From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-vn0-x22d.google.com (mail-vn0-x22d.google.com [IPv6:2607:f8b0:400c:c0f::22d]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 9B1E021F2AD for ; Sun, 21 Jun 2015 10:33:50 -0700 (PDT) Received: by vnbf190 with SMTP id f190so4557433vnb.4 for ; Sun, 21 Jun 2015 10:33:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=AxF6CmChopVureSTnbkI6xjNWV09Uxmib7kxnTxFkvM=; b=nWHTQHPY5v/3/vsICbjbPngTJCXAvT5fg1BZY2ms+HeUVQP6lcv3b1r++A3TANMDHI 9yviI/rtjD/fFsl1pd5FhLsB0WJBewSk7DWxxbOLioA/fvREH1rHfg8TEwtyUA1KrH8u u1gRsTzZjhnJIb1XHhV8ia7Ev78C0YQHvk1a4CHku84ZNLR98GZPU+RF98yGhfLwbND2 OiqA/J+FGocXbgjsGMdsQ7N/0cyUQXc7qLQzzV/n7VFiuKbADNXCtAV3uNID0hX6AHpF y8tlnrRPDp7bb6w1VwNjWhfIfrCbOQL6h8i/U1FKFMXOO642a7dw2Iua/q3r5A5R3FjE BMGg== MIME-Version: 1.0 X-Received: by 10.52.92.14 with SMTP id ci14mr22182453vdb.42.1434908029328; Sun, 21 Jun 2015 10:33:49 -0700 (PDT) Received: by 10.52.12.167 with HTTP; Sun, 21 Jun 2015 10:33:49 -0700 (PDT) Received: by 10.52.12.167 with HTTP; Sun, 21 Jun 2015 10:33:49 -0700 (PDT) In-Reply-To: <5586EEF0.7090302@gmail.com> References: <5586EEF0.7090302@gmail.com> Date: Sun, 21 Jun 2015 20:33:49 +0300 Message-ID: From: Jonathan Morton To: Alan Jenkins Content-Type: multipart/alternative; boundary=20cf307f3a045fa4bb05190a8f4c Cc: bloat Subject: Re: [Bloat] TCP congestion detection - random thoughts X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 21 Jun 2015 17:34:18 -0000 --20cf307f3a045fa4bb05190a8f4c Content-Type: text/plain; charset=UTF-8 There are also a couple of TCPs that are sensitive to the RTT signal in the way you describe, but don't completely stop their window increases, in order to avoid being permanently outcompeted. Illinois is in Linux, and Compound TCP is a Microsoft thing. Also noteworthy is Westwood+, which uses RTT and window size to compute available bandwidth, then upon receiving a congestion signal it uses the minimum RTT and the bandwidth to infer the correct new window size rather than blindly halving it. This actually works pretty well with AQM's preference for short queues, without sacrificing bandwidth; the main shortcoming is that the smoothed bandwidth estimate tends to be an underestimate during the early phases of the connection, ie at the critical moment of exiting slow start. - Jonathan Morton --20cf307f3a045fa4bb05190a8f4c Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable

There are also a couple of TCPs that are sensitive to the RT= T signal in the way you describe, but don't completely stop their windo= w increases, in order to avoid being permanently outcompeted. Illinois is i= n Linux, and Compound TCP is a Microsoft thing.

Also noteworthy is Westwood+, which uses RTT and window size= to compute available bandwidth, then upon receiving a congestion signal it= uses the minimum RTT and the bandwidth to infer the correct new window siz= e rather than blindly halving it. This actually works pretty well with AQM&= #39;s preference for short queues, without sacrificing bandwidth; the main = shortcoming is that the smoothed bandwidth estimate tends to be an underest= imate during the early phases of the connection, ie at the critical moment = of exiting slow start.

- Jonathan Morton

--20cf307f3a045fa4bb05190a8f4c--