guobj commented on issue #9859:
URL:
https://github.com/apache/incubator-gluten/issues/9859#issuecomment-2938285555
The execution plan of spark is like this：
== Physical Plan ==
Execute InsertIntoHiveTable (43)
+- AdaptiveSparkPlan (42)
+- == Final Plan ==
* Project (25)
+- * SortMergeJoin LeftOuter (24)
:- * Project (8)
: +- * Filter (7)
: +- Window (6)
: +- * Sort (5)
: +- AQEShuffleRead (4)
: +- ShuffleQueryStage (3)
: +- Exchange (2)
: +- Scan hive
loan_data_warehouse.ads_did_deviceid_mapping_df (1)
+- SortAggregate (23)
+- * Sort (22)
+- AQEShuffleRead (21)
+- ShuffleQueryStage (20)
+- Exchange (19)
+- SortAggregate (18)
+- * Project (17)
+- * Filter (16)
+- Window (15)
+- * Sort (14)
+- AQEShuffleRead (13)
+- ShuffleQueryStage (12)
+- Exchange (11)
+- * Filter (10)
+- Scan hive
loan_data_warehouse.ads_did_deviceid_mapping_df (9)
+- == Initial Plan ==
Project (41)
+- SortMergeJoin LeftOuter (40)
:- Project (29)
: +- Filter (28)
: +- Window (27)
: +- Sort (26)
: +- Exchange (2)
: +- Scan hive
loan_data_warehouse.ads_did_deviceid_mapping_df (1)
+- SortAggregate (39)
+- Sort (38)
+- Exchange (37)
+- SortAggregate (36)
+- Project (35)
+- Filter (34)
+- Window (33)
+- Sort (32)
+- Exchange (31)
+- Filter (30)
+- Scan hive
loan_data_warehouse.ads_did_deviceid_mapping_df (9)
And I found that spark has only 2 jobs, but gluten has 4 jobs.
--
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]
