Answer Posted / Manik Dubey
A Spark Shuffle is an operation that is performed during tasks in Apache Spark to sort data before or after the reduce phase. It involves redistributing data among nodes, causing a significant overhead in terms of network bandwidth and CPU usage. However, it ensures that data is processed in sorted order if required.
| Is This Answer Correct ? | 0 Yes | 0 No |
Post New Answer View All Answers