From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Monjalon Subject: Re: [PATCH 1/4 v4] add vector PMD RX for FVL Date: Fri, 30 Oct 2015 16:33:39 +0100 Message-ID: <1494626.99fePb7LtU@xps13> References: <1446210115-13927-1-git-send-email-zhe.tao@intel.com> <1446214599-14669-1-git-send-email-zhe.tao@intel.com> <1446214599-14669-2-git-send-email-zhe.tao@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7Bit Cc: dev@dpdk.org To: Zhe Tao Return-path: Received: from mail-wm0-f50.google.com (mail-wm0-f50.google.com [74.125.82.50]) by dpdk.org (Postfix) with ESMTP id 6B27C8E92 for ; Fri, 30 Oct 2015 16:34:50 +0100 (CET) Received: by wmeg8 with SMTP id g8so14630810wme.0 for ; Fri, 30 Oct 2015 08:34:50 -0700 (PDT) In-Reply-To: <1446214599-14669-2-git-send-email-zhe.tao@intel.com> 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" 2015-10-30 22:16, Zhe Tao: > The vPMD RX function uses the multi-buffer and SSE instructions to > accelerate the RX speed, but now the pktype cannot be supported by the vPMD RX, > because it will decrease the performance heavily. So we cannot rely on the pktype information? Depending on which Rx path is used, we will have the information or not. > Signed-off-by: Zhe Tao > +CONFIG_RTE_LIBRTE_I40E_RX_OLFLAGS_ENABLE=y When we'll have some devargs options for PCI dev, we could move this option to runtime.