Golang 垃圾回收剖析

func mallocgc(size uintptr, typ *_type, needzero bool) unsafe.Pointer {
    ...
    shouldhelpgc := false
    // 分配的对象小于 32K byte
    if size <= maxSmallSize {
        ...
    } else {
        shouldhelpgc = true
        ...
    }
    ...
    // gcShouldStart() 函数进行触发条件检测
    if shouldhelpgc && gcShouldStart(false) {
        // gcStart() 函数进行垃圾回收
        gcStart(gcBackgroundMode, false)
    }
}

// GC runs a garbage collection and blocks the caller until the
// garbage collection is complete. It may also block the entire
// program.
func GC() {
    gcStart(gcForceBlockMode, false)
}

// gcShouldStart returns true if the exit condition for the _GCoff
// phase has been met. The exit condition should be tested when
// allocating.
//
// If forceTrigger is true, it ignores the current heap size, but
// checks all other conditions. In general this should be false.
func gcShouldStart(forceTrigger bool) bool {
    return gcphase == _GCoff && (forceTrigger || memstats.heap_live >= memstats.gc_trigger) && memstats.enablegc && panicking == 0 && gcpercent >= 0
}

//初始化的时候设置 GC 的触发阈值
func gcinit() {
    _ = setGCPercent(readgogc())
    memstats.gc_trigger = heapminimum
    ...
}
// 启动的时候通过 GOGC 传递百分比 x
// 触发阈值等于 x * defaultHeapMinimum (defaultHeapMinimum 默认是 4M)
func readgogc() int32 {
    p := gogetenv("GOGC")
    if p == "off" {
        return -1
    }
    if n, ok := atoi32(p); ok {
        return n
    }
    return 100
}

// gcStart 是 GC 的入口函数，根据 gcMode 做处理。
// 1. gcMode == gcBackgroundMode（后台运行，也就是并行）, _GCoff -> _GCmark
// 2. 否则 GCoff -> _GCmarktermination，这个时候就是主动 GC 
func gcStart(mode gcMode, forceTrigger bool) {
    ...
}

func gcStart(mode gcMode, forceTrigger bool) {
    ...
    //在后台启动 mark worker 
    if mode == gcBackgroundMode {
        gcBgMarkStartWorkers()
    }
    ...
    // Stop The World
    systemstack(stopTheWorldWithSema)
    ...
    if mode == gcBackgroundMode {
        // GC 开始前的准备工作

        //处理设置 GCPhase，setGCPhase 还会 enable write barrier
        setGCPhase(_GCmark)
      	
        gcBgMarkPrepare() // Must happen before assist enable.
        gcMarkRootPrepare()

        // Mark all active tinyalloc blocks. Since we're
        // allocating from these, they need to be black like
        // other allocations. The alternative is to blacken
        // the tiny block on every allocation from it, which
        // would slow down the tiny allocator.
        gcMarkTinyAllocs()
      	
        // Start The World
        systemstack(startTheWorldWithSema)
    } else {
        ...
    }
}

func gcStart(mode gcMode, forceTrigger bool) {
    ...
    //在后台启动 mark worker 
    if mode == gcBackgroundMode {
        gcBgMarkStartWorkers()
    }
}

func gcBgMarkStartWorkers() {
    // Background marking is performed by per-P G's. Ensure that
    // each P has a background GC G.
    for _, p := range &allp {
        if p == nil || p.status == _Pdead {
            break
        }
        if p.gcBgMarkWorker == 0 {
            go gcBgMarkWorker(p)
            notetsleepg(&work.bgMarkReady, -1)
            noteclear(&work.bgMarkReady)
        }
    }
}
// gcBgMarkWorker 是一直在后台运行的，大部分时候是休眠状态，通过 gcController 来调度
func gcBgMarkWorker(_p_ *p) {
    for {
        // 将当前 goroutine 休眠，直到满足某些条件
        gopark(...)
        ...
        // mark 过程
        systemstack(func() {
        // Mark our goroutine preemptible so its stack
        // can be scanned. This lets two mark workers
        // scan each other (otherwise, they would
        // deadlock). We must not modify anything on
        // the G stack. However, stack shrinking is
        // disabled for mark workers, so it is safe to
        // read from the G stack.
        casgstatus(gp, _Grunning, _Gwaiting)
        switch _p_.gcMarkWorkerMode {
        default:
            throw("gcBgMarkWorker: unexpected gcMarkWorkerMode")
        case gcMarkWorkerDedicatedMode:
            gcDrain(&_p_.gcw, gcDrainNoBlock|gcDrainFlushBgCredit)
        case gcMarkWorkerFractionalMode:
            gcDrain(&_p_.gcw, gcDrainUntilPreempt|gcDrainFlushBgCredit)
        case gcMarkWorkerIdleMode:
            gcDrain(&_p_.gcw, gcDrainIdle|gcDrainUntilPreempt|gcDrainFlushBgCredit)
        }
        casgstatus(gp, _Gwaiting, _Grunning)
        })
        ...
    }
}

// gcDrain scans roots and objects in work buffers, blackening grey
// objects until all roots and work buffers have been drained.
func gcDrain(gcw *gcWork, flags gcDrainFlags) {
    ...	
    // Drain root marking jobs.
    if work.markrootNext < work.markrootJobs {
        for !(preemptible && gp.preempt) {
            job := atomic.Xadd(&work.markrootNext, +1) - 1
            if job >= work.markrootJobs {
                break
            }
            markroot(gcw, job)
            if idle && pollWork() {
                goto done
            }
        }
    }
  	
    // 处理 heap 标记
    // Drain heap marking jobs.
    for !(preemptible && gp.preempt) {
        ...
        //从灰色列队中取出对象
        var b uintptr
        if blocking {
            b = gcw.get()
        } else {
            b = gcw.tryGetFast()
            if b == 0 {
                b = gcw.tryGet()
            }
        }
        if b == 0 {
            // work barrier reached or tryGet failed.
            break
        }
        //扫描灰色对象的引用对象，标记为灰色，入灰色队列
        scanobject(b, gcw)
    }
}

func gcMarkTermination() {
    // World is stopped.
    // Run gc on the g0 stack. We do this so that the g stack
    // we're currently running on will no longer change. Cuts
    // the root set down a bit (g0 stacks are not scanned, and
    // we don't need to scan gc's internal state).  We also
    // need to switch to g0 so we can shrink the stack.
    systemstack(func() {
        gcMark(startTime)
        // Must return immediately.
        // The outer function's stack may have moved
        // during gcMark (it shrinks stacks, including the
        // outer function's stack), so we must not refer
        // to any of its variables. Return back to the
        // non-system stack to pick up the new addresses
        // before continuing.
    })
    ...
}

func gcSweep(mode gcMode) {
    ...
    //阻塞式
    if !_ConcurrentSweep || mode == gcForceBlockMode {
        // Special case synchronous sweep.
        ...
        // Sweep all spans eagerly.
        for sweepone() != ^uintptr(0) {
            sweep.npausesweep++
        }
        // Do an additional mProf_GC, because all 'free' events are now real as well.
        mProf_GC()
        mProf_GC()
        return
    }
  	
    // 并行式
    // Background sweep.
    lock(&sweep.lock)
    if sweep.parked {
        sweep.parked = false
        ready(sweep.g, 0, true)
    }
    unlock(&sweep.lock)
}

func bgsweep(c chan int) {
    sweep.g = getg()

    lock(&sweep.lock)
    sweep.parked = true
    c <- 1
    goparkunlock(&sweep.lock, "GC sweep wait", traceEvGoBlock, 1)

    for {
        for gosweepone() != ^uintptr(0) {
            sweep.nbgsweep++
            Gosched()
        }
        lock(&sweep.lock)
        if !gosweepdone() {
            // This can happen if a GC runs between
            // gosweepone returning ^0 above
            // and the lock being acquired.
            unlock(&sweep.lock)
            continue
        }
        sweep.parked = true
        goparkunlock(&sweep.lock, "GC sweep wait", traceEvGoBlock, 1)
    }
}

func gosweepone() uintptr {
    var ret uintptr
    systemstack(func() {
        ret = sweepone()
    })
    return ret
}

// sweeps one span
// returns number of pages returned to heap, or ^uintptr(0) if there is nothing to sweep
func sweepone() uintptr {
    ...
    for {
        s := mheap_.sweepSpans[1-sg/2%2].pop()
        ...
        if !s.sweep(false) {
            // Span is still in-use, so this returned no
            // pages to the heap and the span needs to
            // move to the swept in-use list.
            npages = 0
        }
    }
}

// Sweep frees or collects finalizers for blocks not marked in the mark phase.
// It clears the mark bits in preparation for the next GC round.
// Returns true if the span was returned to heap.
// If preserve=true, don't return it to heap nor relink in MCentral lists;
// caller takes care of it.
func (s *mspan) sweep(preserve bool) bool {
    ...
}

type p struct {
    ...
    gcw gcWork
}

type gcWork struct {
    // wbuf1 and wbuf2 are the primary and secondary work buffers.
    wbuf1, wbuf2 wbufptr
  
    // Bytes marked (blackened) on this gcWork. This is aggregated
    // into work.bytesMarked by dispose.
    bytesMarked uint64

    // Scan work performed on this gcWork. This is aggregated into
    // gcController by dispose and may also be flushed by callers.
    scanWork int64
}

var work struct {
    full  uint64                   // lock-free list of full blocks workbuf
    empty uint64                   // lock-free list of empty blocks workbuf
    pad0  [sys.CacheLineSize]uint8 // prevents false-sharing between full/empty and nproc/nwait
    ...
}

func (w *gcWork) init() {
    w.wbuf1 = wbufptrOf(getempty())
    wbuf2 := trygetfull()
    if wbuf2 == nil {
        wbuf2 = getempty()
    }
    w.wbuf2 = wbufptrOf(wbuf2)
}

// put enqueues a pointer for the garbage collector to trace.
// obj must point to the beginning of a heap object or an oblet.
func (w *gcWork) put(obj uintptr) {
    wbuf := w.wbuf1.ptr()
    if wbuf == nil {
        w.init()
        wbuf = w.wbuf1.ptr()
        // wbuf is empty at this point.
    } else if wbuf.nobj == len(wbuf.obj) {
        w.wbuf1, w.wbuf2 = w.wbuf2, w.wbuf1
        wbuf = w.wbuf1.ptr()
        if wbuf.nobj == len(wbuf.obj) {
            putfull(wbuf)
            wbuf = getempty()
            w.wbuf1 = wbufptrOf(wbuf)
            flushed = true
        }
    }

    wbuf.obj[wbuf.nobj] = obj
    wbuf.nobj++
}

// get dequeues a pointer for the garbage collector to trace, blocking
// if necessary to ensure all pointers from all queues and caches have
// been retrieved.  get returns 0 if there are no pointers remaining.
//go:nowritebarrier
func (w *gcWork) get() uintptr {
    wbuf := w.wbuf1.ptr()
    if wbuf == nil {
        w.init()
        wbuf = w.wbuf1.ptr()
        // wbuf is empty at this point.
    }
    if wbuf.nobj == 0 {
        w.wbuf1, w.wbuf2 = w.wbuf2, w.wbuf1
        wbuf = w.wbuf1.ptr()
        if wbuf.nobj == 0 {
            owbuf := wbuf
            wbuf = getfull()
            if wbuf == nil {
                return 0
            }
            putempty(owbuf)
            w.wbuf1 = wbufptrOf(wbuf)
        }
    }

    // TODO: This might be a good place to add prefetch code

    wbuf.nobj--
    return wbuf.obj[wbuf.nobj]
}

// The main goroutine
func main() {
    ...
    systemstack(func() {
      	newm(sysmon, nil)
    })
}
// Always runs without a P, so write barriers are not allowed.
func sysmon() {
    ...
    for {
        now := nanotime()
        unixnow := unixnanotime()
      	
        lastgc := int64(atomic.Load64(&memstats.last_gc))
        if gcphase == _GCoff && lastgc != 0 && unixnow-lastgc > forcegcperiod && atomic.Load(&forcegc.idle) != 0 {
            lock(&forcegc.lock)
            forcegc.idle = 0
            forcegc.g.schedlink = 0
            injectglist(forcegc.g)	// 将 forcegc goroutine 加入 runnable queue
            unlock(&forcegc.lock)
        }
    }
}

var forcegcperiod int64 = 2 * 60 *1e9	//两分钟