Josh Rosen created SPARK-8964:
---------------------------------
Summary: Use Exchange in limit operations (per partition limit ->
exchange to one partition -> per partition limit)
Key: SPARK-8964
URL: https://issues.apache.org/jira/browse/SPARK-8964
Project: Spark
Issue Type: Improvement
Components: SQL
Reporter: Josh Rosen
Assignee: Josh Rosen
Spark SQL's physical Limit operator currently performs its own shuffle rather
than using Exchange to perform the shuffling. This is less efficient since
this non-exchange shuffle path won't be able to benefit from SQL-specific
shuffling optimizations, such as SQLSerializer2. It also involves additional
unnecessary row copying.
Instead, I think that we should rewrite Limit to expand into three physical
operators:
PerParititonLimit -> Exchange to one partition -> PerPartitionLimit
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
