Return-Path: <owner-ips@ece.cmu.edu>
X-Sieve: cmu-sieve 2.0
Return-Path: <owner-ips@ece.cmu.edu>
Received: (from majordom@localhost)
	by ece.cmu.edu (8.11.0/8.10.2) id h0NLgpK24617
	for ips-outgoing; Thu, 23 Jan 2003 16:42:51 -0500 (EST)
X-Authentication-Warning: ece.cmu.edu: majordom set sender to owner-ips@ece.cmu.edu using -f
Received: from nonamea.ptu.promise.com ([205.185.57.6])
	by ece.cmu.edu (8.11.0/8.10.2) with ESMTP id h0NLglW24607
	for <ips@ece.cmu.edu>; Thu, 23 Jan 2003 16:42:48 -0500 (EST)
Received: from venkat ([192.168.2.103]) by nonamea.ptu.promise.com with Microsoft SMTPSVC(5.0.2195.5329);
	 Thu, 23 Jan 2003 13:42:38 -0800
From: "Venkat Ramakrishnan" <venkatr@promise.com>
To: <pverma@marantinetworks.com>, <ips@ece.cmu.edu>
Subject: RE: Minimum PDU Size & CRC.
Date: Thu, 23 Jan 2003 13:42:38 -0800
Message-ID: <001001c2c328$59664d20$6702a8c0@ptu.promise.com>
MIME-Version: 1.0
Content-Type: text/plain;
	charset="US-ASCII"
Content-Transfer-Encoding: 7bit
X-Priority: 3 (Normal)
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook, Build 10.0.3416
In-Reply-To: <006101c2c31a$37081dc0$b6000a0a@maranti.com>
X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106
Importance: Normal
X-OriginalArrivalTime: 23 Jan 2003 21:42:38.0921 (UTC) FILETIME=[599AA390:01C2C328]
Sender: owner-ips@ece.cmu.edu
Precedence: bulk

Preetam,

What you are seeing may not be a iSCSI payload. It could be because your
TCP stack advertised a Window size of zero and the Initiator's TCP stack
is sending Window Probes with 1-byte Payload. Since, the Dst TCP port is
3260, your packet sniffer could be interpreting this as iSCSI Payload.
Most probably, the TCP acks from your TCP stack will have a Window size
of Zero for all this Window Probes.

Hope this helps!

-Venkat

-----Original Message-----
From: owner-ips@ece.cmu.edu [mailto:owner-ips@ece.cmu.edu] On Behalf Of
Preetam Verma
Sent: Thursday, January 23, 2003 12:01 PM
To: ips@ece.cmu.edu
Subject: Minimum PDU Size & CRC.

Eddy/Julo

I'm trying to reassemble ISCSI PDUs from data from a TCP offload engine.
During congestion, an initiator may send 1 byte in the TCP payload. I
wish
to know whether an initiator can send unpadded 1 byte in a TCP payload.
When
it comes to data intensive applications, people generally check/generate
CRC. I am not sure whether it's the application that needs to check
whether
the data received had proper CRC. I am talking from a hardware
perspective.

I'd greatly appreciate your help.

Regards

Preetam