Linux Foundation Announces Major Network Functions Virtualization Project

← Back to Stories (view on slashdot.org)

Linux Foundation Announces Major Network Functions Virtualization Project

Posted by Soulskill on Tuesday September 30, 2014 @07:35AM from the building-future-tech dept.

Andy Updegrove writes: The Linux Foundation this morning announced the latest addition to its family of major hosted open source initiatives: the Open Platform for NFV Project (OPNFV). Its mission is to develop and maintain a carrier-grade, integrated, open source reference platform for the telecom industry. Importantly, the thirty-eight founding members include not only cloud and service infrastructure vendors, but telecom service providers, developers and end users as well. The announcement of OPNFV highlights three of the most significant trends in IT: virtualization (the NFV part of the name refers to network function virtualization), moving software and services to the cloud, and collaboratively developing complex open source platforms in order to accelerate deployment of new business models while enabling interoperability across a wide range of products and services. The project is also significant for reflecting a growing recognition that open source projects need to incorporate open standards planning into their work programs from the beginning, rather than as an afterthought.

40 comments

Min score:

Reason:

Sort:

Businessese Bingo by Art3x · 2014-09-30 07:37 · Score: 5, Funny

collaboratively developing complex open source platforms in order to accelerate deployment of new business models while enabling interoperability across a wide range of products and services
Bingo!
1. Re:Businessese Bingo by jeffmeden · 2014-09-30 07:54 · Score: 1
  
  collaboratively developing complex open source platforms in order to accelerate deployment of new business models while enabling interoperability across a wide range of products and services
  Bingo!
  I was thinking the same thing. They basically came up with a "great" reason for a whole new standard. To hell with the old standard! Whoever invented that was obviously dumb!
2. Re:Businessese Bingo by i+kan+reed · 2014-09-30 07:54 · Score: 0
  
  Let's try a sanity reword and measure how much they added unnecessary(caveat: I'm prone to being overly verbose as well, and I won't do a great job)
  
  We make open source middleware
  Did I get it right?
3. Re:Businessese Bingo by Trepidity · 2014-09-30 07:57 · Score: 3, Funny
  
  * complex open source middleware
  * for the cloud
  
  --
  10 PRINT CHR$(205.5+RND(1)); : GOTO 10
4. Re:Businessese Bingo by i+kan+reed · 2014-09-30 08:16 · Score: 0
  
  That's the part before what the OP quoted. And all software is complex, or at least complex enough to have bugs.
5. Re:Businessese Bingo by Anonymous Coward · 2014-09-30 08:19 · Score: 1
  
  I follow this area from decently close, although I'mnot a contributor. A less-buzzwordy explanation is that the project is adapting current virtualization and middleware infrastructure to let telecom workloads (network elements) run in VMs. Broadly this means developing ways to reduce packet processing overheads, more efficient virtual switching, and controlling latency much more tightly than current mainstream solutions.
6. Re:Businessese Bingo by jeffmeden · 2014-09-30 08:39 · Score: 1
  
  all software is complex, or at least complex enough to have bugs.
  Your first Hello World didn't go so well, did it?
7. Re:Businessese Bingo by jeffmeden · 2014-09-30 08:43 · Score: 0
  
  I follow this area from decently close, although I'mnot a contributor. A less-buzzwordy explanation is that the project is adapting current virtualization and middleware infrastructure to let telecom workloads (network elements) run in VMs. Broadly this means developing ways to reduce packet processing overheads, more efficient virtual switching, and controlling latency much more tightly than current mainstream solutions.
  Maybe you can answer this then: What is a "Telecom workload" except perhaps a domestic spying node? Isn't the point of being a Telecom to just move the fucking packets? Why are we virtualizing that when at present, big dedicated routers are needed to do it properly? Are they seriously saying they want to get an even bigger machine, put a bunch of software in the middle that might increase reliability (but most likely just create a new, unknown single point of failure), and call it "improved"? Or, are they just trying to carve out new markets for virtualization now that all the easy ones have been bled dry?
8. Re:Businessese Bingo by deroby · 2014-09-30 08:44 · Score: 1
  
  I had to power-cycle my C= 64 ...
  
  --
  If there is one thing to be learned on slashdot, it has to be sarcasm.
9. Re:Businessese Bingo by i+kan+reed · 2014-09-30 09:12 · Score: 1
  
  That's not really software though, is it? Think about the "ware" part, in means a vendable item.
10. Re:Businessese Bingo by qpqp · 2014-09-30 09:49 · Score: 1
  
  So, an open software-defined networking (aka SDN) solution?
11. Re:Businessese Bingo by Anonymous Coward · 2014-09-30 10:20 · Score: 1
  
  I can answer that. A Telecom workload is one of the 12 systems in between two people talking on their cellphones. You're calling from the Sprint Network using an iPhone, you call a friend using Tmo and an old Motorola Cliq. A whole bunch of systems get involved when you press send and they have to:
  Check whether his number was ported out of area-code, and find out who owns it.
  Convert your i-voice codec to an appropriate standard for exchange with that carrier
  Tmo has to look him up to find his last registration on their network (HLR/VLRs etc)
  Tmo has to send out the paging signal get the request for a voice pipe (like a channel)
  Tmo has to connect it to a media gateway to convert Cliq-AMR to a codec compatible with the one Sprint picked
  Tmo has to tell the point of ingress to route your voice packtes to the same gateway.
  All these systems have to have very low processing and network latencies, or your call set up time will violate a standard and get dropped (or just get unbearably long).
  Currently keeping the latencies low enough pretty well demands these systems run "on the metal." Telcos would love to have the flexiblity you and I enjoy with the elacticity of virtual capacity.
12. Re:Businessese Bingo by jon3k · 2014-09-30 10:21 · Score: 1
  
  There's always a relevant XKCD.
13. Re:Businessese Bingo by ssufficool · 2014-09-30 13:47 · Score: 0
  
  Damn, you beat me to it. The take away from this is... you still have a shit ton of (re)programming to do to take advantage of this technology.
14. Re:Businessese Bingo by skids · 2014-09-30 14:18 · Score: 1
  
  No this is more reasonable than SDN. SDN pretends to be a road to virtualizing the capabilities of actual grunt-work networking equipment, without being arsed to actually be able to enumerate said capabilities and thus is doomed to never fully succeed. This, however, is for the higher level intelligence well suited to virtualization -- basically the stuff thateats all your RSPs' CPU.
  
  --
  Someone had to do it.
15. Re: Businessese Bingo by Anonymous Coward · 2014-09-30 16:31 · Score: 0
  
  Is anyone selling a perl hello world? The first ten I bought were unreadable.
16. Re:Businessese Bingo by brakarific · 2014-09-30 16:35 · Score: 3, Informative
  
  I happen to work as a field engineer for one of the bigger companies that is funding this project. I work pretty closely with our product management and software development group. There are massive network virtualization projects going on now with a couple of Tier 1 Carriers and Hosting companies. There are probably more projects that I'm unaware of. The Carriers and Hosting Companies aren't looking for new standards, they are just tired of buying a $20k - $150k router that can only ever be a router. That is a large capex risk that you can't recoup if you don't need it after a year or two. A x86 platform on the other hand is very low risk as it is the swiss army knife of data center expenditures. If you can place almost everything on x86 gear then your expense risk is pretty much nill.
  
  We all know that there is a reason ASICs have always been used for TCP/IP processing and not x86 procs. Up until about a year ago that fact still held true. That was until Intel developed a cool little piece of code called DPDK. Seriously, look into it if you want to know why x86 might actually be OK for simple L3/4 IP/TCP tasks such as routing/firewall/vpn etc. I know that today you can push 40gbps line speed L3 operations on COTS hardware on a single proc (8 cores) in a server. To buy a router today that can do the same will cost you around $25 - $30k. Switching operations that still require low latency and high port density will still need to be done on dedicated switches, but anything requiring brute horsepower for L3 forwarding at high throughput (not the same as latency) will be able to be done in virtual appliances now.
  
  While we are still a few years away from mass market enterprise virtual router/firewall parity to hardware, we will make it there. The is a boatload of money to be made any time there is a huge market disruption. There are only three companies that don't want this kind of disruption, namely Cisco, Juniper, and Huawei. Every other networking vendor is watering at the mouth at the very thought that they could steal money and market share from those three. There are huge amounts of money and talent working on this (Intel, VMWare, Red Hat, HP, Brocade, and many more). I know for a fact that Intel is going to invest massively in networking over the next few years. Sit tight and watch John Chambers writhe in his comfy leather chair. It's gonna be fun watching that company go the way of Blackberry.
17. Re:Businessese Bingo by Anonymous Coward · 2014-09-30 18:47 · Score: 0
  
  Gah. I had copied *exactly* the same sequence of words, preparing to complain that my buzzwordmeter had gone to 11 and broken its needle (analog model here, I'm an old fart, but perhaps I can cobble up something with an Arduino... but I disgress).
  Then I saw your post. There should be a tax on that.
18. Re:Businessese Bingo by qpqp · 2014-10-01 04:13 · Score: 1
  
  Should we call this SDN 2.0 then?
  'cause
  
  carrier-grade, integrated, open source reference platform [...] to advance the evolution of NFV and ensure consistency, performance and interoperability among multiple open source components
  Just doesn't sound as catchy.
yay, just like the old days by Anonymous Coward · 2014-09-30 07:40 · Score: 0

when all you had was a virtual network connection: sneakernet to the science building
The path ahead is pretty well laid out by donour · 2014-09-30 07:47 · Score: 1

... in Crossbow http://en.wikipedia.org/wiki/O...
Beware by TechyImmigrant · 2014-09-30 07:54 · Score: 2

The telecoms contributors will play dirty. I promise you.

--
I should use this sig to advertise my book ISBN-13 : 978-1501515132.
1. Re:Beware by kloro2006 · 2014-09-30 08:28 · Score: 1
  
  the strength of linux is the people who maintain it and keep it secure. i doubt if we will continue our support if linux becomes mainly a tool for capitalist profits.
  
  the free software community came to be because tech heads cdn't get the tools they needed on small machines using proprietary OS. this is the core of FS strength. f*ck with that and we will go away.
2. Re:Beware by Anonymous Coward · 2014-09-30 08:39 · Score: 0
  
  you probably haven't heard of systemd yet, have you? :) it's open source and it's dirty bloated and crap.
  Linux as we know it will be no more soon.
  And guess what, those great open source developers are of the past... now people are after money, and nobody
  has the will to fork and maintain udef... nor they can properly fix bash.
3. Re:Beware by TechyImmigrant · 2014-09-30 09:21 · Score: 1
  
  The telecoms would add X25d with ASN.1 line coding to systemd if they could get away with it.
  
  --
  I should use this sig to advertise my book ISBN-13 : 978-1501515132.
4. Re:Beware by Xipher · 2014-09-30 09:46 · Score: 1
  
  The telecoms are looking for cheaper implementations for shit they already have to deploy. They want to piggy back on everyone else's work, so they don't have to spend so much money.
  
  --
  I don't know everything.
5. Re:Beware by Anonymous Coward · 2014-09-30 11:10 · Score: 0
  
  hint: "those great open source developers" use BSD systems, which haven't sold out.
6. Re:Beware by TechyImmigrant · 2014-09-30 12:36 · Score: 1
  
  They will try to put CALEA crap in by default with no option to turn off.
  
  --
  I should use this sig to advertise my book ISBN-13 : 978-1501515132.
But can anyone tell it is a major project? by Anonymous Coward · 2014-09-30 07:55 · Score: 0

Who prey?
OpenDaylight? by Anonymous Coward · 2014-09-30 08:17 · Score: 0

So is this a replacement for OpenDaylight? Another Linux Foundation project?
Security Is A Network Function by Anonymous Coward · 2014-09-30 08:51 · Score: 0

I guess security in the network has already been "virtualized" so instead of buzzword bingo maybe we should play Whack-A-Mole instead.
horrible VM latency by fredness · 2014-09-30 09:30 · Score: 2

Translation: VM's are cheap and flexible, but have horrible packet latency
Solution: don't use a VM
Move along, nothing to see here, yawn.
1. Re:horrible VM latency by blue9steel · 2014-09-30 09:44 · Score: 1
  
  Capitalist solution: Deploy VMs for non-priority traffic, charge extra for "fast lane" hardware routers.
Re:Businessese Bingo and Telecom Workloads by billstewart · 2014-09-30 10:48 · Score: 2

No, the point of being a telecom company is to connect your customers together, move their data where they want it efficiently, and get them to pay you for it. Telecom workloads not only include digging ditches for your access line and running wavelength division multiplexors across them, they also include things like routing IPv4/IPv6, firewalls, load balancing, intrusion detection, preventing and mitigating DDOS, hosting CDNs, routing lots of private networks that all run RFC1918 addresses and maybe VLANs, MPLS, maintaining really large BGP tables, fast rerouting around failures, etc.
We're virtualizing that stuff instead of buying big expensive custom-built routers for the same reasons you're virtualizing your compute loads instead of stacking up lots of 1U machines. Internet-scale routers are blazingly expensive, and we want to use Moore's Law to do the compute-bound parts of the workload cheaply and efficiently and let us build new services quickly because we only have to upgrade the software, while using expensive custom hardware only for the things that really need it, plus a lot of that hardware is getting replaced by things like Openflow switches and SDN, which we'd like to take advantage of, and buying expensive dedicated-purpose hardware means you're often stuck overbuilding because the scale of your different types of workloads changes faster than you can redesign hardware.
Also, the transition of lots of enterprise corporate computing from traditional data center structures to clouds means that the communication patterns change a lot faster, and we need to keep up with them. This stuff does seem to be driven a lot more by the needs of the users (telecom and data center) than by the manufacturers of virtualization software or traditional hardware.
And yes, every bit of business buzzword bingo does flow across our desks.

--

Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Crossbow for Linux by Anonymous Coward · 2014-09-30 12:39 · Score: 1

Would be just fantastic, but for the love of god please don't let poettering anywhere near this
Re:Businessese Bingo and Telecom Workloads by snowsnoot · 2014-09-30 13:03 · Score: 1

Sorry but this is never gonna work for real IP moving workloads unless the hardware evolves to support fast switching as efficiently as a Juni MX or a Cisco CRS. I agree it applies to core support nodes involved in signalling (HSS/HLR/MSC/CSCF etc) but that's something we can potentially do today, not something that requires a whole project to rework the standards to achieve. The problem today is that most of the vendors won't sell you the software without the hardware anyway. Probably what's going to happen is this thing will still end up running on their hardware and you pay for the privilege, just look at Ericsson Blade System which is basically their own virtualized platform that runs on OpenStack. I dont see them releasing CUDB's or HSS's or CSCF's that can run on RedHat and VMWare, but it's something that would work well for me if it were available.
Those who do not understand ASN1 by Anonymous Coward · 2014-09-30 13:22 · Score: 0

Are doomed to re-invent it.
1. Re:Those who do not understand ASN1 by TechyImmigrant · 2014-10-01 05:05 · Score: 1
  
  I have lived the ASN.1 horror. I will kill it. I will show no mercy. Know this, for it is true.
  
  --
  I should use this sig to advertise my book ISBN-13 : 978-1501515132.