Kontinuation opened a new pull request, #1021: URL: https://github.com/apache/datafusion-comet/pull/1021
## Which issue does this PR close? This issue relates to https://github.com/apache/datafusion-comet/issues/996 and https://github.com/apache/datafusion-comet/pull/1004 ## Rationale for this change Investigating various approaches to simplify memory-related configuration and reduce the memory required to run large queries. ## What changes are included in this PR? This PR adds a `spark.comet.exec.memoryPool` configuration for easily running queries using various memory pool setups. * `greedy` (default): Each operator has its own GreedyMemoryPool * `fair_spill`: Each operator has its own FairSpillPool * `fair_spill_task_shared`: All operators for the same task attempt shares the same FairSpillPool * `greedy_global`: All operators in the same executor instance shares the same GreedyMemoryPool * `fair_spill_global`: All operators in the same executor instance shares the same FairSpillPool ## How are these changes tested? This PR is for experimentation purposes and the default configuration has no behavioral changes. Other configurations will be tested manually by running experiments. -- 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]
