# 关键源码
# INDEX2SIZE(I)
是一个宏，用于将类别转化为块大小。
#define INDEX2SIZE(I) (((uint)(I) + 1) << ALIGNMENT_SHIFT)
# pool_header
/* Pool for small blocks. */
struct pool_header {
union { block *_padding;
uint count; } ref; /* number of allocated blocks */
block *freeblock; /* pool's free list head */
struct pool_header *nextpool; /* next pool of this size class */
struct pool_header *prevpool; /* previous pool "" */
uint arenaindex; /* index into arenas of base adr */
uint szidx; /* block size class index */
uint nextoffset; /* bytes to virgin block */
uint maxnextoffset; /* largest valid nextoffset */
};
# _gc_head
typedef union _gc_head {
struct {
union _gc_head *gc_next;
union _gc_head *gc_prev;
Py_ssize_t gc_refs;
} gc;
long double dummy; /* force worst-case alignment */
// malloc returns memory block aligned for any built-in types and
// long double is the largest standard C type.
// On amd64 linux, long double requires 16 byte alignment.
// See bpo-27987 for more discussion.
} PyGC_Head;
# gc_generation
struct gc_generation {
PyGC_Head head;
int threshold; /* collection threshold */
int count; /* count of allocations or collections of younger
generations */
};
# collect
static Py_ssize_t
collect(int generation, Py_ssize_t *n_collected, Py_ssize_t *n_uncollectable,
int nofail)
{
int i;
Py_ssize_t m = 0; /* # objects collected */
Py_ssize_t n = 0; /* # unreachable objects that couldn't be collected */
PyGC_Head *young; /* the generation we are examining */
PyGC_Head *old; /* next older generation */
PyGC_Head unreachable; /* non-problematic unreachable trash */
PyGC_Head finalizers; /* objects with, & reachable from, __del__ */
PyGC_Head *gc;
_PyTime_t t1 = 0; /* initialize to prevent a compiler warning */
struct gc_generation_stats *stats = &_PyRuntime.gc.generation_stats[generation];
if (_PyRuntime.gc.debug & DEBUG_STATS) {
PySys_WriteStderr("gc: collecting generation %d...\n",
generation);
PySys_WriteStderr("gc: objects in each generation:");
for (i = 0; i < NUM_GENERATIONS; i++)
PySys_FormatStderr(" %zd",
gc_list_size(GEN_HEAD(i)));
PySys_WriteStderr("\ngc: objects in permanent generation: %zd",
gc_list_size(&_PyRuntime.gc.permanent_generation.head));
t1 = _PyTime_GetMonotonicClock();
PySys_WriteStderr("\n");
}
if (PyDTrace_GC_START_ENABLED())
PyDTrace_GC_START(generation);
/* update collection and allocation counters */
if (generation+1 < NUM_GENERATIONS)
_PyRuntime.gc.generations[generation+1].count += 1;
for (i = 0; i <= generation; i++)
_PyRuntime.gc.generations[i].count = 0;
/* merge younger generations with one we are currently collecting */
for (i = 0; i < generation; i++) {
gc_list_merge(GEN_HEAD(i), GEN_HEAD(generation));
}
/* handy references */
young = GEN_HEAD(generation);
if (generation < NUM_GENERATIONS-1)
old = GEN_HEAD(generation+1);
else
old = young;
/* Using ob_refcnt and gc_refs, calculate which objects in the
* container set are reachable from outside the set (i.e., have a
* refcount greater than 0 when all the references within the
* set are taken into account).
*/
update_refs(young);
subtract_refs(young);
/* Leave everything reachable from outside young in young, and move
* everything else (in young) to unreachable.
* NOTE: This used to move the reachable objects into a reachable
* set instead. But most things usually turn out to be reachable,
* so it's more efficient to move the unreachable things.
*/
gc_list_init(&unreachable);
move_unreachable(young, &unreachable);
/* Move reachable objects to next generation. */
if (young != old) {
if (generation == NUM_GENERATIONS - 2) {
_PyRuntime.gc.long_lived_pending += gc_list_size(young);
}
gc_list_merge(young, old);
}
else {
/* We only untrack dicts in full collections, to avoid quadratic
dict build-up. See issue #14775. */
untrack_dicts(young);
_PyRuntime.gc.long_lived_pending = 0;
_PyRuntime.gc.long_lived_total = gc_list_size(young);
}
/* All objects in unreachable are trash, but objects reachable from
* legacy finalizers (e.g. tp_del) can't safely be deleted.
*/
gc_list_init(&finalizers);
move_legacy_finalizers(&unreachable, &finalizers);
/* finalizers contains the unreachable objects with a legacy finalizer;
* unreachable objects reachable *from* those are also uncollectable,
* and we move those into the finalizers list too.
*/
move_legacy_finalizer_reachable(&finalizers);
/* Collect statistics on collectable objects found and print
* debugging information.
*/
for (gc = unreachable.gc.gc_next; gc != &unreachable;
gc = gc->gc.gc_next) {
m++;
if (_PyRuntime.gc.debug & DEBUG_COLLECTABLE) {
debug_cycle("collectable", FROM_GC(gc));
}
}
/* Clear weakrefs and invoke callbacks as necessary. */
m += handle_weakrefs(&unreachable, old);
/* Call tp_finalize on objects which have one. */
finalize_garbage(&unreachable);
if (check_garbage(&unreachable)) {
revive_garbage(&unreachable);
gc_list_merge(&unreachable, old);
}
else {
/* Call tp_clear on objects in the unreachable set. This will cause
* the reference cycles to be broken. It may also cause some objects
* in finalizers to be freed.
*/
delete_garbage(&unreachable, old);
}
/* Collect statistics on uncollectable objects found and print
* debugging information. */
for (gc = finalizers.gc.gc_next;
gc != &finalizers;
gc = gc->gc.gc_next) {
n++;
if (_PyRuntime.gc.debug & DEBUG_UNCOLLECTABLE)
debug_cycle("uncollectable", FROM_GC(gc));
}
if (_PyRuntime.gc.debug & DEBUG_STATS) {
_PyTime_t t2 = _PyTime_GetMonotonicClock();
if (m == 0 && n == 0)
PySys_WriteStderr("gc: done");
else
PySys_FormatStderr(
"gc: done, %zd unreachable, %zd uncollectable",
n+m, n);
PySys_WriteStderr(", %.4fs elapsed\n",
_PyTime_AsSecondsDouble(t2 - t1));
}
/* Append instances in the uncollectable set to a Python
* reachable list of garbage. The programmer has to deal with
* this if they insist on creating this type of structure.
*/
handle_legacy_finalizers(&finalizers, old);
/* Clear free list only during the collection of the highest
* generation */
if (generation == NUM_GENERATIONS-1) {
clear_freelists();
}
if (PyErr_Occurred()) {
if (nofail) {
PyErr_Clear();
}
else {
if (gc_str == NULL)
gc_str = PyUnicode_FromString("garbage collection");
PyErr_WriteUnraisable(gc_str);
Py_FatalError("unexpected exception during garbage collection");
}
}
/* Update stats */
if (n_collected)
*n_collected = m;
if (n_uncollectable)
*n_uncollectable = n;
stats->collections++;
stats->collected += m;
stats->uncollectable += n;
if (PyDTrace_GC_DONE_ENABLED())
PyDTrace_GC_DONE(n+m);
return n+m;
}
# update_refs
static void
update_refs(PyGC_Head *containers)
{
PyGC_Head *gc = containers->gc.gc_next;
for (; gc != containers; gc = gc->gc.gc_next) {
assert(_PyGCHead_REFS(gc) == GC_REACHABLE);
_PyGCHead_SET_REFS(gc, Py_REFCNT(FROM_GC(gc)));
/* Python's cyclic gc should never see an incoming refcount
* of 0: if something decref'ed to 0, it should have been
* deallocated immediately at that time.
* Possible cause (if the assert triggers): a tp_dealloc
* routine left a gc-aware object tracked during its teardown
* phase, and did something-- or allowed something to happen --
* that called back into Python. gc can trigger then, and may
* see the still-tracked dying object. Before this assert
* was added, such mistakes went on to allow gc to try to
* delete the object again. In a debug build, that caused
* a mysterious segfault, when _Py_ForgetReference tried
* to remove the object from the doubly-linked list of all
* objects a second time. In a release build, an actual
* double deallocation occurred, which leads to corruption
* of the allocator's internal bookkeeping pointers. That's
* so serious that maybe this should be a release-build
* check instead of an assert?
*/
assert(_PyGCHead_REFS(gc) != 0);
}
}
内存泄漏诊断 →