Hacker News Reader

Comment by amelius | Hacker News Reader

Skimming through the article, it seems to me that this server spawns a thread per connection, is that correct?

We use a very different model actually. Since spawning OS threads is expensive, we opted for the popular nonblocking-IO approach. Each worker thread (usually 1 per core on the CPU) is given connections in a round robin fashion from the listening socket. The worker thread runs an event loop processing events on the accepted socket.

What kind of programming technique did you use to implement the handling of the protocols? Did you implement them as finite-state machines, or did you use coroutines, or some other technique?

Do you think that C++ is a well suited language for this kind of processing? Is it possible to say, now this project is in a mature state, that other languages (e.g. Rust) could have helped make your implementation simpler?

Hey, I'm a Software Engineer on Proxygen as well. Proxygen heavily relies on folly's buffer management abstractions such as IOBuf (https://github.com/facebook/folly/blob/master/folly/io/IOBuf...) and Cursor (https://github.com/facebook/folly/blob/master/folly/io/Curso...). Protocol parsing implementation uses folly::io::Cursor to safely read byte sequences across non-contiguous buffers. Errors during parsing are wrapped up in Result types (https://github.com/facebook/proxygen/blob/master/proxygen/li...) which take an inspiration from Rust. Such constructs simplify our implementation to a reasonable extent and are still low-level enough to extract performance.

Note: as google discovered a few years ago, round-robining the connections is probably less than ideal.

Reply on news.ycombinator.com