Bikas Saha created TEZ-2201:
-------------------------------
Summary: Improvements to input split grouping
Key: TEZ-2201
URL: https://issues.apache.org/jira/browse/TEZ-2201
Project: Apache Tez
Issue Type: Task
Reporter: Bikas Saha
Assignee: Bikas Saha
Today Tez has helper grouping libraries that group hadoop input splits into
larger groups for efficiency. This grouping logic is based on a min/max size of
groups and a wave based heuristic that tries to run mappers in waves to hide
the effect of stragglers.
This logic can be brittle based on input size and cluster size and can be
improved to be more dynamic and responsive.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
