Some Linux SCTP code that someone could build upon...
Michael Welzl <michawe@ifi.uio.no> Tue, 27 March 2012 20:52 UTC
Return-Path: <michawe@ifi.uio.no>
X-Original-To: tsvwg@ietfa.amsl.com
Delivered-To: tsvwg@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id C382E21F85C2 for <tsvwg@ietfa.amsl.com>; Tue, 27 Mar 2012 13:52:00 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -102.524
X-Spam-Level:
X-Spam-Status: No, score=-102.524 tagged_above=-999 required=5 tests=[AWL=0.075, BAYES_00=-2.599, USER_IN_WHITELIST=-100]
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 agfgN+vw4FNy for <tsvwg@ietfa.amsl.com>; Tue, 27 Mar 2012 13:51:59 -0700 (PDT)
Received: from mail-out1.uio.no (mail-out1.uio.no [IPv6:2001:700:100:10::57]) by ietfa.amsl.com (Postfix) with ESMTP id A44FC21F85A1 for <tsvwg@ietf.org>; Tue, 27 Mar 2012 13:51:59 -0700 (PDT)
Received: from mail-mx2.uio.no ([129.240.10.30]) by mail-out1.uio.no with esmtp (Exim 4.75) (envelope-from <michawe@ifi.uio.no>) id 1SCdN0-0000vt-C1 for tsvwg@ietf.org; Tue, 27 Mar 2012 22:51:58 +0200
Received: from dhcp-4123.meeting.ietf.org ([130.129.65.35]) by mail-mx2.uio.no with esmtpsa (TLSv1:AES128-SHA:128) user michawe (Exim 4.76) (envelope-from <michawe@ifi.uio.no>) id 1SCdMz-0003G6-QY for tsvwg@ietf.org; Tue, 27 Mar 2012 22:51:58 +0200
Message-Id: <B4FD29F7-E932-42FD-B196-D72C9CBCD569@ifi.uio.no>
From: Michael Welzl <michawe@ifi.uio.no>
To: tsvwg WG <tsvwg@ietf.org>
Content-Type: text/plain; charset="US-ASCII"; format="flowed"; delsp="yes"
Content-Transfer-Encoding: 7bit
Mime-Version: 1.0 (Apple Message framework v936)
Subject: Some Linux SCTP code that someone could build upon...
Date: Tue, 27 Mar 2012 22:51:56 +0200
X-Mailer: Apple Mail (2.936)
X-UiO-Ratelimit-Test: rcpts/h 5 msgs/h 5 sum rcpts/h 7 sum msgs/h 7 total rcpts 18804 max rcpts/h 45 ratelimit 0
X-UiO-Spam-info: not spam, SpamAssassin (score=-5.0, required=5.0, autolearn=disabled, UIO_MAIL_IS_INTERNAL=-5, uiobl=NO, uiouri=NO)
X-UiO-Scanned: E841D86345C0D58148061919635D3CE8092F921F
X-UiO-SPAM-Test: remote_host: 130.129.65.35 spam_score: -49 maxlevel 80 minaction 2 bait 0 mail/h: 5 total 14 max/h 5 blacklist 0 greylist 0 ratelimit 0
X-BeenThere: tsvwg@ietf.org
X-Mailman-Version: 2.1.12
Precedence: list
List-Id: Transport Area Working Group <tsvwg.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/tsvwg>, <mailto:tsvwg-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/tsvwg>
List-Post: <mailto:tsvwg@ietf.org>
List-Help: <mailto:tsvwg-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/tsvwg>, <mailto:tsvwg-request@ietf.org?subject=subscribe>
X-List-Received-Date: Tue, 27 Mar 2012 20:52:00 -0000
Hi! About a year ago, I finished a small project with Morten Hustveit, funded by the nl.net foundation. In this project, Morten addressed two major things that often contributed to making Linux SCTP work much worse than TCP (at that time): the lack of of auto-buffer tuning[1] and the lack of pluggable congestion control[2]. [1] http://michawe.at.ifi.uio.no/research/projects/new-transport/implementing-sctp-auto-buffer-tuning.html [2] http://michawe.at.ifi.uio.no/research/projects/new-transport/implementing-sctp-pluggable-congestion-control.html From looking at the graphs at [2], it seems that pluggable congestion control never really worked 100%, but by the time the project ended, we didn't figure out why - there might not be too much missing?! Morten has submitted [1]: http://marc.info/?l=linux-sctp&m=129545178506213&w=2 but without success, and following up on this was also not possible within the scope of this project. Now, after so much time has passed, I have come to realize that this will probably pointlessly rest on my webpage forever, where it remains unknown and unused, and that's the end of that story - I don't think anyone on my side is ever going to fix the problem in [2], or re- submit [1]. So, with this email, I'd like to inform the community that this code exists, and whoever feels like it is free to take it and do whatever they wish with it :-) Cheers, Michael
- Re: Some Linux SCTP code that someone could build… Hagen Paul Pfeifer
- Some Linux SCTP code that someone could build upo… Michael Welzl