comphead commented on code in PR #11218:
URL: https://github.com/apache/datafusion/pull/11218#discussion_r1678496388
##########
datafusion/physical-plan/src/joins/sort_merge_join.rs:
##########
@@ -602,15 +622,38 @@ impl BufferedBatch {
+ mem::size_of::<Range<usize>>()
+ mem::size_of::<usize>();
+ let num_rows = batch.num_rows();
BufferedBatch {
batch,
range,
join_arrays,
null_joined: vec![],
size_estimation,
join_filter_failed_idxs: HashSet::new(),
+ num_rows,
+ spill_file: None,
}
}
+
+ fn spill_to_disk(
+ &mut self,
+ path: RefCountedTempFile,
+ buffered_schema: SchemaRef,
+ batch_size: usize,
+ ) -> Result<()> {
+ let batch = std::mem::replace(
Review Comment:
I think it makes sense, let me try if that works
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
