MapR Enhances Performance With Fusion-io SSD

MapR Technologies, Inc. announced at Hadoop Summit the results of joint testing with Fusion-io, Inc. using the Fusion ioMemory platform and the MapR M7 big data platform.

The combined solution accelerated performance 25 times faster for read intensive Apache HBase applications.

HBase application performance throughput has previously been limited by disk storage bottlenecks. The combined performance of Fusion-io and MapR break through these performance barriers to offer an solution for performance-sensitive NoSQL applications.

MapR’s testing results were obtained on a MapR cluster with a 1.2TB Fusion ioDrive2. The ioMemory platform is built to accelerate organizations’ most important applications, such as HBase, which integrates with the M7 platform. Unlike SSDs, Fusion ioMemory platforms are architected to manage flash like memory, providing low latency performance for databases in demanding datacenters.

"Customers requiring big data analytics seek reliable, fast, and easy to implement solutions," said Gary Orenstein, Fusion-io EVP. "As these test results demonstrate, running MapR on Fusion ioMemory delivers significant acceleration, while simultaneously ensuring data reliability in a solution that fits current datacenter infrastructure."

"This record is significant because it eliminates one of the barriers to HBase adoption in high-performance environments," said Bill Bonin, VP business development, MapR. "Where information assets are growing at unprecedented rates, enterprises must respond quickly with scale-out performance in order to benefit from the full power of business analytics."

The MapR enterprise platform supports a set of mission-critical and real-time production uses. MapR brings dependability, ease-of-use and world-record speed to Hadoop, NoSQL, database and streaming applications in one unified big data platform. MapR is a distribution for Hadoop that supports standard Linux commands and provides POSIX-compliant NFS access.