User guide

The purpose of fault tolerant configurations on the Smart Array 431 Controller
is to protect against data loss due to drive failure. Although the Smart Array
431 Controller firmware is designed to protect against normal drive failure, it
is imperative that the system operator perform the correct actions to recover
from a drive failure without inadvertently inducing any additional drive
failures. Multiple drive failures in the same array generally result in data loss
(exceptions include failures following activation of a spare drive, and failure
of drives in a mirroring configuration that are not mirrored to one another).
The system operator can recognize a drive failure in one of several ways:
■ Amber LED will be illuminated on failed drives in a hot-pluggable tray.
This, however, assumes the storage system is powered-on and the SCSI
cable is working. Note that the amber LED may be illuminated briefly
when a hot-pluggable drive is inserted; this is normal.
■ Amber LED will be illuminated on the front of a ProLiant Storage
System if failed drives are inside (other problems such as fan failure or
over-temperature conditions will also cause this LED to be illuminated).
■ A Power-On Self-Test (POST) message will list failed drives whenever
the system is restarted (assumes that one or more “good” drives are
detected by the controller). (See Appendix G for interpretation of POST
messages).
■ Array Diagnostics Utility (ADU) will list all failed drives.