What are the main structures of the Go scheduler?

The Go scheduler is based on an M:N model, where M is the number of system threads (OS threads), and N is the number of goroutines.

• G (Goroutine) — represents an individual goroutine, containing its stack, state, and execution context.
• M (Machine) — a system thread that executes goroutines.
• P (Processor) — a logical processor that links M and G, managing the queue of goroutines ready to run.

The scheduler's work involves distributing goroutines (G) across available processors (P), which are in turn executed by threads (M). The number of P usually equals the number of available CPUs, allowing efficient utilization of multithreading and scheduling goroutine execution with minimal overhead.