From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qt0-x22a.google.com (mail-qt0-x22a.google.com [IPv6:2607:f8b0:400d:c0d::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 5CFFE3B29E for ; Fri, 8 Sep 2017 07:50:28 -0400 (EDT) Received: by mail-qt0-x22a.google.com with SMTP id i50so5761302qtf.0 for ; Fri, 08 Sep 2017 04:50:28 -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=ptHazQc7+btHvchWn5FU1/86k/KRR/aPgWuDPzTmi8A=; b=eYJND74UCMX7znQJ3MJKDnD/KS+0VvNDQwYia6zhU//WXSHACC212Bi+qtH8PEcMH8 RCwPOwA8CgsqZ6vEYNuE/X95Myi1xg/dly9lremSsR9b+nzqP8si8s4cx4pTXuZI9CpZ ErgQ4HbbXOfRzwVgWkXo7xjxmtHNPHY1xUGkSfHTW7rr22sA4uaCHENLF5ljwjIxgWVG pBcvcRagEhRxUX+UjY3pQ7soYLWON5KAin7psE3/7N0FyNv4YL61vMb7ThfoLirLBHpE 5mVAlkPypn65Pz9o6iezMGzDjneidgj4PU2wQIymwU3mHbzBYGH+Ftq0lC5gCn/FpHKB qYwQ== 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=ptHazQc7+btHvchWn5FU1/86k/KRR/aPgWuDPzTmi8A=; b=Vg2R++ldkLdpcAubbKgxYPnUBh0DkFabwKY7zi6YovThQS99GJaP5PE00JcMcXABjj ykaIYM9cAopWM69Jq1XOOQXt+gbtFPmeuza+yt4o82RLAFAJQlIKM676sK9cOTcXa719 iUjoLA/rt8DTUw9ptZzAaC3sb2uYyP/pBV1y7+q8jsvxaAhmLIFHrEmuxoLe+/32CkGl 5nAiTcfZXuq/reBIyZXs+fT09HQKt3faJrN6TGmtkV/rJUwL5/xvEvcXg04zJ4vw+kHt HNPixnISeT9TIK4BJSbMIZqjqKCzyCcQRcFNFzn69X0DmelusHvaoqrQl5/yvkudMHjh LVuQ== X-Gm-Message-State: AHPjjUjIDwAjvcNROmJqvjrPms14MfP8zfp10SO2cP6YWm633O2KjAju rfOGsc43NkTjzadKp6PEJW+ITAjZ0Q== X-Google-Smtp-Source: AOwi7QBZLxgeR45jEkPWvIFiWvB9Vn7xSCrT0N2fXvd2S5uu6VecQJHycaOabexlTz1iCihvNtRbVL2USbhGk9aKt9g= X-Received: by 10.200.2.72 with SMTP id o8mr3402785qtg.63.1504871427932; Fri, 08 Sep 2017 04:50:27 -0700 (PDT) MIME-Version: 1.0 Received: by 10.140.40.177 with HTTP; Fri, 8 Sep 2017 04:50:26 -0700 (PDT) Received: by 10.140.40.177 with HTTP; Fri, 8 Sep 2017 04:50:26 -0700 (PDT) In-Reply-To: <20170908073215.dba5utrwuwvruw55@sesse.net> References: <20170908073215.dba5utrwuwvruw55@sesse.net> From: Jonathan Morton Date: Fri, 8 Sep 2017 14:50:26 +0300 Message-ID: To: "Steinar H. Gunderson" Cc: bloat Content-Type: multipart/alternative; boundary="f403045e8042e5077d0558ac2e7f" Subject: Re: [Bloat] dash traffic "chunklets" verses pie and fq_codel 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: Fri, 08 Sep 2017 11:50:28 -0000 --f403045e8042e5077d0558ac2e7f Content-Type: text/plain; charset="UTF-8" While interesting from a scientific point of view, I do think they're trying to solve the wrong problem here. As stated in the paper, the big problem with DASH is the tendency of TCPs to revert to slow start (ie. beginning from a small cwnd) after a gap in availability of data to transmit. If that occurs after as short an interval as 2 seconds (the DASH chunk length), I consider that to be a flaw in those TCP implementations. Theoretically, 2 seconds is as long as DASH should wait while playing video continuously, in the steady state condition where the link capacity is known and the buffer is full. I can see little reason for it to wait longer; I would consider that an implementation flaw in the DASH client. Also, given a nearly full buffer, I would expect DASH to resist reducing the video quality due to a possibly transient reduction in measured link capacity. If the reduction persists long enough to substantially empty the buffer (say to 50%), then it would be reasonable to step down in quality to match the new measurement. Again, this is a quality of implementation problem in the client. The other problem their solution addresses, but is not stated as the primary goal, is to reduce DASH susceptibility to competition versus multiple flow applications such as Steam downloads. But that is not a problem specific to flow isolating AQM systems (if anything, it's worse with plain FIFO). They do note that fq_codel greatly improves the situation versus reverse bulk traffic, just as it should, but they don't seem to highlight that this benefit is reduced with "chunklets" in use, according to the measurements presented. - Jonathan Morton --f403045e8042e5077d0558ac2e7f Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

While interesting from a scientific point of view, I do thin= k they're trying to solve the wrong problem here.

As stated in the paper, the big problem with DASH is the ten= dency of TCPs to revert to slow start (ie. beginning from a small cwnd) aft= er a gap in availability of data to transmit.=C2=A0 If that occurs after as= short an interval as 2 seconds (the DASH chunk length), I consider that to= be a flaw in those TCP implementations.

Theoretically, 2 seconds is as long as DASH should wait whil= e playing video continuously, in the steady state condition where the link = capacity is known and the buffer is full.=C2=A0 I can see little reason for= it to wait longer; I would consider that an implementation flaw in the DAS= H client.

Also, given a nearly full buffer, I would expect DASH to res= ist reducing the video quality due to a possibly transient reduction in mea= sured link capacity. If the reduction persists long enough to substantially= empty the buffer (say to 50%), then it would be reasonable to step down in= quality to match the new measurement.=C2=A0 Again, this is a quality of im= plementation problem in the client.

The other problem their solution addresses, but is not state= d as the primary goal, is to reduce DASH susceptibility to competition vers= us multiple flow applications such as Steam downloads.=C2=A0 But that is no= t a problem specific to flow isolating AQM systems (if anything, it's w= orse with plain FIFO).=C2=A0 They do note that fq_codel greatly improves th= e situation versus reverse bulk traffic, just as it should, but they don= 9;t seem to highlight that this benefit is reduced with "chunklets&quo= t; in use, according to the measurements presented.

- Jonathan Morton

--f403045e8042e5077d0558ac2e7f--