From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm0-x22b.google.com (mail-wm0-x22b.google.com [IPv6:2a00:1450:400c:c09::22b]) (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 BC4363B2C9 for ; Wed, 2 Mar 2016 15:53:58 -0500 (EST) Received: by mail-wm0-x22b.google.com with SMTP id l68so6603965wml.0 for ; Wed, 02 Mar 2016 12:53:58 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=subject:to:references:cc:from:message-id:date:user-agent :mime-version:in-reply-to:content-transfer-encoding; bh=LK0HhHIZmBpTXMnXIx/zOMVQdAvq6D7gQe3yH9FtdOw=; b=Nsrn6bbPy/rPnjs+RO7NGI17ajwY8dqUXk5frq+2sY93Vsc6G72y+/OgObDyU/XYxG a19ulczFr5aEbzKfBBCJL6lXW4wNN5fxpzBI3r0uYCrM8c0UhW10fGpwo4v+PgXbQMr5 8GEBhHZDPBf0Hu4CMJiOAOf0sZKAaHQ+2JGM2KZIlhg/QTG7LG5TgvElzhkJ0OtoKP/m 3HHlfs9JhY+62GMQBcXlv+BXuRO9rd6m9axbeVHJnvvMLSt+zXUdjWkwqMx5igtT2MFm gJM8DnO69SUorsenR8XLRdDQEUjv9xhSKvTeBIkVxDUctydYXk5FraIuxjIb0kYYuFhP OVgQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:subject:to:references:cc:from:message-id:date :user-agent:mime-version:in-reply-to:content-transfer-encoding; bh=LK0HhHIZmBpTXMnXIx/zOMVQdAvq6D7gQe3yH9FtdOw=; b=FKpYbDLDFtAa2rs7QO6UEEU+Wf88Tw6ae/+VtsbgdrYI6m6m2acMPQpKpGsyntsCym udoZcV5ssxZLxzOmv3pZ2q5FGKjl53wFLePnvjyY4UZqlrnucaJmv6GPbvxF5gBtB5he AScj7OPDhf/dtSh2TqAdSnN/84RMptfAekO4dtsYLEkeS7+AjYgZsceXV5hPzOck+P/3 gg8FLAGedGRJ7DVboC0okkwMmDu+MXBnZJIuyHybVcoeFiMhjOg69o5yUFmnz2y2sybu qELhErAVGp2g2dZXG5bCX6MCcGRsU5I3NQvxY0narIVLWgJVWJDq5RLWNcpR/Q1DU7Oj Zg8Q== X-Gm-Message-State: AD7BkJIUs5GxgAuq6glwYR83JRo2OJoT4ZRhXWQrunga/XXM9qMc0iu0BUHGHc2aeoV9zg== X-Received: by 10.28.13.76 with SMTP id 73mr2098737wmn.14.1456952037785; Wed, 02 Mar 2016 12:53:57 -0800 (PST) Received: from localhost.localdomain (host-89-243-96-209.as13285.net. [89.243.96.209]) by smtp.googlemail.com with ESMTPSA id ll9sm37549345wjc.29.2016.03.02.12.53.56 (version=TLSv1/SSLv3 cipher=OTHER); Wed, 02 Mar 2016 12:53:56 -0800 (PST) To: "Fred Baker (fred)" , =?UTF-8?Q?Dave_T=c3=a4ht?= References: <56BB8F05.2030006@mti-systems.com> <56D1F349.6040601@taht.net> <650D8A08-A9FF-4EDF-9374-B4DBF3EB87CD@cisco.com> Cc: "aqm@ietf.org" , "bloat@lists.bufferbloat.net" From: Alan Jenkins Message-ID: <56D752E3.40507@gmail.com> Date: Wed, 2 Mar 2016 20:53:55 +0000 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.6.0 MIME-Version: 1.0 In-Reply-To: <650D8A08-A9FF-4EDF-9374-B4DBF3EB87CD@cisco.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Bloat] review: Deployment of RITE mechanisms, in use-case trial testbeds report part 1 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: Wed, 02 Mar 2016 20:53:58 -0000 On 02/03/16 18:09, Fred Baker (fred) wrote: >> On Feb 27, 2016, at 11:04 AM, Dave T=C3=A4ht wrote: >> >> https://reproducingnetworkresearch.wordpress.com/2014/06/03/cs244-14-c= onfused-timid-and-unstable-picking-a-video-streaming-rate-is-hard/ >> >>> o the results are very poor with a particular popular AQM >> Define "very poor". ? > Presuming this is Adaptive Bitrate Video, as in Video-in-TCP, we (as in= Cisco engineers, not me personally; you have met them) have observed thi= s as well. Our belief is that this is at least in part a self-inflicted w= ound; when the codec starts transmission on any four second segment excep= t the first, there is no slow-start phase because the TCP session is stil= l open (and in the case of some services, there are several TCP sessions = open and the application chooses the one with the highest cwnd value). Yo= u can now think of the behavior of the line as repeating a four phase seq= uence: nobody is talking, then one is talking, then both are, and then th= e other is talking. When only one is talking, whichever it is, its cwnd v= alue is slowing increasing - especially if cwnd*mss/rtt < bottleneck line= rate, minimizing RTT. At the start of the "both are talking" phase, the = one already talking has generally found a cwnd value that fills the line = and its RTT is slowly increasing. The one starting sends a burst of cwnd = packets, creating an instant queue and often causing one or both to drop = a packet - reducing their respective cwnd values. Depending on the TCP im= plementation in question at the sender, if the induced drop isn't a singl= e packet but is two or three, that can make the affected session pause fo= r as many RTO timeouts (Reno), RTTs (New Reno), or at least retransmit th= e lost packets in the subsequent RTT and then reduce cwnd by at least tha= t amount (cubic) and maybe half (SACK). Interesting! Just as Dave reminds us that Google avoid the bursts you=20 describe, using pacing. (See end of message=20 https://lists.bufferbloat.net/pipermail/bloat/2016-February/007205.html) You can call the result a disadvantage of FQ in the real world if you=20 want. But you can also say it provides some necessary alignment of=20 incentives. Incentives for applications to develop more=20 network-friendly behaviour :). I was surprised that a project with=20 large ISP involvement seems to take the first point of view. (Also the part about connections being chosen by cwnd helps explain the=20 fq_codel throughput graph. You can see the audio and video connections=20 switch roles several times. The same times as the bitrate fluctuates, I = notice) I was just skimming PANDA[1], which does AIMD for adaptive streaming. So = they decrement the interval between chunk fetches, until the observed=20 throughput _over the full on-off cycle_ is sufficient to sustain the=20 next quality level. It could just as easily pace the fetch=20 over the full period. No more on-off cycle, no damaging bursts=20 of packets? Alan [1] http://arxiv.org/pdf/1305.0510.pdf