[zoombini29]

do you have perf benchmarks under heavier concurrency? (e.g., how does it do with 100 concurrent clients? 1000?)

[1st1]

The HTTP benchmarks were actually run under concurrency level of 300. I've just updated the post with extra details. See also the full report of HTTP benchmark [1]

[1] http://magic.io/blog/uvloop-blazing-fast-python-networking/h...