peter-toth commented on pull request #29132: URL: https://github.com/apache/spark/pull/29132#issuecomment-659478964
I measured nice improvement using a bit amended (spark.sql.cbo.enabled=true, spark.sql.cbo.joinReorder.enabled=true, analized source tables) TPCDSQueryBenchmark on scaleFactor=5 data with TPCDS queries: Q10: 18%, Q17: 10%, Q18: 19%, Q25: 29%, Q29: 49%, Q30: 35%, Q37: 22%, Q50: 59%, Q65: 19%, Q69: 34%, Q73: 45%, Q76: 21%, Q81: 29%, Q82: 51%, Q91: 12% Only 2 of the queries suffered performance degradation: Q16: -19%, Q49: -18% Please note that the % here are showing the difference due to this PR as the baseline was set with (spark.sql.cbo.enabled=true, spark.sql.cbo.joinReorder.enabled=true, analized source tables). ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
