From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <wbahacer@126.com>
Received: from m50-112.126.com (m50-112.126.com [123.125.50.112])
 by dpdk.org (Postfix) with ESMTP id 0528CB62
 for <users@dpdk.org>; Sat, 19 Dec 2015 07:23:25 +0100 (CET)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=126.com;
 s=s110527; h=From:Subject:Message-ID:Date:MIME-Version; bh=Oz4su
 yeB+0KBmIQimx4dc6RvVwF6C8HexTkwo+yAz9E=; b=WT+peR+0q7YXpI5nGc4be
 S2mbljYQdqosrbaNdbglj9MKTVOLnpMH29xONVIMKKj8Dc1PmLrMkq9Y7QJQg29H
 9Wyo3UkwsiVqTCXqDZNwKYECYZcaGyGLnwyAxpqfeQvvYqLx5gRn8UETrW4mLoAT
 m8ZLkRBhabjxZHKMh6bm/k=
Received: from [10.24.0.239] (unknown [159.226.43.35])
 by smtp6 (Coremail) with SMTP id j9KowADHFt_Z93RWqXOfBQ--.1621S2;
 Sat, 19 Dec 2015 14:23:22 +0800 (CST)
To: users@dpdk.org
From: Furong <WBAHACER@126.com>
Message-ID: <5674F7D8.3040102@126.com>
Date: Sat, 19 Dec 2015 14:23:20 +0800
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101
 Thunderbird/38.4.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-CM-TRANSID: j9KowADHFt_Z93RWqXOfBQ--.1621S2
X-Coremail-Antispam: 1Uf129KBjvdXoWrZrWUGF1fCF1kurWkKF45ZFb_yoWkuFXE9w
 13Xw1kZ3yUJws8KF1Ygr1akws7W34DW3WrGa1rXF90y3yUu3Z7Jws7uFyI9r1DGa1Iqry8
 urn3KryxCr42kjkaLaAFLSUrUUUUUb8apTn2vfkv8UJUUUU8Yxn0WfASr-VFAUDa7-sFnT
 9fnUUvcSsGvfC2KfnxnUUI43ZEXa7IUnuT5JUUUUU==
X-Originating-IP: [159.226.43.35]
X-CM-SenderInfo: xzedxtxfhuqiyswou0bp/1tbiThrVMFR0Z5iXrAAAsV
Subject: [dpdk-users] l2fwd performance in VM with SR-IOV
X-BeenThere: users@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: usage discussions <users.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/users>,
 <mailto:users-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/users/>
List-Post: <mailto:users@dpdk.org>
List-Help: <mailto:users-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/users>,
 <mailto:users-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Sat, 19 Dec 2015 06:23:27 -0000

Hello, everybody.
     I have measured performace of example/l2fwd in VM with SR-IOV.
     My experiment server: CPU: 32 core Intel Xeon E5-4603 v2 @ 
2.20GHz,  NIC: 10G Intel 82599ES， OS：ubuntu14.04.3.
     I started a VM with this command：
         # qemu-system-x86_64 -enable-kvm -cpu host -m 4G -smp 4 -net 
none -device vfio-pci,host=<vf1-pcie-addr> -device 
vfio-pci,host=<vf2-pcie-addr> -hda vm.img -vnc :1
     In VM:
         I bound vf1 & vf2 to igb_uio, then started a example/l2fwd in VM.
     Then i started a pktgen in another server (same hardware & os with 
this server) to send packets (small packet - 64bit).
     The results is :
         1. when i sent packets with pktgen from only 1 port , the 
throughput (measured by pktgen rx/tx rates) was 7.0Gbps.
         2. when i sent packets from both 2 port, the throughput was 
7.2Gbps (3.6Gbps each port).

     But, i have measured l2fwd performance in host with SR-IOV (binding 
vf1 & vf2 to vfio-pci & starting l2fwd in host).
     The result is :
         when i sent packets from both 2 port, the throughput was 
14.4Gbps (7.2Gbps each port).

     I want to ask when i ran l2fwd in VM, Can i achieve similar 
performance with host? or, there are some methods to tune the performance ?

     Thanks a lot!
     Furong