Dell Launches New Big Data Storage Configuration

By Chris Preimesberger  |  Posted 2012-07-23

Dell's key market target is the midrange company that ostensibly doesn't have to process huge data workloads on a regular basis. Nonetheless, the company is moving deeper into the storage and handling of big data workloads.

Dell on July 23 launched what it calls a Big Data Retention object and structured-data storage package that can, it claims, provide more effective management of that data for search and analysis, thus saving costs over time.

This package, actually a reconfiguration of already extant Dell products, combines Dell storage, the DX Object Storage Platform and RainStor database. Oh yes, and plenty of Dell custom services from the former Perot folks, too.

Standard M.O.: Plug It Right In

Dell's Big Data Retention system, aimed at enterprises that use--or are starting to use--data analytics as a business tool, follows the company's standard method of data center operation: It integrates directly with existing analytics platforms, should a company own any. The new hardware and software system serves as a capacious front-end repository for large data sets or an archive.

The new package can add capacity in increments of 2 terabytes and scale up to petabytes--and billions of objects--without the set-up and management issues and costs of traditional file and block storage, Dell Storage Vice President and General Manager Darren Thomas said.

This rack of machines also can serve as a standalone repository or as an analytics platform with Apache Hadoop, currently the most popular batch-level data analytics system in the enterprise world.

Thanks to more than a dozen company acquisitions and numerous new partnerships established in the last three years, Dell has put together most of the ingredients to build new-generation cloud computing systems in house.

Cloudera as Front End Running Hadoop

For example, with the Big Data Retention system, users can plug in Dell's Cloudera front-end management platform, Apache Hadoop running on Dell PowerEdge C- and R-series servers, Force 10 networking and a Crowbar deployment toolkit.

"Being able to cost effectively capture and store all of the relevant data makes it possible to gain insights that support innovation and business value," Thomas said. "The key is having the right data management solution to fluidly move data, tier it, dedupe it, protect it and archive it. To us, that means your data is fluid."

The Dell Big Data Retention system can provide an average data compression ratio of up to 40:1, which frees up disk space approximately 97 percent, Thomas said. This greatly reduced footprint can accelerate query access for analytics, he said.

The new system configurations are available now in the U.S., Thomas said.

Rocket Fuel