Storing Big Data on Tape

April 29, 2011

A new article discusses one of the most effective methods for storing Big Data: tape. Jason Bovberg states, “The truth is, the demise of tape has been greatly exaggerated. In fact, many argue that there’s just no better way to store ‘Big Data.’ According to Matt Starr, SpectraLogic’s CTO, the amount of data stored on tape continues to surge, as massive and growing digital archive demands compel users to seek practical and economic ways to address escalating data volumes. Spectra Logic expects worldwide tape archive capacity to grow more than sixfold over the next five years—from just under 13 exabytes in 2010 to over 81 exabytes by 2015, driven by both new digital content and extended storage timelines.”

Bovberg quotes Matt Starr who recently wrote, “Tape is Big Data… Eighty percent of the world’s data is stored on tape, and tape is the only media that can scale to exabyte(s) and still be cost effective. In fact, tape is the only cost-effective method of storing Big Data. Tape storage is denser than disk storage, costs less up-front and is 10 times less expensive to operate over time than a disk-based solution. I’m not implying that disk does not have a play in the Big Data world; it is just not well suited as the ‘meat’ of a storage environment.”

Bovberg continues, “But what about ensuring the integrity of data stored on tape for long periods of time—say, three, five, or even ten years? To that end, Spectra Logic has announced that it is offering free data integrity verification across its complete line of T-Series tape libraries from SME to Enterprise. Spectra’s BlueScale Data Integrity Verification for tape libraries is an industry first and an important long-term data reliability feature that ensures data written to tape is retrievable now and for years into the future. With Data Integrity Verification, Spectra’s tape libraries are the only tape storage systems on the market today that actively, automatically check the media and the data on tape throughout the storage life of the data.”