goroutine调度器概述(11)

......
for i := 0; i < N; i++ { // 创建N个操作系统线程执行schedule函数
    create_os_thread(schedule) // 创建一个操作系统线程执行schedule函数
}
//schedule函数实现调度逻辑
func schedule() {
   for { //调度循环
         // 根据某种算法从M个goroutine中找出一个需要运行的goroutine
         g := find_a_runnable_goroutine_from_M_goroutines()
         run_g(g) // CPU运行该goroutine，直到需要调度其它goroutine才返回
         save_status_of_g(g) // 保存goroutine的状态，主要是寄存器的值
    }
}

......
for i := 0; i < N; i++ { // 创建N个操作系统线程执行schedule函数
     create_os_thread(schedule) // 创建一个操作系统线程执行schedule函数
}

// ThreadLocal用来定义线程私有全局变量
ThreadLocal self *m 
//schedule函数实现调度逻辑
func schedule() {
    // 创建和初始化m结构体对象，并赋值给私有全局变量self
    self = initm()   
    for { //调度循环
          if (self.p.runqueue is empty) {
                 // 根据某种算法从全局运行队列中找出一个需要运行的goroutine
                 g := find_a_runnable_goroutine_from_global_runqueue()
           } else {
                 // 根据某种算法从私有的局部运行队列中找出一个需要运行的goroutine
                 g := find_a_runnable_goroutine_from_local_runqueue()
           }
          run_g(g) // CPU运行该goroutine，直到需要调度其它goroutine才返回
          save_status_of_g(g) // 保存goroutine的状态，主要是寄存器的值
     }
}

type gobuf struct {
    // The offsets of sp, pc, and g are known to (hard-coded in) libmach.
    //
    // ctxt is unusual with respect to GC: it may be a
    // heap-allocated funcval, so GC needs to track it, but it
    // needs to be set and cleared from assembly, where it's
    // difficult to have write barriers. However, ctxt is really a
    // saved, live register, and we only ever exchange it between
    // the real register and the gobuf. Hence, we treat it as a
    // root during stack scanning, which means assembly that saves
    // and restores it doesn't need write barriers. It's still
    // typed as a pointer so that any other writes from Go get
    // write barriers.
    sp   uintptr  // 保存CPU的rsp寄存器的值
    pc   uintptr  // 保存CPU的rip寄存器的值
    g    guintptr // 记录当前这个gobuf对象属于哪个goroutine
    ctxt unsafe.Pointer
 
    // 保存系统调用的返回值，因为从系统调用返回之后如果p被其它工作线程抢占，
    // 则这个goroutine会被放入全局运行队列被其它工作线程调度，其它线程需要知道系统调用的返回值。
    ret  sys.Uintreg  
    lr   uintptr
 
    // 保存CPU的rip寄存器的值
    bp   uintptr // for GOEXPERIMENT=framepointer
}

type g struct {
    // Stack parameters.
    // stack describes the actual stack memory: [stack.lo, stack.hi).
    // stackguard0 is the stack pointer compared in the Go stack growth prologue.
    // It is stack.lo+StackGuard normally, but can be StackPreempt to trigger a preemption.
    // stackguard1 is the stack pointer compared in the C stack growth prologue.
    // It is stack.lo+StackGuard on g0 and gsignal stacks.
    // It is ~0 on other goroutine stacks, to trigger a call to morestackc (and crash).
 
    // 记录该goroutine使用的栈
    stack       stack   // offset known to runtime/cgo
    // 下面两个成员用于栈溢出检查，实现栈的自动伸缩，抢占调度也会用到stackguard0
    stackguard0 uintptr // offset known to liblink
    stackguard1 uintptr // offset known to liblink

    ......
 
    // 此goroutine正在被哪个工作线程执行
    m              *m      // current m; offset known to arm liblink
    // 保存调度信息，主要是几个寄存器的值
    sched          gobuf
 
    ......
    // schedlink字段指向全局运行队列中的下一个g，
    //所有位于全局运行队列中的g形成一个链表
    schedlink      guintptr

    ......
    // 抢占调度标志，如果需要抢占调度，设置preempt为true
    preempt        bool       // preemption signal, duplicates stackguard0 = stackpreempt

   ......
}

type m struct {
    // g0主要用来记录工作线程使用的栈信息，在执行调度代码时需要使用这个栈
    // 执行用户goroutine代码时，使用用户goroutine自己的栈，调度时会发生栈的切换
    g0      *g     // goroutine with scheduling stack

    // 通过TLS实现m结构体对象与工作线程之间的绑定
    tls           [6]uintptr   // thread-local storage (for x86 extern register)
    mstartfn      func()
    // 指向工作线程正在运行的goroutine的g结构体对象
    curg          *g       // current running goroutine
 
    // 记录与当前工作线程绑定的p结构体对象
    p             puintptr // attached p for executing go code (nil if not executing go code)
    nextp         puintptr
    oldp          puintptr // the p that was attached before executing a syscall
   
    // spinning状态：表示当前工作线程正在试图从其它工作线程的本地运行队列偷取goroutine
    spinning      bool // m is out of work and is actively looking for work
    blocked       bool // m is blocked on a note
   
    // 没有goroutine需要运行时，工作线程睡眠在这个park成员上，
    // 其它线程通过这个park唤醒该工作线程
    park          note
    // 记录所有工作线程的一个链表
    alllink       *m // on allm
    schedlink     muintptr

    // Linux平台thread的值就是操作系统线程ID
    thread        uintptr // thread handle
    freelink      *m      // on sched.freem

    ......
}

type p struct {
    lock mutex

    status       uint32 // one of pidle/prunning/...
    link            puintptr
    schedtick   uint32     // incremented on every scheduler call
    syscalltick  uint32     // incremented on every system call
    sysmontick  sysmontick // last tick observed by sysmon
    m                muintptr   // back-link to associated m (nil if idle)

    ......

    // Queue of runnable goroutines. Accessed without lock.
    //本地goroutine运行队列
    runqhead uint32  // 队列头
    runqtail uint32     // 队列尾
    runq     [256]guintptr  //使用数组实现的循环队列
    // runnext, if non-nil, is a runnable G that was ready'd by
    // the current G and should be run next instead of what's in
    // runq if there's time remaining in the running G's time
    // slice. It will inherit the time left in the current time
    // slice. If a set of goroutines is locked in a
    // communicate-and-wait pattern, this schedules that set as a
    // unit and eliminates the (potentially large) scheduling
    // latency that otherwise arises from adding the ready'd
    // goroutines to the end of the run queue.
    runnext guintptr

    // Available G's (status == Gdead)
    gFree struct {
        gList
        n int32
    }

    ......
}

type schedt struct {
    // accessed atomically. keep at top to ensure alignment on 32-bit systems.
    goidgen  uint64
    lastpoll uint64

    lock mutex

    // When increasing nmidle, nmidlelocked, nmsys, or nmfreed, be
    // sure to call checkdead().

    // 由空闲的工作线程组成链表
    midle        muintptr // idle m's waiting for work
    // 空闲的工作线程的数量
    nmidle       int32    // number of idle m's waiting for work
    nmidlelocked int32    // number of locked m's waiting for work
    mnext        int64    // number of m's that have been created and next M ID
    // 最多只能创建maxmcount个工作线程
    maxmcount    int32    // maximum number of m's allowed (or die)
    nmsys        int32    // number of system m's not counted for deadlock
    nmfreed      int64    // cumulative number of freed m's

    ngsys uint32 // number of system goroutines; updated atomically

    // 由空闲的p结构体对象组成的链表
    pidle      puintptr // idle p's
    // 空闲的p结构体对象的数量
    npidle     uint32
    nmspinning uint32 // See "Worker thread parking/unparking" comment in proc.go.

    // Global runnable queue.
    // goroutine全局运行队列
    runq     gQueue
    runqsize int32

    ......

    // Global cache of dead G's.
    // gFree是所有已经退出的goroutine对应的g结构体对象组成的链表
    // 用于缓存g结构体对象，避免每次创建goroutine时都重新分配内存
    gFree struct {
        lock          mutex
        stack        gList // Gs with stacks
        noStack   gList // Gs without stacks
        n              int32
    }
 
    ......
}

allgs     []*g     // 保存所有的g
allm       *m    // 所有的m构成的一个链表，包括下面的m0
allp       []*p    // 保存所有的p，len(allp) == gomaxprocs

ncpu             int32   // 系统中cpu核的数量，程序启动时由runtime代码初始化
gomaxprocs int32   // p的最大值，默认等于ncpu，但可以通过GOMAXPROCS修改

sched      schedt     // 调度器结构体对象，记录了调度器的工作状态

m0  m       // 代表进程的主线程
g0   g        // m0的g0，也就是m0.g0 = &g0