From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zoltan Kiss Subject: Re: [PATCH v1] ixgbe: remove vector pmd burst size restriction Date: Fri, 31 Jul 2015 15:49:33 +0100 Message-ID: <55BB8AFD.7010407@linaro.org> References: <1438330669-25942-1-git-send-email-cunming.liang@intel.com> <55BB47FB.3000409@linaro.org> <2601191342CEEE43887BDE71AB97725836A6B79C@irsmsx105.ger.corp.intel.com> <55BB62A3.2040906@linaro.org> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit To: "Ananyev, Konstantin" , "Liang, Cunming" , "dev@dpdk.org" Return-path: Received: from mail-wi0-f174.google.com (mail-wi0-f174.google.com [209.85.212.174]) by dpdk.org (Postfix) with ESMTP id C5AB2C6EC for ; Fri, 31 Jul 2015 16:49:35 +0200 (CEST) Received: by wicgj17 with SMTP id gj17so21191525wic.1 for ; Fri, 31 Jul 2015 07:49:35 -0700 (PDT) In-Reply-To: <55BB62A3.2040906@linaro.org> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 31/07/15 12:57, Zoltan Kiss wrote: >> >> Another thing, that I just thought about: >> Right now we invoke ixgbe_rxq_rearm() only at the start of >> _recv_raw_pkts_vec(). >> Before it was ok, as _recv_raw_pkts_vec() would never try to read more >> then 32 RXDs. >> But what would happen if nb_pkts > rxq->nb_desc and rxq->rxrearm_nb == 0? > Yes, that call would deplete the RX ring, the card wouldn't be able to > receive more, so the receive function wouldn't be called again to rearm > the ring. > Actually not, the problem is that the recv function would probably overran the the descriptor ring. But anyway, we should limit nb_pkts indeed.