##// 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:

r36669:6b1eb4c6 default
r36838:f33a87cf default
Show More
httpconnection.py
109 lines | 3.6 KiB | text/x-python | PythonLexer
# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Matt Mackall <mpm@selenic.com>
# Copyright 2006, 2007 Alexis S. L. Carvalho <alexis@cecm.usp.br>
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
# Copyright 2011 Google, 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
import os
from .i18n import _
from . import (
pycompat,
util,
)
urlerr = util.urlerr
urlreq = util.urlreq
# moved here from url.py to avoid a cycle
class httpsendfile(object):
"""This is a wrapper around the objects returned by python's "open".
Its purpose is to send file-like objects via HTTP.
It do however not define a __len__ attribute because the length
might be more than Py_ssize_t can handle.
"""
def __init__(self, ui, *args, **kwargs):
self.ui = ui
self._data = open(*args, **kwargs)
self.seek = self._data.seek
self.close = self._data.close
self.write = self._data.write
self.length = os.fstat(self._data.fileno()).st_size
self._pos = 0
self._total = self.length // 1024 * 2
def read(self, *args, **kwargs):
ret = self._data.read(*args, **kwargs)
if not ret:
self.ui.progress(_('sending'), None)
return ret
self._pos += len(ret)
# We pass double the max for total because we currently have
# to send the bundle twice in the case of a server that
# requires authentication. Since we can't know until we try
# once whether authentication will be required, just lie to
# the user and maybe the push succeeds suddenly at 50%.
self.ui.progress(_('sending'), self._pos // 1024,
unit=_('kb'), total=self._total)
return ret
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.close()
# moved here from url.py to avoid a cycle
def readauthforuri(ui, uri, user):
uri = pycompat.bytesurl(uri)
# Read configuration
groups = {}
for key, val in ui.configitems('auth'):
if key in ('cookiefile',):
continue
if '.' not in key:
ui.warn(_("ignoring invalid [auth] key '%s'\n") % key)
continue
group, setting = key.rsplit('.', 1)
gdict = groups.setdefault(group, {})
if setting in ('username', 'cert', 'key'):
val = util.expandpath(val)
gdict[setting] = val
# Find the best match
scheme, hostpath = uri.split('://', 1)
bestuser = None
bestlen = 0
bestauth = None
for group, auth in groups.iteritems():
if user and user != auth.get('username', user):
# If a username was set in the URI, the entry username
# must either match it or be unset
continue
prefix = auth.get('prefix')
if not prefix:
continue
p = prefix.split('://', 1)
if len(p) > 1:
schemes, prefix = [p[0]], p[1]
else:
schemes = (auth.get('schemes') or 'https').split()
if (prefix == '*' or hostpath.startswith(prefix)) and \
(len(prefix) > bestlen or (len(prefix) == bestlen and \
not bestuser and 'username' in auth)) \
and scheme in schemes:
bestlen = len(prefix)
bestauth = group, auth
bestuser = auth.get('username')
if user and not bestuser:
auth['username'] = user
return bestauth