view hgext/strip.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 1acaa9f37377
line wrap: on
line source

"""strip changesets and their descendants from history

This extension allows you to strip changesets and all their descendants from the
repository. See the command help for details.
"""
from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import (
    bookmarks as bookmarksmod,
    cmdutil,
    error,
    hg,
    lock as lockmod,
    merge,
    node as nodemod,
    pycompat,
    registrar,
    repair,
    scmutil,
    util,
)
nullid = nodemod.nullid
release = lockmod.release

cmdtable = {}
command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'

def checksubstate(repo, baserev=None):
    '''return list of subrepos at a different revision than substate.
    Abort if any subrepos have uncommitted changes.'''
    inclsubs = []
    wctx = repo[None]
    if baserev:
        bctx = repo[baserev]
    else:
        bctx = wctx.p1()
    for s in sorted(wctx.substate):
        wctx.sub(s).bailifchanged(True)
        if s not in bctx.substate or bctx.sub(s).dirty():
            inclsubs.append(s)
    return inclsubs

def checklocalchanges(repo, force=False, excsuffix=''):
    cmdutil.checkunfinished(repo)
    s = repo.status()
    if not force:
        if s.modified or s.added or s.removed or s.deleted:
            _("local changes found") # i18n tool detection
            raise error.Abort(_("local changes found" + excsuffix))
        if checksubstate(repo):
            _("local changed subrepos found") # i18n tool detection
            raise error.Abort(_("local changed subrepos found" + excsuffix))
    return s

def _findupdatetarget(repo, nodes):
    unode, p2 = repo.changelog.parents(nodes[0])
    currentbranch = repo[None].branch()

    if (util.safehasattr(repo, 'mq') and p2 != nullid
        and p2 in [x.node for x in repo.mq.applied]):
        unode = p2
    elif currentbranch != repo[unode].branch():
        pwdir = 'parents(wdir())'
        revset = 'max(((parents(%ln::%r) + %r) - %ln::%r) and branch(%s))'
        branchtarget = repo.revs(revset, nodes, pwdir, pwdir, nodes, pwdir,
                                 currentbranch)
        if branchtarget:
            cl = repo.changelog
            unode = cl.node(branchtarget.first())

    return unode

def strip(ui, repo, revs, update=True, backup=True, force=None, bookmarks=None,
          soft=False):
    with repo.wlock(), repo.lock():

        if update:
            checklocalchanges(repo, force=force)
            urev = _findupdatetarget(repo, revs)
            hg.clean(repo, urev)
            repo.dirstate.write(repo.currenttransaction())

        if soft:
            repair.softstrip(ui, repo, revs, backup)
        else:
            repair.strip(ui, repo, revs, backup)

        repomarks = repo._bookmarks
        if bookmarks:
            with repo.transaction('strip') as tr:
                if repo._activebookmark in bookmarks:
                    bookmarksmod.deactivate(repo)
                repomarks.applychanges(repo, tr, [(b, None) for b in bookmarks])
            for bookmark in sorted(bookmarks):
                ui.write(_("bookmark '%s' deleted\n") % bookmark)

@command("strip",
         [
          ('r', 'rev', [], _('strip specified revision (optional, '
                               'can specify revisions without this '
                               'option)'), _('REV')),
          ('f', 'force', None, _('force removal of changesets, discard '
                                 'uncommitted changes (no backup)')),
          ('', 'no-backup', None, _('do not save backup bundle')),
          ('', 'nobackup', None, _('do not save backup bundle '
                                   '(DEPRECATED)')),
          ('n', '', None, _('ignored  (DEPRECATED)')),
          ('k', 'keep', None, _("do not modify working directory during "
                                "strip")),
          ('B', 'bookmark', [], _("remove revs only reachable from given"
                                  " bookmark"), _('BOOKMARK')),
          ('', 'soft', None,
          _("simply drop changesets from visible history (EXPERIMENTAL)")),
         ],
          _('hg strip [-k] [-f] [-B bookmark] [-r] REV...'),
          helpcategory=command.CATEGORY_MAINTENANCE)
def stripcmd(ui, repo, *revs, **opts):
    """strip changesets and all their descendants from the repository

    The strip command removes the specified changesets and all their
    descendants. If the working directory has uncommitted changes, the
    operation is aborted unless the --force flag is supplied, in which
    case changes will be discarded.

    If a parent of the working directory is stripped, then the working
    directory will automatically be updated to the most recent
    available ancestor of the stripped parent after the operation
    completes.

    Any stripped changesets are stored in ``.hg/strip-backup`` as a
    bundle (see :hg:`help bundle` and :hg:`help unbundle`). They can
    be restored by running :hg:`unbundle .hg/strip-backup/BUNDLE`,
    where BUNDLE is the bundle file created by the strip. Note that
    the local revision numbers will in general be different after the
    restore.

    Use the --no-backup option to discard the backup bundle once the
    operation completes.

    Strip is not a history-rewriting operation and can be used on
    changesets in the public phase. But if the stripped changesets have
    been pushed to a remote repository you will likely pull them again.

    Return 0 on success.
    """
    opts = pycompat.byteskwargs(opts)
    backup = True
    if opts.get('no_backup') or opts.get('nobackup'):
        backup = False

    cl = repo.changelog
    revs = list(revs) + opts.get('rev')
    revs = set(scmutil.revrange(repo, revs))

    with repo.wlock():
        bookmarks = set(opts.get('bookmark'))
        if bookmarks:
            repomarks = repo._bookmarks
            if not bookmarks.issubset(repomarks):
                raise error.Abort(_("bookmark '%s' not found") %
                    ','.join(sorted(bookmarks - set(repomarks.keys()))))

            # If the requested bookmark is not the only one pointing to a
            # a revision we have to only delete the bookmark and not strip
            # anything. revsets cannot detect that case.
            nodetobookmarks = {}
            for mark, node in repomarks.iteritems():
                nodetobookmarks.setdefault(node, []).append(mark)
            for marks in nodetobookmarks.values():
                if bookmarks.issuperset(marks):
                    rsrevs = scmutil.bookmarkrevs(repo, marks[0])
                    revs.update(set(rsrevs))
            if not revs:
                with repo.lock(), repo.transaction('bookmark') as tr:
                    bmchanges = [(b, None) for b in bookmarks]
                    repomarks.applychanges(repo, tr, bmchanges)
                for bookmark in sorted(bookmarks):
                    ui.write(_("bookmark '%s' deleted\n") % bookmark)

        if not revs:
            raise error.Abort(_('empty revision set'))

        descendants = set(cl.descendants(revs))
        strippedrevs = revs.union(descendants)
        roots = revs.difference(descendants)

        # if one of the wdir parent is stripped we'll need
        # to update away to an earlier revision
        update = any(p != nullid and cl.rev(p) in strippedrevs
                     for p in repo.dirstate.parents())

        rootnodes = set(cl.node(r) for r in roots)

        q = getattr(repo, 'mq', None)
        if q is not None and q.applied:
            # refresh queue state if we're about to strip
            # applied patches
            if cl.rev(repo.lookup('qtip')) in strippedrevs:
                q.applieddirty = True
                start = 0
                end = len(q.applied)
                for i, statusentry in enumerate(q.applied):
                    if statusentry.node in rootnodes:
                        # if one of the stripped roots is an applied
                        # patch, only part of the queue is stripped
                        start = i
                        break
                del q.applied[start:end]
                q.savedirty()

        revs = sorted(rootnodes)
        if update and opts.get('keep'):
            urev = _findupdatetarget(repo, revs)
            uctx = repo[urev]

            # only reset the dirstate for files that would actually change
            # between the working context and uctx
            descendantrevs = repo.revs(b"%d::.", uctx.rev())
            changedfiles = []
            for rev in descendantrevs:
                # blindly reset the files, regardless of what actually changed
                changedfiles.extend(repo[rev].files())

            # reset files that only changed in the dirstate too
            dirstate = repo.dirstate
            dirchanges = [f for f in dirstate if dirstate[f] != 'n']
            changedfiles.extend(dirchanges)

            repo.dirstate.rebuild(urev, uctx.manifest(), changedfiles)
            repo.dirstate.write(repo.currenttransaction())

            # clear resolve state
            merge.mergestate.clean(repo, repo['.'].node())

            update = False


        strip(ui, repo, revs, backup=backup, update=update,
              force=opts.get('force'), bookmarks=bookmarks,
              soft=opts['soft'])

    return 0