December 7, 2009 – As much as we might rail against the terminology itself, and despite the rampant hype around the technology, cloud storage is here to stay. And at least for a while, the seemingly hundreds of cloud storage providers can survive (pending the inevitable shakeout), jockeying and jousting for position and differentiation.
As cloud storage garners the attention of both large and small IT organizations, technological advances will come rapidly next year.
I recently spoke to Sajai Krishnan, ParaScale’s CEO (and fellow skiing enthusiast) about what to look for in cloud storage in 2010. Here are his predictions and comments.
Virtualization will drive adoption of private clouds in the enterprise. Virtualization has driven huge efficiencies in organizations but the weak link today is the storage infrastructure behind virtualized servers. The need to eliminate the SAN bottleneck and automate provisioning, configuration, management and recovery across the compute and storage tiers will drive enterprises to begin to adopt cloud storage.
“The SAN performance issue is the controller,” says Krishnan. “VMware has a best practices for storage page that starts by saying you need to figure out what the I/O requirements are for each of your applications. Any storage administrator would love to have that information, but admins often don’t have a clue about the I/O requirements of their VMized applications.”
“You have controller bottlenecks. How many disks are you going to stack up behind the controller as you scale out? It’s much more manageable when you can buy cheap servers like popcorn and just keep scaling out [in a cloud architecture].”
Service providers will start to unify cloud computing and cloud storage. In 2009 service providers began expanding cloud storage offerings. The cost and management efficiencies provided a much-needed storage alternative for consumers, SMBs and enterprises. To further drive efficiencies, cost savings and management ease of use, service providers will begin executing VMs directly on cloud storage platforms. Unifying cloud compute and storage infrastructure will also provide a platform for service providers to build new value-added services.
“With large cloud storage implementations you discover that 90% of the data is cold, and you have a lot of CPUs idle,” Krishnan explains. “Some people are looking at running hypervisors and VMs on the storage nodes.”
The middle tier emerges. The strategic importance of a low-cost, self-managing tier that provides a platform for analysis and integrated applications will emerge in organizations with large stores of file data. This middle tier will provide opportunity for administrators to automate storage management and optimize for performance and cost; support large-scale analysis, while eliminating related data migration and administrative tasks; and enable “cloud bursting,” the seamless ability for service providers to offer spillover capacity and compute to enterprises.
“The middle tier will expand significantly next year,” says Krishnan. “Traditionally, you have the processing tier and the archive tier. But now you’ll need a smart middle tier that’s going to keep the 90% of data. The archive tier is ok, but it’s very inflexible and could be proprietary. The middle tier is priced like the archive tier, it’s persistent, and it’s ‘burstable.’”
Krishnan says that ‘cloud bursting’ refers to the ability to burst into the public cloud for certain periods of time, but not use the public cloud as the repository where you keep data on a permanent basis (although if you Google the term you’ll wind up with altogether different discussions and clips from The Men Who Stare at Goats film.)
Commodity hardware displaces proprietary storage. “Just as Linux displaced expensive server gear with its attractive commodity footprint, Linux-based cloud storage will displace expensive legacy storage for the same reason: it gives the user choice and it’s inexpensive, highly scalable and easy to manage,” says Krishnan.
Opex, not capex, will emerge as the most important criteria driving storage purchases. “Management and operating costs will figure much more prominently in storage decisions in 2010. Maintenance costs on existing gear will be under heavy review with the emergence of commodity-based hardware storage options. Customers will look for a storage platform that is self-managed – including the ability to monitor, configure, manage and heal itself,” according to Krishnan.
Cloud becomes an action verb. “We’ve already seen ‘cloud’ taken to new heights as an overused adjective and noun. In 2010, marketers will outdo themselves by clouding the landscape with more product names and descriptions. Admittedly, this prediction is somewhat tongue-in-cheek, but unfortunately fairly close to the mark,” says Krishnan.
(ParaScale is a cloud storage software provider that recently released the 2.0 version of its software. See “ParaScale beefs up cloud storage platform.” )