Scaleout Software, a provider of in-memory data grids (IMDGs), announced the availability of ScaleOut hServer V2, which incorporates new technology to run Hadoop MapReduce on live data. This new platform now gives users the ability to analyze live data using standard Hadoop MapReduce code, in memory and in parallel, without the need to install and manage the Hadoop stack of software.
According to the vendor, the new version ScaleOut hServer V2 has demonstrated a 20x speed up in Hadoop execution times and delivers real-time analytics by providing fast execution of standard Hadoop MapReduce code. This is an improvement over the initial ScaleOut hServer - was released in April 2013 - that provided low latency data access for Hadoop.
“What hServer V2 is providing is a self-contained Hadoop MapReduce engine, which means the standard Hadoop open source distribution does not have to be installed,” explained Bill Bain, CEO, ScaleOut Software. ScaleOut hServer is not intended to replace Hadoop, but instead integrates MapReduce functionality and selected Hadoop components within ScaleOut’s in-memory data grid and analytics engine, reducing the installation time from a few days to minutes and simplifies deployment, the company says.
“The community of Java users has really migrated toward Hadoop MapReduce and so the hServer V2 is a way to bring them to this platform and let them benefit from real-time performance while using a familiar programming model,” added David Brinker, COO, ScaleOut Software. ScaleOut hServer is compatible with most Java-based Hadoop MapReduce applications developed for the standard Hadoop distributions. According to the vendor, only a one-line code change is required to execute applications using ScaleOut hServer.
ScaleOut hServe is available in both a free community edition as well as several commercial editions.
Visit www.scaleoutsoftware.com for more information.