Apache MapReduce

Apache MapReduce is a programming model and an associated Java-based software framework for processing vast amounts of data in parallel across large clusters of commodity hardware. It allows developers to write programs that analyze big data by breaking down a task into smaller, independent…

Key facts

First appeared: 2005
Category: technology
Problem solved: Apache MapReduce was created to address the immense challenge of processing and analyzing petabytes of data distributed across thousands of machines efficiently and fault-tolerantly, a task that traditional relational databases and single-node processing simply could not handle.
Platforms: Unix-like systems, Linux

Related technologies

Apache HDFS (Hadoop Distributed File System)
Apache ZooKeeper
Apache Hive
Apache YARN (Yet Another Resource Negotiator)
Apache Oozie
Apache Pig

Notable users

Amazon (via AWS EMR instances)
Facebook (early)
Twitter (early)
LinkedIn (early)
Yahoo!