andygrove commented on PR #5998: URL: https://github.com/apache/datafusion-comet/pull/5998#issuecomment-5849556970
Closing: charging JVM Arrow allocations to Spark's pool turns native spills into task failures, because Spark can't reclaim memory from Comet's native consumer. The details are in https://github.com/apache/datafusion-comet/issues/5997#issuecomment-5849554596. #6250 makes this memory visible in the executor memory usage log instead. -- 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]
