What is SMART?
If a failure is likely to
occur to hard drives, S.M.A.R.T. makes a status report available so that the
host can prompt the user to back up data on the failing drive. However, not
all failures can be predicted. S.M.A.R.T. predictability is limited to the attributes
the drive can monitor which are selected by the device manufacturer based on
the attribute’s ability to contribute to the prediction of degrading or
fault conditions. Although attributes are drive specific, a variety of typical
characteristics can be identified:
• head flying height
• data throughput performance
• spin-up time
• re-allocated sector count
• seek error rate
• seek time performance
• spin try recount
• drive calibration retry count
Implementations with SMART Technologies
SMART is supported on hard drives that comply with ANSI-SCSI Informational Exception
Control (IEC) document X3T10/94-190 standard.
Disable:
Disable S.M.A.R.T.-related functions
Detect Only:
S.M.A.R.T. function enabled, commands will be issued to enable all drives' S.M.A.R.T.
function, if a drive predicts a problem, the subsystem will report the problem
in the form of an event log.
Perpetual Clone:
S.M.A.R.T. function enabled, commands will be issued to enable all drives' S.M.A.R.T.
function. If a drive predicts a problem, controller will report in the form
of an event log. Controller will clone the drive if there is a Dedicated/Global
spare available. The drive with predicted errors will not be taken off-line,
and the clone drive will still behave as a standby drive.
If the drive with predicted errors fails, the clone drive will take over immediately.
Under the circumstance that the problematic drive is still working and another
drive in the same logical drive should fail, the clone drive will resume the
role of a standby spare and start to rebuild the failed drive immediately. This
is to prevent a fatal drive error if yet another drive should fail.
Clone + Replace:
Controller will enable all drives' S.M.A.R.T. function. If a drive predicts
a problem, controller will report in the form of event log. Controller will
then clone the problematic drive to a standby spare and take the problematic
drive off-line as soon as the cloning process is completed.