接下来看另一个模板:
typedef __default_alloc_template<__NODE_ALLOCATOR_THREADS, 0> alloc;
__default_alloc_template的实现。
template
class __default_alloc_template {
private:
// Really we should use static const int x = N
// instead of enum { x = N }, but few compilers accept the former.
# ifndef __SUNPRO_CC
enum {__ALIGN = 8};
enum {__MAX_BYTES = 128};
enum {__NFREELISTS = __MAX_BYTES/__ALIGN};
# endif
static size_t ROUND_UP(size_t bytes) {
return (((bytes) + __ALIGN-1) & ~(__ALIGN - 1));
}
__PRIVATE:
union obj {
union obj * free_list_link;
char client_data[1]; /* The client sees this. */
};
private:
# ifdef __SUNPRO_CC
static obj * __VOLATILE free_list[];
// Specifying a size results in duplicate def for 4.1
# else
static obj * __VOLATILE free_list[__NFREELISTS];
# endif
static size_t FREELIST_INDEX(size_t bytes) {
return (((bytes) + __ALIGN-1)/__ALIGN - 1);
}
// Returns an object of size n, and optionally adds to size n free list.
static void *refill(size_t n);
// Allocates a chunk for nobjs of size "size". nobjs may be reduced
// if it is inconvenient to allocate the requested number.
static char *chunk_alloc(size_t size, int &nobjs);
// Chunk allocation state.
static char *start_free;
static char *end_free;
static size_t heap_size;
# ifdef __STL_SGI_THREADS
static volatile unsigned long __node_allocator_lock;
static void __lock(volatile unsigned long *);
static inline void __unlock(volatile unsigned long *);
# endif
# ifdef __STL_PTHREADS
static pthread_mutex_t __node_allocator_lock;
# endif
# ifdef __STL_WIN32THREADS
static CRITICAL_SECTION __node_allocator_lock;
static bool __node_allocator_lock_initialized;
public:
__default_alloc_template() {
// This assumes the first constructor is called before threads
// are started.
if (!__node_allocator_lock_initialized) {
InitializeCriticalSection(&__node_allocator_lock);
__node_allocator_lock_initialized = true;
}
}
private:
# endif
class lock {
public:
lock() { __NODE_ALLOCATOR_LOCK; }
~lock() { __NODE_ALLOCATOR_UNLOCK; }
};
friend class lock;
public:
/* n must be > 0 */
static void * allocate(size_t n)
{
obj * __VOLATILE * my_free_list;
obj * __RESTRICT result;
if (n > (size_t) __MAX_BYTES) {
return(malloc_alloc::allocate(n));
}
my_free_list = free_list + FREELIST_INDEX(n);
// Acquire the lock here with a constructor call.
// This ensures that it is released in exit or during stack
// unwinding.
# ifndef _NOTHREADS
/*REFERENCED*/
lock lock_instance;
# endif
result = *my_free_list;
if (result == 0) {
void *r = refill(ROUND_UP(n));
return r;
}
*my_free_list = result -> free_list_link;
return (result);
};
/* p may not be 0 */
static void deallocate(void *p, size_t n)
{
obj *q = (obj *)p;
obj * __VOLATILE * my_free_list;
if (n > (size_t) __MAX_BYTES) {
malloc_alloc::deallocate(p, n);
return;
}
my_free_list = free_list + FREELIST_INDEX(n);
// acquire lock
# ifndef _NOTHREADS
/*REFERENCED*/
lock lock_instance;
# endif /* _NOTHREADS */
q -> free_list_link = *my_free_list;
*my_free_list = q;
// lock is released here
}
static void * reallocate(void *p, size_t old_sz, size_t new_sz);
} ;
很多宏判断,我们暂且不管,只关注内存是怎么分配的。先看allocte函数
/* n must be > 0 */
static void * allocate(size_t n)
{
obj * __VOLATILE * my_free_list;
obj * __RESTRICT result;
if (n > (size_t) __MAX_BYTES) {
return(malloc_alloc::allocate(n));
}
my_free_list = free_list + FREELIST_INDEX(n);
// Acquire the lock here with a constructor call.
// This ensures that it is released in exit or during stack
// unwinding.
# ifndef _NOTHREADS
/*REFERENCED*/
lock lock_instance;
# endif
result = *my_free_list;
if (result == 0) {
void *r = refill(ROUND_UP(n));
return r;
}
*my_free_list = result -> free_list_link;
return (result);
};
当分配的内存比较大的时候,直接调用了malloc_alloc::allocate(n)方法,也就是直接调用了底层的 malloc 函数(详细见:STL内存分配器详解之__malloc_alloc_template)
在讲解后续的代码前,先介绍下FREELIST_INDEX
static size_t FREELIST_INDEX(size_t bytes) {
return (((bytes) + __ALIGN-1)/__ALIGN - 1);
}
这个函数的目的是求得bytes是__ALIGN的多少倍。为的是,需要取N个字节时,会先确定N是8的多少倍,然后在对应的free_list中取空间进行分配给客户端。
free_list是个指针数组,其中每一个元素挂载了一个链表,第0条链表每一个元素的大小为8个字节,第1条链表,每个元素大小为16字节,.....第N条,每个元素大小为(N+1)*8。
//allocate 步骤
//1.如果需要的内存大于128,直接调用malloc_alloc::allocate
//2.如果是小于128的区块, 则执行下面的流程。
//2.1获得链表。
//2.2取第一号元素。如果取不到就调用refill函数,进行填充。
取到,则将该链表指向下一个元素。
refill 函数
template
void* __default_alloc_template::refill(size_t n)
{
int nobjs = 20;
char * chunk = chunk_alloc(n, nobjs);
obj * __VOLATILE * my_free_list;
obj * result;
obj * current_obj, * next_obj;
int i;
if (1 == nobjs) return(chunk);
my_free_list = free_list + FREELIST_INDEX(n);
/* Build free list in chunk */
result = (obj *)chunk;
*my_free_list = next_obj = (obj *)(chunk + n);
for (i = 1; ; i++) {
current_obj = next_obj;
next_obj = (obj *)((char *)next_obj + n);
if (nobjs - 1 == i) {
current_obj -> free_list_link = 0;//将最后一个置为空
break;
} else {
current_obj -> free_list_link = next_obj;
}
}
return(result);
}
直接就先调用了chunk_alloc函数,暂时不看chunk_alloc的动作,假设内部已经调整好了内存。返回一个chunk。
如果nobjs的大小为1,就直接返回chunk,也就是说,如果只分配了一个小块,就直接返回这个块。
否则的话,找到n对应的那个链表。然后将获得的chunk切分为n的大小,并连接起来。注意:这里的n已经调整为8的倍数了。
下面看chunk_alloc是怎么进行分配的。
char* __default_alloc_template::chunk_alloc(size_t size, int& nobjs)
{
char * result;
size_t total_bytes = size * nobjs;
size_t bytes_left = end_free - start_free;
if (bytes_left >= total_bytes) {//如果空间足够,直接返回,并调整空闲池。
result = start_free;
start_free += total_bytes;
return(result);
} else if (bytes_left >= size) {//空间不是足够,但是够一个以上的size。
nobjs = bytes_left/size;
total_bytes = size * nobjs;
result = start_free;
start_free += total_bytes;
return(result);
}
else
{
size_t bytes_to_get = 2 * total_bytes + ROUND_UP(heap_size >> 4);
// Try to make use of the left-over piece.
//回收空闲池中的碎片。
if (bytes_left > 0) {
obj * __VOLATILE * my_free_list =
free_list + FREELIST_INDEX(bytes_left);
((obj *)start_free) -> free_list_link = *my_free_list;
*my_free_list = (obj *)start_free;
}
//尝试从系统中获取所需空间。
start_free = (char *)malloc(bytes_to_get);
if (0 == start_free) {
int i;
obj * __VOLATILE * my_free_list, *p;
// Try to make do with what we have. That can't
// hurt. We do not try smaller requests, since that tends
// to result in disaster on multi-process machines.
//如果从系统中请求不到,这个时候从 free_list中更大的区块中获取区块。
for (i = size; i <= __MAX_BYTES; i += __ALIGN) {
my_free_list = free_list + FREELIST_INDEX(i);
p = *my_free_list;
if (0 != p) {
*my_free_list = p -> free_list_link;
start_free = (char *)p;
end_free = start_free + i;
return(chunk_alloc(size, nobjs));
// Any leftover piece will eventually make it to the
// right free list.
}
}
//如果临近的更大区块,获取不到。再次尝试malloc_alloc 的 allocate调用,这个函数会会调用用户定义的内存不足处理函数,
//用户可能会尝试去施放一些暂时可以施放的空间。
end_free = 0; // In case of exception.
start_free = (char *)malloc_alloc::allocate(bytes_to_get);
// This should either throw an
// exception or remedy the situation. Thus we assume it
// succeeded.
}
heap_size += bytes_to_get;
end_free = start_free + bytes_to_get;
return(chunk_alloc(size, nobjs));
}
}
flow:这里的start_free, end_free。这里称为:reserve_space 区间就是空闲空间,尚未被切分的空间。与free_list中挂载的链表但未使用的节点不是同一个东西。
1.如果reserve_space空间足够大于 total_bytes,20个n 的大小。