view hgdemandimport/__init__.py @ 43891:7eb6a2680ae6

dirstate: when calling rebuild(), avoid some N^2 codepaths

I had a user repo with 200k files in it. Calling `hg debugrebuilddirstate` took
tens of minutes (I didn't wait for it). In that situation,
changedfiles==allfiles, and both are lists. This meant that we had to run an
average of 100k comparisons, for each of 200k files, just to check whether a
file needed to have normallookup called (it always did), or drop.

While it's probably not a huge issue, in my very awkward synthetic benchmark I
wrote (not using a benchmark library or anything), I was seeing some slowdowns
for small-changedfiles and very-large-allfiles invocations, with an inflection
somewhere around 10 items in changedfiles (regardless of the size of allfiles);
above 10 items in changedfiles, the new code appears to always be faster. For
the case of 50k files in changedfiles and the same items in allfiles, I'm seeing
differences of 15s of just running comparisons vs. 0.003793s. I haven't bothered
to run a comparison of 200k items in changedfiles and allfiles. :)

Differential Revision: https://phab.mercurial-scm.org/D7665

# hgdemandimport - 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.

'''demandimport - automatic demand-loading of modules'''

# This is in a separate package from mercurial because in Python 3,
# demand loading is per-package. Keeping demandimport in the mercurial package
# would disable demand loading for any modules in mercurial.

from __future__ import absolute_import

import os
import sys

if sys.version_info[0] >= 3:
    from . import demandimportpy3 as demandimport
else:
    from . import demandimportpy2 as demandimport

# Full module names which can't be lazy imported.
# Extensions can add to this set.
IGNORES = {
    '__future__',
    '_hashlib',
    # ImportError during pkg_resources/__init__.py:fixup_namespace_package
    '_imp',
    '_xmlplus',
    'fcntl',
    'nt',  # pathlib2 tests the existence of built-in 'nt' module
    'win32com.gen_py',
    'win32com.shell',  # 'appdirs' tries to import win32com.shell
    '_winreg',  # 2.7 mimetypes needs immediate ImportError
    'pythoncom',
    # imported by tarfile, not available under Windows
    'pwd',
    'grp',
    # imported by profile, itself imported by hotshot.stats,
    # not available under Windows
    'resource',
    # this trips up many extension authors
    'gtk',
    # setuptools' pkg_resources.py expects "from __main__ import x" to
    # raise ImportError if x not defined
    '__main__',
    '_ssl',  # conditional imports in the stdlib, issue1964
    '_sre',  # issue4920
    'rfc822',
    'mimetools',
    'sqlalchemy.events',  # has import-time side effects (issue5085)
    # setuptools 8 expects this module to explode early when not on windows
    'distutils.msvc9compiler',
    '__builtin__',
    'builtins',
    'urwid.command_map',  # for pudb
}

_pypy = '__pypy__' in sys.builtin_module_names

if _pypy:
    # _ctypes.pointer is shadowed by "from ... import pointer" (PyPy 5)
    IGNORES.add('_ctypes.pointer')

demandimport.init(IGNORES)

# Re-export.
isenabled = demandimport.isenabled
disable = demandimport.disable
deactivated = demandimport.deactivated


def enable():
    # chg pre-imports modules so do not enable demandimport for it
    if (
        'CHGINTERNALMARK' not in os.environ
        and os.environ.get('HGDEMANDIMPORT') != 'disable'
    ):
        demandimport.enable()