view hgext/fetch.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 8ff1ecfadcd1
children 2f290136b7d6
line wrap: on
line source

# fetch.py - pull and merge remote changes
#
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''pull, update and merge in one command (DEPRECATED)'''

from __future__ import absolute_import

from mercurial.i18n import _
from mercurial.node import short
from mercurial import (
    cmdutil,
    error,
    exchange,
    hg,
    lock,
    pycompat,
    registrar,
    util,
)
from mercurial.utils import dateutil

release = lock.release
cmdtable = {}
command = registrar.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 = b'ships-with-hg-core'


@command(
    b'fetch',
    [
        (
            b'r',
            b'rev',
            [],
            _(b'a specific revision you would like to pull'),
            _(b'REV'),
        ),
        (b'', b'edit', None, _(b'invoke editor on commit messages')),
        (b'', b'force-editor', None, _(b'edit commit message (DEPRECATED)')),
        (b'', b'switch-parent', None, _(b'switch parents when merging')),
    ]
    + cmdutil.commitopts
    + cmdutil.commitopts2
    + cmdutil.remoteopts,
    _(b'hg fetch [SOURCE]'),
    helpcategory=command.CATEGORY_REMOTE_REPO_MANAGEMENT,
)
def fetch(ui, repo, source=b'default', **opts):
    '''pull changes from a remote repository, merge new changes if needed.

    This finds all changes from the repository at the specified path
    or URL and adds them to the local repository.

    If the pulled changes add a new branch head, the head is
    automatically merged, and the result of the merge is committed.
    Otherwise, the working directory is updated to include the new
    changes.

    When a merge is needed, the working directory is first updated to
    the newly pulled changes. Local changes are then merged into the
    pulled changes. To switch the merge order, use --switch-parent.

    See :hg:`help dates` for a list of formats valid for -d/--date.

    Returns 0 on success.
    '''

    opts = pycompat.byteskwargs(opts)
    date = opts.get(b'date')
    if date:
        opts[b'date'] = dateutil.parsedate(date)

    parent = repo.dirstate.p1()
    branch = repo.dirstate.branch()
    try:
        branchnode = repo.branchtip(branch)
    except error.RepoLookupError:
        branchnode = None
    if parent != branchnode:
        raise error.Abort(
            _(b'working directory not at branch tip'),
            hint=_(b"use 'hg update' to check out branch tip"),
        )

    wlock = lock = None
    try:
        wlock = repo.wlock()
        lock = repo.lock()

        cmdutil.bailifchanged(repo)

        bheads = repo.branchheads(branch)
        bheads = [head for head in bheads if len(repo[head].children()) == 0]
        if len(bheads) > 1:
            raise error.Abort(
                _(
                    b'multiple heads in this branch '
                    b'(use "hg heads ." and "hg merge" to merge)'
                )
            )

        other = hg.peer(repo, opts, ui.expandpath(source))
        ui.status(
            _(b'pulling from %s\n') % util.hidepassword(ui.expandpath(source))
        )
        revs = None
        if opts[b'rev']:
            try:
                revs = [other.lookup(rev) for rev in opts[b'rev']]
            except error.CapabilityError:
                err = _(
                    b"other repository doesn't support revision lookup, "
                    b"so a rev cannot be specified."
                )
                raise error.Abort(err)

        # Are there any changes at all?
        modheads = exchange.pull(repo, other, heads=revs).cgresult
        if modheads == 0:
            return 0

        # Is this a simple fast-forward along the current branch?
        newheads = repo.branchheads(branch)
        newchildren = repo.changelog.nodesbetween([parent], newheads)[2]
        if len(newheads) == 1 and len(newchildren):
            if newchildren[0] != parent:
                return hg.update(repo, newchildren[0])
            else:
                return 0

        # Are there more than one additional branch heads?
        newchildren = [n for n in newchildren if n != parent]
        newparent = parent
        if newchildren:
            newparent = newchildren[0]
            hg.clean(repo, newparent)
        newheads = [n for n in newheads if n != newparent]
        if len(newheads) > 1:
            ui.status(
                _(
                    b'not merging with %d other new branch heads '
                    b'(use "hg heads ." and "hg merge" to merge them)\n'
                )
                % (len(newheads) - 1)
            )
            return 1

        if not newheads:
            return 0

        # Otherwise, let's merge.
        err = False
        if newheads:
            # By default, we consider the repository we're pulling
            # *from* as authoritative, so we merge our changes into
            # theirs.
            if opts[b'switch_parent']:
                firstparent, secondparent = newparent, newheads[0]
            else:
                firstparent, secondparent = newheads[0], newparent
                ui.status(
                    _(b'updating to %d:%s\n')
                    % (repo.changelog.rev(firstparent), short(firstparent))
                )
            hg.clean(repo, firstparent)
            ui.status(
                _(b'merging with %d:%s\n')
                % (repo.changelog.rev(secondparent), short(secondparent))
            )
            err = hg.merge(repo, secondparent, remind=False)

        if not err:
            # we don't translate commit messages
            message = cmdutil.logmessage(ui, opts) or (
                b'Automated merge with %s' % util.removeauth(other.url())
            )
            editopt = opts.get(b'edit') or opts.get(b'force_editor')
            editor = cmdutil.getcommiteditor(edit=editopt, editform=b'fetch')
            n = repo.commit(
                message, opts[b'user'], opts[b'date'], editor=editor
            )
            ui.status(
                _(b'new changeset %d:%s merges remote changes with local\n')
                % (repo.changelog.rev(n), short(n))
            )

        return err

    finally:
        release(lock, wlock)