SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    RE: iscsi: unsolicited data question



    Dennis,
     
    FirstBurstSize may be larger than MaxRecvPDUDataSize so InitialR2T=No can allow one to send more unsolicited data than immediate data alone. Also, an implementation may set ImmediateData=No because it prefers to handle command and data in separate PDUs but still accept unsolicited data by setting InitialR2T=No.
     
    Pat
     
     
    -----Original Message-----
    From: Dennis Young [mailto:dyoung@rhapsodynetworks.com]
    Sent: Wednesday, June 12, 2002 10:50 AM
    To: 'Julian Satran'
    Cc: ips@ece.cmu.edu; owner-ips@ece.cmu.edu
    Subject: RE: iscsi: unsolicited data question

    Are you saying that, for a session that has InitialR2T=No in effect, the initiator
    must send all its data as unsolicited first, up to the amount negotiated in
    FirstBurstSize, before it waits for a R2T from the target? 
     
    Can you shed some light on why we need unsolicited Data-out PDU when there 
    is ImmediateData, seems like they both serve the same purpose, having both of
    them only make the spec more complex.
     
    Thanks,
    -Dennis
     
     -----Original Message-----
    From: Julian Satran [mailto:Julian_Satran@il.ibm.com]
    Sent: Wednesday, June 12, 2002 10:19 AM
    To: Dennis Young
    Cc: ips@ece.cmu.edu; owner-ips@ece.cmu.edu
    Subject: RE: iscsi: unsolicited data question


    This is the reason why the initiator is required to send ALL unsolicited data (target can count on it and start sending R2Ts as soon as it sees the first header>
    Neither bandwidth nor latency are wasted.

    Julo


    Dennis Young <dyoung@rhapsodynetworks.com>

    06/12/2002 08:05 PM
    Please respond to Dennis Young

           
            To:        Julian Satran/Haifa/IBM@IBMIL
            cc:        ips@ece.cmu.edu, owner-ips@ece.cmu.edu
            Subject:        RE: iscsi: unsolicited data question

           


    Julian,
     
    This leads me to a more interesting question.
    A session with InitialR2T=No in effect, i.e. unsolicited Data-out
    allowed, could cause unintended waste of bandwidth, depending on
    how fast the target sends our R2T in response to the SCSI Write.
     
    If the target sees the unsolicited Data-out PDU before building the
    R2T, then everything is fine.
    If the target doesn't see the unsolicited Data-out PDU before building
    the R2T, the R2T would request the same portion of data in the
    unsolicited Data-out, thus bandwidth is wasted.
     
    The question is, how can a target be smart about this?
    Should the target wait a moment for the possible unsolicited Data-out
    after receiving each SCSI Write, this sounds kludgy.
     
    Also, why do we need the unsolicited Data-out PDU feature when
    there is ImmediateData?
     
    Regards,
    Dennis
     
    -----Original Message-----
    From:
    Julian Satran [mailto:Julian_Satran@il.ibm.com]
    Sent:
    Wednesday, June 12, 2002 6:05 AM
    To:
    Dennis Young
    Cc:
    ips@ece.cmu.edu; owner-ips@ece.cmu.edu
    Subject:
    Re: iscsi: unsolicited data question


    yes - julo


    Dennis Young <dyoung@rhapsodynetworks.com>
    Sent by: owner-ips@ece.cmu.edu

    06/12/2002 06:20 AM
    Please respond to Dennis Young

           
           To:        ips@ece.cmu.edu

           cc:        

           Subject:        iscsi: unsolicited data question


         



    I have a question which has been asked before, but I couldn't find a direct
    answer in the archive.  The table on page 200 of draft 12 doesn't directly
    answer this question either.

    The first paragraph on page 36 of draft 12 says "Targets operate in either
    solicitied (R2T) data mode or unsolicited (non R2T) data mode."
    tells me that a target, at all times during a data sequence transfer, can be

    one or the other, but not both (non R2T for the initial data out, R2T for
    the
    remaining data).  Is this correct?

    Thanks,
    Dennis

    ---snip from an old email dated 3/30/2001---

    " Hi Julian
    Sorry if I'm covering old ground... Is it possible to use unsolicited data
    for the first burst and then request any remaining data using R2T? For
    example, if the target has a previously allocated buffer available (length
    defined by FirstBurstSize) for unsolicited data, then once the initiator has
    sent unsolicited data up to and including this amount then the remaining
    data (if any) can be requested using R2T once the target has the buffer
    space available.
    ...Matthew Burbridge Hewlett Packard, Bristol Telnet: 312 7010 E-mail:
    matthewb@bri.hp.com "







Home

Last updated: Wed Jun 12 21:18:41 2002
10745 messages in chronological order