alamb commented on code in PR #8020:
URL: https://github.com/apache/arrow-datafusion/pull/8020#discussion_r1453335862
##########
datafusion/physical-plan/src/joins/hash_join.rs:
##########
@@ -1039,76 +1058,32 @@ pub fn build_equal_condition_join_indices<T:
JoinHashMapType>(
.into_array(build_input_buffer.num_rows())
})
.collect::<Result<Vec<_>>>()?;
- hashes_buffer.clear();
- hashes_buffer.resize(probe_batch.num_rows(), 0);
- let hash_values = create_hashes(&keys_values, random_state,
hashes_buffer)?;
- // In case build-side input has not been inverted while JoinHashMap
creation, the chained list algorithm
- // will return build indices for each probe row in a reverse order as such:
- // Build Indices: [5, 4, 3]
- // Probe Indices: [1, 1, 1]
- //
- // This affects the output sequence. Hypothetically, it's possible to
preserve the lexicographic order on the build side.
- // Let's consider probe rows [0,1] as an example:
- //
- // When the probe iteration sequence is reversed, the following pairings
can be derived:
- //
- // For probe row 1:
- // (5, 1)
- // (4, 1)
- // (3, 1)
- //
- // For probe row 0:
- // (5, 0)
- // (4, 0)
- // (3, 0)
- //
- // After reversing both sets of indices, we obtain reversed indices:
- //
- // (3,0)
- // (4,0)
- // (5,0)
- // (3,1)
- // (4,1)
- // (5,1)
- //
- // With this approach, the lexicographic order on both the probe side and
the build side is preserved.
- let (mut probe_indices, mut build_indices) = if fifo_hashmap {
- build_hashmap.get_matched_indices(hash_values.iter().enumerate(),
deleted_offset)
- } else {
- let (mut matched_probe, mut matched_build) = build_hashmap
- .get_matched_indices(hash_values.iter().enumerate().rev(),
deleted_offset);
-
- matched_probe.as_slice_mut().reverse();
- matched_build.as_slice_mut().reverse();
+ let mut hashes_buffer = vec![0; probe_batch.num_rows()];
Review Comment:
I will plan to do some profiling today and report my findings
--
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]
