IBM has made progress over the past year in developing a new water-cooled, modular mass storage system designed to be highly fault-tolerant and make more efficient use of electric power and cooling capacity.
Called CIB (Collective Intelligent Bricks), the storage system is under development at IBMs Almaden Research Center in San Jose, Calif. IBM officials discussed its work on the prototype intelligent brick storage system with reporters and editors Wednesday as part of a general briefing on its storage research efforts.
CIB is an effort to make highly reliable storage systems from less-reliable standard components, said Robert Garner, a research center staff member and co-leader of the development project at IBM. The storage units are literally designed as square bricks that can be assembled into large, Rubiks Cube-like blocks.
Each brick has its own CPU, memory, cache and networking connections. This makes the brick "appliance-like and easy to add by end-users," Garner said.
Individual bricks can have varying amounts of storage capacity of up to 80GB. The bricks can be assembled into systems containing terabytes or even petabytes of storage capacity.
Rather than using typical wire prongs or plugs, the bricks are connected with a novel technology called "capacitive coupling," in which one block is mated to the next through a conductive plate. Garner displayed two different prototype couplers, one made of Mylar and the other of thin ceramic. The couplers are actually able to transmit data through the extremely thin layer of air between one brick and the next, Garner said.
One of the key goals is to make storage systems that are easier to build and maintain by customers, Garner said. It should be easy enough, he said, to enable a data center technician "to walk up to the system, attach the storage and then walk away."
IBM also believes the bricks will allow it to design storage systems that are as much as three orders of magnitude more scalable than existing storage arrays while reducing complexity and simplifying maintenance, he said.
The bricks can use cheaper, less reliable components because the failure of a single brick or even several bricks will not shut down the system or corrupt data in the other bricks, because the data is mirrored in other sections of the array or in backup systems, he said. As a result, defective bricks can stay in place until they are replaced as part of scheduled maintenance, Garner said.
The bricks can be assembled "in a big pile of bricks or it could be a one-dimensional wall of bricks," which could make maintenance even easier. IBM is studying which configurations would be most effective for maintenance, Garner said.
IBM is experimenting with water cooling with these systems because it is becoming increasingly difficult to provide efficient air cooling for the huge volume of storage devices that customers are cramming into their data centers, Garner said. He and other IBM officials declined to say when the experimental IceCube technology might be released as a product.
Garner indicated that his task was to demonstrate the effectiveness and practicality of the system before the company decided whether to release it as a product.
The system offers significant potential benefits to customers, he said, because liquid cooling can save as much as seven times the amount of floor space required for effective air cooling and reduce the amount of power used for cooling by 20 percent to 50 percent, he said.
The laboratory model displayed by IBM used aluminum cooling jackets to circulate water through stacks of individual bricks. The water would pass through an external heat exchanger on a building roof or in an outdoor tank, much like an air-conditioning system, he said.