One of the biggest efficiency issues in data centers is the underutilization of servers. In a 2014 issue brief (pdf), the Natural Resources Defense Council (NRDC) blamed peak provisioning for the waste: organizations install sufficient equipment to handle their peak annual load, and then some, resulting in vast underutilization of the servers for the majority of the time.

Indeed, the average data center is utilized at 56 percent capacity from a power perspective, according to a 2015 enterprise data center survey by 451 Research (pdf). So on average 44 percent of the power that enterprises are allocated – and paying for – is unused. That’s a huge opportunity for efficiency gains.

Beyond cost inefficiency, underutilization is inefficient from a growth management perspective as well. When data center utilization isn’t optimized, enterprises end up having to build out new capacity sooner than they otherwise would to accommodate growth – at hefty capital cost.

Overprovisioning as the rational response to the realities of data center management

Underutilization is caused by overprovisioning – that is, overestimating capacity demand and provisioning based on that overestimate. Yet overprovisioning has been a perfectly rational response to the realities of data center management. Realities including:

  • A lack of alignment between IT and lines of business
  • A lack of visibility into actual utilization relative to capacity
  • A lack of flexibility to do anything about it

Most IT infrastructure managers, facing those realities, mitigate the risk of not delivering the capacity the business needs by provisioning according to the hardware’s nameplate rating – that is, its maximum power draw. Even for those who provision based on estimates of actual power consumption, the inability to manage power consumption at the granular level of a desired circuit or chassis still leads to considerable stranded capacity in modern data centers.

Finding solutions to capacity inefficiency

The NRDC suggests that the data center industry adopt a simple metric such as average CPU utilization to bring visibility to the underutilization problem. Visibility is an essential step. But as Paul Fox, Aligned Data Centers’ Director of Data Center Operations, says, if IT infrastructure managers are going to raise average utilization rates, the data center needs to be flexible enough to a) handle spikes in the load; and b) add capacity quickly when it’s needed.

In a recent article in Mission Critical magazine, Fox explains what characteristics a data center needs to have in order to enable IT infrastructure managers to raise utilization comfortably. “When you have rack-level and infrastructure visibility, monitoring, and predictive analytics, and the data center is flexible enough to deliver new capacity on demand, then overprovisioning isn’t necessary to mitigate risk,” Fox says.

How the data center can support efficient capacity planning

The realities that have led IT infrastructure managers to overprovision are changing. There’s an increasing awareness of the importance of collaboration between lines of business, IT, and facilities. In new data centers, sophisticated DCIM tools enable visibility and predictive analytics. And new data center models enable timely responsiveness to capacity demands. So now, rather than hedging your bets against worst-case scenarios, you can provision based on actual utilization while keeping a close eye on growth and deploying new capacity as it’s needed.

Beyond mitigating the risk of capacity constraints, efficient capacity planning reduces costs as well. As Fox says, “Organizations understand that they’re overspending on data center power, cooling, and space. Given that those are the largest operational expenses in a data center – and they’re rising – the pressure is on to find ways to be smarter about the data center investment and deliver capacity more efficiently. The ultimate goal is to understand the true demand, to maximize CapEx and OpEx investment on each piece of data center infrastructure.”

In Mission Critical, Fox outlines five data center characteristics that enable you to achieve both risk mitigation and cost savings:

  1. Communication and collaboration between the IT manager who controls the compute and the data center manager who controls the power and cooling
  2. Plug-level monitoring and reporting for visibility into actual utilization
  3. Predictive analytics to know when to add capacity
  4. Plug-and-play infrastructure deployable just in time
  5. Consumption-based pricing to better align what you’re spending with what you’re getting

Read about each in depth in Mission Critical.

Bottom line

To raise utilization levels, IT infrastructure managers need visibility into actual utilization and a data center flexible enough to add capacity quickly. The benefits are tremendous: significant reductions in wasted energy and costs that actually align with your needs.

Aligned Data Centers is committed to enabling IT managers and data center managers to raise utilization levels, save energy, and reduce costs.