IBM and Fujifilm have figured out how to fit 220TB of data on a standard-size tape that fits in your hand, flexing the technology's strengths as a long-term storage medium.
The prototype Fujifilm tape and accompanying drive technology from IBM labs packs 88 times as much data onto a tape as industry-standard LTO-6 (Linear Tape-Open) systems using the same size cartridge, IBM says. LTO6 tape can hold 2.5TB, uncompressed, on a cartridge about 10 by 10 centimeters (4 by 4 inches) across and 2 centimeters thick.
The new technologies won't come out in products for several years and may not be quite as extreme when they do, but the advances show tape can keep getting more dense into the future, said Mark Lantz, manager of IBM's Advanced Tape Technologies Group.
Tape is already the least expensive storage medium per bit, easily beating spinning hard disks or solid-state drives. The trade-off is slower retrieval time -- about a minute -- but this makes tape perfect for archiving large amounts of infrequently used data, Lantz said. IBM thinks it's perfect for cloud storage and is working on other advances toward that end, such as an object-storage interface. The interface could make tape systems work with cloud object storage systems such as OpenStack Swift, IBM says.
But the core advantages of tape all come back to density, and the technology IBM is demonstrating this week at the National Association of Broadcasters show in Las Vegas boosts this in several ways. The tracks on the tape are narrower, the heads are smaller, and even the particles of barium ferrite that store each bit are finer. All are now measured in nanometers, so the movement of the heads has to be more precise, too. It's accurate to within less than 6 nanometers, IBM says.
The density of tape storage doubles about every two years, and that's likely to continue over the next decade, Lantz said. But innovations take a while to get from labs to enterprises. For example, tape technologies IBM developed in 2007 are hitting the market only now. It's likely the latest prototypes will take about as long, counting both development and product design, he said.
And when those future tape cartridges and drives go on sale, they probably won't hold quite as much as they did in the lab, Lantz noted. That's because IBM tries to make new products compatible with previous generations. For example, if the heads were too small they might not be able to read the tracks on older tapes, Lantz said.