Hacker News new | ask | show | jobs
by joamag 3517 days ago
We really wanted to create a pure non blocking async IO network library in pure Python without any dependencies. On top of that we also wanted to prove that it's possible to archive 200K HTTP req/s in Python using PyPy with JIT.
1 comments

That's an impressive benchmark. On what hardware is it achieved?
While I'm not sure what hardware was used, if you want to try it yourself the benchmark is pretty easily reproducible [1].

[1] https://github.com/hivesolutions/netius/blob/c431b9c258baa0b...