Skip to content

Commit daf8e02

Browse files
cmaloneycmaloney
committed
gh-139871: Update bytearray to contain PyBytesObject
This sets up so the bytes can be "taken" as a byes object without requiring a copy. I ran pyperformance (results below) and don't see any major speedups or slowdowns with this; all seems to be in the noise of my machine. ------ pyperformance compare main.json bytearray_bytes.json -O table main.json ========= Performance version: 1.11.0 Report on Linux-6.17.1-arch1-1-x86_64-with-glibc2.42 Number of logical CPUs: 32 Start date: 2025-10-14 00:55:52.519236 End date: 2025-10-14 02:23:01.308400 bytearray_bytes.json ==================== Performance version: 1.11.0 Report on Linux-6.17.1-arch1-1-x86_64-with-glibc2.42 Number of logical CPUs: 32 Start date: 2025-10-13 23:22:29.928152 End date: 2025-10-14 00:49:34.467284 +----------------------------------+-----------+----------------------+--------------+------------------------+ | Benchmark | main.json | bytearray_bytes.json | Change | Significance | +==================================+===========+======================+==============+========================+ | 2to3 | 137 ms | 136 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_generators | 193 ms | 195 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_cpu_io_mixed | 285 ms | 286 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_cpu_io_mixed_tg | 289 ms | 290 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager | 50.4 ms | 51.5 ms | 1.02x slower | Significant (t=-10.40) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_cpu_io_mixed | 223 ms | 225 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_cpu_io_mixed_tg | 263 ms | 264 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_io | 370 ms | 372 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_io_tg | 380 ms | 384 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_memoization | 125 ms | 126 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_memoization_tg | 161 ms | 162 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_eager_tg | 125 ms | 125 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_io | 366 ms | 360 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_io_tg | 359 ms | 361 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_memoization | 177 ms | 181 ms | 1.02x slower | Significant (t=-9.20) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_memoization_tg | 188 ms | 189 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_none | 151 ms | 151 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | async_tree_none_tg | 150 ms | 151 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | asyncio_tcp | 182 ms | 161 ms | 1.13x faster | Significant (t=32.85) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | asyncio_tcp_ssl | 548 ms | 553 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | asyncio_websockets | 342 ms | 339 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | bench_mp_pool | 7.12 ms | 7.08 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | bench_thread_pool | 818 us | 819 us | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | bpe_tokeniser | 2.10 sec | 2.09 sec | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | chaos | 27.9 ms | 28.0 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | comprehensions | 7.45 us | 7.24 us | 1.03x faster | Significant (t=3.27) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | connected_components | 308 ms | 309 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | coroutines | 11.1 ms | 11.2 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | coverage | 33.6 ms | 34.1 ms | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | create_gc_cycles | 1.16 ms | 1.16 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | crypto_pyaes | 37.1 ms | 35.6 ms | 1.04x faster | Significant (t=10.63) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | dask | 347 ms | 351 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | deepcopy | 118 us | 117 us | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | deepcopy_memo | 12.8 us | 12.7 us | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | deepcopy_reduce | 1.32 us | 1.34 us | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | deltablue | 1.65 ms | 1.64 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | django_template | 17.9 ms | 17.8 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | docutils | 1.19 sec | 1.20 sec | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | dulwich_log | 19.5 ms | 19.7 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | fannkuch | 184 ms | 181 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | float | 37.1 ms | 36.7 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | gc_traversal | 3.04 ms | 2.84 ms | 1.07x faster | Significant (t=19.48) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | generators | 15.9 ms | 15.3 ms | 1.04x faster | Significant (t=7.03) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | genshi_text | 11.3 ms | 11.2 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | genshi_xml | 25.5 ms | 25.5 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | go | 57.6 ms | 56.7 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | hexiom | 2.92 ms | 2.88 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | html5lib | 26.0 ms | 26.5 ms | 1.02x slower | Significant (t=-9.20) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | json_dumps | 4.48 ms | 4.44 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | json_loads | 11.7 us | 11.7 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | k_core | 1.41 sec | 1.42 sec | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | logging_format | 3.27 us | 3.30 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | logging_silent | 45.5 ns | 45.8 ns | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | logging_simple | 3.02 us | 3.01 us | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | mako | 6.02 ms | 6.03 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | many_optionals | 473 us | 478 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | mdp | 587 ms | 578 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | meteor_contest | 50.2 ms | 50.5 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | nbody | 54.6 ms | 52.4 ms | 1.04x faster | Significant (t=10.72) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | nqueens | 41.7 ms | 40.4 ms | 1.03x faster | Significant (t=6.79) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pathlib | 9.77 ms | 9.73 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pickle | 5.99 us | 6.01 us | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pickle_dict | 12.5 us | 12.8 us | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pickle_list | 1.98 us | 1.96 us | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pickle_pure_python | 149 us | 150 us | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pidigits | 111 ms | 115 ms | 1.03x slower | Significant (t=-18.53) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pprint_pformat | 737 ms | 748 ms | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pprint_safe_repr | 362 ms | 369 ms | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | pyflate | 211 ms | 205 ms | 1.03x faster | Significant (t=7.43) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | python_startup | 7.88 ms | 7.88 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | python_startup_no_site | 4.72 ms | 4.76 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | raytrace | 130 ms | 128 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | regex_compile | 50.0 ms | 50.2 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | regex_dna | 101 ms | 103 ms | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | regex_effbot | 1.72 ms | 1.77 ms | 1.03x slower | Significant (t=-26.42) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | regex_v8 | 12.5 ms | 12.3 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | richards | 20.4 ms | 20.0 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | richards_super | 23.4 ms | 22.8 ms | 1.03x faster | Significant (t=11.36) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | scimark_fft | 154 ms | 153 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | scimark_lu | 55.4 ms | 57.0 ms | 1.03x slower | Significant (t=-5.67) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | scimark_monte_carlo | 32.8 ms | 32.8 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | scimark_sor | 57.8 ms | 56.9 ms | 1.02x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | scimark_sparse_mat_mult | 2.75 ms | 2.76 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | shortest_path | 316 ms | 318 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | spectral_norm | 47.7 ms | 51.6 ms | 1.08x slower | Significant (t=-2.01) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sphinx | 465 ms | 467 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sqlglot_v2_normalize | 50.3 ms | 50.2 ms | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sqlglot_v2_optimize | 24.2 ms | 24.4 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sqlglot_v2_parse | 576 us | 572 us | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sqlglot_v2_transpile | 724 us | 722 us | 1.00x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sqlite_synth | 1.14 us | 1.15 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | subparsers | 20.6 ms | 20.7 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sympy_expand | 181 ms | 184 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sympy_integrate | 8.54 ms | 8.55 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sympy_str | 103 ms | 105 ms | 1.02x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | sympy_sum | 55.9 ms | 56.0 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | telco | 3.39 ms | 3.34 ms | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | tomli_loads | 971 ms | 982 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | typing_runtime_protocols | 73.2 us | 73.6 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | unpack_sequence | 25.2 ns | 23.0 ns | 1.10x faster | Significant (t=7.03) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | unpickle | 6.99 us | 7.05 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | unpickle_list | 2.07 us | 2.10 us | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | unpickle_pure_python | 105 us | 104 us | 1.01x faster | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | xml_etree_generate | 40.5 ms | 40.7 ms | 1.00x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | xml_etree_iterparse | 49.7 ms | 50.4 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+ | xml_etree_parse | 77.2 ms | 79.1 ms | 1.02x slower | Significant (t=-16.14) | +----------------------------------+-----------+----------------------+--------------+------------------------+ | xml_etree_process | 29.5 ms | 29.8 ms | 1.01x slower | Not significant | +----------------------------------+-----------+----------------------+--------------+------------------------+
1 parent 8e0bf4f commit daf8e02

File tree

3 files changed

+23
-18
lines changed

3 files changed

+23
-18
lines changed

‎Include/cpython/bytearrayobject.h‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@ typedef struct {
99
char *ob_bytes; /* Physical backing buffer */
1010
char *ob_start; /* Logical start inside ob_bytes */
1111
Py_ssize_t ob_exports; /* How many buffer exports */
12+
PyObject *ob_bytes_object; /* PyBytes for zero-copy bytes conversion */
1213
} PyByteArrayObject;
1314

1415
PyAPI_DATA(char) _PyByteArray_empty_string[];

‎Lib/test/test_sys.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1583,7 +1583,7 @@ def test_objecttypes(self):
15831583
samples = [b'', b'u'*100000]
15841584
for sample in samples:
15851585
x = bytearray(sample)
1586-
check(x, vsize('n2Pi') + x.__alloc__())
1586+
check(x, vsize('n2PiP') + x.__alloc__())
15871587
# bytearray_iterator
15881588
check(iter(bytearray()), size('nP'))
15891589
# bytes

‎Objects/bytearrayobject.c‎

Lines changed: 21 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -141,22 +141,26 @@ PyByteArray_FromStringAndSize(const char *bytes, Py_ssize_t size)
141141
}
142142

143143
new = PyObject_New(PyByteArrayObject, &PyByteArray_Type);
144-
if (new == NULL)
144+
if (new == NULL) {
145145
return NULL;
146+
}
146147

147148
if (size == 0) {
149+
new->ob_bytes_object = NULL;
148150
new->ob_bytes = NULL;
149151
alloc = 0;
150152
}
151153
else {
152154
alloc = size + 1;
153-
new->ob_bytes = PyMem_Malloc(alloc);
155+
new->ob_bytes_object = PyBytes_FromStringAndSize(NULL, alloc);
156+
new->ob_bytes = PyBytes_AsString(new->ob_bytes_object);
154157
if (new->ob_bytes == NULL) {
155158
Py_DECREF(new);
156159
return PyErr_NoMemory();
157160
}
158-
if (bytes != NULL && size > 0)
161+
if (bytes != NULL && size > 0) {
159162
memcpy(new->ob_bytes, bytes, size);
163+
}
160164
new->ob_bytes[size] = '\0'; /* Trailing null byte */
161165
}
162166
Py_SET_SIZE(new, size);
@@ -189,7 +193,6 @@ static int
189193
bytearray_resize_lock_held(PyObject *self, Py_ssize_t requested_size)
190194
{
191195
_Py_CRITICAL_SECTION_ASSERT_OBJECT_LOCKED(self);
192-
void *sval;
193196
PyByteArrayObject *obj = ((PyByteArrayObject *)self);
194197
/* All computations are done unsigned to avoid integer overflows
195198
(see issue #22335). */
@@ -244,25 +247,28 @@ bytearray_resize_lock_held(PyObject *self, Py_ssize_t requested_size)
244247
return -1;
245248
}
246249

250+
/* re-align data to the start of the allocation. */
247251
if (logical_offset > 0) {
248-
sval = PyMem_Malloc(alloc);
249-
if (sval == NULL) {
250-
PyErr_NoMemory();
252+
memmove(obj->ob_bytes, obj->ob_start,
253+
Py_MIN(requested_size, Py_SIZE(self)));
254+
}
255+
256+
if (obj->ob_bytes_object == NULL) {
257+
obj->ob_bytes_object = PyBytes_FromStringAndSize(NULL, alloc);
258+
if (obj->ob_bytes_object == NULL) {
251259
return -1;
252260
}
253-
memcpy(sval, PyByteArray_AS_STRING(self),
254-
Py_MIN((size_t)requested_size, (size_t)Py_SIZE(self)));
255-
PyMem_Free(obj->ob_bytes);
256261
}
257262
else {
258-
sval = PyMem_Realloc(obj->ob_bytes, alloc);
259-
if (sval == NULL) {
260-
PyErr_NoMemory();
263+
if (_PyBytes_Resize(&obj->ob_bytes_object, alloc) == -1) {
264+
Py_SET_SIZE(self, 0);
265+
obj->ob_bytes = obj->ob_start = NULL;
266+
FT_ATOMIC_STORE_SSIZE_RELAXED(obj->ob_alloc, 0);
261267
return -1;
262268
}
263269
}
264270

265-
obj->ob_bytes = obj->ob_start = sval;
271+
obj->ob_bytes = obj->ob_start = PyBytes_AS_STRING(obj->ob_bytes_object);
266272
Py_SET_SIZE(self, size);
267273
FT_ATOMIC_STORE_SSIZE_RELAXED(obj->ob_alloc, alloc);
268274
obj->ob_bytes[size] = '\0'; /* Trailing null byte */
@@ -1169,9 +1175,7 @@ bytearray_dealloc(PyObject *op)
11691175
"deallocated bytearray object has exported buffers");
11701176
PyErr_Print();
11711177
}
1172-
if (self->ob_bytes != 0) {
1173-
PyMem_Free(self->ob_bytes);
1174-
}
1178+
Py_CLEAR(self->ob_bytes_object);
11751179
Py_TYPE(self)->tp_free((PyObject *)self);
11761180
}
11771181

0 commit comments

Comments
 (0)