Core Switch Architecture Evolution

Application is always the driving force of technological development. In the face of increasingly complex business applications, the technology architecture of network equipment has become a key factor in the application of equipment, and different applications require different network equipment. For example, the application of NGN needs to be based on softswitch technology architecture equipment, such as vertical network need to pay attention to routers, park network is the focus of the switch and so on, which all indicate that a technical framework for the emergence of a certain type of application and service.

So, in the current trend of network convergence, what kind of architecture does the core switch need?

Evolution of the Exchange architecture

With the increase of Internet users and the expansion of bandwidth, the structure of the switch is also constantly developing, from the time of introduction, the Exchange architecture has experienced the bus-type and crossbar two stages. But since the development of Ethernet technology is thousands of miles, so the two architectures of the switch are currently active in the market.

Total line Pattern Switching architecture

The switch based on bus structure is generally divided into two categories: Shared bus and shared memory bus.

A shared-memory-structured switch uses a large amount of high speed RAM to store input data while relying on the central switching engine to provide a full port high-performance connection, with the core engine checking each input packet to determine the route. This kind of switch design is relatively easy to implement, but when the switching capacity to a certain extent, memory operation will cause delay; In addition, in this design, because of the problem of bus interconnection increase redundant exchange, the engine is relatively complex. So if the switch provides a dual engine, it is relatively difficult to be very stable. So we can see that the core switches that were launched early in the market are often single engines, especially as the switch ports increase, and the price of central memory becomes high because of the need for greater memory capacity and faster speed. Switching engines can be a bottleneck for performance implementations.

crossbar+ Shared Memory Architecture

Crossbar (that is, crosspoint) is called a crossover-switch matrix or a crossbar exchange matrix. It can make up for some deficiencies in the shared memory mode.

First, the crossbar implementation is relatively simple. The physical connection between the line card and the switching structure in the shared Exchange architecture is simplified to point-to-point connection, so it is more convenient to realize the stability of the large capacity switch.

Second, there is no obstruction inside the crossbar. As long as multiple cross nodes (CrossPoint) are closed simultaneously, multiple different ports can transmit data at the same time. In this sense, we believe that all crossbar are internally non-blocking because it can support all ports at the same time exchanging data at the same speed.

In addition, because of its simple realization principle and the non-blocking switching structure, which can run at very high speed, the semiconductor manufacturer can now use the traditional CMOS technology to manufacture the point-to-point serial transceiver chip with 10GBIT/S rate.

However, this structure still exists the problem of crossbar interconnection between the Business board bus and the switching network board. Because the data on the Business Board bus is the standard Ethernet frame, the general crossbar adopts the mode of the exchange of the crossbar to embody the efficiency and performance of the system. Therefore, the structure of the shared bus used on the business board affects the efficiency of crossbar to a certain extent, and the performance of the whole machine is limited by the crossbar of the switching network board.

Distributed Crossbar Architecture

The exchange capacity of the core switch has now developed to hundreds of Gbps, while supporting multiple gigabit interfaces and the size of the metropolitan area Network backbone and campus network core. The Distributed crossbar architecture is a good solution to the challenge of the high performance and flexibility faced by the core switches in the new application environment.

In other words, in addition to the switching network board using the crossbar architecture, in each business board also adopted the crossbar+ switching chip architecture. Switching chips on the business board can be a good solution to the problem of local exchange, the crossbar chip between the Business Board switching chip and the switching network board solves the problem of the business data of the business board, which improves the exchange efficiency, and makes the data type of the business board and the Exchange Network Board's signal become two planes. That is, you can have a very rich business boards, such as firewalls, IDS systems, routers, content exchange, IPV6 and other types of business integration into the core Exchange platform, thus greatly improving the core switch business expansion capabilities.

At the same time, this crossbar has the corresponding high-speed interface, respectively connects to two main control board or the Exchange Network board, thus greatly enhances the dual main control main standby switching speed.

Bighammer for Network Fusion service

At present, the development of the network shows obvious integration trend, which includes business integration, technology integration and network integration. Port network's million core switch BigHammer6800 series core switches because of the use of distributed crossbar and distributed Exchange architecture, to solve the problem of large capacity exchange, multiple service delivery, so that can help the user network to better achieve these integration.

For the fusion of data, voice and video service, the crossbar chip of business board can simplify the large data stream of voice and video into the way of fixed-length exchange, and improve the exchange efficiency. This is one of the reasons that BigHammer6800 can realize the "million-line speed exchange ability".

In the solution of Exchange routing integration, IPV4/V6 network integration, the port network solution is also trustworthy. Bighammer Series equipment not only supports rich routing protocols, but also solves the biggest problem facing the network through MPLS Technology--ipv4 Network transition to IPV6 network. MPLS speeds up the search and forwarding of packets, and on the other hand provides a more efficient tunneling mechanism. Integrated Ipv6 on MPLS Networks is currently recognized as the most reasonable transition scheme for IPV4 to IPV6. MPLS is implemented by a business board based on NP design, which has strong performance and scalability.

The switch architecture has completed the process of evolution from "shared bus" to "crossbar+ shared memory" to "full distributed crossbar", and will continue to evolve in the coming days.