On 07/11/2010 12:47 AM, Mikael Abrahamsson wrote:
On Sun, 11 Jul 2010, Robert Hancock wrote:
Unfortunately that's a pretty generic timeout error that could be
caused by quite a few things, like a hardware issue, bad cable, etc.
as well as possible driver problem..
Oki, in my case I saw it with multiple drives (all WD though) and
multiple cables, but with just a single motherboard. The other people in
the threads I quoted seem to have worked around it by disabling NCQ. I
saw it on both channels on my motherboard as well, but I guess that
could be hardware issue. I don't really have any way of fault finding
this further as I have no lab machine, but it was fairly easy to
reproduce (letting mdadm hammer the drive with an array check made it
happen every time).
mdadm never kicked the drive, so whatever was going on was handled
gracefully, but of course any file access was stopped for 10+ seconds.
In a lot of cases with people having trouble when running multiple hard
drives in a machine - especially with simultaneous access situations,
like a RAID check/rebuild - the problem has been a power issue. It seems
that some hard drives can cause power draw spikes that some PSUs can't
handle, especially if multiple drives are connected to the some cable
from the power supply.
--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
