MapReduce-MPI library features and non-features

• open-source C++ library
• C interface provided, thus callable from any hi-level language: C++, C, Fortran, scripting language, etc
• Python wrapper provided, so MapReduce programs can be written in Python
• OINK scripting language wrapper provided for easy scripting and development
• small, portable code base
• operates in serial or on any parallel platform that supports MPI
• operates in-core for data sets that fit in memory
• operates out-of-core for data sets that do not

• no fault tolerance

Fault tolerance is really an MPI issue, which future versions of MPI may address. Since big parallel machines never crash, nor do their processors die, hopefully it's a non-issue for performing MapReduce operations.