php入门到就业线上直播课:进入学习
API 文档、设计、调试、自动化测试一体化协作工具:点击使用
sync.Map
但实际应用场景中,key和value是(包含)指针类型数据是很常见的,因此使用缓存框架需要特别注意其对gc影响,从是否对GC影响角度来看缓存框架大致分为2类:
- 零GC开销:比如freecache或bigcache这种,底层基于ringbuf,减小指针个数;
- 有GC开销:直接基于Map来实现的缓存框架。
对于map而言,gc时会扫描所有key/value键值对,如果其都是基本类型,那么gc便不会再扫描。
下面以freecache为例分析下其实现原理,代码示例如下:
func main() { cacheSize := 100 * 1024 * 1024 cache := freecache.NewCache(cacheSize) for i := 0; i < N; i++ { str := strconv.Itoa(i) _ = cache.Set([]byte(str), []byte(str), 1) } now := time.Now() runtime.GC() fmt.Printf("freecache, GC took: %s\n", time.Since(now)) _, _ = cache.Get([]byte("aa")) now = time.Now() for i := 0; i < N; i++ { str := strconv.Itoa(i) _, _ = cache.Get([]byte(str)) } fmt.Printf("freecache, Get took: %s\n\n", time.Since(now)) }
1 初始化
注意切片为指针类型
type segment struct { rb RingBuf // ring buffer that stores data segId int _ uint32 // 占位 missCount int64 hitCount int64 entryCount int64 totalCount int64 // number of entries in ring buffer, including deleted entries. totalTime int64 // used to calculate least recent used entry. timer Timer // Timer giving current time totalEvacuate int64 // used for debug totalExpired int64 // used for debug overwrites int64 // used for debug touched int64 // used for debug vacuumLen int64 // up to vacuumLen, new data can be written without overwriting old data. slotLens [256]int32 // The actual length for every slot. slotCap int32 // max number of entry pointers a slot can hold. slotsData []entryPtr // 索引指针 } func NewCacheCustomTimer(size int, timer Timer) (cache *Cache) { cache = new(Cache) for i := 0; i < segmentCount; i++ { cache.segments[i] = newSegment(size/segmentCount, i, timer) } } func newSegment(bufSize int, segId int, timer Timer) (seg segment) { seg.rb = NewRingBuf(bufSize, 0) seg.segId = segId seg.timer = timer seg.vacuumLen = int64(bufSize) seg.slotCap = 1 seg.slotsData = make([]entryPtr, 256*seg.slotCap) // 每个slotData初始化256个单位大小 }
2 读写流程
[]byteSet
_ = cache.Set([]byte(str), []byte(str), 1)
[]entryPtr[]entryPtr
每个segment对应一个lock(sync.Mutex),因此其能够支持较大并发量,而不像sync.Map只有一个锁。
func (cache *Cache) Set(key, value []byte, expireSeconds int) (err error) { hashVal := hashFunc(key) segID := hashVal & segmentAndOpVal // 低8位 cache.locks[segID].Lock() // 加锁 err = cache.segments[segID].set(key, value, hashVal, expireSeconds) cache.locks[segID].Unlock() } func (seg *segment) set(key, value []byte, hashVal uint64, expireSeconds int) (err error) { slotId := uint8(hashVal >> 8) hash16 := uint16(hashVal >> 16) slot := seg.getSlot(slotId) idx, match := seg.lookup(slot, hash16, key) var hdrBuf [ENTRY_HDR_SIZE]byte hdr := (*entryHdr)(unsafe.Pointer(&hdrBuf[0])) if match { // 有数据更新操作 matchedPtr := &slot[idx] seg.rb.ReadAt(hdrBuf[:], matchedPtr.offset) hdr.slotId = slotId hdr.hash16 = hash16 hdr.keyLen = uint16(len(key)) originAccessTime := hdr.accessTime hdr.accessTime = now hdr.expireAt = expireAt hdr.valLen = uint32(len(value)) if hdr.valCap >= hdr.valLen { // 已存在数据value空间能存下此次value大小 atomic.AddInt64(&seg.totalTime, int64(hdr.accessTime)-int64(originAccessTime)) seg.rb.WriteAt(hdrBuf[:], matchedPtr.offset) seg.rb.WriteAt(value, matchedPtr.offset+ENTRY_HDR_SIZE+int64(hdr.keyLen)) atomic.AddInt64(&seg.overwrites, 1) return } // 删除对应entryPtr,涉及到slotsData内存copy,ringbug中只是标记删除 seg.delEntryPtr(slotId, slot, idx) match = false // increase capacity and limit entry len. for hdr.valCap < hdr.valLen { hdr.valCap *= 2 } if hdr.valCap > uint32(maxKeyValLen-len(key)) { hdr.valCap = uint32(maxKeyValLen - len(key)) } } else { // 无数据 hdr.slotId = slotId hdr.hash16 = hash16 hdr.keyLen = uint16(len(key)) hdr.accessTime = now hdr.expireAt = expireAt hdr.valLen = uint32(len(value)) hdr.valCap = uint32(len(value)) if hdr.valCap == 0 { // avoid infinite loop when increasing capacity. hdr.valCap = 1 } } // 数据实际长度为 ENTRY_HDR_SIZE=24 + key和value的长度 entryLen := ENTRY_HDR_SIZE + int64(len(key)) + int64(hdr.valCap) slotModified := seg.evacuate(entryLen, slotId, now) if slotModified { // the slot has been modified during evacuation, we need to looked up for the 'idx' again. // otherwise there would be index out of bound error. slot = seg.getSlot(slotId) idx, match = seg.lookup(slot, hash16, key) // assert(match == false) } newOff := seg.rb.End() seg.insertEntryPtr(slotId, hash16, newOff, idx, hdr.keyLen) seg.rb.Write(hdrBuf[:]) seg.rb.Write(key) seg.rb.Write(value) seg.rb.Skip(int64(hdr.valCap - hdr.valLen)) atomic.AddInt64(&seg.totalTime, int64(now)) atomic.AddInt64(&seg.totalCount, 1) seg.vacuumLen -= entryLen return }
oldOff := seg.rb.End() + seg.vacuumLen - seg.rb.Size()
[]entryPtrseg.expand
写入ringbuf就是执行rb.Write即可。
func (seg *segment) evacuate(entryLen int64, slotId uint8, now uint32) (slotModified bool) { var oldHdrBuf [ENTRY_HDR_SIZE]byte consecutiveEvacuate := 0 for seg.vacuumLen < entryLen { oldOff := seg.rb.End() + seg.vacuumLen - seg.rb.Size() seg.rb.ReadAt(oldHdrBuf[:], oldOff) oldHdr := (*entryHdr)(unsafe.Pointer(&oldHdrBuf[0])) oldEntryLen := ENTRY_HDR_SIZE + int64(oldHdr.keyLen) + int64(oldHdr.valCap) if oldHdr.deleted { // 已删除 consecutiveEvacuate = 0 atomic.AddInt64(&seg.totalTime, -int64(oldHdr.accessTime)) atomic.AddInt64(&seg.totalCount, -1) seg.vacuumLen += oldEntryLen continue } expired := oldHdr.expireAt != 0 && oldHdr.expireAt < now leastRecentUsed := int64(oldHdr.accessTime)*atomic.LoadInt64(&seg.totalCount) <= atomic.LoadInt64(&seg.totalTime) if expired || leastRecentUsed || consecutiveEvacuate > 5 { // 可以回收 seg.delEntryPtrByOffset(oldHdr.slotId, oldHdr.hash16, oldOff) if oldHdr.slotId == slotId { slotModified = true } consecutiveEvacuate = 0 atomic.AddInt64(&seg.totalTime, -int64(oldHdr.accessTime)) atomic.AddInt64(&seg.totalCount, -1) seg.vacuumLen += oldEntryLen if expired { atomic.AddInt64(&seg.totalExpired, 1) } else { atomic.AddInt64(&seg.totalEvacuate, 1) } } else { // evacuate an old entry that has been accessed recently for better cache hit rate. newOff := seg.rb.Evacuate(oldOff, int(oldEntryLen)) seg.updateEntryPtr(oldHdr.slotId, oldHdr.hash16, oldOff, newOff) consecutiveEvacuate++ atomic.AddInt64(&seg.totalEvacuate, 1) } } }
freecache的Get流程相对来说简单点,通过hash找到对应segment,通过slotId找到对应索引slot,然后通过二分+遍历寻找数据,如果找不到直接返回ErrNotFound,否则更新一些time指标。Get流程还会更新缓存命中率相关指标。
func (cache *Cache) Get(key []byte) (value []byte, err error) { hashVal := hashFunc(key) segID := hashVal & segmentAndOpVal cache.locks[segID].Lock() value, _, err = cache.segments[segID].get(key, nil, hashVal, false) cache.locks[segID].Unlock() return } func (seg *segment) get(key, buf []byte, hashVal uint64, peek bool) (value []byte, expireAt uint32, err error) { hdr, ptr, err := seg.locate(key, hashVal, peek) // hash+定位查找 if err != nil { return } expireAt = hdr.expireAt if cap(buf) >= int(hdr.valLen) { value = buf[:hdr.valLen] } else { value = make([]byte, hdr.valLen) } seg.rb.ReadAt(value, ptr.offset+ENTRY_HDR_SIZE+int64(hdr.keyLen)) }
[]byte
3 总结
从常见的几个缓存框架压测性能来看,Set性能差异较大但还不是数量级别的差距,Get性能差异不大,因此对于绝大多数场景来说不用太关注Set/Get性能,重点应该看功能是否满足业务需求和gc影响,性能压测比较见:https://golang2.eddycjy.com/posts/ch5/04-performance/
缓存有一个特殊的场景,那就是将数据全部缓存在内存,涉及到更新时都是全量更新(替换),该场景下使用freecache,如果size未设置好可能导致部分数据被淘汰,是不符合预期的,这个一定要注意。为了使用freecache避免该问题,需要将size设置"足够大",但也要注意其内存空间占用。
更多编程相关知识,请访问:编程教学!!