From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Friesen Subject: Re: TCP funny-ness when over-driving a 1Gbps link (and wifi) Date: Thu, 26 May 2011 09:28:16 -0600 Message-ID: <4DDE7190.3080503@genband.com> References: <4DD59DF2.2070707@candelatech.com> <20110519161827.2ba4b40e@nehalam> <4DD5A5CD.7040303@candelatech.com> <4DD5AAFC.8070509@candelatech.com> <1305849940.8149.1122.camel@tardy> <4DD5B202.7080701@candelatech.com> <1305851079.8149.1127.camel@tardy> <4DD5B7B3.2000505@candelatech.com> <1305852377.8149.1133.camel@tardy> <4DD5E270.3030209@candelatech.com> <4DD6DE1C.8090607@candelatech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: rick.jones2@hp.com, Stephen Hemminger , netdev To: Ben Greear Return-path: Received: from exprod7og106.obsmtp.com ([64.18.2.165]:47442 "EHLO exprod7og106.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932445Ab1EZP2u (ORCPT ); Thu, 26 May 2011 11:28:50 -0400 In-Reply-To: <4DD6DE1C.8090607@candelatech.com> Sender: netdev-owner@vger.kernel.org List-ID: On 05/20/2011 03:33 PM, Ben Greear wrote: > I tried a different test today: 3 TCP connections between two > wifi station interfaces (using ath9k). Each connection is > endpoint configured to send 100Mbps of traffic to the peer. > > With a single connection, it does OK (maybe 250ms round-trip time max). > With 3 of them running, round-trip user-space to user-space latency > often goes above 3 seconds. > So, seems a general issue with over-driving links with multiple TCP > connections. Doesn't seem like a regression, and probably not really > a bug, but maybe the buffer-bloat project will help this sort of > thing... Given that one rule of thumb for the send buffer size is twice the bandwidth delay product, it seems clear that on a wifi connection 3 seconds worth of buffering is excessive. I think I'd classify that as a bug. Chris -- Chris Friesen Software Developer GENBAND chris.friesen@genband.com www.genband.com