jhorstmann opened a new issue #1973: URL: https://github.com/apache/arrow-datafusion/issues/1973
**Describe the bug** The `jit` benchmark calls `batch.schema()` for each row, internally the `schema` method clones an `Arc`. Normally cloning an `Arc` is not a problem, but doing it for every row adds some overhead. **To Reproduce** Running the benchmark under a profiler like `perf` and then checking the hotspots shows some atomic instructions on the hot path ``` perf record cargo bench --features row,jit --bench jit ``` -- 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]
