Re: iSCSI: immediate data

[julian_satran@il.ibm.com]

Matt,

F is the end of the sequence. If you don't have immediate data but have
some unsolicited data PDU
the keep F at 0 until the last unsolicited PDU (presence or absence of
immediate is indicated by length).

If you have immediate but no other unsolicited or no immediate and no other
unsolicited F will be 1.

Julo

"Matt Wakeley" <matt_wakeley@agilent.com> on 09-05-2001 19:29:05

Please respond to Matt Wakeley <matt_wakeley@agilent.com>

To:   ips@ece.cmu.edu
cc:
Subject:  Re: iSCSI: immediate data




The way I interpret the question is, what if you negotiated immediate data,
but have no intention on sending immediate data for this command?  Is
setting
the F bit, without sending any immediate data valid? (once again, more
options....)

-Matt

julian_satran@il.ibm.com wrote:
>
> That is correct. The final bit indicates the end of unsolicited  data.
> If all you have is immediate then the final bit is 1in the command.
> If you have immediate and other unsolicited (if enabled!) then set F to
0.
>
> 2.3.1 has been fixed accordingly.
>
> Regards,
> Julo
>
> sandeepj@research.bell-labs.com (Sandeep Joshi) on 09-05-2001 01:56:25
>
> Please respond to sandeepj@research.bell-labs.com (Sandeep Joshi)
>
> To:   matt_wakeley@agilent.com
> cc:   ips@ece.cmu.edu
> Subject:  Re: iSCSI: immediate data
>
> Umm.....Julian replied to this one and said the final bit on ScsiCmd
> would indicate it.   Apparently, a single command can now send
> the unsolicited data both with the command and in separate PDUs.
>
> I cant seem to find the email but I believe Sec 2.3.1 was changed
> accordingly.  Julian..?
>
> -Sandeep
>
> > The intention is that if an initiator requests to send immediate data
> (and is
> > granted the request), then it will always send immediate data.
> >
> > It sounds like you are asking for wishy washy mode... sometimes send
> immediate
> > data, sometimes not.
> >
> > -Matt
> >
> > Sandeep Joshi wrote:
> > >
> > > Julian,
> > >
> > > I had a follow-up question on an old thread.
> > >   http://ips.pdl.cs.cmu.edu/mail/msg03373.html
> > >
> > > The initiator is allowed to send firstburst in immediate
> > > or in separate PDUs...but can it do neither ?  I dont
> > > see any statement to the effect that it MUST send a
> > > firstburst.
> > >
> > > Here's a possible problem :
> > > 1) FirstBurst is 4K
> > > 2) Expected data length of command is 16K
> > > 3) Initiator sends the Scsi command without immediate
> > >    data.   (final flag on Scsi command is not set)
> > >    And it decides to send no further data PDUs.
> > >
> > > The target does not know if R2Ts can be sent since it does
> > > not know if any unsolicited PDUs are expected.
> > >
> > > Perhaps the semantics on the final flag on SCSI command
> > > need to be changed to indicate that no unsolicited data
> > > will be sent with this command.  Currently, the flag implies
> > > (Sec 2.3.1) that all the required data has been sent with
> > > the command.
> > >
> > > And here's a typo to fix.  Appendix E (Key=immediateData)
> > > The following should say "initialR2T is no".
> > > The table has got it right.
> > >
> > > > If ImmediateData is set to yes and InitialR2T is set
> > > > to yes then the initiator MAY send unsolicited immediate
> > > > data or one unsolicited burst of Data-OUT PDUs but
> > > > MUST NOT send both immediate and a unsolicited burst of
> > > > Data-OUT PDUs for any one command.
> > >
> > > -Sandeep