Hi, I posted earlier here https://groups.google.com/forum/#!topic/akka-user/7jwQC7vuYQs but i wanted to reframe what i think is going on and seek some advice.
The code is available on GitHub if anybody is interested. https://github.com/vardhanv/cosbench_ng Essentially, i am writing an S3 performance tester. Because it is a performance tester it needs to scale.. My architecture is - An akka cluster, with a singleton consistent hashing router - Many slaves running on other servers (default is 2 slave workers per host) - An akka streams implementation that is routing jobs to the slaves (gets/PUTs) etc - Slave workers that receive the commands and forward them to - a stateless S3 scala object that does blocking S3 PUTs - but is protected by a custom thread pool executor with 40 threads My default test setup is "one server that also has two slaves, and one agent that hosts two more slaves - for a total of 4 slaves". All this in docker containers, so that deployment is simple. I believe that the inconsistent behavior i am seeing with startup, message passing, unexpected shutdowns are to do with how these various pieces and their threads are getting scheduled. I am wondering if my hypothesis is true, and what can i do to protect these components from each other (cluster message passing, from stream messages, from the blocking calls) Best Regards Vishnu -- >>>>>>>>>> Read the docs: http://akka.io/docs/ >>>>>>>>>> Check the FAQ: >>>>>>>>>> http://doc.akka.io/docs/akka/current/additional/faq.html >>>>>>>>>> Search the archives: https://groups.google.com/group/akka-user --- You received this message because you are subscribed to the Google Groups "Akka User List" group. To unsubscribe from this group and stop receiving emails from it, send an email to akka-user+unsubscr...@googlegroups.com. To post to this group, send email to akka-user@googlegroups.com. Visit this group at https://groups.google.com/group/akka-user. For more options, visit https://groups.google.com/d/optout.