aokolnychyi commented on code in PR #8571:
URL: https://github.com/apache/iceberg/pull/8571#discussion_r1328954186
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/sql/TestStoragePartitionedJoins.java:
##########
@@ -489,11 +489,9 @@ public void testJoinsWithOneSplitTables() {
sql("INSERT INTO %s VALUES (1L, 100, 'software')",
tableName(OTHER_TABLE_NAME));
- // Spark should be able to avoid shuffles even without SPJ if each side
has only one split
Review Comment:
The remaining shuffle is a global sort to order the results. Also, Spark
starts to prefer the parallelism and now inserts shuffles even with 1 split
(without SPJ).
--
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]
