NEC HYDRAstor is a disk-based

grid storage Grid energy storage (also called large-scale energy storage) is a collection of methods used for energy storage on a large scale within an electrical power grid. Electrical energy is stored during times when electricity is plentiful and inexpe ...

system with

data deduplication In computing, data deduplication is a technique for eliminating duplicate copies of repeating data. Successful implementation of the technique can improve storage utilization, which may in turn lower capital expenditure by reducing the overall amou ...

for

backups In information technology, a backup, or data backup is a copy of computer data taken and stored elsewhere so that it may be used to restore the original after a data loss event. The verb form, referring to the process of doing so, is "wikt:back u ...

and

archiving An archive is an accumulation of historical records or materials – in any medium – or the physical facility in which they are located. Archives contain primary source documents that have accumulated over the course of an individual or ...

, developed by

NEC Corporation is a Japanese multinational information technology and electronics corporation, headquartered in Minato, Tokyo. The company was known as the Nippon Electric Company, Limited, before rebranding in 1983 as NEC. It provides IT and network soluti ...

. A HYDRAstor storage system can be composed of multiple nodes, starting from one up to 100+ nodes. Each node contains standard hardware including disk drives, CPU, memory and network interfaces and is integrated with the HYDRAstor software into a single storage pool. HYDRAstor software incorporates multiple features of distributed storage systems:

content-addressable storage Content-addressable storage (CAS), also referred to as content-addressed storage or fixed-content storage, is a way to store information so it can be retrieved based on its content, not its name or location. It has been used for high-speed storage ...

, global data deduplication, variable block size,

Rabin fingerprint The Rabin fingerprinting scheme is a method for implementing fingerprints using polynomials over a finite field. It was proposed by Michael O. Rabin. Scheme Given an ''n''-bit message ''m''0,...,''m''n-1, we view it as a polynomial of degree ''n''- ...

ing,

erasure code In coding theory, an erasure code is a forward error correction (FEC) code under the assumption of bit erasures (rather than bit errors), which transforms a message of ''k'' symbols into a longer message (code word) with ''n'' symbols such that the ...

s, data

encryption In cryptography, encryption is the process of encoding information. This process converts the original representation of the information, known as plaintext, into an alternative form known as ciphertext. Ideally, only authorized parties can decip ...

and load balancing.

History

HYDRAstor project was started in 2002 by Cezary Dubnicki and Cristian Ungureanu in NEC Research in Princeton, NJ. Prototype version was implemented and evaluated in 2004. After another 3 years of development, first version of HYDRAstor was brought to the market in US and Japan. Subsequent version with improved software and hardware were released in following years, with latest version, HS8-5000, providing 72 TB raw storage per node, up to 11.88 PB of raw capacity in its maximum configuration.

Main features

HYDRAstor can be scaled from single node to 165 nodes in a multi-

rack Rack or racks may refer to: Storage and installation * Amp rack, short for amplifier rack, a piece of furniture in which amplifiers are mounted * Bicycle rack, a frame for storing bicycles when not in use * Bustle rack, a type of storage bin ...

grid appliance. Capacity and bandwidth can be scaled independently by using different types of nodes: * storage nodes – adding capacity * hybrid nodes – adding both capacity and performance HYDRAstor supports online expansion, with automatic data migration and with no downtime. In standard configuration, HYDRAstor provides resiliency to up to 3 concurrent disk or node failures. Failures are automatically detected and data reconstruction is automatically performed, which means that if time between failures is enough to reconstruct data, system can withstand any number of them.

References

{{NEC Corporation Backup software Backup