Story image

Virtualisation evolved: the modular data centre

01 Apr 2012

Less is more. It’s a classic mantra and one that’s driven design philosophy for data centre technology for years, even decades.   New trends like cloud storage and not-so-new techniques like virtualisation owe their development to this principle, as do many other modern approaches to data centre design. Today we find ourselves at an enviable juncture, where many of these techniques have evolved to the point where they can be modified, advanced and combined to achieve unprecedented levels of efficiency, utility and flexibility. A good example of this is the modular data centre. Modularisation is essentially the integration of the different infrastructure and equipment components in the data centre, which can then be assembled and reassembled to fit different spaces, locations, sizes and configurations. By that description alone it’s clear where a technique like virtualisation can benefit from a modular data centre approach. Virtualisation increases the relative computing power of a data centre by shrinking multiple physical servers into fewer – often singular – servers or blades, as they’re better known today. The popularity of virtualisation has largely changed the size and shape of the modern data centre, influencing layout, rack arrangement and infrastructure requirements. Similarly the emergence of modular data centres adds a level of flexibility and scalability previously unattainable with traditional data centres. It also vastly reduces the time needed to deploy data centres in remote areas, or for geographically dispersed projects. Even large-scale broadband networks, like New Zealand’s Ultra-Fast Broadband Network or Australia’s National Broadband Network are cases in point. These networks rely on smaller, purpose-built data centre facilities at their traffic distribution nodes, and are typically built to aggressive, government-driven schedules that would be difficult if not impossible to meet using traditional data centre design techniques. Whereas virtualisation would allow such projects to be developed using fewer components, modularisation further pushes the envelope by allowing for rapid deployment of 'containerised' data centres purpose-built to provide the necessary computing power at the lowest possible cost and in the shortest space of time. Even accounting for the sheer size and scope of these networks, each can be built up and scaled to meet future demands simply by building and deploying additional containerised data centres. One major benefit of modularisation is that many of the components can be sourced from different facilities – even countries – and then assembled on-site. Another major advantage of modularisation is that the data centre can be built off-site and tested in parallel with the actual building of the site. Once the site is ready, the data centre can be transported, switched on and is ready to go.   The advantages of virtualisation in a modular data centre aren’t limited to large capital projects. The same concepts are just as attractive in the enterprise, and some would likely filter down to small-and-medium-sized companies as well.   Regardless of the size of the deployment, however, the common element to any project that marries virtualisation with modular data centre design is management.   With so many different combinations of equipment and infrastructure available to the design team, rigorous and accurate management – typically software-based – is required to optimise the initial design, and then expand (or shrink) it to meet the changing demands of the business. It’s important to see, for example, what the impact would be of additional blades in a contained space on the supporting infrastructure. Or on the additional load placed on the power and cooling equipment as a result of increasing the processing power of individual blades. The proper management tools are also critical for future planning, providing what-if scenarios that allow designers to replace older equipment with new solutions, further improving efficiency, lowering the heat ceiling, or simply doing away with redundant infrastructure based on actual usage. Technology advances come to us in many different forms. The ability to pack more processing power into ever-smaller components is revolutionising the way we communicate, do business, and advance as a society. Our ability to combine the benefits of these technologies into flexible, pre-packaged and scalable designs is now changing how much utility we can get from them, and reducing the cost and time taken to do more with less. 

Orange Belgium opens 1,000 sqm Antwerp data centre
It consists of more than 500 high-density 52 unit racks, installed on the equivalent of 12 tennis courts.
Time to build tech on the automobile, not the horse and cart
Nutanix’s Jeff Smith believes one of the core problems of businesses struggling to digitally ‘transform’ lies in the infrastructure they use, the data centre.
Cloud providers increasingly jumping into gaming market
Aa number of major cloud service providers are uniquely placed to capitalise on the lucrative cloud gaming market.
Intel building US’s first exascale supercomputer
Intel and the Department of Energy are building potentially the world’s first exascale supercomputer, capable of a quintillion calculations per second.
NVIDIA announces enterprise servers optimised for data science
“The rapid adoption of T4 on the world’s most popular business servers signals the start of a new era in enterprise computing."
Unencrypted Gearbest database leaves over 1.5mil shoppers’ records exposed
Depending on the countries and information requirements, the data could give hackers access to online government portals, banking apps, and health insurance records.
Storage is all the rage, and SmartNICs are the key
Mellanox’s Kevin Deierling shares the results from a new survey that identifies the key role of the network in boosting data centre performance.
Opinion: Moving applications between cloud and data centre
OpsRamp's Bhanu Singh discusses the process of moving legacy systems and applications to the cloud, as well as pitfalls to avoid.