Comment on large DBI buffer model example
keiji_katata at post.pioneer.co.jp
keiji_katata at post.pioneer.co.jp
Sun Nov 3 19:02:07 PST 2002
* From the T10 Reflector (t10 at t10.org), posted by:
* keiji_katata at post.pioneer.co.jp
*
Hi all,
I got a comment that following example is not good for Large buffer model.
Large buffer model must cover entire discs and should not have any
possibility of overflow.
(strikethrough: "Device memory can store about 10% different packet start
address of entire disc and length of consecutive defective packets.")
In Fuji discussion, members agreed that there is no doubt that 10%
different packet start address and their length field can cause Sparing
Area overflow. Because these 10% packets DBIs are newly reported and are
not spared yet. So there is no difference for the result between bitmap
implementation and 10% list implementation.
Once Sparing Area overflow happens, system should terminate current writing
operation or may continue current writing operation with ignoring DBI
report.
So I think this example is acceptable.
Please send your opinion.
Best regards,
Keiji Katata
PIONEER CORP.
*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org
More information about the T10
mailing list