Re: regarding bug #5914 - fs corruption on SATA

[Soeren Sonnenburg <kernel@nn7.de>]

On Thu, 2006-01-26 at 11:58 -0500, Jeff Garzik wrote:
> David Greaves wrote:
> > Have a look for subjects such as
> >   Problems with multiple Promise SATA150 TX4 cards
> 
> This is almost certainly either a power or PCI bus/slot issue.

So you mean the freeze I am observing when I copy files from the sata
disk to some
ieee1394 device (they are sharing interrupt 16)

 16:     430796   IO-APIC-level  ide2, ide3, libata, ohci1394

leading to lots of output as...

ata2: translated ATA stat/err 0x51/0c to SCSI SK/ASC/ASCQ 0xb/00/00
ata2: status=0x51 { DriveReady SeekComplete Error }
ata2: error=0x0c { DriveStatusError }

could be a cause of just that ?

> >   Possible libata/sata/Asus problem (was Re: Need to upgrade to latest
> > stable mdadm version?)
> 
> Highly likely to be a motherboard/BIOS issue related to properly tuning 
> and timing the hardware.
> 
> HOWEVER, libata can help (via Tejun's recent patches) by properly 
> handling the error when throw to us by hardware.

So it could help in the first case but also with this: I can freeze the
system bei hdparm -y /dev/sda ... will this patch also help in that
case ?

Soeren.
-- 
Sometimes, there's a moment as you're waking, when you become aware of
the real world around you, but you're still dreaming.