mercurial/setdiscovery.py
author "Yann E. MORIN" <yann.morin.1998@anciens.enib.fr>
Thu, 22 Sep 2011 01:36:01 +0200
changeset 15155 f4a8d754cd0a
parent 15063 c20688b7c061
child 15497 9bea3aed6ee1
permissions -rw-r--r--
templates: add 'bisect' keyword to return a cset's bisect status This new 'bisect' template expands to a cset's bisection status (good, bad and so on...). There is also a new 'shortbisect' filter that yields a single char representing the cset's bisection status. It uses the two recently-added hbisect.label() and .shortlabel() functions. Example output using the repository in test-bisect2.t, and some made-up state of the 'end at merge' test (with graphlog, it's so explicit): $ hg glog --template '{rev}:{node|short} {bisect}\n' \ -r 'bisect(range)|bisect(ignored)' o 17:228c06deef46: bad | o 16:609d82a7ebae: bad (implicit) | o 15:857b178a7cf3: bad |\ | o 13:b0a32c86eb31: good | | | o 12:9f259202bbe7: good (implicit) | | | o 11:82ca6f06eccd: good | | @ | 10:429fcd26f52d: untested |\ \ | o | 9:3c77083deb4a: skipped | |/ | o 8:dab8161ac8fc: good | | o | 6:a214d5d3811a: ignored |\ \ | o | 5:385a529b6670: ignored | | | o | | 4:5c668c22234f: ignored | | | o | | 3:0950834f0a9c: ignored |/ / o / 2:051e12f87bf1: ignored |/ And now the same with the short label: $ hg log --template '{bisect|shortbisect} {rev}:{node|short}\n' 18:d42e18c7bc9b B 17:228c06deef46 B 16:609d82a7ebae B 15:857b178a7cf3 14:faa450606157 G 13:b0a32c86eb31 G 12:9f259202bbe7 G 11:82ca6f06eccd U 10:429fcd26f52d S 9:3c77083deb4a G 8:dab8161ac8fc 7:50c76098bbf2 I 6:a214d5d3811a I 5:385a529b6670 I 4:5c668c22234f I 3:0950834f0a9c I 2:051e12f87bf1 1:4ca5088da217 0:33b1f9bc8bc5 Signed-off-by: "Yann E. MORIN" <yann.morin.1998@anciens.enib.fr>

# setdiscovery.py - improved discovery of common nodeset for mercurial
#
# Copyright 2010 Benoit Boissinot <bboissin@gmail.com>
# and Peter Arrenbrecht <peter@arrenbrecht.ch>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from node import nullid
from i18n import _
import random, collections, util, dagutil

def _updatesample(dag, nodes, sample, always, quicksamplesize=0):
    # if nodes is empty we scan the entire graph
    if nodes:
        heads = dag.headsetofconnecteds(nodes)
    else:
        heads = dag.heads()
    dist = {}
    visit = collections.deque(heads)
    seen = set()
    factor = 1
    while visit:
        curr = visit.popleft()
        if curr in seen:
            continue
        d = dist.setdefault(curr, 1)
        if d > factor:
            factor *= 2
        if d == factor:
            if curr not in always: # need this check for the early exit below
                sample.add(curr)
                if quicksamplesize and (len(sample) >= quicksamplesize):
                    return
        seen.add(curr)
        for p in dag.parents(curr):
            if not nodes or p in nodes:
                dist.setdefault(p, d + 1)
                visit.append(p)

def _setupsample(dag, nodes, size):
    if len(nodes) <= size:
        return set(nodes), None, 0
    always = dag.headsetofconnecteds(nodes)
    desiredlen = size - len(always)
    if desiredlen <= 0:
        # This could be bad if there are very many heads, all unknown to the
        # server. We're counting on long request support here.
        return always, None, desiredlen
    return always, set(), desiredlen

def _takequicksample(dag, nodes, size, initial):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    if initial:
        fromset = None
    else:
        fromset = nodes
    _updatesample(dag, fromset, sample, always, quicksamplesize=desiredlen)
    sample.update(always)
    return sample

def _takefullsample(dag, nodes, size):
    always, sample, desiredlen = _setupsample(dag, nodes, size)
    if sample is None:
        return always
    # update from heads
    _updatesample(dag, nodes, sample, always)
    # update from roots
    _updatesample(dag.inverse(), nodes, sample, always)
    assert sample
    if len(sample) > desiredlen:
        sample = set(random.sample(sample, desiredlen))
    elif len(sample) < desiredlen:
        more = desiredlen - len(sample)
        sample.update(random.sample(list(nodes - sample - always), more))
    sample.update(always)
    return sample

def findcommonheads(ui, local, remote,
                    initialsamplesize=100,
                    fullsamplesize=200,
                    abortwhenunrelated=True):
    '''Return a tuple (common, anyincoming, remoteheads) used to identify
    missing nodes from or in remote.

    shortcutlocal determines whether we try use direct access to localrepo if
    remote is actually local.
    '''
    roundtrips = 0
    cl = local.changelog
    dag = dagutil.revlogdag(cl)

    # early exit if we know all the specified remote heads already
    ui.debug("query 1; heads\n")
    roundtrips += 1
    ownheads = dag.heads()
    sample = ownheads
    if remote.local():
        # stopgap until we have a proper localpeer that supports batch()
        srvheadhashes = remote.heads()
        yesno = remote.known(dag.externalizeall(sample))
    elif remote.capable('batch'):
        batch = remote.batch()
        srvheadhashesref = batch.heads()
        yesnoref = batch.known(dag.externalizeall(sample))
        batch.submit()
        srvheadhashes = srvheadhashesref.value
        yesno = yesnoref.value
    else:
        # compatibitity with pre-batch, but post-known remotes during 1.9 devel
        srvheadhashes = remote.heads()
        sample = []

    if cl.tip() == nullid:
        if srvheadhashes != [nullid]:
            return [nullid], True, srvheadhashes
        return [nullid], False, []

    # start actual discovery (we note this before the next "if" for
    # compatibility reasons)
    ui.status(_("searching for changes\n"))

    srvheads = dag.internalizeall(srvheadhashes, filterunknown=True)
    if len(srvheads) == len(srvheadhashes):
        ui.debug("all remote heads known locally\n")
        return (srvheadhashes, False, srvheadhashes,)

    if sample and util.all(yesno):
        ui.note("all local heads known remotely\n")
        ownheadhashes = dag.externalizeall(ownheads)
        return (ownheadhashes, True, srvheadhashes,)

    # full blown discovery
    undecided = dag.nodeset() # own nodes where I don't know if remote knows them
    common = set() # own nodes I know we both know
    missing = set() # own nodes I know remote lacks

    # treat remote heads (and maybe own heads) as a first implicit sample response
    common.update(dag.ancestorset(srvheads))
    undecided.difference_update(common)

    full = False
    while undecided:

        if sample:
            commoninsample = set(n for i, n in enumerate(sample) if yesno[i])
            common.update(dag.ancestorset(commoninsample, common))

            missinginsample = [n for i, n in enumerate(sample) if not yesno[i]]
            missing.update(dag.descendantset(missinginsample, missing))

            undecided.difference_update(missing)
            undecided.difference_update(common)

        if not undecided:
            break

        if full:
            ui.note("sampling from both directions\n")
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
        elif common:
            # use cheapish initial sample
            ui.debug("taking initial sample\n")
            sample = _takefullsample(dag, undecided, size=fullsamplesize)
        else:
            # use even cheaper initial sample
            ui.debug("taking quick initial sample\n")
            sample = _takequicksample(dag, undecided, size=initialsamplesize,
                                      initial=True)

        roundtrips += 1
        ui.progress(_('searching'), roundtrips, unit=_('queries'))
        ui.debug("query %i; still undecided: %i, sample size is: %i\n"
                 % (roundtrips, len(undecided), len(sample)))
        # indices between sample and externalized version must match
        sample = list(sample)
        yesno = remote.known(dag.externalizeall(sample))
        full = True

    result = dag.headsetofconnecteds(common)
    ui.progress(_('searching'), None)
    ui.debug("%d total queries\n" % roundtrips)

    if not result and srvheadhashes != [nullid]:
        if abortwhenunrelated:
            raise util.Abort(_("repository is unrelated"))
        else:
            ui.warn(_("warning: repository is unrelated\n"))
        return (set([nullid]), True, srvheadhashes,)

    anyincoming = (srvheadhashes != [nullid])
    return dag.externalizeall(result), anyincoming, srvheadhashes