Skip to content

perf: Optimize NULL handling in find_in_set#21464

Merged
mbutrovich merged 3 commits intoapache:mainfrom
neilconway:neilc/perf-find-in-set-nulls
Apr 10, 2026
Merged

perf: Optimize NULL handling in find_in_set#21464
mbutrovich merged 3 commits intoapache:mainfrom
neilconway:neilc/perf-find-in-set-nulls

Conversation

@neilconway
Copy link
Copy Markdown
Contributor

Which issue does this PR close?

Rationale for this change

find_in_set uses PrimitiveArray::<T>::builder to construct its results, which means building the internal null buffer in an iterative fashion (via repeated append_null calls). It is more efficient to construct the null buffer directly, via NullBuffer::union (when multiple arguments might be NULL) or just cloning the input null buffer (when passed a single argument).

Benchmarks (ARM64):

  - find_in_set/string_len_8: 589.0 µs → 529.0 µs (-10.2%)
  - find_in_set/string_len_32: 736.2 µs → 660.5 µs (-10.3%)
  - find_in_set/string_len_1024: 7.5 ms → 7.4 ms (-1.3%)
  - find_in_set/string_view_len_8: 616.0 µs → 579.9 µs (-5.9%)
  - find_in_set/string_view_len_32: 748.0 µs → 701.9 µs (-6.2%)
  - find_in_set/string_view_len_1024: 7.6 ms → 7.6 ms (0.0%)
  - find_in_set_scalar/string_len_8: 76.7 µs → 48.0 µs (-37.4%)
  - find_in_set_scalar/string_len_32: 76.5 µs → 47.6 µs (-37.8%)
  - find_in_set_scalar/string_len_1024: 76.2 µs → 48.0 µs (-37.0%)
  - find_in_set_scalar/string_view_len_8: 81.9 µs → 55.7 µs (-32.0%)
  - find_in_set_scalar/string_view_len_32: 85.5 µs → 56.8 µs (-33.6%)
  - find_in_set_scalar/string_view_len_1024: 85.2 µs → 57.4 µs (-32.6%)

The change should be an improvement for both scalar and array cases. The relative improvement is larger in the scalar case because the scalar case is doing less work and so NULL handling was a larger fraction of the total runtime.

What changes are included in this PR?

  • Optimize NULL handling for both scalar and array arg cases

Are these changes tested?

Yes.

Are there any user-facing changes?

No.

@github-actions github-actions bot added the functions Changes to functions implementation label Apr 8, 2026
@neilconway
Copy link
Copy Markdown
Contributor Author

Btw I tried refactoring this to use an explicit for (so we can dispense with the zero dummy assignment), but it was a bit slower than the map approach:

  - find_in_set/string_len_8: 588.6 µs → 530.9 µs (-9.8%)
  - find_in_set/string_len_32: 735.2 µs → 669.5 µs (-8.9%)
  - find_in_set/string_len_1024: 7.5 ms → 7.4 ms (-1.3%)
  - find_in_set/string_view_len_8: 615.7 µs → 581.0 µs (-5.6%)
  - find_in_set/string_view_len_32: 743.8 µs → 708.9 µs (-4.7%)
  - find_in_set/string_view_len_1024: 7.6 ms → 7.6 ms (-0.0%)
  - find_in_set_scalar/string_len_8: 76.7 µs → 56.9 µs (-25.8%)
  - find_in_set_scalar/string_len_32: 76.7 µs → 56.8 µs (-25.9%)
  - find_in_set_scalar/string_len_1024: 76.4 µs → 56.9 µs (-25.5%)
  - find_in_set_scalar/string_view_len_8: 81.5 µs → 59.0 µs (-27.6%)
  - find_in_set_scalar/string_view_len_32: 85.3 µs → 59.4 µs (-30.4%)
  - find_in_set_scalar/string_view_len_1024: 85.0 µs → 59.2 µs (-30.4%)

@neilconway neilconway changed the title perf: Optimize find_in_set NULL handling perf: Optimize NULL handling in find_in_set Apr 10, 2026
Copy link
Copy Markdown
Contributor

@mbutrovich mbutrovich left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for continually improving performance, @neilconway!

@mbutrovich mbutrovich added this pull request to the merge queue Apr 10, 2026
Merged via the queue into apache:main with commit d61be49 Apr 10, 2026
32 checks passed
@neilconway neilconway deleted the neilc/perf-find-in-set-nulls branch April 10, 2026 20:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

functions Changes to functions implementation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Optimize NULL handling for find_in_set

2 participants