Mercurial > public > mercurial-scm > hg
view mercurial/exewrapper.c @ 44118:f81c17ec303c
hgdemandimport: apply lazy module loading to sys.meta_path finders
Python's `sys.meta_path` finders are the primary objects whose job it
is to find a module at import time. When `import` is called, Python
iterates objects in this list and calls `o.find_spec(...)` to find
a `ModuleSpec` (or None if the module couldn't be found by that
finder). If no meta path finder can find a module, import fails.
One of the default meta path finders is `PathFinder`. Its job is to
import modules from the filesystem and is probably the most important
importer. This finder looks at `sys.path` and `sys.path_hooks` to do
its job.
The `ModuleSpec` returned by `MetaPathImporter.find_spec()` has a
`loader` attribute, which defines the concrete module loader to use.
`sys.path_hooks` is a hook point for teaching `PathFinder` to
instantiate custom loader types.
Previously, we injected a custom `sys.path_hook` that told `PathFinder`
to wrap the default loaders with a loader that creates a module object
that is lazy.
This approach worked. But its main limitation was that it only applied
to the `PathFinder` meta path importer. There are other meta path
importers that are registered. And in the case of PyOxidizer loading
modules from memory, `PathFinder` doesn't come into play since
PyOxidizer's own meta path importer was handling all imports.
This commit changes our approach to lazy module loading by proxying
all meta path importers. Specifically, we overload the `find_spec()`
method to swap in a wrapped loader on the `ModuleSpec` before it
is returned. The end result of this is all meta path importers should
be lazy.
As much as I would have loved to utilize .__class__ manipulation to
achieve this, some meta path importers are implemented in C/Rust
in such a way that they cannot be monkeypatched. This is why we
use __getattribute__ to define a proxy.
Also, this change could theoretically open us up to regressions in
meta path importers whose loader is creating module objects which
can't be monkeypatched. But I'm not aware of any of these in the
wild. So I think we'll be safe.
According to hyperfine, this change yields a decent startup time win of
5-6ms:
```
Benchmark #1: ~/.pyenv/versions/3.6.10/bin/python ./hg version
Time (mean ? ?): 86.8 ms ? 0.5 ms [User: 78.0 ms, System: 8.7 ms]
Range (min ? max): 86.0 ms ? 89.1 ms 50 runs
Time (mean ? ?): 81.1 ms ? 2.7 ms [User: 74.5 ms, System: 6.5 ms]
Range (min ? max): 77.8 ms ? 90.5 ms 50 runs
Benchmark #2: ~/.pyenv/versions/3.7.6/bin/python ./hg version
Time (mean ? ?): 78.9 ms ? 0.6 ms [User: 70.2 ms, System: 8.7 ms]
Range (min ? max): 78.1 ms ? 81.2 ms 50 runs
Time (mean ? ?): 73.4 ms ? 0.6 ms [User: 65.3 ms, System: 8.0 ms]
Range (min ? max): 72.4 ms ? 75.7 ms 50 runs
Benchmark #3: ~/.pyenv/versions/3.8.1/bin/python ./hg version
Time (mean ? ?): 78.1 ms ? 0.6 ms [User: 70.2 ms, System: 7.9 ms]
Range (min ? max): 77.4 ms ? 80.9 ms 50 runs
Time (mean ? ?): 72.1 ms ? 0.4 ms [User: 64.4 ms, System: 7.6 ms]
Range (min ? max): 71.4 ms ? 74.1 ms 50 runs
```
Differential Revision: https://phab.mercurial-scm.org/D7954
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Mon, 20 Jan 2020 23:51:25 -0800 |
parents | ef7119cd4965 |
children | 825d5a5907b4 |
line wrap: on
line source
/* exewrapper.c - wrapper for calling a python script on Windows Copyright 2012 Adrian Buehlmann <adrian@cadifra.com> and others This software may be used and distributed according to the terms of the GNU General Public License version 2 or any later version. */ #include <Python.h> #include <stdio.h> #include <tchar.h> #include <windows.h> #include "hgpythonlib.h" #ifdef __GNUC__ int strcat_s(char *d, size_t n, const char *s) { return !strncat(d, s, n); } int strcpy_s(char *d, size_t n, const char *s) { return !strncpy(d, s, n); } #define _tcscpy_s strcpy_s #define _tcscat_s strcat_s #define _countof(array) (sizeof(array) / sizeof(array[0])) #endif static TCHAR pyscript[MAX_PATH + 10]; static TCHAR pyhome[MAX_PATH + 10]; static TCHAR pydllfile[MAX_PATH + 10]; int _tmain(int argc, TCHAR *argv[]) { TCHAR *p; int ret; int i; int n; TCHAR **pyargv; WIN32_FIND_DATA fdata; HANDLE hfind; const char *err; HMODULE pydll; void(__cdecl * Py_SetPythonHome)(TCHAR * home); int(__cdecl * Py_Main)(int argc, TCHAR *argv[]); #if PY_MAJOR_VERSION >= 3 Py_LegacyWindowsStdioFlag = 1; #endif if (GetModuleFileName(NULL, pyscript, _countof(pyscript)) == 0) { err = "GetModuleFileName failed"; goto bail; } p = _tcsrchr(pyscript, '.'); if (p == NULL) { err = "malformed module filename"; goto bail; } *p = 0; /* cut trailing ".exe" */ _tcscpy_s(pyhome, _countof(pyhome), pyscript); hfind = FindFirstFile(pyscript, &fdata); if (hfind != INVALID_HANDLE_VALUE) { /* pyscript exists, close handle */ FindClose(hfind); } else { /* file pyscript isn't there, take <pyscript>exe.py */ _tcscat_s(pyscript, _countof(pyscript), _T("exe.py")); } pydll = NULL; p = _tcsrchr(pyhome, _T('\\')); if (p == NULL) { err = "can't find backslash in module filename"; goto bail; } *p = 0; /* cut at directory */ /* check for private Python of HackableMercurial */ _tcscat_s(pyhome, _countof(pyhome), _T("\\hg-python")); hfind = FindFirstFile(pyhome, &fdata); if (hfind != INVALID_HANDLE_VALUE) { /* Path .\hg-python exists. We are probably in HackableMercurial scenario, so let's load python dll from this dir. */ FindClose(hfind); _tcscpy_s(pydllfile, _countof(pydllfile), pyhome); _tcscat_s(pydllfile, _countof(pydllfile), _T("\\") _T(HGPYTHONLIB) _T(".dll")); pydll = LoadLibrary(pydllfile); if (pydll == NULL) { err = "failed to load private Python DLL " HGPYTHONLIB ".dll"; goto bail; } Py_SetPythonHome = (void *)GetProcAddress(pydll, "Py_SetPythonHome"); if (Py_SetPythonHome == NULL) { err = "failed to get Py_SetPythonHome"; goto bail; } Py_SetPythonHome(pyhome); } if (pydll == NULL) { pydll = LoadLibrary(_T(HGPYTHONLIB) _T(".dll")); if (pydll == NULL) { err = "failed to load Python DLL " HGPYTHONLIB ".dll"; goto bail; } } Py_Main = (void *)GetProcAddress(pydll, "Py_Main"); if (Py_Main == NULL) { err = "failed to get Py_Main"; goto bail; } /* Only add the pyscript to the args, if it's not already there. It may already be there, if the script spawned a child process of itself, in the same way as it got called, that is, with the pyscript already in place. So we optionally accept the pyscript as the first argument (argv[1]), letting our exe taking the role of the python interpreter. */ if (argc >= 2 && _tcscmp(argv[1], pyscript) == 0) { /* pyscript is already in the args, so there is no need to copy the args and we can directly call the python interpreter with the original args. */ return Py_Main(argc, argv); } /* Start assembling the args for the Python interpreter call. We put the name of our exe (argv[0]) in the position where the python.exe canonically is, and insert the pyscript next. */ pyargv = malloc((argc + 5) * sizeof(TCHAR *)); if (pyargv == NULL) { err = "not enough memory"; goto bail; } n = 0; pyargv[n++] = argv[0]; pyargv[n++] = pyscript; /* copy remaining args from the command line */ for (i = 1; i < argc; i++) pyargv[n++] = argv[i]; /* argv[argc] is guaranteed to be NULL, so we forward that guarantee */ pyargv[n] = NULL; ret = Py_Main(n, pyargv); /* The Python interpreter call */ free(pyargv); return ret; bail: fprintf(stderr, "abort: %s\n", err); return 255; }