From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ian Campbell Subject: Re: compound skb frag pages appearing in start_xmit Date: Tue, 9 Oct 2012 15:40:30 +0100 Message-ID: <1349793630.21847.208.camel@zakaz.uk.xensource.com> References: <1349790467.21847.185.camel@zakaz.uk.xensource.com> <1349790863.21172.4406.camel@edumazet-glaptop> <1349792241.21847.199.camel@zakaz.uk.xensource.com> <1349792847.21172.4479.camel@edumazet-glaptop> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Eric Dumazet , xen-devel , "netdev@vger.kernel.org" , Konrad Rzeszutek Wilk , Sander Eikelenboom To: Eric Dumazet Return-path: Received: from smtp.ctxuk.citrix.com ([62.200.22.115]:9693 "EHLO SMTP.EU.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751110Ab2JIOke (ORCPT ); Tue, 9 Oct 2012 10:40:34 -0400 In-Reply-To: <1349792847.21172.4479.camel@edumazet-glaptop> Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 2012-10-09 at 15:27 +0100, Eric Dumazet wrote: > On Tue, 2012-10-09 at 15:17 +0100, Ian Campbell wrote: > > > Does the higher order pages effectively reduce the number of frags which > > are in use? e.g if MAX_SKB_FRAGS is 16, then for order-0 pages you could > > have 64K worth of frag data. > > > > If we switch to order-3 pages everywhere then can the skb contain 512K > > of data, or does the effective maximum number of frags in an skb reduce > > to 2? > > effective number of frags reduce to 2 or 3 > > (We still limit GSO packets to ~63536 bytes) Great! Then I think the fix is more/less trivial... As an aside, when the skb head is < 4096 bytes is that necessarily a compound page or might it just be a large kmalloc area? Only really relevant since it impacts the possibility for code sharing between the head and the frags sending. Ian