From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id AE4858E7E for ; Mon, 19 Oct 2015 11:32:53 +0200 (CEST) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by fmsmga102.fm.intel.com with ESMTP; 19 Oct 2015 02:32:52 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.17,701,1437462000"; d="scan'208";a="829866171" Received: from irsmsx105.ger.corp.intel.com ([163.33.3.28]) by orsmga002.jf.intel.com with ESMTP; 19 Oct 2015 02:32:51 -0700 Received: from irsmsx106.ger.corp.intel.com ([169.254.8.229]) by irsmsx105.ger.corp.intel.com ([169.254.7.75]) with mapi id 14.03.0248.002; Mon, 19 Oct 2015 10:32:50 +0100 From: "Loftus, Ciara" To: Tetsuya Mukawa , "Richardson, Bruce" Thread-Topic: [dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD Thread-Index: AQHQ46EZDQst5vy2d0C0oFzvXGhqQZ5uSx8AgAP+EACAAI3P8A== Date: Mon, 19 Oct 2015 09:32:50 +0000 Message-ID: <74F120C019F4A64C9B78E802F6AD4CC24F7A881E@IRSMSX106.ger.corp.intel.com> References: <1440993326-21205-1-git-send-email-mukawa@igel.co.jp> <1440993326-21205-2-git-send-email-mukawa@igel.co.jp> <20151016125254.GA9980@bricha3-MOBL3> <56244C84.4090309@igel.co.jp> In-Reply-To: <56244C84.4090309@igel.co.jp> Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" , "ann.zhuangyanying@huawei.com" Subject: Re: [dpdk-dev] [RFC PATCH v2] vhost: Add VHOST PMD 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, 19 Oct 2015 09:32:54 -0000 > On 2015/10/16 21:52, Bruce Richardson wrote: > > On Mon, Aug 31, 2015 at 12:55:26PM +0900, Tetsuya Mukawa wrote: > >> The patch introduces a new PMD. This PMD is implemented as thin > wrapper > >> of librte_vhost. It means librte_vhost is also needed to compile the P= MD. > >> The PMD can have 'iface' parameter like below to specify a path to > connect > >> to a virtio-net device. > >> > >> $ ./testpmd -c f -n 4 --vdev 'eth_vhost0,iface=3D/tmp/sock0' -- -i > >> > >> To connect above testpmd, here is qemu command example. > >> > >> $ qemu-system-x86_64 \ > >> > >> -chardev socket,id=3Dchr0,path=3D/tmp/sock0 \ > >> -netdev vhost-user,id=3Dnet0,chardev=3Dchr0,vhostforce \ > >> -device virtio-net-pci,netdev=3Dnet0 > >> > >> Signed-off-by: Tetsuya Mukawa > > With this PMD in place, is there any need to keep the existing vhost li= brary > > around as a separate entity? Can the existing library be > subsumed/converted into > > a standard PMD? > > > > /Bruce >=20 > Hi Bruce, >=20 > I concern about whether the PMD has all features of librte_vhost, > because librte_vhost provides more features and freedom than ethdev API > provides. > In some cases, user needs to choose limited implementation without > librte_vhost. > I am going to eliminate such cases while implementing the PMD. > But I don't have strong belief that we can remove librte_vhost now. >=20 > So how about keeping current separation in next DPDK? > I guess people will try to replace librte_vhost to vhost PMD, because > apparently using ethdev APIs will be useful in many cases. > And we will get feedbacks like "vhost PMD needs to support like this usag= e". > (Or we will not have feedbacks, but it's also OK.) > Then, we will be able to merge librte_vhost and vhost PMD. I agree with the above. One the concerns I had when reviewing the patch was= that the PMD removes some freedom that is available with the library. Eg. = Ability to implement the new_device and destroy_device callbacks. If using = the PMD you are constrained to the implementations of these in the PMD driv= er, but if using librte_vhost, you can implement your own with whatever fun= ctionality you like - a good example of this can be seen in the vhost sampl= e app. On the other hand, the PMD is useful in that it removes a lot of complexity= for the user and may work for some more general use cases. So I would be i= n favour of having both options available too. Ciara >=20 > Thanks, > Tetsuya