Growth is normally a boon for any business. Servers hum faster when an ecommerce site attracts more customers (and more credit card transactions). When storage requirements for a new business that handles documentation for large companies suddenly escalate, executives high-five each other.
Scaling can be so costly, though, that fast growth isn't always a positive. Fortunately, new technologies can help a company ramp up quickly and efficiently, removing some of the pain of having to expand a data centre. Instead of being faced with a major capital outlay that offsets new revenue, these innovations make the impact of scaling up a data centre to meet demand less of a drain.
1. Modular Data Center Additions But Not Modules
Most large companies know they can turn to Microsoft, HP and others to purchase entire data centre modules. They provide a way to scale quickly, but usually a high cost.
A new addition might consist of multiple racks and as few as 30, assembled remotely so that the cooling systems, power, cabinets and servers are all ready to go by the time they are installed. (The company can also install racks with up to 10,000 servers for larger companies.)
One key component: A power busway that provides greater flexibility for adding modules. Major electrical manufactures, including Siemens, Snyder, PDI and Universal Electric, offer busway solutions, Cantrell says. Verne Global standardized on Universal Electric Starline infrastructure for its modular data centres, he says, given the company's track record and its monitoring options, which let the company provide "very granular feedback" to customers.
2. Power Enterprise Pools: 'Elastic Capacity'
One challenge in scaling a data centre is knowing when to invest in servers and how many to add. There are often spikes in demand, but it's difficult to predict when they will occur - and what to do when you don't need the extra capacity.
One answer: Enterprise Pools, a scaling infrastructure from IBM that works with the IBM Power servers. "Demands for data application is driving clients to look at continuous availability," says Steve Sibley, the director of IBM Power Systems. "When new apps roll out, they need to be able to scale rapidly or recover IT resources and scale down. There needs to be an elastic capability similar to the cloud and a way to not overpay for capabilities."
The idea of managing down to the processor level isn't a new concept. What is new is that data centers can add move, and remove virtual processors and memory for spikes in usage or maintenance. They don't have to pay for extra capacity but only pay for the servers they need. They also pay only for a portion of the full cost of processors and memory up front. IBM estimates the cost of these pools is $0.67 per hour, based on per-day costs for processor and memory allocations. Data center operators can manually adjust the service levels for an application as often as they want, then use those service levels for automation.
Sign up for CIO Asia eNewsletters.