An analog of Hadoop's "Combiner" will reduce the amount of data needed to be written to the global map output for certain workloads.
The combiner should have the same interface as reducer -- but will need to be run in the mapper before any output is written
An analog of Hadoop's "Combiner" will reduce the amount of data needed to be written to the global map output for certain workloads.
The combiner should have the same interface as
reducer-- but will need to be run in the mapper before any output is written