Re: [tcmtf] Improvements in TCM-TF according to the received comments: Problem 2: Path MTU

"Jose Saldana" <> Tue, 18 February 2014 08:39 UTC

Return-Path: <>
Received: from localhost ( []) by (Postfix) with ESMTP id 66B961A0454; Tue, 18 Feb 2014 00:39:21 -0800 (PST)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -3.348
X-Spam-Status: No, score=-3.348 tagged_above=-999 required=5 tests=[BAYES_05=-0.5, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_MED=-2.3, RP_MATCHES_RCVD=-0.548, SPF_PASS=-0.001] autolearn=ham
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id yl7B1GXxxlL5; Tue, 18 Feb 2014 00:39:17 -0800 (PST)
Received: from ( []) by (Postfix) with ESMTP id CAE481A0388; Tue, 18 Feb 2014 00:39:16 -0800 (PST)
Received: from usuarioPC ( []) by (8.13.8/8.13.8/Debian-3) with ESMTP id s1I8cjCW011405; Tue, 18 Feb 2014 09:39:05 +0100
From: "Jose Saldana" <>
To: "'Luigi Iannone'" <>
References: <007b01cf226a$a41cc3a0$ec564ae0$> <>
In-Reply-To: <>
Date: Tue, 18 Feb 2014 09:38:53 +0100
Message-ID: <00ef01cf2c84$e6724f30$b356ed90$>
MIME-Version: 1.0
Content-Type: multipart/alternative; boundary="----=_NextPart_000_00F0_01CF2C8D.48383DD0"
X-Mailer: Microsoft Outlook 14.0
Thread-Index: AQKXehMp81FSHWhIgWYyoPZ5krjLqALVRsfymRJuFAA=
Content-Language: es
Subject: Re: [tcmtf] Improvements in TCM-TF according to the received comments: Problem 2: Path MTU
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: "Tunneling Compressed Multiplexed Traffic Flows \(TCMTF\) discussion list" <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Tue, 18 Feb 2014 08:39:21 -0000

In some research papers we have somewhat considered the problem of the MTU.
I mean, let' suppose you have a high number of flows to be optimized
together. Then, you define a period to multiplex them. But it may happen
that, before ending the period, you have enough small packets so as to fill
an MTU-sized multiplexed one. At that point, you should end that period,
send the packet and start a new period. If you include a size threshold in
addition to the period, the method is better.
However, perhaps this is just an implementation issue. Do you think we
should recommend this in the documents:
- know the maximum MTU
- use it in addition to the Period in order to trigger the sending of the
multiplexed packet.
De: Luigi Iannone [] 
Enviado el: lunes, 10 de febrero de 2014 16:40
Para: Jose Saldana
Asunto: Re: [tcmtf] Improvements in TCM-TF according to the received
comments: Problem 2: Path MTU
On 5 Feb. 2014, at 13:06 , Jose Saldana < <>> wrote:

Gorry: Perhaps we should also look at PMTU issues?
In TCMTF?  I would avoid that. MTU is a common problem for any tunnelling
mechanism I would more support a "tunnel-spefici-independent" solution
(probably to be discussed elsewhere).

Al: Yes. The operations considerations should be thought about.
Solution: (see this thread:
The current charter talks about MTU in number 7.
tcmtf mailing list