Golang sync.Pool的源码解析

package pool
import (
	"io/ioutil"
	"sync"
	"testing"
)
type Data [1024]byte
// 直接创建对象
func BenchmarkWithoutPool(t *testing.B) {
	for i := 0; i < t.N; i++ {
		var data Data
		ioutil.Discard.Write(data[:])
	}
}
// 使用Pool复用对象
func BenchmarkWithPool(t *testing.B) {
	pool := &sync.Pool{
		// 若没有可用对象，则调用New创建一个对象
		New: func() interface{} {
			return &Data{}
		},
	}
	for i := 0; i < t.N; i++ {
		// 取
		data := pool.Get().(*Data)
		// 用
		ioutil.Discard.Write(data[:])
		// 存
		pool.Put(data)
	}
}
// 并发的直接创建对象
func BenchmarkWithoutPoolConncurrency(t *testing.B) {
	t.RunParallel(func(pb *testing.PB) {
		for pb.Next() {
			var data Data
			ioutil.Discard.Write(data[:])
		}
	})
}
// 使用Pool并发的复用对象
func BenchmarkWithPoolConncurrency(t *testing.B) {
	pool := &sync.Pool{
		// 若没有可用对象，则调用New创建一个对象
		New: func() interface{} {
			return &Data{}
		},
	}
	t.RunParallel(func(pb *testing.PB) {
		for pb.Next() {
			// 取
			data := pool.Get().(*Data)
			// 用
			ioutil.Discard.Write(data[:])
			// 存
			pool.Put(data)
		}
	})
}

goos: darwin
goarch: amd64
pkg: leetcode/pool
cpu: Intel(R) Core(TM) i5-1038NG7 CPU @ 2.00GHz
BenchmarkWithoutPool-8                   7346660               148.1 ns/op          1024 B/op          1 allocs/op
BenchmarkWithPool-8                     80391398                14.41 ns/op            0 B/op          0 allocs/op
BenchmarkWithoutPoolConncurrency-8       7893248               153.3 ns/op          1024 B/op          1 allocs/op
BenchmarkWithPoolConncurrency-8         363329767                4.245 ns/op           0 B/op          0 allocs/op
PASS
ok      leetcode/pool   6.590s

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() any
}

// Local per-P Pool appendix.
type poolLocalInternal struct {
	private any       // Can be used only by the respective P.
	shared  poolChain // Local P can pushHead/popHead; any P can popTail.
}
type poolLocal struct {
	poolLocalInternal
	// Prevents false sharing on widespread platforms with
	// 128 mod (cache line size) = 0 .
	pad [128 - unsafe.Sizeof(poolLocalInternal{})%128]byte
}

import (
	"sync/atomic"
	"testing"
	"unsafe"
)
type StudentWithCacheLine struct {
	Age uint32
	_   [128 - unsafe.Sizeof(uint32(0))%128]byte
}
// 有填充的场景下，并发修改Age
func BenchmarkWithCacheLine(b *testing.B) {
	count := 10
	students := make([]StudentWithCacheLine, count)
	b.RunParallel(func(pb *testing.PB) {
		for pb.Next() {
			for j := 0; j < count; j++ {
				atomic.AddUint32(&students[j].Age, 1)
			}
		}
	})
}
type StudentWithoutCacheLine struct {
	Age uint32
}
// 无填充的场景下，并发修改Age
func BenchmarkWithoutCacheLine(b *testing.B) {
	count := 10
	students := make([]StudentWithoutCacheLine, count)
	b.RunParallel(func(pb *testing.PB) {
		for pb.Next() {
			for j := 0; j < count; j++ {
				atomic.AddUint32(&students[j].Age, 1)
			}
		}
	})
}

goos: darwin
goarch: amd64
pkg: leetcode/pool
cpu: Intel(R) Core(TM) i5-1038NG7 CPU @ 2.00GHz
BenchmarkWithCacheLine-8        17277380                70.18 ns/op            0 B/op          0 allocs/op
BenchmarkWithoutCacheLine-8      8916874               133.8 ns/op             0 B/op          0 allocs/op

// 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() any {
	if race.Enabled {
		race.Disable()
	}
	// 1. 找到当前goroutine所在的P对应的poolLocalInternal和P对应的id
	l, pid := p.pin()
	x := l.private
	l.private = nil
  // 2. 如果private是空，在从shared进行popHead
	if x == nil {
		// Try to pop the head of the local shard. We prefer
		// the head over the tail for temporal locality of
		// reuse.
		// 3. 尝试从shared上取值
		x, _ = l.shared.popHead()
		// 4. 如果还如空，则尝试从其他P的poolLocalInternal或者victim中获取
		if x == nil {
			x = p.getSlow(pid)
		}
	}
	runtime_procUnpin()
	if race.Enabled {
		race.Enable()
		if x != nil {
			race.Acquire(poolRaceAddr(x))
		}
	}
	// 5. 如果还如空，则直接使用New初始化一个
	if x == nil && p.New != nil {
		x = p.New()
	}
	return x
}

// 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
}
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
}