yadavay-amzn commented on PR #56243: URL: https://github.com/apache/spark/pull/56243#issuecomment-4608269742
@cloud-fan Could you take a look? AQE's CoalesceShufflePartitions can coalesce join stages to 1 partition (after OptimizeSkewedJoin finds no skew), eliminating parallelism. The fix adds a data-aware minimum partition floor for join groups. Reporter confirmed the production impact (552,948x data concentration on straggler tasks). Thanks! -- 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]
