Use case - In case of MapReduce - where each Map tasks generates set of map output files - one for each reduce.
Currently all these files are stored together in a DU, and later all the files related to a reduce from Map tasks are segregated by the MapReduce framework to pass the DU's as inputs to reduce task.
This could be optimized, if we can allow a Map task to write output files to multiple reduce DU's directly.
I envison, this could be a useful feature for other use cases too.
Use case - In case of MapReduce - where each Map tasks generates set of map output files - one for each reduce.
Currently all these files are stored together in a DU, and later all the files related to a reduce from Map tasks are segregated by the MapReduce framework to pass the DU's as inputs to reduce task.
This could be optimized, if we can allow a Map task to write output files to multiple reduce DU's directly.
I envison, this could be a useful feature for other use cases too.