From alexander.froemmgen@kom.tu-darmstadt.de Mon Apr 2 10:07:12 2018 Return-Path: X-Original-To: multipathtcp@ietfa.amsl.com Delivered-To: multipathtcp@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 46975126D45 for ; Mon, 2 Apr 2018 10:07:12 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -2.992 X-Spam-Level: X-Spam-Status: No, score=-2.992 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, HTML_MESSAGE=0.001, MIME_HEADER_CTYPE_ONLY=0.717, RCVD_IN_DNSWL_MED=-2.3, T_RP_MATCHES_RCVD=-0.01, URI_NOVOWEL=0.5] autolearn=ham autolearn_force=no Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id wfsynd4BDijJ for ; Mon, 2 Apr 2018 10:07:09 -0700 (PDT) Received: from lnx500.hrz.tu-darmstadt.de (mailout.hrz.tu-darmstadt.de [130.83.156.225]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id A617012D778 for ; Mon, 2 Apr 2018 10:07:07 -0700 (PDT) Received: from kommail.kom.e-technik.tu-darmstadt.de (kommail.kom.e-technik.tu-darmstadt.de [130.83.198.181]) by lnx500.hrz.tu-darmstadt.de (8.14.4/8.14.4/HRZ/PMX) with ESMTP id w32H5tuO002126; Mon, 2 Apr 2018 19:05:56 +0200 (envelope-from alexander.froemmgen@kom.tu-darmstadt.de) Received: by kommail.kom.e-technik.tu-darmstadt.de (Postfix, from userid 998) id D2CE02A073A; Mon, 2 Apr 2018 19:06:53 +0200 (CEST) From: =?iso-8859-1?Q?Alexander_Fr=F6mmgen?= To: Date: Mon, 2 Apr 2018 19:06:53 +0200 Message-ID: <009301d3caa5$00872db0$01958910$@kom.tu-darmstadt.de> Content-Type: multipart/alternative; boundary="----=_NextPart_000_0094_01D3CAB5.C413CE40" Content-Language: de Thread-Index: AdPKpK0puXnf5OGhQ/2R28S9bpSZew== X-PMX-TU: seen v1.2 by 5.6.1.2065439, Antispam-Engine: 2.7.2.376379, Antispam-Data: 2018.4.2.165716 X-PMX-RELAY: outgoing Archived-At: X-Mailman-Approved-At: Mon, 02 Apr 2018 10:17:04 -0700 Subject: [multipathtcp] One-way delay-aware scheduling X-BeenThere: multipathtcp@ietf.org X-Mailman-Version: 2.1.22 Precedence: list List-Id: Multi-path extensions for TCP List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 Apr 2018 17:08:32 -0000 This is a multipart message in MIME format. ------=_NextPart_000_0094_01D3CAB5.C413CE40 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Hi all, I just noticed that there was a discussion about one-way delay-aware scheduling at the last IETF meeting. During our work on ProgMP[0], we implemented one-way delay-aware MPTCP scheduling in combination with active probing of subflows [1]. Parts of the source are already available and the remaining stuff will follow soon. In general, our experiments show that it works J In particular, we can reach application-layer round-trip times below the minimum subflow round-trip time. However, we do not really know the real world delay asymmetries. If you visit http://amiusingmptcp.de with MPTCP and multiple subflows, the page will show your round-trip time statistics as well as one-way delay estimates. This might help us to gather some real world delay distributions. Please contact me if you experience problems or measurement artefacts with this page. Kind regards, Alexander [0] https://progmp.net [1] https://progmp.net/thinStreams.html ------=_NextPart_000_0094_01D3CAB5.C413CE40 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable

Hi = all,

 

I just noticed that there was a discussion about = one-way delay-aware scheduling at the last IETF meeting. During our work = on ProgMP[0], we implemented one-way delay-aware MPTCP scheduling in = combination with active probing of subflows [1]. Parts of the source are = already available and the remaining stuff will follow = soon.

 

In general, our experiments show that it works J =A0In particular, we can reach = application-layer round-trip times below the minimum subflow round-trip = time. However, we do not really know the real world delay = asymmetries.

 

If you visit http://amiusingmptcp.de with MPTCP = and multiple subflows, the page will show your round-trip time = statistics as well as one-way delay estimates. This might help us to = gather some real world delay distributions. Please contact me if you = experience problems or measurement artefacts with this = page.

 

Kind regards,

 

Alexander

 

 

[0] https://progmp.net

[1] https://progmp.net/thinStrea= ms.html

------=_NextPart_000_0094_01D3CAB5.C413CE40-- From nobody Wed Apr 4 01:08:01 2018 Return-Path: X-Original-To: multipathtcp@ietfa.amsl.com Delivered-To: multipathtcp@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 46C80124205 for ; Wed, 4 Apr 2018 01:08:00 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -1.911 X-Spam-Level: X-Spam-Status: No, score=-1.911 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_NONE=-0.0001, SPF_PASS=-0.001, T_RP_MATCHES_RCVD=-0.01] autolearn=ham autolearn_force=no Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 63gUMbXNm0sB for ; Wed, 4 Apr 2018 01:07:58 -0700 (PDT) Received: from mail.sfc.wide.ad.jp (shonan.sfc.wide.ad.jp [203.178.142.130]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 21C74120047 for ; Wed, 4 Apr 2018 01:07:57 -0700 (PDT) Received: from mail-io0-f178.google.com (mail-io0-f178.google.com [209.85.223.178]) by mail.sfc.wide.ad.jp (Postfix) with ESMTPSA id 3E369278280 for ; Wed, 4 Apr 2018 17:07:55 +0900 (JST) Received: by mail-io0-f178.google.com with SMTP id m83so25235881ioi.8 for ; Wed, 04 Apr 2018 01:07:55 -0700 (PDT) X-Gm-Message-State: AElRT7EuQ3FXhiLY7nIMSytOcAjKqYDyVqVgKx06sI0tbEt8DGxA1gZc u6zEnvOmBr0GIk43uh6n7OTA4XxxHXkOOZxjkKo= X-Google-Smtp-Source: AIpwx4/R9PBCtHFj1vy7gJlb300HcGP+hudxFeJMigG4P1hvN07Vxzlkut9HmLqDNFI5+ldJw7dC+gKnoMf/7G09Nvw= X-Received: by 10.107.57.84 with SMTP id g81mr15175892ioa.6.1522829274173; Wed, 04 Apr 2018 01:07:54 -0700 (PDT) MIME-Version: 1.0 Received: by 10.79.36.141 with HTTP; Wed, 4 Apr 2018 01:07:53 -0700 (PDT) From: Yoshifumi Nishida Date: Wed, 4 Apr 2018 01:07:53 -0700 X-Gmail-Original-Message-ID: Message-ID: To: multipathtcp Content-Type: text/plain; charset="UTF-8" Archived-At: Subject: [multipathtcp] comments on draft-hesmans-mptcp-socket-03 X-BeenThere: multipathtcp@ietf.org X-Mailman-Version: 2.1.22 Precedence: list List-Id: Multi-path extensions for TCP List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 04 Apr 2018 08:08:00 -0000 Hi, I've read draft-hesmans-mptcp-socket-03 and have comments on several points listed below. 1: I think expression of __u8 or __u16 are not very common. (I guess linux specific) So, I guess uint8_t or uint16_t might be better for them unless there's specific reasons. 2: Do we need 16 bits for low_prio, although it is currently used for binary info? Also, I am wondering prio might be better rather than low_prio. Because I'm not very sure how to use low_prio=2 or 3. However, I can image using prio=2 or 3 to indicate higher priority. 3: Section 3.4 uses the same name for the structure in Section 3.1 (mptcp_sub_tuple). But, the members in the structure are different.. Is this intentional? 4: It seems to me that if_idx and ipv6_srh will be overwritten when the second inet_pton() is called in the sample code in Figure 11. Also, I think sin_family, sin_port and sin_addr should be sin6_. Thanks, -- Yoshi