Virtualization and consolidation are among the key strategies of IT managers facing the threat of running out of data center space, power, and cooling.
(click image for larger view)
Slideshow: Google's Oregon Data Center
As data centers continue to face growing volumes of informaton to process and store, a series of new surveys is highlighting what has become a serious problem--data center capacity is strained and struggling to meet ongoing demands.
More than a third (36%) of data center facilities will run out of space, power, or cooling, or all the above in 2011 or 2012, according to the Uptime Institute, which recently surveyed 525 data center operators and owners, with 71% situated in North America. Of those that will run out of one or more data center lifelines, 40% plan to build a new data center, 62% plan to consolidate servers, and 29% plan to lease collocation space.
These recent pressures on data centers are due not only to the increasing amount of data being generated and stored by organizations of all stripes, but an increase in IT budgets for data center growth, which were stagnant or put on hold during the recession of the last few years, according to the Uptime Institute.
"We're looking at a lot of data center growth over the next year to 18 months, since IT budgets have stalled over the last few years," Matt Stansberry, director of content and publications at the Uptime Institute, said in an interview. "So now companies are upgrading services because they don't have a choice and as they upgrade the capacity the constraints increase at the data center."
Part of the problem facing enterprises is that most data centers were built 10 to 15 years ago to support mainframe technology and don't have the capabilities needed to support current technologies, David Cappuccio, Gartner vice president and chief of research for data centers, said in an interview. The good news, he said, is that vendors have been releasing products to ease the data burden.
"Over the last 2 years, the number of companies that state this is a big problem is beginning to shrink since vendors are helping out," Cappuccio said. "Vendors are offering products that use two-thirds less power and a higher performance."
IT is looking to meet growing demands for more computing power through consolidation, virtualization, and hardware upgrades. Seventy-eight percent of respondents are virtualizing and consolidating servers, according to the InformationWeek survey.
When new data centers are being built, IT is often taking a phased approach by buying portable data centers that can be added to when needed, Cappuccio and Stansberry said. Cisco and Hewlett-Packard recently introduced Containerized Data Centers to address this need.
Enterprise IT managers also are turning to automated tiering applications, available from numerous vendors, to reduce the amount of on-site storage, Those systems use pre-designated controls like usage, frequency, and value to store data on appropriate systems. They let enterprises store non-critical data in the cloud and keep critical data in the company data center, Cappuccio said.
"We see the data center of the future 10 to 15 times smaller, denser, and almost exclusively focused on mission-critical applications," he said.
A Gartner survey last November found that 47% of representatives from 1,004 large enterprises from eight countries ranked data growth in their top three challenges. This was followed by system performance and scalability at 37%, and network congestion and connectivity architecture at 36%. Sixty-two percent of respondents reported that they will be investing in data archiving or retirement by the end of 2011 to address the data growth challenge.
Servers running VMs are still just servers. Stick with security practices you know to minimize risk. Also in the new all-digital InformationWeek supplement: Trust but verify when it comes to hypervisor security. Download it now. (Free registration required.)
Multicloud Infrastructure & Application ManagementEnterprise cloud adoption has evolved to the point where hybrid public/private cloud designs and use of multiple providers is common. Who among us has mastered provisioning resources in different clouds; allocating the right resources to each application; assigning applications to the "best" cloud provider based on performance or reliability requirements.
InformationWeek Must Reads Oct. 21, 2014InformationWeek's new Must Reads is a compendium of our best recent coverage of digital strategy. Learn why you should learn to embrace DevOps, how to avoid roadblocks for digital projects, what the five steps to API management are, and more.