This has been posted twice before[1][2]. It should be noted that this benchmark was done over localhost, i.e. packets did not actually leave the computer, so who knows what kind of optimizations were done by the kernel / networking stack.<p>When looking at examples where packets actually leave the computer, at least one person achieved 1M concurrent connections with Erlang in 2008, and WhatsApp were hitting 2.8M concurrent connections with Erlang in a production system in 2012[4]. Of course memory usage was a lot higher in these examples, but at least they were exercising the networking stack.<p>[1]: <a href="https://news.ycombinator.com/item?id=5127251" rel="nofollow">https://news.ycombinator.com/item?id=5127251</a><p>[2]: <a href="https://news.ycombinator.com/item?id=5474331" rel="nofollow">https://news.ycombinator.com/item?id=5474331</a><p>[3]: <a href="http://www.metabrew.com/article/a-million-user-comet-application-with-mochiweb-part-1" rel="nofollow">http://www.metabrew.com/article/a-million-user-comet-applica...</a><p>[4]: <a href="http://www.erlang-factory.com/upload/presentations/558/efsf2012-whatsapp-scaling.pdf" rel="nofollow">http://www.erlang-factory.com/upload/presentations/558/efsf2...</a>
10 seconds until someone mentions this benchmark is somehow unfair and nonsensical :)<p>Still a very informative, promising and well formatted article, props.
OT: I didn't know this nice http server with unified API for websocket and long polling. Maybe this is the reason SockJS and Socket.IO aren't getting the attention I thought they would? People are just using websocket or long polling, ignoring the other fallbacks??
Has anyone similar data on EC2 instances? I'd be particularly interested in small/medium ones. (localhost+no database are fine, it's just for the sake of comparison)