Mercurial > hg
view hgext/purge.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 | c303d65d2e34 |
children | 2372284d9457 |
line wrap: on
line source
# Copyright (C) 2006 - Marco Barisione <marco@barisione.org> # # This is a small extension for Mercurial (https://mercurial-scm.org/) # that removes files not known to mercurial # # This program was inspired by the "cvspurge" script contained in CVS # utilities (http://www.red-bean.com/cvsutils/). # # For help on the usage of "hg purge" use: # hg help purge # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, see <http://www.gnu.org/licenses/>. '''command to delete untracked files from the working directory''' from __future__ import absolute_import from mercurial.i18n import _ from mercurial import ( cmdutil, merge as mergemod, pycompat, registrar, scmutil, ) cmdtable = {} command = registrar.command(cmdtable) # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # be specifying the version(s) of Mercurial they are tested with, or # leave the attribute unspecified. testedwith = 'ships-with-hg-core' @command('purge|clean', [('a', 'abort-on-err', None, _('abort if an error occurs')), ('', 'all', None, _('purge ignored files too')), ('', 'dirs', None, _('purge empty directories')), ('', 'files', None, _('purge files')), ('p', 'print', None, _('print filenames instead of deleting them')), ('0', 'print0', None, _('end filenames with NUL, for use with xargs' ' (implies -p/--print)')), ] + cmdutil.walkopts, _('hg purge [OPTION]... [DIR]...'), helpcategory=command.CATEGORY_MAINTENANCE) def purge(ui, repo, *dirs, **opts): '''removes files not tracked by Mercurial Delete files not known to Mercurial. This is useful to test local and uncommitted changes in an otherwise-clean source tree. This means that purge will delete the following by default: - Unknown files: files marked with "?" by :hg:`status` - Empty directories: in fact Mercurial ignores directories unless they contain files under source control management But it will leave untouched: - Modified and unmodified tracked files - Ignored files (unless --all is specified) - New files added to the repository (with :hg:`add`) The --files and --dirs options can be used to direct purge to delete only files, only directories, or both. If neither option is given, both will be deleted. If directories are given on the command line, only files in these directories are considered. Be careful with purge, as you could irreversibly delete some files you forgot to add to the repository. If you only want to print the list of files that this program would delete, use the --print option. ''' opts = pycompat.byteskwargs(opts) act = not opts.get('print') eol = '\n' if opts.get('print0'): eol = '\0' act = False # --print0 implies --print removefiles = opts.get('files') removedirs = opts.get('dirs') if not removefiles and not removedirs: removefiles = True removedirs = True match = scmutil.match(repo[None], dirs, opts) paths = mergemod.purge( repo, match, ignored=opts.get('all', False), removeemptydirs=removedirs, removefiles=removefiles, abortonerror=opts.get('abort_on_err'), noop=not act) for path in paths: if not act: ui.write('%s%s' % (path, eol))