Disruptor VS JCTools

https://lmax-exchange.github.io/disruptor/#_what_is_the_disr.... Unfortunately IIUC writing this in Go still prevents the spin-locked acceptor thread from achieving the kind of performance you could get in a non-GC language, unless you chose to disable GC, so I'd guess Envoy is still faster.

https://gnet.host/docs/quickstart/ it's nice that you can use this simply though. Envoy is kind of tricky to setup with custom filters, so most of the time it's just a standalone binary.

[0] https://blog.envoyproxy.io/envoy-threading-model-a8d44b92231...

[1] https://lmax-exchange.github.io/disruptor/#_what_is_the_disr...

See also the Java LMAX Disruptor https://github.com/LMAX-Exchange/disruptor

I've built a similar lock-free ring buffer in C++11 https://github.com/posterior/loom/blob/master/doc/adapting.m...

"Why we chose Java for our High-Frequency Trading application"

https://medium.com/@jadsarmo/why-we-chose-java-for-our-high-...

LMAX Disruptor customers

https://lmax-exchange.github.io/disruptor/

Among many other examples.

Current documentation

https://lmax-exchange.github.io/disruptor/

LMAX Disruptor has on their wiki that average latency to send a message from one thread to another at 53 nanoseconds. For comparison a mutex is like 25 nanoseconds and more if Contended but a mutex is point to point synchronization.

The great thing about it is that multiple threads can receive the same message without much more effort.

https://github.com/LMAX-Exchange/disruptor/wiki/Performance-...

https://gist.github.com/rmacy/2879257

I am dreaming of language that is similar to Smalltalk that stays single threaded until it makes sense to parallise.

I am looking for problems to parallelism that are not big data. Parallelism is like adding more cars to the road rather than increasing the speed of the car. But what does a desktop or mobile user need to do locally that could take advantage of the mathematical power of a computer? I'm still searching.

Database config should be two connection strings, 1 for the admin user that creates the tables and anther for the queue user. Everything else should be stored in the database itself. Each queue should be in its own set of tables. Large blobs may or may not be referenced to an external file.

Shouldn't a message send be worst case a CAS. It really seems like all the work around garbage collection would have some use for in-memory high speed queues.

Are you familiar with the LMAX Disruptor? Is is a Java based cross thread messaging library used for day trading applications.

https://lmax-exchange.github.io/disruptor/

Disruptor for inter-thread messaging

I have never worked in any industries where a perf margin was that small. It is funny, in HFT there are folks using Lmax (Java) and then you have folks writing their own TCP/IP stacks on FPGAs to do trading.

Install some tool that would help you see the performance of your system, like a graph of the CPU usage, the top processes being used, disk activity/read/write, etc. Every time you run your program, glance at those numbers, eventually you'll develop an intuition. Basically write code and profile. A good exercise would be practicing with data structures, this site has an exhaustive list of them, find some stuff that's interesting then google the implementation, then build it yourself, test it, debug, profile, optimize, and understand the performance constraints. Eventually you'll develop better understanding and can compare between other people's works, optimizing them. If you want to go beyond, read some papers on lock-free algorithms https://github.com/JCTools/JCTools/tree/master/resources then read Brendan Gregg's blog and books. Read about how profiling tools work https://github.com/andikleen/pmu-tools/wiki/toplev-manual

If I fork this implementation's repo and then publish a release (of the forked version) with my own commits via jitpack.io (committing with Android Studio IDE).