From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qk0-x22a.google.com (mail-qk0-x22a.google.com [IPv6:2607:f8b0:400d:c09::22a]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id B808F3BA8E for ; Thu, 30 Nov 2017 02:48:25 -0500 (EST) Received: by mail-qk0-x22a.google.com with SMTP id u184so7742462qkd.6 for ; Wed, 29 Nov 2017 23:48:25 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc; bh=5y4zD35BVkm28h69l8mfgec3se0kAxjDB9ud+qjOUjY=; b=ofh8af8N1wwYtsmmvfNUTqt4RV3IJ+xbg0MwHfxWW1p1SoEM21wNQAOaw8cPWx4zHo yjZinevfixvFwSigKFWGoj5VwEl+7HJoXpdyAdLoOW4l8LknlmOHbwKOIkLrFEkk6lQb 5vUixO+Xysp0nNVqXy2h/baNyZrepCZhegsK/PxSo0Xp+pR+r7x4TcTD//fhMgI9o4vd Foc3xixkIEyvMGj/kOCLxkFHqL/uw57/Z0PLK+co2yWofTo6J2XZh95fhr53AH6HWpCs j3/3xjBKG7UHL5RY2A5oSBlSCNM46KTkmv/+R6TaXDwnh7OjrEoEtDAM9y5WVdL7kArp Zb9g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:cc; bh=5y4zD35BVkm28h69l8mfgec3se0kAxjDB9ud+qjOUjY=; b=YxIl0i1JmkmGJ72m893jTZj5mLhbnaA3BlEOQQCql34DbPPMU68JgNMUzoiplAOOT1 x98Ccm4EL5DaxaICen0TMMtvhhqK4Sa5gJERigK3DOhMIDPymUkMg7p+CRppz+iP1FEy XFPRZOYZ6gPjE7z2CtZuAM19wqOaqj/fSNYuKJUF7LFXQAX3nse5Y4fQr+lJWV/XtXfC kSMTYV07UtRklpo00FmsSC2ZpP6fyE9FkeNCHtFvu8FzyyASLYeXXR4UQck8Rti3a2M1 O5tgQKJr/0AQYbv47AtCWvQ96GsgFl+l26KM6QHgXVm8qLDQ8IHfhh398rzQNmzYSxod djJQ== X-Gm-Message-State: AKGB3mKA4eytgtkcU0rJbsdkWIrVlqLnBXaPWq8hPOdpk7C4XH18qQpm 7ZxnAR2VCc6MLp/zYTPcO7yNZPVZqZnugXAUJ1I= X-Google-Smtp-Source: AGs4zMYCXFBXDgFK+gmS93cR5qCUNdhaEuVbv/aMYnEYE0mtyoJzL+Q1gOfTxkC1JVc49XUxIJMy5tT3ymXbsyIRKso= X-Received: by 10.55.123.135 with SMTP id w129mr1351271qkc.273.1512028105388; Wed, 29 Nov 2017 23:48:25 -0800 (PST) MIME-Version: 1.0 Received: by 10.140.102.179 with HTTP; Wed, 29 Nov 2017 23:48:24 -0800 (PST) Received: by 10.140.102.179 with HTTP; Wed, 29 Nov 2017 23:48:24 -0800 (PST) In-Reply-To: <7B92DF4D-B6B5-4A64-9E10-119DCA2D4A6F@ifi.uio.no> References: <4D0E907C-E15D-437C-B6F7-FF348346D615@gmx.de> <7B92DF4D-B6B5-4A64-9E10-119DCA2D4A6F@ifi.uio.no> From: Jonathan Morton Date: Thu, 30 Nov 2017 09:48:24 +0200 Message-ID: To: Michael Welzl Cc: bloat , David Ros Content-Type: multipart/alternative; boundary="94eb2c05c4f41cb7db055f2e7a46" Subject: Re: [Bloat] benefits of ack filtering 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: Thu, 30 Nov 2017 07:48:25 -0000 --94eb2c05c4f41cb7db055f2e7a46 Content-Type: text/plain; charset="UTF-8" I do see your arguments. Let it be known that I didn't initiate the ack-filter in Cake, though it does seem to work quite well. With respect to BBR, I don't think it depends strongly on the return rate of acks in themselves, but rather on the rate of sequence number advance that they indicate. For this purpose, having the receiver emit sparser but still regularly spaced acks would be better than having some middlebox delete some less-predictable subset of them. So I think BBR could be a good testbed for AckCC implementation, especially as it is inherently paced and thus doesn't suffer from burstiness as a conventional ack-clocked TCP might. The real trouble with AckCC is that it requires implementation on the client as well as the server. That's most likely why Google hasn't tried it yet; there are no receivers in the wild that would give them valid data on its effectiveness. Adding support in Linux would help here, but aside from Android devices, Linux is only a relatively small proportion of Google's client traffic - and Android devices are slow to pick up new kernel features if they can't immediately turn it into a consumer-friendly bullet point. Meanwhile we have highly asymmetric last-mile links (10:1 is typical, 50:1 is occasionally seen), where a large fraction of upload bandwidth is occupied by acks in order to fully utilise the download bandwidth in TCP. Any concurrent upload flows have to compete with that dense ack flow, which in various schemes is unfair to either the upload or the download throughput. That is a problem as soon as you have multiple users on the same link, eg. a family household at the weekend. Thinning out those acks in response to uplink congestion is a solution. Maybe not the best possible solution, but a deployable one that works. - Jonathan Morton --94eb2c05c4f41cb7db055f2e7a46 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

I do see your arguments.=C2=A0 Let it be known that I didn&#= 39;t initiate the ack-filter in Cake, though it does seem to work quite wel= l.

With respect to BBR, I don't think it depends strongly o= n the return rate of acks in themselves, but rather on the rate of sequence= number advance that they indicate.=C2=A0 For this purpose, having the rece= iver emit sparser but still regularly spaced acks would be better than havi= ng some middlebox delete some less-predictable subset of them.=C2=A0 So I t= hink BBR could be a good testbed for AckCC implementation, especially as it= is inherently paced and thus doesn't suffer from burstiness as a conve= ntional ack-clocked TCP might.

The real trouble with AckCC is that it requires implementati= on on the client as well as the server.=C2=A0 That's most likely why Go= ogle hasn't tried it yet; there are no receivers in the wild that would= give them valid data on its effectiveness.=C2=A0 Adding support in Linux w= ould help here, but aside from Android devices, Linux is only a relatively = small proportion of Google's client traffic - and Android devices are s= low to pick up new kernel features if they can't immediately turn it in= to a consumer-friendly bullet point.

Meanwhile we have highly asymmetric last-mile links (10:1 is= typical, 50:1 is occasionally seen), where a large fraction of upload band= width is occupied by acks in order to fully utilise the download bandwidth = in TCP.=C2=A0 Any concurrent upload flows have to compete with that dense a= ck flow, which in various schemes is unfair to either the upload or the dow= nload throughput.

That is a problem as soon as you have multiple users on the = same link, eg. a family household at the weekend.=C2=A0 Thinning out those = acks in response to uplink congestion is a solution.=C2=A0 Maybe not the be= st possible solution, but a deployable one that works.

- Jonathan Morton

--94eb2c05c4f41cb7db055f2e7a46--