view mercurial/hbisect.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%)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Thu, 10 Oct 2019 03:49:33 +0200
parents 687b865b95ad
children f37da59a36d9
line wrap: on
line source

# changelog bisection for mercurial
#
# Copyright 2007 Matt Mackall
# Copyright 2005, 2006 Benoit Boissinot <benoit.boissinot@ens-lyon.org>
#
# Inspired by git bisect, extension skeleton taken from mq.py.
#
# 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 collections

from .i18n import _
from .node import (
    hex,
    short,
)
from . import error


def bisect(repo, state):
    """find the next node (if any) for testing during a bisect search.
    returns a (nodes, number, good) tuple.

    'nodes' is the final result of the bisect if 'number' is 0.
    Otherwise 'number' indicates the remaining possible candidates for
    the search and 'nodes' contains the next bisect target.
    'good' is True if bisect is searching for a first good changeset, False
    if searching for a first bad one.
    """

    repo = repo.unfiltered()
    changelog = repo.changelog
    clparents = changelog.parentrevs
    skip = {changelog.rev(n) for n in state[b'skip']}

    def buildancestors(bad, good):
        badrev = min([changelog.rev(n) for n in bad])
        ancestors = collections.defaultdict(lambda: None)
        for rev in repo.revs(b"descendants(%ln) - ancestors(%ln)", good, good):
            ancestors[rev] = []
        if ancestors[badrev] is None:
            return badrev, None
        return badrev, ancestors

    good = False
    badrev, ancestors = buildancestors(state[b'bad'], state[b'good'])
    if not ancestors:  # looking for bad to good transition?
        good = True
        badrev, ancestors = buildancestors(state[b'good'], state[b'bad'])
    bad = changelog.node(badrev)
    if not ancestors:  # now we're confused
        if (
            len(state[b'bad']) == 1
            and len(state[b'good']) == 1
            and state[b'bad'] != state[b'good']
        ):
            raise error.Abort(_(b"starting revisions are not directly related"))
        raise error.Abort(
            _(b"inconsistent state, %d:%s is good and bad")
            % (badrev, short(bad))
        )

    # build children dict
    children = {}
    visit = collections.deque([badrev])
    candidates = []
    while visit:
        rev = visit.popleft()
        if ancestors[rev] == []:
            candidates.append(rev)
            for prev in clparents(rev):
                if prev != -1:
                    if prev in children:
                        children[prev].append(rev)
                    else:
                        children[prev] = [rev]
                        visit.append(prev)

    candidates.sort()
    # have we narrowed it down to one entry?
    # or have all other possible candidates besides 'bad' have been skipped?
    tot = len(candidates)
    unskipped = [c for c in candidates if (c not in skip) and (c != badrev)]
    if tot == 1 or not unskipped:
        return ([changelog.node(c) for c in candidates], 0, good)
    perfect = tot // 2

    # find the best node to test
    best_rev = None
    best_len = -1
    poison = set()
    for rev in candidates:
        if rev in poison:
            # poison children
            poison.update(children.get(rev, []))
            continue

        a = ancestors[rev] or [rev]
        ancestors[rev] = None

        x = len(a)  # number of ancestors
        y = tot - x  # number of non-ancestors
        value = min(x, y)  # how good is this test?
        if value > best_len and rev not in skip:
            best_len = value
            best_rev = rev
            if value == perfect:  # found a perfect candidate? quit early
                break

        if y < perfect and rev not in skip:  # all downhill from here?
            # poison children
            poison.update(children.get(rev, []))
            continue

        for c in children.get(rev, []):
            if ancestors[c]:
                ancestors[c] = list(set(ancestors[c] + a))
            else:
                ancestors[c] = a + [c]

    assert best_rev is not None
    best_node = changelog.node(best_rev)

    return ([best_node], tot, good)


def extendrange(repo, state, nodes, good):
    # bisect is incomplete when it ends on a merge node and
    # one of the parent was not checked.
    parents = repo[nodes[0]].parents()
    if len(parents) > 1:
        if good:
            side = state[b'bad']
        else:
            side = state[b'good']
        num = len(set(i.node() for i in parents) & set(side))
        if num == 1:
            return parents[0].ancestor(parents[1])
    return None


def load_state(repo):
    state = {b'current': [], b'good': [], b'bad': [], b'skip': []}
    for l in repo.vfs.tryreadlines(b"bisect.state"):
        kind, node = l[:-1].split()
        node = repo.unfiltered().lookup(node)
        if kind not in state:
            raise error.Abort(_(b"unknown bisect kind %s") % kind)
        state[kind].append(node)
    return state


def save_state(repo, state):
    f = repo.vfs(b"bisect.state", b"w", atomictemp=True)
    with repo.wlock():
        for kind in sorted(state):
            for node in state[kind]:
                f.write(b"%s %s\n" % (kind, hex(node)))
        f.close()


def resetstate(repo):
    """remove any bisect state from the repository"""
    if repo.vfs.exists(b"bisect.state"):
        repo.vfs.unlink(b"bisect.state")


def checkstate(state):
    """check we have both 'good' and 'bad' to define a range

    Raise Abort exception otherwise."""
    if state[b'good'] and state[b'bad']:
        return True
    if not state[b'good']:
        raise error.Abort(_(b'cannot bisect (no known good revisions)'))
    else:
        raise error.Abort(_(b'cannot bisect (no known bad revisions)'))


def get(repo, status):
    """
    Return a list of revision(s) that match the given status:

    - ``good``, ``bad``, ``skip``: csets explicitly marked as good/bad/skip
    - ``goods``, ``bads``      : csets topologically good/bad
    - ``range``              : csets taking part in the bisection
    - ``pruned``             : csets that are goods, bads or skipped
    - ``untested``           : csets whose fate is yet unknown
    - ``ignored``            : csets ignored due to DAG topology
    - ``current``            : the cset currently being bisected
    """
    state = load_state(repo)
    if status in (b'good', b'bad', b'skip', b'current'):
        return map(repo.unfiltered().changelog.rev, state[status])
    else:
        # In the following sets, we do *not* call 'bisect()' with more
        # than one level of recursion, because that can be very, very
        # time consuming. Instead, we always develop the expression as
        # much as possible.

        # 'range' is all csets that make the bisection:
        #   - have a good ancestor and a bad descendant, or conversely
        # that's because the bisection can go either way
        range = b'( bisect(bad)::bisect(good) | bisect(good)::bisect(bad) )'

        _t = repo.revs(b'bisect(good)::bisect(bad)')
        # The sets of topologically good or bad csets
        if len(_t) == 0:
            # Goods are topologically after bads
            goods = b'bisect(good)::'  # Pruned good csets
            bads = b'::bisect(bad)'  # Pruned bad csets
        else:
            # Goods are topologically before bads
            goods = b'::bisect(good)'  # Pruned good csets
            bads = b'bisect(bad)::'  # Pruned bad csets

        # 'pruned' is all csets whose fate is already known: good, bad, skip
        skips = b'bisect(skip)'  # Pruned skipped csets
        pruned = b'( (%s) | (%s) | (%s) )' % (goods, bads, skips)

        # 'untested' is all cset that are- in 'range', but not in 'pruned'
        untested = b'( (%s) - (%s) )' % (range, pruned)

        # 'ignored' is all csets that were not used during the bisection
        # due to DAG topology, but may however have had an impact.
        # E.g., a branch merged between bads and goods, but whose branch-
        # point is out-side of the range.
        iba = b'::bisect(bad) - ::bisect(good)'  # Ignored bads' ancestors
        iga = b'::bisect(good) - ::bisect(bad)'  # Ignored goods' ancestors
        ignored = b'( ( (%s) | (%s) ) - (%s) )' % (iba, iga, range)

        if status == b'range':
            return repo.revs(range)
        elif status == b'pruned':
            return repo.revs(pruned)
        elif status == b'untested':
            return repo.revs(untested)
        elif status == b'ignored':
            return repo.revs(ignored)
        elif status == b"goods":
            return repo.revs(goods)
        elif status == b"bads":
            return repo.revs(bads)
        else:
            raise error.ParseError(_(b'invalid bisect state'))


def label(repo, node):
    rev = repo.changelog.rev(node)

    # Try explicit sets
    if rev in get(repo, b'good'):
        # i18n: bisect changeset status
        return _(b'good')
    if rev in get(repo, b'bad'):
        # i18n: bisect changeset status
        return _(b'bad')
    if rev in get(repo, b'skip'):
        # i18n: bisect changeset status
        return _(b'skipped')
    if rev in get(repo, b'untested') or rev in get(repo, b'current'):
        # i18n: bisect changeset status
        return _(b'untested')
    if rev in get(repo, b'ignored'):
        # i18n: bisect changeset status
        return _(b'ignored')

    # Try implicit sets
    if rev in get(repo, b'goods'):
        # i18n: bisect changeset status
        return _(b'good (implicit)')
    if rev in get(repo, b'bads'):
        # i18n: bisect changeset status
        return _(b'bad (implicit)')

    return None


def printresult(ui, repo, state, displayer, nodes, good):
    repo = repo.unfiltered()
    if len(nodes) == 1:
        # narrowed it down to a single revision
        if good:
            ui.write(_(b"The first good revision is:\n"))
        else:
            ui.write(_(b"The first bad revision is:\n"))
        displayer.show(repo[nodes[0]])
        extendnode = extendrange(repo, state, nodes, good)
        if extendnode is not None:
            ui.write(
                _(
                    b'Not all ancestors of this changeset have been'
                    b' checked.\nUse bisect --extend to continue the '
                    b'bisection from\nthe common ancestor, %s.\n'
                )
                % extendnode
            )
    else:
        # multiple possible revisions
        if good:
            ui.write(
                _(
                    b"Due to skipped revisions, the first "
                    b"good revision could be any of:\n"
                )
            )
        else:
            ui.write(
                _(
                    b"Due to skipped revisions, the first "
                    b"bad revision could be any of:\n"
                )
            )
        for n in nodes:
            displayer.show(repo[n])
    displayer.close()