调度(Scheduling)

线程(Thread)

• 用户线程(User-level Thread)
  • 协程(Coroutines)
  • Go Goroutine
  • Erlang process
  • 绿色线程(Green Thread)
• 内核线程(Kernel-level Thread)
• 纤程(Fibers)

用户线程(User-level Thread)

• Elixir: 0.48 GB (Process)
• Golang: 1.91 GB (Goroutine)
• Java: 977 GB (Thread)
• PHP: 6836 GB (Laravel Request)

用户线程的轻量除了提现在调度的上下文切换开销上，还体现了在对内存的需求上。如果要在4核心4GB内存的笔记本电脑中测试同时生成100万个线程的话，不同编程语言对内存的需求

线程模型(Thread Model)

上下文切换(Context switching)

Source: How long does it take to make a context switch?

Context switching is expensive. My rule of thumb is that it’ll cost you about 30µs of CPU overhead…Applications that create too many threads that are constantly fighting for CPU time (such as Apache’s HTTPd or many Java applications) can waste considerable amounts of CPU cycles just to switch back and forth between different threads…I think the sweet spot for optimal CPU use is to have the same number of worker threads as there are hardware threads, and write code in an asynchronous / non-blocking fashion.

一些延时数据

I/O模型(I/O Model)

• 同步(Synchronous)
  • 阻塞式(Blocking)
  • 非阻塞式(Non-blocking)
  • 多路复用(Multiplexing)
  • 信号驱动(Signal Driven)
• 异步(Asynchronous)

并发还是并行

• CPU密集型(CPU bound)
• I/O密集型(I/O bound)

并发模型