From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.taht.net (mail.taht.net [176.58.107.8]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 4B8263B29E for ; Tue, 4 Feb 2020 15:21:47 -0500 (EST) Received: from dancer.taht.net (unknown [IPv6:2601:646:8301:676f:eea8:6bff:fefe:9a2]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.taht.net (Postfix) with ESMTPSA id 756B72286B; Tue, 4 Feb 2020 20:21:45 +0000 (UTC) From: Dave Taht To: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= Cc: bloat@lists.bufferbloat.net References: <871rra62z8.fsf@toke.dk> Date: Tue, 04 Feb 2020 12:21:43 -0800 In-Reply-To: <871rra62z8.fsf@toke.dk> ("Toke \=\?utf-8\?Q\?H\=C3\=B8iland-J\?\= \=\?utf-8\?Q\?\=C3\=B8rgensen\=22's\?\= message of "Tue, 04 Feb 2020 11:50:19 +0100") Message-ID: <877e12w1bc.fsf@taht.net> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.5 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [Bloat] Adding congestion control to the Tor network X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 04 Feb 2020 20:21:47 -0000 I'm looking forward to their upcoming netdevconf talk: https://netdevconf.info/0x14/session.html?talk-reducing-kernel-queuing-dela= ys-with-TCP-window-space-events There are a metric ton of network and congestion control related talks at this conference in this go-round. Some ideas seem brilliant, others, brain damaged. Toke H=C3=B8iland-J=C3=B8rgensen writes: > I figured that this lengthy overview of past and future attempts at > adding congestion control to the Tor network might be interesting to > people here: > > https://lists.torproject.org/pipermail/tor-dev/2020-January/014140.html That was reallly good, thank you. Heavy on ECN derived ideas... fq_codel/pie not in there...=20 Once again FQ gets a bit of short shrift, given that only a few fat flows need congestion control to kick in relative to the others. Of course I have no idea from the regularity of classic FQ how that yields to traffic analysis in one way or another, but I do certainly hope they are mixing up traffic as much as possible within a cell? I've generally found tor to be pretty unusable for my impatient self.=20 The last time I paid attention was in this: http://www.cypherpunks.ca/~iang= /pubs/defenestrator.pdf which is also referenced in the above discussion. > > -Toke > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat