go语言调度gmp原理

go语言调度gmp原理(1)

调度器启动

运行时通过runtime.schedinit初始化调度器

func schedinit() {
	lockInit(&sched.lock, lockRankSched)
	lockInit(&sched.sysmonlock, lockRankSysmon)
	lockInit(&sched.deferlock, lockRankDefer)
	lockInit(&sched.sudoglock, lockRankSudog)
	lockInit(&deadlock, lockRankDeadlock)
	lockInit(&paniclk, lockRankPanic)
	lockInit(&allglock, lockRankAllg)
	lockInit(&allpLock, lockRankAllp)
	lockInit(&reflectOffs.lock, lockRankReflectOffs)
	lockInit(&finlock, lockRankFin)
	lockInit(&trace.bufLock, lockRankTraceBuf)
	lockInit(&trace.stringsLock, lockRankTraceStrings)
	lockInit(&trace.lock, lockRankTrace)
	lockInit(&cpuprof.lock, lockRankCpuprof)
	lockInit(&trace.stackTab.lock, lockRankTraceStackTab)
	// Enforce that this lock is always a leaf lock.
	// All of this lock's critical sections should be
	// extremely short.
	lockInit(&memstats.heapStats.noPLock, lockRankLeafRank)

	// raceinit must be the first call to race detector.
	// In particular, it must be done before mallocinit below calls racemapshadow.
	gp := getg()
	if raceenabled {
		gp.racectx, raceprocctx0 = raceinit()
	}

	sched.maxmcount = 10000

	// The world starts stopped.
	worldStopped()

	moduledataverify()
	stackinit()
	mallocinit()
	godebug := getGodebugEarly()
	initPageTrace(godebug) // must run after mallocinit but before anything allocates
	cpuinit(godebug)       // must run before alginit
	alginit()              // maps, hash, fastrand must not be used before this call
	fastrandinit()         // must run before mcommoninit
	mcommoninit(gp.m, -1)
	modulesinit()   // provides activeModules
	typelinksinit() // uses maps, activeModules
	itabsinit()     // uses activeModules
	stkobjinit()    // must run before GC starts

	sigsave(&gp.m.sigmask)
	initSigmask = gp.m.sigmask

	goargs()
	goenvs()
	parsedebugvars()
	gcinit()

	// if disableMemoryProfiling is set, update MemProfileRate to 0 to turn off memprofile.
	// Note: parsedebugvars may update MemProfileRate, but when disableMemoryProfiling is
	// set to true by the linker, it means that nothing is consuming the profile, it is
	// safe to set MemProfileRate to 0.
	if disableMemoryProfiling {
		MemProfileRate = 0
	}

	lock(&sched.lock)
	sched.lastpoll.Store(nanotime())
	procs := ncpu
	if n, ok := atoi32(gogetenv("GOMAXPROCS")); ok && n > 0 {
		procs = n
	}
	if procresize(procs) != nil {
		throw("unknown runnable goroutine during bootstrap")
	}
	unlock(&sched.lock)

	// World is effectively started now, as P's can run.
	worldStarted()

	// For cgocheck > 1, we turn on the write barrier at all times
	// and check all pointer writes. We can't do this until after
	// procresize because the write barrier needs a P.
	if debug.cgocheck > 1 {
		writeBarrier.cgo = true
		writeBarrier.enabled = true
		for _, pp := range allp {
			pp.wbBuf.reset()
		}
	}

	if buildVersion == "" {
		// Condition should never trigger. This code just serves
		// to ensure runtime·buildVersion is kept in the resulting binary.
		buildVersion = "unknown"
	}
	if len(modinfo) == 1 {
		// Condition should never trigger. This code just serves
		// to ensure runtime·modinfo is kept in the resulting binary.
		modinfo = ""
	}
}

在调度器初始函数执行的过程中会将maxmcount设置成10000，这是go语言程序能够创建的最大线程数。虽然最多可以创建10000个线程，但是可以同时运行的线程还是由GOMAXPROCS变量控制的。

我们从环境变量GOMAXPROCS获取了程序能够同时运行的最大处理器数之后，就会调用runtime.procresize更新程序中处理器的数量，此时整个程序不会执行任何用户goroutine，调度器也会进入锁定状态，runtime.procresize的执行过程如下

func procresize(nprocs int32) *p {
	assertLockHeld(&sched.lock)
	assertWorldStopped()

	old := gomaxprocs
	if old < 0 || nprocs <= 0 {
		throw("procresize: invalid arg")
	}
	if trace.enabled {
		traceGomaxprocs(nprocs)
	}

	// update statistics
	now := nanotime()
	if sched.procresizetime != 0 {
		sched.totaltime += int64(old) * (now - sched.procresizetime)
	}
	sched.procresizetime = now

	maskWords := (nprocs + 31) / 32

	// Grow allp if necessary.
	if nprocs > int32(len(allp)) {
		// Synchronize with retake, which could be running
		// concurrently since it doesn't run on a P.
		lock(&allpLock)
		if nprocs <= int32(cap(allp)) {
			allp = allp[:nprocs]
		} else {
			nallp := make([]*p, nprocs)
			// Copy everything up to allp's cap so we
			// never lose old allocated Ps.
			copy(nallp, allp[:cap(allp)])
			allp = nallp
		}

		if maskWords <= int32(cap(idlepMask)) {
			idlepMask = idlepMask[:maskWords]
			timerpMask = timerpMask[:maskWords]
		} else {
			nidlepMask := make([]uint32, maskWords)
			// No need to copy beyond len, old Ps are irrelevant.
			copy(nidlepMask, idlepMask)
			idlepMask = nidlepMask

			ntimerpMask := make([]uint32, maskWords)
			copy(ntimerpMask, timerpMask)
			timerpMask = ntimerpMask
		}
		unlock(&allpLock)
	}

	// initialize new P's
	for i := old; i < nprocs; i++ {
		pp := allp[i]
		if pp == nil {
			pp = new(p)
		}
		pp.init(i)
		atomicstorep(unsafe.Pointer(&allp[i]), unsafe.Pointer(pp))
	}

	gp := getg()
	if gp.m.p != 0 && gp.m.p.ptr().id < nprocs {
		// continue to use the current P
		gp.m.p.ptr().status = _Prunning
		gp.m.p.ptr().mcache.prepareForSweep()
	} else {
		// release the current P and acquire allp[0].
		//
		// We must do this before destroying our current P
		// because p.destroy itself has write barriers, so we
		// need to do that from a valid P.
		if gp.m.p != 0 {
			if trace.enabled {
				// Pretend that we were descheduled
				// and then scheduled again to keep
				// the trace sane.
				traceGoSched()
				traceProcStop(gp.m.p.ptr())
			}
			gp.m.p.ptr().m = 0
		}
		gp.m.p = 0
		pp := allp[0]
		pp.m = 0
		pp.status = _Pidle
		acquirep(pp)
		if trace.enabled {
			traceGoStart()
		}
	}

	// g.m.p is now set, so we no longer need mcache0 for bootstrapping.
	mcache0 = nil

	// release resources from unused P's
	for i := nprocs; i < old; i++ {
		pp := allp[i]
		pp.destroy()
		// can't free P itself because it can be referenced by an M in syscall
	}

	// Trim allp.
	if int32(len(allp)) != nprocs {
		lock(&allpLock)
		allp = allp[:nprocs]
		idlepMask = idlepMask[:maskWords]
		timerpMask = timerpMask[:maskWords]
		unlock(&allpLock)
	}

	var runnablePs *p
	for i := nprocs - 1; i >= 0; i-- {
		pp := allp[i]
		if gp.m.p.ptr() == pp {
			continue
		}
		pp.status = _Pidle
		if runqempty(pp) {
			pidleput(pp, now)
		} else {
			pp.m.set(mget())
			pp.link.set(runnablePs)
			runnablePs = pp
		}
	}
	stealOrder.reset(uint32(nprocs))
	var int32p *int32 = &gomaxprocs // make compiler check that gomaxprocs is an int32
	atomic.Store((*uint32)(unsafe.Pointer(int32p)), uint32(nprocs))
	if old != nprocs {
		// Notify the limiter that the amount of procs has changed.
		gcCPULimiter.resetCapacity(now, nprocs)
	}
	return runnablePs
}

1. 如果全局变量allp切片中的处理器数量少于期望数量，会对切片进行扩容
2. 使用new创建新的处理器结构体，并调用runtime.p.init初始化刚刚扩容的处理器
3. 通过指针将线程m0和处理器allp[0]绑定到一起
4. 调用runtime.destroy释放不再使用的处理器结构
5. 通过截断改变全局变量allp的长度保证与期望处理器数量相等
6. 将除allp[0]外的处理器P全部设置成_Pidle并加入全局的空闲队列中

调用runtime.procresize是调度器启动的最后一步，之后调度器会启动响应数量的处理器，等待用户创建、运行新的goroutine并为goroutine调度处理器资源

小结

go语言运行时启动时会初始化g0和m0并绑定，然后调用schedinit来进行各种初始化，将会初始化m的数量和GOMAXPROCS个处理器来的来等待调度