In-Memory MapReduce
Apache Ignite comes with in-memory implementation of Hadoop MapReduce APIs which provides significant acceleration over the native Hadoop MapReduce implementation. Ignite MapReduce performs much better than Hadoop due to push-based resource allocation as well as in-process collocation of computations with data.
Additionally, since Ignite File System (IGFS) does not need a Name Node, when used with IGFS, Ignite MapReduce jobs go directly to the IGFS data nodes in a single round-trip.
See MapReduce documentation to plug Ignite MapReduce natively into Hadoop deployments.
Ignite MapReduce Features
| Feature | Description |
|---|---|
| Native Hadoop MapReduce |
Ignite MapReduce is an implementation of Hadoop MapReduce APIs and can be natively plugged into existing Hadoop installations to provide a significant performance boost. |
| Hadoop Accelerator |
Ignite comes with Hadoop Accelerator distribution which provides both, Ignite File System (IGFS) and Ignite MapReduce, in one installation which can be easily plugged into existing Hadoop installations. |