Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 31 Jan 2009 13:21:56 +0100
From:      Christoph Mallon <christoph.mallon@gmx.de>
To:        Dylan Alex Simon <dylan@dylex.net>
Cc:        freebsd-current@FreeBSD.ORG
Subject:   Re: SATA DMA errors on second ICH10 bus
Message-ID:  <49844264.7000300@gmx.de>
In-Reply-To: <20090131010855.GA7991@datura.dylex.net>
References:  <8cb6106e0901200641x4b0bda9ag31e6f059f13035a7@mail.gmail.com>	<200901201829.n0KITE8V072323@lurza.secnetix.de> <20090131010855.GA7991@datura.dylex.net>

next in thread | previous in thread | raw e-mail | index | archive | help
Dylan Alex Simon schrieb:
>> That advice seems to be particularly valuable given the
>> current firmware problems that particular Seagate disks
>> are exhibiting.
> 
> I've confirmed with Seagate and others that the firmware these disks already
> have (CC1F) is not affected by the firmware problems.  The instability (as
> described in kern/130726) continues with a kernel from today.  I've traced it
> down to exclusively and reliably being caused by access to disks on multiple
> channels simultaneously (access to any pair of disks on the same channel works
> fine).  If anyone has any suggestions or any other data I should collect let
> me know as I will have to put these machines into production shortly (without
> freebsd unfortunately).

I suspect I see the same problem with some nvidia SATA controller. If 
there is high load on both channels of one controller, there are exactly 
the errors you showed.
Your kernel does not use INVARIANTS, is this correct? Otherwise you 
should see a very specific panic caused by a KASSERT(). I analysed the 
problem a bit. You can see my findings in the thread "Question about 
panic in brelse()".
I suspect a hardware bug plus incorrect error handling in the driver in 
FreeBSD. As a workaround, I suggest you connect each disk to a separate 
controller - if you have not more disks than controllers.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?49844264.7000300>