view mercurial/treediscovery.py @ 16719:e7bf09acd410

localrepo: add branchtip() method for faster single-branch lookups For the PyPy repo with 744 branches and 843 branch heads, this brings hg log -r default over NFS from: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 3249 0 1.3222 1.3222 <open> 3244 0 0.6211 0.6211 <method 'close' of 'file' objects> 3243 0 0.0800 0.0800 <method 'read' of 'file' objects> 3241 0 0.0660 0.0660 <method 'seek' of 'file' objects> 3905 0 0.0476 0.0476 <zlib.decompress> 3281 0 2.6756 0.0472 mercurial.changelog:182(read) +3281 0 2.5256 0.0453 +mercurial.revlog:881(revision) +3276 0 0.0389 0.0196 +mercurial.changelog:28(decodeextra) +6562 0 0.0123 0.0123 +<method 'split' of 'str' objects> +6562 0 0.0408 0.0073 +mercurial.encoding:61(tolocal) +3281 0 0.0054 0.0054 +<method 'index' of 'str' objects> 3241 0 2.2464 0.0456 mercurial.revlog:818(_loadchunk) +3241 0 0.6205 0.6205 +<method 'close' of 'file' objects> +3241 0 0.0765 0.0765 +<method 'read' of 'file' objects> +3241 0 0.0660 0.0660 +<method 'seek' of 'file' objects> +3241 0 1.4209 0.0135 +mercurial.store:374(__call__) +3241 0 0.0122 0.0107 +mercurial.revlog:810(_addchunk) 3281 0 2.5256 0.0453 mercurial.revlog:881(revision) +3280 0 0.0175 0.0175 +mercurial.revlog:305(rev) +3281 0 2.2819 0.0119 +mercurial.revlog:847(_chunkraw) +3281 0 0.0603 0.0083 +mercurial.revlog:945(_checkhash) +3281 0 0.0051 0.0051 +mercurial.revlog:349(flags) +3281 0 0.0040 0.0040 +<mercurial.mpatch.patches> 13682 0 0.0479 0.0248 <method 'decode' of 'str' objects> +7418 0 0.0228 0.0076 +encodings.utf_8:15(decode) +1 0 0.0003 0.0000 +encodings:71(search_function) 3248 0 1.3995 0.0246 mercurial.scmutil:218(__call__) +3248 0 1.3222 1.3222 +<open> +3248 0 0.0235 0.0184 +os.path:80(split) +3248 0 0.0084 0.0068 +mercurial.scmutil:92(__call__) Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000) down to: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 55 31 0.0197 0.0163 <__import__> +1 0 0.0006 0.0002 +mercurial.context:8(<module>) +1 0 0.0042 0.0001 +mercurial.revlog:12(<module>) +1 0 0.0002 0.0001 +mercurial.match:8(<module>) +1 0 0.0003 0.0001 +mercurial.dirstate:7(<module>) +1 0 0.0057 0.0001 +mercurial.changelog:8(<module>) 1 0 0.0117 0.0032 mercurial.localrepo:525(_readbranchcache) +844 0 0.0015 0.0015 +<binascii.unhexlify> +845 0 0.0010 0.0010 +<method 'split' of 'str' objects> +843 0 0.0045 0.0009 +mercurial.encoding:61(tolocal) +843 0 0.0004 0.0004 +<method 'setdefault' of 'dict' objects> +1 0 0.0003 0.0003 +<method 'close' of 'file' objects> 3 0 0.0029 0.0029 <method 'read' of 'file' objects> 9 0 0.0018 0.0018 <open> 990 0 0.0017 0.0017 <binascii.unhexlify> 53 0 0.0016 0.0016 mercurial.demandimport:43(__init__) 862 0 0.0015 0.0015 <_codecs.utf_8_decode> 862 0 0.0037 0.0014 <method 'decode' of 'str' objects> +862 0 0.0023 0.0008 +encodings.utf_8:15(decode) 981 0 0.0011 0.0011 <method 'split' of 'str' objects> 861 0 0.0046 0.0009 mercurial.encoding:61(tolocal) +861 0 0.0037 0.0014 +<method 'decode' of 'str' objects> 862 0 0.0023 0.0008 encodings.utf_8:15(decode) +862 0 0.0015 0.0015 +<_codecs.utf_8_decode> 4 0 0.0008 0.0008 <method 'close' of 'file' objects> 179 154 0.0202 0.0004 mercurial.demandimport:83(__getattribute__) +36 11 0.0199 0.0003 +mercurial.demandimport:55(_load) +72 0 0.0001 0.0001 +mercurial.demandimport:83(__getattribute__) +36 0 0.0000 0.0000 +<getattr> 1 0 0.0015 0.0004 mercurial.tags:148(_readtagcache) Time: real 0.060 secs (user 0.030+0.000 sys 0.010+0.000)
author Brodie Rao <brodie@sf.io>
date Sun, 13 May 2012 14:04:04 +0200
parents df902fe3d79e
children 107a3270a24a
line wrap: on
line source

# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 Matt Mackall <mpm@selenic.com>
#
# 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, short
from i18n import _
import util, error

def findcommonincoming(repo, remote, heads=None, force=False):
    """Return a tuple (common, fetch, heads) used to identify the common
    subset of nodes between repo and remote.

    "common" is a list of (at least) the heads of the common subset.
    "fetch" is a list of roots of the nodes that would be incoming, to be
      supplied to changegroupsubset.
    "heads" is either the supplied heads, or else the remote's heads.
    """

    m = repo.changelog.nodemap
    search = []
    fetch = set()
    seen = set()
    seenbranch = set()
    base = set()

    if not heads:
        heads = remote.heads()

    if repo.changelog.tip() == nullid:
        base.add(nullid)
        if heads != [nullid]:
            return [nullid], [nullid], list(heads)
        return [nullid], [], heads

    # assume we're closer to the tip than the root
    # and start by examining the heads
    repo.ui.status(_("searching for changes\n"))

    unknown = []
    for h in heads:
        if h not in m:
            unknown.append(h)
        else:
            base.add(h)

    if not unknown:
        return list(base), [], list(heads)

    req = set(unknown)
    reqcnt = 0

    # search through remote branches
    # a 'branch' here is a linear segment of history, with four parts:
    # head, root, first parent, second parent
    # (a branch always has two parents (or none) by definition)
    unknown = remote.branches(unknown)
    while unknown:
        r = []
        while unknown:
            n = unknown.pop(0)
            if n[0] in seen:
                continue

            repo.ui.debug("examining %s:%s\n"
                          % (short(n[0]), short(n[1])))
            if n[0] == nullid: # found the end of the branch
                pass
            elif n in seenbranch:
                repo.ui.debug("branch already found\n")
                continue
            elif n[1] and n[1] in m: # do we know the base?
                repo.ui.debug("found incomplete branch %s:%s\n"
                              % (short(n[0]), short(n[1])))
                search.append(n[0:2]) # schedule branch range for scanning
                seenbranch.add(n)
            else:
                if n[1] not in seen and n[1] not in fetch:
                    if n[2] in m and n[3] in m:
                        repo.ui.debug("found new changeset %s\n" %
                                      short(n[1]))
                        fetch.add(n[1]) # earliest unknown
                    for p in n[2:4]:
                        if p in m:
                            base.add(p) # latest known

                for p in n[2:4]:
                    if p not in req and p not in m:
                        r.append(p)
                        req.add(p)
            seen.add(n[0])

        if r:
            reqcnt += 1
            repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
            repo.ui.debug("request %d: %s\n" %
                        (reqcnt, " ".join(map(short, r))))
            for p in xrange(0, len(r), 10):
                for b in remote.branches(r[p:p + 10]):
                    repo.ui.debug("received %s:%s\n" %
                                  (short(b[0]), short(b[1])))
                    unknown.append(b)

    # do binary search on the branches we found
    while search:
        newsearch = []
        reqcnt += 1
        repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
        for n, l in zip(search, remote.between(search)):
            l.append(n[1])
            p = n[0]
            f = 1
            for i in l:
                repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
                if i in m:
                    if f <= 2:
                        repo.ui.debug("found new branch changeset %s\n" %
                                          short(p))
                        fetch.add(p)
                        base.add(i)
                    else:
                        repo.ui.debug("narrowed branch search to %s:%s\n"
                                      % (short(p), short(i)))
                        newsearch.append((p, i))
                    break
                p, f = i, f * 2
            search = newsearch

    # sanity check our fetch list
    for f in fetch:
        if f in m:
            raise error.RepoError(_("already have changeset ")
                                  + short(f[:4]))

    base = list(base)
    if base == [nullid]:
        if force:
            repo.ui.warn(_("warning: repository is unrelated\n"))
        else:
            raise util.Abort(_("repository is unrelated"))

    repo.ui.debug("found new changesets starting at " +
                 " ".join([short(f) for f in fetch]) + "\n")

    repo.ui.progress(_('searching'), None)
    repo.ui.debug("%d total queries\n" % reqcnt)

    return base, list(fetch), heads