:0:0:0): CAM status: SCSI Status Error
(da8:isci0:0:0:0): SCSI status: Check Condition
(da8:isci0:0:0:0): SCSI sense: MEDIUM ERROR asc:ffffffff,ffffffff (Reserved
ASC/ASCQ pair)
(da8:isci0:0:0:0): Info: 0x4215378
(da8:isci0:0:0:0): Retrying command (per sense data)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 53 8 0 1 0 0
(da8:isci0:0:0:0): CAM status: SCSI Status Error
(da8:isci0:0:0:0): SCSI status: Check Condition
(da8:isci0:0:0:0): SCSI sense: MEDIUM ERROR asc:ffffffff,ffffffff (Reserved
ASC/ASCQ pair)
(da8:isci0:0:0:0): Info: 0x4215378
(da8:isci0:0:0:0): Retrying command (per sense data)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 53 8 0 1 0 0
(da8:isci0:0:0:0): CAM status: SCSI Status Error
(da8:isci0:0:0:0): SCSI status: Check Condition
(da8:isci0:0:0:0): SCSI sense: MEDIUM ERROR asc:ffffffff,ffffffff (Reserved
ASC/ASCQ pair)
(da8:isci0:0:0:0): Info: 0x4215378
(da8:isci0:0:0:0): Retrying command (per sense data)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 53 8 0 1 0 0
(da8:isci0:0:0:0): CAM status: SCSI Status Error
(da8:isci0:0:0:0): SCSI status: Check Condition
(da8:isci0:0:0:0): SCSI sense: MEDIUM ERROR asc:ffffffff,ffffffff (Reserved
ASC/ASCQ pair)
(da8:isci0:0:0:0): Info: 0x4215378
(da8:isci0:0:0:0): Retrying command (per sense data)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 53 8 0 1 0 0
(da8:isci0:0:0:0): CAM status: SCSI Status Error
(da8:isci0:0:0:0): SCSI status: Check Condition
(da8:isci0:0:0:0): SCSI sense: MEDIUM ERROR asc:ffffffff,ffffffff (Reserved
ASC/ASCQ pair)
(da8:isci0:0:0:0): Info: 0x4215378
(da8:isci0:0:0:0): Error 5, Retries exhausted

and then again for the following:

(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 65 8 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 75 8 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 21 76 8 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 82 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 83 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 84 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 94 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 95 58 0 1 0 0 (only 2 retries)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 9b 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 a4 58 0 1 0 0 (only 1 retry)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 a5 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 a6 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 b4 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 b5 58 0 1 0 0 (2 retries)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 b6 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 bc 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 c7 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 d7 58 0 1 0 0 (1 retry)
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 d8 58 0 1 0 0
(da8:isci0:0:0:0): READ(10). CDB: 28 0 4 1 e8 58 0 1 0 0

Obviously, the cause of my problems would seem to be a hosed disk. However
the kernel msgbuf shows no complaints from the drive before reboot.

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)

I can understand the drive failing, I just can't understand how it hung the
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.

I've also had these drives fail on the onboard SATA controller, along with
SAS drives on the SAS controllers, with no undesirable effects (other than
having to swap it out).

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 calls?

I'm going to move all these SSDs onto the SATA controller, and see if I can
replicate the problem, but I'm not holding my breath over a conclusive result.



-- 
Sorry for the below...

The information contained in this message is confidential and intended for the addressee only. If you have received this message in error, or there are any problems with its content, please contact the sender. 

iCritical is a trading name of Critical Software Ltd. Registered in England: 04909220.
Registered Office: IC2, Keele Science Park, Keele, Staffordshire, ST5 5NH.

This message has been scanned for security threats by iCritical. www.icritical.com




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?50C1DDE8.9030503>