view hgext/split.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 42e2c7c52e1b
children 2372284d9457
line wrap: on
line source

# split.py - split a changeset into smaller ones
#
# Copyright 2015 Laurent Charignon <lcharignon@fb.com>
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""command to split a changeset into smaller ones (EXPERIMENTAL)"""

from __future__ import absolute_import

from mercurial.i18n import _

from mercurial.node import (
    nullid,
    short,
)

from mercurial import (
    bookmarks,
    cmdutil,
    commands,
    error,
    hg,
    obsolete,
    phases,
    pycompat,
    registrar,
    revsetlang,
    scmutil,
)

# allow people to use split without explicitly enabling rebase extension
from . import (
    rebase,
)

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'

@command('split',
    [('r', 'rev', '', _("revision to split"), _('REV')),
     ('', 'rebase', True, _('rebase descendants after split')),
    ] + cmdutil.commitopts2,
    _('hg split [--no-rebase] [[-r] REV]'),
    helpcategory=command.CATEGORY_CHANGE_MANAGEMENT, helpbasic=True)
def split(ui, repo, *revs, **opts):
    """split a changeset into smaller ones

    Repeatedly prompt changes and commit message for new changesets until there
    is nothing left in the original changeset.

    If --rev was not given, split the working directory parent.

    By default, rebase connected non-obsoleted descendants onto the new
    changeset. Use --no-rebase to avoid the rebase.
    """
    opts = pycompat.byteskwargs(opts)
    revlist = []
    if opts.get('rev'):
        revlist.append(opts.get('rev'))
    revlist.extend(revs)
    with repo.wlock(), repo.lock(), repo.transaction('split') as tr:
        revs = scmutil.revrange(repo, revlist or ['.'])
        if len(revs) > 1:
            raise error.Abort(_('cannot split multiple revisions'))

        rev = revs.first()
        ctx = repo[rev]
        if rev is None or ctx.node() == nullid:
            ui.status(_('nothing to split\n'))
            return 1
        if ctx.node() is None:
            raise error.Abort(_('cannot split working directory'))

        # rewriteutil.precheck is not very useful here because:
        # 1. null check is done above and it's more friendly to return 1
        #    instead of abort
        # 2. mergestate check is done below by cmdutil.bailifchanged
        # 3. unstable check is more complex here because of --rebase
        #
        # So only "public" check is useful and it's checked directly here.
        if ctx.phase() == phases.public:
            raise error.Abort(_('cannot split public changeset'),
                              hint=_("see 'hg help phases' for details"))

        descendants = list(repo.revs('(%d::) - (%d)', rev, rev))
        alloworphaned = obsolete.isenabled(repo, obsolete.allowunstableopt)
        if opts.get('rebase'):
            # Skip obsoleted descendants and their descendants so the rebase
            # won't cause conflicts for sure.
            torebase = list(repo.revs('%ld - (%ld & obsolete())::',
                                      descendants, descendants))
            if not alloworphaned and len(torebase) != len(descendants):
                raise error.Abort(_('split would leave orphaned changesets '
                                    'behind'))
        else:
            if not alloworphaned and descendants:
                raise error.Abort(
                    _('cannot split changeset with children without rebase'))
            torebase = ()

        if len(ctx.parents()) > 1:
            raise error.Abort(_('cannot split a merge changeset'))

        cmdutil.bailifchanged(repo)

        # Deactivate bookmark temporarily so it won't get moved unintentionally
        bname = repo._activebookmark
        if bname and repo._bookmarks[bname] != ctx.node():
            bookmarks.deactivate(repo)

        wnode = repo['.'].node()
        top = None
        try:
            top = dosplit(ui, repo, tr, ctx, opts)
        finally:
            # top is None: split failed, need update --clean recovery.
            # wnode == ctx.node(): wnode split, no need to update.
            if top is None or wnode != ctx.node():
                hg.clean(repo, wnode, show_stats=False)
            if bname:
                bookmarks.activate(repo, bname)
        if torebase and top:
            dorebase(ui, repo, torebase, top)

def dosplit(ui, repo, tr, ctx, opts):
    committed = [] # [ctx]

    # Set working parent to ctx.p1(), and keep working copy as ctx's content
    if ctx.node() != repo.dirstate.p1():
        hg.clean(repo, ctx.node(), show_stats=False)
    with repo.dirstate.parentchange():
        scmutil.movedirstate(repo, ctx.p1())

    # Any modified, added, removed, deleted result means split is incomplete
    incomplete = lambda repo: any(repo.status()[:4])

    # Main split loop
    while incomplete(repo):
        if committed:
            header = (_('HG: Splitting %s. So far it has been split into:\n')
                      % short(ctx.node()))
            for c in committed:
                firstline = c.description().split('\n', 1)[0]
                header += _('HG: - %s: %s\n') % (short(c.node()), firstline)
            header += _('HG: Write commit message for the next split '
                        'changeset.\n')
        else:
            header = _('HG: Splitting %s. Write commit message for the '
                       'first split changeset.\n') % short(ctx.node())
        opts.update({
            'edit': True,
            'interactive': True,
            'message': header + ctx.description(),
        })
        commands.commit(ui, repo, **pycompat.strkwargs(opts))
        newctx = repo['.']
        committed.append(newctx)

    if not committed:
        raise error.Abort(_('cannot split an empty revision'))

    scmutil.cleanupnodes(repo, {ctx.node(): [c.node() for c in committed]},
                         operation='split', fixphase=True)

    return committed[-1]

def dorebase(ui, repo, src, destctx):
    rebase.rebase(ui, repo, rev=[revsetlang.formatspec('%ld', src)],
                  dest=revsetlang.formatspec('%d', destctx.rev()))