On Fri, Apr 30, 2010 at 3:09 PM, Chris McEniry <[email protected]> wrote:
> Has anyone seen a SATA error of a device in a RAID1 md setup (+lvm on
> that) send a server off into the weeds?

I've seen a server completely fall over immediately after a SCSI
attached RAID array (RAID 6) spat out a few read errors on one of the
array's SATA disks.  The array itself thought that the drive was okay,
but the server load spiked to 450+, there were many processes stuck in
state D, and the server had to be hard power-cycled to bring it back
up.

I've had other drive failures in the same array, but in those cases
the SMART status on the drive showed failure and the system remained
relatively unaffected from a processing standpoint.

This probably doesn't help much with your issue, but it's a couple of
data points.

M
_______________________________________________
Tech mailing list
[email protected]
http://lopsa.org/cgi-bin/mailman/listinfo/tech
This list provided by the League of Professional System Administrators
 http://lopsa.org/

Reply via email to