From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-21-ewr.dyndns.com (mxout-071-ewr.mailhop.org [216.146.33.71]) by lists.bufferbloat.net (Postfix) with ESMTP id D19362E0392 for ; Tue, 15 Mar 2011 18:59:27 -0700 (PDT) Received: from scan-21-ewr.mailhop.org (scan-21-ewr.local [10.0.141.243]) by mail-21-ewr.dyndns.com (Postfix) with ESMTP id 06DD517FA for ; Wed, 16 Mar 2011 01:59:27 +0000 (UTC) X-Spam-Score: 0.1 () X-Mail-Handler: MailHop by DynDNS X-Originating-IP: 75.145.127.229 Received: from gw.co.teklibre.org (75-145-127-229-Colorado.hfc.comcastbusiness.net [75.145.127.229]) by mail-21-ewr.dyndns.com (Postfix) with ESMTP id ABC59B32 for ; Wed, 16 Mar 2011 01:59:22 +0000 (UTC) Received: from cruithne.co.teklibre.org (unknown [IPv6:2002:4b91:7fe5:1::20]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "cruithne.co.teklibre.org", Issuer "CA Cert Signing Authority" (verified OK)) by gw.co.teklibre.org (Postfix) with ESMTPS id 10A8F5EADB for ; Tue, 15 Mar 2011 19:59:22 -0600 (MDT) Received: by cruithne.co.teklibre.org (Postfix, from userid 1000) id E44C612085F; Tue, 15 Mar 2011 19:59:19 -0600 (MDT) From: d@taht.net (Dave =?utf-8?Q?T=C3=A4ht?=) To: Jonathan Morton Organization: Teklibre - http://www.teklibre.com References: <4D7F4121.40307@freedesktop.org> <20110315175942.GA10064@goldfish> <1300212877.2087.2155.camel@tardy> <20110315183111.GB2542@tuxdriver.com> <29B06777-CC5F-4802-8727-B04F58CDA9E3@gmail.com> <20110315205146.GF2542@tuxdriver.com> <219C7840-ED79-49EA-929D-96C5A6200401@gmail.com> <20110315151946.31e86b46@nehalam> <1300228592.2087.2191.camel@tardy> <1300229578.2565.29.camel@edumazet-laptop> <87fwqo54n7.fsf@cruithne.co.teklibre.org> <823E2A7B-4F46-4159-8029-BD3B075CC4CE@gmail.com> <87bp1b6fo0.fsf@cruithne.co.teklibre.org> Date: Tue, 15 Mar 2011 19:59:19 -0600 In-Reply-To: (Jonathan Morton's message of "Wed, 16 Mar 2011 03:28:54 +0200") Message-ID: <87bp1b4yh4.fsf@cruithne.co.teklibre.org> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: Stephen Hemminger , bloat Subject: Re: [Bloat] Random idea in reaction to all the discussion of TCP flavours - timestamps? 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: Wed, 16 Mar 2011 01:59:28 -0000 Jonathan Morton writes: > On 16 Mar, 2011, at 3:02 am, Dave T=C3=A4ht wrote: > >>>>> 1) Wired devices, where we want to push more 10+ Gbps, so we can assu= me >>>>> a posted skb is transmitted immediately. Even a basic qdisc can be a >>>>> performance bottleneck. Set TX ring size to 256 or 1024+ buffers to >>>>> avoid taking too many interrupts. >>>>=20 >>>> To talk to this a bit, the huge dynamic range discrepancy between a >>>> 10GigE device and what it may be connected to worries me. Some form of >>>> fair queuing should be applied before the data hits the driver. >>>=20 >>> You mean plugging a 10GigE card into a 10Base-T hub? :-D >>=20 >> More like 10GigE into a 1Gig switch. Or spewing out the entire contents >> of a stream to one destination across the internet.=20 > > Then that's no different to what I have in my apartment right now - a >GigE switch connected to a 100base-TX switch, then to a 2Mbps DSL >uplink, which could then be routed (after bouncing around backhauls for >a bit) through a 500Kbps 3G downlink to a computer I've isolated from >the LAN. Having won one battle today (with ecn and pfifo) I'm ill inclined to start another... The problem with your analogy is you are starting from the edge in, rather from the center out. Consider a topology such as 10 Gig E - 10Gig Switch to 1Gig | | | | | | | | | | 1 2 3 4 5 6 7 8 9 0=20 And the server connected servicing hundreds of flows. Statistically, with fair queuing the number of receive buffers required per port will be close to or equal to 1, where in a primitive FIFO setup, something > 10 are required. Multiply the number of ports that are effectively strewn across the eventual path along with the number of streams, and the enormous disparity between the source data rate and the receive data rate is lessened.=20 This is what I mean by talking to fair queuing or any of a zillion variants thereof.=20 > If the flow is responsive, as with every sane TCP, the queue will end But isn't with large buffers that we are dealing with at present with bufferbloat.=20 > up in front of the slowest link - at the 3G tower. That's where the > AQM would need to be. The GigE adapter in my nettop would be largely > idle, as a normal function of the TCP congestion window. Yes. But you started from a different place in your analogy than mine. > > If it isn't, the queue will build up at *every* narrowing of the > channel and the packet loss will be astronomical. All AQM could do > then is to pick any real traffic out of the din. Never said we had only one problem. :) > > - Jonathan > --=20 Dave Taht http://nex-6.taht.net