From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lf0-x230.google.com (mail-lf0-x230.google.com [IPv6:2a00:1450:4010:c07::230]) (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 DCC203B2A4 for ; Sun, 21 May 2017 08:49:41 -0400 (EDT) Received: by mail-lf0-x230.google.com with SMTP id 99so18784316lfu.1 for ; Sun, 21 May 2017 05:49:41 -0700 (PDT) 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=WcMs4SePY9h445fdOcEGU8Z61Xhv4+7/+jmmyMIUKO4=; b=T0Hmej44bbCWQjLhsqaMpBZriETZs28PM1TPfHNxqaKYzDxa/rv5t3MbDCdHOG8JWV qaBNVGpjqkbUUwR3wP+snHozFUIruUW2etRKZ8tsN56JLs1H5TVulqNHIT/2O9xJwF7T YPjBQBx0z0Lsi9IjiUvU22Hi0MIeNQBhrfx8Vys+DEc9ykW/xK8GSn3F1gc7ms+3yB/t TwoXMfQoqWsNEfL87OMxaQMBNVMUY9sKxdDQtndxhnjcP8n6f5YaCP4CLnesck6NEAiJ csibo6lTUAxKKe4J5rrtJZS41/fY5JL2R/zN9BlGgSz3kOsm+afT+u3BcAbyBQ05m/pQ 30Ug== 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=WcMs4SePY9h445fdOcEGU8Z61Xhv4+7/+jmmyMIUKO4=; b=e8gQWsd8eP0KYnfoCmnvx1hpXuzCO/prQlRurAauhQr/s2d3YNqLHLg8bd8n1WTTok hosp2wiKp9vnvLrd13ouJmcYJnYRzPwvhqvwHVa7cWs9F+uwINaW0sg9S/mQXPw1qhm7 KbC4EG0LQQRyaBXWMIRHwLGvdRAjKYUCCNH8UwY2DT3rbmU+kADoFW+9ZO5VgQvhYbdL +82mGDTvWr2HhuHisN1wZrMPQtuDHC0NvB23kqnWhcYhWKrVqBb49tNexNDC3XETjg6W 2Bzxn7GN+geLpHY89yRWcZK72H7J+fMr7yr8bqYXpFxMTioCergDwtghS7z1YUtVq4wD ov+g== X-Gm-Message-State: AODbwcAmgMecHByujH194mA33sqx9vp6AZAf7JkhKb4t32dYpDr8a4Fg leT5V+KHQlYM/RcGSUhyYg42uq3Fug== X-Received: by 10.46.81.89 with SMTP id b25mr348512lje.33.1495370980613; Sun, 21 May 2017 05:49:40 -0700 (PDT) MIME-Version: 1.0 Received: by 10.25.19.220 with HTTP; Sun, 21 May 2017 05:49:39 -0700 (PDT) In-Reply-To: References: From: Benjamin Cronce Date: Sun, 21 May 2017 07:49:39 -0500 Message-ID: To: cloneman Cc: bloat Content-Type: multipart/alternative; boundary="f403045ff5681b66900550083038" Subject: Re: [Bloat] Steam's distribution service - exceeding inbound policiers and bufferbloat 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: Sun, 21 May 2017 12:49:42 -0000 --f403045ff5681b66900550083038 Content-Type: text/plain; charset="UTF-8" All current TCP implementations have a minimum window size of two segments. If you have 20 open connections, then the minimum bandwidth TCP will attempt to consume is (2 segments * 20 connection)/latency. If you have very low latency relative to your bandwidth, the sender will not respond to congestion. On Thu, Apr 6, 2017 at 9:47 PM, cloneman wrote: > Hi, > > Appologies in advance if this is the wrong place to ask, I haven't been > able to locate an official discussion board. > > I'm looking for any comments on Steam's game distribution download system > - specifically how it defeats any bufferbloat mitigation system I've used. > > It seems to push past inbound policers, exceeding them by about 40%. That > is to say, if you police steam traffic to half of your line rate, enough > capacity will remain to avoid packet loss, latency, jitter etc. Obviously > this is too much bandwidth to reserve. > > Without any inbound control, you can expect very heavy packet loss and > jitter. With fq_codel or sfq and taking the usual recommended 15% off the > table, you get improved, but still unacceptable performance in your small > flows / ping etc. > > The behavior can be observed by downloading any free game on their > platform. I'm trying to figure out how they've accomplished this and how to > mitigate this behavior. It operates with 20 http connections > simultaneously, which is normally not an issue (multiple web downloads > perform well under fq_codel) > > Note: in my testing cable and vdsl below 100mbit were vulnerable to this > behavior, while fiber was immune. > > Basically there are edge cases on the internet that like to push too many > bytes down a line that is dropping or delaying packets. I would like to see > more discussion on this issue. > > I haven't tried tweaking any of the parameters / latency targets in > fq_codel. > > > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat > > --f403045ff5681b66900550083038 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
All current TCP implementations have a minimum window size= of two segments. If you have 20 open connections, then the minimum bandwid= th TCP will attempt to consume is (2 segments * 20 connection)/latency. If = you have very low latency relative to your bandwidth, the sender will not r= espond to congestion.

On Thu, Apr 6, 2017 at 9:47 PM, cloneman <cloneman@gmail.com> wrote:
Hi,= =C2=A0

Appologies in advance i= f this is the wrong place to ask, I haven't been able to locate an offi= cial discussion board.=C2=A0

I'm looking for any comments on Steam's game distribution down= load system - specifically how it defeats any bufferbloat mitigation system= I've used. =C2=A0

I= t seems to push past inbound policers, exceeding them by about 40%. That is= to say, if you police steam traffic to half of your line rate, enough capa= city will remain to avoid packet loss, latency, jitter etc. Obviously this = is too much bandwidth to reserve.=C2=A0

Without any inbound control, you can expect very heavy pack= et loss and jitter. With fq_codel or sfq and taking the usual recommended 1= 5% off the table, you get improved, but still unacceptable performance in y= our small flows / ping etc.=C2=A0

The behavior can be observed by downloading any free game on thei= r platform. I'm trying to figure out how they've accomplished this = and how to mitigate this behavior. It operates with 20 http connections sim= ultaneously, which is normally not an issue (multiple web downloads =C2=A0p= erform well under fq_codel)=C2=A0

Note: in my testing cable and vdsl below 100mbit were vulnerable = to this behavior, while fiber was immune.

=
Basically there are edge cases on the internet that like = to push too many bytes down a line that is dropping or delaying packets. I = would like to see more discussion on this issue.=C2=A0

I haven't tried tweaking any of the para= meters / latency targets in fq_codel.=C2=A0


_______________________________________________
Bloat mailing list
Bloat@lists.bufferbloat.net<= /a>
https://lists.bufferbloat.net/listinfo/bloat

--f403045ff5681b66900550083038--