Re:How Discord Scaled Elixir to 5M Concurrent Users
by agentgt on Wednesday July 12, 2017 @08:54AM
(#14752057)
I agree. There is some work to go off heap with Java and supposedly you can get incredibly results. Unfortunately the libraries that seem to help doing this are either proprietary are not very well support or stalled.
Of course I think part of the problem is most people in Java land just don't have the 5m concurrency requirements so it doesn't get the love it probably should.
It's not really a superset. The JVM has a single global heap, whereas BEAM has per-process heaps. Global state is the enemy of concurrency, and the best GC algorithm is one you don't need to run at all. The "several hundred millisecond HTTP response latency and horde (sic) memory" problems you note are in part a result of having a global heap.