From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cassarossa.samfundet.no (cassarossa.samfundet.no [129.241.93.19]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 9578D208AC5 for ; Wed, 9 May 2012 17:08:57 -0700 (PDT) Received: from pannekake.samfundet.no ([2001:700:300:1800::dddd]) by cassarossa.samfundet.no with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.72) (envelope-from ) id 1SSGwB-0001Hl-2V for bloat@lists.bufferbloat.net; Thu, 10 May 2012 02:08:55 +0200 Received: from sesse by pannekake.samfundet.no with local (Exim 4.72) (envelope-from ) id 1SSGwA-0008JF-O9 for bloat@lists.bufferbloat.net; Thu, 10 May 2012 02:08:54 +0200 Date: Thu, 10 May 2012 02:08:54 +0200 From: "Steinar H. Gunderson" To: bloat@lists.bufferbloat.net Message-ID: <20120510000854.GB8131@uio.no> References: <4FA9FDC0.9010600@superduper.net> <44673AC5-4320-4C19-9788-87A63C47549D@cisco.com> <4FAAE5F0.2030404@freedesktop.org> <1336607919.12504.119.camel@edumazet-glaptop> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <1336607919.12504.119.camel@edumazet-glaptop> X-Operating-System: Linux 3.3.4 on a x86_64 User-Agent: Mutt/1.5.20 (2009-06-14) Subject: Re: [Bloat] [Codel] The challenge X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 10 May 2012 00:08:58 -0000 On Thu, May 10, 2012 at 01:58:39AM +0200, Eric Dumazet wrote: > One solution is at the producer level (TCP stack of the sender in this > case) to properly pace the transmits in MSS units given the RTT and > cwnd, supposedly done with TCP Hybla. FWIW, I gave Hybla a quick test (echo hybla > /proc/sys/net/ipv4/tcp_congestion_control and then start a VLC server; Linux 3.3.4 on both sides), and it doesn't pace for me. It happily sends packets at what appears to be line speed, even to a host ~100ms away on a much slower line. /* Steinar */ -- Homepage: http://www.sesse.net/