Write Buffer question

Gerry.Houlder at seagate.com Gerry.Houlder at seagate.com
Fri Oct 27 13:43:58 PDT 2006


* From the T10 Reflector (t10 at t10.org), posted by:
* Gerry.Houlder at seagate.com
*
The boundary alignment normally checked by verifying the Buffer Offset
field. Since this is ignored for Echo Buffer option the target will assume
that zero is the intended value for this field. Zero is a "4 byte aligned"
value. The only way the target would notice a descrepancy is if the
Transfer Length was not a multiple of 4. Even this may not be seen as an
error since the standard doesn't require a multiple of 4 bytes have to be
sent. Typical usage is to use a 256 byte pattern on each command.
	     Kade Soprano						   
	     <kade.soprano at tex						   
	     memsys.com>						To 
	     Sent by:		       t10 at t10.org			   
	     owner-t10 at t10.org						cc 
	     No Phone Info						   
	     Available						   Subject 
	     10/27/2006 01:53						   
	     PM 							   
* From the T10 Reflector (t10 at t10.org), posted by:
* Kade Soprano <kade.soprano at texmemsys.com>
*
Sir/Madam,
I am writing in regards to a question that I have about the WRITE BUFFER
SCSI command.
In particular, my question pertains to the data sent from the
application client for the echo
buffer mode (0AH).
The specification (SPC-3) states that "Data shall be sent aligned on
four-byte boundaries."
Does this mean that the device server should check that the data is
aligned on four-byte
boundaries and terminate the command with a CHECK CONDITION status if
the data
isn't aligned properly, or, to be a little less harsh, properly align
[down] the data if it isn't?
This is what I gather from my reading of the specifications, but since
it's not explicitly
stated, I cannot be sure.
Thank you for your time.
Kade M. Soprano
*
* For T10 Reflector information, send a message with
* 'info t10' (no quotes) in the message body to majordomo at t10.org
*
* 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