Github user sujith71955 commented on the issue:
https://github.com/apache/spark/pull/16677
@viirya i tested with the above mentioned approach with sample data, it has
improved the performance almost into 3X
Please find the test report
Total No of Executers = 3
Total Memory assigned = 66 G
Total Number of cores = 15 core
Number of Partition = 200
Data size = 10745616 (>10 milliion)
Limit value = 10000000 (10 million)
query executed: create destination_table as select * from source_table
limit 10000000;
Time Taken with current implementation with single partition : 383 seconds
**With use map output statistics(spark open source proposed solution) :120
sec** which is great!!!
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
