c – Boost池分配器比新的慢

memory_pools.hpp

#ifndef MEMORY_POOL_HPP
# define MEMORY_POOLS_HPP

// boost
# include <boost/pool/pool.hpp>
# include <boost/unordered_map.hpp>

template<typename ElementType>
class   memory_pools
{
public:
  template <typename>
  friend class memory_pools;

private:
  using pool = boost::pool<>;

public:
  using value_type = ElementType;
  using pointer = value_type*;
  using const_pointer = const value_type*;
  using reference = value_type&;
  using const_reference = const value_type&;
  using size_type = pool::size_type;
  using difference_type = pool::difference_type;

public:

  template<typename OtherElementType>
  struct rebind
  {
    using other = memory_pools<OtherElementType>;
  };

public:
  memory_pools();

  template<typename SourceElement>
  memory_pools(const memory_pools<SourceElement>&);

public:
  pointer   allocate(const size_type n);
  void  deallocate(const pointer ptr,const size_type n);

  template<typename... Args>
  void  construct(pointer,Args...);
  void  destroy(pointer);

public:
  bool  operator==(const memory_pools&);
  bool  operator!=(const memory_pools&);

private:
  using pools_map = boost::unordered_map<std::size_t,std::shared_ptr<pool>>;

private:
  std::shared_ptr<pools_map>      pools_map_;
  std::shared_ptr<pool>           pool_;
};

# include <memory_pools.ipp>

#endif

memory_pools.ipp

#ifndef MEMORY_POOLS_IPP
# define MEMORY_POOLS_IPP

template<typename ElementType>
memory_pools<ElementType>::memory_pools()
  :
  pools_map_(std::make_shared<pools_map>
             (pools_map
             {
               std::make_pair
                 (sizeof(ElementType),make_shared<pool>(sizeof(ElementType)))
             })),pool_(pools_map_->at(sizeof(ElementType)))
{
}

template<typename ElementType>
template<typename SourceElement>
memory_pools<ElementType>::memory_pools
(const memory_pools<SourceElement>& rebinded_from)
  :
  pools_map_(rebinded_from.pools_map_),pool_(pools_map_->insert
        (std::make_pair(sizeof(ElementType),make_shared<pool>(sizeof(ElementType)))).first->second)
  {
  }

template<typename ElementType>
typename memory_pools<ElementType>::pointer memory_pools<ElementType>::allocate
(const size_type n)
{
  pointer ret = static_cast<pointer>(pool_->ordered_malloc(n));

  if ((!ret) && n)
    throw std::bad_alloc();

  return (ret);
}

template<typename ElementType>
void        memory_pools<ElementType>::deallocate
(const pointer ptr,const size_type n)
{
  pool_->ordered_free(ptr,n);
}

template<typename ElementType>
template<typename... Args>
void        memory_pools<ElementType>::construct(pointer ptr,Args... args)
{
  new (ptr) ElementType(std::forward<Args>(args)...);
}

template<typename ElementType>
void        memory_pools<ElementType>::destroy(pointer ptr)
{
  ptr->~ElementType();
}

template<typename ElementType>
bool        memory_pools<ElementType>::operator==(const memory_pools& rhs)
{
  return (pools_map_ == rhs.pools_map_);
}

template<typename ElementType>
bool        memory_pools<ElementType>::operator!=(const memory_pools& rhs)
{
  return (pools_map_ != rhs.pools_map_);
}

#endif

然后我用它测试它：

#include <memory_pools.hpp>

int     main(void)
{
  using pools_type = memory_pools<std::pair<const int,int>>;
  pools_type    pools;

  boost::unordered_map<int,int,boost::hash<int>,std::equal_to<int>,pools_type>      map;
  //boost::unordered_map<int,std::equal_to<int>>      map;

  for (unsigned int i = 0; i < 20000; ++i)
    {
      map[i] = i + 1;
    }

  return (0);
}

使用macOSX 10.10上的clang3.5,我得到了：

$time ./a.out

real    0m1.873s
user    0m1.850s
sys     0m0.009s

而当我发布时：

#include <memory_pools.hpp>

int     main(void)
{
  using pools_type = memory_pools<std::pair<const int,int>>;
  pools_type    pools;

  //boost::unordered_map<int,pools_type>      map;
  boost::unordered_map<int,std::equal_to<int>>      map;

  for (unsigned int i = 0; i < 20000; ++i)
    {
      map[i] = i + 1;
    }

  return (0);
}

我有：

$time ./a.out

real    0m0.019s
user    0m0.016s
sys     0m0.002s

题

使用boost pool的内存分配应该是那么慢还是我的测试由于某种原因无效？

编辑

在Carmeron的评论之后,我添加了-O3和-DNDEBUG标志,现在我有：

$time ./a.out

real    0m0.438s
user    0m0.431s
sys     0m0.003s

对于memory_pools版本,以及：

$time ./a.out

real    0m0.008s
user    0m0.006s
sys     0m0.002s

对于标准分配器版本.

题

问题仍然存在,它是否正常更慢？