Legacy
Smart Disk Cloning |
S.M.A.R.T. Implementation
S.M.A.R.T. stands for Self-Monitoring, Analysis and Reporting Technology. It is a
technology that allow disk drives to predict near-term failure. Disk drives equipped with
S.M.A.R.T. will make a status report to the host if it detects degradation with
predetermined drive attributes. Not all failures are predictable. S.M.A.R.T.
predictability is limited to the attributes that the drive can monitor. Typically,
these include:
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
For SCSI drives, an industry standard specification is
used as defined in the ANSI-SCSI Informational Exception Control (IEC) document
X3T10/94-190. Normally, SCSI drives with S.M.A.R.T. capability communicate a reliability
condition as either good or failing. The specification provides for a sense bit to be
flagged if a reliability issue exists. The host may then alert the user.
Legacys Implementation
Legacy is using ANSI-SCSI Informational Exception Control (IEC) document X3T10/94-190
standard as well. There are four settings relating to S.M.A.R.T. function in the
firmware setup:
1. Disable - S.M.A.R.T. function not activated
2. Detect - S.M.A.R.T. function enabled. RAID Controller(s) will send command to
enable all the drives' S.M.A.R.T. function. If a drive detects a problem, the RAID
Controller(s) will send an event log.
3. Perpetual Clone - S.M.A.R.T. function enabled. RAID Controller(s) will send
command to enable all drives' S.M.A.R.T. function. If a drive detects a problem, the
Raid Controller(s) will send an event log. The Raid Controller(s) will clone the drive if
there is a hot-spare drive. The faulty drive will not be taken off-line, and the cloned
drive still continues to operate as a spare drive. In case the faulty drive stops working,
the spare drive will take over immediately. If the faulty drive continues to function and
another drive fails instead, the spare drive will become active data rebuild into it.
4. Clone + Replace - S.M.A.R.T. function enabled. RAID Controller(s)
will send command to enable all drives' S.M.A.R.T. function. If a drive detects a problem,
Raid Controller(s) will send an event log. The Raid Controller(s) will clone the
drive to the spare drive and take the failed drive off-line.
Legacy Disk Cloning Benefits
All RAID 5 Subsystems can only protect against a single
disk drive failure. Recovery from a failed disk is accomplished with the help of the
parity information stored on the remaining disks. During a single drive failure, not only
is there peformance loss from having to recalculate from parity for all read requests, the
entire system is at risk of a complete failure should a second disk fail before a rebuild
is completed.
The more disks there are within a RAID Subsystem, the more likelihood of a second disk
failure. For our example below, it's easy to see why a hot spare disk is commonly used as
another level of protection. Rather than waiting for a failed disk to be replaced and then
rebuilt, simply having a Hot Spare Disk within the RAID Subsystem can reduce the risk of a
second disk failure by 4 times!
|