From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Vrabel Subject: Re: [Xen-devel] [PATCHv1 net] xen-netback: use skb to determine number of required guest Rx requests Date: Fri, 15 Jan 2016 10:31:57 +0000 Message-ID: <5698CA9D.5040707@citrix.com> References: <1452784710-11923-1-git-send-email-david.vrabel@citrix.com> <20160114.165456.1025501284568544813.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit Cc: , , , To: David Miller , Return-path: Received: from smtp02.citrix.com ([66.165.176.63]:62373 "EHLO SMTP02.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755176AbcAOKcH (ORCPT ); Fri, 15 Jan 2016 05:32:07 -0500 In-Reply-To: <20160114.165456.1025501284568544813.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 14/01/16 21:54, David Miller wrote: > From: David Vrabel > Date: Thu, 14 Jan 2016 15:18:30 +0000 > >> - needed = xenvif_rx_ring_slots_needed(queue->vif); >> + skb = skb_peek(&queue->rx_queue); >> + if (!skb) >> + return false; >> + >> + needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); >> + if (skb_is_gso(skb)) >> + needed++; > > If I am not mistaken, we moved away from this kind of test exactly because > it is inaccurate and may under-estimate the needs. > > It is possible for an N byte SKB to require N segments. Therefore, the: > > DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE); > > calculation doesn't cut it. After 1650d5455bd2dc6b5ee134bd6fc1a3236c266b5b (xen-netback: always fully coalesce guest Rx packets) we always fully pack a packet into its guest Rx slots. Each slot has space for XEN_PAGE_SIZE bytes so this calculation for the number of slots is correct. Shall I resend with a more description changelog? David