annotate mercurial/repair.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)

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <[e-mail]>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial import changegroup, bookmarks
from mercurial.node import short
from mercurial.i18n import _
import os
import errno

def _bundle(repo, bases, heads, node, suffix, compress=True):
    """create a bundle with the specified revisions as a backup"""
    cg = repo.changegroupsubset(bases, heads, 'strip')
    backupdir = repo.join("strip-backup")
    if not os.path.isdir(backupdir):
        os.mkdir(backupdir)
    name = os.path.join(backupdir, "%s-%s.hg" % (short(node), suffix))
    if compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"
    return changegroup.writebundle(cg, name, bundletype)

def _collectfiles(repo, striprev):
    """find out the filelogs affected by the strip"""
    files = set()

    for x in xrange(striprev, len(repo)):
        files.update(repo[x].files())

    return sorted(files)

def _collectbrokencsets(repo, files, striprev):
    """return the changesets which will be broken by the truncation"""
    s = set()
    def collectone(revlog):
        linkgen = (revlog.linkrev(i) for i in revlog)
        # find the truncation point of the revlog
        for lrev in linkgen:
            if lrev >= striprev:
                break
        # see if any revision after this point has a linkrev
        # less than striprev (those will be broken by strip)
        for lrev in linkgen:
            if lrev < striprev:
                s.add(lrev)

    collectone(repo.manifest)
    for fname in files:
        collectone(repo.file(fname))

    return s

def strip(ui, repo, nodelist, backup="all", topic='backup'):
    # It simplifies the logic around updating the branchheads cache if we only
    # have to consider the effect of the stripped revisions and not revisions
    # missing because the cache is out-of-date.
    repo.updatebranchcache()

    cl = repo.changelog
    # TODO handle undo of merge sets
    if isinstance(nodelist, str):
        nodelist = [nodelist]
    striplist = [cl.rev(node) for node in nodelist]
    striprev = min(striplist)

    # Set of potential new heads resulting from the strip.  The parents of any
    # node removed could be a new head because the node to be removed could have
    # been the only child of the parent.
    # Do a list->set->list conversion to remove duplicates.
    stringstriplist = [str(rev) for rev in striplist]
    newheadrevs = set(repo.revs("parents(%lr::) - %lr::", stringstriplist,
                                stringstriplist))

    keeppartialbundle = backup == 'strip'

    # Some revisions with rev > striprev may not be descendants of striprev.
    # We have to find these revisions and put them in a bundle, so that
    # we can restore them after the truncations.
    # To create the bundle we use repo.changegroupsubset which requires
    # the list of heads and bases of the set of interesting revisions.
    # (head = revision in the set that has no descendant in the set;
    #  base = revision in the set that has no ancestor in the set)
    tostrip = set(striplist)
    for rev in striplist:
        for desc in cl.descendants(rev):
            tostrip.add(desc)

    files = _collectfiles(repo, striprev)
    saverevs = _collectbrokencsets(repo, files, striprev)

    # compute heads
    saveheads = set(saverevs)
    for r in xrange(striprev + 1, len(cl)):
        if r not in tostrip:
            saverevs.add(r)
            saveheads.difference_update(cl.parentrevs(r))
            saveheads.add(r)
    saveheads = [cl.node(r) for r in saveheads]

    # compute base nodes
    if saverevs:
        descendants = set(cl.descendants(*saverevs))
        saverevs.difference_update(descendants)
    savebases = [cl.node(r) for r in saverevs]
    stripbases = [cl.node(r) for r in tostrip]

    bm = repo._bookmarks
    updatebm = []
    for m in bm:
        rev = repo[bm[m]].rev()
        if rev in tostrip:
            updatebm.append(m)

    # create a changegroup for all the branches we need to keep
    backupfile = None
    if backup == "all":
        backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
        repo.ui.status(_("saved backup bundle to %s\n") % backupfile)
    if saveheads or savebases:
        # do not compress partial bundle if we remove it from disk later
        chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
                            compress=keeppartialbundle)

    mfst = repo.manifest

    tr = repo.transaction("strip")
    offset = len(tr.entries)

    try:
        tr.startgroup()
        cl.strip(striprev, tr)
        mfst.strip(striprev, tr)
        for fn in files:
            repo.file(fn).strip(striprev, tr)
        tr.endgroup()

        try:
            for i in xrange(offset, len(tr.entries)):
                file, troffset, ignore = tr.entries[i]
                repo.sopener(file, 'a').truncate(troffset)
            tr.close()
        except: # re-raises
            tr.abort()
            raise

        if saveheads or savebases:
            ui.note(_("adding branch\n"))
            f = open(chgrpfile, "rb")
            gen = changegroup.readbundle(f, chgrpfile)
            if not repo.ui.verbose:
                # silence internal shuffling chatter
                repo.ui.pushbuffer()
            repo.addchangegroup(gen, 'strip', 'bundle:' + chgrpfile, True)
            if not repo.ui.verbose:
                repo.ui.popbuffer()
            f.close()
            if not keeppartialbundle:
                os.unlink(chgrpfile)

        # remove undo files
        for undofile in repo.undofiles():
            try:
                os.unlink(undofile)
            except OSError, e:
                if e.errno != errno.ENOENT:
                    ui.warn(_('error removing %s: %s\n') % (undofile, str(e)))

        for m in updatebm:
            bm[m] = repo['.'].node()
        bookmarks.write(repo)
    except: # re-raises
        if backupfile:
            ui.warn(_("strip failed, full bundle stored in '%s'\n")
                    % backupfile)
        elif saveheads:
            ui.warn(_("strip failed, partial bundle stored in '%s'\n")
                    % chgrpfile)
        raise

    repo.destroyed(newheadrevs)