From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: TCP rx window autotuning harmful at LAN context Date: Wed, 11 Mar 2009 06:30:58 -0700 (PDT) Message-ID: <20090311.063058.236235660.davem@davemloft.net> References: <20090309200505.GA58375@bts.sk> <20090309.170927.130334650.davem@davemloft.net> <87bps8fkaw.fsf@basil.nowhere.org> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: md@bts.sk, netdev@vger.kernel.org To: andi@firstfloor.org Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:50951 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752344AbZCKNbM (ORCPT ); Wed, 11 Mar 2009 09:31:12 -0400 In-Reply-To: <87bps8fkaw.fsf@basil.nowhere.org> Sender: netdev-owner@vger.kernel.org List-ID: From: Andi Kleen Date: Wed, 11 Mar 2009 11:03:35 +0100 > Perhaps this points to the default buffer sizing heuristics to > be too aggressive for >= 1GB? It's necessary Andi, you can't fill a connection on a trans- continental connection without at least a 4MB receive buffer. Did you read the commit message of the change that increased the limit?