SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    Re: Multiple Connections. How would they work?



    
    
    The 00 draft (Adelaide) had the commands go down over one specific control
     stream while the data went on any available connection.
    Synchronizing them and providing for hardware implementation across several
    adapters was felt to be complex.
    
    However command ordering was trivial.
    
    The symmetric model in 01 requires ordering and this is why you have the
    command ordering.
    A proposal to get back to the asymmetric model but decide ahead of time (?
    when) what
    path data will be taking was forwarded by Kalman.
    
    We call this the asymmetric model (it can still evolve).
    
    I hope this helps.
    
    Regards,
    Julo
    
    Robert Snively <rsnively@Brocade.COM> on 06/09/2000 18:46:40
    
    Please respond to Robert Snively <rsnively@Brocade.COM>
    
    To:   ips@ece.cmu.edu
    cc:    (bcc: Julian Satran/Haifa/IBM)
    Subject:  Multiple Connections.  How would they work?
    
    
    
    
    What am I missing?  The reason I felt that iSCSI might possibly
    work was the text from 2.2.4 of draft-satran-iscsi-01.txt.
    
         " For SCSI commands that require data and/or parameter
         transfer, the (optional) data and the status for a
         command must be sent over the same TCP connection that
         was used to deliver the SCSI command (connection
              allegiance).  Thus if an initiator issues a READ
         command, the target must send the requested data followed
         by the status to the initiator over the same TCP connection
         that was used to deliver the SCSI command."
    
    >From this, I extrapolated that multiple connections and sessions
    were mechanisms to manage multiple paths, each of which would
    carry all the traffic related to a single command, probably with
    no ordering among them.  I had expected TCP/IP and iSCSI state
    required for execution of an iSCSI operation to be contained within
    a single NIC.
    
    How does this map into the multiple connection structures that are
    being discussed?
    
    How do the multiple connection structures map into the low cost highly
    efficient hardware assisted NIC implementations that presently typify
    SCSI implementations?
    
    
    
    


Home

Last updated: Tue Sep 04 01:07:28 2001
6315 messages in chronological order