From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753061Ab0DKVlb (ORCPT ); Sun, 11 Apr 2010 17:41:31 -0400 Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:42355 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753022Ab0DKVla (ORCPT ); Sun, 11 Apr 2010 17:41:30 -0400 Date: Sun, 11 Apr 2010 14:41:33 -0700 (PDT) Message-Id: <20100411.144133.193724547.davem@davemloft.net> To: andi@firstfloor.org Cc: cristiklein@gmail.com, linux-kernel@vger.kernel.org Subject: Re: [PATCH] tcp: add setsockopt to disable slow start after idle From: David Miller In-Reply-To: <87hbnhbtrg.fsf@basil.nowhere.org> References: <1270863015-19597-1-git-send-email-cristiklein@gmail.com> <20100409.221307.246951787.davem@davemloft.net> <87hbnhbtrg.fsf@basil.nowhere.org> X-Mailer: Mew version 6.3 on Emacs 23.1 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Andi Kleen Date: Sun, 11 Apr 2010 22:48:19 +0200 > It should be safe as long as you don't have any packet loss (which > means the network can take it). Or I am missing something? > > So perhaps allow it, but force disable it on the first retransmit? Unless you can detect packet loss or queueing delay incurred by everyone else on the internet, this won't work. Look, just drop this discussion, people simply don't understand the implications of what they are suggesting. The only thing I am willing to consider is a per-route attribute for this setting, because that would be another legitimate to make this setting.