view mercurial/policy.py @ 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 b56de57c45ce
children 61e7464477ac
line wrap: on
line source

# policy.py - module policy logic for Mercurial.
#
# Copyright 2015 Gregory Szorc <gregory.szorc@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os
import sys

from .pycompat import getattr

# Rules for how modules can be loaded. Values are:
#
#    c - require C extensions
#    rust+c - require Rust and C extensions
#    rust+c-allow - allow Rust and C extensions with fallback to pure Python
#                   for each
#    allow - allow pure Python implementation when C loading fails
#    cffi - required cffi versions (implemented within pure module)
#    cffi-allow - allow pure Python implementation if cffi version is missing
#    py - only load pure Python modules
#
# By default, fall back to the pure modules so the in-place build can
# run without recompiling the C extensions. This will be overridden by
# __modulepolicy__ generated by setup.py.
policy = b'allow'
_packageprefs = {
    # policy: (versioned package, pure package)
    b'c': ('cext', None),
    b'allow': ('cext', 'pure'),
    b'cffi': ('cffi', None),
    b'cffi-allow': ('cffi', 'pure'),
    b'py': (None, 'pure'),
    # For now, rust policies impact importrust only
    b'rust+c': ('cext', None),
    b'rust+c-allow': ('cext', 'pure'),
}

try:
    from . import __modulepolicy__

    policy = __modulepolicy__.modulepolicy
except ImportError:
    pass

# PyPy doesn't load C extensions.
#
# The canonical way to do this is to test platform.python_implementation().
# But we don't import platform and don't bloat for it here.
if '__pypy__' in sys.builtin_module_names:
    policy = b'cffi'

# Environment variable can always force settings.
if sys.version_info[0] >= 3:
    if 'HGMODULEPOLICY' in os.environ:
        policy = os.environ['HGMODULEPOLICY'].encode('utf-8')
else:
    policy = os.environ.get('HGMODULEPOLICY', policy)


def _importfrom(pkgname, modname):
    # from .<pkgname> import <modname> (where . is looked through this module)
    fakelocals = {}
    pkg = __import__(pkgname, globals(), fakelocals, [modname], level=1)
    try:
        fakelocals[modname] = mod = getattr(pkg, modname)
    except AttributeError:
        raise ImportError('cannot import name %s' % modname)
    # force import; fakelocals[modname] may be replaced with the real module
    getattr(mod, '__doc__', None)
    return fakelocals[modname]


# keep in sync with "version" in C modules
_cextversions = {
    ('cext', 'base85'): 1,
    ('cext', 'bdiff'): 3,
    ('cext', 'mpatch'): 1,
    ('cext', 'osutil'): 4,
    ('cext', 'parsers'): 16,
}

# map import request to other package or module
_modredirects = {
    ('cext', 'charencode'): ('cext', 'parsers'),
    ('cffi', 'base85'): ('pure', 'base85'),
    ('cffi', 'charencode'): ('pure', 'charencode'),
    ('cffi', 'parsers'): ('pure', 'parsers'),
}


def _checkmod(pkgname, modname, mod):
    expected = _cextversions.get((pkgname, modname))
    actual = getattr(mod, 'version', None)
    if actual != expected:
        raise ImportError(
            'cannot import module %s.%s '
            '(expected version: %d, actual: %r)'
            % (pkgname, modname, expected, actual)
        )


def importmod(modname):
    """Import module according to policy and check API version"""
    try:
        verpkg, purepkg = _packageprefs[policy]
    except KeyError:
        raise ImportError('invalid HGMODULEPOLICY %r' % policy)
    assert verpkg or purepkg
    if verpkg:
        pn, mn = _modredirects.get((verpkg, modname), (verpkg, modname))
        try:
            mod = _importfrom(pn, mn)
            if pn == verpkg:
                _checkmod(pn, mn, mod)
            return mod
        except ImportError:
            if not purepkg:
                raise
    pn, mn = _modredirects.get((purepkg, modname), (purepkg, modname))
    return _importfrom(pn, mn)


def _isrustpermissive():
    """Assuming the policy is a Rust one, tell if it's permissive."""
    return policy.endswith(b'-allow')


def importrust(modname, member=None, default=None):
    """Import Rust module according to policy and availability.

    If policy isn't a Rust one, this returns `default`.

    If either the module or its member is not available, this returns `default`
    if policy is permissive and raises `ImportError` if not.
    """
    if not policy.startswith(b'rust'):
        return default

    try:
        mod = _importfrom('rustext', modname)
    except ImportError:
        if _isrustpermissive():
            return default
        raise
    if member is None:
        return mod

    try:
        return getattr(mod, member)
    except AttributeError:
        if _isrustpermissive():
            return default
        raise ImportError("Cannot import name %s" % member)