msokolov commented on PR #13472: URL: https://github.com/apache/lucene/pull/13472#issuecomment-2173285915
The luceneutil results reported here are astounding. So astounding I'm not sure I believe them? I wonder if somehow we did not run with concurrency enabled on the main branch test ... or if there was some other testing artifact? Part of my thinking is that if this change was so impactful, then wouldn't we have seen a huge regression when moving from the prior situation (where we ran N-1 tasks in the threadpool and one task on the main thread) to the current situation? Hmm I do see your comment that this is different since the "main" thread is continuing to do more tasks. Still I'm really surprised at the impact. If I can get a moment I'll try to corroborate the test result. -- 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
