copies: move from a copy on branchpoint to a copy on write approach
Before this changes, any branch points results in a copy of the dictionary containing the
copy information. This can be very costly for branchy history with few rename
information. Instead, we take a "copy on write" approach. Copying the input data
only when we are about to update them.
In practice we where already doing the copying in half of these case (because
`_chain` makes a copy), so we don't add a significant cost here even in the
linear case. However the speed up in branchy case is very significant. Here are
some timing on the pypy repository.
revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 1.399863 comb 1.400000 user 1.370000 sys 0.030000 (median of 10)
after: ! wall 0.766453 comb 0.770000 user 0.750000 sys 0.020000 (median of 11)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 1.876748 comb 1.890000 user 1.870000 sys 0.020000 (median of 10)
after: ! wall 1.167223 comb 1.170000 user 1.150000 sys 0.020000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.242457 comb 0.240000 user 0.240000 sys 0.000000 (median of 39)
after: ! wall 0.211476 comb 0.210000 user 0.210000 sys 0.000000 (median of 45)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013193 comb 0.020000 user 0.020000 sys 0.000000 (median of 224)
after: ! wall 0.013290 comb 0.010000 user 0.010000 sys 0.000000 (median of 222)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.001673 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after: ! wall 0.001677 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 8023)
after: ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 7997)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.201898 comb 0.210000 user 0.200000 sys 0.010000 (median of 48)
after: ! wall 0.167415 comb 0.170000 user 0.160000 sys 0.010000 (median of 58)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.036820 comb 0.040000 user 0.040000 sys 0.000000 (median of 100)
after: ! wall 0.035797 comb 0.040000 user 0.040000 sys 0.000000 (median of 100)
The extra cost in the linear case can be reclaimed later with some extra logic.
Differential Revision: https://phab.mercurial-scm.org/D7124
# uncommit - undo the actions of a commit
#
# Copyright 2011 Peter Arrenbrecht <peter.arrenbrecht@gmail.com>
# Logilab SA <contact@logilab.fr>
# Pierre-Yves David <pierre-yves.david@ens-lyon.org>
# Patrick Mezard <patrick@mezard.eu>
# Copyright 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.
"""uncommit part or all of a local changeset (EXPERIMENTAL)
This command undoes the effect of a local commit, returning the affected
files to their uncommitted state. This means that files modified, added or
removed in the changeset will be left unchanged, and so will remain modified,
added and removed in the working directory.
"""
from __future__ import absolute_import
from mercurial.i18n import _
from mercurial import (
cmdutil,
commands,
context,
copies as copiesmod,
error,
node,
obsutil,
pycompat,
registrar,
rewriteutil,
scmutil,
util,
)
cmdtable = {}
command = registrar.command(cmdtable)
configtable = {}
configitem = registrar.configitem(configtable)
configitem(
b'experimental', b'uncommitondirtywdir', default=False,
)
configitem(
b'experimental', b'uncommit.keep', default=False,
)
# 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'
def _commitfiltered(
repo, ctx, match, keepcommit, message=None, user=None, date=None
):
"""Recommit ctx with changed files not in match. Return the new
node identifier, or None if nothing changed.
"""
base = ctx.p1()
# ctx
initialfiles = set(ctx.files())
exclude = set(f for f in initialfiles if match(f))
# No files matched commit, so nothing excluded
if not exclude:
return None
# return the p1 so that we don't create an obsmarker later
if not keepcommit:
return ctx.p1().node()
files = initialfiles - exclude
# Filter copies
copied = copiesmod.pathcopies(base, ctx)
copied = dict(
(dst, src) for dst, src in pycompat.iteritems(copied) if dst in files
)
def filectxfn(repo, memctx, path, contentctx=ctx, redirect=()):
if path not in contentctx:
return None
fctx = contentctx[path]
mctx = context.memfilectx(
repo,
memctx,
fctx.path(),
fctx.data(),
fctx.islink(),
fctx.isexec(),
copysource=copied.get(path),
)
return mctx
if not files:
repo.ui.status(_(b"note: keeping empty commit\n"))
if message is None:
message = ctx.description()
if not user:
user = ctx.user()
if not date:
date = ctx.date()
new = context.memctx(
repo,
parents=[base.node(), node.nullid],
text=message,
files=files,
filectxfn=filectxfn,
user=user,
date=date,
extra=ctx.extra(),
)
return repo.commitctx(new)
@command(
b'uncommit',
[
(b'', b'keep', None, _(b'allow an empty commit after uncommitting')),
(
b'',
b'allow-dirty-working-copy',
False,
_(b'allow uncommit with outstanding changes'),
),
(b'n', b'note', b'', _(b'store a note on uncommit'), _(b'TEXT')),
]
+ commands.walkopts
+ commands.commitopts
+ commands.commitopts2
+ commands.commitopts3,
_(b'[OPTION]... [FILE]...'),
helpcategory=command.CATEGORY_CHANGE_MANAGEMENT,
)
def uncommit(ui, repo, *pats, **opts):
"""uncommit part or all of a local changeset
This command undoes the effect of a local commit, returning the affected
files to their uncommitted state. This means that files modified or
deleted in the changeset will be left unchanged, and so will remain
modified in the working directory.
If no files are specified, the commit will be pruned, unless --keep is
given.
"""
opts = pycompat.byteskwargs(opts)
cmdutil.checknotesize(ui, opts)
cmdutil.resolvecommitoptions(ui, opts)
with repo.wlock(), repo.lock():
m, a, r, d = repo.status()[:4]
isdirtypath = any(set(m + a + r + d) & set(pats))
allowdirtywcopy = opts[
b'allow_dirty_working_copy'
] or repo.ui.configbool(b'experimental', b'uncommitondirtywdir')
if not allowdirtywcopy and (not pats or isdirtypath):
cmdutil.bailifchanged(
repo,
hint=_(b'requires --allow-dirty-working-copy to uncommit'),
)
old = repo[b'.']
rewriteutil.precheck(repo, [old.rev()], b'uncommit')
if len(old.parents()) > 1:
raise error.Abort(_(b"cannot uncommit merge changeset"))
match = scmutil.match(old, pats, opts)
# Check all explicitly given files; abort if there's a problem.
if match.files():
s = old.status(old.p1(), match, listclean=True)
eligible = set(s.added) | set(s.modified) | set(s.removed)
badfiles = set(match.files()) - eligible
# Naming a parent directory of an eligible file is OK, even
# if not everything tracked in that directory can be
# uncommitted.
if badfiles:
badfiles -= {f for f in util.dirs(eligible)}
for f in sorted(badfiles):
if f in s.clean:
hint = _(
b"file was not changed in working directory parent"
)
elif repo.wvfs.exists(f):
hint = _(b"file was untracked in working directory parent")
else:
hint = _(b"file does not exist")
raise error.Abort(
_(b'cannot uncommit "%s"') % scmutil.getuipathfn(repo)(f),
hint=hint,
)
with repo.transaction(b'uncommit'):
if not (opts[b'message'] or opts[b'logfile']):
opts[b'message'] = old.description()
message = cmdutil.logmessage(ui, opts)
keepcommit = pats
if not keepcommit:
if opts.get(b'keep') is not None:
keepcommit = opts.get(b'keep')
else:
keepcommit = ui.configbool(
b'experimental', b'uncommit.keep'
)
newid = _commitfiltered(
repo,
old,
match,
keepcommit,
message=message,
user=opts.get(b'user'),
date=opts.get(b'date'),
)
if newid is None:
ui.status(_(b"nothing to uncommit\n"))
return 1
mapping = {}
if newid != old.p1().node():
# Move local changes on filtered changeset
mapping[old.node()] = (newid,)
else:
# Fully removed the old commit
mapping[old.node()] = ()
with repo.dirstate.parentchange():
scmutil.movedirstate(repo, repo[newid], match)
scmutil.cleanupnodes(repo, mapping, b'uncommit', fixphase=True)
def predecessormarkers(ctx):
"""yields the obsolete markers marking the given changeset as a successor"""
for data in ctx.repo().obsstore.predecessors.get(ctx.node(), ()):
yield obsutil.marker(ctx.repo(), data)
@command(
b'unamend',
[],
helpcategory=command.CATEGORY_CHANGE_MANAGEMENT,
helpbasic=True,
)
def unamend(ui, repo, **opts):
"""undo the most recent amend operation on a current changeset
This command will roll back to the previous version of a changeset,
leaving working directory in state in which it was before running
`hg amend` (e.g. files modified as part of an amend will be
marked as modified `hg status`)
"""
unfi = repo.unfiltered()
with repo.wlock(), repo.lock(), repo.transaction(b'unamend'):
# identify the commit from which to unamend
curctx = repo[b'.']
rewriteutil.precheck(repo, [curctx.rev()], b'unamend')
# identify the commit to which to unamend
markers = list(predecessormarkers(curctx))
if len(markers) != 1:
e = _(b"changeset must have one predecessor, found %i predecessors")
raise error.Abort(e % len(markers))
prednode = markers[0].prednode()
predctx = unfi[prednode]
# add an extra so that we get a new hash
# note: allowing unamend to undo an unamend is an intentional feature
extras = predctx.extra()
extras[b'unamend_source'] = curctx.hex()
def filectxfn(repo, ctx_, path):
try:
return predctx.filectx(path)
except KeyError:
return None
# Make a new commit same as predctx
newctx = context.memctx(
repo,
parents=(predctx.p1(), predctx.p2()),
text=predctx.description(),
files=predctx.files(),
filectxfn=filectxfn,
user=predctx.user(),
date=predctx.date(),
extra=extras,
)
newprednode = repo.commitctx(newctx)
newpredctx = repo[newprednode]
dirstate = repo.dirstate
with dirstate.parentchange():
scmutil.movedirstate(repo, newpredctx)
mapping = {curctx.node(): (newprednode,)}
scmutil.cleanupnodes(repo, mapping, b'unamend', fixphase=True)