CentOS - Jun 2008 - Asus M3A78-EMH HDMI NCQ-issues

Hi all,

I'm sure this eventually will be resolved with a BIOS or kernel update, 
but in case someone experiences this on this or a similar motherboard, I 
thought I'd post a problem-and-workaround report.

Platform CentOS5, x86_64 kernel-2.6.18-53.1.21.el5
Motherboard Asus M3a78-EMH HDMI
SATA-controller configured as AHCI

Experienced symptom; Periodic, ~20s lockups/freezes, several a day, in 
conjunction with disk (SATA) I/O. Kernel logs something like this;

ata3.00: exception Emask 0x0 SAct 0x1 SErr 0x0 action 0x2 frozen
ata3.00: cmd 61/08:00:71:18:7d/00:00:02:00:00/40 tag 0 cdb 0x0 data 4096 out
          res 40/00:00:00:4f:c2/00:00:00:4f:c2/00 Emask 0x4 (timeout)
ata3: soft resetting port
ata3: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata3.00: configured for UDMA/133
ata3: EH complete
SCSI device sdc: 234441648 512-byte hdwr sectors (120034 MB)
sdc: Write Protect is off
sdc: Mode Sense: 00 3a 00 00
SCSI device sdc: drive cache: write back


(on a side note, the system has 6 SATA disks, the older ST3120827AS 
Seagate-disk here exhibits this significantly more often than the 
others, but they too are affected)

 From other sources this is reported as a AHCI NCQ bug.

My workaround, which was suggested somewhere else, was to disable NCQ;

(in rc.local)
for D in sd{a,b,c,d,e,f} ; do
   echo 1 > /sys/block/$a/device/queue_depth
done

This resolves the above issue, and from several times an hour, I have 
not experienced it since (~30h).

Yours,
-S
-- 
Simen Thoresen, Dolphin ICS
Systems Administration and Wulfkit Support

On Tue, Jun 3, 2008 at 9:42 AM, Simen Timian Thoresen
<simentt at dolphinics.no> wrote:
:
>
> (in rc.local)
> for D in sd{a,b,c,d,e,f} ; do
>  echo 1 > /sys/block/$a/device/queue_depth
> done
>
Did you mean $D instead of $a in the echo line of the loop?

mhr