CSE 2015

Recitation #4: MapReduce

The paper can be downloaded here. It is published on OSDI'04 by Google. It was one of the three major technologies of Google, while the other two are Big Table and Google FS (will be discussed in OS class).

Please read the MapReduce paper, and think about the following question: - What exactly would happen if one block of one hard drive got erased during a map/reduce computation? What parts of the system would fix the error (if any), and what parts of the system would be oblivious (if any)? - How do "stragglers" impact performance? - There is an article named "MapReduce: A Major Step Backwards" (URL). Please skim the article and try to understand why the authors had such statement. Do you agree them or not? - Please raise at least one question of your own for the discussion.

The deadline of your answer and questions is 23:59, 2015-4-23.