static void scheduler(void) {
	G* gp;
	lock(&sched);

	if(gosave(&m->sched)){
		lock(&sched);
		gp = m->curg;
		switch(gp->status){
		case Grunnable:
		case Grunning:
			gp->status = Grunnable;
			gput(gp);
			break;
		...
		}
		notewakeup(&gp->stopped);
	}

	gp = nextgandunlock();
	noteclear(&gp->stopped);
	gp->status = Grunning;
	m->curg = gp;
	g = gp;
	gogo(&gp->sched);
}

static void schedule(G *gp) {
	schedlock();
	if(gp != nil) {
		gp->m = nil;
		uint32 v = runtime·xadd(&runtime·sched.atomic, -1<<mcpuShift);
		if(atomic_mcpu(v) > maxgomaxprocs)
			runtime·throw("negative mcpu in scheduler");

		switch(gp->status){
		case Grunning:
			gp->status = Grunnable;
			gput(gp);
			break;
		case ...:
		}
	} else {
		...
	}
	gp = nextgandunlock();
	gp->status = Grunning;
	m->curg = gp;
	gp->m = m;
	runtime·gogo(&gp->sched, 0);
}

struct P {
	Lock;

	uint32	status;
	P*	link;
	uint32	tick;
	M*	m;
	MCache*	mcache;

	G**	runq;
	int32	runqhead;
	int32	runqtail;
	int32	runqsize;

	G*	gfree;
	int32	gfreecnt;
};

// /usr/local/go/src/runtime/runtime2.go
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 // status of this goroutine
	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
	preemptStop   bool // transition to _Gpreempted on preemption; otherwise, just deschedule
	preemptShrink bool // shrink stack at synchronous safe point

	// asyncSafePoint is set if g is stopped at an asynchronous
	// safe point. This means there are frames on the stack
	// without precise pointer information.
	asyncSafePoint bool

	paniconfault bool // panic (instead of crash) on unexpected fault address
	gcscandone   bool // g has scanned stack; protected by _Gscan bit in status
	throwsplit   bool // must not split stack
	// activeStackChans indicates that there are unlocked channels
	// pointing into this goroutine's stack. If true, stack
	// copying needs to acquire channel locks to protect these
	// areas of the stack.
	activeStackChans bool

	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
}

// /usr/local/go/src/runtime/runtime2.go
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
	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   func(*g, unsafe.Pointer) bool
	waitlock      unsafe.Pointer
	waittraceev   byte
	waittraceskip int
	startingtrace bool
	syscalltick   uint32
	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

	// preemptGen counts the number of completed preemption
	// signals. This is used to detect when a preemption is
	// requested, but fails. Accessed atomically.
	preemptGen uint32

	// Whether this is a pending preemption signal on this M.
	// Accessed atomically.
	signalPending uint32

	dlogPerM

	mOS
}

// /usr/local/go/src/runtime/runtime2.go
type p struct {
	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
	pcache      pageCache
	raceprocctx 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

	// Cache of mspan objects from the heap.
	mspancache struct {
		// We need an explicit length here because this field is used
		// in allocation codepaths where write barriers are not allowed,
		// and eliminating the write barrier/keeping it eliminated from
		// slice updates is tricky, moreso than just managing the length
		// ourselves.
		len int
		buf [128]*mspan
	}

	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

	_ uint32 // Alignment for atomic fields below

	// The when field of the first entry on the timer heap.
	// This is updated using atomic functions.
	// This is 0 if the timer heap is empty.
	timer0When uint64

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

	// Lock for timers. We normally access the timers while running
	// on this P, but the scheduler can also do it from a different P.
	timersLock mutex

	// Actions to take at some time. This is used to implement the
	// standard library's time package.
	// Must hold timersLock to access.
	timers []*timer

	// Number of timers in P's heap.
	// Modified using atomic instructions.
	numTimers uint32

	// Number of timerModifiedEarlier timers on P's heap.
	// This should only be modified while holding timersLock,
	// or while the timer status is in a transient state
	// such as timerModifying.
	adjustTimers uint32

	// Number of timerDeleted timers in P's heap.
	// Modified using atomic instructions.
	deletedTimers uint32

	// Race context used while executing timer functions.
	timerRaceCtx uintptr

	// preempt is set to indicate that this P should be enter the
	// scheduler ASAP (regardless of what G is running on it).
	preempt bool

	pad cpu.CacheLinePad
}

// /usr/local/go/src/runtime/proc.go
// forcePreemptNS is the time slice given to a G before it is
// preempted.
const forcePreemptNS = 10 * 1000 * 1000 // 10ms

func retake(now int64) uint32 {
	n := 0
	// Prevent allp slice changes. This lock will be completely
	// uncontended unless we're already stopping the world.
	lock(&allpLock)
	// We can't use a range loop over allp because we may
	// temporarily drop the allpLock. Hence, we need to re-fetch
	// allp each time around the loop.
	for i := 0; i < len(allp); i++ {
	...

runtime.schedule() {
    // only 1/61 of the time, check the global runnable queue for a G.
    // if not found, check the local queue.
    // if not found,
    //     try to steal from other Ps.
    //     if not, check the global runnable queue.
    //     if not found, poll network.
}

$ GODEBUG=schedtrace=1000 ./program
SCHED 0ms: gomaxprocs=4 idleprocs=3 threads=3 spinningthreads=0 idlethreads=0 runqueue=0 [0 0 0 0]
SCHED 1001ms: gomaxprocs=4 idleprocs=0 threads=9 spinningthreads=0 idlethreads=3 runqueue=2 [8 14 5 2]
SCHED 2006ms: gomaxprocs=4 idleprocs=0 threads=25 spinningthreads=0 idlethreads=19 runqueue=12 [0 0 4 0]
SCHED 3006ms: gomaxprocs=4 idleprocs=0 threads=26 spinningthreads=0 idlethreads=8 runqueue=2 [0 1 1 0]

... ...

以上面例子中最后一行为例：

SCHED 6016ms: gomaxprocs=4 idleprocs=0 threads=26 spinningthreads=0 idlethreads=20 runqueue=1 [3 4 0 10]

SCHED：调试信息输出标志字符串，代表本行是goroutine scheduler的输出；
6016ms：即从程序启动到输出这行日志的时间；
gomaxprocs: P的数量；
idleprocs: 处于idle状态的P的数量；通过gomaxprocs和idleprocs的差值，我们就可知道执行go代码的P的数量；
threads: os threads的数量，包含scheduler使用的m数量，加上runtime自用的类似sysmon这样的thread的数量；
spinningthreads: 处于自旋状态的os thread数量；
idlethread: 处于idle状态的os thread的数量；
runqueue=1： go scheduler全局队列中G的数量；
[3 4 0 10]: 分别为4个P的local queue中的G的数量。

$ GODEBUG=schedtrace=1000,scheddetail=1 ./program

SCHED 0ms: gomaxprocs=4 idleprocs=3 threads=3 spinningthreads=0 idlethreads=0 runqueue=0 gcwaiting=0 nmidlelocked=0 stopwait=0 sysmonwait=0
  P0: status=1 schedtick=0 syscalltick=0 m=0 runqsize=0 gfreecnt=0
  P1: status=0 schedtick=0 syscalltick=0 m=-1 runqsize=0 gfreecnt=0
  P2: status=0 schedtick=0 syscalltick=0 m=-1 runqsize=0 gfreecnt=0
  P3: status=0 schedtick=0 syscalltick=0 m=-1 runqsize=0 gfreecnt=0
  M2: p=-1 curg=-1 mallocing=0 throwing=0 preemptoff= locks=1 dying=0 helpgc=0 spinning=false blocked=false lockedg=-1
  M1: p=-1 curg=17 mallocing=0 throwing=0 preemptoff= locks=0 dying=0 helpgc=0 spinning=false blocked=false lockedg=17
  M0: p=0 curg=1 mallocing=0 throwing=0 preemptoff= locks=1 dying=0 helpgc=0 spinning=false blocked=false lockedg=1
  G1: status=8() m=0 lockedm=0
  G17: status=3() m=1 lockedm=1

SCHED 1002ms: gomaxprocs=4 idleprocs=0 threads=13 spinningthreads=0 idlethreads=7 runqueue=6 gcwaiting=0 nmidlelocked=0 stopwait=0 sysmonwait=0

 P0: status=2 schedtick=2293 syscalltick=18928 m=-1 runqsize=12 gfreecnt=2
  P1: status=1 schedtick=2356 syscalltick=19060 m=11 runqsize=11 gfreecnt=0
  P2: status=2 schedtick=2482 syscalltick=18316 m=-1 runqsize=37 gfreecnt=1
  P3: status=2 schedtick=2816 syscalltick=18907 m=-1 runqsize=2 gfreecnt=4
  M12: p=-1 curg=-1 mallocing=0 throwing=0 preemptoff= locks=0 dying=0 helpgc=0 spinning=false blocked=true lockedg=-1
  M11: p=1 curg=6160 mallocing=0 throwing=0 preemptoff= locks=2 dying=0 helpgc=0 spinning=false blocked=false lockedg=-1
  M10: p=-1 curg=-1 mallocing=0 throwing=0 preemptoff= locks=0 dying=0 helpgc=0 spinning=false blocked=true lockedg=-1
 ... ...

SCHED 2002ms: gomaxprocs=4 idleprocs=0 threads=23 spinningthreads=0 idlethreads=5 runqueue=4 gcwaiting=0 nmidlelocked=0 stopwait=0 sysmonwait=0
  P0: status=0 schedtick=2972 syscalltick=29458 m=-1 runqsize=0 gfreecnt=6
  P1: status=2 schedtick=2964 syscalltick=33464 m=-1 runqsize=0 gfreecnt=39
  P2: status=1 schedtick=3415 syscalltick=33283 m=18 runqsize=0 gfreecnt=12
  P3: status=2 schedtick=3736 syscalltick=33701 m=-1 runqsize=1 gfreecnt=6
  M22: p=-1 curg=-1 mallocing=0 throwing=0 preemptoff= locks=0 dying=0 helpgc=0 spinning=false blocked=true lockedg=-1
  M21: p=-1 curg=-1 mallocing=0 throwing=0 preemptoff= locks=0 dying=0 helpgc=0 spinning=false blocked=true lockedg=-1
... ...