match: making visitdir() deal with non-recursive entries
Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).
I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
"hg files -r . -I rootfilesin:browser".
The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
subdirectories, with "hg files -r . -I rootfilesin:REDACTED".
I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.
These were the results:
Cold cache Warm cache
Before After Before After
firefox 0m5.1s 0m2.18s 0m0.22s 0m0.14s
google3 dir 2m3.9s 0m1.57s 0m8.12s 0m0.16s
Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).
# 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)