##// END OF EJS Templates
match: match explicit file using a set...
match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)

File last commit:

r50715:3eac9250 default
r51286:81c7d04f stable
Show More
policy.py
153 lines | 4.6 KiB | text/x-python | PythonLexer
# 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.
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 'HGMODULEPOLICY' in os.environ:
policy = os.environ['HGMODULEPOLICY'].encode('utf-8')
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'): 21,
}
# 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)