Seagate ST936751FC Manuale Utente

Pagina di 84
38
Savvio 15K.1 FC Product Manual, Rev. B
The drive firmware error recovery algorithms consists of 11 levels for read recoveries and five levels for write. 
Each level may consist of multiple steps, where a step is defined as a recovery function involving a single re-
read or re-write attempt. The maximum level used by the drive in LBA recovery is determined by the read and 
write retry counts.
Table 4 equates the read and write retry count with the maximum possible recovery time for read and write 
recovery of individual LBAs. The times given do not include time taken to perform reallocations. Reallocations 
are performed when the ARRE bit (for reads) or AWRE bit (for writes) is one, the RC bit is zero, and the recov-
ery time limit for the command has not yet been met. Time needed to perform reallocation is not counted 
against the recovery time limit.
When the RC bit is one, reallocations are disabled even if the ARRE or AWRE bits are one. The drive will still 
perform data recovery actions within the limits defined by the Read Retry Count, Write Retry Count, and 
Recovery Time Limit parameters. However, the drive does not report any unrecovered errors.
[1]
Setting these retry counts to a value below the default setting could result in degradation of the unrecov-
ered error rate. For example, suppose the read/write recovery page has the RC bit = 0, the read retry 
count set to 4, and the recovery time limit set to 450. A 4-block read command can take up to 401 msec 
recovery time for each block and a maximum of 450 msec recovery for all four blocks. If either of these 
limits is reached and a block has not yet been recovered, the command will end with Check Condition sta-
tus and an unrecoverable read error will be reported.
7.3
FC-AL system errors
Information on the reporting of operational errors or faults across the interface is given in the Fibre Channel 
Interface Manual
. The FCP 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 Fibre Channel 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.
Table 4:
Read and write retry count maximum recovery times
Read retry count
Maximum recovery time per 
LBA (cumulative, msec)
Write retry count
Maximum recovery time per 
LBA (cumulative, msec)
0
51.87
0
23.94
1
59.85
1
35.91
2
203.49
2
55.86
3
219.45
3
67.83
4
253.11
4
119.79
5
279.35
5 (default)
147.72
6
311.27
7
395.12
8
463.12
9
495.04
10
530.95
11 (default)
1,282.97