siddhantsangwan commented on PR #9583: URL: https://github.com/apache/ozone/pull/9583#issuecomment-3710036517
> With the thread-local generator the same pipeline may be chosen for several concurrent requests in the worst case. If that happens, container selection may be quicker by a small margin, but write will be slower due to hitting the same datanodes. What's the reason for this? I think that can only happen if Java uses the same seed for each ThreadLocalRandom generator? I'm looking into how Java implements ThreadLocalRandom. Otherwise, even the shared instance of Random can output the same pipeline multiple times in the worst case. -- 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]
