Of the many functions involved in running a data center, none is arguably as important to a facility's longevity as capacity planning.
TechTarget defines data center capacity planning as "the establishment of a strategy that ensures an IT organization's computing resources, power load, footprint and cooling capacity will be able to meet the workload demands of its users and customers." Compliance and security can also be added to this list. In addition to scaling efficiently, data centers must also be able to scale responsibly.
Capacity planning is difficult. The success of your business – and if you're a cloud vendor, your clients' businesses –depend entirely upon your ability to scale IT resources quickly, effectively and securely. To help you succeed in this endeavor, below is a list of a few critical best practices for data center capacity planning:
1. Realize that capacity planning never ends
Capacity planning is not a monthly, quarterly or annual project. It is an unceasing task that impacts the day-to-day success of a data center. This is mainly because daily usage of IT resources and supporting infrastructure (cooling, environmental monitoring, security, etc.) need to be closely monitored for in-the-moment usage spikes or drop-offs. In today's IT landscape, capacity needs can change within an hour – we're no longer just planning a few months or even weeks outs. Data center operators need to be ready to accommodate capacity shifts almost immediately.
Furthermore, before data center managers can plan for future purchases of new equipment, they need to know their current usage metrics like the back of their hand. This means having insight into this information over a continuous period, rather than a few time-specific reports. For this to be possible, managers need at-a-glance access to the complete scope of data center performance, at all times.
2. Dissolve silos between business stakeholders and IT
Often, the lines of communication between data center workers and business stakeholders are too thin. According to industry expert Bill Kleyman, one of the best ways to succeed at capacity planning is to bridge this gap.
"Upper-level IT managers must have their data center forecasting views directly in line with the goals of the business," Kleyman wrote. "By understanding a company's business growth strategy, IT executives are able to better forecast growth within their data centers."
Likewise, any chasm between facilities (those who handle power consumption and environmental monitoring) and IT (the teams responsible for racks, cabinets, servers and other network equipment) will hinder a data center's ability to respond to changes in overall capacity, in the moment, and in the future.
3. Strong DCIM is mandatory
A data center without data center infrastructure management (DCIM) software is like a computer without an operating system. What's more, without DCIM, capacity planning is more or less impossible.
One of DCIM's primary functions is the aggregation and analysis of metrics throughout the entire data center, including environmental conditions, power consumption, the status of equipment in use and much more. On a day-to-day basis, this helps data center staff maintain operational efficiency by identifying sources of waste or potential causes of downtime early. All of these insights can also be used to improve capacity planning.
Best-of-breed DCIM makes it easy for operators to complete tasks related to capacity planning. This includes identifying how the inclusion of new servers will affect temperature and power consumption, the extent to which a facility's infrastructure can handle unexpected spikes in network traffic and much more.
Managing a data center's capacity is a complex undertaking, but it's one that DCIM can simplify.