Re: iSCSI : Digest Error Problems & CmdSN/ExpCmdSN window issues

[Santosh Rao <santoshr@cup.hp.com>]

Julian,

My responses enclosed inline.

Regards,
Santosh

julian_satran@il.ibm.com wrote:

> 1) The initiator task tag cannot be trusted when a header digest error
> is seen. What does the phrase "provided it can recognize the initiator
> task tag" mean ?
> How can an initiator reliably claim that the initiator task tag is
> trustworthy ?
>
> <js> an initiator may choose to provide some redundancy in the tag itself
> </js>

All of these excessive "mays" only serve to complicate the standard and end up
as un-used features. They are better off removed.

>
> 2) The use of a "discard and re-start" policy can cause some  problems.
> The target is un-aware that the initiator has discarded the task and
> will then receive a 2nd command with the same Initiator Task Tag and
> CmdSN for a task already in progress, which can cause transmission of
> duplicate sets of data on the same I.T.T.
>
> Any policy of "discard and re-start" must be modified to "discard, abort
>
> and then, re-start, and the draft MUST specify connection allegiance of
> the command and its Abort Task".
>
> <js> a restart is recognized as such through the restart bit. Why would you
> require abort?

Where does the draft EXPLICITLY state that the "retry" bit implies an implicit
abort of the command followed by re-start ?

In the absence of such explicit clarifications, the draft is opening up
opportunities for numerous creative mis-interpretations.

Despite this, there is still a window b/n the command being re-started at the
initiator and the target receiving the command with "retry" bit set, when
stale frames continue to arrive at the initiator for that I.T.T. Therefore, in
order to avoid stale frames from the previous command continuing to arrive at
the initiator in this window, there needs to be an abort followed by a
re-start.

All of this complexity is only in the case of digest error handling [and not
in the case of connection failures]. The draft can be rid of all this
complexity if digest errors were to be recovered at a connection level,
instead of this "discard & restart" policy which adds all these complexities.

>
> please explain </js>
>
> 3) The policy of "discard and restart" is also subject some race
> conditions in the CmdSN sliding window. At the time the digest error was
>
> detected at the initiator, the ExpCmdSN may not yet have acknowledged
> that
> command. This causes the initiator to restart the command with the same
> Initiator Task Tag, CmdSN and "retry" bit set.
>
> However, by the time the command gets to the target, the target may have
>
> updated its ExpCmdSN window having sent a later PDU which updated the
> ExpCmdSN. This results in the target discarding the received CmdSN since
>
> <js> at command restart you never really rely on the CmdSN. you will want
> to check
> the Initiator Task Tag and accept it in the above case. </js>

The draft states the following on this subject :

Section 5.1
=========
-    the initiator will reissue all outstanding commands with their
      original Initiator Task Tag and their original CmdRN if they
      are not acknowledged yet or a CmdRN of 0 (not-numbered) if they
      were acknowledged; the retry (X) flag in the command PDU will
      be set

Section 1.2.2.1
===========
- The target MUST silently ignore any command
   outside this range or duplicates within the range not flagged with
   the retry bit (the X bit in the opcode).

This, to me, means :
- ignore all commands outside the (ExpCmdSN, MaxCmdSN) range.
- ignore all commands within the range that are not flagged with the retry
bit.

Can you please clarify the intent of the text ?


begin:vcard 
n:Rao;Santosh 
tel;work:408-447-3751
x-mozilla-html:FALSE
org:Hewlett Packard, Cupertino.;SISL
adr:;;19420, Homestead Road, M\S 43LN,	;Cupertino.;CA.;95014.;USA.
version:2.1
email;internet:santoshr@cup.hp.com
title:Software Design Engineer
x-mozilla-cpt:;21088
fn:Santosh Rao
end:vcard