This article can also be found in the Premium Editorial Download "Storage magazine: What's in store for storage technology in 2009?."
Download it now to read this article plus other related content.
In a financial meltdown, it's difficult to fund research aimed at solving truly big problems, such as lowering the cost of managing storage.
Today, storage admins write scripts that automate many tasks. According to Sandeep M. Uttamchandani, research staff member and storage PIC chair at the IBM Almaden Research Center in San Jose, CA, as QoS goals, devices and protocols increase, "it becomes difficult to ensure performance, provisioning, availability and security simply by writing ad-hoc scripts."
Uttamchandani is working on IBM's Storage Management Analytics and Reasoning Technology (Smart) project to develop algorithms that might create models for storage components and workloads, and a "first-of-a-kind optimization [storage] engine" that considers constraints such as budget and outputs a schedule of actions.
Whether this research will come to fruition is unknown. But, in an uncertain economy, it's reassuring that it's being funded.
This was first published in December 2008