IBM Builds Monster 120-Petabyte Data "Drive"
This massive storage is for a supercomputer used by an unnamed client, and includes 200,000 physical drives.
The data storage group at IBM's Almaden, California, research lab is currently building a 120 petabyte drive comprised of 200,000 conventional hard disk drives working together. The team is throwing this storage monster together for an unnamed client that needs a new supercomputer for detailed simulations of real-world phenomena (like weather, climate changes etc).
Despite the insane capacity, the technologies that were developed to handle the monstrous repository could enable similar systems for more conventional commercial computing, claims Bruce Hillsberg, director of storage research at IBM and leader of the project. "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."
The technology behind the 120 petabyte "drive" includes modified horizontal drawers stacked inside typical data center racks which are significantly wider so that more disks can be crammed into nearly the same amount of physical space. The IBM engineers also ditched the standard fan setup as a cooling system, and went with a more reliable liquid cooling design to keep the drives chilled and to reduce the overall energy consumption
In addition to modifying the rack system, IBM also developed a file system known as GPFS to enable supercomputers faster data access. This new file system spreads individual files throughout multiple disks so that numerous parts of a file can be read or written simultaneously. GPFS also enables a large system to keep track of its many files without "laboriously" scanning through every one. Ultimately this system on a whole is not expected to lose any data for a million years without making any compromises on performance.
Hillsberg added that keeping track of the names, types, and other attributes of the files stored in the system will consume around two petabytes of its capacity. To put this number in perspective, 120 petabytes equals to 120 million gigabytes which theoretically could hold 24 billion 5MB MP3 files or 60 copies of the Internet Archive's WayBack Machine.
To read more about IBM's 120 petabyte drive, head here.
- Storage,
- IBM,
- 120-petabyte ,
- IBM-Almaden ,
- Bruce-Hillsberg ,
- rack-mount ,
- GPFS
- Will Tim Cook Become the Next Steve Ballmer?
- UK Launch for Google TV Confirmed by Eric Schmidt
- ViewSonic 7x to Launch Next Month at £315
- OWC's $129.99 60GB SSD Does 556MB/s Reads
- Acer Says Tablet Fever is Already Cooling Down
- BT to Raise Prices of Landline Calls and Line Rentals
- Microsoft Making File Copying Better in Windows 8
- The Razer Blade is a Stunning New 17" Gaming Laptop
- Microsoft Shows Off New Quad-core Tablet
- LG Unveils Ultra-slim New LCD Monitors
- A Pentium III Autopsy Using an Electron Microscope
- Motorola Tough Defy+ Smartphone Gets a UK Release Date
- Sainsbury's Adds iPad Docking Stations to Trolleys
- Like Tom's Hardware? Then Get Your Free VIPRE Antivirus
- Modern Warfare 3 Will Have Full Steam Support
- Apple Files Dynamic Cell Memory Patent
- HP May Spin-Off PC Business Rather Than Sell
- Corsair Releases Two New Force Series GT SSDs
The technology is already there, the method is new.
Do I win a prize for finding the "check if anyone reads this" sentence?
There is no way this could run for a million years and not lose data - has someone just got their sums wrong when looking at MTBF figures?
(It's rather like saying a hybrid car can do 120mpg when the electric only range is 30 miles and in hybrid mode it does 60mpg.)
^
"Ultimately this system on a whole"
the complete "drive" wont lose any data.
but they'll have to replace the 200k independent drives every x years
For a million years... so you will be able to buy replacement drives a million years from now?
It's like the old joke "I've had the same broom for thirty years", "Really?", "Yes, in that time I've replaced the head ten times and the handle three times, ..." so you could say that while the replacement drives are available the chances of losing data due to multiple drive failure (beyond the ability of the array to recover) is "once in a million years", but that's not the same as saying it won't lose any data for a million years. We've not been around long enough to make any predictions that far in advance. On a related note, there were plans to use the type of cement Roman's used for nuclear waste because we know it will last thousands of years - modern cement has not been around long enough to "know" it can last long, no matter what predictions might say.
They didn't need to develop a new file system. There is a certain open source file system that could provide that... ZFS? as in "Zettabyte File System"? Just because it was invented by Sun won't they use it?