sync.Pool实现原理

    type Pool struct {
        noCopy noCopy

        local     unsafe.Pointer // local fixed-size per-P pool, actual type is [P]poolLocal
        localSize uintptr        // size of the local array

        // New optionally specifies a function to generate
        // a value when Get would otherwise return nil.
        // It may not be changed concurrently with calls to Get.
        New func() interface{}
    }

    type poolLocalInternal struct {
        private interface{}   // Can be used only by the respective P.
        shared  []interface{} // Can be used by any P.
        Mutex                 // Protects shared.
    }

    // Put adds x to the pool.
    func (p *Pool) Put(x interface{}) {
        if x == nil {
            return
        }
        if race.Enabled {
            if fastrand()%4 == 0 {
                // Randomly drop x on floor.
                return
            }
            race.ReleaseMerge(poolRaceAddr(x))
            race.Disable()
        }
        l := p.pin()
        if l.private == nil {
            l.private = x
            x = nil
        }
        runtime_procUnpin()
        if x != nil {
            l.Lock()
            l.shared = append(l.shared, x)
            l.Unlock()
        }
        if race.Enabled {
            race.Enable()
        }
    }

func (p *Pool) pin() *poolLocal {
	pid := runtime_procPin()
	// In pinSlow we store to localSize and then to local, here we load in opposite order.
	// Since we've disabled preemption, GC cannot happen in between.
	// Thus here we must observe local at least as large localSize.
	// We can observe a newer/larger local, it is fine (we must observe its zero-initialized-ness).
	s := atomic.LoadUintptr(&p.localSize) // load-acquire
	l := p.local                          // load-consume
	if uintptr(pid) < s {                 // 这句话的意思是如果当前pool的localPool切片尚未创建，尚未创建这句话肯定是false的
		return indexLocal(l, pid)
	}
	return p.pinSlow()
}

func (p *Pool) pinSlow() *poolLocal {
	// Retry under the mutex.
	// Can not lock the mutex while pinned.
	runtime_procUnpin()
	allPoolsMu.Lock()
	defer allPoolsMu.Unlock()
	pid := runtime_procPin()
	// poolCleanup won't be called while we are pinned.
	s := p.localSize
	l := p.local
	if uintptr(pid) < s {
		return indexLocal(l, pid)
	}
	if p.local == nil {
		allPools = append(allPools, p)
	}
	// If GOMAXPROCS changes between GCs, we re-allocate the array and lose the old one.
	size := runtime.GOMAXPROCS(0)
	local := make([]poolLocal, size)
	atomic.StorePointer(&p.local, unsafe.Pointer(&local[0])) // store-release
	atomic.StoreUintptr(&p.localSize, uintptr(size))         // store-release
	return &local[pid]
}

    func (p *Pool) Get() interface{} {
        if race.Enabled {
            race.Disable()
        }
        l := p.pin()
        x := l.private
        l.private = nil
        runtime_procUnpin()
        if x == nil {
            l.Lock()
            last := len(l.shared) - 1
            if last >= 0 {
                x = l.shared[last]
                l.shared = l.shared[:last]
            }
            l.Unlock()
            if x == nil {
                x = p.getSlow()
            }
        }
        if race.Enabled {
            race.Enable()
            if x != nil {
                race.Acquire(poolRaceAddr(x))
            }
        }
        if x == nil && p.New != nil {
            x = p.New()
        }
        return x
    }

    func (p *Pool) getSlow() (x interface{}) {
        // See the comment in pin regarding ordering of the loads.
        size := atomic.LoadUintptr(&p.localSize) // load-acquire
        local := p.local                         // load-consume
        // Try to steal one element from other procs.
        pid := runtime_procPin()
        runtime_procUnpin()
        for i := 0; i < int(size); i++ {
            l := indexLocal(local, (pid+i+1)%int(size))
            l.Lock()
            last := len(l.shared) - 1
            if last >= 0 {
                x = l.shared[last]
                l.shared = l.shared[:last]
                l.Unlock()
                break
            }
            l.Unlock()
        }
        return x
    }

func poolCleanup() {
	// This function is called with the world stopped, at the beginning of a garbage collection.
	// It must not allocate and probably should not call any runtime functions.
	// Defensively zero out everything, 2 reasons:
	// 1. To prevent false retention of whole Pools.
	// 2. If GC happens while a goroutine works with l.shared in Put/Get,
	//    it will retain whole Pool. So next cycle memory consumption would be doubled.
	for i, p := range allPools {
		allPools[i] = nil
		for i := 0; i < int(p.localSize); i++ {
			l := indexLocal(p.local, i)
			l.private = nil
			for j := range l.shared {
				l.shared[j] = nil
			}
			l.shared = nil
		}
		p.local = nil
		p.localSize = 0
	}
	allPools = []*Pool{}
}