THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
...
The root cause of the performance issue mentioned above is the receive API implementation in the network-based TMB, which uses the sleep system call for blocking. We need a better implementation, e.g., event-driven based.
One alternative is to avoid the client side polling, by refactoring the Receive RPC API the server-side blocking implementation, instead of client-side streaming.
10-node-cluster Setup in CloudLab
...