[tcpm] Increasing Initial CWND and CWND setting after fast recovery

<Karen.Nielsen@tieto.com> Tue, 05 March 2013 13:19 UTC

Return-Path: <Karen.Nielsen@tieto.com>
X-Original-To: tcpm@ietfa.amsl.com
Delivered-To: tcpm@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 0B24221F8654 for <tcpm@ietfa.amsl.com>; Tue, 5 Mar 2013 05:19:19 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -6.598
X-Spam-Level:
X-Spam-Status: No, score=-6.598 tagged_above=-999 required=5 tests=[BAYES_00=-2.599, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_MED=-4]
Received: from mail.ietf.org ([12.22.58.30]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id d4JZsEZTbiUc for <tcpm@ietfa.amsl.com>; Tue, 5 Mar 2013 05:19:18 -0800 (PST)
Received: from ebb06.tieto.com (ebb06.tieto.com [131.207.168.38]) by ietfa.amsl.com (Postfix) with ESMTP id 9814021F8648 for <tcpm@ietf.org>; Tue, 5 Mar 2013 05:19:17 -0800 (PST)
X-AuditID: 83cfa826-b7f386d000004d8b-bb-5135f0d4d9c9
Received: from FIVLA-EXHUB02.eu.tieto.com ( [131.207.136.42]) by ebb06.tieto.com (SMTP Mailer) with SMTP id 08.A7.19851.4D0F5315; Tue, 5 Mar 2013 15:19:16 +0200 (EET)
Received: from EXMB03.eu.tieto.com ([169.254.1.113]) by FIVLA-EXHUB02.eu.tieto.com ([131.207.136.42]) with mapi; Tue, 5 Mar 2013 15:19:15 +0200
From: Karen.Nielsen@tieto.com
To: tcpm@ietf.org, mattmathis@google.com
Date: Tue, 05 Mar 2013 15:19:14 +0200
Thread-Topic: Increasing Initial CWND and CWND setting after fast recovery
Thread-Index: Ac4ZpAgD72VLHAdbTp6QJtZzmPAWEQ==
Message-ID: <CF340E42AED0874C81947E18863DE77B25F0230139@EXMB03.eu.tieto.com>
Accept-Language: en-US
Content-Language: en-US
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
acceptlanguage: en-US
Content-Type: multipart/alternative; boundary="_000_CF340E42AED0874C81947E18863DE77B25F0230139EXMB03eutieto_"
MIME-Version: 1.0
X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFlrKKsWRmVeSWpSXmKPExsXSfL5DS/fKB9NAg4Ndohbnz11itdh2cj6T A5PHgk2lHkuW/GQKYIrisklJzcksSy3St0vgynh4ey9TwVezivM77zI3MO436GLk5JAQMJF4 9ug2K4QtJnHh3nq2LkYuDiGBlYwSpyZMYIVwJjNKrHv2jRGkik1AXmLu3lXsILaIgI7EhF+9 YHEWARWJnT+OsoDYwgKuEqdfXWSFqPGS2NzQxwhh60lc+j4TrJdXwEfi+cnlTCA2I9Dm76fW gNnMAuISt57MZ4K4SEBiyZ7zzBC2qMTLx/9YIepFJe60r2eEqM+XOLvmOhPETEGJkzOfsExg FJqFZNQsJGWzkJRBxHUkFuz+xAZha0ssW/iaGcY+c+AxE7L4Akb2VYz8qUlJBmZ6JZmpJfl6 yfm5mxjBsbFCbQfjswdShxgFOBiVeHgjjpsECrEmlhVX5h5ilORgUhLlFXlkGijEl5SfUpmR WJwRX1Sak1p8iFGCg1lJhHf+e6Acb0piZVVqUT5MSpqDRUmc9+kcg0AhgfTEktTs1NSC1CKY rAwHh5IEb/U7oEbBotT01Iq0zJwShDQTByfIcB6g4XNBaniLCxJzizPTIfKnGBWlxHl3gyQE QBIZpXlwvbDU9YpRHOgVYd4WkCoeYNqD634FNJgJaLBHqAnI4JJEhJRUA6Nq7M47yTGPJswu /973XobRlWl+/7pdEfHcnxKflfS/DzZ7vS6J78LU1xkVr+0Y3duOTu2ZKd8jeuzZdJnUPY+c 5AymWLh1nVikKjrfv/H/PjVekana274L9e1v1F2ocL/2wb+JVXwXCiwj1Vr2TF4W5Xnn3/rd 5YuCDlptTjVSjL53qXZr9RMlluKMREMt5qLiRADRSOM/OAMAAA==
Subject: [tcpm] Increasing Initial CWND and CWND setting after fast recovery
X-BeenThere: tcpm@ietf.org
X-Mailman-Version: 2.1.12
Precedence: list
List-Id: TCP Maintenance and Minor Extensions Working Group <tcpm.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/tcpm>, <mailto:tcpm-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/tcpm>
List-Post: <mailto:tcpm@ietf.org>
List-Help: <mailto:tcpm-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/tcpm>, <mailto:tcpm-request@ietf.org?subject=subscribe>
X-List-Received-Date: Tue, 05 Mar 2013 13:19:19 -0000

Hi,

RFC5681 following RFC3390 increased the initial window of TCP to 4MTU/MSS, but left the loss window after Fast Recovery
by bounded only by 2MTU from below, by formula (4) of RFC5681. I.e., ssthress = MAX (flightsize/2, 2MSS)

SCTP, from RFC2960 to RFC4960, however led the increase of the IW from 2 MTU to 4 MTU by RFC3390 impact also the loss window after Fast Recovery,
by setting ssthresh= MAX(cwnd/2, 4MTU).
(This increase may have been partly unfounded (?), nevertheless it was done with this motivation, e.g. see RFC4460)

draft-ietf-tcmp-initcwnd-08.txt mentions that the increase of the IW does NOT apply to the loss window after retransmit timeout, but
it is otherwise silent about the window after Fast Recovery. For the sake of TCP alone, but also in light of the different paths taken by TCP and SCTP
after RFC3390, then I wonder if it would not be beneficiary to clarify that the proposed increase also does NOT apply for the loss window after Fast Recovery.

If, on the contrary, the proposed increase of the windows MAY apply also to the loss window after Fast Recovery, presumably with the
disclaimer that it must not increase the CWND as it is said for the restart window, then I would very much appreciate such clarification.

I hope that you can help clarify the issue.
Thanks.

BR, Karen Nielsen