After Rust - Now Python 3.5 beats golang

[rebootcode]

Japronto - https://github.com/squeaky-pl/japronto which is built over python 3.5 now claims to beat golang by twice the speed and performance.

My Question is - Can python beat this ?

What version of Go are you using (go version)?

1.8.3

What operating system and processor architecture are you using (go env)?

Ubuntu 16.04

What did you do?

Benchmark

[dlsniper]

it's nice of Japronto that they are doing 1.2 million requests a second. But if you need any meaningful help, I suggest you have a look at these places to get help https://golang.org/help/#help on how to optimize your code to make sure it makes the best out of Go. This is not a real Go issue as far as I can tell and should be closed.

[dlsniper]

Oh, and so that you don't leave confused from this interaction:

https://github.com/squeaky-pl/japronto/tree/master/benchmarks/golang -> looking at the code there's an extra condition in there executed for Go and not for the Python thingy. squeaky-pl/japronto#29 -> PR opened since Feb 3rd reflects that.

But, worse, GOMAXPROCS is set to 1 on a m4.2xl instance which has 8 vCPUs, which means Go will run on a single core instead of 8.

You can do your own benchmarks after receiving this information and see what happens :)

Hope it helps.

[rebootcode]

To be fair all the contestants (including Go) were running single worker process. Servers were load tested using wrk with 1 thread, 100 connections and 24 simultaneous (pipelined) requests per connection (cumulative parallelism of 2400 requests).

[faiface]

The server is written in hand tweaked C trying to take advantage of modern CPUs.

Pure Python would be way slower.

[davecheney]

The discussion on this issue has ended. I am closing comments on this issue.

You may continue to debate it on other forums if you wish. Please see https://golang.org/wiki/Questions for good places to ask. Thanks.