Apache Spark (DataBricks) breaks previous sort record
29th April 2015

Is MapReduce coming to an end?
DataBricks recently published their benchmarks results for sorting 100 TB of Data over AWS Ec2 Machines, The results have clearly proven it as general purpose distributed processing framework which is meant for both in-memory and on-disk. They have used recent version of Apache Spark(Spark 1.1).

Write your comment here ...

Leave a Reply