annotate mercurial/repair.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

# 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

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):
        links = (revlog.linkrev(i) for i in revlog)
        # find the truncation point of the revlog
        for lrev in links:
            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 links:
            if lrev < striprev:
                s.add(lrev)

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

    return s

def strip(ui, repo, node, backup="all"):
    cl = repo.changelog
    # TODO delete the undo files, and handle undo of merge sets
    striprev = cl.rev(node)

    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(cl.descendants(striprev))
    tostrip.add(striprev)

    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]

    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, [node], cl.heads(), node, 'backup')
        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:
            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)

        for m in updatebm:
            bm[m] = repo['.'].node()
        bookmarks.write(repo)

    except:
        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()