view mercurial/repair.py @ 42044:bb271ec2fbfb

compression: introduce a `storage.revlog.zstd.level` configuration This option control the zstd compression level used when compressing revlog chunk. The usage of zstd for revlog compression has not graduated from experimental yet, but we intend to fix that soon. The option name for the compression level is more straight forward to pick, so this changesets comes first. Having a dedicated option for each compression engine is useful because they don't support the same range of values. I ran the same measurement as for the zlib compression level (in the parent changesets). The variation in repository size is stay mostly in the same (small) range. The "read/write" performance see smallish variation, but are overall much better than zlib. Write performance show the same tend of having better write performance for when reaching high-end compression. Again, we don't intend to change the default zstd compression level (currently: 3) in this series. However this is worth investigating in the future. The Performance comparison of zlib vs zstd is quite impressive. The repository size stay in the same range, but the performance are much better in all situations. Comparison summary ================== We are looking at: - performance range for zlib - performance range for zstd - comparison of default zstd (level-3) to default zlib (level 6) - comparison of the slowest zstd time to the fastest zlib time Read performance: ----------------- | zlib | zstd | cmp | f2s mercurial | 0.170159 - 0.189219 | 0.144127 - 0.149624 | 80% | 88% pypy | 2.679217 - 2.768691 | 1.532317 - 1.705044 | 60% | 63% netbeans | 122.477027 - 141.620281 | 72.996346 - 89.731560 | 58% | 73% mozilla | 147.867662 - 170.572118 | 91.700995 - 105.853099 | 56% | 71% Write performance: ------------------ | zlib | zstd | cmp | f2s mercurial | 53.250304 - 56.2936129 | 40.877025 - 45.677286 | 75% | 86% pypy | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65% netbeans | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82% mozilla | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80% Raw data -------- repo alg lvl .hg/store size 00manifest.d read write mercurial zlib 1 49,402,813 5,963,475 0.170159 53.250304 mercurial zlib 6 47,197,397 5,875,730 0.182820 56.264320 mercurial zlib 9 47,121,596 5,849,781 0.189219 56.293612 mercurial zstd 1 49,737,084 5,966,355 0.144127 40.877025 mercurial zstd 3 48,961,867 5,895,208 0.146376 42.268142 mercurial zstd 5 48,200,592 5,938,676 0.149624 43.162875 mercurial zstd 10 47,833,520 5,913,353 0.145185 44.012489 mercurial zstd 15 47,314,604 5,728,679 0.147686 45.677286 mercurial zstd 20 47,330,502 5,830,539 0.145789 45.025407 mercurial zstd 22 47,330,076 5,830,539 0.143996 44.690460 pypy zlib 1 370,830,572 28,462,425 2.679217 460.721984 pypy zlib 6 340,112,317 27,648,747 2.768691 467.537158 pypy zlib 9 338,360,736 27,639,003 2.763495 476.589918 pypy zstd 1 362,377,479 27,916,214 1.532317 270.545409 pypy zstd 3 354,137,693 27,905,988 1.686718 294.951509 pypy zstd 5 342,640,043 27,655,774 1.705044 301.002219 pypy zstd 10 334,224,327 27,164,493 1.567287 285.186239 pypy zstd 15 329,000,363 26,645,965 1.637729 299.561332 pypy zstd 20 324,534,039 26,199,547 1.526813 302.149827 pypy zstd 22 324,530,595 26,198,932 1.525718 307.821218 netbeans zlib 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans zlib 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans zlib 9 1,197,135,671 155,034,586 141.620281 678.297064 netbeans zstd 1 1,259,581,737 160,840,613 72.996346 370.356311 netbeans zstd 3 1,232,978,122 157,691,551 81.622317 396.733087 netbeans zstd 5 1,208,034,075 160,246,880 83.080549 364.342626 netbeans zstd 10 1,188,624,176 156,083,417 79.323935 403.594602 netbeans zstd 15 1,176,973,589 153,859,477 89.731560 428.329652 netbeans zstd 20 1,162,958,258 151,147,535 82.842667 392.335349 netbeans zstd 22 1,162,707,029 151,150,220 82.565695 402.840655 mozilla zlib 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla zlib 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla zlib 9 2,587,542,494 287,018,264 163.622338 739.803002 mozilla zstd 1 2,723,159,348 286,617,532 91.700995 570.042751 mozilla zstd 3 2,665,055,001 286,152,013 95.240155 561.412805 mozilla zstd 5 2,607,819,817 288,060,030 101.978048 505.152906 mozilla zstd 10 2,558,761,085 283,967,648 104.113481 497.771202 mozilla zstd 15 2,526,216,060 275,581,300 105.853099 591.930683 mozilla zstd 20 2,485,114,806 266,478,859 95.268795 576.515389 mozilla zstd 22 2,484,869,080 266,456,505 94.429282 572.785537
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 27 Mar 2019 18:35:59 +0100
parents 8c42b4a3d447
children e10b8058da84
line wrap: on
line source

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <mason@suse.com>
# 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 __future__ import absolute_import

import errno
import hashlib

from .i18n import _
from .node import (
    hex,
    short,
)
from . import (
    bundle2,
    changegroup,
    discovery,
    error,
    exchange,
    obsolete,
    obsutil,
    phases,
    pycompat,
    util,
)
from .utils import (
    stringutil,
)

def backupbundle(repo, bases, heads, node, suffix, compress=True,
                 obsolescence=True):
    """create a bundle with the specified revisions as a backup"""

    backupdir = "strip-backup"
    vfs = repo.vfs
    if not vfs.isdir(backupdir):
        vfs.mkdir(backupdir)

    # Include a hash of all the nodes in the filename for uniqueness
    allcommits = repo.set('%ln::%ln', bases, heads)
    allhashes = sorted(c.hex() for c in allcommits)
    totalhash = hashlib.sha1(''.join(allhashes)).digest()
    name = "%s/%s-%s-%s.hg" % (backupdir, short(node),
                               hex(totalhash[:4]), suffix)

    cgversion = changegroup.localversion(repo)
    comp = None
    if cgversion != '01':
        bundletype = "HG20"
        if compress:
            comp = 'BZ'
    elif compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"

    outgoing = discovery.outgoing(repo, missingroots=bases, missingheads=heads)
    contentopts = {
        'cg.version': cgversion,
        'obsolescence': obsolescence,
        'phases': True,
    }
    return bundle2.writenewbundle(repo.ui, repo, 'strip', name, bundletype,
                                  outgoing, contentopts, vfs, compression=comp)

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

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

    return sorted(files)

def _collectrevlog(revlog, striprev):
    _, brokenset = revlog.getstrippoint(striprev)
    return [revlog.linkrev(r) for r in brokenset]

def _collectmanifest(repo, striprev):
    return _collectrevlog(repo.manifestlog.getstorage(b''), striprev)

def _collectbrokencsets(repo, files, striprev):
    """return the changesets which will be broken by the truncation"""
    s = set()

    s.update(_collectmanifest(repo, striprev))
    for fname in files:
        s.update(_collectrevlog(repo.file(fname), striprev))

    return s

def strip(ui, repo, nodelist, backup=True, topic='backup'):
    # This function requires the caller to lock the repo, but it operates
    # within a transaction of its own, and thus requires there to be no current
    # transaction when it is called.
    if repo.currenttransaction() is not None:
        raise error.ProgrammingError('cannot strip from inside a transaction')

    # Simple way to maintain backwards compatibility for this
    # argument.
    if backup in ['none', 'strip']:
        backup = False

    repo = repo.unfiltered()
    repo.destroying()
    vfs = repo.vfs
    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)

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

    # 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)
    saveheads = set(saverevs)
    for r in cl.revs(start=striprev + 1):
        if any(p in tostrip for p in cl.parentrevs(r)):
            tostrip.add(r)

        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]

    stripobsidx = obsmarkers = ()
    if repo.ui.configbool('devel', 'strip-obsmarkers'):
        obsmarkers = obsutil.exclusivemarkers(repo, stripbases)
    if obsmarkers:
        stripobsidx = [i for i, m in enumerate(repo.obsstore)
                       if m in obsmarkers]

    newbmtarget, updatebm = _bookmarkmovements(repo, tostrip)

    backupfile = None
    node = nodelist[-1]
    if backup:
        backupfile = _createstripbackup(repo, stripbases, node, topic)
    # create a changegroup for all the branches we need to keep
    tmpbundlefile = None
    if saveheads:
        # do not compress temporary bundle if we remove it from disk later
        #
        # We do not include obsolescence, it might re-introduce prune markers
        # we are trying to strip.  This is harmless since the stripped markers
        # are already backed up and we did not touched the markers for the
        # saved changesets.
        tmpbundlefile = backupbundle(repo, savebases, saveheads, node, 'temp',
                                     compress=False, obsolescence=False)

    with ui.uninterruptible():
        try:
            with repo.transaction("strip") as tr:
                # TODO this code violates the interface abstraction of the
                # transaction and makes assumptions that file storage is
                # using append-only files. We'll need some kind of storage
                # API to handle stripping for us.
                offset = len(tr._entries)

                tr.startgroup()
                cl.strip(striprev, tr)
                stripmanifest(repo, striprev, tr, files)

                for fn in files:
                    repo.file(fn).strip(striprev, tr)
                tr.endgroup()

                for i in pycompat.xrange(offset, len(tr._entries)):
                    file, troffset, ignore = tr._entries[i]
                    with repo.svfs(file, 'a', checkambig=True) as fp:
                        fp.truncate(troffset)
                    if troffset == 0:
                        repo.store.markremoved(file)

                deleteobsmarkers(repo.obsstore, stripobsidx)
                del repo.obsstore
                repo.invalidatevolatilesets()
                repo._phasecache.filterunknown(repo)

            if tmpbundlefile:
                ui.note(_("adding branch\n"))
                f = vfs.open(tmpbundlefile, "rb")
                gen = exchange.readbundle(ui, f, tmpbundlefile, vfs)
                if not repo.ui.verbose:
                    # silence internal shuffling chatter
                    repo.ui.pushbuffer()
                tmpbundleurl = 'bundle:' + vfs.join(tmpbundlefile)
                txnname = 'strip'
                if not isinstance(gen, bundle2.unbundle20):
                    txnname = "strip\n%s" % util.hidepassword(tmpbundleurl)
                with repo.transaction(txnname) as tr:
                    bundle2.applybundle(repo, gen, tr, source='strip',
                                        url=tmpbundleurl)
                if not repo.ui.verbose:
                    repo.ui.popbuffer()
                f.close()

            with repo.transaction('repair') as tr:
                bmchanges = [(m, repo[newbmtarget].node()) for m in updatebm]
                repo._bookmarks.applychanges(repo, tr, bmchanges)

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

        except: # re-raises
            if backupfile:
                ui.warn(_("strip failed, backup bundle stored in '%s'\n")
                        % vfs.join(backupfile))
            if tmpbundlefile:
                ui.warn(_("strip failed, unrecovered changes stored in '%s'\n")
                        % vfs.join(tmpbundlefile))
                ui.warn(_("(fix the problem, then recover the changesets with "
                          "\"hg unbundle '%s'\")\n") % vfs.join(tmpbundlefile))
            raise
        else:
            if tmpbundlefile:
                # Remove temporary bundle only if there were no exceptions
                vfs.unlink(tmpbundlefile)

    repo.destroyed()
    # return the backup file path (or None if 'backup' was False) so
    # extensions can use it
    return backupfile

def softstrip(ui, repo, nodelist, backup=True, topic='backup'):
    """perform a "soft" strip using the archived phase"""
    tostrip = [c.node() for c in repo.set('sort(%ln::)', nodelist)]
    if not tostrip:
        return None

    newbmtarget, updatebm = _bookmarkmovements(repo, tostrip)
    if backup:
        node = tostrip[0]
        backupfile = _createstripbackup(repo, tostrip, node, topic)

    with repo.transaction('strip') as tr:
        phases.retractboundary(repo, tr, phases.archived, tostrip)
        bmchanges = [(m, repo[newbmtarget].node()) for m in updatebm]
        repo._bookmarks.applychanges(repo, tr, bmchanges)
    return backupfile


def _bookmarkmovements(repo, tostrip):
    # compute necessary bookmark movement
    bm = repo._bookmarks
    updatebm = []
    for m in bm:
        rev = repo[bm[m]].rev()
        if rev in tostrip:
            updatebm.append(m)
    newbmtarget = None
    if updatebm: # don't compute anything is there is no bookmark to move anyway
        # For a set s, max(parents(s) - s) is the same as max(heads(::s - s)),
        # but is much faster
        newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
        if newbmtarget:
            newbmtarget = repo[newbmtarget.first()].node()
        else:
            newbmtarget = '.'
    return newbmtarget, updatebm

def _createstripbackup(repo, stripbases, node, topic):
    # backup the changeset we are about to strip
    vfs = repo.vfs
    cl = repo.changelog
    backupfile = backupbundle(repo, stripbases, cl.heads(), node, topic)
    repo.ui.status(_("saved backup bundle to %s\n") %
                   vfs.join(backupfile))
    repo.ui.log("backupbundle", "saved backup bundle to %s\n",
                vfs.join(backupfile))
    return backupfile

def safestriproots(ui, repo, nodes):
    """return list of roots of nodes where descendants are covered by nodes"""
    torev = repo.unfiltered().changelog.rev
    revs = set(torev(n) for n in nodes)
    # tostrip = wanted - unsafe = wanted - ancestors(orphaned)
    # orphaned = affected - wanted
    # affected = descendants(roots(wanted))
    # wanted = revs
    revset = '%ld - ( ::( (roots(%ld):: and not _phase(%s)) -%ld) )'
    tostrip = set(repo.revs(revset, revs, revs, phases.internal, revs))
    notstrip = revs - tostrip
    if notstrip:
        nodestr = ', '.join(sorted(short(repo[n].node()) for n in notstrip))
        ui.warn(_('warning: orphaned descendants detected, '
                  'not stripping %s\n') % nodestr)
    return [c.node() for c in repo.set('roots(%ld)', tostrip)]

class stripcallback(object):
    """used as a transaction postclose callback"""

    def __init__(self, ui, repo, backup, topic):
        self.ui = ui
        self.repo = repo
        self.backup = backup
        self.topic = topic or 'backup'
        self.nodelist = []

    def addnodes(self, nodes):
        self.nodelist.extend(nodes)

    def __call__(self, tr):
        roots = safestriproots(self.ui, self.repo, self.nodelist)
        if roots:
            strip(self.ui, self.repo, roots, self.backup, self.topic)

def delayedstrip(ui, repo, nodelist, topic=None, backup=True):
    """like strip, but works inside transaction and won't strip irreverent revs

    nodelist must explicitly contain all descendants. Otherwise a warning will
    be printed that some nodes are not stripped.

    Will do a backup if `backup` is True. The last non-None "topic" will be
    used as the backup topic name. The default backup topic name is "backup".
    """
    tr = repo.currenttransaction()
    if not tr:
        nodes = safestriproots(ui, repo, nodelist)
        return strip(ui, repo, nodes, backup=backup, topic=topic)
    # transaction postclose callbacks are called in alphabet order.
    # use '\xff' as prefix so we are likely to be called last.
    callback = tr.getpostclose('\xffstrip')
    if callback is None:
        callback = stripcallback(ui, repo, backup=backup, topic=topic)
        tr.addpostclose('\xffstrip', callback)
    if topic:
        callback.topic = topic
    callback.addnodes(nodelist)

def stripmanifest(repo, striprev, tr, files):
    revlog = repo.manifestlog.getstorage(b'')
    revlog.strip(striprev, tr)
    striptrees(repo, tr, striprev, files)

def striptrees(repo, tr, striprev, files):
    if 'treemanifest' in repo.requirements: # safe but unnecessary
                                            # otherwise
        for unencoded, encoded, size in repo.store.datafiles():
            if (unencoded.startswith('meta/') and
                unencoded.endswith('00manifest.i')):
                dir = unencoded[5:-12]
                repo.manifestlog.getstorage(dir).strip(striprev, tr)

def rebuildfncache(ui, repo):
    """Rebuilds the fncache file from repo history.

    Missing entries will be added. Extra entries will be removed.
    """
    repo = repo.unfiltered()

    if 'fncache' not in repo.requirements:
        ui.warn(_('(not rebuilding fncache because repository does not '
                  'support fncache)\n'))
        return

    with repo.lock():
        fnc = repo.store.fncache
        # Trigger load of fncache.
        if 'irrelevant' in fnc:
            pass

        oldentries = set(fnc.entries)
        newentries = set()
        seenfiles = set()

        progress = ui.makeprogress(_('rebuilding'), unit=_('changesets'),
                                   total=len(repo))
        for rev in repo:
            progress.update(rev)

            ctx = repo[rev]
            for f in ctx.files():
                # This is to minimize I/O.
                if f in seenfiles:
                    continue
                seenfiles.add(f)

                i = 'data/%s.i' % f
                d = 'data/%s.d' % f

                if repo.store._exists(i):
                    newentries.add(i)
                if repo.store._exists(d):
                    newentries.add(d)

        progress.complete()

        if 'treemanifest' in repo.requirements: # safe but unnecessary otherwise
            for dir in util.dirs(seenfiles):
                i = 'meta/%s/00manifest.i' % dir
                d = 'meta/%s/00manifest.d' % dir

                if repo.store._exists(i):
                    newentries.add(i)
                if repo.store._exists(d):
                    newentries.add(d)

        addcount = len(newentries - oldentries)
        removecount = len(oldentries - newentries)
        for p in sorted(oldentries - newentries):
            ui.write(_('removing %s\n') % p)
        for p in sorted(newentries - oldentries):
            ui.write(_('adding %s\n') % p)

        if addcount or removecount:
            ui.write(_('%d items added, %d removed from fncache\n') %
                     (addcount, removecount))
            fnc.entries = newentries
            fnc._dirty = True

            with repo.transaction('fncache') as tr:
                fnc.write(tr)
        else:
            ui.write(_('fncache already up to date\n'))

def deleteobsmarkers(obsstore, indices):
    """Delete some obsmarkers from obsstore and return how many were deleted

    'indices' is a list of ints which are the indices
    of the markers to be deleted.

    Every invocation of this function completely rewrites the obsstore file,
    skipping the markers we want to be removed. The new temporary file is
    created, remaining markers are written there and on .close() this file
    gets atomically renamed to obsstore, thus guaranteeing consistency."""
    if not indices:
        # we don't want to rewrite the obsstore with the same content
        return

    left = []
    current = obsstore._all
    n = 0
    for i, m in enumerate(current):
        if i in indices:
            n += 1
            continue
        left.append(m)

    newobsstorefile = obsstore.svfs('obsstore', 'w', atomictemp=True)
    for bytes in obsolete.encodemarkers(left, True, obsstore._version):
        newobsstorefile.write(bytes)
    newobsstorefile.close()
    return n