In the never-ending race to build the biggest and most bitchin’ hardware on the planet, IBM has taken the lead. Again!
IBM’s newest pet is their 120 petabyte (120 million gigabytes) storage array system, a disk drive system made up of 200,000 drives. It will hold 1 trillion files. This far surpasses the current title holder of the world’s-largest-storage array, that has a measly 15 petabytes.
To put the ridiculously large number of 120 petabytes into proportion, it could hold 24 billion standard MP3 files, or replicate 60 times over the current biggest backup of the Internet from WayBack Machine’s 150 billion stored webpages.
Surprisingly this new super-computer storage system being created in IBM’s Almaden, California facility actually has a use. Even more surprising is that they already have a customer for it; a client running in-depth simulations for a super computer detecting real world weather and climate phenomena.
IBM believes that this new breakthrough in ‘fringe’ hardware could soon have current-day uses for many of their enterprise clients. Bruce Hillsberg, IBM’s Director of Storage says that, “this 120 petabyte system is on the lunatic fringe now, but in a few years it may be that all cloud computing systems are like it. Just keeping track of the names, types, and other attributes of the files stored in the system will consume around two petabytes of its capacity.”
The Nitty Gritty
Obviously IBM struggled with the standard issues when dealing with large-scale storage including cooling, fail safes and rack spacing, but IBM thinks they have done the trick. The new storage system solves cooling issues by using water cooling in space of the traditional air. And has built in fail-overs by not only storing multiple data copies on several disks but also has the ability to pull data from alternate drives should the initial ones go down. Also, if many disks fail simultaneously the system goes into overdrive by speeding up the rebuilding process.
Apparently they also have a million-year guarantee.