Mercurial > hg
view hgext/sparse.py @ 43301:90213d027154
sidedatacopies: only fetch information once for merge
Before this change, merge would result in reading the data from revlog twice.
With this change, we keep the information in memory until we encounter the other
parent.
When looking at pypy, I see about 1/3 of the changesets with copy information
being merge. Not doing duplicated fetch for them provide a significant speedup.
revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 0.767042 comb 0.760000 user 0.750000 sys 0.010000 (median of 11)
after: ! wall 0.671162 comb 0.670000 user 0.650000 sys 0.020000 (median of 13)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 1.170169 comb 1.170000 user 1.130000 sys 0.040000 (median of 10)
after: ! wall 1.030596 comb 1.040000 user 1.010000 sys 0.030000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.209846 comb 0.200000 user 0.200000 sys 0.000000 (median of 46)
after: ! wall 0.170981 comb 0.170000 user 0.170000 sys 0.000000 (median of 56)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013248 comb 0.010000 user 0.010000 sys 0.000000 (median of 223)
after: ! wall 0.013295 comb 0.020000 user 0.020000 sys 0.000000 (median of 222)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.001672 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after: ! wall 0.001666 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8010)
after: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 8007)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.168599 comb 0.160000 user 0.160000 sys 0.000000 (median of 58)
after: ! wall 0.133316 comb 0.140000 user 0.140000 sys 0.000000 (median of 73)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.036052 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)
after: ! wall 0.032558 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)
Differential Revision: https://phab.mercurial-scm.org/D7127
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Thu, 17 Oct 2019 02:17:24 +0200 |
parents | 66f2cc210a29 |
children | 9f70512ae2cf |
line wrap: on
line source
# sparse.py - allow sparse checkouts of the working directory # # Copyright 2014 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. """allow sparse checkouts of the working directory (EXPERIMENTAL) (This extension is not yet protected by backwards compatibility guarantees. Any aspect may break in future releases until this notice is removed.) This extension allows the working directory to only consist of a subset of files for the revision. This allows specific files or directories to be explicitly included or excluded. Many repository operations have performance proportional to the number of files in the working directory. So only realizing a subset of files in the working directory can improve performance. Sparse Config Files ------------------- The set of files that are part of a sparse checkout are defined by a sparse config file. The file defines 3 things: includes (files to include in the sparse checkout), excludes (files to exclude from the sparse checkout), and profiles (links to other config files). The file format is newline delimited. Empty lines and lines beginning with ``#`` are ignored. Lines beginning with ``%include `` denote another sparse config file to include. e.g. ``%include tests.sparse``. The filename is relative to the repository root. The special lines ``[include]`` and ``[exclude]`` denote the section for includes and excludes that follow, respectively. It is illegal to have ``[include]`` after ``[exclude]``. Non-special lines resemble file patterns to be added to either includes or excludes. The syntax of these lines is documented by :hg:`help patterns`. Patterns are interpreted as ``glob:`` by default and match against the root of the repository. Exclusion patterns take precedence over inclusion patterns. So even if a file is explicitly included, an ``[exclude]`` entry can remove it. For example, say you have a repository with 3 directories, ``frontend/``, ``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond to different projects and it is uncommon for someone working on one to need the files for the other. But ``tools/`` contains files shared between both projects. Your sparse config files may resemble:: # frontend.sparse frontend/** tools/** # backend.sparse backend/** tools/** Say the backend grows in size. Or there's a directory with thousands of files you wish to exclude. You can modify the profile to exclude certain files:: [include] backend/** tools/** [exclude] tools/tests/** """ from __future__ import absolute_import from mercurial.i18n import _ from mercurial.pycompat import setattr from mercurial import ( commands, dirstate, error, extensions, hg, logcmdutil, match as matchmod, pycompat, registrar, sparse, util, ) # 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 = b'ships-with-hg-core' cmdtable = {} command = registrar.command(cmdtable) def extsetup(ui): sparse.enabled = True _setupclone(ui) _setuplog(ui) _setupadd(ui) _setupdirstate(ui) def replacefilecache(cls, propname, replacement): """Replace a filecache property with a new class. This allows changing the cache invalidation condition.""" origcls = cls assert callable(replacement) while cls is not object: if propname in cls.__dict__: orig = cls.__dict__[propname] setattr(cls, propname, replacement(orig)) break cls = cls.__bases__[0] if cls is object: raise AttributeError( _(b"type '%s' has no property '%s'") % (origcls, propname) ) def _setuplog(ui): entry = commands.table[b'log|history'] entry[1].append( ( b'', b'sparse', None, b"limit to changesets affecting the sparse checkout", ) ) def _initialrevs(orig, repo, opts): revs = orig(repo, opts) if opts.get(b'sparse'): sparsematch = sparse.matcher(repo) def ctxmatch(rev): ctx = repo[rev] return any(f for f in ctx.files() if sparsematch(f)) revs = revs.filter(ctxmatch) return revs extensions.wrapfunction(logcmdutil, b'_initialrevs', _initialrevs) def _clonesparsecmd(orig, ui, repo, *args, **opts): include_pat = opts.get(r'include') exclude_pat = opts.get(r'exclude') enableprofile_pat = opts.get(r'enable_profile') narrow_pat = opts.get(r'narrow') include = exclude = enableprofile = False if include_pat: pat = include_pat include = True if exclude_pat: pat = exclude_pat exclude = True if enableprofile_pat: pat = enableprofile_pat enableprofile = True if sum([include, exclude, enableprofile]) > 1: raise error.Abort(_(b"too many flags specified.")) # if --narrow is passed, it means they are includes and excludes for narrow # clone if not narrow_pat and (include or exclude or enableprofile): def clonesparse(orig, self, node, overwrite, *args, **kwargs): sparse.updateconfig( self.unfiltered(), pat, {}, include=include, exclude=exclude, enableprofile=enableprofile, usereporootpaths=True, ) return orig(self, node, overwrite, *args, **kwargs) extensions.wrapfunction(hg, b'updaterepo', clonesparse) return orig(ui, repo, *args, **opts) def _setupclone(ui): entry = commands.table[b'clone'] entry[1].append((b'', b'enable-profile', [], b'enable a sparse profile')) entry[1].append((b'', b'include', [], b'include sparse pattern')) entry[1].append((b'', b'exclude', [], b'exclude sparse pattern')) extensions.wrapcommand(commands.table, b'clone', _clonesparsecmd) def _setupadd(ui): entry = commands.table[b'add'] entry[1].append( ( b's', b'sparse', None, b'also include directories of added files in sparse config', ) ) def _add(orig, ui, repo, *pats, **opts): if opts.get(r'sparse'): dirs = set() for pat in pats: dirname, basename = util.split(pat) dirs.add(dirname) sparse.updateconfig(repo, list(dirs), opts, include=True) return orig(ui, repo, *pats, **opts) extensions.wrapcommand(commands.table, b'add', _add) def _setupdirstate(ui): """Modify the dirstate to prevent stat'ing excluded files, and to prevent modifications to files outside the checkout. """ def walk(orig, self, match, subrepos, unknown, ignored, full=True): # hack to not exclude explicitly-specified paths so that they can # be warned later on e.g. dirstate.add() em = matchmod.exact(match.files()) sm = matchmod.unionmatcher([self._sparsematcher, em]) match = matchmod.intersectmatchers(match, sm) return orig(self, match, subrepos, unknown, ignored, full) extensions.wrapfunction(dirstate.dirstate, b'walk', walk) # dirstate.rebuild should not add non-matching files def _rebuild(orig, self, parent, allfiles, changedfiles=None): matcher = self._sparsematcher if not matcher.always(): allfiles = [f for f in allfiles if matcher(f)] if changedfiles: changedfiles = [f for f in changedfiles if matcher(f)] if changedfiles is not None: # In _rebuild, these files will be deleted from the dirstate # when they are not found to be in allfiles dirstatefilestoremove = set(f for f in self if not matcher(f)) changedfiles = dirstatefilestoremove.union(changedfiles) return orig(self, parent, allfiles, changedfiles) extensions.wrapfunction(dirstate.dirstate, b'rebuild', _rebuild) # Prevent adding files that are outside the sparse checkout editfuncs = [ b'normal', b'add', b'normallookup', b'copy', b'remove', b'merge', ] hint = _( b'include file with `hg debugsparse --include <pattern>` or use ' + b'`hg add -s <file>` to include file directory while adding' ) for func in editfuncs: def _wrapper(orig, self, *args, **kwargs): sparsematch = self._sparsematcher if not sparsematch.always(): for f in args: if f is not None and not sparsematch(f) and f not in self: raise error.Abort( _( b"cannot add '%s' - it is outside " b"the sparse checkout" ) % f, hint=hint, ) return orig(self, *args, **kwargs) extensions.wrapfunction(dirstate.dirstate, func, _wrapper) @command( b'debugsparse', [ (b'I', b'include', False, _(b'include files in the sparse checkout')), (b'X', b'exclude', False, _(b'exclude files in the sparse checkout')), (b'd', b'delete', False, _(b'delete an include/exclude rule')), ( b'f', b'force', False, _(b'allow changing rules even with pending changes'), ), (b'', b'enable-profile', False, _(b'enables the specified profile')), (b'', b'disable-profile', False, _(b'disables the specified profile')), (b'', b'import-rules', False, _(b'imports rules from a file')), (b'', b'clear-rules', False, _(b'clears local include/exclude rules')), ( b'', b'refresh', False, _(b'updates the working after sparseness changes'), ), (b'', b'reset', False, _(b'makes the repo full again')), ] + commands.templateopts, _(b'[--OPTION] PATTERN...'), helpbasic=True, ) def debugsparse(ui, repo, *pats, **opts): """make the current checkout sparse, or edit the existing checkout The sparse command is used to make the current checkout sparse. This means files that don't meet the sparse condition will not be written to disk, or show up in any working copy operations. It does not affect files in history in any way. Passing no arguments prints the currently applied sparse rules. --include and --exclude are used to add and remove files from the sparse checkout. The effects of adding an include or exclude rule are applied immediately. If applying the new rule would cause a file with pending changes to be added or removed, the command will fail. Pass --force to force a rule change even with pending changes (the changes on disk will be preserved). --delete removes an existing include/exclude rule. The effects are immediate. --refresh refreshes the files on disk based on the sparse rules. This is only necessary if .hg/sparse was changed by hand. --enable-profile and --disable-profile accept a path to a .hgsparse file. This allows defining sparse checkouts and tracking them inside the repository. This is useful for defining commonly used sparse checkouts for many people to use. As the profile definition changes over time, the sparse checkout will automatically be updated appropriately, depending on which changeset is checked out. Changes to .hgsparse are not applied until they have been committed. --import-rules accepts a path to a file containing rules in the .hgsparse format, allowing you to add --include, --exclude and --enable-profile rules in bulk. Like the --include, --exclude and --enable-profile switches, the changes are applied immediately. --clear-rules removes all local include and exclude rules, while leaving any enabled profiles in place. Returns 0 if editing the sparse checkout succeeds. """ opts = pycompat.byteskwargs(opts) include = opts.get(b'include') exclude = opts.get(b'exclude') force = opts.get(b'force') enableprofile = opts.get(b'enable_profile') disableprofile = opts.get(b'disable_profile') importrules = opts.get(b'import_rules') clearrules = opts.get(b'clear_rules') delete = opts.get(b'delete') refresh = opts.get(b'refresh') reset = opts.get(b'reset') count = sum( [ include, exclude, enableprofile, disableprofile, delete, importrules, refresh, clearrules, reset, ] ) if count > 1: raise error.Abort(_(b"too many flags specified")) if count == 0: if repo.vfs.exists(b'sparse'): ui.status(repo.vfs.read(b"sparse") + b"\n") temporaryincludes = sparse.readtemporaryincludes(repo) if temporaryincludes: ui.status( _(b"Temporarily Included Files (for merge/rebase):\n") ) ui.status((b"\n".join(temporaryincludes) + b"\n")) return else: raise error.Abort( _( b'the debugsparse command is only supported on' b' sparse repositories' ) ) if include or exclude or delete or reset or enableprofile or disableprofile: sparse.updateconfig( repo, pats, opts, include=include, exclude=exclude, reset=reset, delete=delete, enableprofile=enableprofile, disableprofile=disableprofile, force=force, ) if importrules: sparse.importfromfiles(repo, opts, pats, force=force) if clearrules: sparse.clearrules(repo, force=force) if refresh: try: wlock = repo.wlock() fcounts = map( len, sparse.refreshwdir( repo, repo.status(), sparse.matcher(repo), force=force ), ) sparse.printchanges( ui, opts, added=fcounts[0], dropped=fcounts[1], conflicting=fcounts[2], ) finally: wlock.release()