From 36cdb6831ca7d7b998016018851dd9c157d64617 Mon Sep 17 00:00:00 2001 From: Ciro Spaciari Date: Sun, 13 Nov 2022 11:51:37 -0300 Subject: [PATCH] Update README.md --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 32b6e72..c4681c5 100644 --- a/README.md +++ b/README.md @@ -62,8 +62,7 @@ Source code in [bench](https://github.com/cirospaciari/socketify.py/tree/main/be Machine OS: Debian GNU/Linux bookworm/sid x86_64 Kernel: 6.0.0-2-amd64 CPU: Intel i7-7700HQ (8) @ 3.800GHz Memory: 32066MiB -> Today socketify has get 30% performance hit due to workarounds between asyncio + libuv, so we will got even faster! See more info in [this issue](https://github.com/cirospaciari/socketify.py/issues/18), Python3 and PyPy3 performance will improve when we migrate to [HPy](https://github.com/cirospaciari/socketify.py/issues/16). In TechEmPower benchmarks we are faster than japronto in plaintext (about 1,300k req/s using PyPy3 without workaround and about 770k req/s with the current state vs 582k from japronto you can follow details in [this discussion](https://github.com/cirospaciari/socketify.py/discussions/10) - +> Today socketify has get 30% performance hit due to workarounds between asyncio + libuv, so we will got even faster! See more info in [this issue](https://github.com/cirospaciari/socketify.py/issues/18), Python3 and PyPy3 performance will improve when we migrate to [HPy](https://github.com/cirospaciari/socketify.py/issues/16). In TechEmPower paintext benchmarks we are the fastest in active web framework for Python/PyPy with more than 2 millions of req/s, followed by [Robyn](https://github.com/sansyrox/robyn) with almost 1.2 million req/s and [Falcon](https://github.com/falconry/falcon/tree/master/falcon) using meinheld with about 560k req/s. ## 📦 Installation For macOS x64 & Silicon, Linux x64, Windows