alamb opened a new issue, #22202: URL: https://github.com/apache/datafusion/issues/22202
### Is your feature request related to a problem or challenge? `RepartitionExec` emits one small `RecordBatch` per (input batch × non-empty output partition), then coalesces them back to target size on the consumer side. The channel layer (memory accounting, sender gate, await suspensions) therefore does work proportional to `num_output_partitions` per input batch, even though each sub-batch only carries ~`batch_size / num_output_partitions` rows. This becomes a real cost at high fanout. In [`datafusion-distributed`](https://github.com/datafusion-contrib/datafusion-distributed), `RepartitionExec` is the backbone for network shuffles and is scaled to `P * W` partitions (P ≈ 12–24, W up to thousands), where per-batch channel overhead dominates. ### Additional context A candidate implementation is in #22010. -- 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]
