Table of Contents
Advertisement
PRODUCT DESCRIPTION
Defect Management Zone (DMZ)
Each drive model has a fixed number of spare sectors per drive, all of which are located at the end of the drive. Upon
detection of a bad sector that has been reassigned, the next sequential sector is used.
For example, if sector 3 is flagged, data that would have been stored there is "pushed down" and recorded in sector 4.
Sector 4 then effectively becomes sector 3, as sequential sectors are "pushed down" across the entire drive. The first spare
sector makes up for the loss of sector 3, and so maintains the sequential order of data. This push down method assures
maximum performance.
On-the-Fly Hardware Error Correction Code (ECC)
10 bits, single burst, guaranteed
Software ECC Correction
64 bits, single burst, guaranteed; 28 bits, double bursts, guaranteed
Automatic Park and Lock Operation
Immediately following power down, dynamic braking of the spinning disks delays momentarily allowing the read/write
heads to move to an inner mechanical stop. A small fixed magnet holds the rotary actuator in place as the disk spins down.
The rotary actuator is released only when power is again applied.
Cache Management
Buffer Segmentation
The data buffer is organized into two segments: the data buffer and the micro controller scratch pad. The data buffer is
dynamically allocated for read and write data depending on the commands received. A variable number
of read and write buffers may exist at the same time.
Read-Ahead Mode
Normally, this mode is active. Following a read request, disk read-ahead begins on the first sector and continues
sequentially until the allocated buffer is full. If a read request is received during the read-ahead operation, the buffer is
examined to determine if the request is in the cache. If a cache hit occurs, read-ahead mode continues without
interruption and the host transfer begins immediately.
Automatic Write Reallocation (AWR)
This feature is part of the write cache and reduces the risk of data loss during deferred write operations. If a disk error
occurs during the disk write process, the disk task stops and the suspect sector is reallocated to a pool of alternate sectors
located at the end of the drive. Following reallocation, the disk write task continues until it is complete.
Write Cache Stacking
Normally, this mode is active. Write cache mode accepts the host write data into the buffer until the buffer is full or the
host transfer is complete. A command complete interrupt is generated at the end of the transfer.
A disk write task begins to store the host data to disk. Host write commands continue to be accepted and data transferred to
the buffer until either the write command stack is full or the data buffer is full. The drive may reorder write commands to
optimize drive throughput.
2 – 12
Advertisement
Table of Contents
