SATA READ_DMA timeouts - SOLVED?

[Jeremy Chadwick]

(I'm not subscribed to freebsd-questions, so please CC me on replies.
I'm also not sure how I ended up getting this mail in the first place;
it looks like someone BCC'd my koitsu at freebsd.org address).

Reid,

The Wikipedia article you refer to documents a very well-known topic:
the SATA150-limiting jumpers on hard disks.  Drive vendors have this
jumper enabled (capped) by default due to incompatibilities with certain
chipsets (VIA, SiS, and nVidia -- who isn't mentioned).

The jumper in question is available on Western Digital and Seagate
disks; I have not checked to see if Maxtor, Samsung, or Fujitsu disks
offer this capability.

Maxtor disks also have further incompatibilities with nVidia chipsets,
specifically with regards to broken NCQ support (the disk will literally
lock up/hang, causing Windows or other operating systems to blue screen
or crash).  A disk firmware update from Maxtor is available to fix this
problem, but you have to go through Tier 1 support hell to get the
patch.  Additionally, the patch does not increment/change the f/w
version string, so there's no way to tell if your drive already has
the patch or not.  (I do have the patch laying around, but I can't
remember which models of Maxtor disk it affects.)

Furthermore, one of the most common reports on the FreeBSD lists is the
exact opposite -- users complaining that "their disks are SATA300 but
only operate at SATA150" (caused by that jumper).  Users are told to
remove the jumper, and are reminded that the reason the jumper is
enabled by default is said chipset incompatibilities.

That said, your mail confuses me for one reason:

Were you receiving DMA errors with the jumper REMOVED (e.g. SATA300
operation), or with the jumper ENABLED (SATA150 operation)?  Your below
description does not state what exactly you did with the jumper to make
your drives work reliably, only "that the jumper capability on your
disks was available".

-- 
| Jeremy Chadwick                                jdc at parodius.com |
| Parodius Networking                       http://www.parodius.com/ |
| UNIX Systems Administrator                  Mountain View, CA, USA |
| Making life hard for others since 1977.              PGP: 4BD6C0CB |

On Mon, Sep 29, 2008 at 04:19:22PM -0500, Reid Linnemann wrote:
> I've seen a number of people having DMA troubles with SATA disks on  
> FreeBSD6 and FreeBSD7, and I'm in the same boat. A while back I posted  
> looking for help but none could really be found. Today I finally got to  
> the bottom of things (at least so far).
>
> Hardware incompatibility.
>
> According to  
> http://en.wikipedia.org/wiki/SATA#SATA_1.5_Gbit.2Fs_and_SATA_3_Gbit.2Fs  
> there is an upward compatibility problem between a number of VIA and SiS  
> chipsets and SATA300 disks. I happen to have one of those controllers  
> (SiS964) and a pair of WD1600AAJS disks, which are SATA300 disks.
>
> I ripped apart my machine, and sure enough I had a jumper on each disk  
> labelled 'OPT1', which is documented to force SATA150 operation.
>
> I've since cold booted, warm booted, and booted after a power  
> interruption with no READ_DMA timeouts on these disks. I think this  
> solved the problem in my case.