1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
#ifndef Py_INTERNAL_PYMEM_H
#define Py_INTERNAL_PYMEM_H
#ifdef __cplusplus
extern "C" {
#endif
#ifndef Py_BUILD_CORE
# error "this header requires Py_BUILD_CORE define"
#endif
#include "objimpl.h"
#include "pymem.h"
/* GC runtime state */
/* If we change this, we need to change the default value in the
signature of gc.collect. */
#define NUM_GENERATIONS 3
/*
NOTE: about the counting of long-lived objects.
To limit the cost of garbage collection, there are two strategies;
- make each collection faster, e.g. by scanning fewer objects
- do less collections
This heuristic is about the latter strategy.
In addition to the various configurable thresholds, we only trigger a
full collection if the ratio
long_lived_pending / long_lived_total
is above a given value (hardwired to 25%).
The reason is that, while "non-full" collections (i.e., collections of
the young and middle generations) will always examine roughly the same
number of objects -- determined by the aforementioned thresholds --,
the cost of a full collection is proportional to the total number of
long-lived objects, which is virtually unbounded.
Indeed, it has been remarked that doing a full collection every
<constant number> of object creations entails a dramatic performance
degradation in workloads which consist in creating and storing lots of
long-lived objects (e.g. building a large list of GC-tracked objects would
show quadratic performance, instead of linear as expected: see issue #4074).
Using the above ratio, instead, yields amortized linear performance in
the total number of objects (the effect of which can be summarized
thusly: "each full garbage collection is more and more costly as the
number of objects grows, but we do fewer and fewer of them").
This heuristic was suggested by Martin von Löwis on python-dev in
June 2008. His original analysis and proposal can be found at:
http://mail.python.org/pipermail/python-dev/2008-June/080579.html
*/
/*
NOTE: about untracking of mutable objects.
Certain types of container cannot participate in a reference cycle, and
so do not need to be tracked by the garbage collector. Untracking these
objects reduces the cost of garbage collections. However, determining
which objects may be untracked is not free, and the costs must be
weighed against the benefits for garbage collection.
There are two possible strategies for when to untrack a container:
i) When the container is created.
ii) When the container is examined by the garbage collector.
Tuples containing only immutable objects (integers, strings etc, and
recursively, tuples of immutable objects) do not need to be tracked.
The interpreter creates a large number of tuples, many of which will
not survive until garbage collection. It is therefore not worthwhile
to untrack eligible tuples at creation time.
Instead, all tuples except the empty tuple are tracked when created.
During garbage collection it is determined whether any surviving tuples
can be untracked. A tuple can be untracked if all of its contents are
already not tracked. Tuples are examined for untracking in all garbage
collection cycles. It may take more than one cycle to untrack a tuple.
Dictionaries containing only immutable objects also do not need to be
tracked. Dictionaries are untracked when created. If a tracked item is
inserted into a dictionary (either as a key or value), the dictionary
becomes tracked. During a full garbage collection (all generations),
the collector will untrack any dictionaries whose contents are not
tracked.
The module provides the python function is_tracked(obj), which returns
the CURRENT tracking status of the object. Subsequent garbage
collections may change the tracking status of the object.
Untracking of certain containers was introduced in issue #4688, and
the algorithm was refined in response to issue #14775.
*/
struct gc_generation {
PyGC_Head head;
int threshold; /* collection threshold */
int count; /* count of allocations or collections of younger
generations */
};
/* Running stats per generation */
struct gc_generation_stats {
/* total number of collections */
Py_ssize_t collections;
/* total number of collected objects */
Py_ssize_t collected;
/* total number of uncollectable objects (put into gc.garbage) */
Py_ssize_t uncollectable;
};
struct _gc_runtime_state {
/* List of objects that still need to be cleaned up, singly linked
* via their gc headers' gc_prev pointers. */
PyObject *trash_delete_later;
/* Current call-stack depth of tp_dealloc calls. */
int trash_delete_nesting;
int enabled;
int debug;
/* linked lists of container objects */
struct gc_generation generations[NUM_GENERATIONS];
PyGC_Head *generation0;
/* a permanent generation which won't be collected */
struct gc_generation permanent_generation;
struct gc_generation_stats generation_stats[NUM_GENERATIONS];
/* true if we are currently running the collector */
int collecting;
/* list of uncollectable objects */
PyObject *garbage;
/* a list of callbacks to be invoked when collection is performed */
PyObject *callbacks;
/* This is the number of objects that survived the last full
collection. It approximates the number of long lived objects
tracked by the GC.
(by "full collection", we mean a collection of the oldest
generation). */
Py_ssize_t long_lived_total;
/* This is the number of objects that survived all "non-full"
collections, and are awaiting to undergo a full collection for
the first time. */
Py_ssize_t long_lived_pending;
};
PyAPI_FUNC(void) _PyGC_Initialize(struct _gc_runtime_state *);
/* Set the memory allocator of the specified domain to the default.
Save the old allocator into *old_alloc if it's non-NULL.
Return on success, or return -1 if the domain is unknown. */
PyAPI_FUNC(int) _PyMem_SetDefaultAllocator(
PyMemAllocatorDomain domain,
PyMemAllocatorEx *old_alloc);
/* Heuristic checking if a pointer value is newly allocated
(uninitialized) or newly freed. The pointer is not dereferenced, only the
pointer value is checked.
The heuristic relies on the debug hooks on Python memory allocators which
fills newly allocated memory with CLEANBYTE (0xCD) and newly freed memory
with DEADBYTE (0xDD). Detect also "untouchable bytes" marked
with FORBIDDENBYTE (0xFD). */
static inline int _PyMem_IsPtrFreed(void *ptr)
{
uintptr_t value = (uintptr_t)ptr;
#if SIZEOF_VOID_P == 8
return (value == (uintptr_t)0xCDCDCDCDCDCDCDCD
|| value == (uintptr_t)0xDDDDDDDDDDDDDDDD
|| value == (uintptr_t)0xFDFDFDFDFDFDFDFD);
#elif SIZEOF_VOID_P == 4
return (value == (uintptr_t)0xCDCDCDCD
|| value == (uintptr_t)0xDDDDDDDD
|| value == (uintptr_t)0xFDFDFDFD);
#else
# error "unknown pointer size"
#endif
}
PyAPI_FUNC(int) _PyMem_GetAllocatorName(
const char *name,
PyMemAllocatorName *allocator);
/* Configure the Python memory allocators.
Pass PYMEM_ALLOCATOR_DEFAULT to use default allocators.
PYMEM_ALLOCATOR_NOT_SET does nothing. */
PyAPI_FUNC(int) _PyMem_SetupAllocators(PyMemAllocatorName allocator);
#ifdef __cplusplus
}
#endif
#endif /* !Py_INTERNAL_PYMEM_H */
|
