annotate mercurial/repoview.py @ 43198:c16fe77e340a

pathcopies: give up any optimization based on `introrev`

Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the
introduction revision during path copies. However, further checking show that
finding the introduction revision is still expensive and that we are better off
without it. So we simply drop it and only rely on the linkrev optimisation.

I ran `perfpathcopies` on 6989 pair of revision in the pypy
repository (`hg perfhelper-pathcopies`. The result is massively in favor of
dropping this condition. The result of the copy tracing are unchanged.

Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it
can return wrong result. The following changesets broke test-mv-cp-st-diff.t

    -        if not f.isintroducedafter(limit):
    +        if limit >= 0 and f.linkrev() < limit:
                 return None


Here are various numbers (before this changeset/after this changesets)

            source       destination  before      after    saved-time  ratio
worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675
            c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743
            22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420
            682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074
            5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817
worse  1%   dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320
worse  5%   c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488
worse 10%   3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156
worse 25%   321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259
median      2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947
best 25%    915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673
best 10%    ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278
best  5%    d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126
best  1%    81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813
best cases  c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483
            c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508
            058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442
            9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463
            442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487


As one can see, the average case is not really impacted. However, the worth case
we get after this changeset are much better than the one we had before it. We
have 30 pairs where improvements are above 10 minutes.

This reflect in the combined time for all pairs
before: 26256s
after:   1300s (-95%)

If we remove these pathological 30 cases, we still see a significant improvements:
before:  1631s
after:   1245s (-24%)

# repoview.py - Filtered view of a localrepo object
#
# Copyright 2012 Pierre-Yves David <[e-mail]>
#                Logilab SA        <[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.

from __future__ import absolute_import

import copy
import weakref

from .node import nullrev
from .pycompat import (
    delattr,
    getattr,
    setattr,
)
from . import (
    obsolete,
    phases,
    pycompat,
    tags as tagsmod,
    util,
)
from .utils import repoviewutil


def hideablerevs(repo):
    """Revision candidates to be hidden

    This is a standalone function to allow extensions to wrap it.

    Because we use the set of immutable changesets as a fallback subset in
    branchmap (see mercurial.utils.repoviewutils.subsettable), you cannot set
    "public" changesets as "hideable". Doing so would break multiple code
    assertions and lead to crashes."""
    obsoletes = obsolete.getrevs(repo, b'obsolete')
    internals = repo._phasecache.getrevset(repo, phases.localhiddenphases)
    internals = frozenset(internals)
    return obsoletes | internals


def pinnedrevs(repo):
    """revisions blocking hidden changesets from being filtered
    """

    cl = repo.changelog
    pinned = set()
    pinned.update([par.rev() for par in repo[None].parents()])
    pinned.update([cl.rev(bm) for bm in repo._bookmarks.values()])

    tags = {}
    tagsmod.readlocaltags(repo.ui, repo, tags, {})
    if tags:
        rev, nodemap = cl.rev, cl.nodemap
        pinned.update(rev(t[0]) for t in tags.values() if t[0] in nodemap)
    return pinned


def _revealancestors(pfunc, hidden, revs):
    """reveals contiguous chains of hidden ancestors of 'revs' by removing them
    from 'hidden'

    - pfunc(r): a funtion returning parent of 'r',
    - hidden: the (preliminary) hidden revisions, to be updated
    - revs: iterable of revnum,

    (Ancestors are revealed exclusively, i.e. the elements in 'revs' are
    *not* revealed)
    """
    stack = list(revs)
    while stack:
        for p in pfunc(stack.pop()):
            if p != nullrev and p in hidden:
                hidden.remove(p)
                stack.append(p)


def computehidden(repo, visibilityexceptions=None):
    """compute the set of hidden revision to filter

    During most operation hidden should be filtered."""
    assert not repo.changelog.filteredrevs

    hidden = hideablerevs(repo)
    if hidden:
        hidden = set(hidden - pinnedrevs(repo))
        if visibilityexceptions:
            hidden -= visibilityexceptions
        pfunc = repo.changelog.parentrevs
        mutable = repo._phasecache.getrevset(repo, phases.mutablephases)

        visible = mutable - hidden
        _revealancestors(pfunc, hidden, visible)
    return frozenset(hidden)


def computesecret(repo, visibilityexceptions=None):
    """compute the set of revision that can never be exposed through hgweb

    Changeset in the secret phase (or above) should stay unaccessible."""
    assert not repo.changelog.filteredrevs
    secrets = repo._phasecache.getrevset(repo, phases.remotehiddenphases)
    return frozenset(secrets)


def computeunserved(repo, visibilityexceptions=None):
    """compute the set of revision that should be filtered when used a server

    Secret and hidden changeset should not pretend to be here."""
    assert not repo.changelog.filteredrevs
    # fast path in simple case to avoid impact of non optimised code
    hiddens = filterrevs(repo, b'visible')
    secrets = filterrevs(repo, b'served.hidden')
    if secrets:
        return frozenset(hiddens | secrets)
    else:
        return hiddens


def computemutable(repo, visibilityexceptions=None):
    assert not repo.changelog.filteredrevs
    # fast check to avoid revset call on huge repo
    if any(repo._phasecache.phaseroots[1:]):
        getphase = repo._phasecache.phase
        maymutable = filterrevs(repo, b'base')
        return frozenset(r for r in maymutable if getphase(repo, r))
    return frozenset()


def computeimpactable(repo, visibilityexceptions=None):
    """Everything impactable by mutable revision

    The immutable filter still have some chance to get invalidated. This will
    happen when:

    - you garbage collect hidden changeset,
    - public phase is moved backward,
    - something is changed in the filtering (this could be fixed)

    This filter out any mutable changeset and any public changeset that may be
    impacted by something happening to a mutable revision.

    This is achieved by filtered everything with a revision number egal or
    higher than the first mutable changeset is filtered."""
    assert not repo.changelog.filteredrevs
    cl = repo.changelog
    firstmutable = len(cl)
    for roots in repo._phasecache.phaseroots[1:]:
        if roots:
            firstmutable = min(firstmutable, min(cl.rev(r) for r in roots))
    # protect from nullrev root
    firstmutable = max(0, firstmutable)
    return frozenset(pycompat.xrange(firstmutable, len(cl)))


# function to compute filtered set
#
# When adding a new filter you MUST update the table at:
#     mercurial.utils.repoviewutil.subsettable
# Otherwise your filter will have to recompute all its branches cache
# from scratch (very slow).
filtertable = {
    b'visible': computehidden,
    b'visible-hidden': computehidden,
    b'served.hidden': computesecret,
    b'served': computeunserved,
    b'immutable': computemutable,
    b'base': computeimpactable,
}

_basefiltername = list(filtertable)


def extrafilter(ui):
    """initialize extra filter and return its id

    If extra filtering is configured, we make sure the associated filtered view
    are declared and return the associated id.
    """
    frevs = ui.config(b'experimental', b'extra-filter-revs')
    if frevs is None:
        return None

    fid = pycompat.sysbytes(util.DIGESTS[b'sha1'](frevs).hexdigest())[:12]

    combine = lambda fname: fname + b'%' + fid

    subsettable = repoviewutil.subsettable

    if combine(b'base') not in filtertable:
        for name in _basefiltername:

            def extrafilteredrevs(repo, *args, **kwargs):
                baserevs = filtertable[name](repo, *args, **kwargs)
                extrarevs = frozenset(repo.revs(frevs))
                return baserevs | extrarevs

            filtertable[combine(name)] = extrafilteredrevs
            if name in subsettable:
                subsettable[combine(name)] = combine(subsettable[name])
    return fid


def filterrevs(repo, filtername, visibilityexceptions=None):
    """returns set of filtered revision for this filter name

    visibilityexceptions is a set of revs which must are exceptions for
    hidden-state and must be visible. They are dynamic and hence we should not
    cache it's result"""
    if filtername not in repo.filteredrevcache:
        func = filtertable[filtername]
        if visibilityexceptions:
            return func(repo.unfiltered, visibilityexceptions)
        repo.filteredrevcache[filtername] = func(repo.unfiltered())
    return repo.filteredrevcache[filtername]


class repoview(object):
    """Provide a read/write view of a repo through a filtered changelog

    This object is used to access a filtered version of a repository without
    altering the original repository object itself. We can not alter the
    original object for two main reasons:
    - It prevents the use of a repo with multiple filters at the same time. In
      particular when multiple threads are involved.
    - It makes scope of the filtering harder to control.

    This object behaves very closely to the original repository. All attribute
    operations are done on the original repository:
    - An access to `repoview.someattr` actually returns `repo.someattr`,
    - A write to `repoview.someattr` actually sets value of `repo.someattr`,
    - A deletion of `repoview.someattr` actually drops `someattr`
      from `repo.__dict__`.

    The only exception is the `changelog` property. It is overridden to return
    a (surface) copy of `repo.changelog` with some revisions filtered. The
    `filtername` attribute of the view control the revisions that need to be
    filtered.  (the fact the changelog is copied is an implementation detail).

    Unlike attributes, this object intercepts all method calls. This means that
    all methods are run on the `repoview` object with the filtered `changelog`
    property. For this purpose the simple `repoview` class must be mixed with
    the actual class of the repository. This ensures that the resulting
    `repoview` object have the very same methods than the repo object. This
    leads to the property below.

        repoview.method() --> repo.__class__.method(repoview)

    The inheritance has to be done dynamically because `repo` can be of any
    subclasses of `localrepo`. Eg: `bundlerepo` or `statichttprepo`.
    """

    def __init__(self, repo, filtername, visibilityexceptions=None):
        object.__setattr__(self, r'_unfilteredrepo', repo)
        object.__setattr__(self, r'filtername', filtername)
        object.__setattr__(self, r'_clcachekey', None)
        object.__setattr__(self, r'_clcache', None)
        # revs which are exceptions and must not be hidden
        object.__setattr__(self, r'_visibilityexceptions', visibilityexceptions)

    # not a propertycache on purpose we shall implement a proper cache later
    @property
    def changelog(self):
        """return a filtered version of the changeset

        this changelog must not be used for writing"""
        # some cache may be implemented later
        unfi = self._unfilteredrepo
        unfichangelog = unfi.changelog
        # bypass call to changelog.method
        unfiindex = unfichangelog.index
        unfilen = len(unfiindex)
        unfinode = unfiindex[unfilen - 1][7]

        revs = filterrevs(unfi, self.filtername, self._visibilityexceptions)
        cl = self._clcache
        newkey = (unfilen, unfinode, hash(revs), unfichangelog._delayed)
        # if cl.index is not unfiindex, unfi.changelog would be
        # recreated, and our clcache refers to garbage object
        if cl is not None and (
            cl.index is not unfiindex or newkey != self._clcachekey
        ):
            cl = None
        # could have been made None by the previous if
        if cl is None:
            cl = copy.copy(unfichangelog)
            cl.filteredrevs = revs
            object.__setattr__(self, r'_clcache', cl)
            object.__setattr__(self, r'_clcachekey', newkey)
        return cl

    def unfiltered(self):
        """Return an unfiltered version of a repo"""
        return self._unfilteredrepo

    def filtered(self, name, visibilityexceptions=None):
        """Return a filtered version of a repository"""
        if name == self.filtername and not visibilityexceptions:
            return self
        return self.unfiltered().filtered(name, visibilityexceptions)

    def __repr__(self):
        return r'<%s:%s %r>' % (
            self.__class__.__name__,
            pycompat.sysstr(self.filtername),
            self.unfiltered(),
        )

    # everything access are forwarded to the proxied repo
    def __getattr__(self, attr):
        return getattr(self._unfilteredrepo, attr)

    def __setattr__(self, attr, value):
        return setattr(self._unfilteredrepo, attr, value)

    def __delattr__(self, attr):
        return delattr(self._unfilteredrepo, attr)


# Python <3.4 easily leaks types via __mro__. See
# https://bugs.python.org/issue17950. We cache dynamically created types
# so they won't be leaked on every invocation of repo.filtered().
_filteredrepotypes = weakref.WeakKeyDictionary()


def newtype(base):
    """Create a new type with the repoview mixin and the given base class"""
    if base not in _filteredrepotypes:

        class filteredrepo(repoview, base):
            pass

        _filteredrepotypes[base] = filteredrepo
    return _filteredrepotypes[base]