How_will_data_center_fabrics_affect_me

Data center network design has been undergoing rapid changes with the adoption of technologies such as server virtualization. As a result, data center traffic is changing from predominantly north-south (i.e., into and out of the data center) to east-west (i.e., server-to-server within the data center).

Traditional Architecture Issues


A traditional three-tier switching architecture using core, aggregation and access switches is not ideal for large, virtualized data centers. For one server to communicate with another, the data may need to traverse north from an access switch along a hierarchical path through aggregation switches and a core switch and then south again through more switches before reaching the other server.

In other words, the data has to go through more “hops” as it moves from switch to switch. This adds latency, which can ultimately create traffic bottlenecks—something every data center manager strives to avoid.

Optimal Architecture


Data center switch fabrics that typically use only one or two tiers of switches are now widely viewed as the optimal architectures to enable east-west traffic. These flattened architectures provide low-latency and high-bandwidth communications between any two points to meet the needs of virtualized networks and ever-increasing application and traffic load.

switch-fabric

In data center switch fabric architectures, any server can communicate with any other server via no more than one interconnection switch path between any two access switches. Data center switch fabric architectures feature switches with large numbers of connections to other switches that are all active to provide multiple paths that minimize latency and provide maximum switch fabric bandwidth.

Data Center Fabrics Guidelines


In February 2013, the Telecommunications Industry Association approved the ANSI/TIA-942-A-1 standard, Cabling Guidelines for Data Center Fabrics.

This standard describes various data center fabric architectures such as fat-tree (leaf and spine), full mesh, interconnected-meshes, fabric centralized switch and fabric virtual switch.

Understanding the various fabrics and how to implement them over structured cabling is key to providing an efficient communications path between all the servers connected to the fabric.

How Will This Impact You?


To learn more about data center fabrics and how to design structured cabling to support them, read my standards update, "Data Centre Fabrics Explained". And, as always, feel free to see what is new in our whitepaper library.

Download our 10 Steps to Holistic Data Center Design white paper