elstar.com.au

I have an Intel Modular server with firmware version: 2.7.100.20090226.16239
and today all the 11 Hard Disks in the chassis have shutdown.
from 7:25am Drive 1 was marked Dead, followed then Drive 2, then Drive 3, etc and by 7:26am the last Drive 11 was marked Dead.

The fix was to remove power to the server. Then when power was applied and the the server hard disks functioned normally and the server was operational again.

The cause is unknown, however the server room air conditioning was not working and the fans on the server were running at maximum.

I have since updated the Firmware to Version: 5.0.100.20090928.19055

Four months later this Intel SCM controller died completely. Luckily I had purchased a spare SCM and installed this to get the server running again. Intel have replaced the failed SCM under warranty.

When the replacement SCM was received, I updated the drivers on the Intel Modular Server and the compute modules to latest versions from the intel.com web site, and then added the 2nd SCM module. The unit now is using both modules automatically and in theory if one fails the system will keep running on the other SCM.