Nigel Stevens on Managing Capacity in a World of Relentless Data Generation: Data Centre Scalability

In a recent article in Data Centre Solutions Europe, I shared some of the best ways for IT leaders to respond to exponential increases in data and the associated demand for IT capacity. I shared best practices for meeting your organization’s capacity needs today and into the future – even as future needs are uncertain. And I suggested questions to ask as you explore data centre colocation.

In particular, I outlined tactics for IT leaders who are: 1) matching infrastructure density to application requirements; and 2) seeking options for data center scalability to meet their changing demands; and 3) trying to forecast when and where new – or different – capacity will be needed.

It is an understatement to say that the digital universe is expanding quickly. We now generate as much data in two days as was generated between the dawn of civilization and 2003. The impact of big data and the Internet of Things has been extraordinary and broad, and it has only just begun.

With this data explosion comes increased demand for data centre capacity – demand that many data centers are not equipped to accommodate. What’s the best way for IT leaders to respond to this demand? The short answer is with a data centre solution that matches infrastructure density to application requirements and can scale to meet changing demands. Add data centre infrastructure management (DCIM) software that enables capacity planning, and your IT team will be well on the way to being prepared for the future.

1) Matching infrastructure density to application requirements

Matching infrastructure density to application requirements is important because, as my colleague Patrick Flynn, group leader of Applied Intelligence at IO, explains, “If you’ve over-provisioned your data centre, then you’re underutilizing capacity. And that’s incredibility inefficient.” In other words, if you’re running all your applications on high density infrastructure because a few of them require it, you’re wasting capacity on the rest of your applications.

So the data centre should be able to support mixed densities, giving organisations the ability to match infrastructure to application requirements. In a modular data centre like IO.London, customers can for example run high performance computing applications in a module architected to support high density infrastructure (up to 30kW per rack) and have their data storage or less demanding applications in a module set up to support low density infrastructure (say, 3-5kW per rack). Same data centre, but the infrastructure is matched to application requirements so capacity is optimized.

2) Seeking options for data centre scalability to meet their changing demands

In addition to optimizing capacity (so like Goldilocks you’re provisioned just right), a mixed-density data centre also enables scalability – both vertical scalability (densification) and horizontal scalability (expansion).

The modular data centre can accommodate much higher densities than a traditional raised-floor data centre can. In a raised-floor data centre, organisations more quickly reach power density limits. In contrast, a modular data centre accommodates up to six times higher density, enabling organisations to scale without having to expand the footprint.

Yet, there are of course cases where horizontal expansion – that is, expanding your data centre footprint – is desirable or essential. That kind of scale is a quicker process in a modular data centre; at IO, for example, we can deploy a new module in as little as 120 days. Where deploying new raised-floor capacity can take many times that long.

3) Trying to forecast when and where new – or different – capacity is needed

It’s essential in this data growth climate to match infrastructure density to application requirements and to be able to scale – vertically and horizontally. But it’s equally important to understand when and where new or different capacity is needed.

The predictive analysis that is possible by data centre infrastructure management (DCIM) software helps organisations to be more efficient in allocating resources, identifying capacity bottlenecks, and anticipating future resource needs. At IO, DCIM gives you a single view of your organisation’s data centre assets – even across multiple data centre locations – so you can optimise decisions about capacity.

Next steps

The research firm IDC has suggests that by 2020, the amount of information processed online will have grown tenfold from 2013. Doing nothing is not an option. IT leaders have to be able to meet that increased demand, efficiently, and quickly.

As you explore options for meeting your organisation’s data needs, here are 9 questions to ask about data centre capacity management, from Cutting through the hype: How the IO data center solution delivers truly scalable capacity (download it at:

  1. How does the data centre enable me to match density to application needs?
  2. Does the data centre support mixed densities?
  3. Does the data centre offer an on-premises private cloud option?
  4. How does the data centre enable me to scale as my demand for compute capacity changes?
  5. What is the maximum watts per square metre (or kW per rack) the data centre can support?
  6. How many square metres of unused space are available in the data centre?
  7. What is the total capacity available at data centre (# MW and M2)?
  8. How long does it take to deploy new IT infrastructure?
  9. How does the data centre enable capacity planning?

Nigel Stevens is managing director for IO in the United Kingdom.

Related Blog Posts

How the IO Data Center Solution Delivers Truly Scalable CapacityGartner Names IO a Visionary in Inaugural Magic Quadrant for Data Center Infrastructure Management (DCIM) ToolsThe Internet of Things and Data Center Automation

DISCLAIMER: This document is for reference purposes only. The information contained herein should not be relied on and neither IO Data Centers, LLC nor any of its affiliates makes any warranties or representations as to its accuracy.