wirybeaver commented on PR #2749: URL: https://github.com/apache/datafusion-ballista/pull/2749#issuecomment-6618547794
Thanks for the review. To clarify, each query has **at least 9 measured runs per arm**, rather than three. I’ve updated the PR body to make this explicit. **Will do in this PR** - Reuse existing filters for partitioned-fallback probes. - Freeze filters on first actual task binding. **Will evaluate in this PR** - Near-saturation Bloom bypass. - Skipping sibling-only producers in zero-wait mode. We previously removed a broader speculative multi-join producer guard after SF10 experiments did not establish a clear benefit. The narrower sibling-only case still needs evaluation. **Already deferred to personal PRs** - **Task 3:** MinMax-based Parquet pruning — [PR #3](https://github.com/wirybeaver/datafusion-ballista/pull/3). General row-level MinMax filtering can be evaluated there. - **Task 4:** Optional nonzero waiting, deadline wakeups, and early release for fully saturated partial Blooms — [PR #13](https://github.com/wirybeaver/datafusion-ballista/pull/13). -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
