It gets even more interesting on bigger hardware. A user ran the benchmarks on a 10 core Xeon, Phoenix got 180,000 req/s and peaked at 75% CPU, so IO was still the bottleneck. We were also able to have ~600µs average latency with that load.

https://gist.github.com/omnibs/e5e72b31e6bd25caf39a

other benchmark : https://www.techempower.com/benchmarks/