by Mark Kidd

EMC’s Greenplum Analytics: 1,000-Node Hadoop Testing and Development Cluster

EMC has announced the activation of the Greenplum Analytics Workbench, a 1,000-node cluster with 24 petabytes of physical storage that will act as a lab environment for accelerating development of Apache Hadoop. EMC Greenplum will use the Analytics Workbench to test the limits of scale-out infrastructure technology, refine models for applying Big Data analytics, and an environment for running scale validation of the Apache Hadoop codebase.

The Greenplum Analytics Workbench is the result of hardware and software companies coming together to facilitate its development, including EMC, Intel, Micron, Seagate, Switch and VMware. The cluster takes advantage of Mellanox Technology’s 10/40GbE and FDR 56Gb/s InfiniBand interconnect solutions, and SuperMicro provided resources for data node infrastructure and integration.

Greenplum is working with the Apache Software Foundation to make results from the Analytics Workbench available to the open-source community in an effort to accelerate Hadoop development. The cluster will also be made available to members of Greenplum's training and certification classes for Hadoop beginning Summer 2012, which will offer any individual who successfully completes the course access to the Greenplum Analytics cluster to use as a sandbox environment.

Individuals or organizations looking for more information on access to the Analytics Workbench can visit the product page.

Discuss This Story