Thanks to visit codestin.com
Credit goes to github.com

Skip to content

feat(vortex-datafusion): push st_distance into the scan as GeoDistance#8455

Draft
HarukiMoriarty wants to merge 2 commits into
nemo/geo-q1from
nemo/spatialbench-q1
Draft

feat(vortex-datafusion): push st_distance into the scan as GeoDistance#8455
HarukiMoriarty wants to merge 2 commits into
nemo/geo-q1from
nemo/spatialbench-q1

Conversation

@HarukiMoriarty

Copy link
Copy Markdown
Contributor

Status: blocked on upstream geodatafusion

Adds a temporary dependency on the geodatafusion fork HarukiMoriarty/geodatafusion@3d50d7e (manually bumped to DataFusion 54).

Not for merge as-is. Unblocks when geodatafusion publishes a DataFusion-54 release on crates.io; the git dep then swaps to a version and this un-drafts.

Stacks on #8453.

Summary

Recognizes geodatafusion's st_distance during DataFusion → Vortex expression conversion and pushes it into the scan as a native GeoDistance expression, instead of letting it run row-by-row above the scan.

@HarukiMoriarty HarukiMoriarty marked this pull request as draft June 16, 2026 19:12
@codspeed-hq

codspeed-hq Bot commented Jun 16, 2026

Copy link
Copy Markdown

Merging this PR will degrade performance by 26.96%

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

❌ 3 regressed benchmarks
✅ 1542 untouched benchmarks
⏩ 10 skipped benchmarks1

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

Mode Benchmark BASE HEAD Efficiency
Simulation chunked_bool_canonical_into[(1000, 10)] 20.4 µs 35.5 µs -42.54%
Simulation chunked_varbinview_canonical_into[(1000, 10)] 161.7 µs 197.9 µs -18.3%
Simulation chunked_varbinview_into_canonical[(1000, 10)] 176.8 µs 213 µs -17%

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.


Comparing nemo/spatialbench-q1 (d842e32) with nemo/geo-q1 (46c1d5c)

Open in CodSpeed

Footnotes

  1. 10 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports.

@HarukiMoriarty HarukiMoriarty added the changelog/feature A new feature label Jun 16, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

changelog/feature A new feature

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant