Comment 51 for bug 550559

If this is indeed a power issue, then why does it manifest now? These
two drives have been spinning in the same configuration for years,
never had any problems.

> Switching to a single 12V raile (max 50A) seems to have helped.
> Doesn't really make sense, drive has max 2A draw, but its hard to
> ignore the fact that it appears to make a difference...
What does make a difference mean, is it gone or appears less often? It
could be just coincidence, as it seems for me the problem is quite
erratic.

> Of course, only had these issues with seagate barracuda lp 2tb drives
> so far (only seagate drives I have); sata2 variant of the drives.
Other people here that don't have Seagates also have the problem, so
we should be careful not to make a premature assumption that this
problem has a causal relationship with Seagate drives. It could be
that Seagates are somehow more susceptible to the phenomenon, but it
looks like not limited to only Seagates.

> If you can rig it, try to run the drives off a diff psu and see if
> that works??? Definitely less than ideal....

I don't have a spare PSU lying around.

>
>
>
> On 2011-04-01, Vasco <email address hidden> wrote:
>>> Add to your boot params: libata.force=noncq
>>> It's not a guarantee to work, just helps quite a bit.
>> Reading the comments above I dont see this helping much.
>>
>>>
>>> Also are you running in any sort of RAID configuration?
>> Yes, I am. I have four disks attached to the controller; on each pair
>> of disks two partitions are in a RAID 1.
>>
>>> I found a new PSU
>>> helped a little as well, had very few incidents up until yesterday...
>> I dont see a reason to assume this is related to the PSU. This very
>> thread more or less proves this is a either a bug in linux kernel or
>> in firmware/hardware.
>>
>>> I still blame Seagate drives as being part of the problem.
>> I just checked and it turns out I do actually have two Seagate
>> Barracuda 7200.10 disks (I thought I had only Samsung). And it is
>> indeed one of those that is causing problems. This is interesting.
>>
>>>
>>> On Thu, Mar 31, 2011 at 14:36, Vasco <email address hidden> wrote:
>>>
>>>> I can confirm this bug as well. I also have a Gigabyte mainbord with the
>>>> SB700/800 chipset. I have no option to disable NCQ.
>>>>
>>>> System is running Ubuntu kernel 2.6.32-30-generic
>>>>
>>>> --
>>>> You received this bug notification because you are a direct subscriber
>>>> of the bug.
>>>> https://bugs.launchpad.net/bugs/550559
>>>>
>>>> Title:
>>>>  hdd problems, failed command: READ FPDMA QUEUED
>>>>
>>>> Status in Ubuntu:
>>>>  Confirmed
>>>>
>>>> Bug description:
>>>>  Hello!
>>>>
>>>>  I have a brand new computer. With a SSD device and a SATA hard drive,
>>>>  a Seagate Barracuda XT specifically 6Gb / s of 2TB. The latter is
>>>>  connected to a Marvell 9123 controller that I set AHCI mode in BIOS