From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: skb_shared_info() Date: Mon, 14 Aug 2006 09:45:53 +0200 Message-ID: <200608140945.53713.ak@suse.de> References: <20060808.163915.03600382.davem@davemloft.net> <200608140704.01533.ak@suse.de> <20060814072903.GA14138@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: David Miller , netdev@vger.kernel.org, johnpol@2ka.mipt.ru Return-path: Received: from mx2.suse.de ([195.135.220.15]:58053 "EHLO mx2.suse.de") by vger.kernel.org with ESMTP id S1751658AbWHNHs3 (ORCPT ); Mon, 14 Aug 2006 03:48:29 -0400 To: Herbert Xu In-Reply-To: <20060814072903.GA14138@gondor.apana.org.au> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Monday 14 August 2006 09:29, Herbert Xu wrote: > On Mon, Aug 14, 2006 at 07:04:01AM +0200, Andi Kleen wrote: > > > > Another reason to move it in the sk_buff would be better cache > > coloring? Currently on large/small MTU packets it will be always on > > the same colors. > > If we went with a fully paged skbs this should be a non-issue, right? Even for 1.5k MTU? (which is still the most common case after all) > In a fully paged representation the head would be small which is the > perfect place to place the skb_shared_info. If the head is small and allocated with kmalloc then slab should color it yes. It won't for big allocations. -Andi