Question

Point out the correct statement.

(a) The right number of reduces seems to be 0.95 or 1.75

(b) Increasing the number of reduces increases the framework overhead

(c) With 0.95 all of the reduces can launch immediately and start transferring map outputs as the maps finish

(d) All of the mentioned

This question was addressed to me in an interview for job.

My question is based upon MapReduce Features in portion Developing a MapReduce Application of Hadoop

Answer 1

Right choice is (c) With 0.95 all of the reduces can launch immediately and start transferring map outputs as the maps finish

The best I can explain: With 1.75 the faster nodes will finish their first round of reduces and launch a second wave of reduces doing a much better job of load balancing.