From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH v11 6/9] net/virtio: implement receive path for packed queues Date: Wed, 5 Dec 2018 14:52:54 -0800 Message-ID: <20181205145254.1eec5bae@xeon-e3> References: <20181203141515.28368-1-jfreimann@redhat.com> <20181203141515.28368-7-jfreimann@redhat.com> <21e02d5f-6f57-3333-3e82-69ab1ea64735@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Jens Freimann , dev@dpdk.org, tiwei.bie@intel.com, Gavin.Hu@arm.com To: Maxime Coquelin Return-path: Received: from mail-pg1-f195.google.com (mail-pg1-f195.google.com [209.85.215.195]) by dpdk.org (Postfix) with ESMTP id EA33969D4 for ; Wed, 5 Dec 2018 23:52:57 +0100 (CET) Received: by mail-pg1-f195.google.com with SMTP id z11so9704199pgu.0 for ; Wed, 05 Dec 2018 14:52:57 -0800 (PST) In-Reply-To: <21e02d5f-6f57-3333-3e82-69ab1ea64735@redhat.com> List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On Wed, 5 Dec 2018 12:28:27 +0100 Maxime Coquelin wrote: > > +static uint16_t > > In think it should be inlined. > > > +virtqueue_dequeue_burst_rx_packed(struct virtqueue *vq, > > + struct rte_mbuf **rx_pkts, > > + uint32_t *len, > > + uint16_t num) Compiler will inline it anyway, and ignore inline directive if it is too big. Bottom line is for static functions there is no need of inline directive.