In a MapReduce job counting 311 reason codes, one mega-popular code sends almost all intermediate values to a single reducer and the job crawls. What problem does this illustrate?
Select an answer to reveal the explanation.
Short Explanation
If one mail bin gets ninety percent of the city's letters, that clerk becomes the bottleneck. Hot keys create data skew in MapReduce. Even partitions and healthy YARN scheduling are the opposite story.
Full Explanation
Data skew occurs when key distribution is highly uneven, so one reducer receives a disproportionate share of values and becomes a straggler. Popular civic reason codes are a common real-world trigger. Mitigations include salting keys, custom partitioning, or pre-aggregation; pretending partitions are always even ignores the operational risk.