view hgext/fetch.py @ 24735:07200e3332a1

tags: extract .hgtags filenodes cache to a standalone file

Resolution of .hgtags filenodes values has historically been a
performance pain point for large repositories, where reading individual
manifests can take over 100ms. Multiplied by hundreds or even thousands
of heads and resolving .hgtags filenodes becomes a performance issue.

This patch establishes a standalone cache file holding the .hgtags
filenodes for each changeset. After this patch, the .hgtags filenode
for any particular changeset should only have to be computed once
during the lifetime of the repository.

The introduced hgtagsfnodes1 cache file is modeled after the rev branch
cache: the cache is effectively an array of entries consisting of a
changeset fragment and the filenode for a revision. The file grows in
proportion to the length of the repository (24 bytes per changeset) and
is truncated when the repository is stripped. The file is not written
unless tag info is requested and tags have changed since last time.

This patch partially addresses issue4550. Future patches will split the
"tags" cache file into per-filter files and will refactor the cache
format to not capture the .hgtags fnodes, as these are now stored in
the hgtagsfnodes1 cache. This patch is capable of standing alone. We
should not have to wait on the tags cache filter split and format
refactor for this patch to land.

# 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 mercurial.i18n import _
from mercurial.node import short
from mercurial import commands, cmdutil, hg, util, error
from mercurial.lock import release
from mercurial import exchange

cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'

@command('fetch',
    [('r', 'rev', [],
     _('a specific revision you would like to pull'), _('REV')),
    ('e', 'edit', None, _('invoke editor on commit messages')),
    ('', 'force-editor', None, _('edit commit message (DEPRECATED)')),
    ('', 'switch-parent', None, _('switch parents when merging')),
    ] + commands.commitopts + commands.commitopts2 + commands.remoteopts,
    _('hg fetch [SOURCE]'))
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.
    '''

    date = opts.get('date')
    if date:
        opts['date'] = util.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 util.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 util.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 util.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)