fengnanli commented on pull request #2651: URL: https://github.com/apache/hadoop/pull/2651#issuecomment-771903717
> Thanks @fengnanli for you works here. Leave some nit comment inline. > Sorry I do not get why the change can reduce connections here after review the changes, is it related "Be greedy here to close as many connections as possible in one shot"? It will be helpful if we add some javadocs explicitly. Thanks. Thanks for the review @Hexiaoqiao I put the reason behind this change in the design doc in the original JIRA ticket. In short, I did synchronous connection closing + better picking connections + greedy closing connections. I have seen 50% reduce in number of connections and better ProxyTime. It will be great if you can try in your setup as well. ---------------------------------------------------------------- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
