D-DS-FN-23: Data Science FoundationsDemo

By Dell · Question Mode

QuestionQ18

Advanced Analytics for Big Data - Technology and Tools

What is one advantage of Spark’s in-memory data processing compared with MapReduce?

  • A Avoids writing intermediate data to disk, which speeds up processing
  • B Supports processing unstructured data, which MapReduce does not allow
  • C Removes the need to use disks at all, which reduces cost
  • D Allows parallel processing, which MapReduce does not support
Explanation

Spark can keep intermediate results in memory rather than repeatedly writing them to disk between processing stages. Reducing disk I/O can substantially speed up data processing.

Community Discussion

No comments yet. Be the first to start the discussion!