outgoing: add a simple fastpath when there is no common
This further speed up case like `hg bundle --all` for larger repository.
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
before: 316.749699
after: 311.165461 (-1.76%, -5.58)
There is further work to be done in this area like not doing any outgoing
computation in the stream case for example. however the recent changes already
gives use a large win for a small amount of local work.
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
pre-%ln-change: 1.263859
the-%ln-change: 0.700229 (-44.60%, -0.56)
prev-changeset: 0.496050 (-60.75%, -0.77)
this-changeset: 0.495243 (-60.81%, -0.77)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
pre-%ln-change: 2.975765
the-%ln-change: 1.870798 (-37.13%, -1.10)
prev-changeset: 1.461583 (-50.88%, -1.51)
this-changeset: 1.469185 (-50.63%, -1.51)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
pre-%ln-change: 4.540080
the-%ln-change: 3.401700 (-25.07%, -1.14)
prev-changeset: 2.915810 (-35.78%, -1.62)
this-changeset: 2.911643 (-35.87%, -1.63)
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
pre-%ln-change: 10.138396
the-%ln-change: 7.750458 (-23.55%, -2.39)
prev-changeset: 6.665565 (-34.25%, -3.47)
this-changeset: 6.672078 (-34.19%, -3.47)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
pre-%ln-change: 399.484481
the-%ln-change: 346.508952 (-13.26%, -52.98)
prev-changeset: 316.749699 (-20.71%, -82.73)
this-changeset: 311.165461 (-22.11%, -88.32)
# automv.py
#
# Copyright 2013-2016 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.
"""check for unrecorded moves at commit time (EXPERIMENTAL)
This extension checks at commit/amend time if any of the committed files
comes from an unrecorded mv.
The threshold at which a file is considered a move can be set with the
``automv.similarity`` config option. This option takes a percentage between 0
(disabled) and 100 (files must be identical), the default is 95.
"""
# Using 95 as a default similarity is based on an analysis of the mercurial
# repositories of the cpython, mozilla-central & mercurial repositories, as
# well as 2 very large facebook repositories. At 95 50% of all potential
# missed moves would be caught, as well as correspond with 87% of all
# explicitly marked moves. Together, 80% of moved files are 95% similar or
# more.
#
# See http://markmail.org/thread/5pxnljesvufvom57 for context.
from mercurial.i18n import _
from mercurial import (
commands,
copies,
error,
extensions,
pycompat,
registrar,
scmutil,
similar,
)
configtable = {}
configitem = registrar.configitem(configtable)
configitem(
b'automv',
b'similarity',
default=95,
)
def extsetup(ui):
entry = extensions.wrapcommand(commands.table, b'commit', mvcheck)
entry[1].append(
(b'', b'no-automv', None, _(b'disable automatic file move detection'))
)
def mvcheck(orig, ui, repo, *pats, **opts):
"""Hook to check for moves at commit time"""
renames = None
disabled = opts.pop('no_automv', False)
with repo.wlock():
if not disabled:
threshold = ui.configint(b'automv', b'similarity')
if not 0 <= threshold <= 100:
raise error.Abort(
_(b'automv.similarity must be between 0 and 100')
)
if threshold > 0:
match = scmutil.match(
repo[None], pats, pycompat.byteskwargs(opts)
)
added, removed = _interestingfiles(repo, match)
uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
renames = _findrenames(
repo, uipathfn, added, removed, threshold / 100.0
)
if renames is not None:
with repo.dirstate.changing_files(repo):
# XXX this should be wider and integrated with the commit
# transaction. At the same time as we do the `addremove` logic
# for commit. However we can't really do better with the
# current extension structure, and this is not worse than what
# happened before.
scmutil._markchanges(repo, (), (), renames)
return orig(ui, repo, *pats, **opts)
def _interestingfiles(repo, matcher):
"""Find what files were added or removed in this commit.
Returns a tuple of two lists: (added, removed). Only files not *already*
marked as moved are included in the added list.
"""
stat = repo.status(match=matcher)
added = stat.added
removed = stat.removed
copy = copies.pathcopies(repo[b'.'], repo[None], matcher)
# remove the copy files for which we already have copy info
added = [f for f in added if f not in copy]
return added, removed
def _findrenames(repo, uipathfn, added, removed, similarity):
"""Find what files in added are really moved files.
Any file named in removed that is at least similarity% similar to a file
in added is seen as a rename.
"""
renames = {}
if similarity > 0:
for src, dst, score in similar.findrenames(
repo, added, removed, similarity
):
if repo.ui.verbose:
repo.ui.status(
_(b'detected move of %s as %s (%d%% similar)\n')
% (uipathfn(src), uipathfn(dst), score * 100)
)
renames[dst] = src
if renames:
repo.ui.status(_(b'detected move of %d files\n') % len(renames))
return renames