Sync Pool 源码分析

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
package main

import "sync"

type People struct {
	Age int
}

func main() {
  // 创建一个对象并放入对象池
	pool := sync.Pool{
		New: func() interface{} {
			return &People{
				Age: 1,
			}
		},
	}

  // 从对象池获取对象
	p1 := pool.Get().(*People)
	println(p1.Age)

  // 对象放回对象池
	pool.Put(p1)
 
  // 从对象池获取刚刚放回的对象
	p2 := pool.Get().(*People)
	println(p2.Age)
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
// A Pool must not be copied after first use.
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

	victim     unsafe.Pointer // local from previous cycle
	victimSize uintptr        // size of victims 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{}
}

1
2
3
4
5
6
7
8
9
10
11
12
13
type poolLocal struct {
	poolLocalInternal

	// Prevents false sharing on widespread platforms with
	// 128 mod (cache line size) = 0 .
	pad [128 - unsafe.Sizeof(poolLocalInternal{})%128]byte
}

// Local per-P Pool appendix.
type poolLocalInternal struct {
	private interface{} // Can be used only by the respective P.
	shared  poolChain   // Local P can pushHead/popHead; any P can popTail.
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
// poolChain is a dynamically-sized version of poolDequeue.
//
// This is implemented as a doubly-linked list queue of poolDequeues
// where each dequeue is double the size of the previous one. Once a
// dequeue fills up, this allocates a new one and only ever pushes to
// the latest dequeue. Pops happen from the other end of the list and
// once a dequeue is exhausted, it gets removed from the list.
type poolChain struct {
	// head is the poolDequeue to push to. This is only accessed
	// by the producer, so doesn't need to be synchronized.
	head *poolChainElt

	// tail is the poolDequeue to popTail from. This is accessed
	// by consumers, so reads and writes must be atomic.
	tail *poolChainElt
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
type poolChainElt struct {
	poolDequeue

	// next and prev link to the adjacent poolChainElts in this
	// poolChain.
	//
	// next is written atomically by the producer and read
	// atomically by the consumer. It only transitions from nil to
	// non-nil.
	//
	// prev is written atomically by the consumer and read
	// atomically by the producer. It only transitions from
	// non-nil to nil.
	next, prev *poolChainElt
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
// poolDequeue is a lock-free fixed-size single-producer,
// multi-consumer queue. The single producer can both push and pop
// from the head, and consumers can pop from the tail.
//
// It has the added feature that it nils out unused slots to avoid
// unnecessary retention of objects. This is important for sync.Pool,
// but not typically a property considered in the literature.
type poolDequeue struct {
	// headTail packs together a 32-bit head index and a 32-bit
	// tail index. Both are indexes into vals modulo len(vals)-1.
	//
	// tail = index of oldest data in queue
	// head = index of next slot to fill
	//
	// Slots in the range [tail, head) are owned by consumers.
	// A consumer continues to own a slot outside this range until
	// it nils the slot, at which point ownership passes to the
	// producer.
	//
	// The head index is stored in the most-significant bits so
	// that we can atomically add to it and the overflow is
	// harmless.
	headTail uint64

	// vals is a ring buffer of interface{} values stored in this
	// dequeue. The size of this must be a power of 2.
	//
	// vals[i].typ is nil if the slot is empty and non-nil
	// otherwise. A slot is still in use until *both* the tail
	// index has moved beyond it and typ has been set to nil. This
	// is set to nil atomically by the consumer and read
	// atomically by the producer.
	vals []eface
}

1
2
3
4
5
func (d *poolDequeue) pack(head, tail uint32) uint64 {
	const mask = 1<<dequeueBits - 1
	return (uint64(head) << dequeueBits) |
		uint64(tail&mask)
}

1
2
3
4
5
6
func (d *poolDequeue) unpack(ptrs uint64) (head, tail uint32) {
	const mask = 1<<dequeueBits - 1
	head = uint32((ptrs >> dequeueBits) & mask)
	tail = uint32(ptrs & mask)
	return
}

1
atomic.CompareAndSwapUint64(&d.headTail, ptrs, ptrs2)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
// 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
	}
	if x != nil {
		l.shared.pushHead(x)
	}
	runtime_procUnpin()
	if race.Enabled {
		race.Enable()
	}
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
// pin pins the current goroutine to P, disables preemption and
// returns poolLocal pool for the P and the P's id.
// Caller must call runtime_procUnpin() when done with the pool.
func (p *Pool) pin() (*poolLocal, int) {
	pid := runtime_procPin()
	// In pinSlow we store to local and then to localSize, 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 := runtime_LoadAcquintptr(&p.localSize) // load-acquire
	l := p.local                              // load-consume
	if uintptr(pid) < s {
		return indexLocal(l, pid), pid
	}
	return p.pinSlow()
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
// Get selects an arbitrary item from the Pool, removes it from the
// Pool, and returns it to the caller.
// Get may choose to ignore the pool and treat it as empty.
// Callers should not assume any relation between values passed to Put and
// the values returned by Get.
//
// If Get would otherwise return nil and p.New is non-nil, Get returns
// the result of calling p.New.
func (p *Pool) Get() interface{} {
	if race.Enabled {
		race.Disable()
	}
	l, pid := p.pin()
	x := l.private
	l.private = nil
	if x == nil {
		// Try to pop the head of the local shard. We prefer
		// the head over the tail for temporal locality of
		// reuse.
		x, _ = l.shared.popHead()
		if x == nil {
			x = p.getSlow(pid)
		}
	}
	runtime_procUnpin()
	if race.Enabled {
		race.Enable()
		if x != nil {
			race.Acquire(poolRaceAddr(x))
		}
	}
	if x == nil && p.New != nil {
		x = p.New()
	}
	return x
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
func (p *Pool) getSlow(pid int) interface{} {
	// See the comment in pin regarding ordering of the loads.
	size := runtime_LoadAcquintptr(&p.localSize) // load-acquire
	locals := p.local                            // load-consume
	// Try to steal one element from other procs.
	for i := 0; i < int(size); i++ {
		l := indexLocal(locals, (pid+i+1)%int(size))
		if x, _ := l.shared.popTail(); x != nil {
			return x
		}
	}

	// Try the victim cache. We do this after attempting to steal
	// from all primary caches because we want objects in the
	// victim cache to age out if at all possible.
	size = atomic.LoadUintptr(&p.victimSize)
	if uintptr(pid) >= size {
		return nil
	}
	locals = p.victim
	l := indexLocal(locals, pid)
	if x := l.private; x != nil {
		l.private = nil
		return x
	}
	for i := 0; i < int(size); i++ {
		l := indexLocal(locals, (pid+i)%int(size))
		if x, _ := l.shared.popTail(); x != nil {
			return x
		}
	}

	// Mark the victim cache as empty for future gets don't bother
	// with it.
	atomic.StoreUintptr(&p.victimSize, 0)

	return nil
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
func init() {
	runtime_registerPoolCleanup(poolCleanup)
}

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.

	// Because the world is stopped, no pool user can be in a
	// pinned section (in effect, this has all Ps pinned).

	// Drop victim caches from all pools.
	for _, p := range oldPools {
		p.victim = nil
		p.victimSize = 0
	}

	// Move primary cache to victim cache.
	for _, p := range allPools {
		p.victim = p.local
		p.victimSize = p.localSize
		p.local = nil
		p.localSize = 0
	}

	// The pools with non-empty primary caches now have non-empty
	// victim caches and no pools have primary caches.
	oldPools, allPools = allPools, nil
}