commit 89351183c3cb08382f5618196054f5d545d66420 Author: drygrass Date: Tue Nov 18 23:41:04 2025 +0800 first comit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..1d02fad --- /dev/null +++ b/.gitignore @@ -0,0 +1,28 @@ +# CMake 生成目录 +build/ +CMakeFiles/ +CMakeCache.txt +.cache/ +.vscode/ +.test + +# CMake 生成的可执行文件和库 +*.exe +*.out +*.a +*.so +*.dylib +*.lib +*.dll + +# CMake 临时文件 +*.cmake +Makefile +CMakeScripts/ + +# 其他常见生成文件 +*.ninja +.ninja_deps +.ninja_log +compile_commands.json +install_manifest.txt \ No newline at end of file diff --git a/CMakeLists.txt b/CMakeLists.txt new file mode 100644 index 0000000..2695ab2 --- /dev/null +++ b/CMakeLists.txt @@ -0,0 +1,21 @@ +# 设置最低 CMake 版本要求 +cmake_minimum_required(VERSION 3.10) + +# 设置项目名称 +project(KCacheSystem) + +# 设置 C++ 标准 +set(CMAKE_CXX_STANDARD 17) +set(CMAKE_CXX_STANDARD_REQUIRED True) + +# 指定源文件目录下的所有 .cpp 文件 +file(GLOB SOURCES "*.cpp") + +# 设置目标可执行文件 +add_executable(main ${SOURCES}) + +# 清理中间的 .o 文件 +set_target_properties(main PROPERTIES CLEAN_DIRECT_OUTPUT 1) + +# 额外的编译选项（可根据需要启用） +# target_compile_options(main PRIVATE -Wall -Wextra -O2) \ No newline at end of file diff --git a/KArcCache/KArcCache.h b/KArcCache/KArcCache.h new file mode 100644 index 0000000..c239640 --- /dev/null +++ b/KArcCache/KArcCache.h @@ -0,0 +1,92 @@ +#pragma once + +#include "../KICachePolicy.h" +#include "KArcLruPart.h" +#include "KArcLfuPart.h" +#include + +namespace KamaCache +{ + +template +class KArcCache : public KICachePolicy +{ +public: + explicit KArcCache(size_t capacity = 10, size_t transformThreshold = 2) + : capacity_(capacity) + , transformThreshold_(transformThreshold) + , lruPart_(std::make_unique>(capacity, transformThreshold)) + , lfuPart_(std::make_unique>(capacity, transformThreshold)) + {} + + ~KArcCache() override = default; + + void put(Key key, Value value) override + { + checkGhostCaches(key); + + // 检查 LFU 部分是否存在该键 + bool inLfu = lfuPart_->contain(key); + // 更新 LRU 部分缓存 + lruPart_->put(key, value); + // 如果 LFU 部分存在该键，则更新 LFU 部分 + if (inLfu) + { + lfuPart_->put(key, value); + } + } + + bool get(Key key, Value& value) override + { + checkGhostCaches(key); + + bool shouldTransform = false; + if (lruPart_->get(key, value, shouldTransform)) + { + if (shouldTransform) + { + lfuPart_->put(key, value); + } + return true; + } + return lfuPart_->get(key, value); + } + + Value get(Key key) override + { + Value value{}; + get(key, value); + return value; + } + +private: + bool checkGhostCaches(Key key) + { + bool inGhost = false; + if (lruPart_->checkGhost(key)) + { + if (lfuPart_->decreaseCapacity()) + { + lruPart_->increaseCapacity(); + } + inGhost = true; + } + else if (lfuPart_->checkGhost(key)) + { + if (lruPart_->decreaseCapacity()) + { + lfuPart_->increaseCapacity(); + } + inGhost = true; + } + return inGhost; + } + +private: + size_t capacity_; + size_t transformThreshold_; + std::unique_ptr> lruPart_; + std::unique_ptr> lfuPart_; +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/KArcCache/KArcCacheNode.h b/KArcCache/KArcCacheNode.h new file mode 100644 index 0000000..f19a1e1 --- /dev/null +++ b/KArcCache/KArcCacheNode.h @@ -0,0 +1,41 @@ +#pragma once + +#include + +namespace KamaCache +{ + +template +class ArcNode +{ +private: + Key key_; + Value value_; + size_t accessCount_; + std::weak_ptr prev_; + std::shared_ptr next_; + +public: + ArcNode() : accessCount_(1), next_(nullptr) {} + + ArcNode(Key key, Value value) + : key_(key) + , value_(value) + , accessCount_(1) + , next_(nullptr) + {} + + // Getters + Key getKey() const { return key_; } + Value getValue() const { return value_; } + size_t getAccessCount() const { return accessCount_; } + + // Setters + void setValue(const Value& value) { value_ = value; } + void incrementAccessCount() { ++accessCount_; } + + template friend class ArcLruPart; + template friend class ArcLfuPart; +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/KArcCache/KArcLfuPart.h b/KArcCache/KArcLfuPart.h new file mode 100644 index 0000000..5387c13 --- /dev/null +++ b/KArcCache/KArcLfuPart.h @@ -0,0 +1,231 @@ +#pragma once + +#include "KArcCacheNode.h" +#include +#include +#include + +namespace KamaCache +{ + +template +class ArcLfuPart +{ +public: + using NodeType = ArcNode; + using NodePtr = std::shared_ptr; + using NodeMap = std::unordered_map; + using FreqMap = std::map>; + + explicit ArcLfuPart(size_t capacity, size_t transformThreshold) + : capacity_(capacity) + , ghostCapacity_(capacity) + , transformThreshold_(transformThreshold) + , minFreq_(0) + { + initializeLists(); + } + + bool put(Key key, Value value) + { + if (capacity_ == 0) + return false; + + std::lock_guard lock(mutex_); + auto it = mainCache_.find(key); + if (it != mainCache_.end()) + { + return updateExistingNode(it->second, value); + } + return addNewNode(key, value); + } + + bool get(Key key, Value& value) + { + std::lock_guard lock(mutex_); + auto it = mainCache_.find(key); + if (it != mainCache_.end()) + { + updateNodeFrequency(it->second); + value = it->second->getValue(); + return true; + } + return false; + } + + bool contain(Key key) + { + return mainCache_.find(key) != mainCache_.end(); + } + + bool checkGhost(Key key) + { + auto it = ghostCache_.find(key); + if (it != ghostCache_.end()) + { + removeFromGhost(it->second); + ghostCache_.erase(it); + return true; + } + return false; + } + + void increaseCapacity() { ++capacity_; } + + bool decreaseCapacity() + { + if (capacity_ <= 0) return false; + if (mainCache_.size() == capacity_) + { + evictLeastFrequent(); + } + --capacity_; + return true; + } + +private: + void initializeLists() + { + ghostHead_ = std::make_shared(); + ghostTail_ = std::make_shared(); + ghostHead_->next_ = ghostTail_; + ghostTail_->prev_ = ghostHead_; + } + + bool updateExistingNode(NodePtr node, const Value& value) + { + node->setValue(value); + updateNodeFrequency(node); + return true; + } + + bool addNewNode(const Key& key, const Value& value) + { + if (mainCache_.size() >= capacity_) + { + evictLeastFrequent(); + } + + NodePtr newNode = std::make_shared(key, value); + mainCache_[key] = newNode; + + // 将新节点添加到频率为1的列表中 + if (freqMap_.find(1) == freqMap_.end()) + { + freqMap_[1] = std::list(); + } + freqMap_[1].push_back(newNode); + minFreq_ = 1; + + return true; + } + + void updateNodeFrequency(NodePtr node) + { + size_t oldFreq = node->getAccessCount(); + node->incrementAccessCount(); + size_t newFreq = node->getAccessCount(); + + // 从旧频率列表中移除 + auto& oldList = freqMap_[oldFreq]; + oldList.remove(node); + if (oldList.empty()) + { + freqMap_.erase(oldFreq); + if (oldFreq == minFreq_) + { + minFreq_ = newFreq; + } + } + + // 添加到新频率列表 + if (freqMap_.find(newFreq) == freqMap_.end()) + { + freqMap_[newFreq] = std::list(); + } + freqMap_[newFreq].push_back(node); + } + + void evictLeastFrequent() + { + if (freqMap_.empty()) + return; + + // 获取最小频率的列表 + auto& minFreqList = freqMap_[minFreq_]; + if (minFreqList.empty()) + return; + + // 移除最少使用的节点 + NodePtr leastNode = minFreqList.front(); + minFreqList.pop_front(); + + // 如果该频率的列表为空，则删除该频率项 + if (minFreqList.empty()) + { + freqMap_.erase(minFreq_); + // 更新最小频率 + if (!freqMap_.empty()) + { + minFreq_ = freqMap_.begin()->first; + } + } + + // 将节点移到幽灵缓存 + if (ghostCache_.size() >= ghostCapacity_) + { + removeOldestGhost(); + } + addToGhost(leastNode); + + // 从主缓存中移除 + mainCache_.erase(leastNode->getKey()); + } + + void removeFromGhost(NodePtr node) + { + if (!node->prev_.expired() && node->next_) { + auto prev = node->prev_.lock(); + prev->next_ = node->next_; + node->next_->prev_ = node->prev_; + node->next_ = nullptr; // 清空指针，防止悬垂引用 + } + } + + void addToGhost(NodePtr node) + { + node->next_ = ghostTail_; + node->prev_ = ghostTail_->prev_; + if (!ghostTail_->prev_.expired()) { + ghostTail_->prev_.lock()->next_ = node; + } + ghostTail_->prev_ = node; + ghostCache_[node->getKey()] = node; + } + + void removeOldestGhost() + { + NodePtr oldestGhost = ghostHead_->next_; + if (oldestGhost != ghostTail_) + { + removeFromGhost(oldestGhost); + ghostCache_.erase(oldestGhost->getKey()); + } + } + +private: + size_t capacity_; + size_t ghostCapacity_; + size_t transformThreshold_; + size_t minFreq_; + std::mutex mutex_; + + NodeMap mainCache_; + NodeMap ghostCache_; + FreqMap freqMap_; + + NodePtr ghostHead_; + NodePtr ghostTail_; +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/KArcCache/KArcLruPart.h b/KArcCache/KArcLruPart.h new file mode 100644 index 0000000..65396e1 --- /dev/null +++ b/KArcCache/KArcLruPart.h @@ -0,0 +1,222 @@ +#pragma once + +#include "KArcCacheNode.h" +#include +#include + +namespace KamaCache +{ + +template +class ArcLruPart +{ +public: + using NodeType = ArcNode; + using NodePtr = std::shared_ptr; + using NodeMap = std::unordered_map; + + explicit ArcLruPart(size_t capacity, size_t transformThreshold) + : capacity_(capacity) + , ghostCapacity_(capacity) + , transformThreshold_(transformThreshold) + { + initializeLists(); + } + + bool put(Key key, Value value) + { + if (capacity_ == 0) return false; + + std::lock_guard lock(mutex_); + auto it = mainCache_.find(key); + if (it != mainCache_.end()) + { + return updateExistingNode(it->second, value); + } + return addNewNode(key, value); + } + + bool get(Key key, Value& value, bool& shouldTransform) + { + std::lock_guard lock(mutex_); + auto it = mainCache_.find(key); + if (it != mainCache_.end()) + { + shouldTransform = updateNodeAccess(it->second); + value = it->second->getValue(); + return true; + } + return false; + } + + bool checkGhost(Key key) + { + auto it = ghostCache_.find(key); + if (it != ghostCache_.end()) { + removeFromGhost(it->second); + ghostCache_.erase(it); + return true; + } + return false; + } + + void increaseCapacity() { ++capacity_; } + + bool decreaseCapacity() + { + if (capacity_ <= 0) return false; + if (mainCache_.size() == capacity_) { + evictLeastRecent(); + } + --capacity_; + return true; + } + +private: + void initializeLists() + { + mainHead_ = std::make_shared(); + mainTail_ = std::make_shared(); + mainHead_->next_ = mainTail_; + mainTail_->prev_ = mainHead_; + + ghostHead_ = std::make_shared(); + ghostTail_ = std::make_shared(); + ghostHead_->next_ = ghostTail_; + ghostTail_->prev_ = ghostHead_; + } + + bool updateExistingNode(NodePtr node, const Value& value) + { + node->setValue(value); + moveToFront(node); + return true; + } + + bool addNewNode(const Key& key, const Value& value) + { + if (mainCache_.size() >= capacity_) + { + evictLeastRecent(); // 驱逐最近最少访问 + } + + NodePtr newNode = std::make_shared(key, value); + mainCache_[key] = newNode; + addToFront(newNode); + return true; + } + + bool updateNodeAccess(NodePtr node) + { + moveToFront(node); + node->incrementAccessCount(); + return node->getAccessCount() >= transformThreshold_; + } + + void moveToFront(NodePtr node) + { + // 先从当前位置移除 + if (!node->prev_.expired() && node->next_) { + auto prev = node->prev_.lock(); + prev->next_ = node->next_; + node->next_->prev_ = node->prev_; + node->next_ = nullptr; // 清空指针，防止悬垂引用 + } + + // 添加到头部 + addToFront(node); + } + + void addToFront(NodePtr node) + { + node->next_ = mainHead_->next_; + node->prev_ = mainHead_; + mainHead_->next_->prev_ = node; + mainHead_->next_ = node; + } + + void evictLeastRecent() + { + NodePtr leastRecent = mainTail_->prev_.lock(); + if (!leastRecent || leastRecent == mainHead_) + return; + + // 从主链表中移除 + removeFromMain(leastRecent); + + // 添加到幽灵缓存 + if (ghostCache_.size() >= ghostCapacity_) + { + removeOldestGhost(); + } + addToGhost(leastRecent); + + // 从主缓存映射中移除 + mainCache_.erase(leastRecent->getKey()); + } + + void removeFromMain(NodePtr node) + { + if (!node->prev_.expired() && node->next_) { + auto prev = node->prev_.lock(); + prev->next_ = node->next_; + node->next_->prev_ = node->prev_; + node->next_ = nullptr; // 清空指针，防止悬垂引用 + } + } + + void removeFromGhost(NodePtr node) + { + if (!node->prev_.expired() && node->next_) { + auto prev = node->prev_.lock(); + prev->next_ = node->next_; + node->next_->prev_ = node->prev_; + node->next_ = nullptr; // 清空指针，防止悬垂引用 + } + } + + void addToGhost(NodePtr node) + { + // 重置节点的访问计数 + node->accessCount_ = 1; + + // 添加到幽灵缓存的头部 + node->next_ = ghostHead_->next_; + node->prev_ = ghostHead_; + ghostHead_->next_->prev_ = node; + ghostHead_->next_ = node; + + // 添加到幽灵缓存映射 + ghostCache_[node->getKey()] = node; + } + + void removeOldestGhost() + { + // 使用lock()方法，并添加null检查 + NodePtr oldestGhost = ghostTail_->prev_.lock(); + if (!oldestGhost || oldestGhost == ghostHead_) + return; + + removeFromGhost(oldestGhost); + ghostCache_.erase(oldestGhost->getKey()); + } + + +private: + size_t capacity_; + size_t ghostCapacity_; + size_t transformThreshold_; // 转换门槛值 + std::mutex mutex_; + + NodeMap mainCache_; // key -> ArcNode + NodeMap ghostCache_; + + // 主链表 + NodePtr mainHead_; + NodePtr mainTail_; + // 淘汰链表 + NodePtr ghostHead_; + NodePtr ghostTail_; +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/KICachePolicy.h b/KICachePolicy.h new file mode 100644 index 0000000..8fbbc82 --- /dev/null +++ b/KICachePolicy.h @@ -0,0 +1,22 @@ +#pragma once + +namespace KamaCache +{ + +template +class KICachePolicy +{ +public: + virtual ~KICachePolicy() {}; + + // 添加缓存接口 + virtual void put(Key key, Value value) = 0; + + // key是传入参数 访问到的值以传出参数的形式返回 | 访问成功返回true + virtual bool get(Key key, Value& value) = 0; + // 如果缓存中能找到key，则直接返回value + virtual Value get(Key key) = 0; + +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/KLfuCache.h b/KLfuCache.h new file mode 100644 index 0000000..023ebab --- /dev/null +++ b/KLfuCache.h @@ -0,0 +1,379 @@ +#pragma once + +#include +#include +#include +#include +#include +#include + +#include "KICachePolicy.h" + +namespace KamaCache +{ + +template class KLfuCache; + +template +class FreqList +{ +private: + struct Node + { + int freq; // 访问频次 + Key key; + Value value; + std::weak_ptr pre; // 上一结点改为weak_ptr打破循环引用 + std::shared_ptr next; + + Node() + : freq(1), next(nullptr) {} + Node(Key key, Value value) + : freq(1), key(key), value(value), next(nullptr) {} + }; + + using NodePtr = std::shared_ptr; + int freq_; // 访问频率 + NodePtr head_; // 假头结点 + NodePtr tail_; // 假尾结点 + +public: + explicit FreqList(int n) + : freq_(n) + { + head_ = std::make_shared(); + tail_ = std::make_shared(); + head_->next = tail_; + tail_->pre = head_; + } + + bool isEmpty() const + { + return head_->next == tail_; + } + + // 提那家结点管理方法 + void addNode(NodePtr node) + { + if (!node || !head_ || !tail_) + return; + + node->pre = tail_->pre; + node->next = tail_; + tail_->pre.lock()->next = node; // 使用lock()获取shared_ptr + tail_->pre = node; + } + + void removeNode(NodePtr node) + { + if (!node || !head_ || !tail_) + return; + if (node->pre.expired() || !node->next) + return; + + auto pre = node->pre.lock(); // 使用lock()获取shared_ptr + pre->next = node->next; + node->next->pre = pre; + node->next = nullptr; // 确保显式置空next指针，彻底断开节点与链表的连接 + } + + NodePtr getFirstNode() const { return head_->next; } + + friend class KLfuCache; +}; + +template +class KLfuCache : public KICachePolicy +{ +public: + using Node = typename FreqList::Node; + using NodePtr = std::shared_ptr; + using NodeMap = std::unordered_map; + + KLfuCache(int capacity, int maxAverageNum = 1000000) + : capacity_(capacity), minFreq_(INT8_MAX), maxAverageNum_(maxAverageNum), + curAverageNum_(0), curTotalNum_(0) + {} + + ~KLfuCache() override = default; + + void put(Key key, Value value) override + { + if (capacity_ == 0) + return; + + std::lock_guard lock(mutex_); + auto it = nodeMap_.find(key); + if (it != nodeMap_.end()) + { + // 重置其value值 + it->second->value = value; + // 找到了直接调整就好了，不用再去get中再找一遍，但其实影响不大 + getInternal(it->second, value); + return; + } + + putInternal(key, value); + } + + // value值为传出参数 + bool get(Key key, Value& value) override + { + std::lock_guard lock(mutex_); + auto it = nodeMap_.find(key); + if (it != nodeMap_.end()) + { + getInternal(it->second, value); + return true; + } + + return false; + } + + Value get(Key key) override + { + Value value; + get(key, value); + return value; + } + + // 清空缓存,回收资源 + void purge() + { + nodeMap_.clear(); + freqToFreqList_.clear(); + } + +private: + void putInternal(Key key, Value value); // 添加缓存 + void getInternal(NodePtr node, Value& value); // 获取缓存 + + void kickOut(); // 移除缓存中的过期数据 + + void removeFromFreqList(NodePtr node); // 从频率列表中移除节点 + void addToFreqList(NodePtr node); // 添加到频率列表 + + void addFreqNum(); // 增加平均访问等频率 + void decreaseFreqNum(int num); // 减少平均访问等频率 + void handleOverMaxAverageNum(); // 处理当前平均访问频率超过上限的情况 + void updateMinFreq(); + +private: + int capacity_; // 缓存容量 + int minFreq_; // 最小访问频次(用于找到最小访问频次结点) + int maxAverageNum_; // 最大平均访问频次 + int curAverageNum_; // 当前平均访问频次 + int curTotalNum_; // 当前访问所有缓存次数总数 + std::mutex mutex_; // 互斥锁 + NodeMap nodeMap_; // key 到 缓存节点的映射 + std::unordered_map*> freqToFreqList_;// 访问频次到该频次链表的映射 +}; + +template +void KLfuCache::getInternal(NodePtr node, Value& value) +{ + // 找到之后需要将其从低访问频次的链表中删除，并且添加到+1的访问频次链表中， + // 访问频次+1, 然后把value值返回 + value = node->value; + // 从原有访问频次的链表中删除节点 + removeFromFreqList(node); + node->freq++; + addToFreqList(node); + // 如果当前node的访问频次如果等于minFreq+1，并且其前驱链表为空，则说明 + // freqToFreqList_[node->freq - 1]链表因node的迁移已经空了，需要更新最小访问频次 + if (node->freq - 1 == minFreq_ && freqToFreqList_[node->freq - 1]->isEmpty()) + minFreq_++; + + // 总访问频次和当前平均访问频次都随之增加 + addFreqNum(); +} + +template +void KLfuCache::putInternal(Key key, Value value) +{ + // 如果不在缓存中，则需要判断缓存是否已满 + if (nodeMap_.size() == capacity_) + { + // 缓存已满，删除最不常访问的结点，更新当前平均访问频次和总访问频次 + kickOut(); + } + + // 创建新结点，将新结点添加进入，更新最小访问频次 + NodePtr node = std::make_shared(key, value); + nodeMap_[key] = node; + addToFreqList(node); + addFreqNum(); + minFreq_ = std::min(minFreq_, 1); +} + +template +void KLfuCache::kickOut() +{ + NodePtr node = freqToFreqList_[minFreq_]->getFirstNode(); + removeFromFreqList(node); + nodeMap_.erase(node->key); + decreaseFreqNum(node->freq); +} + +template +void KLfuCache::removeFromFreqList(NodePtr node) +{ + // 检查结点是否为空 + if (!node) + return; + + auto freq = node->freq; + freqToFreqList_[freq]->removeNode(node); +} + +template +void KLfuCache::addToFreqList(NodePtr node) +{ + // 检查结点是否为空 + if (!node) + return; + + // 添加进入相应的频次链表前需要判断该频次链表是否存在 + auto freq = node->freq; + if (freqToFreqList_.find(node->freq) == freqToFreqList_.end()) + { + // 不存在则创建 + freqToFreqList_[node->freq] = new FreqList(node->freq); + } + + freqToFreqList_[freq]->addNode(node); +} + +template +void KLfuCache::addFreqNum() +{ + curTotalNum_++; + if (nodeMap_.empty()) + curAverageNum_ = 0; + else + curAverageNum_ = curTotalNum_ / nodeMap_.size(); + + if (curAverageNum_ > maxAverageNum_) + { + handleOverMaxAverageNum(); + } +} + +template +void KLfuCache::decreaseFreqNum(int num) +{ + // 减少平均访问频次和总访问频次 + curTotalNum_ -= num; + if (nodeMap_.empty()) + curAverageNum_ = 0; + else + curAverageNum_ = curTotalNum_ / nodeMap_.size(); +} + +template +void KLfuCache::handleOverMaxAverageNum() +{ + if (nodeMap_.empty()) + return; + + // 当前平均访问频次已经超过了最大平均访问频次，所有结点的访问频次- (maxAverageNum_ / 2) + for (auto it = nodeMap_.begin(); it != nodeMap_.end(); ++it) + { + // 检查结点是否为空 + if (!it->second) + continue; + + NodePtr node = it->second; + + // 先从当前频率列表中移除 + removeFromFreqList(node); + + // 减少频率 + node->freq -= maxAverageNum_ / 2; + if (node->freq < 1) node->freq = 1; + + // 添加到新的频率列表 + addToFreqList(node); + } + + // 更新最小频率 + updateMinFreq(); +} + +template +void KLfuCache::updateMinFreq() +{ + minFreq_ = INT8_MAX; + for (const auto& pair : freqToFreqList_) + { + if (pair.second && !pair.second->isEmpty()) + { + minFreq_ = std::min(minFreq_, pair.first); + } + } + if (minFreq_ == INT8_MAX) + minFreq_ = 1; +} + +// 并没有牺牲空间换时间，他是把原有缓存大小进行了分片。 +template +class KHashLfuCache +{ +public: + KHashLfuCache(size_t capacity, int sliceNum, int maxAverageNum = 10) + : sliceNum_(sliceNum > 0 ? sliceNum : std::thread::hardware_concurrency()) + , capacity_(capacity) + { + size_t sliceSize = std::ceil(capacity_ / static_cast(sliceNum_)); // 每个lfu分片的容量 + for (int i = 0; i < sliceNum_; ++i) + { + lfuSliceCaches_.emplace_back(new KLfuCache(sliceSize, maxAverageNum)); + } + } + + void put(Key key, Value value) + { + // 根据key找出对应的lfu分片 + size_t sliceIndex = Hash(key) % sliceNum_; + lfuSliceCaches_[sliceIndex]->put(key, value); + } + + bool get(Key key, Value& value) + { + // 根据key找出对应的lfu分片 + size_t sliceIndex = Hash(key) % sliceNum_; + return lfuSliceCaches_[sliceIndex]->get(key, value); + } + + Value get(Key key) + { + Value value; + get(key, value); + return value; + } + + // 清除缓存 + void purge() + { + for (auto& lfuSliceCache : lfuSliceCaches_) + { + lfuSliceCache->purge(); + } + } + +private: + // 将key计算成对应哈希值 + size_t Hash(Key key) + { + std::hash hashFunc; + return hashFunc(key); + } + +private: + size_t capacity_; // 缓存总容量 + int sliceNum_; // 缓存分片数量 + std::vector>> lfuSliceCaches_; // 缓存lfu分片容器 +}; + +} // namespace KamaCache + diff --git a/KLruCache.h b/KLruCache.h new file mode 100644 index 0000000..09c2f89 --- /dev/null +++ b/KLruCache.h @@ -0,0 +1,326 @@ +#pragma once + +#include +#include +#include +#include +#include + +#include "KICachePolicy.h" + +namespace KamaCache +{ + +// 前向声明 +template class KLruCache; + +template +class LruNode +{ +private: + Key key_; + Value value_; + size_t accessCount_; // 访问次数 + std::weak_ptr> prev_; // 改为weak_ptr打破循环引用 + std::shared_ptr> next_; + +public: + LruNode(Key key, Value value) + : key_(key) + , value_(value) + , accessCount_(1) + {} + + // 提供必要的访问器 + Key getKey() const { return key_; } + Value getValue() const { return value_; } + void setValue(const Value& value) { value_ = value; } + size_t getAccessCount() const { return accessCount_; } + void incrementAccessCount() { ++accessCount_; } + + friend class KLruCache; +}; + + +template +class KLruCache : public KICachePolicy +{ +public: + using LruNodeType = LruNode; + using NodePtr = std::shared_ptr; + using NodeMap = std::unordered_map; + + KLruCache(int capacity) + : capacity_(capacity) + { + initializeList(); + } + + ~KLruCache() override = default; + + // 添加缓存 + void put(Key key, Value value) override + { + if (capacity_ <= 0) + return; + + std::lock_guard lock(mutex_); + auto it = nodeMap_.find(key); + if (it != nodeMap_.end()) + { + // 如果在当前容器中,则更新value,并调用get方法，代表该数据刚被访问 + updateExistingNode(it->second, value); + return ; + } + + addNewNode(key, value); + } + + bool get(Key key, Value& value) override + { + std::lock_guard lock(mutex_); + auto it = nodeMap_.find(key); + if (it != nodeMap_.end()) + { + moveToMostRecent(it->second); + value = it->second->getValue(); + return true; + } + return false; + } + + Value get(Key key) override + { + Value value{}; + // memset(&value, 0, sizeof(value)); // memset 是按字节设置内存的，对于复杂类型（如 string）使用 memset 可能会破坏对象的内部结构 + get(key, value); + return value; + } + + // 删除指定元素 + void remove(Key key) + { + std::lock_guard lock(mutex_); + auto it = nodeMap_.find(key); + if (it != nodeMap_.end()) + { + removeNode(it->second); + nodeMap_.erase(it); + } + } + +private: + void initializeList() + { + // 创建首尾虚拟节点 + dummyHead_ = std::make_shared(Key(), Value()); + dummyTail_ = std::make_shared(Key(), Value()); + dummyHead_->next_ = dummyTail_; + dummyTail_->prev_ = dummyHead_; + } + + void updateExistingNode(NodePtr node, const Value& value) + { + node->setValue(value); + moveToMostRecent(node); + } + + void addNewNode(const Key& key, const Value& value) + { + if (nodeMap_.size() >= capacity_) + { + evictLeastRecent(); + } + + NodePtr newNode = std::make_shared(key, value); + insertNode(newNode); + nodeMap_[key] = newNode; + } + + // 将该节点移动到最新的位置 + void moveToMostRecent(NodePtr node) + { + removeNode(node); + insertNode(node); + } + + void removeNode(NodePtr node) + { + if(!node->prev_.expired() && node->next_) + { + auto prev = node->prev_.lock(); // 使用lock()获取shared_ptr + prev->next_ = node->next_; + node->next_->prev_ = prev; + node->next_ = nullptr; // 清空next_指针，彻底断开节点与链表的连接 + } + } + + // 从尾部插入结点 + void insertNode(NodePtr node) + { + node->next_ = dummyTail_; + node->prev_ = dummyTail_->prev_; + dummyTail_->prev_.lock()->next_ = node; // 使用lock()获取shared_ptr + dummyTail_->prev_ = node; + } + + // 驱逐最近最少访问 + void evictLeastRecent() + { + NodePtr leastRecent = dummyHead_->next_; + removeNode(leastRecent); + nodeMap_.erase(leastRecent->getKey()); + } + +private: + int capacity_; // 缓存容量 + NodeMap nodeMap_; // key -> Node + std::mutex mutex_; + NodePtr dummyHead_; // 虚拟头结点 + NodePtr dummyTail_; +}; + +// LRU优化：Lru-k版本。 通过继承的方式进行再优化 +template +class KLruKCache : public KLruCache +{ +public: + KLruKCache(int capacity, int historyCapacity, int k) + : KLruCache(capacity) // 调用基类构造 + , historyList_(std::make_unique>(historyCapacity)) + , k_(k) + {} + + Value get(Key key) + { + // 首先尝试从主缓存获取数据 + Value value{}; + bool inMainCache = KLruCache::get(key, value); + + // 获取并更新访问历史计数 + size_t historyCount = historyList_->get(key); + historyCount++; + historyList_->put(key, historyCount); + + // 如果数据在主缓存中，直接返回 + if (inMainCache) + { + return value; + } + + // 如果数据不在主缓存，但访问次数达到了k次 + if (historyCount >= k_) + { + // 检查是否有历史值记录 + auto it = historyValueMap_.find(key); + if (it != historyValueMap_.end()) + { + // 有历史值，将其添加到主缓存 + Value storedValue = it->second; + + // 从历史记录移除 + historyList_->remove(key); + historyValueMap_.erase(it); + + // 添加到主缓存 + KLruCache::put(key, storedValue); + + return storedValue; + } + // 没有历史值记录，无法添加到缓存，返回默认值 + } + + // 数据不在主缓存且不满足添加条件，返回默认值 + return value; + } + + void put(Key key, Value value) + { + // 检查是否已在主缓存 + Value existingValue{}; + bool inMainCache = KLruCache::get(key, existingValue); + + if (inMainCache) + { + // 已在主缓存，直接更新 + KLruCache::put(key, value); + return; + } + + // 获取并更新访问历史 + size_t historyCount = historyList_->get(key); + historyCount++; + historyList_->put(key, historyCount); + + // 保存值到历史记录映射，供后续get操作使用 + historyValueMap_[key] = value; + + // 检查是否达到k次访问阈值 + if (historyCount >= k_) + { + // 达到阈值，添加到主缓存 + historyList_->remove(key); + historyValueMap_.erase(key); + KLruCache::put(key, value); + } + } + +private: + int k_; // 进入缓存队列的评判标准 + std::unique_ptr> historyList_; // 访问数据历史记录(value为访问次数) + std::unordered_map historyValueMap_; // 存储未达到k次访问的数据值 +}; + +// lru优化：对lru进行分片，提高高并发使用的性能 +template +class KHashLruCaches +{ +public: + KHashLruCaches(size_t capacity, int sliceNum) + : capacity_(capacity) + , sliceNum_(sliceNum > 0 ? sliceNum : std::thread::hardware_concurrency()) + { + size_t sliceSize = std::ceil(capacity / static_cast(sliceNum_)); // 获取每个分片的大小 + for (int i = 0; i < sliceNum_; ++i) + { + lruSliceCaches_.emplace_back(new KLruCache(sliceSize)); + } + } + + void put(Key key, Value value) + { + // 获取key的hash值，并计算出对应的分片索引 + size_t sliceIndex = Hash(key) % sliceNum_; + lruSliceCaches_[sliceIndex]->put(key, value); + } + + bool get(Key key, Value& value) + { + // 获取key的hash值，并计算出对应的分片索引 + size_t sliceIndex = Hash(key) % sliceNum_; + return lruSliceCaches_[sliceIndex]->get(key, value); + } + + Value get(Key key) + { + Value value; + memset(&value, 0, sizeof(value)); + get(key, value); + return value; + } + +private: + // 将key转换为对应hash值 + size_t Hash(Key key) + { + std::hash hashFunc; + return hashFunc(key); + } + +private: + size_t capacity_; // 总容量 + int sliceNum_; // 切片数量 + std::vector>> lruSliceCaches_; // 切片LRU缓存 +}; + +} // namespace KamaCache \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f9de5c --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +# KamaCache + +> ⭐️ 本项目为[【代码随想录知识星球】](https://programmercarl.com/other/kstar.html) 教学项目 +> ⭐️ 在 [缓存项目文档](https://www.programmercarl.com/other/project_huancun.html) 里详细讲解：**项目前置知识 + 项目细节 + 代码解读 + 项目难点 + 面试题与回答 + 简历写法 + 项目拓展**。 全面帮助你用这个项目求职面试！ + + +## 项目介绍 +本项目使用多个页面替换策略实现一个线程安全的缓存： +- LRU：最近最久未使用 +- LFU：最近不经常使用 +- ARC：自适应替换 + +对于LRU和LFU策略，我在其基础的缓存策略上进行了相应的优化，例如： + +- LRU优化： + - LRU分片：对多线程下的高并发访问有性能上的优化 + - LRU-k：一定程度上防止热点数据被冷数据挤出容器而造成缓存污染等问题 + +- LFU优化： + - LFU分片：对多线程下的高并发访问有性能上的优化 + - 引入最大平均访问频次：解决过去的热点数据最近一直没被访问，却仍占用缓存等问题 + +## 系统环境 +``` +Ubuntu 22.04 LTS +``` +## 编译 +创建一个build文件夹并进入 +``` +mkdir build && cd build +``` +生成构建文件 +``` +cmake .. +``` +构建项目 +``` +make +``` +如果要清理生成的可执行文件 +``` +make clean +``` + +## 运行 +``` +./main +``` + +## 测试结果 +不同缓存策略缓存命中率测试对比结果如下： +（ps: 该测试代码只是尽可能地模拟真实的访问场景，但是跟真实的场景仍存在一定差距，测试结果仅供参考。） + +![alt text](images/hitTest.jpg) diff --git a/images/hitTest.jpg b/images/hitTest.jpg new file mode 100644 index 0000000..5816558 Binary files /dev/null and b/images/hitTest.jpg differ diff --git a/testAllCachePolicy.cpp b/testAllCachePolicy.cpp new file mode 100644 index 0000000..44a7569 --- /dev/null +++ b/testAllCachePolicy.cpp @@ -0,0 +1,286 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include "KICachePolicy.h" +#include "KLfuCache.h" +#include "KLruCache.h" +#include "KArcCache/KArcCache.h" + +class Timer { +public: + Timer() : start_(std::chrono::high_resolution_clock::now()) {} + + double elapsed() { + auto now = std::chrono::high_resolution_clock::now(); + return std::chrono::duration_cast(now - start_).count(); + } + +private: + std::chrono::time_point start_; +}; + +// 辅助函数：打印结果 +void printResults(const std::string& testName, int capacity, + const std::vector& get_operations, + const std::vector& hits) { + std::cout << "=== " << testName << " 结果汇总 ===" << std::endl; + std::cout << "缓存大小: " << capacity << std::endl; + + // 假设对应的算法名称已在测试函数中定义 + std::vector names; + if (hits.size() == 3) { + names = {"LRU", "LFU", "ARC"}; + } else if (hits.size() == 4) { + names = {"LRU", "LFU", "ARC", "LRU-K"}; + } else if (hits.size() == 5) { + names = {"LRU", "LFU", "ARC", "LRU-K", "LFU-Aging"}; + } + + for (size_t i = 0; i < hits.size(); ++i) { + double hitRate = 100.0 * hits[i] / get_operations[i]; + std::cout << (i < names.size() ? names[i] : "Algorithm " + std::to_string(i+1)) + << " - 命中率: " << std::fixed << std::setprecision(2) + << hitRate << "% "; + // 添加具体命中次数和总操作次数 + std::cout << "(" << hits[i] << "/" << get_operations[i] << ")" << std::endl; + } + + std::cout << std::endl; // 添加空行，使输出更清晰 +} + +void testHotDataAccess() { + std::cout << "\n=== 测试场景1：热点数据访问测试 ===" << std::endl; + + const int CAPACITY = 20; // 缓存容量 + const int OPERATIONS = 500000; // 总操作次数 + const int HOT_KEYS = 20; // 热点数据数量 + const int COLD_KEYS = 5000; // 冷数据数量 + + KamaCache::KLruCache lru(CAPACITY); + KamaCache::KLfuCache lfu(CAPACITY); + KamaCache::KArcCache arc(CAPACITY); + // 为LRU-K设置合适的参数： + // - 主缓存容量与其他算法相同 + // - 历史记录容量设为可能访问的所有键数量 + // - k=2表示数据被访问2次后才会进入缓存，适合区分热点和冷数据 + KamaCache::KLruKCache lruk(CAPACITY, HOT_KEYS + COLD_KEYS, 2); + KamaCache::KLfuCache lfuAging(CAPACITY, 20000); + + std::random_device rd; + std::mt19937 gen(rd()); + + // 基类指针指向派生类对象，添加LFU-Aging + std::array*, 5> caches = {&lru, &lfu, &arc, &lruk, &lfuAging}; + std::vector hits(5, 0); + std::vector get_operations(5, 0); + std::vector names = {"LRU", "LFU", "ARC", "LRU-K", "LFU-Aging"}; + + // 为所有的缓存对象进行相同的操作序列测试 + for (int i = 0; i < caches.size(); ++i) { + // 先预热缓存，插入一些数据 + for (int key = 0; key < HOT_KEYS; ++key) { + std::string value = "value" + std::to_string(key); + caches[i]->put(key, value); + } + + // 交替进行put和get操作，模拟真实场景 + for (int op = 0; op < OPERATIONS; ++op) { + // 大多数缓存系统中读操作比写操作频繁 + // 所以设置30%概率进行写操作 + bool isPut = (gen() % 100 < 30); + int key; + + // 70%概率访问热点数据，30%概率访问冷数据 + if (gen() % 100 < 70) { + key = gen() % HOT_KEYS; // 热点数据 + } else { + key = HOT_KEYS + (gen() % COLD_KEYS); // 冷数据 + } + + if (isPut) { + // 执行put操作 + std::string value = "value" + std::to_string(key) + "_v" + std::to_string(op % 100); + caches[i]->put(key, value); + } else { + // 执行get操作并记录命中情况 + std::string result; + get_operations[i]++; + if (caches[i]->get(key, result)) { + hits[i]++; + } + } + } + } + + // 打印测试结果 + printResults("热点数据访问测试", CAPACITY, get_operations, hits); +} + +void testLoopPattern() { + std::cout << "\n=== 测试场景2：循环扫描测试 ===" << std::endl; + + const int CAPACITY = 50; // 缓存容量 + const int LOOP_SIZE = 500; // 循环范围大小 + const int OPERATIONS = 200000; // 总操作次数 + + KamaCache::KLruCache lru(CAPACITY); + KamaCache::KLfuCache lfu(CAPACITY); + KamaCache::KArcCache arc(CAPACITY); + // 为LRU-K设置合适的参数： + // - 历史记录容量设为总循环大小的两倍，覆盖范围内和范围外的数据 + // - k=2，对于循环访问，这是一个合理的阈值 + KamaCache::KLruKCache lruk(CAPACITY, LOOP_SIZE * 2, 2); + KamaCache::KLfuCache lfuAging(CAPACITY, 3000); + + std::array*, 5> caches = {&lru, &lfu, &arc, &lruk, &lfuAging}; + std::vector hits(5, 0); + std::vector get_operations(5, 0); + std::vector names = {"LRU", "LFU", "ARC", "LRU-K", "LFU-Aging"}; + + std::random_device rd; + std::mt19937 gen(rd()); + + // 为每种缓存算法运行相同的测试 + for (int i = 0; i < caches.size(); ++i) { + // 先预热一部分数据（只加载20%的数据） + for (int key = 0; key < LOOP_SIZE / 5; ++key) { + std::string value = "loop" + std::to_string(key); + caches[i]->put(key, value); + } + + // 设置循环扫描的当前位置 + int current_pos = 0; + + // 交替进行读写操作，模拟真实场景 + for (int op = 0; op < OPERATIONS; ++op) { + // 20%概率是写操作，80%概率是读操作 + bool isPut = (gen() % 100 < 20); + int key; + + // 按照不同模式选择键 + if (op % 100 < 60) { // 60%顺序扫描 + key = current_pos; + current_pos = (current_pos + 1) % LOOP_SIZE; + } else if (op % 100 < 90) { // 30%随机跳跃 + key = gen() % LOOP_SIZE; + } else { // 10%访问范围外数据 + key = LOOP_SIZE + (gen() % LOOP_SIZE); + } + + if (isPut) { + // 执行put操作，更新数据 + std::string value = "loop" + std::to_string(key) + "_v" + std::to_string(op % 100); + caches[i]->put(key, value); + } else { + // 执行get操作并记录命中情况 + std::string result; + get_operations[i]++; + if (caches[i]->get(key, result)) { + hits[i]++; + } + } + } + } + + printResults("循环扫描测试", CAPACITY, get_operations, hits); +} + +void testWorkloadShift() { + std::cout << "\n=== 测试场景3：工作负载剧烈变化测试 ===" << std::endl; + + const int CAPACITY = 30; // 缓存容量 + const int OPERATIONS = 80000; // 总操作次数 + const int PHASE_LENGTH = OPERATIONS / 5; // 每个阶段的长度 + + KamaCache::KLruCache lru(CAPACITY); + KamaCache::KLfuCache lfu(CAPACITY); + KamaCache::KArcCache arc(CAPACITY); + KamaCache::KLruKCache lruk(CAPACITY, 500, 2); + KamaCache::KLfuCache lfuAging(CAPACITY, 10000); + + std::random_device rd; + std::mt19937 gen(rd()); + std::array*, 5> caches = {&lru, &lfu, &arc, &lruk, &lfuAging}; + std::vector hits(5, 0); + std::vector get_operations(5, 0); + std::vector names = {"LRU", "LFU", "ARC", "LRU-K", "LFU-Aging"}; + + // 为每种缓存算法运行相同的测试 + for (int i = 0; i < caches.size(); ++i) { + // 先预热缓存，只插入少量初始数据 + for (int key = 0; key < 30; ++key) { + std::string value = "init" + std::to_string(key); + caches[i]->put(key, value); + } + + // 进行多阶段测试，每个阶段有不同的访问模式 + for (int op = 0; op < OPERATIONS; ++op) { + // 确定当前阶段 + int phase = op / PHASE_LENGTH; + + // 每个阶段的读写比例不同 + int putProbability; + switch (phase) { + case 0: putProbability = 15; break; // 阶段1: 热点访问，15%写入更合理 + case 1: putProbability = 30; break; // 阶段2: 大范围随机，写比例为30% + case 2: putProbability = 10; break; // 阶段3: 顺序扫描，10%写入保持不变 + case 3: putProbability = 25; break; // 阶段4: 局部性随机，微调为25% + case 4: putProbability = 20; break; // 阶段5: 混合访问，调整为20% + default: putProbability = 20; + } + + // 确定是读还是写操作 + bool isPut = (gen() % 100 < putProbability); + + // 根据不同阶段选择不同的访问模式生成key - 优化后的访问范围 + int key; + if (op < PHASE_LENGTH) { // 阶段1: 热点访问 - 热点数量5，使热点更集中 + key = gen() % 5; + } else if (op < PHASE_LENGTH * 2) { // 阶段2: 大范围随机 - 范围400，更适合30大小的缓存 + key = gen() % 400; + } else if (op < PHASE_LENGTH * 3) { // 阶段3: 顺序扫描 - 保持100个键 + key = (op - PHASE_LENGTH * 2) % 100; + } else if (op < PHASE_LENGTH * 4) { // 阶段4: 局部性随机 - 优化局部性区域大小 + // 产生5个局部区域，每个区域大小为15个键，与缓存大小20接近但略小 + int locality = (op / 800) % 5; // 调整为5个局部区域 + key = locality * 15 + (gen() % 15); // 每区域15个键 + } else { // 阶段5: 混合访问 - 增加热点访问比例 + int r = gen() % 100; + if (r < 40) { // 40%概率访问热点（从30%增加） + key = gen() % 5; // 5个热点键 + } else if (r < 70) { // 30%概率访问中等范围 + key = 5 + (gen() % 45); // 缩小中等范围为50个键 + } else { // 30%概率访问大范围（从40%减少） + key = 50 + (gen() % 350); // 大范围也相应缩小 + } + } + + if (isPut) { + // 执行写操作 + std::string value = "value" + std::to_string(key) + "_p" + std::to_string(phase); + caches[i]->put(key, value); + } else { + // 执行读操作并记录命中情况 + std::string result; + get_operations[i]++; + if (caches[i]->get(key, result)) { + hits[i]++; + } + } + } + } + + printResults("工作负载剧烈变化测试", CAPACITY, get_operations, hits); +} + +int main() { + testHotDataAccess(); + testLoopPattern(); + testWorkloadShift(); + return 0; +}