From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH 1/4 net-next] net: allow skb->head to be a page fragment Date: Sat, 28 Apr 2012 05:22:38 -0400 (EDT) Message-ID: <20120428.052238.1177963256540298198.davem@davemloft.net> References: <4F9B3980.1080605@intel.com> <1335597403.2900.29.camel@edumazet-glaptop> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: eric.dumazet@gmail.com, alexander.h.duyck@intel.com, netdev@vger.kernel.org, ilpo.jarvinen@helsinki.fi, ncardwell@google.com, therbert@google.com, maze@google.com, jeffrey.t.kirsher@intel.com, bhutchings@solarflare.com, mcarlson@broadcom.com, mchan@broadcom.com, herbert@gondor.hengli.com.au To: alexander.duyck@gmail.com Return-path: Received: from shards.monkeyblade.net ([198.137.202.13]:50117 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750885Ab2D1JXA (ORCPT ); Sat, 28 Apr 2012 05:23:00 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: From: Alexander Duyck Date: Sat, 28 Apr 2012 01:27:24 -0700 > I was thinking there would be a bigger gain with a change like this > but essentially all you are doing is making the packets more mergable > resulting in you being able to drop the 256 bytes for the sk_buff in > either GRO or when it gets queued for the socket. He's also avoiding the SLUB slow path almost all of the time.