jaehoon ko created MAPREDUCE-5946: ------------------------------------- Summary: Last spill of map task is not necessary for final merge Key: MAPREDUCE-5946 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5946 Project: Hadoop Map/Reduce Issue Type: Improvement Components: performance, security Affects Versions: 2.4.0 Reporter: jaehoon ko Assignee: jaehoon ko
In map task, merge starts only after the last spill is completely written to disk. This is not necessary nor efficient because the last spill should to be reloaded soon for merge, probably immediately because spills are merged in the order of their sizes and the last spill is likely smallest. OS page cache is not the answer due to its opportunistic nature. I'm starting to work on it. Please give me your thoughts. -- This message was sent by Atlassian JIRA (v6.2#6252)