SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


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

    RE: iSCSI: aborting an immediate command with ABORT TASK



    Tony,
    
    > > 1) The possible out-of-order arrival of an abort and the immediate
    command
    > > upon which it is supposed to act
    > > 2) The race between an immediate command finishing normally 
    > > (causing the target to free the command and forget its associated ITT)
    > >  and the initiator aborting it
    > > 3) The immediate command to be aborted may have been 
    > > discarded due to a header digest error
    > 
    > Replying to myself, #1 should actually not happen because of the
    requirement
    > for an ABORT TASK to be issued on the same connection to which the task
    > being acted upon is currently allegiant.  Points #2 and #3 are still valid
    > though.
    
    That's not correct.  In case 2) the ABORT TASK always succeeds no
    matter how the race turns out - SAM-2 Section 6.2 says:
    
    	If the logical unit supports this function, a response of
    	FUNCTION COMPLETE shall indicate that the task was aborted
    	or was not in the task set.
    
    The words "or was not in the task set" are the crucial ones.  In
    case 2), the ABORT TASK always returns FUNCTION COMPLETE, and there may
    or may not be a response from the aborted task prior to that FUNCTION
    COMPLETE, but there MUST NOT be one afterwards.
    
    The analysis for 3) is similar - if the command to be aborted was
    discarded due to a header digest error, the ABORT TASK still succeeds
    because the task "was not in the task set".
    
    > Another possibility is that the target is in the process of sending
    > a Reject PDU for the immediate command to be aborted when it receives the
    > ABORT TASK command, and the target implementation doesn't check the ITT
    from
    > a PDU that it has chosen to reject.
    
    Yet another similar analysis - the ABORT TASK succeeds whether it was
    received before or after the Reject PDU was sent.  Similar to the above,
    the Reject PDU MUST NOT follow the response to the ABORT TASK.
    
    Thanks,
    --David
    ---------------------------------------------------
    David L. Black, Senior Technologist
    EMC Corporation, 42 South St., Hopkinton, MA  01748
    +1 (508) 249-6449            FAX: +1 (508) 497-8018
    black_david@emc.com       Mobile: +1 (978) 394-7754
    ---------------------------------------------------
    


Home

Last updated: Wed Sep 04 09:18:52 2002
11755 messages in chronological order