How is the distribution of goroutines across execution threads implemented?

In Go, the scheduling of goroutines onto OS threads is handled by the runtime's scheduler. A goroutine is a lightweight coroutine that does not directly correspond to a single OS thread.

The Go scheduler uses an M:N model, where M is the number of OS threads and N is the number of goroutines. It dynamically maps goroutines to threads to efficiently utilize available system resources.

Main components:

• G (goroutine) — the goroutine itself.
• M (machine) — an OS thread.
• P (processor) — a logical processor that manages goroutine execution.

Process:

1. A goroutine is assigned a P.
2. The P is associated with an M (OS thread).
3. The M executes the goroutine.

If a goroutine blocks (for example, on a system call), the scheduler can switch execution to another goroutine on a different thread to avoid idle time.

Thus, the distribution of goroutines across threads happens automatically and transparently to the developer, ensuring high concurrency and scalability.

Example of creating a goroutine:

 go func() {
    fmt.Println("Hello from goroutine")
}()

Here, the scheduler will decide on which OS thread to run this goroutine.