view hgext/uncommit.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents d0310f21ee9e
children 9d2b2df2c2ba
line wrap: on
line source

# 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,
    pathutil,
    pycompat,
    registrar,
    rewriteutil,
    scmutil,
)

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():

        st = repo.status()
        m, a, r, d = st.modified, st.added, st.removed, st.deleted
        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 pathutil.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)