bpo-46608: exclude marshalled-frozen data if deep-freezing to save 300 KB space (GH-31074)

This reduces the size of the data segment by **300 KB** of the executable because if the modules are deep-frozen then the marshalled frozen data just wastes space. This was inspired by comment by @gvanrossum in https://github.com/python/cpython/pull/29118#issuecomment-958521863. Note: There is a new option `--deepfreeze-only` in `freeze_modules.py` to change this behavior, it is on be default to save disk space.
```console 
# du -s ./python before
27892   ./python
# du -s ./python after
27524   ./python
```

Automerge-Triggered-By: GH:ericsnowcurrently
This commit is contained in:
Kumar Aditya 2022-02-04 23:27:03 +05:30 committed by GitHub
parent 9b4e3d94a5
commit bf95ff91f2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 87 additions and 84 deletions

View file

@ -39,29 +39,6 @@
#include "pycore_import.h"
/* Includes for frozen modules: */
#include "frozen_modules/importlib._bootstrap.h"
#include "frozen_modules/importlib._bootstrap_external.h"
#include "frozen_modules/zipimport.h"
#include "frozen_modules/abc.h"
#include "frozen_modules/codecs.h"
#include "frozen_modules/io.h"
#include "frozen_modules/_collections_abc.h"
#include "frozen_modules/_sitebuiltins.h"
#include "frozen_modules/genericpath.h"
#include "frozen_modules/ntpath.h"
#include "frozen_modules/posixpath.h"
#include "frozen_modules/os.h"
#include "frozen_modules/site.h"
#include "frozen_modules/stat.h"
#include "frozen_modules/importlib.util.h"
#include "frozen_modules/importlib.machinery.h"
#include "frozen_modules/runpy.h"
#include "frozen_modules/__hello__.h"
#include "frozen_modules/__phello__.h"
#include "frozen_modules/__phello__.ham.h"
#include "frozen_modules/__phello__.ham.eggs.h"
#include "frozen_modules/__phello__.spam.h"
#include "frozen_modules/frozen_only.h"
/* End includes */
#define GET_CODE(name) _Py_get_##name##_toplevel
@ -98,49 +75,47 @@ extern PyObject *_Py_get___phello___spam_toplevel(void);
extern PyObject *_Py_get_frozen_only_toplevel(void);
/* End extern declarations */
/* Note that a negative size indicates a package. */
static const struct _frozen bootstrap_modules[] = {
{"_frozen_importlib", _Py_M__importlib__bootstrap, (int)sizeof(_Py_M__importlib__bootstrap), GET_CODE(importlib__bootstrap)},
{"_frozen_importlib_external", _Py_M__importlib__bootstrap_external, (int)sizeof(_Py_M__importlib__bootstrap_external), GET_CODE(importlib__bootstrap_external)},
{"zipimport", _Py_M__zipimport, (int)sizeof(_Py_M__zipimport), GET_CODE(zipimport)},
{"_frozen_importlib", NULL, 0, false, GET_CODE(importlib__bootstrap)},
{"_frozen_importlib_external", NULL, 0, false, GET_CODE(importlib__bootstrap_external)},
{"zipimport", NULL, 0, false, GET_CODE(zipimport)},
{0, 0, 0} /* bootstrap sentinel */
};
static const struct _frozen stdlib_modules[] = {
/* stdlib - startup, without site (python -S) */
{"abc", _Py_M__abc, (int)sizeof(_Py_M__abc), GET_CODE(abc)},
{"codecs", _Py_M__codecs, (int)sizeof(_Py_M__codecs), GET_CODE(codecs)},
{"io", _Py_M__io, (int)sizeof(_Py_M__io), GET_CODE(io)},
{"abc", NULL, 0, false, GET_CODE(abc)},
{"codecs", NULL, 0, false, GET_CODE(codecs)},
{"io", NULL, 0, false, GET_CODE(io)},
/* stdlib - startup, with site */
{"_collections_abc", _Py_M___collections_abc, (int)sizeof(_Py_M___collections_abc), GET_CODE(_collections_abc)},
{"_sitebuiltins", _Py_M___sitebuiltins, (int)sizeof(_Py_M___sitebuiltins), GET_CODE(_sitebuiltins)},
{"genericpath", _Py_M__genericpath, (int)sizeof(_Py_M__genericpath), GET_CODE(genericpath)},
{"ntpath", _Py_M__ntpath, (int)sizeof(_Py_M__ntpath), GET_CODE(ntpath)},
{"posixpath", _Py_M__posixpath, (int)sizeof(_Py_M__posixpath), GET_CODE(posixpath)},
{"os.path", _Py_M__posixpath, (int)sizeof(_Py_M__posixpath), GET_CODE(posixpath)},
{"os", _Py_M__os, (int)sizeof(_Py_M__os), GET_CODE(os)},
{"site", _Py_M__site, (int)sizeof(_Py_M__site), GET_CODE(site)},
{"stat", _Py_M__stat, (int)sizeof(_Py_M__stat), GET_CODE(stat)},
{"_collections_abc", NULL, 0, false, GET_CODE(_collections_abc)},
{"_sitebuiltins", NULL, 0, false, GET_CODE(_sitebuiltins)},
{"genericpath", NULL, 0, false, GET_CODE(genericpath)},
{"ntpath", NULL, 0, false, GET_CODE(ntpath)},
{"posixpath", NULL, 0, false, GET_CODE(posixpath)},
{"os.path", NULL, 0, false, GET_CODE(posixpath)},
{"os", NULL, 0, false, GET_CODE(os)},
{"site", NULL, 0, false, GET_CODE(site)},
{"stat", NULL, 0, false, GET_CODE(stat)},
/* runpy - run module with -m */
{"importlib.util", _Py_M__importlib_util, (int)sizeof(_Py_M__importlib_util), GET_CODE(importlib_util)},
{"importlib.machinery", _Py_M__importlib_machinery, (int)sizeof(_Py_M__importlib_machinery), GET_CODE(importlib_machinery)},
{"runpy", _Py_M__runpy, (int)sizeof(_Py_M__runpy), GET_CODE(runpy)},
{"importlib.util", NULL, 0, false, GET_CODE(importlib_util)},
{"importlib.machinery", NULL, 0, false, GET_CODE(importlib_machinery)},
{"runpy", NULL, 0, false, GET_CODE(runpy)},
{0, 0, 0} /* stdlib sentinel */
};
static const struct _frozen test_modules[] = {
{"__hello__", _Py_M____hello__, (int)sizeof(_Py_M____hello__), GET_CODE(__hello__)},
{"__hello_alias__", _Py_M____hello__, (int)sizeof(_Py_M____hello__), GET_CODE(__hello__)},
{"__phello_alias__", _Py_M____hello__, -(int)sizeof(_Py_M____hello__), GET_CODE(__hello__)},
{"__phello_alias__.spam", _Py_M____hello__, (int)sizeof(_Py_M____hello__), GET_CODE(__hello__)},
{"__phello__", _Py_M____phello__, -(int)sizeof(_Py_M____phello__), GET_CODE(__phello__)},
{"__phello__.__init__", _Py_M____phello__, (int)sizeof(_Py_M____phello__), GET_CODE(__phello__)},
{"__phello__.ham", _Py_M____phello___ham, -(int)sizeof(_Py_M____phello___ham), GET_CODE(__phello___ham)},
{"__phello__.ham.__init__", _Py_M____phello___ham, (int)sizeof(_Py_M____phello___ham), GET_CODE(__phello___ham)},
{"__phello__.ham.eggs", _Py_M____phello___ham_eggs, (int)sizeof(_Py_M____phello___ham_eggs), GET_CODE(__phello___ham_eggs)},
{"__phello__.spam", _Py_M____phello___spam, (int)sizeof(_Py_M____phello___spam), GET_CODE(__phello___spam)},
{"__hello_only__", _Py_M__frozen_only, (int)sizeof(_Py_M__frozen_only), GET_CODE(frozen_only)},
{"__hello__", NULL, 0, false, GET_CODE(__hello__)},
{"__hello_alias__", NULL, 0, false, GET_CODE(__hello__)},
{"__phello_alias__", NULL, 0, true, GET_CODE(__hello__)},
{"__phello_alias__.spam", NULL, 0, false, GET_CODE(__hello__)},
{"__phello__", NULL, 0, true, GET_CODE(__phello__)},
{"__phello__.__init__", NULL, 0, false, GET_CODE(__phello__)},
{"__phello__.ham", NULL, 0, true, GET_CODE(__phello___ham)},
{"__phello__.ham.__init__", NULL, 0, false, GET_CODE(__phello___ham)},
{"__phello__.ham.eggs", NULL, 0, false, GET_CODE(__phello___ham_eggs)},
{"__phello__.spam", NULL, 0, false, GET_CODE(__phello___spam)},
{"__hello_only__", NULL, 0, false, GET_CODE(frozen_only)},
{0, 0, 0} /* test sentinel */
};
const struct _frozen *_PyImport_FrozenBootstrap = bootstrap_modules;

View file

@ -1297,13 +1297,21 @@ find_frozen(PyObject *nameobj, struct frozen_info *info)
info->nameobj = nameobj; // borrowed
info->data = (const char *)p->code;
info->get_code = p->get_code;
info->size = p->size < 0 ? -(p->size) : p->size;
info->is_package = p->size < 0 ? true : false;
info->size = p->size;
info->is_package = p->is_package;
if (p->size < 0) {
// backward compatibility with negative size values
info->size = -(p->size);
info->is_package = true;
}
info->origname = name;
info->is_alias = resolve_module_alias(name, _PyImport_FrozenAliases,
&info->origname);
}
if (p->code == NULL && p->size == 0 && p->get_code != NULL) {
/* It is only deepfrozen. */
return FROZEN_OKAY;
}
if (p->code == NULL) {
/* It is frozen but marked as un-importable. */
return FROZEN_EXCLUDED;
@ -2224,7 +2232,7 @@ _imp_get_frozen_object_impl(PyObject *module, PyObject *name,
if (info.nameobj == NULL) {
info.nameobj = name;
}
if (info.size == 0) {
if (info.size == 0 && info.get_code == NULL) {
/* Does not contain executable code. */
set_frozen_error(FROZEN_INVALID, name);
return NULL;