Skip to content

Improve performance sort TPCH q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) #15403

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Tracked by #15096
zhuqi-lucas opened this issue Mar 25, 2025 · 2 comments · Fixed by #15447
Closed
Tracked by #15096
Labels
enhancement New feature or request

Comments

@zhuqi-lucas
Copy link
Contributor

zhuqi-lucas commented Mar 25, 2025

Is your feature request related to a problem or challenge?

See the comments,

#15348 (comment)

Sort-preserving merging on a single Utf8View column will cause sort_tpch q3 slow, we need to investigate it.

cc @alamb @2010YOUY01

And for the q 11 case it will be 20% faster with shorter string sort.

#15348 (comment)

To reproduce:

cargo run --profile release-nonlto --bin dfbench -- sort-tpch -p /Users/yongting/Code/datafusion/benchmarks/data/tpch_sf10 -q 3

Describe the solution you'd like

No response

Describe alternatives you've considered

No response

Additional context

No response

@zhuqi-lucas zhuqi-lucas added the enhancement New feature or request label Mar 25, 2025
@alamb alamb changed the title Investigate why Sort-preserving merging on a single Utf8View column will cause sort_tpch q3 slow Improve performance TPCG q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) Mar 25, 2025
@alamb
Copy link
Contributor

alamb commented Mar 25, 2025

Thanks, added to the list on #15096

@alamb alamb changed the title Improve performance TPCG q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) Improve performance TPCH q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) Mar 25, 2025
@zhuqi-lucas zhuqi-lucas changed the title Improve performance TPCH q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) Improve performance sort TPCH q3 with Utf8Vew ( Sort-preserving merging on a single Utf8View ) Mar 27, 2025
@zhuqi-lucas
Copy link
Contributor Author

Submitted a PR for review, the performance has about 40% improvement for sort-tpch q3 with single stringview column.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
2 participants