view mercurial/hbisect.py @ 14365:a8e3931e3fb5

revlog: linearize created changegroups in generaldelta revlogs This greatly improves the speed of the bundling process, and often reduces the bundle size considerably. (Although if the repository is already ordered, this has little effect on both time and bundle size.) For non-generaldelta clients, the reduced bundle size translates to a reduced repository size, similar to shrinking the revlogs (which uses the exact same algorithm). For generaldelta clients the difference is minor. When the new bundle format comes, reordering will not be necessary since we can then store the deltaparent relationsships directly. The eventual default behavior for clients and servers is presented in the table below, where "new" implies support for GD as well as the new bundle format: old client new client old server old bundle, no reorder old bundle, no reorder new server, non-GD old bundle, no reorder[1] old bundle, no reorder[2] new server, GD old bundle, reorder[3] new bundle, no reorder[4] [1] reordering is expensive on the server in this case, skip it [2] client can choose to do its own redelta here [3] reordering is needed because otherwise the pull does a lot of extra work on the server [4] reordering isn't needed because client can get deltabase in bundle format Currently, the default is to reorder on GD-servers, and not otherwise. A new setting, bundle.reorder, has been added to override the default reordering behavior. It can be set to either 'auto' (the default), or any true or false value as a standard boolean setting, to either force the reordering on or off regardless of generaldelta. Some timing data from a relatively branch test repository follows. All bundling is done with --all --type none options. Non-generaldelta, non-shrunk repo: ----------------------------------- Size: 276M Without reorder (default): Bundle time: 14.4 seconds Bundle size: 939M With reorder: Bundle time: 1 minute, 29.3 seconds Bundle size: 381M Generaldelta, non-shrunk repo: ----------------------------------- Size: 87M Without reorder: Bundle time: 2 minutes, 1.4 seconds Bundle size: 939M With reorder (default): Bundle time: 25.5 seconds Bundle size: 381M
author Sune Foldager <cryo@cyanite.org>
date Wed, 18 May 2011 23:26:26 +0200
parents e5a59d31bb04
children 01e0091679c0
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.

import os
from i18n import _
from node import short, hex
import util

def bisect(changelog, 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.
    """

    clparents = changelog.parentrevs
    skip = set([changelog.rev(n) for n in state['skip']])

    def buildancestors(bad, good):
        # only the earliest bad revision matters
        badrev = min([changelog.rev(n) for n in bad])
        goodrevs = [changelog.rev(n) for n in good]
        goodrev = min(goodrevs)
        # build visit array
        ancestors = [None] * (len(changelog) + 1) # an extra for [-1]

        # set nodes descended from goodrev
        ancestors[goodrev] = []
        for rev in xrange(goodrev + 1, len(changelog)):
            for prev in clparents(rev):
                if ancestors[prev] == []:
                    ancestors[rev] = []

        # clear good revs from array
        for node in goodrevs:
            ancestors[node] = None
        for rev in xrange(len(changelog), -1, -1):
            if ancestors[rev] is None:
                for prev in clparents(rev):
                    ancestors[prev] = None

        if ancestors[badrev] is None:
            return badrev, None
        return badrev, ancestors

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

    # build children dict
    children = {}
    visit = [badrev]
    candidates = []
    while visit:
        rev = visit.pop(0)
        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(rev) for rev 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 load_state(repo):
    state = {'good': [], 'bad': [], 'skip': []}
    if os.path.exists(repo.join("bisect.state")):
        for l in repo.opener("bisect.state"):
            kind, node = l[:-1].split()
            node = repo.lookup(node)
            if kind not in state:
                raise util.Abort(_("unknown bisect kind %s") % kind)
            state[kind].append(node)
    return state


def save_state(repo, state):
    f = repo.opener("bisect.state", "w", atomictemp=True)
    wlock = repo.wlock()
    try:
        for kind in state:
            for node in state[kind]:
                f.write("%s %s\n" % (kind, hex(node)))
        f.rename()
    finally:
        wlock.release()