sonic VS monoio

Since most of the time would be spent decoding json, you could try to cut this time using https://github.com/bytedance/sonic or https://github.com/json-iterator/go, both are drop-in replacements for the stdlib, sonic is faster.

Also worth looking at https://github.com/bytedance/sonic

The article inside does not mention this.

Good morning.I hope this is not the wrong place to post… so let me introduce my first public Golang package. This is a JSON decoder called Sonnet ( https://github.com/sugawarayuuta/sonnet ) that has given faster results (at least in my environment) than Sonic - https://github.com/bytedance/sonic (which is said that it's the fastest) without the help of assembly!

JSON is a very well-known file format. It is used by everyone who does programming. However, it is also not uncommon to find problems with encoding/json and other third-party libraries. for more… (see https://github.com/sugawarayuuta/sonnet#problems-we-had )

I decided to create a new, standard library-compatible decoder that would be both easy to use and fast.

Thanks for reading, feel free to use, help, or ask questions, I look forward to hearing from you. All benchmarks and other information can be found in the link at the top.

Good morning. Let me introduce my first public Go package. This is a JSON decoder called Sonnet ( https://github.com/sugawarayuuta/sonnet ) that has given faster results (at least in my environment) than Sonic (which is said that it's the fastest) without the help of assembly!

I'd say the https://github.com/bytedance/sonic has the fastest encoder due to C and assembly optimization. (Use at your own risk.)

There is also another thread-per-core implementation by ByteDance (TikTok) for Rust called Monoio with benchmarks[0] comparing it to Tokio and Glommio.

[0] https://github.com/bytedance/monoio/blob/master/docs/en/benc...

My understanding is you always need a runtime, somethings needs to drive the async flow. But there are others on the market, just not without the.. market domination... of tokio.

https://github.com/smol-rs/smol looks promising simply for being minimal

https://github.com/bytedance/monoio looks potentially easier to work with than tokio

https://github.com/DataDog/glommio is built around linux io_uring and seems somewhat promising for performance reasons.

I haven't played with any of these yet, because Tokio is unfortunately the path of least resistance. And a bit viral in how it's infected tings.

I assume Tokio itself, see e.g monoio or glommio, but also Seastar for C++.

I think monoio is also thread-per-core but also iouring https://github.com/bytedance/monoio. I don't know how you would shard certain keys into different threads, but if you can do that deterministically then there could be a significant speed up.

I believe this is also "thread-per-core".

Bytedance has their in-house monoio <https://github.com/bytedance/monoio> (supports io-uring) but it requires rust nightly.

There's another thread-per-core runtime called https://github.com/bytedance/monoio

It's worth mentioning: Under "Async Executors", for "io_uring" there is only "Glommio"

I recently found out that ByteDance has a competitor library which supposedly has better performance:

https://github.com/bytedance/monoio

https://github.com/DataDog/glommio/issues/554

I see that, I also tried with monoio, but the developer of that runtime mentioned that https://github.com/bytedance/monoio/blob/master/examples/hyper_server.rs might have soundness issues