IBM's Watson Behind Software Defined Storage Offering

The software defined storage game has just gotten a little hotter with IBM throwing its hat into the ring. Big Blue's Elastic Storage, which uses Watson technology, pools storage resources across a variety of storage systems in locations, abstracting the resources to look like one big storage system. IBM will offer it as software and make it available as a cloud-based service through its SoftLayer Infrastructure-as-a-Service platform.

“Digital information is growing at such a rapid rate and in such dramatic volumes that traditional storage systems used to house and manage it will eventually run out of runway,” said Tom Rosamilia, senior vice president, IBM Systems and Technology Group. “Our technology offers the advances in speed, scalability and cost savings that clients require to operate in a world where data is the basis of competitive advantage.”

Born in IBM Research Labs, the patented Elastic Storage technology is suited for the most data-intensive applications, which require high-speed access to massive volumes of information. Examples include seismic data processing, risk management, financial analysis, weather modeling and scientific research.

The Elastic Storage architecture was part of Watson, the "cognitive-computing" system that famously won the TV quiz show Jeopardy! in 2011 against two previous human winners. Watson was able to load 200 million pages (more than 5 terabytes of data) into its memory within minutes during its Jeopardy! appearance.

Watson has become the foundation of many of IBM’s recent technology initiatives. The company plans to offer cognitive computing as a service for applications that include retail, healthcare and beyond.

The benefits of software defined storage include moving less-used data to less expensive commodity storage and using faster, more expensive storage, such as Flash, for the important, urgently needed stored info. Guided by real-time Watson-powered analytics, IBM policies automatically match the types of data to the most appropriate storage systems.