Question: MapReduce implementations provide fault tolerance, where you can re execute only failed mappers or reducers. By default, a partitioned parallel join execution would have to
MapReduce implementations provide fault tolerance, where you can re execute only failed mappers or reducers. By default, a partitioned parallel join execution would have to be rerun completely in case of even one node failure. It is possible to modify a parallel partitioned join execution to add fault tolerance in a manner similar to MapReduce, so failure of a node does not require full re execution of the query, but only actions related to that node. Explain what needs to be done at the time of partitioning at the sending node and receiving node to do this
Step by Step Solution
3.36 Rating (152 Votes )
There are 3 Steps involved in it
At the time of partitioning the sending node will need to send a replica of each partition to ... View full answer
Get step-by-step solutions from verified subject matter experts
