EMC introduces 'big data' computing system

EMC has introduced the Greenplum Data Computing Appliance, an integrated data warehouse system using massively parallel processing architecture.

The purpose-built and integrated database, compute, storage and networking system is shipping 75 days after EMC's acquisition of Greenplum, and is designed to enable "big data" cloud analysis.

This analytic capability is of growing importance to organisations for the efficient storage, management and fast retrieval and manipulation of terabytes of detailed data from various sources across networks, the web, surveillance systems and sensors, according to EMC.

Scott McNealy, EMC Data Computing Products Division executive advisor, claimed that the appliance positions EMC as a major infrastructure player with large and small, casual and critical data across the enterprise for real-time access and advanced business intelligence analytics.

"Greenplum offers next-generation data analytics technology allowing customers to monetise this data. That's what the 'big data' era is about," he said.

Built using the new Greenplum Database 4.0, the appliance's massively parallel processing architecture delivers a data loading performance of 10TB an hour, according to the vendor, which offers up to three times more scalability and up to four times as many database cores than competitive systems.

This makes it twice as fast as Oracle Exadata systems and five times as fast as systems from Netezza and Teradata, EMC said, enabling more data to be analysed faster and at lower costs.

The system is available in half-rack, full-rack and multiple-rack appliance configurations for terabyte to petabyte-scale requirements, and comes i ntegrated with EMC's replication, backup and recovery and deduplication technologies.

Greenplum Database 4.0 is also shipping as a licensed software-only solution for x86 server deployments and integrated infrastructure solutions such as the Virtual Computing Environment coalition Vblock Infrastructure Packages. A Single-Node Edition is also available to download for free.

Clive Longbottom, service director at analyst firm Quocirca, agreed that data growth has been high for a long time and that companies have been struggling to deal with it.

But he believes that appliances do not necessarily fit every requirement, and will facilitate a services play by EMC.

"Vendors have done data marts, data cubes, in-memory databases and so on, all aimed at being the ultimate solution to dealing with ever-growing data volumes, " he said.

"EMC is no different. There is no one answer to the data problem, and trying to lump it all together under the term 'big data' is, at best, misleading.

"Greenplum offers some of the smarts, but the business has to remain in control of the underlying principles of what the data is there for, what the business needs from the data, and the basic policies as to how this will be architected."