Mercurial > hg
view hgext/share.py @ 30561:7c0c722d568d
bdiff: early pruning of common prefix before doing expensive computations
It seems quite common that files don't change completely. New lines are often
pretty much appended, and modifications will often only change a small section
of the file which on average will be in the middle.
There can thus be a big win by pruning a common prefix before starting the more
expensive search for longest common substrings.
Worst case, it will scan through a long sequence of similar bytes without
encountering a newline. Splitlines will then have to do the same again ...
twice for each side. If similar lines are found, splitlines will save the
double iteration and hashing of the lines ... plus there will be less lines to
find common substrings in.
This change might in some cases make the algorith pick shorter or less optimal
common substrings. We can't have the cake and eat it.
This make hg --time bundle --base null -r 4.0 go from 14.5 to 15 s - a 3%
increase.
On mozilla-unified:
perfbdiff -m 3041e4d59df2
! wall 0.053088 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) to
! wall 0.024618 comb 0.020000 user 0.020000 sys 0.000000 (best of 116)
perfbdiff 0e9928989e9c --alldata --count 10
! wall 0.702075 comb 0.700000 user 0.700000 sys 0.000000 (best of 15) to
! wall 0.579235 comb 0.580000 user 0.580000 sys 0.000000 (best of 18)
author | Mads Kiilerich <madski@unity3d.com> |
---|---|
date | Wed, 16 Nov 2016 19:45:35 +0100 |
parents | d5883fd055c6 |
children | 0332b8fafd05 |
line wrap: on
line source
# Copyright 2006, 2007 Matt Mackall <mpm@selenic.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. '''share a common history between several working directories Automatic Pooled Storage for Clones ----------------------------------- When this extension is active, :hg:`clone` can be configured to automatically share/pool storage across multiple clones. This mode effectively converts :hg:`clone` to :hg:`clone` + :hg:`share`. The benefit of using this mode is the automatic management of store paths and intelligent pooling of related repositories. The following ``share.`` config options influence this feature: ``share.pool`` Filesystem path where shared repository data will be stored. When defined, :hg:`clone` will automatically use shared repository storage instead of creating a store inside each clone. ``share.poolnaming`` How directory names in ``share.pool`` are constructed. "identity" means the name is derived from the first changeset in the repository. In this mode, different remotes share storage if their root/initial changeset is identical. In this mode, the local shared repository is an aggregate of all encountered remote repositories. "remote" means the name is derived from the source repository's path or URL. In this mode, storage is only shared if the path or URL requested in the :hg:`clone` command matches exactly to a repository that was cloned before. The default naming mode is "identity." ''' from __future__ import absolute_import import errno from mercurial.i18n import _ from mercurial import ( bookmarks, cmdutil, commands, error, extensions, hg, util, ) repository = hg.repository parseurl = hg.parseurl cmdtable = {} command = cmdutil.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('share', [('U', 'noupdate', None, _('do not create a working directory')), ('B', 'bookmarks', None, _('also share bookmarks'))], _('[-U] [-B] SOURCE [DEST]'), norepo=True) def share(ui, source, dest=None, noupdate=False, bookmarks=False): """create a new shared repository Initialize a new repository and working directory that shares its history (and optionally bookmarks) with another repository. .. note:: using rollback or extensions that destroy/modify history (mq, rebase, etc.) can cause considerable confusion with shared clones. In particular, if two shared clones are both updated to the same changeset, and one of them destroys that changeset with rollback, the other clone will suddenly stop working: all operations will fail with "abort: working directory has unknown parent". The only known workaround is to use debugsetparents on the broken clone to reset it to a changeset that still exists. """ return hg.share(ui, source, dest=dest, update=not noupdate, bookmarks=bookmarks) @command('unshare', [], '') def unshare(ui, repo): """convert a shared repository to a normal one Copy the store data to the repo and remove the sharedpath data. """ if not repo.shared(): raise error.Abort(_("this is not a shared repo")) destlock = lock = None lock = repo.lock() try: # we use locks here because if we race with commit, we # can end up with extra data in the cloned revlogs that's # not pointed to by changesets, thus causing verify to # fail destlock = hg.copystore(ui, repo, repo.path) sharefile = repo.join('sharedpath') util.rename(sharefile, sharefile + '.old') repo.requirements.discard('sharedpath') repo._writerequirements() finally: destlock and destlock.release() lock and lock.release() # update store, spath, svfs and sjoin of repo repo.unfiltered().__init__(repo.baseui, repo.root) # Wrap clone command to pass auto share options. def clone(orig, ui, source, *args, **opts): pool = ui.config('share', 'pool', None) if pool: pool = util.expandpath(pool) opts['shareopts'] = dict( pool=pool, mode=ui.config('share', 'poolnaming', 'identity'), ) return orig(ui, source, *args, **opts) def extsetup(ui): extensions.wrapfunction(bookmarks, '_getbkfile', getbkfile) extensions.wrapfunction(bookmarks.bmstore, 'recordchange', recordchange) extensions.wrapfunction(bookmarks.bmstore, '_writerepo', writerepo) extensions.wrapcommand(commands.table, 'clone', clone) def _hassharedbookmarks(repo): """Returns whether this repo has shared bookmarks""" try: shared = repo.vfs.read('shared').splitlines() except IOError as inst: if inst.errno != errno.ENOENT: raise return False return hg.sharedbookmarks in shared def _getsrcrepo(repo): """ Returns the source repository object for a given shared repository. If repo is not a shared repository, return None. """ if repo.sharedpath == repo.path: return None if util.safehasattr(repo, 'srcrepo') and repo.srcrepo: return repo.srcrepo # the sharedpath always ends in the .hg; we want the path to the repo source = repo.vfs.split(repo.sharedpath)[0] srcurl, branches = parseurl(source) srcrepo = repository(repo.ui, srcurl) repo.srcrepo = srcrepo return srcrepo def getbkfile(orig, repo): if _hassharedbookmarks(repo): srcrepo = _getsrcrepo(repo) if srcrepo is not None: repo = srcrepo return orig(repo) def recordchange(orig, self, tr): # Continue with write to local bookmarks file as usual orig(self, tr) if _hassharedbookmarks(self._repo): srcrepo = _getsrcrepo(self._repo) if srcrepo is not None: category = 'share-bookmarks' tr.addpostclose(category, lambda tr: self._writerepo(srcrepo)) def writerepo(orig, self, repo): # First write local bookmarks file in case we ever unshare orig(self, repo) if _hassharedbookmarks(self._repo): srcrepo = _getsrcrepo(self._repo) if srcrepo is not None: orig(self, srcrepo)