2 min read
Today marks one of the biggest announcements in the history of Hadoop. Google -- the pioneer of MapReduce, the company that ushered in the era of Big Data -- has now opened up their infrastructure so organizations can more effectively process and analyze their own Big Data. To enable more companies to do this successfully Google has partnered with MapR.
MapR and Google announced this partnership at Google I/O a move that further validates the performance, ease of use, dependability and scale of MapR’s platform. MapR’s Distribution is emerging as the defacto standard for Hadoop deployments in the cloud.
Google is also able to demonstrate a significant Hadoop price/performance breakthrough using MapR, completing a one terabyte (TB) TeraSort job on Google Compute Engine in 1 minute 20 seconds. This result was achieved on a cluster with 1256 nodes, 1256 disks and 5024 cores. This result compares favorably with the existing world record of one minute two seconds that was set with a physical cluster with more than four times the disks, twice as many cores, and 200 more servers. What's even more compelling is the cost comparison -- $16 for the Google Compute Engine test compared to a required outlay of around $5M for the physical infrastructure.
Through the Google Compute Engine infrastructure, MapR makes big data accessible to any size business by leveraging the Google Compute Engine to provide a high performance, scalable, predictable, and easy to provision Hadoop infrastructure.
Today, we announced a private beta where customers can get hands-on experience with these performance, and ease of use benefits. If you’re a customer interested in participating in the Beta, please visit mapr.com/google to apply.
Stay ahead of the bleeding edge...get the best of Big Data in your inbox.