Seagate Medalist 2160N (ST52160N), Руководство по эксплуатации продукта

Страница: 118 / 138

tion before other retry mechanisms, but does not perform
T>1 corrections on-the-fly; any successful correction is
reported to the host as a recovered error.
The post error (PER) bit is not supported.
The disable transfer error (DTE) bit is not supported.
The
disable correction (DCR) bit is not supported.
Byte 3 The verify retry count field specifies the number of times the
target attempts its recovery algorithm during a verify opera-
tion. The verify retry count field has a range of 0 through
20
H
.
Byte 4 The verify correction span is the size of the largest read data
error, in bits, on which ECC correction is attempted. The
drive can correct up to 64 bits. Longer errors are reported
as nonrecoverable.
Byte 5–9 Reserved
Byte 10–11 The
verify recovery time limit field has a value of FFFF
H,
which means that recovery time is unlimited.
C.6 Caching page (08
H
)
The drive uses read look-ahead, read caching and write caching to
improve seek times and performance.
C.6.1 Read look-ahead and caching
The drive uses an algorithm that improves seek performance by reading
the next logical sectors after the last requested sector. These unre-
quested sectors are read into a buffer and are ready to be transmitted to
the host before they are requested. Because these sectors are read
before they are requested, access read time for the sectors is virtually
eliminated. This process is called read look-ahead.
Read Caching is any time data read for a command is available to be
sent to an initiator for a subsequent command.
The buffer used for read look-ahead and caching can be divided into
segments as shown in the following table. To change the number of
segments, use byte 13 of the Caching page, which is described in
Appendix C.6.3. on page 110. The default is one 128-Kbyte segment.
108 Medalist Pro 2160N/2160WC Product Manual, Rev. A