You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Hyukjin Kwon (JIRA)" <ji...@apache.org> on 2019/05/21 04:23:39 UTC
[jira] [Updated] (SPARK-12283) Use UnsafeRow as the buffer in
SortBasedAggregation to avoid Unsafe/Safe conversion
[ https://issues.apache.org/jira/browse/SPARK-12283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Hyukjin Kwon updated SPARK-12283:
---------------------------------
Labels: bulk-closed (was: )
> Use UnsafeRow as the buffer in SortBasedAggregation to avoid Unsafe/Safe conversion
> -----------------------------------------------------------------------------------
>
> Key: SPARK-12283
> URL: https://issues.apache.org/jira/browse/SPARK-12283
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Reporter: Davies Liu
> Priority: Major
> Labels: bulk-closed
>
> SortBasedAggregation use GenericMutableRow as aggregation buffer, also requires that the input can't be UnsafeRow, because the we can't compare/evaluate UnsafeRow and GenericInternalRow in the same time. The TungstenSort output UnsafeRow, so multiple Safe/Unsafe projections will be inserted between them.
> If we can make sure that all the mutating happens in ascending order, the buffer of UnsafeRow could be used to update var-length object (String, Binary, Struct etc.)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org