SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    RE: iSCSI: DataACK SNACK


    • To: "Julian Satran" <Julian_Satran@il.ibm.com>
    • Subject: RE: iSCSI: DataACK SNACK
    • From: "Chuck Micalizzi" <chuck.micalizzi@qlogic.com>
    • Date: Mon, 18 Feb 2002 09:18:26 -0800
    • Cc: <ips@ece.cmu.edu>
    • content-class: urn:content-classes:message
    • Content-Type: multipart/alternative;boundary="----_=_NextPart_001_01C1B8A0.4684C40E"
    • Sender: owner-ips@ece.cmu.edu
    • Thread-Index: AcG2vuQgQQLUNiFiTr+IR4gBl4w91AB34+mA
    • Thread-Topic: iSCSI: DataACK SNACK

    Julian,
       
        I agree with your suggestion.
     
        Thank you for the prompt attention.
     
    chuck  
    -----Original Message-----
    From: Julian Satran [mailto:Julian_Satran@il.ibm.com]
    Sent: Friday, February 15, 2002 11:52 PM
    To: Chuck Micalizzi
    Cc: ips@ece.cmu.edu
    Subject: RE: iSCSI: DataACK SNACK


    Chuck,

    The Initiator Task Tag is thhe only reliable indicator the protocol provides today.
    If nobody shouts against it we might let the target provide a Target Transfer Task for Data-In PDUs that have the A bit set
    to be returned with the ACK for target convenience.

    Julo




    "Chuck Micalizzi" <chuck.micalizzi@qlogic.com>

    15-02-02 23:14

           
            To:        Julian Satran/Haifa/IBM@IBMIL
            cc:        <ips@ece.cmu.edu>
            Subject:        RE: iSCSI: DataACK SNACK

           


    Julian,
     
        Thank you for the response.
     
        Let me try to be  more direct. If a target has been issued multiple
        read commands, with transfer counts that exceed the negotiated
        maxBurstSize. After the target sends a data sequence for one of these
        commands must it wait for a DataACK before sending a data sequence
        for another command. Or is it free to send a data sequence for each outstanding
        command?
     
        If the target can have a data sequence in flight for each active command then
        it must expect a DataACK for each sequence sent with the Acknowledge
        bit set. If the DataACK SNACK doesn't include a task Tag the target can't be
        certain as to which data sequence the initiator is acknowledging.  So how can
        the target determine which resources to free or which sequence to send next?
     
    chuck
     
       
     
       
     
       
    -----Original Message-----
    From:
    Julian Satran [mailto:Julian_Satran@il.ibm.com]
    Sent:
    Friday, February 15, 2002 9:30 AM
    To:
    Chuck Micalizzi
    Cc:
    ips@ece.cmu.edu; owner-ips@ece.cmu.edu
    Subject:
    Re: iSCSI: DataACK SNACK


    DataACK is a "bulk ack". Answering the last (in case of several) is good enough.

    I fail to see your point.


    Julo


    "Chuck Micalizzi" <chuck.micalizzi@qlogic.com>
    Sent by: owner-ips@ece.cmu.edu

    14-02-02 21:02

           
           To:        <ips@ece.cmu.edu>

           cc:        

           Subject:        iSCSI: DataACK SNACK


         



    All,
     
      I have a question regarding DataACK.

      Rev. 10 section 10.16.1 states:

      For a Data/R2T SNACK, the Initiator Task Tag MUST be set
      to the Initiator Task Tag of the referenced Command.
      Otherwise, it is reserved.

      it also states:

      The DataACK is used to free resources at the target and
      not to request or imply data retransmission.

      Is the target allowed to have more than one DataACK
      outstanding on a connection?    

      If multiple outstanding DataACKs are allowed per connection
      then in my opinion the DataACK must have a valid task tag
      inorder for the target to associate the DataACK with the
      appropriate resources to be freed.
     

    chuck micalizzi
    Qlogic Corp.






Home

Last updated: Tue Feb 19 05:18:12 2002
8785 messages in chronological order