##// END OF EJS Templates
pathcopies: give up any optimization based on `introrev`...
pathcopies: give up any optimization based on `introrev` Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the introduction revision during path copies. However, further checking show that finding the introduction revision is still expensive and that we are better off without it. So we simply drop it and only rely on the linkrev optimisation. I ran `perfpathcopies` on 6989 pair of revision in the pypy repository (`hg perfhelper-pathcopies`. The result is massively in favor of dropping this condition. The result of the copy tracing are unchanged. Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it can return wrong result. The following changesets broke test-mv-cp-st-diff.t - if not f.isintroducedafter(limit): + if limit >= 0 and f.linkrev() < limit: return None Here are various numbers (before this changeset/after this changesets) source destination before after saved-time ratio worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675 c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743 22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420 682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074 5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817 worse 1% dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320 worse 5% c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488 worse 10% 3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156 worse 25% 321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259 median 2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947 best 25% 915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673 best 10% ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278 best 5% d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126 best 1% 81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813 best cases c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483 c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508 058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442 9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463 442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487 As one can see, the average case is not really impacted. However, the worth case we get after this changeset are much better than the one we had before it. We have 30 pairs where improvements are above 10 minutes. This reflect in the combined time for all pairs before: 26256s after: 1300s (-95%) If we remove these pathological 30 cases, we still see a significant improvements: before: 1631s after: 1245s (-24%)

File last commit:

r43375:649d3ac3 default
r43469:c16fe77e default
Show More
bzr.py
331 lines | 11.9 KiB | text/x-python | PythonLexer
# bzr.py - bzr support for the convert extension
#
# Copyright 2008, 2009 Marek Kubica <marek@xivilization.net> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
# This module is for handling 'bzr', that was formerly known as Bazaar-NG;
# it cannot access 'bar' repositories, but they were never used very much
from __future__ import absolute_import
import os
from mercurial.i18n import _
from mercurial import (
demandimport,
error,
pycompat,
)
from . import common
# these do not work with demandimport, blacklist
demandimport.IGNORES.update(
[b'bzrlib.transactions', b'bzrlib.urlutils', b'ElementPath',]
)
try:
# bazaar imports
import bzrlib.bzrdir
import bzrlib.errors
import bzrlib.revision
import bzrlib.revisionspec
bzrdir = bzrlib.bzrdir
errors = bzrlib.errors
revision = bzrlib.revision
revisionspec = bzrlib.revisionspec
revisionspec.RevisionSpec
except ImportError:
pass
supportedkinds = (b'file', b'symlink')
class bzr_source(common.converter_source):
"""Reads Bazaar repositories by using the Bazaar Python libraries"""
def __init__(self, ui, repotype, path, revs=None):
super(bzr_source, self).__init__(ui, repotype, path, revs=revs)
if not os.path.exists(os.path.join(path, b'.bzr')):
raise common.NoRepo(
_(b'%s does not look like a Bazaar repository') % path
)
try:
# access bzrlib stuff
bzrdir
except NameError:
raise common.NoRepo(_(b'Bazaar modules could not be loaded'))
path = os.path.abspath(path)
self._checkrepotype(path)
try:
self.sourcerepo = bzrdir.BzrDir.open(path).open_repository()
except errors.NoRepositoryPresent:
raise common.NoRepo(
_(b'%s does not look like a Bazaar repository') % path
)
self._parentids = {}
self._saverev = ui.configbool(b'convert', b'bzr.saverev')
def _checkrepotype(self, path):
# Lightweight checkouts detection is informational but probably
# fragile at API level. It should not terminate the conversion.
try:
dir = bzrdir.BzrDir.open_containing(path)[0]
try:
tree = dir.open_workingtree(recommend_upgrade=False)
branch = tree.branch
except (errors.NoWorkingTree, errors.NotLocalUrl):
tree = None
branch = dir.open_branch()
if (
tree is not None
and tree.bzrdir.root_transport.base
!= branch.bzrdir.root_transport.base
):
self.ui.warn(
_(
b'warning: lightweight checkouts may cause '
b'conversion failures, try with a regular '
b'branch instead.\n'
)
)
except Exception:
self.ui.note(_(b'bzr source type could not be determined\n'))
def before(self):
"""Before the conversion begins, acquire a read lock
for all the operations that might need it. Fortunately
read locks don't block other reads or writes to the
repository, so this shouldn't have any impact on the usage of
the source repository.
The alternative would be locking on every operation that
needs locks (there are currently two: getting the file and
getting the parent map) and releasing immediately after,
but this approach can take even 40% longer."""
self.sourcerepo.lock_read()
def after(self):
self.sourcerepo.unlock()
def _bzrbranches(self):
return self.sourcerepo.find_branches(using=True)
def getheads(self):
if not self.revs:
# Set using=True to avoid nested repositories (see issue3254)
heads = sorted([b.last_revision() for b in self._bzrbranches()])
else:
revid = None
for branch in self._bzrbranches():
try:
r = revisionspec.RevisionSpec.from_string(self.revs[0])
info = r.in_history(branch)
except errors.BzrError:
pass
revid = info.rev_id
if revid is None:
raise error.Abort(
_(b'%s is not a valid revision') % self.revs[0]
)
heads = [revid]
# Empty repositories return 'null:', which cannot be retrieved
heads = [h for h in heads if h != b'null:']
return heads
def getfile(self, name, rev):
revtree = self.sourcerepo.revision_tree(rev)
fileid = revtree.path2id(name.decode(self.encoding or b'utf-8'))
kind = None
if fileid is not None:
kind = revtree.kind(fileid)
if kind not in supportedkinds:
# the file is not available anymore - was deleted
return None, None
mode = self._modecache[(name, rev)]
if kind == b'symlink':
target = revtree.get_symlink_target(fileid)
if target is None:
raise error.Abort(
_(b'%s.%s symlink has no target') % (name, rev)
)
return target, mode
else:
sio = revtree.get_file(fileid)
return sio.read(), mode
def getchanges(self, version, full):
if full:
raise error.Abort(_(b"convert from cvs does not support --full"))
self._modecache = {}
self._revtree = self.sourcerepo.revision_tree(version)
# get the parentids from the cache
parentids = self._parentids.pop(version)
# only diff against first parent id
prevtree = self.sourcerepo.revision_tree(parentids[0])
files, changes = self._gettreechanges(self._revtree, prevtree)
return files, changes, set()
def getcommit(self, version):
rev = self.sourcerepo.get_revision(version)
# populate parent id cache
if not rev.parent_ids:
parents = []
self._parentids[version] = (revision.NULL_REVISION,)
else:
parents = self._filterghosts(rev.parent_ids)
self._parentids[version] = parents
branch = self.recode(rev.properties.get(b'branch-nick', u'default'))
if branch == b'trunk':
branch = b'default'
return common.commit(
parents=parents,
date=b'%d %d' % (rev.timestamp, -rev.timezone),
author=self.recode(rev.committer),
desc=self.recode(rev.message),
branch=branch,
rev=version,
saverev=self._saverev,
)
def gettags(self):
bytetags = {}
for branch in self._bzrbranches():
if not branch.supports_tags():
return {}
tagdict = branch.tags.get_tag_dict()
for name, rev in pycompat.iteritems(tagdict):
bytetags[self.recode(name)] = rev
return bytetags
def getchangedfiles(self, rev, i):
self._modecache = {}
curtree = self.sourcerepo.revision_tree(rev)
if i is not None:
parentid = self._parentids[rev][i]
else:
# no parent id, get the empty revision
parentid = revision.NULL_REVISION
prevtree = self.sourcerepo.revision_tree(parentid)
changes = [e[0] for e in self._gettreechanges(curtree, prevtree)[0]]
return changes
def _gettreechanges(self, current, origin):
revid = current._revision_id
changes = []
renames = {}
seen = set()
# Fall back to the deprecated attribute for legacy installations.
try:
inventory = origin.root_inventory
except AttributeError:
inventory = origin.inventory
# Process the entries by reverse lexicographic name order to
# handle nested renames correctly, most specific first.
curchanges = sorted(
current.iter_changes(origin),
key=lambda c: c[1][0] or c[1][1],
reverse=True,
)
for (
fileid,
paths,
changed_content,
versioned,
parent,
name,
kind,
executable,
) in curchanges:
if paths[0] == u'' or paths[1] == u'':
# ignore changes to tree root
continue
# bazaar tracks directories, mercurial does not, so
# we have to rename the directory contents
if kind[1] == b'directory':
if kind[0] not in (None, b'directory'):
# Replacing 'something' with a directory, record it
# so it can be removed.
changes.append((self.recode(paths[0]), revid))
if kind[0] == b'directory' and None not in paths:
renaming = paths[0] != paths[1]
# neither an add nor an delete - a move
# rename all directory contents manually
subdir = inventory.path2id(paths[0])
# get all child-entries of the directory
for name, entry in inventory.iter_entries(subdir):
# hg does not track directory renames
if entry.kind == b'directory':
continue
frompath = self.recode(paths[0] + b'/' + name)
if frompath in seen:
# Already handled by a more specific change entry
# This is important when you have:
# a => b
# a/c => a/c
# Here a/c must not be renamed into b/c
continue
seen.add(frompath)
if not renaming:
continue
topath = self.recode(paths[1] + b'/' + name)
# register the files as changed
changes.append((frompath, revid))
changes.append((topath, revid))
# add to mode cache
mode = (
(entry.executable and b'x')
or (entry.kind == b'symlink' and b's')
or b''
)
self._modecache[(topath, revid)] = mode
# register the change as move
renames[topath] = frompath
# no further changes, go to the next change
continue
# we got unicode paths, need to convert them
path, topath = paths
if path is not None:
path = self.recode(path)
if topath is not None:
topath = self.recode(topath)
seen.add(path or topath)
if topath is None:
# file deleted
changes.append((path, revid))
continue
# renamed
if path and path != topath:
renames[topath] = path
changes.append((path, revid))
# populate the mode cache
kind, executable = [e[1] for e in (kind, executable)]
mode = (executable and b'x') or (kind == b'symlink' and b'l') or b''
self._modecache[(topath, revid)] = mode
changes.append((topath, revid))
return changes, renames
def _filterghosts(self, ids):
"""Filters out ghost revisions which hg does not support, see
<http://bazaar-vcs.org/GhostRevision>
"""
parentmap = self.sourcerepo.get_parent_map(ids)
parents = tuple([parent for parent in ids if parent in parentmap])
return parents