Re: XFS shutting down due to IO timeout on SATA disk (pata_via for CX700)

[Mark Lord <liml@rtr.ca>]

Tejun Heo wrote:
>..
> Hmm.. most of FLUSH timeouts I've seen are either a dying drive or bad
> PSU.  There just isn't much which can go wrong from the driver side.
> IIRC, there was a problem when the unused part of TF is not cleared
> but that was the only one.
> 
>> Smartctl output is clean (no logged errors), and the drives themselves
>> are fine after a reboot -- necessary since libata/scsi kicked the drive out
>> of the RAID array.
>>
>> Something strange is going on here.
> 
> Any chance you can trick the client to hook up the drive to a separate PSU?
..

No, the failures happen randomly at customer sites, and only since they
"upgraded" to SLES10 with libata.  I think the PSUs are probably just fine.

Time to hack the drivers to give proper status on the timeouts, too;
otherwise we won't ever have any clue as to what is really happening.

Cheers