Seagate ST300MX0064 - 512E ユーザーズマニュアル

S

EAGATE 

E

NTERPRISE 

P

ERFORMANCE 

15K HDD 

AND 

E

NTERPRISE 

T

URBO 

SSHD SAS P

RODUCT 

M

ANUAL

, R

EV

. B

 

 40

  

* For read retry count, every tick ~ 5% of total error recovery. Valid range setting is 1-20.

                     e.g. 1 ~ 5%

                            5 ~ 25%

                           20 ~ 100%

Setting these retry counts to a value below the default setting could result in degradation of the unrecovered error rate. For example, 

suppose the read/write recovery page has the RC bit = 0 and if the read retry count is set to 5, this means ~ 25% of error reco very will be 

executed which consumes 621.62 ms (please refer to the table above). If the limit is reached and a LBA has not yet been recover ed (i.e. 

requires retries beyond 621.62 ms), the command will end with Check Condition status report and unrecoverable read error will be 

reported.

Information on the reporting of operational errors or faults across the interface is given in the  SAS Interface Manual. The SSP Response 

returns information to the host about numerous kinds of errors or faults. The Receive Diagnostic Results reports the results of  diagnostic 

operations performed by the drive.

Status returned by the drive to the initiator is described in the SAS Interface Manual. Status reporting plays a role in systems error 

management and its use in that respect is described in sections where the various commands are discussed.

Background Media Scan (BMS) is a self-initiated media scan. BMS is defined in the T10 document SPC-4 available from the T10 

committee. BMS performs sequential reads across the entire pack of the media while the drive is idle. In RAID arrays, BMS allows hot 

spare drives to be scanned for defects prior to being put into service by the host system. On regular duty drives, if the host system makes 

use of the BMS Log Page, it can avoid placing data in suspect locations on the media. Unreadable and recovered error sites will be logged 

or reallocated per ARRE/AWRE settings.

With BMS, the host system can consume less power and system overhead by only checking BMS status and results rather than tying  up 

the bus and consuming power in the process of host-initiated media scanning activity.

Since the background scan functions are only done during idle periods, BMS causes a negligible impact to system performance. Th e first 

BMS scan for a newly manufactured drive is performed as quickly as possible to verify the media and protect data by setting the “Start time 

after idle” to 5ms, all subsequent scans begin after 500ms of idle time. Other features that normally use idle time to function  will function 

normally because BMS functions for time limited bursts then suspends activity to allow other background functions to operate.

BMS interrupts immediately to service host commands from the interface bus while performing reads. BMS will complete any BMS-initiated 

error recovery prior to returning to service host-initiated commands. Overhead associated with a return to host-servicing activity from BMS 

only impacts the first command that interrupted BMS, this results in a typical delay of about 1ms.

Deferred Auto-Reallocation (DAR) simplifies reallocation algorithms at the system level by allowing the drive to reallocate unreadable 

locations on a subsequent write command. Sites are marked for DAR during read operations performed by the drive. When a write 

command is received for an LBA marked for DAR, the auto-reallocation process is invoked and attempts to rewrite the data to the original 

location. If a verification of this rewrite fails, the sector is re-mapped to a spare location.

This is in contrast to the syst em having to use the Reassign  Command to reassign a location  that was unreadable and then genera te a 

write command to rewrite the data. DAR is most effective when AWRE and ARRE are enabled—this is the default setting from the Seagate 

factory. With AWRE and ARRE disabled DAR is unable to reallocate the failing location and will report an error sense code indicating that 

a write command is being attempted to a previously failing location.

Maximum recovery time per LBA 

(cumulative, ms)

0

36

1

124

1

54

5

403

2

80

10

730

3

98

15

1065

4

176

20 (default)

1538

5 (default)

422