Question

Hadoop - Mining Big Data

Given the following keys: 1, 4, 6, 8, 11, 12, 14, 15, 16, 25, 26, 27, 50, 51, 52, 88, 89, 92, 99, describe the following:

1. The distribution and output of these keys across 3 reducers using the default partitioner (% 3)
2. Design a custom sorting partitioner instead of the default one and describe the resulting output across the same 3 reducers
3. What is the downside (i.e., extra overhead) of using a custom partitioner?