mercurial/rcutil.py
author Gregory Szorc <gregory.szorc@gmail.com>
Mon, 20 Jan 2020 23:51:25 -0800
changeset 44118 f81c17ec303c
parent 44032 2d4cad94d08a
child 44243 238790674d69
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 ? ?): 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

# rcutil.py - utilities about config paths, special config sections etc.
#
#  Copyright Mercurial Contributors
#
# 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

from . import (
    encoding,
    pycompat,
    util,
)

from .utils import resourceutil

if pycompat.iswindows:
    from . import scmwindows as scmplatform
else:
    from . import scmposix as scmplatform

fallbackpager = scmplatform.fallbackpager
systemrcpath = scmplatform.systemrcpath
userrcpath = scmplatform.userrcpath


def _expandrcpath(path):
    '''path could be a file or a directory. return a list of file paths'''
    p = util.expandpath(path)
    if os.path.isdir(p):
        join = os.path.join
        return sorted(
            join(p, f) for f, k in util.listdir(p) if f.endswith(b'.rc')
        )
    return [p]


def envrcitems(env=None):
    '''Return [(section, name, value, source)] config items.

    The config items are extracted from environment variables specified by env,
    used to override systemrc, but not userrc.

    If env is not provided, encoding.environ will be used.
    '''
    if env is None:
        env = encoding.environ
    checklist = [
        (b'EDITOR', b'ui', b'editor'),
        (b'VISUAL', b'ui', b'editor'),
        (b'PAGER', b'pager', b'pager'),
    ]
    result = []
    for envname, section, configname in checklist:
        if envname not in env:
            continue
        result.append((section, configname, env[envname], b'$%s' % envname))
    return result


def default_rc_resources():
    """return rc resource IDs in defaultrc"""
    rsrcs = resourceutil.contents(b'mercurial.defaultrc')
    return [
        (b'mercurial.defaultrc', r)
        for r in sorted(rsrcs)
        if resourceutil.is_resource(b'mercurial.defaultrc', r)
        and r.endswith(b'.rc')
    ]


def rccomponents():
    '''return an ordered [(type, obj)] about where to load configs.

    respect $HGRCPATH. if $HGRCPATH is empty, only .hg/hgrc of current repo is
    used. if $HGRCPATH is not set, the platform default will be used.

    if a directory is provided, *.rc files under it will be used.

    type could be either 'path', 'items' or 'resource'. If type is 'path',
    obj is a string, and is the config file path. if type is 'items', obj is a
    list of (section, name, value, source) that should fill the config directly.
    If type is 'resource', obj is a tuple of (package name, resource name).
    '''
    envrc = (b'items', envrcitems())

    if b'HGRCPATH' in encoding.environ:
        # assume HGRCPATH is all about user configs so environments can be
        # overridden.
        _rccomponents = [envrc]
        for p in encoding.environ[b'HGRCPATH'].split(pycompat.ospathsep):
            if not p:
                continue
            _rccomponents.extend((b'path', p) for p in _expandrcpath(p))
    else:
        _rccomponents = [(b'resource', r) for r in default_rc_resources()]

        normpaths = lambda paths: [
            (b'path', os.path.normpath(p)) for p in paths
        ]
        _rccomponents.extend(normpaths(systemrcpath()))
        _rccomponents.append(envrc)
        _rccomponents.extend(normpaths(userrcpath()))
    return _rccomponents


def defaultpagerenv():
    '''return a dict of default environment variables and their values,
    intended to be set before starting a pager.
    '''
    return {b'LESS': b'FRX', b'LV': b'-c'}