dongjoon-hyun commented on code in PR #39470:
URL: https://github.com/apache/spark/pull/39470#discussion_r1065148054
##########
docs/sql-performance-tuning.md:
##########
@@ -286,6 +286,27 @@ This feature coalesces the post shuffle partitions based
on the map output stati
</tr>
</table>
+### Spliting skewed shuffle partitions
+ <table class="table">
+ <tr><th>Property Name</th><th>Default</th><th>Meaning</th><th>Since
Version</th></tr>
+ <tr>
+
<td><code>spark.sql.adaptive.optimizeSkewsInRebalancePartitions.enabled</code></td>
+ <td>true</td>
+ <td>
+ When true and <code>spark.sql.adaptive.enabled</code> is true, Spark
will optimize the skewed shuffle partitions in RebalancePartitions and split
them to smaller ones according to the target size (specified by
<code>spark.sql.adaptive.advisoryPartitionSizeInBytes</code>), to avoid data
skew.
+ </td>
+ <td>3.2.0</td>
+ </tr>
+ <tr>
+
<td><code>spark.sql.adaptive.rebalancePartitionsSmallPartitionFactor</code></td>
Review Comment:
This is a non-internal configuration which has been defined and used for a
while.
https://github.com/apache/spark/blob/786594734bd79017ebd42eb117b62958afad07bb/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala#L792-L799
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
