Move LRUCache structs to lru_cache.h header

Summary: ... so that I can include the header and create LRUCache specific tests for D61977

Test Plan:
   make check

Reviewers: lightmark, IslamAbdelRahman, sdong

Reviewed By: sdong

Subscribers: andrewkr, dhruba, leveldb

Differential Revision: https://reviews.facebook.net/D62145
main
Yi Wu 8 years ago
parent 2fc2fd92a9
commit 2a2ebb6f5e
  1. 202
      util/lru_cache.cc
  2. 190
      util/lru_cache.h

@ -7,98 +7,21 @@
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include "util/lru_cache.h"
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include "port/port.h"
#include "util/autovector.h"
#include "util/mutexlock.h"
#include "util/sharded_cache.h"
namespace rocksdb {
namespace {
// LRU cache implementation
// An entry is a variable length heap-allocated structure.
// Entries are referenced by cache and/or by any external entity.
// The cache keeps all its entries in table. Some elements
// are also stored on LRU list.
//
// LRUHandle can be in these states:
// 1. Referenced externally AND in hash table.
// In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
// 2. Not referenced externally and in hash table. In that case the entry is
// in the LRU and can be freed. (refs == 1 && in_cache == true)
// 3. Referenced externally and not in hash table. In that case the entry is
// in not on LRU and not in table. (refs >= 1 && in_cache == false)
//
// All newly created LRUHandles are in state 1. If you call
// LRUCacheShard::Release
// on entry in state 1, it will go into state 2. To move from state 1 to
// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
// same key.
// To move from state 2 to state 1, use LRUCacheShard::Lookup.
// Before destruction, make sure that no handles are in state 1. This means
// that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
// matching
// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)
struct LRUHandle {
void* value;
void (*deleter)(const Slice&, void* value);
LRUHandle* next_hash;
LRUHandle* next;
LRUHandle* prev;
size_t charge; // TODO(opt): Only allow uint32_t?
size_t key_length;
uint32_t refs; // a number of refs to this entry
// cache itself is counted as 1
bool in_cache; // true, if this entry is referenced by the hash table
uint32_t hash; // Hash of key(); used for fast sharding and comparisons
char key_data[1]; // Beginning of key
Slice key() const {
// For cheaper lookups, we allow a temporary Handle object
// to store a pointer to a key in "value".
if (next == this) {
return *(reinterpret_cast<Slice*>(value));
} else {
return Slice(key_data, key_length);
}
}
void Free() {
assert((refs == 1 && in_cache) || (refs == 0 && !in_cache));
(*deleter)(key(), value);
delete[] reinterpret_cast<char*>(this);
}
};
// We provide our own simple hash table since it removes a whole bunch
// of porting hacks and is also faster than some of the built-in hash
// table implementations in some of the compiler/runtime combinations
// we have tested. E.g., readrandom speeds up by ~5% over the g++
// 4.4.3's builtin hashtable.
class HandleTable {
public:
HandleTable() : length_(0), elems_(0), list_(nullptr) { Resize(); }
template <typename T>
void ApplyToAllCacheEntries(T func) {
for (uint32_t i = 0; i < length_; i++) {
LRUHandle* h = list_[i];
while (h != nullptr) {
auto n = h->next_hash;
assert(h->in_cache);
func(h);
h = n;
}
}
LRUHandleTable::LRUHandleTable() : length_(0), elems_(0), list_(nullptr) {
Resize();
}
~HandleTable() {
LRUHandleTable::~LRUHandleTable() {
ApplyToAllCacheEntries([](LRUHandle* h) {
if (h->refs == 1) {
h->Free();
@ -107,11 +30,11 @@ class HandleTable {
delete[] list_;
}
LRUHandle* Lookup(const Slice& key, uint32_t hash) {
LRUHandle* LRUHandleTable::Lookup(const Slice& key, uint32_t hash) {
return *FindPointer(key, hash);
}
LRUHandle* Insert(LRUHandle* h) {
LRUHandle* LRUHandleTable::Insert(LRUHandle* h) {
LRUHandle** ptr = FindPointer(h->key(), h->hash);
LRUHandle* old = *ptr;
h->next_hash = (old == nullptr ? nullptr : old->next_hash);
@ -127,7 +50,7 @@ class HandleTable {
return old;
}
LRUHandle* Remove(const Slice& key, uint32_t hash) {
LRUHandle* LRUHandleTable::Remove(const Slice& key, uint32_t hash) {
LRUHandle** ptr = FindPointer(key, hash);
LRUHandle* result = *ptr;
if (result != nullptr) {
@ -137,17 +60,7 @@ class HandleTable {
return result;
}
private:
// The table consists of an array of buckets where each bucket is
// a linked list of cache entries that hash into the bucket.
uint32_t length_;
uint32_t elems_;
LRUHandle** list_;
// Return a pointer to slot that points to a cache entry that
// matches key/hash. If there is no such cache entry, return a
// pointer to the trailing slot in the corresponding linked list.
LRUHandle** FindPointer(const Slice& key, uint32_t hash) {
LRUHandle** LRUHandleTable::FindPointer(const Slice& key, uint32_t hash) {
LRUHandle** ptr = &list_[hash & (length_ - 1)];
while (*ptr != nullptr && ((*ptr)->hash != hash || key != (*ptr)->key())) {
ptr = &(*ptr)->next_hash;
@ -155,7 +68,7 @@ class HandleTable {
return ptr;
}
void Resize() {
void LRUHandleTable::Resize() {
uint32_t new_length = 16;
while (new_length < elems_ * 1.5) {
new_length *= 2;
@ -180,88 +93,6 @@ class HandleTable {
list_ = new_list;
length_ = new_length;
}
};
// A single shard of sharded cache.
class LRUCacheShard : public CacheShard {
public:
LRUCacheShard();
virtual ~LRUCacheShard();
// Separate from constructor so caller can easily make an array of LRUCache
// if current usage is more than new capacity, the function will attempt to
// free the needed space
virtual void SetCapacity(size_t capacity) override;
// Set the flag to reject insertion if cache if full.
virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
// Like Cache methods, but with an extra "hash" parameter.
virtual Status Insert(const Slice& key, uint32_t hash, void* value,
size_t charge,
void (*deleter)(const Slice& key, void* value),
Cache::Handle** handle) override;
virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
virtual void Release(Cache::Handle* handle) override;
virtual void Erase(const Slice& key, uint32_t hash) override;
// Although in some platforms the update of size_t is atomic, to make sure
// GetUsage() and GetPinnedUsage() work correctly under any platform, we'll
// protect them with mutex_.
virtual size_t GetUsage() const override {
MutexLock l(&mutex_);
return usage_;
}
virtual size_t GetPinnedUsage() const override {
MutexLock l(&mutex_);
assert(usage_ >= lru_usage_);
return usage_ - lru_usage_;
}
virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
bool thread_safe) override;
virtual void EraseUnRefEntries() override;
private:
void LRU_Remove(LRUHandle* e);
void LRU_Append(LRUHandle* e);
// Just reduce the reference count by 1.
// Return true if last reference
bool Unref(LRUHandle* e);
// Free some space following strict LRU policy until enough space
// to hold (usage_ + charge) is freed or the lru list is empty
// This function is not thread safe - it needs to be executed while
// holding the mutex_
void EvictFromLRU(size_t charge, autovector<LRUHandle*>* deleted);
// Initialized before use.
size_t capacity_;
// Memory size for entries residing in the cache
size_t usage_;
// Memory size for entries residing only in the LRU list
size_t lru_usage_;
// Whether to reject insertion if cache reaches its full capacity.
bool strict_capacity_limit_;
// mutex_ protects the following state.
// We don't count mutex_ as the cache's internal state so semantically we
// don't mind mutex_ invoking the non-const actions.
mutable port::Mutex mutex_;
// Dummy head of LRU list.
// lru.prev is newest entry, lru.next is oldest entry.
// LRU contains items which can be evicted, ie reference only by cache
LRUHandle lru_;
HandleTable table_;
};
LRUCacheShard::LRUCacheShard() : usage_(0), lru_usage_(0) {
// Make empty circular linked list
@ -516,6 +347,17 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
}
}
size_t LRUCacheShard::GetUsage() const {
MutexLock l(&mutex_);
return usage_;
}
size_t LRUCacheShard::GetPinnedUsage() const {
MutexLock l(&mutex_);
assert(usage_ >= lru_usage_);
return usage_ - lru_usage_;
}
class LRUCache : public ShardedCache {
public:
LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
@ -555,8 +397,6 @@ class LRUCache : public ShardedCache {
LRUCacheShard* shards_;
};
} // end anonymous namespace
std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
bool strict_capacity_limit) {
if (num_shard_bits >= 20) {

@ -0,0 +1,190 @@
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#pragma once
#include "util/sharded_cache.h"
#include "port/port.h"
#include "util/autovector.h"
namespace rocksdb {
// LRU cache implementation
// An entry is a variable length heap-allocated structure.
// Entries are referenced by cache and/or by any external entity.
// The cache keeps all its entries in table. Some elements
// are also stored on LRU list.
//
// LRUHandle can be in these states:
// 1. Referenced externally AND in hash table.
// In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
// 2. Not referenced externally and in hash table. In that case the entry is
// in the LRU and can be freed. (refs == 1 && in_cache == true)
// 3. Referenced externally and not in hash table. In that case the entry is
// in not on LRU and not in table. (refs >= 1 && in_cache == false)
//
// All newly created LRUHandles are in state 1. If you call
// LRUCacheShard::Release
// on entry in state 1, it will go into state 2. To move from state 1 to
// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
// same key.
// To move from state 2 to state 1, use LRUCacheShard::Lookup.
// Before destruction, make sure that no handles are in state 1. This means
// that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
// matching
// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)
struct LRUHandle {
void* value;
void (*deleter)(const Slice&, void* value);
LRUHandle* next_hash;
LRUHandle* next;
LRUHandle* prev;
size_t charge; // TODO(opt): Only allow uint32_t?
size_t key_length;
uint32_t refs; // a number of refs to this entry
// cache itself is counted as 1
bool in_cache; // true, if this entry is referenced by the hash table
uint32_t hash; // Hash of key(); used for fast sharding and comparisons
char key_data[1]; // Beginning of key
Slice key() const {
// For cheaper lookups, we allow a temporary Handle object
// to store a pointer to a key in "value".
if (next == this) {
return *(reinterpret_cast<Slice*>(value));
} else {
return Slice(key_data, key_length);
}
}
void Free() {
assert((refs == 1 && in_cache) || (refs == 0 && !in_cache));
(*deleter)(key(), value);
delete[] reinterpret_cast<char*>(this);
}
};
// We provide our own simple hash table since it removes a whole bunch
// of porting hacks and is also faster than some of the built-in hash
// table implementations in some of the compiler/runtime combinations
// we have tested. E.g., readrandom speeds up by ~5% over the g++
// 4.4.3's builtin hashtable.
class LRUHandleTable {
public:
LRUHandleTable();
~LRUHandleTable();
LRUHandle* Lookup(const Slice& key, uint32_t hash);
LRUHandle* Insert(LRUHandle* h);
LRUHandle* Remove(const Slice& key, uint32_t hash);
template <typename T>
void ApplyToAllCacheEntries(T func) {
for (uint32_t i = 0; i < length_; i++) {
LRUHandle* h = list_[i];
while (h != nullptr) {
auto n = h->next_hash;
assert(h->in_cache);
func(h);
h = n;
}
}
}
private:
// Return a pointer to slot that points to a cache entry that
// matches key/hash. If there is no such cache entry, return a
// pointer to the trailing slot in the corresponding linked list.
LRUHandle** FindPointer(const Slice& key, uint32_t hash);
void Resize();
// The table consists of an array of buckets where each bucket is
// a linked list of cache entries that hash into the bucket.
uint32_t length_;
uint32_t elems_;
LRUHandle** list_;
};
// A single shard of sharded cache.
class LRUCacheShard : public CacheShard {
public:
LRUCacheShard();
virtual ~LRUCacheShard();
// Separate from constructor so caller can easily make an array of LRUCache
// if current usage is more than new capacity, the function will attempt to
// free the needed space
virtual void SetCapacity(size_t capacity) override;
// Set the flag to reject insertion if cache if full.
virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
// Like Cache methods, but with an extra "hash" parameter.
virtual Status Insert(const Slice& key, uint32_t hash, void* value,
size_t charge,
void (*deleter)(const Slice& key, void* value),
Cache::Handle** handle) override;
virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
virtual void Release(Cache::Handle* handle) override;
virtual void Erase(const Slice& key, uint32_t hash) override;
// Although in some platforms the update of size_t is atomic, to make sure
// GetUsage() and GetPinnedUsage() work correctly under any platform, we'll
// protect them with mutex_.
virtual size_t GetUsage() const override;
virtual size_t GetPinnedUsage() const override;
virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
bool thread_safe) override;
virtual void EraseUnRefEntries() override;
private:
void LRU_Remove(LRUHandle* e);
void LRU_Append(LRUHandle* e);
// Just reduce the reference count by 1.
// Return true if last reference
bool Unref(LRUHandle* e);
// Free some space following strict LRU policy until enough space
// to hold (usage_ + charge) is freed or the lru list is empty
// This function is not thread safe - it needs to be executed while
// holding the mutex_
void EvictFromLRU(size_t charge, autovector<LRUHandle*>* deleted);
// Initialized before use.
size_t capacity_;
// Memory size for entries residing in the cache
size_t usage_;
// Memory size for entries residing only in the LRU list
size_t lru_usage_;
// Whether to reject insertion if cache reaches its full capacity.
bool strict_capacity_limit_;
// mutex_ protects the following state.
// We don't count mutex_ as the cache's internal state so semantically we
// don't mind mutex_ invoking the non-const actions.
mutable port::Mutex mutex_;
// Dummy head of LRU list.
// lru.prev is newest entry, lru.next is oldest entry.
// LRU contains items which can be evicted, ie reference only by cache
LRUHandle lru_;
LRUHandleTable table_;
};
} // namespace rocksdb
Loading…
Cancel
Save