[
https://issues.apache.org/jira/browse/SPARK-3056?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14097997#comment-14097997
]
Cheng Hao commented on SPARK-3056:
----------------------------------
SPARK-2926 provides external sort in reduce side, which will greatly reduce the
memory usage if too many identical grouping keys in the input tuples.
> Sort-based Aggregation
> ----------------------
>
> Key: SPARK-3056
> URL: https://issues.apache.org/jira/browse/SPARK-3056
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Reporter: Cheng Hao
>
> Currently, SparkSQL only support the hash-based aggregation, which may cause
> OOM if too many identical keys in the input tuples.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
