The flagship Hadoop product offers “zero-administartion” HBase and instant recovery
US analytics expert MapR has just released M7 – the “ultimate decision machine” for Big Data operations. The new product offers simplified, automated administration for the HBase database, increased performance, lower latency and gets rid of JVM (Java Virtual Machine) -related bottlenecks.
The M7 supports Big Data operations ranging from batch analytics to real-time database functions that can be performed with enterprise-grade reliability and security.
It was previously expected in the first quarter of 2013, but was delayed in the beta stage.
MapR was founded in 2009, by some of the same people that developed BigTable analytics at Google. The company specialises in products based on the open source Apache Hadoop framework – which is quickly becoming the de-facto standard in distributed computing applications.
The MapR M7 Edition is the company’s new flagship, which follows in the footsteps of free M3 and more advanced M5 products.
The updated platform is capable of delivering over one million operations per second with a ten-node cluster, and supports up to a trillion tables across thousands of nodes. It also provides instant recovery from failures, which, according to MapR, ensures 99.999 percent reliability.
M7’s zero-administration approach to HBase includes automatic region splits, no RegionServers and self-tuning with no downtime required for any operation, including schema changes.
“The number of enterprise-level deployments of Hadoop MapReduce is rising quickly, driven by a need to understand and potentially adopt this new business analytics platform for business applications,” commented John Webster, principal analyst at Evaluator Group.
“Responding to this demand, MapR delivers a distribution of Apache Hadoop that addresses many of the enterprise quality issues currently limiting its adoption in production data centres. With M7, HBase applications can access data directly without the redundancy of extra layers of communication yielding a single, scalable and more reliable data store that offers high performance and is easier to develop to and administer.”
MapR has also announced the integration of LucidWorks Search engine with its Big Data platform, to enable predictive analytics and advanced database operations. From next quarter, MapR users will be able to search not just through Hadoop data, but also through standard files without having to perform any conversion or transformation.
Last month, MapR announced a partnership with Canonical to bring its free M3 Edition to the Ubuntu operating system. The MapR package for Ubuntu and the new OpenStack Juju Charm were officially released on 25 April 2013.
How well do you know open source software? Take our quiz!