From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from s72.web-hosting.com (s72.web-hosting.com [198.187.29.21]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 2795921F20C for ; Mon, 20 Jan 2014 07:40:29 -0800 (PST) Received: from [117.222.158.211] (port=37869 helo=nako) by server72.web-hosting.com with esmtpsa (UNKNOWN:AES128-GCM-SHA256:128) (Exim 4.80.1) (envelope-from ) id 1W5GxX-003OsN-0K; Mon, 20 Jan 2014 10:40:19 -0500 From: Sujith Manoharan MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <21213.16934.851675.554642@gargle.gargle.HOWL> Date: Mon, 20 Jan 2014 21:05:02 +0530 To: "David P. Reed" In-Reply-To: <0045e4e1-f1dd-4e15-81fb-4d616ffab08d@katmail.1gravity.com> References: <21212.38828.910370.71395@gargle.gargle.HOWL> <21212.40503.163250.285305@gargle.gargle.HOWL> <0045e4e1-f1dd-4e15-81fb-4d616ffab08d@katmail.1gravity.com> X-Mailer: VM 8.2.0b under 24.3.50.1 (x86_64-unknown-linux-gnu) X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - server72.web-hosting.com X-AntiAbuse: Original Domain - lists.bufferbloat.net X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - msujith.org X-Get-Message-Sender-Via: server72.web-hosting.com: authenticated_id: sujith@msujith.org X-Source: X-Source-Args: X-Source-Dir: Cc: "cerowrt-devel@lists.bufferbloat.net" Subject: Re: [Cerowrt-devel] looking over ampdu stats X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 20 Jan 2014 15:41:23 -0000 X-List-Received-Date: Mon, 20 Jan 2014 15:41:23 -0000 David P. Reed wrote: > It's worth remembering that while aggregation of data in single units might > reduce overhead, end to end latency is far more critical to most Internet > apps. > > Focusing on optimizing throughput for the last few percent in corner cases is > NOT desirable. In fact, it is the cause of pervasive buffer bloated designs, > and the creator of "Daddy broke the Internet" scenarios. > > Since LTE is badly configured in the field for Internet use, causing denial of > service to many users because of bloated (multisecond to drain) queues, I > would stop focusing on this, which is only a 10 percent issue. Multisecond > bloat is a disaster. You are fiddling while Rome burns imo. Well, the 10 percent is with a 1x1 card. It becomes worse with 2x2 and with 3x3, it's really bad - about 180 Mbps when it should be close to 290 Mbps. Using more parallel threads appears to improve things, but I don't see this behavior with a windows client, where a single iperf stream gives good results, unlike ath9k. Sujith