IBM announced a patented software defined storage technology this week that it says can reduce digital storage costs up to 90 per cent in some cases. It said the innovation is ideal for big data applications that at times cost big money.
The patented technology behind Elastic Storage includes a method for optimising deduplication in a data storage system by moving the duplicated data onto the most economically priced storage platform.
The method is notable because in many cases cloud storage isn’t as cheap as many assume (especially for big data apps), and because enterprises are still getting dinged (financially and time-wise) for high I/O applications.
IBM said the technology is well-suited to data-intensive applications that require low latency like financial analysis, weather modelling, and scientific research for instance, making these applications more suitable to place in a cloud-based environment. Its architectural limits stretch into the thousands of “yottabytes”; one yottabyte is one billion petabytes.
“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.
The company has used the software defined storage technology to underpin its Watson cognitive computing as a service platform, which can scan through hundreds of millions of pages of structured and unstructured data in seconds.
It also works with the OpenStack platform (Cinder and Swift), and will be used to underpin a range of IBM software services like big data analytics that are based on the open source platform and use storage virtualisation at their core. It will be available on SoftLayer later this year.
“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,” Rosamilia added.
The event covers all sides of software defined technologies through the prism of enterprise organisations. It targets both the CIO for the overall business case behind SDx but also the engineers, working on the nitty-gritty details of the SDDC and SDS.