Breaking all known records by IBM. IBM Research has developed hardware & software technologies what will allow it to strap together 200,000 HDD to create a single storage cluster of 120 PB...
(PetaBytes) or 120 million GB. The drive collective, when it is complete, is expected to store 1 trillion files or 2 billion hrs of MP3 music.
The data repository is being developed for a business person with a capacity of 120PB, this huge storage device will be used for a govt-owned or federally-funded Super Computer or like others High Performance Computing (HPC). 120PB of capacity that you need to store global models of weather or infinitely weapon system simulations, both are rarely carried out by the commercial interests. It could be used to store a large portion of the internet like Google or Facebook or such a deep pockets clients. The largest systems currently in existence are generally around 15 PBytes though, as of 2010, Facebook had a 21PB Hardtop cluster, and now it’s much larger.
It features a new updated version of IBM’s GPFS (General Parallel File System) is a volume spanning file system which stores individual files across multiple disks in other words, instead of reading a multi TB (TeraByte) high resolution model at 100Mbps from each drive, the same file can be read in a massively parallel fashion from multiple drives. It has the ability to create more than 30,000 files per sec. and the GPFS system also supports redundancy and fault tolerance that means when a drive dies, its contents are rebuilt on a replacement drive automatically by the governing computer.