Response: NFV: Will vRouters ever replace hardware routers?

21st May 2014 by Greg Ferro

I’m not the only person pointing out the software routers are reaching unprecedented performance levels. Manav Bhatia starts out with

When i started looking at NFV, i always imagined it being relegated to places in the network that would receive only teeny weeny amount of data traffic since the commodity hardware and software could only handle so much of traffic. I also naively believed that it would be deployed in networks where customers were not uber-sensitive to latency and delay (broadband customers, etc). So if somebody really wanted a loud bang for their buck they had to use specialized hardware to support the network function. You couldnt really use Intel x86-based servers running SW serving customers for whom QoS and QoE were critical and vital.

This opinion is quite common among network engineers but is completely wrong. If you had time to understand what Intel is doing to their processors to be networking friendly you will come to the same conclusion as Manav:

What this shows is that its patently possible for virtual routers to run at speeds comparable to regular hardware based routers and can replace them. This augurs well for NFV since it means that it can be deployed in a lot many places in the carrier network than what most skeptics believed till some time back.

NFV: Will vRouters ever replace hardware routers? | Routing Freak!.

There are many caveats on software based routers. Now that straight line performance has been addressed and acceptably proven at greater than 10gbps, it’s time to consider other functions that might impact performance like Hierarchical QoS or VXLAN/GRE tunneling.

But hey, not many routers actually implement those features in the bigger scheme of things.

The Cost of Software Licensing in Networking – Is the Price Worth It ?

28th April 2014 by Greg Ferro

I’ve been evaluating Cisco Nexus products for a customer. So far, its taken more than 10 hours to check which product licenses are required for each platform. And I’m still not confident that I’ve got it correct and accurate. The licenses are convoluted and I’m really worried that I’ll pick a license and miss the features that I need.

So I checked with the reseller engineer and he doesn’t know either, “that is more of a sales thing” he said. The inside sales person said “I’ll need to the engineer to advise me on that”.

FACEPALM

I once worked on a project with staff from Cisco Professional Services where it took 3 days to build and validate the bill of materials – specifically on the software licensing required for some Nexus switches. At the standard rate of USD$3000 per day for Cisco PS plus my agency day rate at $1500/day, that bill of materials cost the client $13,500. Total vendor purchase was approx. $200,000.

Some time ago, I met with a company that has networking licensing team. These people have a full-time position managing the licensing of network software. Not hardware, just software, feature licenses, maintenance programs. So operating a network means we will soon have licensing professionals ? Microsoft has a certification for “Volume Licensing Specialist” to manage the complexity of administration. That’s ridiculous.

I last ranted about Cisco licensing in September 2012 Rant: Cisco claims “We’re Listening” to Simplifying Cisco Software Licensing – EtherealMind. Two years later and not much has changed.

While I’m wasting time reading manuals about licensing, I’m not working on an SDN Strategy or adding value to the network. That expensive network equipment with a shedload of useful features isn’t returning the investment I promised.

The CIO and project managers complain about long lead times, knows that this isn’t getting value from the investment. We all feel helpless in the face of vendor business models because we just wants to get the job done and improve the network.

There is no right answer here. But the cost of selecting software licenses is getting to be more than the licenses. That’s ridiculous.

Brocade Vyatta & Forwarding Performance on X86 Server

15th April 2014 by Greg Ferro

It’s a constant and oft-repeated fallacy that routing software on x86 servers will never forward packets at speed. Here is Vyatta explaining why their software will be able to go past 100 Million Packets Per Second this year on standard COTS hardware.

At Network Field Day 7, we saw a presentation from Brocade on their Vyatta software code and the recent advances in software architecture that can linearly scale the forwarding performance of x86 architectures according to the number of CPUs. The following slide shows that the limitations previously flatlined due to cache misses.

Slide from Vyatta Presentation showing forwarding performance exceeding 100Mpps. (click to embiggen).

In the Youtube video, Kelly Herrell briefly introduces the performance data and then hands over to the technology guy who explains in quite some details how Vyatta is exploiting the full potential of the Intel architecture.

Click here to Youtube and the video will start directly at the 19:09 mark where the real kicker comes in .

Server Performance, Network Agents, Software Routers and Networking

29th December 2013 by Greg Ferro

Steven emailed me with the following:

Just curious, I’ve been reading many articles and you seem to contradict conclusions between articles. One article you tout the benefit of Network Agents running on hypervisor and using the power of the CPU for tunnels, in another article you dislike this model because of scalability issues (more cpu load = slower network packet processing).

Just curious if you’ve changed your mind after many bad experiences or if you’re suggesting a lighter weight agent would be better in some cases than a vSwitch type module.

I don’t think software switches on shared resources will ever scale to something that dedicated silicon can deliver such as the ASR1000 with a 40-core Quantum Flow CPU.

These are good points. I started to write back and it turned into this post.

Originally

Originally I was of the opinion that hardware server and general purpose software such as VMware ESX, MS Windows or Linux KVM would not be able to handle the packet processing load for encapsulation and packet handling. I’ve used and tested software routing on Linux in the past but realised it was relatively slow, clunky and hard to justify. And, of course, ITIL prevents networking engineers from using servers to deliver network services.

However, I’ve seen information from Intel roadmaps that clearly shows that current generations of server hardware can easily handle 10Gbps of traffic and probably more than 40Gbps with just a single CPU Core. Recent server CPUs and motherboards typically have 8 to 16. While it requires some co-operation with intel to use the correct network drivers and software but this is already underway with a number of vendors.

When you dig deeper, it is clear that intel is investing heavily in technology that improves the network performance to attract network appliance manufacturers to their hardware. Faster buses, new memory architectures, DMA access from NIC to memory and CPU avoidance for certain network operations. In addition, Intel purchased Fulcrum Micro (network silicon manufacturer) a few years back and this technology is on the roadmap to be added to server motherboards. Think about what that means, network technology inside the CPU or support chips.

In short, server hardware is much more capable at networking than before because there is hardware support for it. Intel is building server hardware that performs at the same level as a lot of networking routers on the market today. Linux, VMware and Microsoft all co-operate with Intel to improve their networking performance on the newer generations of CPU and motherboards.

It’s worth noting that networking performance of Intel x86 servers is highly dependent on the motherboard features including bus speed, network adapter chipset, I/O chipsets etc. Older x86 technology does not perform well but modern servers such as Cisco UCS & HP Gen8 series have lots of newer hardware that deliver far greater networking performance.

Given this information there are many more servers than switches, edge networking in the server is practical solution. Scaling is the same as MPLS since the network edge performs the largest amount of processing and because there are many “network edge as servers” then the scaling is performed in the server hardware and not the network hardware.

Custom Hardware Is Just One of Many Solutions or Options

I agree that an ASR1000 with the “40-core Quantum Flow CPU” will always have a performance advantage but the question is whether this technology is relevant in the future ? For example, an IBM mainframe has significantly better performance than an x86 server but the majority of companies chooses to run x86 servers for efficiency and cost effectiveness. Companies can choose a mainframe if that solution meets their need but most, in fact the the vast majority, choose other systems because they are better suited to their requirements.

How many companies have purchased a Cisco ASR1000 or other hardware router that could be replaced with an x86 server ? How many ASR1000’s run at heavy load ? Does every customer need the performance of an ASR1000 ? I don’t think so. I think that many companies could use alternate solutions.

Consider the following scenario, do you really need a custom hardware device to connect to Internet ?

For example, I know several sites that using an ASR1000 to connect a single 10GbE Internet connection and nothing else because of the existing security isolation practices. These companies could seriously consider using a recent model of whitebox x86 server running Brocade Vyatta router software at 10% of the cost (over 5 years TCO) of the Cisco ASR1000. An simple Internet connection requires no “advanced” routing features (for most deployments). Exactly what would be lost in this kind of design when using a software router compared to a hardware router ?

Ethernet Wins

One other enabler for X86 routers is that Ethernet is everywhere. Carriers are avoiding using ATM, DS3 or Frame Relay interfaces and delivering Ethernet connections as WAN connectivity. I don’t need dedicated hardware modules to connect to legacy WAN protocols like ten years ago. From what I can research and discover, an x86 server has all the Ethernet hardware you will ever need and features are determined by the servers.

Operational Wins

Having x86 hardware offers some interesting changes to the way we operate networks. The hardware maintenance contracts on the custom silicon are comparatively expensive. There are other opportunities too – better testing, shorter lead times, predictable and reasonable capital cost.

The EtherealMind View

In the end, I take the view “software networking” will replace some significant percentage of the network market. But, in the same way that TV did not replace Radio & that x86 servers did not replace mainframe, there will be both hardware & software routers in the networks of tomorrow. I have the view that there will be a lot more software routing than people expect – but it is still just networking. Networking is not about a specific piece of hardware, chipset or device. Networking is a group of technologies that forward data between connected systems and doesn’t care about the hardware that makes that happen.

The good news is that there will be more networking devices than ever before. Low cost software routers on x86 make is possible to use ten “software” routers instead of one big hardware device and this will make operation and change control a lot easier.

At least, that is what I think today. I don’t have access to the resources, research and discussions that vendor are having. I can only comment and consider on what I can observe in the marketplace.

Bring on software networking. We need more choices, more options, more solutions to give us more networking.

Rant: Cisco Licensing Webinar – Surely a New Low for Customers

4th October 2012 by Greg Ferro

Check this out. An entire webinar devoted to licensing of just a single product from Cisco. Obviously, Cisco licensing of UCM is now so complicated and involved that there “Subject Matter Experts” dedicated to handling your queries about licensing upgrades. Not the product itself mind you, or the great new features, or planning your migration process.

JUST.THE.LICENSING.

Surely, when it gets to this, Cisco should realise that bureaucracy is getting out of control and that something is seriously broken inside the product management programs.

PS: This is a primary reason why I don’t work or recommend on Cisco IP Telephony – life is too short to waste weeks in meetings over licensing.

During the live event, Cisco subject matter expert Amit Singh will focus on the licensing architecture of Cisco Unified Communications Manager (CUCM) Version 9.x. The session will also include:

Evolution of unified communications licensing up to 9.x

How to calculate 9.x license requirement for a pre-9.x system and prepare for the license migration to 9.x

Different kinds of licenses and what suits specific business requirements

Detailed information about Enterprise License Manager and how to integrate with unified communications products

Manual versus electronic license fulfillment

Troubleshooting and live demo

A bi-weekly newsletter on a network human in IT Infrastructure.

IT Infrastructure is like a puzzle with hundreds of pieces. Some pieces are hardware, some are software and some are business processes. But the most important pieces are the people who design, deploy and operate the technology. Some news, links, opinions. Not too serious and a people focus.

Your email address is never shared.