On Tue, 17 Jul 2012, Roberto Scudeller wrote:
Thanks for the answers.
How do I test your theory?
I would use 'dd' to see if it is possible to transfer data from one of
the problem devices. Gain physical access to the system and check the
signal and power cables to these devices closely.
Use 'iostat -xe' to see what error counts have accumulated. Also
In this case, I use common disks SATA 2, not Nearline SAS (NL SATA) or SAS. Do
you think the disks SATA are the problem?
There have been reports of congestion leading to timeouts and resets
when SATA disks are on expanders. There have also been reports that
one failing disk can cause problems when on expanders. Regardless, if
this system has been previously operating fine for some time, these
errors would indicate a change in the hardware shared by all these
GraphicsMagick Maintainer, http://www.GraphicsMagick.org/
zfs-discuss mailing list