bibhu107 opened a new issue, #11274: URL: https://github.com/apache/hudi/issues/11274
Hi Team, I am upgrading my Spark EMR jobs **FROM [Spark 2.4.8, EMR-5.36.1, Hudi 0.7]** **TO** **[Spark 3.3.1, EMR 6.10.1, and Hudi 0.14]**. This upgrade is leading to a 230% performance degradation. Previously, the jobs were running in 18 minutes, but now they are taking over an hour to complete. I'm sharing screenshots below for reference. There have been no code changes apart from upgrading the dependencies. I am writing to the Hudi table in version 0.14 the same way as I did in version 0.7. For this upgrade, I have created a new copy-on-write table and am using the Simple Indexing approach. Could you please help me debug this issue or suggest any additional configurations that might be required to improve performance?   -- 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]
