alamb commented on PR #9595:
URL:
https://github.com/apache/arrow-datafusion/pull/9595#issuecomment-2012799977
Ok, I re-ran the benchmark and indeed it shows this PT is actually 4x faster
for queries that select large numbers of columns ❤️
```
group dfschema main
----- -------- ----
logical_plan_tpch_all 1.01 16.4±0.15ms ? ?/sec 1.00
16.2±0.20ms ? ?/sec
logical_select_all_from_1000 1.00 25.6±0.26ms ? ?/sec 3.86
98.8±0.44ms ? ?/sec
physical_plan_tpch_all 1.00 127.3±0.82ms ? ?/sec 1.01
128.2±0.60ms ? ?/sec
physical_select_all_from_1000 1.00 175.1±0.53ms ? ?/sec 4.14
724.3±1.56ms ? ?/sec
```
<details><summary>Benchmark scripts</summary>
<p>
```shell
git checkout feat/make-dfschema-wrap-schemaref
cargo bench --bench sql_planner -- all --save-baseline dfschema
MERGE_BASE=$(git merge-base HEAD apache/main)
echo "** Comparing to ${MERGE_BASE}"
git checkout ${MERGE_BASE}
cargo bench --bench sql_planner -- all --save-baseline main
critcmp main dfschema
```
</p>
</details>
--
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]
