This resource is no longer available
Architecture of an Enterprise-Class MapReduce Distributed Runtime Engine
A MapReduce implementation can help an organization effectively perform analytics on massive data sets from multiple sources including unstructured data if it's supported by the right runtime engine.
Read this white paper to learn how a MapReduce distributed runtime engine should be built in order to:
- Support multiple data sources including various commercial and open-source distributed file systems
- Run a variety of heterogeneous compute and data intensive applications without the need to duplicate infrastructure
- Enable easy management
- Ensure high reliability and availability
- And more.