Stanislav Denisov

@DanisJoyal It doesn't help, I already [tried](https://forum.unity.com/threads/benchmarknet-stress-test-for-enet-unet-litenetlib-lidgren-and-miniudp.512507/).

@DanisJoyal I tried to run the test with your fork. Everything goes well, as long as only 1 client is connected to the server. As soon as 2 or more...

@DanisJoyal It works better, but CPU usage is still very high compared to the master branch: 64 clients 32% vs 2% 500 clients 70% (160 was connected - overload) vs...

With your fork, reliable channel as well as unreliable can't handle it. [Here](https://i.imgur.com/b2qFufZ.png) is the results of the master branch.

If no more than 500 clients are connected and send messages - yes.

Sure, [here](https://github.com/nxrighthere/BenchmarkNet) it is.

Everything is fine with the benchmark, the problem in the library. @DanisJoyal has successfully fixed some things and here's the [result](https://s13.postimg.org/fcyr5je7r/optimized2000.png) with 2000 clients.

@RevenantX Can you please tell me your CPU model?

Strange... It's must be more than enough.

Sure, give me some time.