From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Edgar E. Iglesias" Subject: Re: [PATCH] [e1000]: Remove unnecessary tx_lock Date: Sun, 6 Aug 2006 11:18:53 +0200 Message-ID: <20060806091853.GC22168@edgar.underground.se.axis.com> References: <20060806080659.GA22168@edgar.underground.se.axis.com> <20060806090354.GB22168@edgar.underground.se.axis.com> <20060806091020.GA29454@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Edgar E. Iglesias" , davem@davemloft.net, hadi@cyberus.ca, shemminger@osdl.org, mchan@broadcom.com, jesse.brandeburg@intel.com, auke-jan.h.kok@intel.com, netdev@vger.kernel.org Return-path: Received: from miranda.se.axis.com ([193.13.178.8]:30890 "EHLO miranda.se.axis.com") by vger.kernel.org with ESMTP id S1750914AbWHFJS4 (ORCPT ); Sun, 6 Aug 2006 05:18:56 -0400 Received: from axis.com (edgar.se.axis.com [10.92.151.1]) by miranda.se.axis.com (8.12.9/8.12.9/Debian-5local0.1) with ESMTP id k769IrP0032237 for ; Sun, 6 Aug 2006 11:18:53 +0200 To: Herbert Xu Content-Disposition: inline In-Reply-To: <20060806091020.GA29454@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Sun, Aug 06, 2006 at 07:10:20PM +1000, Herbert Xu wrote: > On Sun, Aug 06, 2006 at 11:03:54AM +0200, Edgar E. Iglesias wrote: > > > > > For UDP yes but does this really make sense for TCP? > > > > I don't know :) > > > > The flow may end up with SNDBUF worth of skbs on the socket > > transmit_queue + cwnd worth of skbs on the qdisc queue + full tx ring. In slow > > start we'll increase cwnd and won't se packet loss until the qdisc is full > > (which might be at 1000 pkts). > > For TCP, the packets stay on the transmit queue until they're acked. > So all those packets on the qdisc queue (and tx ring) are still charged > to the socket. The only difference is that right now we're double- > charging the ones on the qdisc queue.. I see, then I guess this won't be a problem. Thanks, -- Programmer Edgar E. Iglesias 46.46.272.1946