duke8253 commented on pull request #7719: URL: https://github.com/apache/trafficserver/pull/7719#issuecomment-825404212
> How does the utilization go up by using std::unordered_map with something else? I'd understand if the something else took up CPU, but you say the unordered_map itself took up CPU if you use it with something else. The only difference I can think of was the way to erase an entry from std::unordered_map. By Key from the something else or by Iterator from std::unordered_map::begin. That could explain why the utilization is high, but I don't think it is the problem here. As I understand it, erase by key is a combination of find by key then erase by iterator. Searching via key is used inside insert to make sure no duplications, one more search should not increase the utilization by that much. -- 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. For queries about this service, please contact Infrastructure at: [email protected]
