Dandandan commented on code in PR #2182:
URL: https://github.com/apache/arrow-datafusion/pull/2182#discussion_r846406278
##########
datafusion/core/src/physical_plan/sorts/sort.rs:
##########
@@ -426,52 +426,78 @@ impl Iterator for SortedIterator {
// Combine adjacent indexes from the same batch to make a slice,
// for more efficient `extend` later.
let mut last_batch_idx = 0;
- let mut start_row_idx = 0;
- let mut len = 0;
+ let mut indices_in_batch = vec![];
let mut slices = vec![];
for i in 0..current_size {
let p = self.pos + i;
let c_index = self.indices.value(p) as usize;
let ci = self.composite[c_index];
- if len == 0 {
+ if indices_in_batch.is_empty() {
last_batch_idx = ci.batch_idx;
- start_row_idx = ci.row_idx;
- len = 1;
+ indices_in_batch.push(ci.row_idx);
} else if ci.batch_idx == last_batch_idx {
- len += 1;
- // since we have pre-sort each of the incoming batches,
- // so if we witnessed a wrong order of indexes from the same
batch,
- // it must be of the same key with the row pointed by
start_row_index.
- start_row_idx = min(start_row_idx, ci.row_idx);
+ indices_in_batch.push(ci.row_idx);
} else {
- slices.push(CompositeSlice {
- batch_idx: last_batch_idx,
- start_row_idx,
- len,
- });
+ let indices = indices_in_batch.drain(..).collect::<Vec<_>>();
+ group_indices(last_batch_idx, indices, &mut slices);
last_batch_idx = ci.batch_idx;
- start_row_idx = ci.row_idx;
- len = 1;
+ indices_in_batch.push(ci.row_idx);
}
}
assert!(
- len > 0,
+ !indices_in_batch.is_empty(),
"There should have at least one record in a sort output slice."
);
- slices.push(CompositeSlice {
- batch_idx: last_batch_idx,
- start_row_idx,
- len,
- });
+ let indices = indices_in_batch.drain(..).collect::<Vec<_>>();
+ group_indices(last_batch_idx, indices, &mut slices);
self.pos += current_size;
Some(slices)
}
}
+/// Group continuous indices into a slice for better `extend` performance
+#[allow(clippy::stable_sort_primitive)]
+fn group_indices(
+ batch_idx: u32,
+ mut positions: Vec<u32>,
+ output: &mut Vec<CompositeSlice>,
+) {
+ // use sort instead of sort_unstable since it's likely nearly sorted.
+ positions.sort();
Review Comment:
This won't give different results, no? Why stable sort here?
--
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]
