Definitely yes (acknowledging the status
is equivalent to acking all the data). In addition resources are help to
enable status retransmission even in commands that do not have data transfers.
Julo
| "Ken Craig" <kcraig <at> istor.com>
18/05/07 23:05
|
|
To
|
Julian Satran/Haifa/IBM <at> IBMIL
|
|
cc
|
<ips <at> ietf.org>
|
|
Subject
|
RE: [Ips] StatSN question |
|
Julian,
When you say "target may
discard whatever it may have
hold for the task" aren't
you saying the same thing as
Eddy. That the ExpStatSN
is an indication that the
Initiator has also received the
data since resources would
have been used for the data.
Thanks,
Ken Craig
-----Original Message-----
From: Julian Satran [mailto:Julian_Satran <at> il.ibm.com]
Sent: Friday, May 18, 2007 12:47 PM
To: Eddy Quicksall
Cc: ips <at> ietf.org; Ken Craig
Subject: Re: [Ips] StatSN question
ExpStatSN indicates to the target that the initiator has received the status
for the task and the target may discard whatever it may have hold for the
task.
It also indicates to to the target when it is safe to send the response
to a task abort or a "group" abort task management function.
Whether you can you use TCP ack for the same pupose dependes on how you
stack is layered and/or how your recovery from end-to-end errors is done.
Julo
| "Eddy Quicksall"
<Quicksall_iSCSI <at> Bellsouth.net>
18/05/07 08:03
|
|
To
|
"Ken Craig" <kcraig <at> istor.com>,
<ips <at> ietf.org>
|
|
cc
|
|
|
Subject
|
Re: [Ips] StatSN question |
|
It would mean the header and data has been received. The reason is because
the target can use ExpStatSN to free the resources used to send the Data-in.
At ERL 0 it is faster to just use the TCP ACK; for ERL > 0 I think there
was
argument given once that the TCP ACK may not really indicate that the data
was received and hence the ExpStatSN would be used for that purpose (I
don't
really remember that well though).
Eddy
----- Original Message -----
From: "Ken Craig" <kcraig <at> istor.com>
To: <ips <at> ietf.org>
Sent: Friday, April 27, 2007 5:23 PM
Subject: [Ips] StatSN question
I have a question about what ExpStatSN means that
I can't find an answer for in the reflector archives
or in any of the RFCs.
I, as an iSCSI Target running at ERL=0, send a
DATA IN PDU with FINAL=1 and a StatSN of 0. I
receive a SCSI CMD PDU with an ExpStatSN of 1.
Does this mean that the Initiator has received
the PDU BHS and all of the data or is it simply
an acknowledgement that it has received the PDU
BHS?
Thanks,
Ken Craig
_______________________________________________
Ips mailing list
Ips <at> ietf.org
https://www1.ietf.org/mailman/listinfo/ips
_______________________________________________
Ips mailing list
Ips <at> ietf.org
https://www1.ietf.org/mailman/listinfo/ips
RSS Feed