yyy1000 commented on code in PR #9469:
URL: https://github.com/apache/arrow-datafusion/pull/9469#discussion_r1514791456
##########
datafusion/physical-plan/src/sorts/partial_sort.rs:
##########
@@ -282,16 +276,31 @@ impl ExecutionPlan for PartialSortExec {
// Make sure common prefix length is larger than 0
// Otherwise, we should use SortExec.
assert!(self.common_prefix_length > 0);
+ let execution_options = &context.session_config().options().execution;
- Ok(Box::pin(PartialSortStream {
- input,
- expr: self.expr.clone(),
- common_prefix_length: self.common_prefix_length,
- in_mem_batches: vec![],
- fetch: self.fetch,
- is_closed: false,
- baseline_metrics: BaselineMetrics::new(&self.metrics_set,
partition),
- }))
+ let mut sorter = crate::sorts::sort::ExternalSorter::new(
+ partition,
+ input.schema(),
+ self.expr.clone(),
+ context.session_config().batch_size(),
+ self.fetch,
+ execution_options.sort_spill_reservation_bytes,
+ execution_options.sort_in_place_threshold_bytes,
+ &self.metrics_set,
+ context.runtime_env(),
+ );
+ let prefix = self.common_prefix_length;
+ Ok(Box::pin(RecordBatchStreamAdapter::new(
+ self.schema(),
+ futures::stream::once(async move {
+ while let Some(batch) = input.next().await {
+ let batch = batch?;
+ sorter.insert_batch_with_prefix(batch, prefix).await?;
+ }
+ sorter.sort()
Review Comment:
Also I have a question is `sort` returns a `SendableRecordBatchStream` and
produce bulk, and `PartialSort` returns chuck by chunk. What're the pros of
`chuck by chunk`? I think they do the same for memory usage. 🤔
--
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]
