vinothchandar commented on issue #1694: URL: https://github.com/apache/hudi/issues/1694#issuecomment-638519702
Beyond the initial shuffle, hudi will auto tune everything so I am not surprised. On countByKey at HoodieBloomindex, what’s the line number? count at HoodieSparkSqlWriter, is actual writing of data. We send 100K records to the same insert partition to write larger file sizes. Can you see if there’s a skew in that stage? It’s tunable ---------------------------------------------------------------- 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]
