view hgext/fetch.py @ 40736:0728d87a8631

store: append to fncache if there are only new files to write

Before this patch, if we have to add a new entry to fncache, we write the whole
fncache again which slows things down on large fncache which have millions of
entries. Addition of a new entry is common operation while pulling new files or
commiting a new file.

This patch adds a new fncache.addls set which keeps track of the additions
happening and store them. When we write the fncache, we will just read the addls
set and append those entries at the end of fncache.
We make sure that the entries are new entries by loading the fncache and making
sure entry does not exists there. In future if we can check if an entry is new
without loading the fncache, that will speed up things more.

Performance numbers for commiting a new file:

mercurial repo
before: 0.08784651756286621
after: 0.08474504947662354

mozilla-central
before: 1.83314049243927
after: 1.7054164409637451

netbeans
before: 0.7953150272369385
after: 0.7202838659286499

pypy
before: 0.17805707454681396
after: 0.13431048393249512

In our internal repo, the performance improvement is in seconds.

I have used octobus's ASV perf benchmark thing to get the above numbers. I also
see some minute perf improvements related to creating a new commit without a new
file, but I believe that's just some noise.

Differential Revision: https://phab.mercurial-scm.org/D5301

# fetch.py - pull and merge remote changes
#
# Copyright 2006 Vadim Gelfer <[e-mail]>
#
# 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 = 'ships-with-hg-core'

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

    parent, _p2 = repo.dirstate.parents()
    branch = repo.dirstate.branch()
    try:
        branchnode = repo.branchtip(branch)
    except error.RepoLookupError:
        branchnode = None
    if parent != branchnode:
        raise error.Abort(_('working directory not at branch tip'),
                         hint=_("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(_('multiple heads in this branch '
                               '(use "hg heads ." and "hg merge" to merge)'))

        other = hg.peer(repo, opts, ui.expandpath(source))
        ui.status(_('pulling from %s\n') %
                  util.hidepassword(ui.expandpath(source)))
        revs = None
        if opts['rev']:
            try:
                revs = [other.lookup(rev) for rev in opts['rev']]
            except error.CapabilityError:
                err = _("other repository doesn't support revision lookup, "
                        "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(_('not merging with %d other new branch heads '
                        '(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['switch_parent']:
                firstparent, secondparent = newparent, newheads[0]
            else:
                firstparent, secondparent = newheads[0], newparent
                ui.status(_('updating to %d:%s\n') %
                          (repo.changelog.rev(firstparent),
                           short(firstparent)))
            hg.clean(repo, firstparent)
            ui.status(_('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
                       ('Automated merge with %s' %
                        util.removeauth(other.url())))
            editopt = opts.get('edit') or opts.get('force_editor')
            editor = cmdutil.getcommiteditor(edit=editopt, editform='fetch')
            n = repo.commit(message, opts['user'], opts['date'], editor=editor)
            ui.status(_('new changeset %d:%s merges remote changes '
                        'with local\n') % (repo.changelog.rev(n),
                                           short(n)))

        return err

    finally:
        release(lock, wlock)