Are these trivial micro benchmarks, (simply respond with an empty 200) not totally misleading to focus on?
Especially when you start to factor in many real workloads that involve disk or network io.
Its not empty because its 1mb but it is misleading because in the original article someone's comment showed Node going much faster than Go. If it were empty then Node would be faster because you can get 4000 req per sec if its empty. I think something weird is going on though because it should be more than 300 per sec with the new Node version even if its 1mb.