我们将判断小集合如何使用216个字节.
首先，用下面的C struct 来表示一个set的对象.
typedef struct {
PyObject_HEAD
Py_ssize_t fill; /* Number active and dummy entries*/
Py_ssize_t used; /* Number active entries */
/* The table contains mask + 1 slots, and that's a power of 2.
* We store the mask instead of the size because the mask is more
* frequently needed.
*/
Py_ssize_t mask;
/* The table points to a fixed-size smalltable for small tables
* or to additional malloc'ed memory for bigger tables.
* The table pointer is never NULL which saves us from repeated
* runtime null-tests.
*/
setentry *table;
Py_hash_t hash; /* Only used by frozenset objects */
Py_ssize_t finger; /* Search finger for pop() */
setentry smalltable[PySet_MINSIZE];
PyObject *weakreflist; /* List of weak references */
} PySetObject;
现在记住，getsizeof() calls the object’s __sizeof__ method and adds an additional garbage collector overhead if the object is managed by the garbage collector.
好的，set implements the __sizeof__个.
static PyObject *
set_sizeof(PySetObject *so, PyObject *Py_UNUSED(ignored))
{
Py_ssize_t res;
res = _PyObject_SIZE(Py_TYPE(so));
if (so->table != so->smalltable)
res = res + (so->mask + 1) * sizeof(setentry);
return PyLong_FromSsize_t(res);
}
现在让我们判断一下线路
res = _PyObject_SIZE(Py_TYPE(so));
_PyObject_SIZE is just a macro，这将扩展到(typeobj)->tp_basicsize.
#define _PyObject_SIZE(typeobj) ( (typeobj)->tp_basicsize )
这段代码实质上是试图访问tp_basicsize slot to get the size in bytes of instances of the type，它只有sizeof(PySetObject) in case of set.
PyTypeObject PySet_Type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"set", /* tp_name */
sizeof(PySetObject), /* tp_basicsize */
0, /* tp_itemsize */
# Skipped rest of the code for brevity.
我对set_sizeofC函数进行了以下更改.
static PyObject *
set_sizeof(PySetObject *so, PyObject *Py_UNUSED(ignored))
{
Py_ssize_t res;
unsigned long py_object_head_size = sizeof(so->ob_base); // Because PyObject_HEAD expands to PyObject ob_base;
unsigned long fill_size = sizeof(so->fill);
unsigned long used_size = sizeof(so->used);
unsigned long mask_size = sizeof(so->mask);
unsigned long table_size = sizeof(so->table);
unsigned long hash_size = sizeof(so->hash);
unsigned long finger_size = sizeof(so->finger);
unsigned long smalltable_size = sizeof(so->smalltable);
unsigned long weakreflist_size = sizeof(so->weakreflist);
int is_using_fixed_size_smalltables = so->table == so->smalltable;
printf("| PySetObject Fields | Size(bytes) |\n");
printf("|------------------------------------|\n");
printf("| PyObject_HEAD | '%zu' |\n", py_object_head_size);
printf("| fill | '%zu' |\n", fill_size);
printf("| used | '%zu' |\n", used_size);
printf("| mask | '%zu' |\n", mask_size);
printf("| table | '%zu' |\n", table_size);
printf("| hash | '%zu' |\n", hash_size);
printf("| finger | '%zu' |\n", finger_size);
printf("| smalltable | '%zu' |\n", smalltable_size);
printf("| weakreflist | '%zu' |\n", weakreflist_size);
printf("-------------------------------------|\n");
printf("| Total | '%zu' |\n", py_object_head_size+fill_size+used_size+mask_size+table_size+hash_size+finger_size+smalltable_size+weakreflist_size);
printf("\n");
printf("Total size of PySetObject '%zu' bytes\n", sizeof(PySetObject));
printf("Is Using fixed size smalltables: '%s'\n", is_using_fixed_size_smalltables ? "True": "False");
res = _PyObject_SIZE(Py_TYPE(so));
if (so->table != so->smalltable)
res = res + (so->mask + 1) * sizeof(setentry);
return PyLong_FromSsize_t(res);
}
编译和运行这些更改为我提供了
>>> import sys
>>>
>>> empty_set = set()
>>> sys.getsizeof(empty_set)
| PySetObject Fields | Size(bytes) |
|------------------------------------|
| PyObject_HEAD | '16' |
| fill | '8' |
| used | '8' |
| mask | '8' |
| table | '8' |
| hash | '8' |
| finger | '8' |
| smalltable | '128' |
| weakreflist | '8' |
-------------------------------------|
| Total | '200' |
Total size of PySetObject '200' bytes
Is Using fixed size smalltables: 'True'
216
返回值是216字节，因为sys.getsize add 16 bytes of GC overhead.
但这里需要注意的是这一行.
| smalltable | '128' |
因为对于较小的表(在第一次调整大小之前)，so->table只有a reference到fixed size(8) so->smalltable(没有错误分配的内存)，所以sizeof(PySetObject)足以获得大小，因为它还包括存储大小(128(16(size of setentry) * 8)).
现在，当调整大小时会发生什么.它构造entirely new table(malloc'ed)并使用so->smalltables中的that table instead，这意味着已调整大小的集合还执行128字节的重载(大小为fixed size small table)以及Malloc‘ed so->table的大小.
else {
newtable = PyMem_NEW(setentry, newsize);
if (newtable == NULL) {
PyErr_NoMemory();
return -1;
}
}
/* Make the set empty, using the new table. */
assert(newtable != oldtable);
memset(newtable, 0, sizeof(setentry) * newsize);
so->mask = newsize - 1;
so->table = newtable;