From mboxrd@z Thu Jan 1 00:00:00 1970 From: "=?ISO-8859-1?Q?Ilpo_J=E4rvinen?=" Subject: Re: initial congestion window for connections in the listen queue Date: Tue, 14 Apr 2009 00:54:40 +0300 (EEST) Message-ID: References: <200904132346.15783.opurdila@ixiacom.com> <20090413.142653.267913010.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: opurdila@ixiacom.com, Netdev To: David Miller Return-path: Received: from courier.cs.helsinki.fi ([128.214.9.1]:47916 "EHLO mail.cs.helsinki.fi" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753546AbZDMVyo (ORCPT ); Mon, 13 Apr 2009 17:54:44 -0400 In-Reply-To: <20090413.142653.267913010.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Mon, 13 Apr 2009, David Miller wrote: > From: Octavian Purdila > Date: Mon, 13 Apr 2009 23:46:15 +0300 > > > > > A question for the TCP wizards: > > > >>struct sock *tcp_create_openreq_child(struct sock *sk, > >> struct request_sock >*req, struct sk_buff *skb) > >>{ > >>... > >> /* So many TCP implementations out there (incorrectly) count the > >> * initial SYN frame in their delayed-ACK and congestion control > >> * algorithms that we must have the following bandaid to talk > >> * efficiently to them. -DaveM > >> */ > >> newtp->snd_cwnd = 2; > > > > Shouldn't the same logic from tcp_init_cwnd() be used here? > > > >>From my traces, this seems to prevent TSO from helping short lived > > connections. > > On any standard ethernet MTU or larger, you should be getting > an initial CWND of 3 or 4 because of the logic in tcp_init_cwnd(). > > Don't just guesstimate what initial ->snd_cwnd value the > kernel is using by looking casually at tcpdump traces. Add > some kernel debugging printk's and find out for sure. A long-standing feature in tcp_init_metrics() is such that any of its goto reset prevents call to tcp_init_cwnd(). I never remembered to fix that. -- i.