WRITE DMA EXT failures with JM20330 based sata2ide

WRITE DMA EXT failures with JM20330 based sata2ide

[Manuel Reimer]

Hello,

I already posted this to the file-systems list, but as this might be the wrong 
list, I'm copying this request to here.

I've converted a 1,5TB SATA drive to IDE to run it on a UDMA100 IDE controller.

Low traffic applications work well. I'm able to create a xfs or ext4 filesystem 
and even a fsck runs without problems and without causing error messages on dmesg.

If I start to copy a file with some gigabytes in size to the new disc, then 
errors like the following keep coming on dmesg:

ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
ata2.00: failed command: WRITE DMA EXT
ata2.00: cmd 35/00:00:30:07:8a/00:04:57:00:00/e0 tag 0 dma 524288 out
          res 40/00:ff:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)
ata2.00: status: { DRDY }
ata2: link is slow to respond, please be patient (ready=0)
ata2: device not ready (errno=-16), forcing hardreset
ata2: soft resetting link
ata2.00: configured for UDMA/25
ata2.00: device reported invalid CHS sector 0
ata2: EH complete

The error repeats many times.

Copying a big file from this disc to another location on the disc, then this 
also works without errors (maybe because of the slow down of the mixed 
read/write access). This copy from disc to same disc also failed before I 
switched the disc to SATA I mode. This is done now, but doesn't seem to fix copy 
from another disc to the new one.

Interesting thing is that always WRITE DMA EXT seems to fail. Is there any way 
to fix this? Maybe it would be a option to increase the timeout, that gets 
triggered here, so the driver waits longer for the result?

What I definetly need is some workaround to stop the kernel from speeding down 
until UDMA/25 is reached. This speed is totally unacceptable for such a big 
drive... :-(

Are there configuration parameters that change how the driver behaves in such 
situations and how to set them to get around this problem?

Thank you very much in advance for any help...

Yours

Manuel

Re: WRITE DMA EXT failures with JM20330 based sata2ide

[Tejun Heo]

Hello,

On Mon, Jun 6, 2011 at 8:51 PM, Manuel Reimer
<Manuel.Spam@nurfuerspam.de> wrote:
> I've converted a 1,5TB SATA drive to IDE to run it on a UDMA100 IDE
> controller.

Hmmm...

> ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
> ata2.00: failed command: WRITE DMA EXT
> ata2.00: cmd 35/00:00:30:07:8a/00:04:57:00:00/e0 tag 0 dma 524288 out
>         res 40/00:ff:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)
> ata2.00: status: { DRDY }

Looks like genuine transmission problems.  Lengthening timeout won't
help anything.  It will just make it take longer to fail.

> What I definetly need is some workaround to stop the kernel from speeding
> down until UDMA/25 is reached. This speed is totally unacceptable for such a
> big drive... :-(

Currently, there's no way to disable automatic speed down without
patching the code and given that the mechanism works well for many
cases, I'm somewhat reluctant to introduce changes / switch solely for
this case.  You're having a genuine transmission problem and I think
fixing the underlying hardware issue would be the better choice than
mucking with EH behaviors.

Thank you.

-- 
tejun

Re: WRITE DMA EXT failures with JM20330 based sata2ide

[Tim Small]

On 09/06/11 15:31, Tejun Heo wrote:
> Hello,
>
> On Mon, Jun 6, 2011 at 8:51 PM, Manuel Reimer
> <Manuel.Spam@nurfuerspam.de> wrote:
>   
>> I've converted a 1,5TB SATA drive to IDE to run it on a UDMA100 IDE
>> controller.
>>     
> You're having a genuine transmission problem and I think
> fixing the underlying hardware issue would be the better choice than
> mucking with EH behaviors.
>   

FWIW, I've played with three different makes and models of SATA<->PATA
bridges at one time or another, and only one of them actually worked
reliably with hard drives - all seemed to be OK with optical drives, but
I assume that was down to their lower transmission speeds / throughput.

If you have any PCI or PCIe slots available, then you may be better off
buying a cheap add-in SATA controller instead (e.g. Silicon Image 3132,
or second-hand 3124, or Marvell 88SExxxx).

Cheers,

Tim.

-- 
South East Open Source Solutions Limited
Registered in England and Wales with company number 06134732.  
Registered Office: 2 Powell Gardens, Redhill, Surrey, RH1 1TQ
VAT number: 900 6633 53  http://seoss.co.uk/ +44-(0)1273-808309

WRITE DMA EXT failures with JM20330 based sata2ide

[Manuel Reimer]

Hello,

I've converted a 1,5TB SATA drive to IDE to run it on a UDMA100 IDE controller.

Low traffic applications work well. I'm able to create a xfs or ext4 filesystem 
and even a fsck runs without problems and without causing error messages on dmesg.

If I start to copy a file with some gigabytes in size to the new disc, then 
errors like the following keep coming on dmesg:

ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
ata2.00: failed command: WRITE DMA EXT
ata2.00: cmd 35/00:00:30:07:8a/00:04:57:00:00/e0 tag 0 dma 524288 out
          res 40/00:ff:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)
ata2.00: status: { DRDY }
ata2: link is slow to respond, please be patient (ready=0)
ata2: device not ready (errno=-16), forcing hardreset
ata2: soft resetting link
ata2.00: configured for UDMA/25
ata2.00: device reported invalid CHS sector 0
ata2: EH complete

The error repeats many times.

Copying a big file from this disc to another location on the disc, then this 
also works without errors (maybe because of the slow down of the mixed 
read/write access). This copy from disc to same disc also failed before I 
switched the disc to SATA I mode. This is done now, but doesn't seem to fix copy 
from another disc to the new one.

Interesting thing is that always WRITE DMA EXT seems to fail. Is there any way 
to fix this? Maybe it would be a option to increase the timeout, that gets 
triggered here, so the driver waits longer for the result?

What I definetly need is some workaround to stop the kernel from speeding down 
until UDMA/25 is reached. This speed is totally unacceptable for such a big 
drive... :-(

Are there configuration parameters that change how the driver behaves in such 
situations and how to set them to get around this problem?

Thank you very much in advance for any help...

Yours

Manuel