Re: [EToSat] What we are looking for from QUIC
Kuhn Nicolas <Nicolas.Kuhn@cnes.fr> Wed, 04 December 2019 16:05 UTC
Return-Path: <Nicolas.Kuhn@cnes.fr>
X-Original-To: etosat@ietfa.amsl.com
Delivered-To: etosat@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 1BAAB120848 for <etosat@ietfa.amsl.com>; Wed, 4 Dec 2019 08:05:44 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.899
X-Spam-Level:
X-Spam-Status: No, score=-1.899 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] 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 qOzc9s4czVHe for <etosat@ietfa.amsl.com>; Wed, 4 Dec 2019 08:05:38 -0800 (PST)
Received: from mx2.cnes.fr (mx2.cnes.fr [194.199.174.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 5073812083D for <etosat@ietf.org>; Wed, 4 Dec 2019 08:05:30 -0800 (PST)
X-IronPort-AV: E=Sophos;i="5.69,277,1571702400"; d="scan'208";a="31337315"
X-IPAS-Result: A2FTAADF2Odd/wUBeAplDgsBAQEBAQEBAQEBAQEBAQEBAREBAQEBAQEBAQEBAYF+gXSBBROBMQqVQ4M9lgmBXwgJAQEBAQEBAQEBIAsMAQGDe0UCgjU4EwIQAQEBBAEBAQEBBQIBAQIChVRMDIYnAQEBAQMBAWsBCxACAQgNCwokJwslAQEECgQFCBEBAYMIgwavboInGoQkAhEPhWEGgTaBZYxMgRFHgh4uPoJkAQEDgS0BEgEJGAWDO4IsBI0JiWeXWgeBPXSCOYRmi3uCW3eBSowaA4tIjkqBRYZ8jRGGYoEKcTMaJ0yCbFARjiEBCYJChRSFBDt0jzaBIoEQAQE
X-URL-LookUp-ScanningError: 1
From: Kuhn Nicolas <Nicolas.Kuhn@cnes.fr>
To: "'gorry@erg.abdn.ac.uk'" <gorry@erg.abdn.ac.uk>
CC: 'Christian Huitema' <huitema@huitema.net>, "Border, John" <John.Border@hughes.com>, "etosat@ietf.org" <etosat@ietf.org>
Thread-Topic: [EToSat] What we are looking for from QUIC
Thread-Index: AdWqBvqSpD0dZHfeQqedFPfMiHoxPwAI+HMAABK9agAABPFsgAAMosxQ
Date: Wed, 04 Dec 2019 16:04:27 +0000
Deferred-Delivery: Wed, 4 Dec 2019 16:05:27 +0000
Message-ID: <F3B0A07CFD358240926B78A680E166FF1ED1EE08@TW-MBX-P03.cnesnet.ad.cnes.fr>
References: <BL0PR11MB3394354FD21C86492999FB8590420@BL0PR11MB3394.namprd11.prod.outlook.com> <540ea43d-8b9b-181c-9f6b-90214cf81905@huitema.net> <F3B0A07CFD358240926B78A680E166FF1ED1D505@TW-MBX-P03.cnesnet.ad.cnes.fr> <5DE791B1.8010905@erg.abdn.ac.uk>
In-Reply-To: <5DE791B1.8010905@erg.abdn.ac.uk>
Accept-Language: fr-FR, en-US
Content-Language: fr-FR
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
x-tm-as-product-ver: SMEX-11.0.0.4255-8.100.1062-25084.001
x-tm-as-result: No--28.649500-0.000000-31
x-tm-as-user-approved-sender: Yes
x-tm-as-user-blocked-sender: No
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
Archived-At: <https://mailarchive.ietf.org/arch/msg/etosat/P2d2ONmnpbNx63NQX7vC70NGjhc>
Subject: Re: [EToSat] What we are looking for from QUIC
X-BeenThere: etosat@ietf.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: "The EToSat list is a non-WG mailing list used to discuss performance implications of running encrypted transports such as QUIC over satellite." <etosat.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/etosat>, <mailto:etosat-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/etosat/>
List-Post: <mailto:etosat@ietf.org>
List-Help: <mailto:etosat-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/etosat>, <mailto:etosat-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 04 Dec 2019 16:05:44 -0000
-----Message d'origine----- De : Gorry Fairhurst <gorry@erg.abdn.ac.uk> Envoyé : mercredi 4 décembre 2019 12:00 À : Kuhn Nicolas <Nicolas.Kuhn@cnes.fr> Cc : 'Christian Huitema' <huitema@huitema.net>; Border, John <John.Border@hughes.com>; etosat@ietf.org Objet : Re: [EToSat] What we are looking for from QUIC On 04/12/2019, 07:51, Kuhn Nicolas wrote: > > *De :* EToSat <etosat-bounces@ietf.org> *De la part de* Christian > Huitema *Envoyé :* mercredi 4 décembre 2019 00:42 *À :* Border, John > <John.Border@hughes.com>; etosat@ietf.org *Objet :* Re: [EToSat] What > we are looking for from QUIC > > On 12/4/2019 2:43 AM, Border, John wrote: > > With TCP spoofing, we can currently achieve very high speeds (e.g. > > 200 Mbps). Mostly this is in the lab but we have shown it over > the air at tradeshows. TCP spoofing also provides minimal > degradation to these speeds in the face of packet loss. Ideally, > we would like QUIC to evolve to match this performance without > spoofing. The ideal is probably not achievable but we want to get > as close as possible. We are looking at FEC to help with the > packet loss problem and large windows to address the throughput > problem. Since enabling FEC and very large windows (especially > initial windows) will not be good defaults for general use, we > need some sort of learning capability to know when they should be > used. I think all of this is well known. > > Yes, that's what I have been testing for with Picoquic. Once the > windows are established, we can certainly get >200Mbps on the > simulator -- we get 600 Mbps in loopback connections. The congestion > control and flow control algorithms are designed to find the right > window values. Starting with 0 knowledge it takes time, but given time > they do find them. The challenge is to shorten that adaptation time in > the general case. > [GF] The params from John seem fine - but for me I'd also like to ensure we test 10/2 Mbps as a baseline - hinted in John's email, because this is also a current service datapoint. [NK] I guess we should at least keep 3 three scenarios : (10/2 Mbps or 50/10 Mbps) (250 Mbps no loss) (250 Mbps with François loss model). I will push an updated version of the regression tests ASAP. > > */[NK] The challenge is to shorten that adaption time indeed - and to > let client and server know about the network underneath for 0-RTT > connections. This is what we tried to achieve with the 0-RTT BDP draft > that we need to update. /* > > Detecting 1% loss and retransmitting the missing packets is obvious. I > don't think we need FEC, unless we value timeliness over efficiency. > The big challenge is to distinguish between congestion losses > happening at the bottleneck and random losses happening elsewhere on > the path. That's possible if the congestion algorithm uses delay > variations and ECN marks instead of losses to detect congestion. > > */[NK] For short flows, 1% losses is not really a big deal. However, > when it comes to long files transfers, things are different. 0.1% > random losses may halve the goodput. Considering FEC in QUIC has been > proposed in NWCRG > [https://tools.ietf.org/html/draft-swett-nwcrg-coding-for-quic-03] but > it looks like going further in this discussion needs to consider the > impacts between FEC and loss-based congestion control [which we tried > to initiate in > https://tools.ietf.org/html/draft-kuhn-coding-congestion-transport-00] > . If the congestion control is delay based, life is easier but > otherwise, distinguishing congestion and random losses is a chimera to > me, if there is no efficient in network signaling. /* > > Then there is a issue of asymmetric links. That requires sending way > fewer ACK than what is specified in the QUIC recovery spec. > > */[NK] Indeed. Looking at the QUIC transport document > [/*https://github.com/quicwg/base-drafts/blob/master/draft-ietf-quic-t > ransport.md*/], I can see : "An ACK frame SHOULD be generated for at > least every second ack-eliciting packet. This recommendation is in > keeping with standard practice for TCP {{?RFC5681}}." However, there > do not seem to be a generic transport parameter for changing > dynamically this value. > /**/Should we file an issue and cha/**/nge the SHOULD for a RECOMMEND > and propose other values and the need for a transport parameter? /* > [GF} We at Aberdeen are digging in this space again. I think what I'd like most to see is a recommendation of how to safely adapt 2 to 10. The number is important because it impacts CC dynamics and the basic smoothness/burstiness of the cwnd growth; and a flow should be more than x10 more aggressive than a new flow. I will argue that the number 10 seems a credible safe number to propose - because we alreday allow IW=10 as a burst (that should of course be paced if you can), but at least the notion exists that 10 buffers are often available on the path. [GF] If this argument stands, I think we should propose adding a decription of why more than 10 needs mroe care, and how you could decide between needing 2 or 10 as the number of packets that are cumulatively ACKed. [NK] I totally agree that we should add that description and change the text on the QUIC draft. > > But, we are also looking ahead. More and more, satellite is being > paired with terrestrial connectivity. Multipath QUIC will work > when that pairing happens at the client. But, it doesn't help when > the client is not aware of the existence of the multiple paths. > Specifically, if the client is connected via WiFi to some sort of > access port and that access port has parallel satellite and > terrestrial (e.g. LTE) connectivity, the existence of the multiple > paths is hidden from the client. One solution path is to somehow > have the access point interact with the client to make the client > aware. (A proxy comes to mind but there are other options.) The > other solution path is to make QUIC be able to adapt quickly to > changes in path characteristics. > > Let's deal with that later. Multipath is on the work list for QUIC v2. > > We just wanted to throw the above out there so we can keep it mind > when working on solutions to the shorter term problem of making > QUIC work well over satellite in the first place.. > > The good news is that while satellite links are special, the three > challenges above are also present in other environments. Faster > adaptation, recognizing non congestion losses or sending fewer ACKs is > beneficial in general. So there is hope... > > */[NK] Indeed !/* > > John > > -- Christian Huitema > > > > _______________________________________________ > EToSat mailing list > EToSat@ietf.org > https://www.ietf.org/mailman/listinfo/etosat Gorry
- [EToSat] What we are looking for from QUIC Border, John
- Re: [EToSat] What we are looking for from QUIC Christian Huitema
- Re: [EToSat] What we are looking for from QUIC Junho Choi
- Re: [EToSat] What we are looking for from QUIC lloyd.wood@yahoo.co.uk
- Re: [EToSat] What we are looking for from QUIC Su, Chi-Jiun
- Re: [EToSat] What we are looking for from QUIC Junho Choi
- Re: [EToSat] What we are looking for from QUIC Kuhn Nicolas
- Re: [EToSat] What we are looking for from QUIC Emmanuel Lochin
- Re: [EToSat] What we are looking for from QUIC Gorry Fairhurst
- Re: [EToSat] What we are looking for from QUIC Kuhn Nicolas
- Re: [EToSat] What we are looking for from QUIC Ted Hardie
- Re: [EToSat] What we are looking for from QUIC Morten V. Pedersen
- Re: [EToSat] What we are looking for from QUIC Su, Chi-Jiun
- Re: [EToSat] What we are looking for from QUIC Border, John
- Re: [EToSat] What we are looking for from QUIC Christian Huitema
- Re: [EToSat] What we are looking for from QUIC Su, Chi-Jiun
- Re: [EToSat] What we are looking for from QUIC Morten V. Pedersen
- Re: [EToSat] What we are looking for from QUIC lloyd.wood@yahoo.co.uk
- Re: [EToSat] What we are looking for from QUIC Su, Chi-Jiun
- Re: [EToSat] What we are looking for from QUIC François Michel
- Re: [EToSat] What we are looking for from QUIC Morten V. Pedersen
- [EToSat] Picoquic, satellites and BBR Christian Huitema
- Re: [EToSat] Picoquic, satellites and BBR Su, Chi-Jiun