gianm opened a new pull request, #12477: URL: https://github.com/apache/druid/pull/12477
Calling isEmpty() and equals() on RangeSets is expensive, because these fall back on default implementations that call size(). And size() is _also_ a default implementation that iterates the entire collection. This is especially noticeable for IN filters. The included benchmark uses a 5000-element IN filter. On my machine, the patch speeds up the benchmark from 190000ns per segment to 625ns per segment. This is a worst-case benchmark: it has a large number of matching ranges per segment. But it's good to know that even in this case, things will be fast. -- 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]
