iSCSI Markers

["John Hufferd" <hufferd@us.ibm.com>]

I stand corrected on the Name, of TUFs and not iWARP.  The draft that will
probably go experimental (TUFs) is a framing item that places PDUs at the
beginning of TCP Segments (hence TCP Mods).  We can not just take TUFs and
add that to our iSCSI protocol since our charter prevents us from doing
that.

I see no relationship to COWS, except both have an 8 byte header.   If you
have TUFs, you do not need to have Word Stuffing.  The problem with COWS is
not is header it is the Word Stuffing and the Replacement Pointers.

You have FIM or COWS, neither one is useful with TUFs, except that they
have a similar header with COWS, not is hardly a reason to put up with the
SCANNING and Stuffing of COWS Pointers in the Data.  This is especially
since depending on the development approach you may find the Pointers
pointing the wrong way for either sending or receiving in some HW
pipelining designs.  And it is always a poorer approach then FIM in
Software.

I think folks want TUFs but we do not have that option now.  And COWS does
NOT bring that any closer any quicker.

.
.
.
John L. Hufferd
Senior Technical Staff Member (STSM)
IBM/SSG San Jose Ca
Main Office (408) 256-0403, Tie: 276-0403,  eFax: (408) 904-4688
Home Office (408) 997-6136, Cell: (408) 499-9702
Internet address: hufferd@us.ibm.com