franz1981 edited a comment on issue #2494: ARTEMIS-2224 Reduce contention on LivePageCacheImpl URL: https://github.com/apache/activemq-artemis/pull/2494#issuecomment-454895122 @qihongxu thanks! I need to put a couple of logs on the code to check how is the behaviour with several consumers and check if live page queries are happening with single-threaded semantic ie are just limited by the efficiency of the query and can't scale. I'm surprised about getValidLastIndex(): it should be the bottleneck (if the paged message query is the caller) only when the cache is empty (no messages) or the index is == cache size. If there is a cache hit I expect that getChunkOf or the volatile get on the message slot to be costy. About the test is a good idea: having 1/200/400 consumers can help to understand the scaling, but I suppose that your intuitions are right here.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
