hgdemandimport/demandimportpy3.py
author Gregory Szorc <gregory.szorc@gmail.com>
Mon, 20 Jan 2020 23:51:25 -0800
changeset 44118 f81c17ec303c
parent 44117 c5e0a9b97b8a
child 44819 a6e12d477595
permissions -rw-r--r--
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 ± σ): 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 ± σ): 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 ± σ): 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 ± σ): 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 ± σ): 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 ± σ): 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

# demandimportpy3 - global demand-loading of modules for Mercurial
#
# Copyright 2017 Facebook Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""Lazy loading for Python 3.6 and above.

This uses the new importlib finder/loader functionality available in Python 3.5
and up. The code reuses most of the mechanics implemented inside importlib.util,
but with a few additions:

* Allow excluding certain modules from lazy imports.
* Expose an interface that's substantially the same as demandimport for
  Python 2.

This also has some limitations compared to the Python 2 implementation:

* Much of the logic is per-package, not per-module, so any packages loaded
  before demandimport is enabled will not be lazily imported in the future. In
  practice, we only expect builtins to be loaded before demandimport is
  enabled.
"""

# This line is unnecessary, but it satisfies test-check-py3-compat.t.
from __future__ import absolute_import

import contextlib
import importlib.util
import sys

from . import tracing

_deactivated = False

# Python 3.5's LazyLoader doesn't work for some reason.
# https://bugs.python.org/issue26186 is a known issue with extension
# importing. But it appears to not have a meaningful effect with
# Mercurial.
_supported = sys.version_info[0:2] >= (3, 6)


class _lazyloaderex(importlib.util.LazyLoader):
    """This is a LazyLoader except it also follows the _deactivated global and
    the ignore list.
    """

    def exec_module(self, module):
        """Make the module load lazily."""
        with tracing.log('demandimport %s', module):
            if _deactivated or module.__name__ in ignores:
                self.loader.exec_module(module)
            else:
                super().exec_module(module)


class LazyFinder(object):
    """A wrapper around a ``MetaPathFinder`` that makes loaders lazy.

    ``sys.meta_path`` finders have their ``find_spec()`` called to locate a
    module. This returns a ``ModuleSpec`` if found or ``None``. The
    ``ModuleSpec`` has a ``loader`` attribute, which is called to actually
    load a module.

    Our class wraps an existing finder and overloads its ``find_spec()`` to
    replace the ``loader`` with our lazy loader proxy.

    We have to use __getattribute__ to proxy the instance because some meta
    path finders don't support monkeypatching.
    """

    __slots__ = ("_finder",)

    def __init__(self, finder):
        object.__setattr__(self, "_finder", finder)

    def __repr__(self):
        return "<LazyFinder for %r>" % object.__getattribute__(self, "_finder")

    # __bool__ is canonical Python 3. But check-code insists on __nonzero__ being
    # defined via `def`.
    def __nonzero__(self):
        return bool(object.__getattribute__(self, "_finder"))

    __bool__ = __nonzero__

    def __getattribute__(self, name):
        if name in ("_finder", "find_spec"):
            return object.__getattribute__(self, name)

        return getattr(object.__getattribute__(self, "_finder"), name)

    def __delattr__(self, name):
        return delattr(object.__getattribute__(self, "_finder"))

    def __setattr__(self, name, value):
        return setattr(object.__getattribute__(self, "_finder"), name, value)

    def find_spec(self, *args, **kwargs):
        finder = object.__getattribute__(self, "_finder")
        spec = finder.find_spec(*args, **kwargs)

        # Lazy loader requires exec_module().
        if (
            spec is not None
            and spec.loader is not None
            and getattr(spec.loader, "exec_module")
        ):
            spec.loader = _lazyloaderex(spec.loader)

        return spec


ignores = set()


def init(ignoreset):
    global ignores
    ignores = ignoreset


def isenabled():
    return not _deactivated and any(
        isinstance(finder, LazyFinder) for finder in sys.meta_path
    )


def disable():
    new_finders = []
    for finder in sys.meta_path:
        new_finders.append(
            finder._finder if isinstance(finder, LazyFinder) else finder
        )
    sys.meta_path[:] = new_finders


def enable():
    if not _supported:
        return

    new_finders = []
    for finder in sys.meta_path:
        new_finders.append(
            LazyFinder(finder) if not isinstance(finder, LazyFinder) else finder
        )
    sys.meta_path[:] = new_finders


@contextlib.contextmanager
def deactivated():
    # This implementation is a bit different from Python 2's. Python 3
    # maintains a per-package finder cache in sys.path_importer_cache (see
    # PEP 302). This means that we can't just call disable + enable.
    # If we do that, in situations like:
    #
    #   demandimport.enable()
    #   ...
    #   from foo.bar import mod1
    #   with demandimport.deactivated():
    #       from foo.bar import mod2
    #
    # mod2 will be imported lazily. (The converse also holds -- whatever finder
    # first gets cached will be used.)
    #
    # Instead, have a global flag the LazyLoader can use.
    global _deactivated
    demandenabled = isenabled()
    if demandenabled:
        _deactivated = True
    try:
        yield
    finally:
        if demandenabled:
            _deactivated = False