Xelerated Xpress

The Implications of Mobile Data Surpassing Voice

A very interesting milestone was recently reached.  As Ericsson reports, mobile data surpassed voice on a global basis in December 2009, Ericsson. This finding is based on Ericsson’s measurements on live networks covering all regions of the world.

So what implications will this have on 3G and 4G?  The most obvious is the demand for more bandwidth in the radio access network. It will have to be optimized for carrying data traffic. Voice services must be preserved, but data will dominate. And keep in mind that we are just in the early stages of the mobile data explosion.

Carriers have been trying to patch their networks in different ways to support more aggressive mobile data traffic volumes for some years now. Ethernet and circuit emulation in different variants have been introduced. Ethernet is a more high performance transport technology compared to ATM (AAL2 for voice and AAL5 for data). But carriers need rigorous synchronization schemes over Ethernet to make it work.  And there are other challenges like where to terminate legacy services and where to introduce the Ethernet ports? How can the new transport network comply to existing service provisioning schemes?

If the trends observed by Ericsson are correct, we are heading toward a data optimized radio access infrastructure faster than anyone expected. The Ethernet-based transport in the radio access network is needed to cope with the mobile data explosion. There are different attempts to solve this. We can learn from China Mobile’s PTN requirements which utilizes an Ethernet-based transport with synchronization support based on point-to-point (PTP) Ethernet. These networks are designed for data growth, but continue to support voice. And these requirements are here and now. They are designed for 2G, 3G and beyond.

by Thomas Eklund on Apr. 8th, 2010

| Comment

Multi-core Disappointment – Here We Go Again

It is time this industry learns from historic mistakes. If not, we may spend huge amounts in engineering efforts only to discover the path taken is a dead end.  I read a recent article by Simon Stanley of Light Reading, and in it his research indicates that multi-core processors are being evaluated from applications in the network processing field. I don’t see this trend when talking to the major network equipment vendors, and this might be  because they also remember what multi-core processors couldn’t deliver ten years ago.

Those who are seriously evaluating multi-core architectures for packet processing should be prepared for some surprises. Again. The same evolution happened several times before with separate processors brought together in a multi-processor architecture on the same die to scale processing performance.  Have people already forgot about why previous multi-core proposals for packet processing did not fly?

First, multi-core architectures consume a lot of power. Second, they are not designed for deterministic wirespeed performance. Third, they are difficult to program efficiently – making it hard to meet the performance requirements in modern packet processing applications.  And using ANSI-C does not help the inefficiency and performance challenges.

Multi-core processors are designed for general purposes, and they are therefore not optimized for packet processing.  They lack the necessary service density. Xelerated’s Dataflow Architecture, in contrast, was designed to solve the challenge of combining programmability and super-efficient packet processing. It is a linearly scalable wirespeed-by-design processing architecture with low power and a great amount of service density.

Support for 40 or 100 G interfaces does not say anything about the device’s ability to perform a meaningful application at these speeds. And when looking into the requirements in advanced Carrier Ethernet, Fiber Access or Mobile Backhaul applications, general-purpose multi-core designs continue to fall short. To give you an idea: Xelerated’s new HX330 has over 900 percent greater service density compared to the most high-end multi-core processor on the market. That is, it has 9 times the processing capacity for network and packet processing!

It is time to learn from history. Multi-core architectures have a bright future in general applications, for the server and consumer markets. Here is where they belong – processing applications, not processing packets.

There is a reason why 20+ NPU vendors that spent multi-million dollars in multi-core architectures failed to deliver a commercial and technically viable option to the networking industry. This history is just ten years away. I’m confident network equipment vendors have a longer memory than this.

by Thomas Eklund on Apr. 7th, 2010

| Comment

IEEE P802.3ba version 3 Is Ready

It is encouraging to see that the standardization work of 100 GE and 40 GE is coming to an end. Draft version 3, more formally IEEE P802.3ba/D3, is now ready and it looks like it will get passed and submitted to the Sponsor Ballot.

This is the formal start of next generation Ethernet innovation. This is good news for the industry, and well supported by us here at Xelerated.

by Thomas Eklund on Dec. 3rd, 2009

| Comment

ADSL Is Losing to Fiber

I read a very interesting article in Computer Sweden which presents the latest broadband statistics for the Swedish market. Fiber-based broadband access is growing,  and copper-based ADSL is losing market share.  Fiber is not only growing faster, but now, for the first time, the number of ADSL subscriptions are actually declining. Also, more people are using IP telephony than POTS – however both are losing to cellular phone services.

Yet another statistical proof point that copper-based services are on a downhill slope. The pace of change to fiber seems to be faster than many of us have expected.

by Thomas Eklund on Nov. 27th, 2009

| Comment

Observations at the Linley Data Center Seminar

I attended Linley Group’s data center seminar this Tuesday to learn more about the latest data center trends.  Xelerated’s Anders Wirkestrand presented on the Network Processor Unit’s (NPU) role in data centers as a key catalyst for virtualization.

One key observation is that an NPU has an enormous amount of service density and could, when used together with a multicore processor, increase the overall performance and transaction rate while lowering the power significantly. The number of instructions per packet is 23 times (yes, you read that correctly!) over a state-of-the-art Intel Core 2 Extreme QX9770 multicore processor. Combining the strength of a state-of-the-art multicore processor and an Xelerated NPU can dramatically improve the overall solution.

It is interesting to see that the data center server players are adding switching functionality, and at the same time, the router and switch vendors are adding server functionality. They end up competing with each other. When the switch becomes a server, and the server becomes a switch, it opens up for a period of strong innovations.  Which architecture model will prevail in the future?

by Thomas Eklund on Nov. 13th, 2009

| Comment

Technology Recycling

It is funny to see how many good ideas come at the wrong time, but can later be recycled when the timing is right. As we all know, predicting the timing of a technology isn’t the easiest.

Look at the famous God Boxes that everyone thought were dead. Today it is the hottest new architecture in Transport and it’s called P-OTS  (hmm, I can’t think of a worse name for a plain old telephone system –  sorry packet optical transport system).

Another famous old technology – thin clients.  But, now what does cloud computing enable?  That’s right – thin clients. As we enter the “Google world of Internet” more and more applications will reside in the cloud – enabled by high speed access networks and virtualization in the data centers.

IP as a bearer of data in radio access network ten years ago was interesting from a technology point of view but never gained any traction with the carriers. Today on the other hand, you see everyone launching new IP or Ethernet-based Radio Access Equipment to carry mobile data.

So whats next – IPv6?

by Thomas Eklund on Nov. 10th, 2009

| Comment

It is All-Ethernet

Follow Ethernet and you will be guaranteed a low cost and robust solution for your network. If the buzzword was All-IP a few years back, it is definitely All-Ethernet these days (and yes, you can still run MPLS and IP over it).

We are now witnessing how Carrier Ethernet is extending into access networks. It is becoming a key technology for unifying EPON, GPON, Active Ethernet, Microwave, and Mobile Backhaul. In parallel, it is emerging as a peering technology in the Core.

Xelerated has been pioneering the Carrier Ethernet technology, contributing with a number of industry firsts.  We believe in Ethernet. It is a superior technology from the access to the core, and nowadays it is not a question of if and how, rather when (can you deliver it) and how (much).

The potential in Carrier Ethernet is recognized by most service providers around the world. AT&T’s position is shared in a recent Light Reading article.  Margaret Chiosi, executive director of Optics & Ethernet Service Development for AT&T Research Labs makes a strong point of using ‘Carrier Ethernet everywhere.’ It is a matter of driving down CAPEX and OPEX, while riding the bandwidth wave. But she also brings up an interesting caveat; “The challenge now is to make Ethernet services available at more locations with more customer choices.” I could not agree more.

Taking AT&T’s statement serious, it has some hard implications to Carrier Ethernet platforms.  As services and standards keep evolving, every platform in the network should be programmable. This enables customized services and tailor made services over time.

When the network becomes All-Ethernet, it better be programmable.

by Thomas Eklund on Nov. 8th, 2009

| Comment

The Net Neutrality Debate is Only Half

Having spent time both in the U.S. and in Europe, I believe the U.S. focused net neutrality debate tends to miss an important point. Net neutrality and open-based access models are interlinked. In the U.S., the debate centers around how to ensure equal and transparent treatment of services by the access providers. In Europe, the regulatory discussion is focused more on how the access player’s competition can be ensured in the long run.

Today EU is endorsing an open-based access model in an attempt to get more “fair” access to the local loop and Central Office spaces typically owned by the incumbent local exchange carrier (ILEC).  The idea is to avoid the problem experienced in the copper-based world with a monopoly organization owning a key public infrastructure resource, and thereby defining the rules for competition with implications both on network services, prices and pace of service innovations. Without sound regulations, alternate multiplay service providers, CLECs, utilities companies, and municipalities would have been effectively locked out to offer broadband services on competitive grounds.

The U.S. is a country where free trade and strong competition are well recognized. The way the regulatory discussion in the U.S. is moving forward, it is limited to content and service transparency and equal treatment. The goal is to limit service providers’ freedom to filter and downgrade user experiences on applications like Peer-to-Peer download. This is an important dimension but I think ultimately customers will leave if the services beeing offered have too poor quality. That is, if there are competitive players around for the consumers to select from. In competitive markets, access service providers who have tried to downgrade user experiences on specific network services have faced strong churn and the brands have taken serious hits in the media as well.

To be effective, broadband stimulus should couple net neutrality with defined rules for open-based access. There are many real world cases where this model has successfully stimulated sound competition.  If done right, competition will be healthy both on services being offered and for the access to the local loop and Central Office space footprint. This drives down price and increases the pace of innovation, pushing vendors and service providers alike to bring better technologies and services to market, all to the benefit of the consumer.

While the debates and the strengths of the different players vary between the U.S. and the European Union, both continents face similar challenges, and can learn from each other. Now is a good time to push for open-based access models and net neutrality. Broadband stimulus may add the necessary extra incentive to increase competition and avoid the new fiber access infrastructures currently being deployed from being locked into monopolies.

by Thomas Eklund on Nov. 5th, 2009

| Comment

Ethernet as a Peering Technology

In recent developments of Metro Ethernet Forum’s MEF23, the industry has been working on standardizing Carrier Ethernet to be used as a core peering technology, complementing today’s IP/MPLS peering model. This is an interesting extension and development into the core market. So why is this needed?

There are limitations to today’s IP/MPLS peering, both commercial and technical, however when looking at the broader context, I believe the main driver for using Ethernet as a peering technology comes down to cost. Historically, the success of Ethernet has been dependent on its ability to scale and reduce cost. Ideally, the MEF 23 standard – which will make it easier to scale Carrier Ethernet services globally – will provide a common framework for operators to interconnect Ethernet services with other operators, helping to improve the reach of those services.

The ENNI global interconnect* looks promising and could offer more robust monitoring of the peering points with Service OAM, faster fail-over-times and high availability at a lower cost for the carriers.

In addition, the use of  multipoint configurations and multi-homing scenarios will drive new feature enhancements to the data plane. Carrier Ethernet systems based on programmable devices, such as Xelerated’s chipsets, can add features to the data plane as they mature. The evolving Ethernet peering technology is another proof point for the benefit of programmability.

Ethernet peering is likely to be one of the next hot areas for the networking industry. At Xelerated, we will not only be watching this closely, but actively contribute to its success. Stay tuned for more updates.

—-

*ENNI is short for Ethernet Network to Network Interface, and defines a common set of rules for interchanging Ethernet services between service provider domains.

by Thomas Eklund on Nov. 4th, 2009

| Comment

Xelerated Nominated to Prestigious Award – Stora Teknikpriset

The Swedish technical paper, Ny Teknik, nominated three finalists to Stora Teknikpriset – Xelerated, Ericsson and SAAB (the defense company). In preparation for the award ceremony there were both articles written and videos taken (in Swedish only) to explain and give some good background to three leading innovations from Sweden.

As always, when competing in the technology business it is hard to rank one  innovation in a specific field to another which applies to a different segment.  At the end of the day it will be the commercial success that will be the ultimate referee. Still, it is a great honor to be nominated to such a prestigious award as Stora Teknikpriset.  It serves as a strong testimony to the innovative technology we provide here at Xelerated, while acknowledging the team’s hard work and dedication of designing a unique packet processing architecture and bringing it to commercial success.

Xelerated didn’t get the gold medal this time around. Instead, I’d like to take the opportunity to congratulate Ericsson for winning the award for their development of “Turbo 3G,” enabling mobile broadband across the world.

by Thomas Eklund on Oct. 30th, 2009

| Comment