Up until a couple of years ago, the data center network was somewhat staid. Today, however, it is anything but staid as the majority of IT organizations are trying to determine how they should evolve their data center networks to support the demands brought about by the ongoing adoption of technologies such as server virtualization.
We are going to use the next two newsletters to discuss the steps that we are taking to drive an industry-wide analysis of the data center network options that are either currently available, or soon will be available, to IT organizations.
Before we discuss how we are going to drive an industry-wide analysis of data center networks, we will highlight what we see as the key characteristics of the traditional data center network. One of those characteristics is that for the last decade, the traditional data center network was based on an architecture and design tailored to satisfy the connectivity requirements of a relatively simple server infrastructure. For example, for the last decade the majority of large data center networks were designed around a three-tier architecture that included access, distribution and core switches. One of the primary reasons why so many IT organizations implemented a three-tier architecture is that the traditional data center switches didn’t support enough high-speed ports to enable a flatter architecture.
Paving the way for a flat architecture
Some of the other cornerstones of the traditional data center network include the fact that each server was dedicated to a single application and had a single IP address and a single media access control address; that the static nature of the application environment lent itself to manual processes for server deployment or redeployment; and that the spanning tree protocol was almost universally used to avoid loops. In addition, nearly all of the traffic within the data center was client/server related. This type of traffic is often referred to as “north-south” traffic. The relatively small amount of traffic that went between servers was readily visible on physical switch ports. This type of traffic is often referred to as “east-west” traffic.
Driven in large part by the adoption of server virtualization, most IT organizations are rethinking their approach to data center networks. The good news is that IT organizations have a lot of new technology and design options that they can use. The bad news is that the breadth of available technology and design options can be overwhelming. That is why, as will be described in the next newsletter, we will be driving a series of six monthly discussions of data center networking with six of the leading vendors. Those vendors are Arista, Avaya, Brocade, Cisco, Extreme and HP.
The first discussion focuses on alternative to the spanning tree protocol. That discussion goes live on Aug. 4 and you can read it here.
