##// END OF EJS Templates
deltas: set estimated compression upper bound to "3x" instead of "10x"...
deltas: set estimated compression upper bound to "3x" instead of "10x" In pratice, we very rarely observer compression better than "3x" on manifest deltas. Having a more aggressive estimate significantly helps our pathological use case on a private repository. Here are a comparison of timings using different upper bound. Estimated compression | ø | ×10 | ×5 | ×3 | timing | 14.11 | 2.61 | 1.96 | 1.53 | We also tested the impact of this series on an array of public repositories. This shown no impact in either size nor timing. Full data set below for those interested. Size ---- Regarding size, not significant impact have been noticed on neither public nor private repositories. Here are the number we gathered on public repositories: zlib/upperbound | no | 10x | 5x | 3x mercurial | 5 875 730 | 5 875 730 | 5 875 730 | 5 875 730 pypy | 27 782 913 | 27 782 913 | 27 782 913 | 27 782 913 netbeans | 159 161 207 | 159 161 207 | 159 161 207 | 159 959 879 (+0.5%) mozilla-central | 323 841 642 | 323 841 642 | 323 841 642 | 319 867 519 (-2.5%) mozilla-try | 746 649 123 | 746 649 123 | 746 649 123 | 741 155 568 (-0.7%) private-repo | 1 485 287 294 | 1 485 287 294 | 1 485 287 294 | 1 409 248 382 (-5.1%) zstd/upperbound | no | 10x | 5x | 3x mercurial | 5 895 206 | 5 895 206 | 5 895 206 | 5 895 206 pypy | 28 689 230 | 28 689 230 | 28 689 230 | 28 689 230 netbeans | 157 636 387 | 157 636 387 | 157 636 387 | 159 692 678 (+1.3%) mozilla-central | 317 650 281 | 317 650 281 | 317 650 281 | 319 613 603 (+0.6%) mozilla-try | 737 555 275 | 737 555 275 | 737 555 275 | 738 079 473 (+0.1%) private-repo | 1 352 362 982 | 1 352 362 982 | 1 346 961 880 | 1 361 327 384 (+0.7%) Speed ------ Timing gathered using `hg perfrevlogwrite -m`. Value are in seconds. mercurial zlib | no | 10x | 5x | 3x | total | 65.551783 | 65.388887 | 65.260658 | 65.321199 | max | 0.034544 | 0.034571 | 0.034659 | 0.034521 | 99.99% | 0.034544 | 0.034571 | 0.034659 | 0.034521 | zstd | no | 10x | 5x | 3x | total | 49.118449 | 49.054062 | 48.753588 | 48.740230 | max | 0.009338 | 0.009239 | 0.009202 | 0.009178 | 99.99% | 0.007618 | 0.007639 | 0.007626 | 0.007621 | pypy zlib | no | 10x | 5x | 3x | total | 560.865984 | 558.983817 | 559.083815 | 559.349152 | max | 0.219614 | 0.215922 | 0.218112 | 0.218107 | 99.99% | 0.219614 | 0.215922 | 0.218112 | 0.218107 | zstd | no | 10x | 5x | 3x | total | 349.393280 | 347.395819 | 347.185407 | 345.643985 | max | 0.084143 | 0.083536 | 0.081834 | 0.082178 | 99.99% | 0.039445 | 0.039639 | 0.039612 | 0.039175 | netbeans zlib | no | 10x | 5x | 3x | total | 33103.327727 | 33314.932260 | 33211.745233 | 33345.891778 | max | 2.666852 | 2.672059 | 2.662453 | 2.662936 | 99.99% | 2.058772 | 2.070429 | 2.069569 | 2.064653 | zstd | no | 10x | 5x | 3x | total | 20112.102708 | 20095.879719 | 20083.390300 | 20123.221859 | max | 2.063482 | 2.062851 | 2.065229 | 2.060147 | 99.99% | 1.146647 | 1.143794 | 1.142933 | 1.146529 | mozilla zlib | no | 10x | 5x | 3x | total | 41374.102138 | 41418.816773 | 41381.956370 | 41334.280732 | max | 3.383474 | 3.387400 | 3.405711 | 3.387316 | 99.99% | 1.006755 | 1.005954 | 1.007700 | 1.007373 | zstd | no | 10x | 5x | 3x | total | 24689.691520 | 24643.939662 | 24664.630027 | 24664.512714 | max | 1.460822 | 1.449640 | 1.439747 | 1.465304 | 99.99% | 0.527111 | 0.527377 | 0.527807 | 0.527226 |

File last commit:

r41700:78b270a5 default
r42669:4a3abb33 default
Show More
diffutil.py
108 lines | 4.5 KiB | text/x-python | PythonLexer
# diffutil.py - utility functions related to diff and patch
#
# Copyright 2006 Brendan Cully <brendan@kublai.com>
# Copyright 2007 Chris Mason <chris.mason@oracle.com>
# Copyright 2018 Octobus <octobus@octobus.net>
#
# 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 (
mdiff,
pycompat,
)
def diffallopts(ui, opts=None, untrusted=False, section='diff',
configprefix=''):
'''return diffopts with all features supported and parsed'''
return difffeatureopts(ui, opts=opts, untrusted=untrusted, section=section,
git=True, whitespace=True, formatchanging=True,
configprefix=configprefix)
def difffeatureopts(ui, opts=None, untrusted=False, section='diff', git=False,
whitespace=False, formatchanging=False, configprefix=''):
'''return diffopts with only opted-in features parsed
Features:
- git: git-style diffs
- whitespace: whitespace options like ignoreblanklines and ignorews
- formatchanging: options that will likely break or cause correctness issues
with most diff parsers
'''
def get(key, name=None, getter=ui.configbool, forceplain=None):
if opts:
v = opts.get(key)
# diffopts flags are either None-default (which is passed
# through unchanged, so we can identify unset values), or
# some other falsey default (eg --unified, which defaults
# to an empty string). We only want to override the config
# entries from hgrc with command line values if they
# appear to have been set, which is any truthy value,
# True, or False.
if v or isinstance(v, bool):
return v
if forceplain is not None and ui.plain():
return forceplain
return getter(section, configprefix + (name or key),
untrusted=untrusted)
# core options, expected to be understood by every diff parser
buildopts = {
'nodates': get('nodates'),
'showfunc': get('show_function', 'showfunc'),
'context': get('unified', getter=ui.config),
}
buildopts['xdiff'] = ui.configbool('experimental', 'xdiff')
if git:
buildopts['git'] = get('git')
# since this is in the experimental section, we need to call
# ui.configbool directory
buildopts['showsimilarity'] = ui.configbool('experimental',
'extendedheader.similarity')
# need to inspect the ui object instead of using get() since we want to
# test for an int
hconf = ui.config('experimental', 'extendedheader.index')
if hconf is not None:
hlen = None
try:
# the hash config could be an integer (for length of hash) or a
# word (e.g. short, full, none)
hlen = int(hconf)
if hlen < 0 or hlen > 40:
msg = _("invalid length for extendedheader.index: '%d'\n")
ui.warn(msg % hlen)
except ValueError:
# default value
if hconf == 'short' or hconf == '':
hlen = 12
elif hconf == 'full':
hlen = 40
elif hconf != 'none':
msg = _("invalid value for extendedheader.index: '%s'\n")
ui.warn(msg % hconf)
finally:
buildopts['index'] = hlen
if whitespace:
buildopts['ignorews'] = get('ignore_all_space', 'ignorews')
buildopts['ignorewsamount'] = get('ignore_space_change',
'ignorewsamount')
buildopts['ignoreblanklines'] = get('ignore_blank_lines',
'ignoreblanklines')
buildopts['ignorewseol'] = get('ignore_space_at_eol', 'ignorewseol')
if formatchanging:
buildopts['text'] = opts and opts.get('text')
binary = None if opts is None else opts.get('binary')
buildopts['nobinary'] = (not binary if binary is not None
else get('nobinary', forceplain=False))
buildopts['noprefix'] = get('noprefix', forceplain=False)
buildopts['worddiff'] = get('word_diff', 'word-diff', forceplain=False)
return mdiff.diffopts(**pycompat.strkwargs(buildopts))