Re: [Nfvrg] results of virtual IMS and virtual SBC testing using COTS hardware. Thanks.
"B. Khasnabish" <vumip1@gmail.com> Tue, 15 December 2015 22:09 UTC
Return-Path: <vumip1@gmail.com>
X-Original-To: nfvrg@ietfa.amsl.com
Delivered-To: nfvrg@ietfa.amsl.com
Received: from localhost (ietfa.amsl.com [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 9DDE71B2BD3 for <nfvrg@ietfa.amsl.com>; Tue, 15 Dec 2015 14:09:49 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.627
X-Spam-Level:
X-Spam-Status: No, score=-0.627 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, FREEMAIL_ENVFROM_END_DIGIT=0.25, FREEMAIL_FROM=0.001, HTML_MESSAGE=0.001, SPF_PASS=-0.001, URI_HEX=1.122] autolearn=no
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id lfwjRmH_HpPh for <nfvrg@ietfa.amsl.com>; Tue, 15 Dec 2015 14:09:44 -0800 (PST)
Received: from mail-lf0-x22b.google.com (mail-lf0-x22b.google.com [IPv6:2a00:1450:4010:c07::22b]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 097011B2BBD for <nfvrg@irtf.org>; Tue, 15 Dec 2015 14:09:43 -0800 (PST)
Received: by mail-lf0-x22b.google.com with SMTP id z124so12052409lfa.3 for <nfvrg@irtf.org>; Tue, 15 Dec 2015 14:09:42 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; bh=PjqpKe75BO3pQX5tQ4NZxxi5Ph3xMXeFx4xUTiqJ4qg=; b=GdLSSkJHnlutxBD0BdKDwR8PgomlzRI+9tV6nYr673kiHQt/O13hPKxJp5it9tL1ET BTcXcPoSSxeNbSxJseh+Q9CkpgpXsOO9XVTCM6LcFBdhIP3UQ/jGHxNDFg4EchEk0F24 tH5+aWNsINJSGi10dXAoUqC7+SU/3KYFL+uTWRy2VxM4q0omMotn7ByJWAiM0xdab2sp ZwFiMxkjzZzeGzthk+MHCcPLtRmrTD1ianwY3WqMG1qvGymjRgLoXkM8k7pnq8bxh/P1 FgXcuUb9xoQJBwCPh3Kn6mCioqDec8D5e45mKINSA4inrDzUaSEljwsJgfPSaDzSrEfY CUuw==
X-Received: by 10.25.29.202 with SMTP id d193mr13991930lfd.55.1450217381142; Tue, 15 Dec 2015 14:09:41 -0800 (PST)
MIME-Version: 1.0
Received: by 10.25.209.71 with HTTP; Tue, 15 Dec 2015 14:09:01 -0800 (PST)
In-Reply-To: <5F6D7C0D-C976-4E6E-A36F-2619BE31D602@telefonica.com>
References: <CANtnpwicbtMPe49ceYj0+MSC8VsWWmoFg6HNXXwUfHu-Fk8TRg@mail.gmail.com> <5F6D7C0D-C976-4E6E-A36F-2619BE31D602@telefonica.com>
From: "B. Khasnabish" <vumip1@gmail.com>
Date: Tue, 15 Dec 2015 17:09:01 -0500
Message-ID: <CANtnpwi2O=7qYNJit_ZS3KzP59cGutgYPAbhs0TMptfBc1Tf8g@mail.gmail.com>
To: DIEGO LOPEZ GARCIA <diego.r.lopez@telefonica.com>
Content-Type: multipart/alternative; boundary="001a114013a8d9a7650526f70bc1"
Archived-At: <http://mailarchive.ietf.org/arch/msg/nfvrg/ow6MxGBeXJttCxSq-AaWP-QOTr4>
Cc: "nfvrg@irtf.org" <nfvrg@irtf.org>
Subject: Re: [Nfvrg] results of virtual IMS and virtual SBC testing using COTS hardware. Thanks.
X-BeenThere: nfvrg@irtf.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: "Network Function Virtualization Research Group \(NFVRG\) discussion list" <nfvrg.irtf.org>
List-Unsubscribe: <https://www.irtf.org/mailman/options/nfvrg>, <mailto:nfvrg-request@irtf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/nfvrg/>
List-Post: <mailto:nfvrg@irtf.org>
List-Help: <mailto:nfvrg-request@irtf.org?subject=help>
List-Subscribe: <https://www.irtf.org/mailman/listinfo/nfvrg>, <mailto:nfvrg-request@irtf.org?subject=subscribe>
X-List-Received-Date: Tue, 15 Dec 2015 22:09:49 -0000
Hi Diego, Sure, no problem, and we understand. Thanks a lot. Best. Bhumip On Tue, Dec 15, 2015 at 2:01 PM, DIEGO LOPEZ GARCIA < diego.r.lopez@telefonica.com> wrote: > Hi Bhumip, > > As NFVRG chair I’d like to request you to refrain from sending this kind > of press releases through the NFVRG list. I hope that you’ll agree with me > that this kind of communications is not relevant to the work of the group > and follows a commercial style that is far from the open discussion on > research and technical matters that is the goal of the NFVRG. > > Thanks for your understanding. > > Be goode, > > On 15 Dec 2015, at 12:35 , B. Khasnabish <vumip1@gmail.com> wrote: > > > ..... In the tests, the *vIMS *& *vSBC *Cloud UniCore solutions achieved > *high *Call Attempts Per Second(*CAPS*) capacity and throughput > with *excellent *Mean Opinion Score (*MOS*) on a Commercial > Off-The-Shelf (*COTS*) Intel-based server. > > (for more details, pls see below and at the following URL: > http://www.cn-c114.net/577/a931739.html) > > ==================================================== > Telefonica Successfully Completes ZTE vIMS and vSBC Performance Tests in > Madrid NFV Reference Lab > > Updated:2015/12/9 10:53 > > ZTE Corporation (0763.HK <http://0763.hk/> / 000063.SZ <http://000063.sz/>), > a major international provider of telecommunications, enterprise and > consumer technology solutions for the Mobile Internet, and Telefonica have > jointly tested ZTE vIMS & vSBC VNFs, part of ZTE’s Cloud UniCore portfolio, > in Telefonica’s NFV Reference Lab in Madrid, Spain. OpenMANO stack, the > ground-breaking module for the easy creation and deployment of complex > network scenarios of Telefonica’s NFV Reference Lab, was used to test ZTE’s > solutions. > > The objective of the tests was to benchmark the deployment and performance > of network functions virtualisation (NFV) solutions. The resulting data has > provided clear evidence of the performance range service providers can > expect from virtualised, software-based networking infrastructure. > > The establishment of NFV benchmarks is part of a joint effort by both > companies within the Telefonica NFV Reference Lab framework. ZTE’s > virtualised evolved packet core (vEPC) was previously tested in > Telefonica’s Reference Lab as part of this effort. > > Cloud UniCore is based on virtualisation technology with software and > hardware decoupling. Hardware resources are virtualised and various > applications can be deployed on the same virtualised hardware platform. > With the quick deployment capabilities of cloud computing, Cloud UniCore > shortens the configuration and provisioning process from several weeks to > several minutes, thus significantly enhancing agility of network expansion. > It also implements dynamic scalability of virtualised network functions to > eliminate capacity bottlenecks. > > The vIMS & vSBC Cloud UniCore solutions were deployed on a set of virtual > machines (VM) which takes advantage of Intel? Xeon? processor-based servers > and the Intel? Data Plane Development Kit in order to meet the performance > required by the world's largest telecommunication and service providers. > > In the tests, the vIMS & vSBC Cloud UniCore solutions achieved high Call > Attempts Per Second(CAPS)capacity and throughput with excellent Mean > Opinion Score(MOS)on a Commercial Off-The-Shelf (COTS) Intel?-based server. > > The results delivered were outstanding, reaching Telefonica’s expected > performance levels and smooth deployment objectives which allowed the test > to be completed in a very short amount of time. ZTE and Telefonica will > continue testing other elements of ZTE’s NFV portfolio in the coming months. > > Javier Gavilán, Planning and Technology Director at Telefonica- Global CTO > said: “Telefonica has been and will be quite active on the evolution of > network virtualisation technologies. With our NFV Reference Lab we aim to > help the ecosystem of partners and network equipment vendors to test and > develop virtualised network functions, so we are very pleased to > collaborate with ZTE, a reference partner in NFV.” > > Antonio Elizondo, Head of Network Virtualisation Strategy at Telefonica > I+D-Global CTO said: “The performance of ZTE vIMS & vSBC Cloud UniCore > solutions is quite high and aligned with our expectations on a > well-designed VNF, as it is needed for its deployment in the commercial > network. We’re looking forward to continuing our work with ZTE, and > strengthening our collaboration in the NFV field.” > > ZTE is committed to the development of NFV and cloud-based network > technologies, cooperating with operators and technology providers around > the world in proof of concept (PoC) projects. To date, ZTE’s virtualised > core network solutions are deployed in 5 commercial, and 28 trial projects > globally. > Source:C114 > ==================================================== > > On Wed, Dec 2, 2015 at 11:03 AM, B. Khasnabish <vumip1@gmail.com> wrote: > >> Dave, Diego, >> >> Many Thanks to both of you. >> >> We plan to address these comments/suggestions in a future version of this >> draft by >> >> (a) adding appropriate citations and reasons behind the assumptions , >> >> (b) adopting a consistent definition, >> >> (c) exploring further the categories of COTS which are more suitable for >> reliable services >> >> (d) discussing any add-on features of COTS that may make certain COTS >> hardware more suitable for reliable services than others >> >> (e) clearly mentioning the functions being simulated, and >> >> (f) exploring how the concept of silent error can be applied to both >> hardware and software. >> >> Once again, many thanks, and we looking forward to other suggestions and >> comments. >> >> Best. >> >> Bhumip >> >> >> Best. >> >> >> >> On Tue, Dec 1, 2015 at 12:36 PM, DIEGO LOPEZ GARCIA < >> diego.r.lopez@telefonica.com> wrote: >> >>> Hi, >>> >>> <unchair_mode> >>> >>> Just to express my support to all of Dave´s comments, and especially to >>> the suspicion you express as conclusion. I see a great value in this draft >>> from the point of view of strategies to achieve system-wide five-nines (or >>> even beyond), and don’t see the need to confront COTS vs special-purpose >>> telecom hardware. >>> >>> </unchair_mode> >>> >>> Be goode, >>> >>> On 1 Dec 2015, at 18:05 , Dave Dolson <ddolson@sandvine.com> wrote: >>> >>> Some comments: >>> >>> 1. In the draft there is a premise that software errors on COTS hardware >>> are different from hardware/software errors on dedicated telecom equipment. >>> Obviously there could be silent hardware and software errors on any type of >>> device. If you are going to have this premise, I think there needs to be >>> some evidence, citation or explanation. In my career I have seen some >>> pretty nasty hardware defects. Some were fatal but some were silent. One >>> could claim that functional hardware flaws are *less* likely in COTS >>> hardware, based on wide adoption and wide testing base. And both types of >>> systems are largely controlled by software. >>> >>> 2. You state COTS machines have relaxed design criteria. Obviously this >>> is a huge generalization, not supported by any citations. Certainly there >>> are also custom hardware solutions with relaxed design criteria. I think >>> you need to be specific by referring to specific designs. E.g., RAM with >>> error correction? Dual power supplies? RAID disks? And in that case, you >>> should discuss hardware with or without such features, not “COTS vs. >>> traditional”. >>> >>> 3. Some of the language in the draft is derogatory or dismissive of COTS >>> equipment. I think you should avoid such language to be respectful of >>> different designs. (use of “cowboy manner”, “COTS hardware and all its >>> undesirable features”, “the COTS hardware and its related software are >>> notorious” …) Don’t treat the COTS systems as poorly designed; rather see >>> the design goals as different. >>> >>> 4. On the subject of five-9s, clearly the NFV approach is to create >>> five-9s at the *system* level vs. the level of the individual box. Can you >>> consistently adopt that definition? For example, it is confusing near the >>> end of section 5 when you say “the requirements for traditional five 9s >>> could be relaxed while keeping the same user experience in downtime.” Above >>> that you say “with only two 9s server availability, the five 9s server part >>> of system availability can be achieved,” which I think is a more useful >>> statement. >>> >>> 5. I think it would be helpful if you explained the function of the >>> system being simulated. It seems like it is a database replicated on >>> several servers? >>> >>> My suspicion is that juxtaposing COTS vs. traditional telecom in this >>> draft is distracting from the value of your research. The silent error idea >>> could be applied to any type of hardware. >>> >>> >>> Sorry, but I’m not comfortable commenting on your theoretical analysis >>> or simulation. Yes, I know that's the main point of the work... But as seen >>> above, I find the assumptions about COTS vs. traditional telecom hardware >>> to undermine any conclusions. >>> >>> >>> -Dave >>> >>> >>> >>> From: Nfvrg [mailto:nfvrg-bounces@irtf.org <nfvrg-bounces@irtf.org>] On >>> Behalf Of B. Khasnabish >>> Sent: Saturday, October 17, 2015 8:24 PM >>> To: nfvrg@irtf.org >>> Subject: [Nfvrg] Requesting review of and comments on >>> draft-mlk-nfvrg-nfv-reliability-using-co >>> >>> Dear All, >>> We have recently published a draft >>> (datatracker.ietf.org/doc/draft-mlk-nfvrg-nfv-reliability-using-cots/) >>> on >>> "NFV Reliability using COTS Hardware" discussing the results of a recent >>> study on the feasibility of using Commercial Off-The-Shelf (COTS) hardware >>> for virtualized network functions in telecom equipment. >>> This draft is based on the presentation >>> (https://www.ietf.org/proceedings/92/slides/slides-92-nfvrg-9.pdf) >>> during IETF/IRTF-92 mtg. in Dallas, TX, USA on >>> the 26th of March 2015. This draft attempts to address the work item >>> no. 4 in the charter (http://datatracker.ietf.org/rg/nfvrg/charter/) >>> >>> ------------------------------------------------------------------------------- >>> 4. Service Verification with Regards to Security and Resiliency >>> Reliability and security issues and relevant solutions related to the >>> nature of VNFs are the objectives of this work item. >>> >>> ---------------------------------------------------------------------------------- >>> We are requesting your review of this draft and comments on it >>> so that we can update the draft ASAP. >>> Many thanks in advance for your kind attention. >>> Best. >>> Bhumip >>> ===================================================== >>> _______________________________________________ >>> Nfvrg mailing list >>> Nfvrg@irtf.org >>> https://www.irtf.org/mailman/listinfo/nfvrg >>> >>> >>> -- >>> "Esta vez no fallaremos, Doctor Infierno" >>> >>> Dr Diego R. Lopez >>> Telefonica I+D >>> http://people.tid.es/diego.lopez/ >>> >>> e-mail: diego.r.lopez@telefonica.com >>> Tel: +34 913 129 041 >>> Mobile: +34 682 051 091 >>> ---------------------------------- >>> >>> >>> ------------------------------ >>> >>> Este mensaje y sus adjuntos se dirigen exclusivamente a su destinatario, >>> puede contener información privilegiada o confidencial y es para uso >>> exclusivo de la persona o entidad de destino. Si no es usted. el >>> destinatario indicado, queda notificado de que la lectura, utilización, >>> divulgación y/o copia sin autorización puede estar prohibida en virtud de >>> la legislación vigente. Si ha recibido este mensaje por error, le rogamos >>> que nos lo comunique inmediatamente por esta misma vía y proceda a su >>> destrucción. >>> >>> The information contained in this transmission is privileged and >>> confidential information intended only for the use of the individual or >>> entity named above. If the reader of this message is not the intended >>> recipient, you are hereby notified that any dissemination, distribution or >>> copying of this communication is strictly prohibited. If you have received >>> this transmission in error, do not read it. Please immediately reply to the >>> sender that you have received this communication in error and then delete >>> it. >>> >>> Esta mensagem e seus anexos se dirigem exclusivamente ao seu >>> destinatário, pode conter informação privilegiada ou confidencial e é para >>> uso exclusivo da pessoa ou entidade de destino. Se não é vossa senhoria o >>> destinatário indicado, fica notificado de que a leitura, utilização, >>> divulgação e/ou cópia sem autorização pode estar proibida em virtude da >>> legislação vigente. Se recebeu esta mensagem por erro, rogamos-lhe que nos >>> o comunique imediatamente por esta mesma via e proceda a sua destruição >>> >> >> > > -- > "Esta vez no fallaremos, Doctor Infierno" > > Dr Diego R. Lopez > Telefonica I+D > http://people.tid.es/diego.lopez/ > > e-mail: diego.r.lopez@telefonica.com > Tel: +34 913 129 041 > Mobile: +34 682 051 091 > ---------------------------------- > > > ------------------------------ > > Este mensaje y sus adjuntos se dirigen exclusivamente a su destinatario, > puede contener información privilegiada o confidencial y es para uso > exclusivo de la persona o entidad de destino. Si no es usted. el > destinatario indicado, queda notificado de que la lectura, utilización, > divulgación y/o copia sin autorización puede estar prohibida en virtud de > la legislación vigente. Si ha recibido este mensaje por error, le rogamos > que nos lo comunique inmediatamente por esta misma vía y proceda a su > destrucción. > > The information contained in this transmission is privileged and > confidential information intended only for the use of the individual or > entity named above. If the reader of this message is not the intended > recipient, you are hereby notified that any dissemination, distribution or > copying of this communication is strictly prohibited. If you have received > this transmission in error, do not read it. Please immediately reply to the > sender that you have received this communication in error and then delete > it. > > Esta mensagem e seus anexos se dirigem exclusivamente ao seu destinatário, > pode conter informação privilegiada ou confidencial e é para uso exclusivo > da pessoa ou entidade de destino. Se não é vossa senhoria o destinatário > indicado, fica notificado de que a leitura, utilização, divulgação e/ou > cópia sem autorização pode estar proibida em virtude da legislação vigente. > Se recebeu esta mensagem por erro, rogamos-lhe que nos o comunique > imediatamente por esta mesma via e proceda a sua destruição >
- [Nfvrg] Fwd: results of virtual IMS and virtual S… B. Khasnabish
- Re: [Nfvrg] results of virtual IMS and virtual SB… DIEGO LOPEZ GARCIA
- Re: [Nfvrg] results of virtual IMS and virtual SB… ANTONIO JOSE ELIZONDO ARMENGOL
- Re: [Nfvrg] results of virtual IMS and virtual SB… B. Khasnabish
- Re: [Nfvrg] results of virtual IMS and virtual SB… B. Khasnabish