From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp001-out.apm-internet.net (smtp001-out.apm-internet.net [85.119.248.222]) by mail.toke.dk (Postfix) with ESMTPS id 8F1D1864411 for ; Fri, 16 Jul 2021 16:46:46 +0200 (CEST) Received: (qmail 31164 invoked from network); 16 Jul 2021 14:46:45 -0000 X-APM-Out-ID: 16264468053116 X-APM-Authkey: 255286/0(253943/0) 983 Received: from unknown (HELO zimbra003.verygoodemail.com) (85.119.248.218) by smtp001.apm-internet.net with SMTP; 16 Jul 2021 14:46:45 -0000 Received: from localhost (localhost [127.0.0.1]) by zimbra003.verygoodemail.com (Postfix) with ESMTP id 56ADB80F45; Fri, 16 Jul 2021 15:46:45 +0100 (BST) Received: from zimbra003.verygoodemail.com ([127.0.0.1]) by localhost (zimbra003.verygoodemail.com [127.0.0.1]) (amavisd-new, port 10026) with ESMTP id 76R8FqdVGLoq; Fri, 16 Jul 2021 15:46:45 +0100 (BST) Received: from phage-rock.fritz.box (p2e5a5d87.dip0.t-ipconnect.de [46.90.93.135]) by zimbra003.verygoodemail.com (Postfix) with ESMTPSA id 2024E80F02; Fri, 16 Jul 2021 15:46:45 +0100 (BST) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 13.4 \(3608.120.23.2.7\)) From: T H Panton In-Reply-To: <878s27aviv.wl-jch@irif.fr> Date: Fri, 16 Jul 2021 16:46:41 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <0AA86EE7-3FFA-4764-A0B2-A6C18A6A231E@pi.pe> References: <35ECF0D3-B549-4C43-868F-58021E7F2BDD@pi.pe> <87k0lxw10s.wl-jch@irif.fr> <04852E87-1E76-458B-ACC1-E06D6901894E@pi.pe> <878s27aviv.wl-jch@irif.fr> To: Juliusz Chroboczek X-Mailer: Apple Mail (2.3608.120.23.2.7) Message-ID-Hash: FNYQ37K7VJF5LHI5RVJAT4YZTF6DVVG7 X-Message-ID-Hash: FNYQ37K7VJF5LHI5RVJAT4YZTF6DVVG7 X-MailFrom: tim@pi.pe X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: galene@lists.galene.org X-Mailman-Version: 3.3.4 Precedence: list Subject: [Galene] Re: using up more ports in ipv6 for better congestion control List-Id: =?utf-8?q?Gal=C3=A8ne_videoconferencing_server_discussion_list?= Archived-At: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: > On 16 Jul 2021, at 03:37, Juliusz Chroboczek wrote: >=20 >>> Tim, I'd be very grateful if you could explain what advantages TWCC = has >>> over REMB. For now, I'm sticking with REMB. >=20 >> I can=E2=80=99t speak from experience (I=E2=80=99ve only used REMB) - = but my sense is >> that the difference really kicks in when you have multiple video = media >> streams using the same path. So perhaps video, screen share and >> audio. REMB treats each stream separately if I recall. >=20 > Then REMB could be modified to perform per-connection congestion = control, > just like TWCC, without all of the chattiness of TWCC. I don=E2=80=99t think it could. - isn't REMB based on watching the = packet arrival interval which is pretty consistent on a single stream. But imagine multiplexing some = opus (50 fps) a screenshare (10fps) a thumbnail (15fps) and a presenter view (60 fps), = you now have multiple valid packet intervals (in some sort of repeating pattern).=20 I imagine that would make the smoother in REMB go badly wrong. TWCC is based on watching the time of flight - which doesn=E2=80=99t = have that problem. >=20 > I really feel that I'm missing something. >=20 > -- Juliusz