SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


    [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

    RE: FCIP/iFCP : Guarantee In-Order delivery for FC N/NL_ports



    David,
    
    In the case of FCIP, a scheme for framing is not to allow buffering in user
    space as perhaps could be said for iSCSI.  The only option allowed would be
    to place the FC frame onto the FC media.  In this case, there is no
    confusion and you are right such scheme would be a violation of TCP.  In
    reality, reading the content of a TCP segment to move the data portion of
    the segment into user space is also not in keeping with TCP in the purist
    sense either.  If you are right about FCIP not allowed to "place" FC frames
    prior to the reception of a missing TCP segment, then there is absolutely no
    reason to have any type of framing for FCIP.  Everything will be required to
    be buffered anyway for as long as it takes.
    
    Doug
    
    > > The FC frame is placed on FC network within a short time of its
    > arrival or
    > > there is no advantage in allowing out of sequence processing.
    >
    > The "there is no advantage" statement depends on
    > the architecture of the implementation.  As usual,
    > Doug continues to confuse out of order placement
    > and processing - some FCIP implementations may be
    > able to take advantage of out of order placement;
    > out-of-order processing and forwarding would violate
    > TCP's in order delivery semantics and cause other
    > problems as described earlier in this thread.
    >
    > Some sort of timestamp approach from FCIP to FCIP
    > (i.e., across TCP transmission and delivery) seems
    > like a reasonable way to deal with issues that could
    > cause an issue with FC fabric timeouts.  It's also
    > the case that the FC fabric timeouts need to be set
    > with some regard to the presence and characteristics
    > of FCIP links.
    >
    > --David
    > ---------------------------------------------------
    > David L. Black, Senior Technologist
    > EMC Corporation, 42 South St., Hopkinton, MA  01748
    > +1 (508) 435-1000 x75140     FAX: +1 (508) 497-8500
    > black_david@emc.com       Mobile: +1 (978) 394-7754
    > ---------------------------------------------------
    >
    >
    
    


Home

Last updated: Tue Sep 04 01:05:45 2001
6315 messages in chronological order