golang调度器底层实现( G、M、P)

go的调度器只要实现在 runtime 包中，路径为： ./src/runtime/proc.go 文件中。

go语言其实是在操作系统提供的内核线程之上搭建了一个特有得 【两级线程】模型。下面再说两级线程模型前，有三个必知的核心元素。(G、M、P)

G：Goroutine的缩写，一个G代表了对一段需要被执行的Go语言代码的封装
M：Machine的缩写，一个M代表了一个内核线程
P：Processor的缩写，一个P代表了M所需的上下文环境
简单的来说，一个G的执行需要M和P的支持。一个M在与一个P关联之后形成了一个有效的G运行环境【内核线程 + 上下文环境】。每个P都会包含一个可运行的G的队列 (runq )。

好了下面我们来具体的看看 G、M、P

M (machine)：
M是machine的头文字, 在当前版本的golang中等同于系统线程.
M可以运行两种代码:

go代码, 即goroutine, M运行go代码需要一个P
原生代码, 例如阻塞的syscall, M运行原生代码不需要P
M会从运行队列中取出G, 然后运行G, 如果G运行完毕或者进入休眠状态, 则从运行队列中取出下一个G运行, 周而复始。
有时候G需要调用一些无法避免阻塞的原生代码, 这时M会释放持有的P并进入阻塞状态, 其他M会取得这个P并继续运行队列中的G.
go需要保证有足够的M可以运行G, 不让CPU闲着, 也需要保证M的数量不能过多。通常创建一个M的原因是由于没有足够的M来关联P并运行其中可运行的G。而且运行时系统执行系统监控的时候，或者GC的时候也会创建M。

M结构体的定义

type m struct {
	g0      *g     // goroutine with scheduling stack
	morebuf gobuf  // gobuf arg to morestack
	divmod  uint32 // div/mod denominator for arm - known to liblink

	// Fields not known to debuggers.
	procid        uint64       // for debuggers, but offset not hard-coded
	gsignal       *g           // signal-handling g
	goSigStack    gsignalStack // Go-allocated signal handling stack
	sigmask       sigset       // storage for saved signal mask
	tls           [6]uintptr   // thread-local storage (for x86 extern register)
	mstartfn      func()
	curg          *g       // current running goroutine
	caughtsig     guintptr // goroutine running during fatal signal
	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
	id            int64
	mallocing     int32
	throwing      int32
	preemptoff    string // if != "", keep curg running on this m
	locks         int32
	dying         int32
	profilehz     int32
	spinning      bool // m is out of work and is actively looking for work
	blocked       bool // m is blocked on a note
	inwb          bool // m is executing a write barrier
	newSigstack   bool // minit on C thread called sigaltstack
	printlock     int8
	incgo         bool   // m is executing a cgo call
	freeWait      uint32 // if == 0, safe to free g0 and delete m (atomic)
	fastrand      [2]uint32
	needextram    bool
	traceback     uint8
	ncgocall      uint64      // number of cgo calls in total
	ncgo          int32       // number of cgo calls currently in progress
	cgoCallersUse uint32      // if non-zero, cgoCallers in use temporarily
	cgoCallers    *cgoCallers // cgo traceback if crashing in cgo call
	park          note
	alllink       *m // on allm
	schedlink     muintptr
	mcache        *mcache
	lockedg       guintptr
	createstack   [32]uintptr    // stack that created this thread.
	lockedExt     uint32         // tracking for external LockOSThread
	lockedInt     uint32         // tracking for internal lockOSThread
	nextwaitm     muintptr       // next m waiting for lock
	waitunlockf   unsafe.Pointer // todo go func(*g, unsafe.pointer) bool
	waitlock      unsafe.Pointer
	waittraceev   byte
	waittraceskip int
	startingtrace bool
	syscalltick   uint32
	thread        uintptr // thread handle
	freelink      *m      // on sched.freem

	// these are here because they are too large to be on the stack
	// of low-level NOSPLIT functions.
	libcall   libcall
	libcallpc uintptr // for cpu profiler
	libcallsp uintptr
	libcallg  guintptr
	syscall   libcall // stores syscall parameters on windows

	vdsoSP uintptr // SP for traceback while in VDSO call (0 if not in call)
	vdsoPC uintptr // PC for traceback while in VDSO call

	mOS
}

P结构体的定义

type p struct {
	lock mutex

	id          int32
	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)
	mcache      *mcache
	racectx     uintptr

	deferpool    [5][]*_defer // pool of available defer structs of different sizes (see panic.go)
	deferpoolbuf [5][32]*_defer

	// Cache of goroutine ids, amortizes accesses to runtime·sched.goidgen.
	goidcache    uint64
	goidcacheend uint64

	// Queue of runnable goroutines. Accessed without lock.
	runqhead uint32
	runqtail uint32
	runq     [256]guintptr
	// 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
	}

	sudogcache []*sudog
	sudogbuf   [128]*sudog

	tracebuf traceBufPtr

	// traceSweep indicates the sweep events should be traced.
	// This is used to defer the sweep start event until a span
	// has actually been swept.
	traceSweep bool
	// traceSwept and traceReclaimed track the number of bytes
	// swept and reclaimed by sweeping in the current sweep loop.
	traceSwept, traceReclaimed uintptr

	palloc persistentAlloc // per-P to avoid mutex

	// Per-P GC state
	gcAssistTime         int64 // Nanoseconds in assistAlloc
	gcFractionalMarkTime int64 // Nanoseconds in fractional mark worker
	gcBgMarkWorker       guintptr
	gcMarkWorkerMode     gcMarkWorkerMode

	// gcMarkWorkerStartTime is the nanotime() at which this mark
	// worker started.
	gcMarkWorkerStartTime int64

	// gcw is this P's GC work buffer cache. The work buffer is
	// filled by write barriers, drained by mutator assists, and
	// disposed on certain GC state transitions.
	gcw gcWork

	// wbBuf is this P's GC write barrier buffer.
	//
	// TODO: Consider caching this in the running G.
	wbBuf wbBuf

	runSafePointFn uint32 // if 1, run sched.safePointFn at next safe point

	pad cpu.CacheLinePad
}

G结构体的定义

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).
	stack       stack   // offset known to runtime/cgo
	stackguard0 uintptr // offset known to liblink
	stackguard1 uintptr // offset known to liblink

	_panic         *_panic // innermost panic - offset known to liblink
	_defer         *_defer // innermost defer
	m              *m      // current m; offset known to arm liblink
	sched          gobuf
	syscallsp      uintptr        // if status==Gsyscall, syscallsp = sched.sp to use during gc
	syscallpc      uintptr        // if status==Gsyscall, syscallpc = sched.pc to use during gc
	stktopsp       uintptr        // expected sp at top of stack, to check in traceback
	param          unsafe.Pointer // passed parameter on wakeup
	atomicstatus   uint32
	stackLock      uint32 // sigprof/scang lock; TODO: fold in to atomicstatus
	goid           int64
	schedlink      guintptr
	waitsince      int64      // approx time when the g become blocked
	waitreason     waitReason // if status==Gwaiting
	preempt        bool       // preemption signal, duplicates stackguard0 = stackpreempt
	paniconfault   bool       // panic (instead of crash) on unexpected fault address
	preemptscan    bool       // preempted g does scan for gc
	gcscandone     bool       // g has scanned stack; protected by _Gscan bit in status
	gcscanvalid    bool       // false at start of gc cycle, true if G has not run since last scan; TODO: remove?
	throwsplit     bool       // must not split stack
	raceignore     int8       // ignore race detection events
	sysblocktraced bool       // StartTrace has emitted EvGoInSyscall about this goroutine
	sysexitticks   int64      // cputicks when syscall has returned (for tracing)
	traceseq       uint64     // trace event sequencer
	tracelastp     puintptr   // last P emitted an event for this goroutine
	lockedm        muintptr
	sig            uint32
	writebuf       []byte
	sigcode0       uintptr
	sigcode1       uintptr
	sigpc          uintptr
	gopc           uintptr         // pc of go statement that created this goroutine
	ancestors      *[]ancestorInfo // ancestor information goroutine(s) that created this goroutine (only used if debug.tracebackancestors)
	startpc        uintptr         // pc of goroutine function
	racectx        uintptr
	waiting        *sudog         // sudog structures this g is waiting on (that have a valid elem ptr); in lock order
	cgoCtxt        []uintptr      // cgo traceback context
	labels         unsafe.Pointer // profiler labels
	timer          *timer         // cached timer for time.Sleep
	selectDone     uint32         // are we participating in a select and did someone win the race?

	// Per-G GC state

	// gcAssistBytes is this G's GC assist credit in terms of
	// bytes allocated. If this is positive, then the G has credit
	// to allocate gcAssistBytes bytes without assisting. If this
	// is negative, then the G must correct this by performing
	// scan work. We track this in bytes to make it fast to update
	// and check for debt in the malloc hot path. The assist ratio
	// determines how this corresponds to scan work debt.
	gcAssistBytes int64
}