Dynamic Sector Repair; Ecc Protection; Battery-Backed Write Cache - HP 273914-B21 - Smart Array 6404/256 RAID Controller Technology Brief

If an active drive fails during system operation, the controller automatically begins rebuilding each
fault-tolerant logical drive onto the online spare; no administrator action is required. Once the rebuild
operation is complete, the system is fully fault-tolerant once again. The failed drive can be replaced at
a convenient time. Once an administrator installs a replacement drive, the controller will restore data
automatically from the failed drive to the new drive. At that point, the original online global spare, as
shown in Figure 6, will return to standby mode.
Figure 6. RAID 5 with an online spare drive
Smart Array Controller

Dynamic sector repair

Under normal operating conditions and over time, disk drive media can develop defects caused by
variances in the drive mechanisms. To protect data from media defects, HP built a dynamic sector
repair feature into Smart Array controllers.
During inactive periods, Smart Array controllers configured with a fault-tolerant logical drive perform
a background surface analysis, continually scanning all drives for media defects. During busy
periods, Smart Array controllers can also detect media defects when accessing a bad sector. If a
Smart Array controller finds a recoverable media defect, the controller automatically remaps the bad
sector to a reserve area on the disk drive. If the controller finds an unrecoverable media defect and a
fault-tolerant logical drive is configured, the controller automatically regenerates the data and writes it
to the remapped reserved area on the disk drive.

ECC protection

HP Smart Array cache modules use ECC technology to protect cache data. DRAM is accessed by
transferring read-or-write data 32 or 64 bits at time, depending on the type of cache module. The
ECC scheme generates 8 bits of check data for every 32 or 64 bits of regular data. This check data
can be used not only to detect data errors, but also to correct them. Data errors could originate inside
the DRAM chip or across the memory bus.

Battery-backed write cache

HP Smart Array controllers ensure that data is protected in a location isolated from server failures
before acknowledging that the data transfer has completed. The write-back cache allows the
controller to acknowledge transfer completion before the data is physically stored in the disk drive. To
improve disk write performance, data is temporarily stored in battery-backed write cache (BBWC),
which uses DRAM and is substantially quicker when compared to the disk drive.
Battery power is required for RAID controllers to perform operations such as write-back cache, array
expansion, logical drive extension, stripe size migration, and RAID migration.
User data
Parity data
Online spare
18