##// 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:

r50170:c6a32435 default
r51286:81c7d04f stable
Show More
osutil.py
207 lines | 5.9 KiB | text/x-python | PythonLexer
# osutil.py - pure Python version of osutil.c
#
# Copyright 2009 Olivia Mackall <olivia@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import ctypes
import ctypes.util
import os
import stat as statmod
from ..pycompat import getattr
from .. import (
encoding,
pycompat,
)
def _mode_to_kind(mode):
if statmod.S_ISREG(mode):
return statmod.S_IFREG
if statmod.S_ISDIR(mode):
return statmod.S_IFDIR
if statmod.S_ISLNK(mode):
return statmod.S_IFLNK
if statmod.S_ISBLK(mode):
return statmod.S_IFBLK
if statmod.S_ISCHR(mode):
return statmod.S_IFCHR
if statmod.S_ISFIFO(mode):
return statmod.S_IFIFO
if statmod.S_ISSOCK(mode):
return statmod.S_IFSOCK
return mode
def listdir(path, stat=False, skip=None):
"""listdir(path, stat=False) -> list_of_tuples
Return a sorted list containing information about the entries
in the directory.
If stat is True, each element is a 3-tuple:
(name, type, stat object)
Otherwise, each element is a 2-tuple:
(name, type)
"""
result = []
prefix = path
if not prefix.endswith(pycompat.ossep):
prefix += pycompat.ossep
names = os.listdir(path)
names.sort()
for fn in names:
st = os.lstat(prefix + fn)
if fn == skip and statmod.S_ISDIR(st.st_mode):
return []
if stat:
result.append((fn, _mode_to_kind(st.st_mode), st))
else:
result.append((fn, _mode_to_kind(st.st_mode)))
return result
if not pycompat.iswindows:
posixfile = open
else:
import msvcrt
_kernel32 = ctypes.windll.kernel32 # pytype: disable=module-attr
_DWORD = ctypes.c_ulong
_LPCSTR = _LPSTR = ctypes.c_char_p
_HANDLE = ctypes.c_void_p
_INVALID_HANDLE_VALUE = _HANDLE(-1).value
# CreateFile
_FILE_SHARE_READ = 0x00000001
_FILE_SHARE_WRITE = 0x00000002
_FILE_SHARE_DELETE = 0x00000004
_CREATE_ALWAYS = 2
_OPEN_EXISTING = 3
_OPEN_ALWAYS = 4
_GENERIC_READ = 0x80000000
_GENERIC_WRITE = 0x40000000
_FILE_ATTRIBUTE_NORMAL = 0x80
# open_osfhandle flags
_O_RDONLY = 0x0000
_O_RDWR = 0x0002
_O_APPEND = 0x0008
_O_TEXT = 0x4000
_O_BINARY = 0x8000
# types of parameters of C functions used (required by pypy)
_kernel32.CreateFileA.argtypes = [
_LPCSTR,
_DWORD,
_DWORD,
ctypes.c_void_p,
_DWORD,
_DWORD,
_HANDLE,
]
_kernel32.CreateFileA.restype = _HANDLE
def _raiseioerror(name):
err = ctypes.WinError() # pytype: disable=module-attr
raise IOError(
err.errno, '%s: %s' % (encoding.strfromlocal(name), err.strerror)
)
class posixfile:
"""a file object aiming for POSIX-like semantics
CPython's open() returns a file that was opened *without* setting the
_FILE_SHARE_DELETE flag, which causes rename and unlink to abort.
This even happens if any hardlinked copy of the file is in open state.
We set _FILE_SHARE_DELETE here, so files opened with posixfile can be
renamed and deleted while they are held open.
Note that if a file opened with posixfile is unlinked, the file
remains but cannot be opened again or be recreated under the same name,
until all reading processes have closed the file."""
def __init__(self, name, mode=b'r', bufsize=-1):
if b'b' in mode:
flags = _O_BINARY
else:
flags = _O_TEXT
m0 = mode[0:1]
if m0 == b'r' and b'+' not in mode:
flags |= _O_RDONLY
access = _GENERIC_READ
else:
# work around http://support.microsoft.com/kb/899149 and
# set _O_RDWR for 'w' and 'a', even if mode has no '+'
flags |= _O_RDWR
access = _GENERIC_READ | _GENERIC_WRITE
if m0 == b'r':
creation = _OPEN_EXISTING
elif m0 == b'w':
creation = _CREATE_ALWAYS
elif m0 == b'a':
creation = _OPEN_ALWAYS
flags |= _O_APPEND
else:
raise ValueError("invalid mode: %s" % pycompat.sysstr(mode))
fh = _kernel32.CreateFileA(
name,
access,
_FILE_SHARE_READ | _FILE_SHARE_WRITE | _FILE_SHARE_DELETE,
None,
creation,
_FILE_ATTRIBUTE_NORMAL,
None,
)
if fh == _INVALID_HANDLE_VALUE:
_raiseioerror(name)
fd = msvcrt.open_osfhandle(fh, flags) # pytype: disable=module-attr
if fd == -1:
_kernel32.CloseHandle(fh)
_raiseioerror(name)
f = os.fdopen(fd, pycompat.sysstr(mode), bufsize)
# unfortunately, f.name is '<fdopen>' at this point -- so we store
# the name on this wrapper. We cannot just assign to f.name,
# because that attribute is read-only.
object.__setattr__(self, 'name', name)
object.__setattr__(self, '_file', f)
def __iter__(self):
return self._file
def __getattr__(self, name):
return getattr(self._file, name)
def __setattr__(self, name, value):
"""mimics the read-only attributes of Python file objects
by raising 'TypeError: readonly attribute' if someone tries:
f = posixfile('foo.txt')
f.name = 'bla'
"""
return self._file.__setattr__(name, value)
def __enter__(self):
self._file.__enter__()
return self
def __exit__(self, exc_type, exc_value, exc_tb):
return self._file.__exit__(exc_type, exc_value, exc_tb)