At present, software-defined networking (SDN) has become a fashionable topic in the industry. SDN technology and its possible impact have been highly valued by academics and industry, and there are also different understandings and understandings of SDN. This paper attempts to analyze the connotation, essential characteristics, application fields and development trends of SDN technology from the development of SDN technology, and then analyze the impact of SDN technology development.

First, "there are different opinions" SDN

At present, experts with high attention to SDN can be roughly divided into three categories: IDC design and operation and maintenance personnel, data equipment design and development personnel, and future network research and test personnel. These three types of experts pay attention to the starting point of SDN and the understanding of SDN, and the vision and expectation of SDN development are also different. After the emergence of a new technology, the discussion of who traced the concept, who proposed it, and whether it was a new concept is usually only academic, and does not help the understanding of the nature of new technology. Discussing the SDN concept is still to start with its real market demand.

(1) SDN commercial demand first appeared in the data center

The internal network of the IDC is usually a Layer 2 network. The difficulty of deployment and management, while the second-tier network does not have this problem.

However, directly applying the existing Layer 2 network technology in the IDC will mainly bring about the following two problems: One is to use the Spanning Tree (STP) protocol in the Layer 2 network to eliminate the loop of the broadcast packet. Build a logical tree between network nodes, and the traffic between nodes is transmitted according to this "tree" topology. Even if there are multiple physical links between network nodes, only one link actually transmits data, and other links The roads are all idle (only backup). However, within IDC, there are frequent data exchange requirements between multiple servers. STP-based tree network topology cannot efficiently support such “horizontal” traffic, and idle links between servers also cause a large amount of network resources. Waste, so the STP-based Layer 2 network is too simple for IDC and needs to be changed. Especially with the development of cloud computing, this IDC internal Layer 2 networking needs are becoming more and more urgent. Another problem is that there are usually many application servers inside IDC, some of which reach tens of thousands or even hundreds of thousands. The Layer 2 switches need to use ARP and other protocols to learn the source address of the received data packets to establish a MAC address table. There are many application servers, so there are many MAC address entries, which usually exceed the capacity of the regular Layer 2 switch MAC address table. As a result, a large number of MAC addresses cannot enter the MAC address table. The Layer 2 switch can not find the MAC address in the MAC address table. The data frame corresponding to the address broadcasts in the Layer 2 domain, causing traffic flooding inside the Layer 2 network and affecting the internal network efficiency of the IDC.

The root cause of the above two problems is that the traditional Layer 2 network design is too simple. The Layer 2 switch only learns the MAC address and does not plan the data forwarding path based on the MAC address. That is to say, there is no one in the traditional Layer 2 network. The control plane (or the control plane is very weak and fused with the forwarding function), only the data plane (responsible for forwarding data frames). Therefore, adding control planes (or strengthening control plane functions) in the Layer 2 network is responsible for traffic scheduling and management among the nodes within the larger Layer 2 network. At present, the more mainstream solution is to use the variant of IS-IS routing protocol to construct the control plane routing function; Openflow is used to define the interface between the control plane and the forwarding plane. This leads to the concept of separating the control plane from the forwarding plane. But this is only the separation of the control plane and the forwarding plane in the Layer 2 network.

(2) SDN commercial demand comes from the optimization of internal functions of the router

In a traditional router, the interface between the control plane responsible for routing planning and routing policy and the data plane responsible for data encapsulation and high-speed forwarding is not open and is tightly coupled. Each manufacturer connects its control plane and forwarding plane through its own protocols or interfaces. This is also the advantage of CISCO, JUNIPER and other dominant vendors to maintain technical barriers and crowd out emerging vendors.

However, there are two forces that are quietly challenging this model: one is a large Internet enterprise, they have the need to build their own corporate networks, and these Internet companies believe that the communication needs of their own corporate networks are specific, while the traditional The function of the router is too complicated. More than 80% of the functions and features are not available in your own network. However, when you purchase these routers, you have to pay for these useless functions. It feels awkward, so there is a simple design. The demand for efficient routers is one of the original intentions of Facebook, Google, Yahoo and other companies to establish ONF (Open Network Forum) and develop SDN standards. Because these Internet companies have the successful experience of using their own customized application servers within IDC, they have good expectations for independently developing efficient routers. Another force is the emerging data equipment vendors who are trying to form an open, standard device interface by breaking the tight coupling between the router's internal control plane and the data plane, so that the control functions can be centralized and stripped out separately. Forwarding devices can be made more versatile and simple, and costs can be made lower, helping to break the monopoly of CISCO, JUNIPER and other vendors, and these vendors can gain new development opportunities.

Based on this consideration, the IETF started the research work on the separation of the internal control plane and the forwarding plane of the router earlier, and established the FORCES working group to define the communication protocol between the internal control plane and the forwarding plane of the router. Although this also leads to the concept of separating the control plane from the forwarding plane, this is the separation of the control plane and the forwarding plane in the three-layer network.

(3) SDN commercial demand comes from future network research and experiment

At present, in order to solve the problems of insufficient network address space, difficult service quality, lack of security and trust mechanism, and poor network management and control capabilities for IP networks, future network researchers are actively researching new network architectures and key technologies to try to solve these problems. At present, although there are many research directions, it does not form a clear and consensus technical route. On the other hand, in the case that the technical route is unclear and new solutions emerge in an endless stream, it is necessary to establish a test of a large-scale future network new technology. The verification environment (test network) flexibly provides a resource-independent test environment for various technical solutions on this test network, thereby incubating the preferred technology. The United States and Europe have established the GENI and FIRE networks respectively, and the purpose is here. In the process of test network construction, designers hope to be able to flexibly control and deploy routing protocols on network nodes to achieve efficient forwarding, thus forming an increasingly strong demand for separation of control planes and forwarding planes on experimental network nodes. Through the separation of the control planes, the intelligence and concentration of the network control functions and the protocol-independent and efficient network forwarding functions can be realized.

In the case where the control plane and the forwarding plane are separated on the experimental network node, each time a new network architecture and solution emerges, it can be designed and configured in software form on the implementation node to quickly implement a new network configuration. Efficiently support network technology innovation and verification.

In addition to the above three SDN requirements and the corresponding three types of experts, some experts understand SDN as a unified intelligent network management, and are committed to achieving the purpose of a network management system to uniformly and intelligently manage multiple network devices, such as deployment in LTE. In the design of IP RAN, multiple simplified edge routers can be configured and managed through an integrated network management system to improve the efficiency of network policy deployment. However, this understanding is to separate the management plane from the control plane and the data plane, not the separation of the control plane and the forwarding plane, and should not be understood as SDN technology.

Second, "正本清源" SDN

The above analysis of the three development needs of SDN, comprehensively, these requirements are pursued by the network "open" concept.

The opening of the network is an inevitable trend of industrial development. It not only brings the efficiency of the corresponding equipment and networks, but also further subdivides the industrial chain and brings new opportunities for industrial development. In that year, the “openness” between mechanical parts realized the standard exchange between parts, refined the industrial chain of machining, improved the production efficiency of finished machinery, and greatly promoted the development of the industrial revolution. In the field of network communication, similar expectations can be achieved through SDN technology.

Within the data device, it can be summarized as two planes, as shown in the following figure:

To understand SDN from the perspective of network openness, we can divide SDN into three categories, and the openness between each category is an incremental relationship:

72V Battery Packs

Best Battery Pack,Dewalt Battery Pack,Plug In Battery Pack,Dash Cam Battery Pack

Zhejiang Xinghai Energy Technology Co.,Ltd , https://www.headwayli-battery.com