annotate mercurial/repoview.py @ 18274:254b708fd37d

performance: speedup computation of mutable revisions

In their current state, revset calls can be very costly, as we test
predicates on the entire repository. The "mutable" filter is used
during branch cache loading operation. We need to make it fast.

This change drops revset calls in favor of direct testing of the
phase of a changeset.

Performance test on my Mercurial checkout
- 19857 total changesets,
- 1646 mutable revision

Before:
  ! mutable
  ! wall 0.032405

After:
  ! mutable
  ! wall 0.001469

Performance test on a Mozilla central checkout:
- 117293 total changesets,
- 1 mutable changeset,

Before:
  ! mutable
  ! wall 0.188636

After:
  ! mutable
  ! wall 0.000022

# 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.

import copy
import phases
import util
import obsolete, bookmarks, revset


def computehidden(repo):
    """compute the set of hidden revision to filter

    During most operation hidden should be filtered."""
    assert not repo.changelog.filteredrevs
    hideable = obsolete.getrevs(repo, 'obsolete')
    if hideable:
        cl = repo.changelog
        firsthideable = min(hideable)
        revs = cl.revs(start=firsthideable)
        blockers = [r for r in revset._children(repo, revs, hideable)
                      if r not in hideable]
        for par in repo[None].parents():
            blockers.append(par.rev())
        for bm in bookmarks.listbookmarks(repo).values():
            blockers.append(repo[bm].rev())
        blocked = cl.ancestors(blockers, inclusive=True)
        return frozenset(r for r in hideable if r not in blocked)
    return frozenset()

def computeunserved(repo):
    """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 = filteredrevs(repo, 'hidden')
    if phases.hassecret(repo):
        cl = repo.changelog
        secret = phases.secret
        getphase = repo._phasecache.phase
        first = min(cl.rev(n) for n in repo._phasecache.phaseroots[secret])
        revs = cl.revs(start=first)
        secrets = set(r for r in revs if getphase(repo, r) >= secret)
        return frozenset(hiddens | secrets)
    else:
        return hiddens
    return frozenset()

def computemutable(repo):
    """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 check to avoid revset call on huge repo
    if util.any(repo._phasecache.phaseroots[1:]):
        getphase = repo._phasecache.phase
        maymutable = filteredrevs(repo, 'impactable')
        return frozenset(r for r in maymutable if getphase(repo, r))
    return frozenset()

def computeimpactable(repo):
    """Everything impactable by mutable revision

    The mutable 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))
    return frozenset(xrange(firstmutable, len(cl)))

# function to compute filtered set
filtertable = {'hidden': computehidden,
               'unserved': computeunserved,
               'mutable':  computemutable,
               'impactable':  computeimpactable}
### Nearest subset relation
# Nearest subset of filter X is a filter Y so that:
# * Y is included in X,
# * X - Y is as small as possible.
# This create and ordering used for branchmap purpose.
# the ordering may be partial
subsettable = {None: 'hidden',
               'hidden': 'unserved',
               'unserved': 'mutable',
               'mutable': 'impactable'}

def filteredrevs(repo, filtername):
    """returns set of filtered revision for this filter name"""
    if filtername not in repo.filteredrevcache:
        func = filtertable[filtername]
        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 `httprepo`.
    """

    def __init__(self, repo, filtername):
        object.__setattr__(self, '_unfilteredrepo', repo)
        object.__setattr__(self, 'filtername', filtername)

    # not a cacheproperty 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
        cl = copy.copy(self._unfilteredrepo.changelog)
        cl.filteredrevs = filteredrevs(self._unfilteredrepo, self.filtername)
        return cl

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

    def filtered(self, name):
        """Return a filtered version of a repository"""
        if name == self.filtername:
            return self
        return self.unfiltered().filtered(name)

    # 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)

    # The `requirement` attribut is initialiazed during __init__. But
    # __getattr__ won't be called as it also exists on the class. We need
    # explicit forwarding to main repo here
    @property
    def requirements(self):
        return self._unfilteredrepo.requirements