##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r35818:d5288b96 stable
r36838:f33a87cf default
Show More
minifileset.py
85 lines | 3.3 KiB | text/x-python | PythonLexer
# minifileset.py - a simple language to select files
#
# 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.
from __future__ import absolute_import
from .i18n import _
from . import (
error,
fileset,
)
def _compile(tree):
if not tree:
raise error.ParseError(_("missing argument"))
op = tree[0]
if op in {'symbol', 'string', 'kindpat'}:
name = fileset.getpattern(tree, {'path'}, _('invalid file pattern'))
if name.startswith('**'): # file extension test, ex. "**.tar.gz"
ext = name[2:]
for c in ext:
if c in '*{}[]?/\\':
raise error.ParseError(_('reserved character: %s') % c)
return lambda n, s: n.endswith(ext)
elif name.startswith('path:'): # directory or full path test
p = name[5:] # prefix
pl = len(p)
f = lambda n, s: n.startswith(p) and (len(n) == pl or n[pl] == '/')
return f
raise error.ParseError(_("unsupported file pattern: %s") % name,
hint=_('paths must be prefixed with "path:"'))
elif op == 'or':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) or func2(n, s)
elif op == 'and':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and func2(n, s)
elif op == 'not':
return lambda n, s: not _compile(tree[1])(n, s)
elif op == 'group':
return _compile(tree[1])
elif op == 'func':
symbols = {
'all': lambda n, s: True,
'none': lambda n, s: False,
'size': lambda n, s: fileset.sizematcher(tree[2])(s),
}
name = fileset.getsymbol(tree[1])
if name in symbols:
return symbols[name]
raise error.UnknownIdentifier(name, symbols.keys())
elif op == 'minus': # equivalent to 'x and not y'
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and not func2(n, s)
elif op == 'negate':
raise error.ParseError(_("can't use negate operator in this context"))
elif op == 'list':
raise error.ParseError(_("can't use a list in this context"),
hint=_('see hg help "filesets.x or y"'))
raise error.ProgrammingError('illegal tree: %r' % (tree,))
def compile(text):
"""generate a function (path, size) -> bool from filter specification.
"text" could contain the operators defined by the fileset language for
common logic operations, and parenthesis for grouping. The supported path
tests are '**.extname' for file extension test, and '"path:dir/subdir"'
for prefix test. The ``size()`` predicate is borrowed from filesets to test
file size. The predicates ``all()`` and ``none()`` are also supported.
'(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
example, will catch all php files whose size is greater than 10 MB, all
files whose name ends with ".zip", and all files under "bin" in the repo
root except for "bin/README".
"""
tree = fileset.parse(text)
return _compile(tree)