SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    Re: iSCSI:SCSI responses for iSCSI errors



    Ken,
    
    > imply the target waits for the entire Expected Data Transfer
    > Length worth to be transferred? 
    
    I don't believe so.  Target is expected to wait for the data in the pipe
    to drain (I believe this section is describing the fundamental behavior
    from the context of one outstanding R2T, section 8.4 spells out what
    ought to be done for multiple).  So, the target does not have to generate 
    a new R2T.
    
    The above behavior is to take care of the race condition where the
    initiator re-uses the same ITT (on receiving a response)  for a different 
    task on a different connection, when the stale data is still in the pipe.
    
    > Is it possible to just reject the original command PDU 
    
    If you meant the usage of Reject PDU, the answer is no - as section
    8.2 clearly calls out.  A response PDU must be returned for concluding
    an instantiated task.
    
    Hope that helps.
    --
    Mallikarjun
    
    Mallikarjun Chadalapaka
    Networked Storage Architecture
    Network Storage Solutions Organization
    Hewlett-Packard MS 5668 
    Roseville CA 95747
    
    ----- Original Message ----- 
    From: "Ken Sandars" <ksandars@eurologic.com>
    To: <ips@ece.cmu.edu>
    Sent: Wednesday, October 31, 2001 9:08 AM
    Subject: iSCSI:SCSI responses for iSCSI errors
    
    
    > Gidday all,
    > 
    > With reference to 3.4.2, when a target detects an error
    > does:
    > 
    > '...MUST wait until it receives a Data PDU with the F
    > bit set, in the last expected sequence, before sending the 
    > Response PDU' 
    > 
    > imply the target waits for the entire Expected Data Transfer
    > Length worth to be transferred? 
    > 
    > If so, the target may have to R2T for the solicited data! Should
    > it R2T with 'correct' values, regardless of what the initiator sent?
    > 
    > In this case it is possible that this clean-up action actually solicits
    > all the required data, however, the command is still going to get
    > a response with sense data indicating an abort.
    > 
    > Is it possible to just reject the original command PDU when validity 
    > checking picks up one of these errors? Any Data-Out PDUs
    > in the pipeline which belong to this rejected command can be silently
    > discarded by the target. What am I missing?
    > 
    > 
    > Thoughts?
    > 
    > Ken Sandars
    > ksandars@eurologic.com
    > Eurologic Systems
    > +44 117 930 9616
    > 
    > 
    
    


Home

Last updated: Thu Nov 01 01:17:31 2001
7488 messages in chronological order