Skip to content

gh-158585: [WIP] Add freelist to bytes #158657

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
vstinner wants to merge 1 commit into from
Closed

gh-158585: [WIP] Add freelist to bytes #158657

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions Include/internal/pycore_freelist_state.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ extern "C" {
#endif

# define PyTuple_MAXSAVESIZE 20 // Largest tuple to save on freelist
# define PyBytes_FREELIST_BUCKETS 8
# define Py_tuple_MAXFREELIST 2000 // Maximum number of tuples of each size to save
# define Py_lists_MAXFREELIST 80
# define Py_list_iters_MAXFREELIST 10
Expand All @@ -28,6 +29,7 @@ extern "C" {
# define Py_object_stack_chunks_MAXFREELIST 4
# define Py_unicode_writers_MAXFREELIST 1
# define Py_bytes_writers_MAXFREELIST 1
# define Py_bytes_MAXFREELIST 20
# define Py_pycfunctionobject_MAXFREELIST 16
# define Py_pycmethodobject_MAXFREELIST 16
# define Py_pymethodobjects_MAXFREELIST 20
Expand Down Expand Up @@ -63,6 +65,7 @@ struct _Py_freelists {
struct _Py_freelist object_stack_chunks;
struct _Py_freelist unicode_writers;
struct _Py_freelist bytes_writers;
struct _Py_freelist bytes[PyBytes_FREELIST_BUCKETS];
struct _Py_freelist pycfunctionobject;
struct _Py_freelist pycmethodobject;
struct _Py_freelist pymethodobjects;
Expand Down
85 changes: 55 additions & 30 deletions Objects/bytesobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,19 @@ class bytes "PyBytesObject *" "&PyBytes_Type"
#include "clinic/bytesobject.c.h"

#define PyBytesObject_SIZE _PyBytesObject_SIZE
#define FREELIST_MAX_SIZE 255
#define PyBytes_FREELIST_BUCKET(size) ((size) / 32)

static inline Py_ssize_t
PyBytes_FREELIST_ALLOC(Py_ssize_t size)
{
if (size <= FREELIST_MAX_SIZE) {
return (PyBytes_FREELIST_BUCKET(size) * 32 + 31);
}
else {
return size;
}
}

/* Forward declaration */
static void* _PyBytesWriter_ResizeAndUpdatePointer(PyBytesWriter *writer,
Expand Down Expand Up @@ -116,10 +129,28 @@ _PyBytes_FromSize(Py_ssize_t size, int use_calloc)
}

/* Inline PyObject_NewVar */
if (use_calloc)
op = (PyBytesObject *)PyObject_Calloc(1, PyBytesObject_SIZE + size);
else
op = (PyBytesObject *)PyObject_Malloc(PyBytesObject_SIZE + size);
if (size <= FREELIST_MAX_SIZE) {
Py_ssize_t alloc = PyBytes_FREELIST_ALLOC(size);
Py_ssize_t bucket = PyBytes_FREELIST_BUCKET(size);
op = _Py_FREELIST_POP_MEM(bytes[bucket]);
if (op != NULL) {
if (use_calloc) {
memset(op, 0, PyBytesObject_SIZE + alloc);
}
}
else {
if (use_calloc)
op = (PyBytesObject *)PyObject_Calloc(1, PyBytesObject_SIZE + alloc);
else
op = (PyBytesObject *)PyObject_Malloc(PyBytesObject_SIZE + alloc);
}
}
else {
if (use_calloc)
op = (PyBytesObject *)PyObject_Calloc(1, PyBytesObject_SIZE + size);
else
op = (PyBytesObject *)PyObject_Malloc(PyBytesObject_SIZE + size);
}
if (op == NULL) {
return PyErr_NoMemory();
}
Expand Down Expand Up @@ -165,11 +196,6 @@ PyBytes_FromString(const char *str)

assert(str != NULL);
size = strlen(str);
if (size > PY_SSIZE_T_MAX - PyBytesObject_SIZE) {
PyErr_SetString(PyExc_OverflowError,
"byte string is too long");
return NULL;
}

if (size == 0) {
return bytes_get_empty();
Expand All @@ -179,12 +205,10 @@ PyBytes_FromString(const char *str)
}

/* Inline PyObject_NewVar */
op = (PyBytesObject *)PyObject_Malloc(PyBytesObject_SIZE + size);
op = (PyBytesObject *)_PyBytes_FromSize(size, 0);
if (op == NULL) {
return PyErr_NoMemory();
}
_PyObject_InitVar((PyVarObject*)op, &PyBytes_Type, size);
set_ob_shash(op, -1);
memcpy(op->ob_sval, str, size+1);
return (PyObject *) op;
}
Expand Down Expand Up @@ -1604,19 +1628,10 @@ _PyBytes_Repeat(PyObject *self, Py_ssize_t n)
if (size == Py_SIZE(a) && PyBytes_CheckExact(a)) {
return Py_NewRef(a);
}
size_t nbytes = (size_t)size;
if (nbytes + PyBytesObject_SIZE <= nbytes) {
PyErr_SetString(PyExc_OverflowError,
"repeated bytes are too long");
return NULL;
}
PyBytesObject *op = PyObject_Malloc(PyBytesObject_SIZE + nbytes);
PyBytesObject *op = (PyBytesObject *)_PyBytes_FromSize(size, 0);
if (op == NULL) {
return PyErr_NoMemory();
}
_PyObject_InitVar((PyVarObject*)op, &PyBytes_Type, size);
set_ob_shash(op, -1);
op->ob_sval[size] = '\0';

_PyBytes_RepeatBuffer(op->ob_sval, size, a->ob_sval, Py_SIZE(a));

Expand Down Expand Up @@ -3212,28 +3227,36 @@ _PyBytes_CheckOverflow(PyObject *self, void *addr, const char *type_name)
type_name, addr, size);
}
}
#endif


static void
bytes_dealloc(PyObject *op)
{
PyBytesObject *self = _PyBytes_CAST(op);
PyTypeObject *type = Py_TYPE(self);
Py_ssize_t size = PyBytes_GET_SIZE(self);
#ifdef Py_DEBUG
_PyBytes_CheckOverflow(op, op, "bytes");
Py_TYPE(self)->tp_free((PyObject *)self);
}
#endif
if (size <= FREELIST_MAX_SIZE && type == &PyBytes_Type) {
Py_ssize_t bucket = PyBytes_FREELIST_BUCKET(size);
if (!_Py_FREELIST_PUSH(bytes[bucket], op, Py_bytes_MAXFREELIST)) {
PyObject_Free(op);
}
}
else {
type->tp_free((PyObject *)self);
}
}


PyTypeObject PyBytes_Type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"bytes",
PyBytesObject_SIZE,
sizeof(char),
#ifdef Py_DEBUG
bytes_dealloc, /* tp_dealloc */
#else
0, /* tp_dealloc */
#endif
0, /* tp_vectorcall_offset */
0, /* tp_getattr */
0, /* tp_setattr */
Expand Down Expand Up @@ -3377,7 +3400,9 @@ bytes_resize_inplace(PyObject **pv, Py_ssize_t newsize)
// Only mutable bytes can be resized in-place
assert(_PyBytes_IsMutable(v));

if ((size_t)newsize > (size_t)PY_SSIZE_T_MAX - PyBytesObject_SIZE) {
#define FREELIST_MAX_SIZE 255
Py_ssize_t alloc = PyBytes_FREELIST_ALLOC(newsize);
if ((size_t)alloc > (size_t)PY_SSIZE_T_MAX - PyBytesObject_SIZE) {
PyErr_SetString(PyExc_OverflowError,
"byte string is too large");
return -1;
Expand All @@ -3388,7 +3413,7 @@ bytes_resize_inplace(PyObject **pv, Py_ssize_t newsize)
#endif
_PyReftracerTrack(v, PyRefTracer_DESTROY);

PyObject *result = PyObject_Realloc(v, PyBytesObject_SIZE + newsize);
PyObject *result = PyObject_Realloc(v, PyBytesObject_SIZE + alloc);
if (result == NULL) {
#ifdef Py_TRACE_REFS
_Py_AddToAllObjects(v);
Expand Down
3 changes: 3 additions & 0 deletions Objects/object.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -952,6 +952,9 @@ _PyObject_ClearFreeLists(struct _Py_freelists *freelists, int is_finalization)
}
clear_freelist(&freelists->unicode_writers, is_finalization, PyMem_Free);
clear_freelist(&freelists->bytes_writers, is_finalization, PyMem_Free);
for (Py_ssize_t i = 0; i < PyBytes_FREELIST_BUCKETS; i++) {
clear_freelist(&freelists->bytes[i], is_finalization, PyObject_Free);
}
clear_freelist(&freelists->ints, is_finalization, free_object);
clear_freelist(&freelists->pycfunctionobject, is_finalization, PyObject_GC_Del);
clear_freelist(&freelists->pycmethodobject, is_finalization, PyObject_GC_Del);
Expand Down
Loading