Over the past year, Juniper Networks has been advocating a New Network vision that includes new technologies, partnerships, and even a venture fund to get tomorrow’s network innovations moving forward at a more rapid pace.

Here,  David Yen, Executive VP and General Manager of Juniper’s Fabric and Switching Technologies Business Group,shares his perspective on Juniper’s 3-2-1 architecture and what it means for the future of data centers.

Q: As the head of Juniper Networks’ Fabric & Switching Technologies Business, can you sum up what Juniper has laid out for customers and others?

A: One major theme we’ve been advocating since our ‘New Network’ launch back in October 2009 is the realization that technology has evolved so much in just about every facet of the IT industry – from the mega data centers to consumer. It's time for a new network to fulfill the promise of today's technology while fostering future innovation. And we believe the most important thing—the first step of this process —is to simplify the data center. Then you can control your cost. You can scale. And you have a much better foundation to automate the network.

Q: Let’s talk a bit about the data center. What has fundamentally changed there in the past few years?

A: For decades the perennial challenge for data center managers has been to strike a balance between the user experience and the economics. With a new network, you actually have a chance to enhance both measures. As everybody has seen in the last decade or so, there have been very significant changes in the data center, particularly on the application, user services and programming style sides. Over the last 10 years, instead of the popular client-server model, the work, the application, has evolved to the Web 2.0 style. You touch on a number of applications written by different people, possibly running on different servers.

With the service-oriented architecture time to market, people no longer develop their applications completely from scratch. Furthermore, more modern applications have fundamentally changed the workload in the data center. In the client-server era, typically people used very capable UNIX servers to run particular application services. And that particular service may be rendered by various processes within the server and dealing with one or maybe more databases also contained, controlled by the server. So the network traffic in the data center primarily ran “north and south,” between the server and the serving client.

Now look at the data center architecture, which today is primarily a multi-layer Ethernet switching tree structure, where at the bottom or “south” of the tree are the servers, while clients come from the top of the tree so traffic is north and south.

With the advent of Web 2.0, the service-oriented architecture, along with the increasingly capable x86 processors that commoditize the server hardware, and also the popular practice of designating a particular server to run a particular application, now, a typical application in the data center may interact with several servers and deal with one or more databases. Each of these databases is probably created by different people for different purposes and they just aggregate all these to provide the services. As the workgroup grows, this tree gets bigger and more complex.

Q: So the data traffic patterns are shifting and data center networks have yet to catch up to this?

A: Well, the interesting thing here is that all traffic that was previously contained within the server now gets completely exposed to the outside of the server and storage. That puts a lot of new types of stress on the data center network. Furthermore, if you refer to this tree-like structure, it's no longer just north and south traffic between the so-called server and the client. Today, as much as 75 percent of network traffic in the data center now involves interactions among servers and storage, so it becomes an “east-west” traffic pattern.

Factor in server consolidation, data center consolidation, new types of content service providers, and cloud computing…and the data center becomes bigger. When the data center gets bigger, interconnecting all the data center resources becomes huge. This traffic pattern change and data center resource increase causes the tree-like structure used in the data center over the last 23 years to all of a sudden become very slow.

Q: Why is it too slow?

A: Because every layer of switching introduces latency. With a tree-like structure and the need to connect more data center resources, layers are added to connect switches which themselves are connecting server and storage resources.  And with the tree-like structure, when sending packets from one server to another, you have to travel all the way up the tree and back down again—in other words, traffic has to travel north and south first in order to move east and west.  For east-west traffic, this north-south path introduces extra hops and delays, which are undesirable.  Imagine what that means in an equity-transaction environment where each delay or bit of latency has a financial impact.

If you look at the tree-like structure in the data center, when you have layers of these switching boxes composing this whole tree, it becomes extremely complicated. At most of the major enterprise data centers you visit today, frequently you will find there are at least four or five switching layers. We have seen customers with as many as seven layers of switching. It becomes very complicated to manage. And furthermore, it obviously is very expensive, both financially and also in terms of power.

So it’s with these drawbacks and challenges in mind that we looked at how to enhance the data center network architecture to improve the experience and economics for our customers.

Q: How is Juniper Networks  tackling this issue for its customers?

A: With all the drawbacks of the legacy data center network approach, and after hearing about specific pain points from customers, we started looking for ways to enhance the network. In May 2010, Juniper announced our architectural vision called “3-2-1.” Simply, it’s time to reconsider the multi-layer switching network for all the reasons I discussed previously. With the technology available today, enterprises and service providers can reduce layers in their data center network to create a very efficient two-layer architecture.

Obviously it's not just by using the latest and greatest switches. You have to supplement it with additional technology like Juniper's Virtual Chassis fabric technology, a software technology that allows a customer to aggregate multiple physical switches to behave like a larger logical switch. By doing that you simplify the management by eliminating the need to individually manage the member switches. Furthermore, within an aggregated cluster, you can accommodate the east-west traffic without going to the top and coming down—in other words, you reduce the number of hops, which reduces latency.

By reducing data centers to fewer larger switches to interconnect, you can eliminate switching layers required to connect/aggregate switches. And you reduce pressure and demand, which will allow you to complete the entire switching network by the next layer chassis-based switches. So it's a two-layer architecture.

Ultimately the goal is to provide a single-layer network to drive any kind of network traffic.  That’s the goal and object of the Project Stratus that Juniper Networks is working on.  That's the 3-2-1 architecture concept—collapse the traditional three-layer network to a simplified two-layer architecture today with our Virtual Chassis technology and in the future to a single layer.  It’s been extremely well received among our customer base, and we are very pleased with that.

Q: When Project Stratus becomes commercially available, is it something that will impact Juniper’s existing business or is it a new opportunity at the very high end of the data center?

A: Project Stratus is very complementary. Juniper’s switching business—all the boxes we build, if you will—is more conventional. It's subject to industry-standard interfaces and industry-standard packaging—24 ports, 48 ports, gigabit and 10 gigabit Ethernet—but they go everywhere. They fit in the legacy architecture, and they fit in the newer two-layer architecture. They go everywhere. They fit in data centers; they fit in campuses.

Stratus, in a way, is half product and half solution. It goes one level higher, because it takes the whole data center network into consideration. And between our switching products and our fabric products, we share the same management layer software, which we call Junos® Space. Plus the internal operating system, Junos, is a common user interface. So it's actually very complementary.

Q: How does Juniper Networks’ vision differ from the competition?

A: A vendor such as Cisco, has a lot of good engineers and is quite respected. However, their data center approach tends to be more incremental. They also need more adjacent markets to quickly grow their business. When a technology or when an industry becomes more mature, incremental is no longer enough if you’re trying to achieve even better economics for customers. You need to start collapsing some architecture layers. Cisco chose an approach to start integrating the storage interface, networking interface, and computing.

In contrast, Juniper’s fabric technology, first with the Virtual Chassis fabric of the EX Series switches and then with Project Stratus, is also collapsing architecture layers, except we chose to focus on the data center network while preserving customers' freedom and choice of best-in-class technologies. They can still choose their preferred server and storage and other appliances, and we just focus on the network. But the fundamental spirit is all trying to look for opportunity to collapse architecture layers.

Unlike the competition, Juniper also helps drive simplification through a single network OS, Junos, that runs across all switching, routing and security devices. Junos follows a single software release chain and offers a flexible software platform with Junos Space. No one else can offer what Juniper can to the developers around the world. An open, multipurpose network application platform that allows customers to directly program multiple layers of their networks can only enhance user experiences, deliver smart economics and allow for faster time to market.

So, different companies have different approaches.

Q: What’s the ultimate goal for Juniper’s data center approach?

A: Juniper is leading the data center network industry by providing our 3-2-1 architecture. Ultimately, our goal is to provide a single flat fabric that connects everything in the data center and ultimately helps to deliver on the promise of a more efficient, more agile data center.

It means connecting any server, every server and storage component, every security appliance and the routers in the data center and collapsing them to a completely flat network that is homogenous, fair, and lossless. Furthermore, the user should be able to drive any kind of data center traffic, not just Ethernet networking, but also fiber channel storage traffic if you so desire. And that's exactly the goal, the objective, of Juniper’s Project Stratus.

David Yen is Executive Vice-President and General Manager of Juniper's Fabric and Switching Technologies Business Group