gruuya commented on issue #7149: URL: https://github.com/apache/arrow-datafusion/issues/7149#issuecomment-1660259340
> why bother with materializing the record batches from the [input stream](https://github.com/apache/arrow-datafusion/blob/main/datafusion/core/src/physical_plan/sorts/sort.rs#L611) and potentially spilling them to the disk at this point, only for them to be [streamed back](https://github.com/apache/arrow-datafusion/blob/main/datafusion/core/src/physical_plan/sorts/sort.rs#L174-L193) into streaming_merge function again? Oh, to answer my own question it's because `streaming_merge` assumes the input is sorted, and to do that we need to materialize the original stream, which also involves disk spill over, got it. One partial improvement would be something like concatenating and sorting the incoming batches into a single batch inside `insert_batch`, and then optionally spilling that over to disk; still, this results in a trade-off between time and memory efficiency of such cases, since it would require sorting of each intermediate batch (albeit partially sorted already). I guess the real solution would be something like an external top-k algorithm which would work on the original input stream and use a min/max heap with spillover in case `fetch` is some value (actually it was my impression this was already implemented). Not sure how viable is that though. -- 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]
