Mercurial > hg
view mercurial/diffutil.py @ 42743:8c9a6adec67a
rust-discovery: using the children cache in add_missing
The DAG range computation often needs to get back to very old
revisions, and turns out to be disproportionately long, given
that the end goal is to remove the descendents of the given
missing revisons from the undecided set.
The fast iteration capabilities available in the Rust case make
it possible to avoid the DAG range entirely, at the cost of
precomputing the children cache, and to simply iterate on
children of the given missing revisions.
This is a case where staying on the same side of the interface
between the two languages has clear benefits.
On discoveries with initial undecided sets
small enough to bypass sampling entirely, the total cost of
computing the children cache and the subsequent iteration
becomes better than the Python + C counterpart, which relies on
reachableroots2.
For example, on a repo with more than one million revisions with
an initial undecided set of 11 elements, we get these figures:
Rust version with simple iteration
addcommons: 57.287us
first undecided computation: 184.278334ms
first children cache computation: 131.056us
addmissings iteration: 42.766us
first addinfo total: 185.24 ms
Python + C version
first addcommons: 0.29 ms
addcommons 0.21 ms
first undecided computation 191.35 ms
addmissings 45.75 ms
first addinfo total: 237.77 ms
On discoveries with large undecided sets, the initial price paid
makes the first addinfo slower than the Python + C version,
but that's more than compensated by the gain in sampling and
subsequent iterations.
Here's an extreme example with an undecided set of a million revisions:
Rust version:
first undecided computation: 293.842629ms
first children cache computation: 407.911297ms
addmissings iteration: 34.312869ms
first addinfo total: 776.02 ms
taking initial sample
query 2: sampling time: 1318.38 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings: 143.062us
Python + C version:
first undecided computation 298.13 ms
addmissings 80.13 ms
first addinfo total: 399.62 ms
taking initial sample
query 2: sampling time: 3957.23 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings 52.88 ms
Differential Revision: https://phab.mercurial-scm.org/D6428
author | Georges Racinet <georges.racinet@octobus.net> |
---|---|
date | Tue, 16 Apr 2019 01:16:39 +0200 |
parents | 78b270a55dc6 |
children | 2372284d9457 |
line wrap: on
line source
# 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))