[tcpm] rfc2581bis [2]: limiting cwnd inflation

Mark Allman <mallman@icir.org> Tue, 13 February 2007 15:06 UTC

Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HGzF0-0001If-Ji; Tue, 13 Feb 2007 10:06:46 -0500
Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HGzEz-0001Hn-1l for tcpm@ietf.org; Tue, 13 Feb 2007 10:06:45 -0500
Received: from pork.icsi.berkeley.edu ([192.150.186.19]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HGzEv-0002IL-Ec for tcpm@ietf.org; Tue, 13 Feb 2007 10:06:45 -0500
Received: from guns.icir.org (adsl-69-222-35-58.dsl.bcvloh.ameritech.net [69.222.35.58]) by pork.ICSI.Berkeley.EDU (8.12.11.20060308/8.12.11) with ESMTP id l1DF6eiL009111 for <tcpm@ietf.org>; Tue, 13 Feb 2007 07:06:40 -0800
Received: from lawyers.icir.org (adsl-69-222-35-58.dsl.bcvloh.ameritech.net [69.222.35.58]) by guns.icir.org (Postfix) with ESMTP id 569107B0438 for <tcpm@ietf.org>; Tue, 13 Feb 2007 10:06:35 -0500 (EST)
Received: from lawyers.icir.org (localhost [127.0.0.1]) by lawyers.icir.org (Postfix) with ESMTP id D2A7A17ABD4 for <tcpm@ietf.org>; Tue, 13 Feb 2007 10:03:47 -0500 (EST)
To: tcpm@ietf.org
From: Mark Allman <mallman@icir.org>
Organization: ICSI Center for Internet Research (ICIR)
Song-of-the-Day: Whole Lotta Love
MIME-Version: 1.0
Date: Tue, 13 Feb 2007 10:03:47 -0500
Message-Id: <20070213150347.D2A7A17ABD4@lawyers.icir.org>
X-Spam-Score: 0.1 (/)
X-Scan-Signature: 3e15cc4fdc61d7bce84032741d11c8e5
Subject: [tcpm] rfc2581bis [2]: limiting cwnd inflation
X-BeenThere: tcpm@ietf.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: mallman@icir.org
List-Id: TCP Maintenance and Minor Extensions Working Group <tcpm.ietf.org>
List-Unsubscribe: <https://www1.ietf.org/mailman/listinfo/tcpm>, <mailto:tcpm-request@ietf.org?subject=unsubscribe>
List-Post: <mailto:tcpm@ietf.org>
List-Help: <mailto:tcpm-request@ietf.org?subject=help>
List-Subscribe: <https://www1.ietf.org/mailman/listinfo/tcpm>, <mailto:tcpm-request@ietf.org?subject=subscribe>
Content-Type: multipart/mixed; boundary="===============1749268911=="
Errors-To: tcpm-bounces@ietf.org

 
Reminder, the draft should pop out of the usual places soon, but until
then you can slurp a copy from:

    http://www.icir.org/mallman/papers/draft-ietf-tcpm-rfc2581bis-02.txt

The second issue ...

We added a note to step 4 of the fast retransmit/recovery procedure:

    4.  For each additional duplicate ACK received (after the third),
        cwnd MUST be incremented by SMSS.  This artificially inflates
        the congestion window in order to reflect the additional segment
        that has left the network.
    
        Note: [SCWA99] discusses a receiver-based attack whereby many
        bogus duplicate ACKs are sent to the data sender in order to
        artificially inflate cwnd and cause a higher than appropriate
        sending rate to be used.  A TCP MAY therefore limit the number
        of times cwnd is artificially inflated during loss recovery
        to the number of outstanding segments (or, an approximation
        thereof). 

That is, we explicitly allow a TCP to limit the number of dupacks that
are acceptable during fast recovery to prevent an attack such as
discussed in [SCWA99].

Note that (1) this is more conservative than the algorithm in 2581 and
so implicitly allowed already (that is, we are just calling attention to
this) and (2) we are not trying to mandate this behavior, just noting
that it might be useful.

Comments would be appreciated.

Thanks,
allman