gortiz commented on PR #13791: URL: https://github.com/apache/pinot/pull/13791#issuecomment-2285732500
> Btw, to be clear I am supportive of the change and the rationale behind it. But (if time permits) it may be useful to see results from real use case or at least some kind of CPU profiling numbers from FlameGraphs or JFR metrics even if it is on the synthetic data The PR includes jmh benchmars, the same we used to merge https://github.com/apache/pinot/pull/12252, https://github.com/apache/pinot/pull/12271 and https://github.com/apache/pinot/pull/12227. These are micro-benchmarks. That means that the impact in a query is going to be smaller. But the performance increase is significant. At worse, they performance should not decrease. Also, changes are very similar to what was changed in these PRs. Anyway, @yashmayya , can you add some benchmarks executing the whole query just to be sure? It will use synthetic data, but it would be the closer we can have to know the performance impact of this change. -- 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: commits-unsubscr...@pinot.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org
