From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: poor network loopback performance and scalability Date: Mon, 21 Apr 2008 03:22:00 -0700 (PDT) Message-ID: <20080421.032200.209759978.davem@davemloft.net> References: <20080421081103.GA31328@elte.hu> <20080421.011623.67335122.davem@davemloft.net> <20080421101908.GC9295@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: mingo@elte.hu, dada1@cosmosbay.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, a.p.zijlstra@chello.nl To: herbert@gondor.apana.org.au Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:32859 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1753041AbYDUKV6 (ORCPT ); Mon, 21 Apr 2008 06:21:58 -0400 In-Reply-To: <20080421101908.GC9295@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-ID: From: Herbert Xu Date: Mon, 21 Apr 2008 18:19:08 +0800 > I belive the current value is a legacy from the days when we didn't > support skb page frags so everything had to be physically contiguous. It's legacy from when my top-of-the-line UltraSPARC-I 130Mhz cpus got the best loopback results using that value :-)