mikemccand commented on PR #13149: URL: https://github.com/apache/lucene/pull/13149#issuecomment-1987369263
> I tried benchmarking this with luceneutil, but did not see any significant change with the default benchmark - I suspect that I'm using the wrong luceneutil tasks to see any major difference. Which luceneutils benchmarks should I be using for these changes? Confusingly named, the `IntsNRQ` task is the only task using points, I think. It runs simple 1D range queries. The [geospatial benchmarks](https://home.apache.org/~mikemccand/geobench.html) (a different benchmark than the normal/nightly `luceneutil`) use multi-dimensional points. Still, given that you saw gains in the "OpenSearch vs Elasticsearch" benchmarks, even if the results are flat with the existing luceneutil benchmarks, I think we should just merge the change. The night after we can watch Lucene's nightly benchmarks and see if the nightly box measured anything. (Hmm, curiously/separately, it looks like something caused a [jump in some geo tasks' performance e.g. distance filter](https://home.apache.org/~mikemccand/geobench.html) ... I'll try to find the cause and add an annotation!). -- 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: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
