From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f173.google.com (mail-wi0-f173.google.com [209.85.212.173]) by dpdk.org (Postfix) with ESMTP id E730AC50E for ; Mon, 29 Jun 2015 03:30:46 +0200 (CEST) Received: by wicgi11 with SMTP id gi11so58751397wic.0 for ; Sun, 28 Jun 2015 18:30:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=jBhq/pghXb4enz8lpTOgImlcsX8rBW+FrZQxivQZTiA=; b=X9+fuTR9CYZOoAg2DY5vWTXqRdATi8u++kmjgNmETla9zo6ZGpEdXcZnhodWnOoTSV 7b96fpVQ/RV7wHq5iBIl1hPm2YR5iHm7qVcJYyYaP7bNapAb0KZAHuwj0lgzHx/rPhsS VoCvk1w1EKINS1F/8gOp2CBZRTIyfZafMe8nHFiG6FElUVGAnqR3bwEveo7FnYMMRk8G GQ2pEKPgjMRw655c5L8u6WJ31UmYfFF1/iLJttODX8IcOo91iwlL2GB6ZQTAZE7FHQwA XHSpV1V9zZO/cqe3XL/1G/f7ZgkE4vSedyiLC3fvUsZzQMmVAzopVQEKwqk4OCjThcK+ C2oQ== MIME-Version: 1.0 X-Received: by 10.180.75.4 with SMTP id y4mr17282948wiv.1.1435541446732; Sun, 28 Jun 2015 18:30:46 -0700 (PDT) Received: by 10.28.173.196 with HTTP; Sun, 28 Jun 2015 18:30:46 -0700 (PDT) In-Reply-To: References: Date: Mon, 29 Jun 2015 10:30:46 +0900 Message-ID: From: Keunhong Lee To: Abhishek Verma Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.15 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] Interface once added to DPDK goes missing from ifconfig X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 29 Jun 2015 01:30:47 -0000 To fully utilize DPDK's performance, it is recommended to use native userspace drivers. Because userspace drivers do not interact with your kernel, it is trivial not having 'interfaces' for your kernel. YES you are bypassing whole kernel, if you are using userspace drivers. You may need KNI when: 1. If you want to work legacy applications alongside DPDK applications. 2. If you do not have native userspaces drivers but kernel drivers. KNI is similar with AF_PACKET interface, but it uses ioctl instead of system calls. (I'm not familiar with KNI, so please tell me if I'm wrong.) *Userspace driver: Bypass whole kernel* *KNI driver: Bypass kernel network stack, but go through kernel driver* Keunhong. 2015-06-29 9:55 GMT+09:00 Abhishek Verma : > Hi Keunhong, > > Thanks for the response. > > I was reading about KNI ( > http://dpdk.org/doc/guides/sample_app_ug/kernel_nic_interface.html), and > that seems to defeat the purpose of DPDK -- the whole point of using DPDK > was to bypass the kernel. Now, when i implement KNI, then packets emanating > from the DPDK get into the Linux kernel -- which is what i really wanted to > avoid. > > Now that i have tied my eth2 to use a dpdk driver, then does it mean that > any packet arriving on that NIC will directly come to my user space > callback? Its like a raw socket -- so i will get all incoming packets with > all payloads, and i will have to implement the IP stack in my user space > now so that i can deal with that packet. Is my understanding correct here? > > If Yes, then what is the need of KNI? Isnt that violating the whole reason > why we have DPDK? > > Thanks, Abhishek > > On Mon, Jun 29, 2015 at 5:46 AM, Keunhong Lee wrote: > >> DPDK's igb_uio driver does not generate 'netdev' interfaces, >> so you cannot see any interface via ifconfig. >> (However, they are registered as 'rte_eth_dev' in your DPDK application.) >> >> You'd better to use KNI drivers to have 'netdev' intefaces. >> >> Keunhong. >> >> >> 2015-06-29 8:51 GMT+09:00 Abhishek Verma : >> >>> Hi, >>> >>> I have three ethernet interfaces in my VirtualBox as shown below: >>> >>> root@VirtualBox:/home/akabra/dpdk/dpdk-2.0.0/tools# ifconfig >>> eth1 Link encap:Ethernet HWaddr 08:00:27:3f:34:56 >>> inet addr:192.168.0.123 Bcast:192.168.0.255 Mask:255.255.255.0 >>> inet6 addr: fe80::a00:27ff:fe3f:3456/64 Scope:Link >>> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 >>> RX packets:132 errors:0 dropped:0 overruns:0 frame:0 >>> TX packets:26 errors:0 dropped:0 overruns:0 carrier:0 >>> collisions:0 txqueuelen:1000 >>> RX bytes:20982 (20.9 KB) TX bytes:3724 (3.7 KB) >>> >>> eth2 Link encap:Ethernet HWaddr 08:00:27:f7:13:f5 >>> inet addr:1.1.1.1 Bcast:1.1.1.255 Mask:255.255.255.0 >>> inet6 addr: fe80::a00:27ff:fef7:13f5/64 Scope:Link >>> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 >>> RX packets:51932 errors:0 dropped:0 overruns:0 frame:0 >>> TX packets:660805 errors:0 dropped:0 overruns:0 carrier:0 >>> collisions:0 txqueuelen:1000 >>> RX bytes:32407739 (32.4 MB) TX bytes:1647410289 (1.6 GB) >>> >>> lo Link encap:Local Loopback >>> inet addr:127.0.0.1 Mask:255.0.0.0 >>> inet6 addr: ::1/128 Scope:Host >>> UP LOOPBACK RUNNING MTU:65536 Metric:1 >>> RX packets:1681 errors:0 dropped:0 overruns:0 frame:0 >>> TX packets:1681 errors:0 dropped:0 overruns:0 carrier:0 >>> collisions:0 txqueuelen:0 >>> RX bytes:358901 (358.9 KB) TX bytes:358901 (358.9 KB) >>> >>> root@manav-VirtualBox:/home/globus/dpdk/dpdk-2.0.0/tools# >>> ./dpdk_nic_bind.py --status >>> >>> >>> >>> Network devices using DPDK-compatible driver >>> >>> ============================================ >>> >>> >>> >>> Network devices using kernel driver >>> >>> =================================== >>> >>> 0000:00:03.0 '82540EM Gigabit Ethernet Controller' if=eth1 drv=e1000 >>> unused=igb_uio,vfio-pci *Active* >>> >>> 0000:00:08.0 '82540EM Gigabit Ethernet Controller' if=eth2 drv=e1000 >>> unused=igb_uio,vfio-pci *Active* >>> >>> >>> I will now add eth2 to DPDK >>> >>> root@manav-VirtualBox:/home/globus/dpdk/dpdk-2.0.0/tools# sudo ifconfig >>> eth2 down >>> >>> root@manav-VirtualBox:/home/globus/dpdk/dpdk-2.0.0/tools# >>> ./dpdk_nic_bind.py -b igb_uio 0000:00:08.0 >>> >>> >>> I now see that eth2 has been removed from my ifconfig output. I cant seem >>> to understand why this has happened? >>> >>> >>> root@manav-VirtualBox:/home/globus/dpdk/dpdk-2.0.0/tools# ifconfig >>> >>> eth1 Link encap:Ethernet HWaddr 08:00:27:3f:34:56 >>> >>> inet addr:192.168.0.123 Bcast:192.168.0.255 >>> Mask:255.255.255.0 >>> >>> inet6 addr: fe80::a00:27ff:fe3f:3456/64 Scope:Link >>> >>> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1 >>> >>> RX packets:182 errors:0 dropped:0 overruns:0 frame:0 >>> >>> TX packets:86 errors:0 dropped:0 overruns:0 carrier:0 >>> >>> collisions:0 txqueuelen:1000 >>> >>> RX bytes:27757 (27.7 KB) TX bytes:12789 (12.7 KB) >>> >>> >>> >>> lo Link encap:Local Loopback >>> >>> inet addr:127.0.0.1 Mask:255.0.0.0 >>> >>> inet6 addr: ::1/128 Scope:Host >>> >>> UP LOOPBACK RUNNING MTU:65536 Metric:1 >>> >>> RX packets:1705 errors:0 dropped:0 overruns:0 frame:0 >>> >>> TX packets:1705 errors:0 dropped:0 overruns:0 carrier:0 >>> >>> collisions:0 txqueuelen:0 >>> >>> RX bytes:360948 (360.9 KB) TX bytes:360948 (360.9 KB) >>> >>> >>> I see that it has been successfully recognized as an interface using DPDK >>> driver, but why dont i see it in my ifconfig. Any ideas here? >>> >>> >>> root@manav-VirtualBox:/home/globus/dpdk/dpdk-2.0.0/tools# >>> ./dpdk_nic_bind.py --status >>> >>> >>> >>> Network devices using DPDK-compatible driver >>> >>> ============================================ >>> >>> 0000:00:08.0 '82540EM Gigabit Ethernet Controller' drv=igb_uio >>> unused=vfio-pci >>> >>> >>> >>> Network devices using kernel driver >>> >>> =================================== >>> >>> 0000:00:03.0 '82540EM Gigabit Ethernet Controller' if=eth1 drv=e1000 >>> unused=igb_uio,vfio-pci *Active* >>> >>> >>> >>> Other network devices >>> >>> >>> Would appreciate some help here. >>> >>> >>> Thanks, Abhishek >>> >> >> >