NEUpanning commented on PR #10235:
URL:
https://github.com/apache/incubator-gluten/pull/10235#issuecomment-3101384611
> Could you conveniently introduce the production scenarios where you have
encountered so many shared string buffers?
@kerwin-zk The physical plan before shuffle did not include any string
functions but I noticed one string buffer was shared by over 30 row vectors. I
am not sure the cause of that.
```
ColumnarExchange hashpartitioning(user_key#326, 8000), ENSURE_REQUIREMENTS,
[user_key#326, collect_date_list#338], [plan_id=1608],
[shuffle_writer_type=sort], [OUTPUT] List(user_key:StringType,
collect_date_list:StringType)
+- ^(2) ProjectExecTransformer [hash(user_key#326, 42) AS
hash_partition_key#391, collect_date_list#338]
+- ^(2) FileScanTransformer orc tableA PartitionFilters:
[isnotnull(partition_date#339), isnotnull(partition_identity_type#341),
isnotnull(partition_sourc...
```
--
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]
