Rohini Palaniswamy created PIG-4165:
---------------------------------------
Summary: Rework Hash based aggregation for Tez
Key: PIG-4165
URL: https://issues.apache.org/jira/browse/PIG-4165
Project: Pig
Issue Type: Sub-task
Reporter: Rohini Palaniswamy
pig.exec.mapPartAgg (https://wiki.apache.org/pig/PigHashBasedAggInMap) is
currently only used for group by if there is any aggregation to be done. In
Tez, should enable hash based grouping for normal and skewed joins, groupby
with or without aggregation on the map side. This will play well with the IFile
optimizations done and support for writing key and list of values (TEZ-1260)
and reduce the sorting time on the map side.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
