Shekharrajak opened a new pull request, #2992: URL: https://github.com/apache/datafusion-comet/pull/2992
## Which issue does this PR close? Closes #2904 ## Rationale for this change Benchmarks show that Comet columnar shuffle with complex/nested types (struct, array, map) is significantly slower than Spark's default shuffle. This PR adds a configuration flag to disable columnar shuffle for complex types, falling back to Spark shuffle for better performance until the underlying performance issues can be addressed. ## What changes are included in this PR? Add spark.comet.columnar.shuffle.complexTypes.enabled config (default: false) When disabled, queries with complex types in the shuffle schema fall back to Spark shuffle Update columnarShuffleSupported() to check this config for StructType, ArrayType, and MapTyp ## How are these changes tested? Updated existing columnar shuffle tests for complex types to explicitly enable the new config Added new test "Fallback to Spark for complex types when config is disabled (default)" that verifies struct, array, and map types fall back to Spark shuffle when the config is disabled -- 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]
