Question #214631 on Graphite changed: https://answers.launchpad.net/graphite/+question/214631
Yee-Ting Li posted a new comment: my custom feeder is actually based around amqp, so it's not really all that applicable for other uses at the moment :( - i don't actually close the socket on the feeder side, i find that the socket is closed by the carbon-instance (so a try/except around the socket.send_all) is often sufficient). yep: i see exactly the same thing with metrics on the carbon-instances with large numbers of queue. i observe that the cpu (normally around 1%) begins to fluculate wildly between 3-20% when the cache is full. also update times on those instances typically can take >10 times what the others do. good luck. -- You received this question notification because you are a member of graphite-dev, which is an answer contact for Graphite. _______________________________________________ Mailing list: https://launchpad.net/~graphite-dev Post to : [email protected] Unsubscribe : https://launchpad.net/~graphite-dev More help : https://help.launchpad.net/ListHelp
