From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp1.sms.unimo.it (smtp1.sms.unimo.it [155.185.44.147]) (using TLSv1 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 053D221F22F for ; Mon, 27 Apr 2015 05:01:44 -0700 (PDT) Received: from [212.84.39.131] (port=55753 helo=[192.168.15.101]) by smtp1.sms.unimo.it with esmtpsa (TLS1.0:RSA_AES_128_CBC_SHA1:128) (Exim 4.80) (envelope-from ) id 1YmhjF-00036y-DY; Mon, 27 Apr 2015 14:01:42 +0200 Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\)) Content-Type: text/plain; charset=windows-1252 From: Paolo Valente In-Reply-To: <87zj5u2aho.fsf@toke.dk> Date: Mon, 27 Apr 2015 14:01:24 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <2B5B39C9-A33D-46ED-84C6-56F237284B21@unimore.it> References: <3E2406CD-0938-4C1F-B171-247CBB5E4C7D@unimore.it> <87zj5u2aho.fsf@toke.dk> To: =?windows-1252?Q?Toke_H=F8iland-J=F8rgensen?= X-Mailer: Apple Mail (2.1878.6) UNIMORE-X-SA-Score: -2.9 Cc: bloat Subject: Re: [Bloat] bufferbloat effects on throughput 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: Mon, 27 Apr 2015 12:02:13 -0000 Il giorno 27/apr/2015, alle ore 11:20, Toke H=F8iland-J=F8rgensen = ha scritto: > Paolo Valente writes: >=20 >> If there are, could anyone please point me to further reading on = these >> aspects? >=20 > Bufferbloat can definitely adversely affect throughput in some cases. > Mainly because it causes throughput to oscillate: when the queue = fills, > a lot of data can be dropped at once, causing throughput to drop, = which > takes a while to recover. This can degrade aggregate throughput. = Having > smart queueing smoothes out the traffic, so the oscillations are lower > and average throughput thus better. >=20 > The effect is most visible when you have several flows sharing a link: > when the (FIFO) queue fills, they will tend to all experience drops at > once, and so all slow down. >=20 Thanks. So, if I understood correctly, average throughput may or may not = be affected, but large throughput fluctuations will always occur in the = presence of bufferbloat. Sorry for my usual refrain, but =85 any pointers to tests, results, = papers and the like? Thanks, Paolo > -Toke -- Paolo Valente =20 Algogroup Dipartimento di Fisica, Informatica e Matematica =09 Via Campi, 213/B 41125 Modena - Italy =20 homepage: http://algogroup.unimore.it/people/paolo/