view hgext/bookflow.py @ 49777:e1953a34c110

bundle: emit full snapshot as is, without doing a redelta With the new `forced` delta-reused policy, it become important to be able to send full snapshot where full snapshot are needed. Otherwise, the fallback delta will simply be used on the client sideā€¦ creating monstrous delta chain, since revision that are meant as a reset of delta-chain chain becoming too complex are simply adding a new full delta-tree on the leaf of another one. In the `non-forced` cases, client process full snapshot from the bundle differently from deltas, so client will still try to convert the full snapshot into a delta if possible. So this will no lead to pathological storage explosion. I have considered making this configurable, but the impact seems limited enough that it does not seems to be worth it. Especially with the current sparse-revlog format that use "delta-tree" with multiple level snapshots, full snapshot are much less frequent and not that different from other intermediate snapshot that we are already sending over the wire anyway. CPU wise, this will help the bundling side a little as it will not need to reconstruct revisions and compute deltas. The unbundling side might save a tiny amount of CPU as it won't need to reconstruct the delta-base to reconstruct the revision full text. This only slightly visible in some of the benchmarks. And have no real impact on most of them. ### data-env-vars.name = pypy-2018-08-01-zstd-sparse-revlog # benchmark.name = perf-bundle # benchmark.variants.revs = last-40000 before: 11.467186 seconds just-emit-full: 11.190576 seconds (-2.41%) with-pull-force: 11.041091 seconds (-3.72%) # benchmark.name = perf-unbundle # benchmark.variants.revs = last-40000 before: 16.744862 just-emit-full:: 16.561036 seconds (-1.10%) with-pull-force: 16.389344 seconds (-2.12%) # benchmark.name = pull # benchmark.variants.revs = last-40000 before: 26.870569 just-emit-full: 26.391188 seconds (-1.78%) with-pull-force: 25.633184 seconds (-4.60%) Space wise (so network-wise) the impact is fairly small. When taking compression into account. Below are tests the size of `hg bundle --all` for a handful of benchmark repositories (with bzip, zstd compression and without it) This show a small increase in the bundle size, but nothing really significant except maybe for mozilla-try (+12%) that nobody really pulls large chunk of anyway. Mozilla-try is also the repository that benefit the most for not having to recompute deltas client size. ### mercurial: bzip-before: 26 406 342 bytes bzip-after: 26 691 543 bytes +1.08% zstd-before: 27 918 645 bytes zstd-after: 28 075 896 bytes +0.56% none-before: 98 675 601 bytes none-after: 100 411 237 bytes +1.76% ### pypy bzip-before: 201 295 752 bytes bzip-after: 209 780 282 bytes +4.21% zstd-before: 202 974 795 bytes zstd-after: 205 165 780 bytes +1.08% none-before: 871 070 261 bytes none-after: 993 595 057 bytes +14.07% ### netbeans bzip-before: 601 314 330 bytes bzip-after: 614 246 241 bytes +2.15% zstd-before: 604 745 136 bytes zstd-after: 615 497 705 bytes +1.78% none-before: 3 338 238 571 bytes none-after: 3 439 422 535 bytes +3.03% ### mozilla-central bzip-before: 1 493 006 921 bytes bzip-after: 1 549 650 570 bytes +3.79% zstd-before: 1 481 910 102 bytes zstd-after: 1 513 052 415 bytes +2.10% none-before: 6 535 929 910 bytes none-after: 7 010 191 342 bytes +7.26% ### mozilla-try bzip-before: 6 583 425 999 bytes bzip-after: 7 423 536 928 bytes +12.76% zstd-before: 6 021 009 212 bytes zstd-after: 6 674 922 420 bytes +10.86% none-before: 22 954 739 558 bytes none-after: 26 013 854 771 bytes +13.32%
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 07 Dec 2022 20:12:23 +0100
parents 6000f5b25c9b
children 3c8a31be81df
line wrap: on
line source

"""implements bookmark-based branching (EXPERIMENTAL)

 - Disables creation of new branches (config: enable_branches=False).
 - Requires an active bookmark on commit (config: require_bookmark=True).
 - Doesn't move the active bookmark on update, only on commit.
 - Requires '--rev' for moving an existing bookmark.
 - Protects special bookmarks (config: protect=@).

 flow related commands

    :hg book NAME: create a new bookmark
    :hg book NAME -r REV: move bookmark to revision (fast-forward)
    :hg up|co NAME: switch to bookmark
    :hg push -B .: push active bookmark
"""

from mercurial.i18n import _
from mercurial import (
    bookmarks,
    commands,
    error,
    extensions,
    registrar,
)

MY_NAME = b'bookflow'

configtable = {}
configitem = registrar.configitem(configtable)

configitem(MY_NAME, b'protect', [b'@'])
configitem(MY_NAME, b'require-bookmark', True)
configitem(MY_NAME, b'enable-branches', False)

cmdtable = {}
command = registrar.command(cmdtable)


def commit_hook(ui, repo, **kwargs):
    active = repo._bookmarks.active
    if active:
        if active in ui.configlist(MY_NAME, b'protect'):
            raise error.Abort(
                _(b'cannot commit, bookmark %s is protected') % active
            )
        if not cwd_at_bookmark(repo, active):
            raise error.Abort(
                _(
                    b'cannot commit, working directory out of sync with active bookmark'
                ),
                hint=_(b"run 'hg up %s'") % active,
            )
    elif ui.configbool(MY_NAME, b'require-bookmark', True):
        raise error.Abort(_(b'cannot commit without an active bookmark'))
    return 0


def bookmarks_update(orig, repo, parents, node):
    if len(parents) == 2:
        # called during commit
        return orig(repo, parents, node)
    else:
        # called during update
        return False


def bookmarks_addbookmarks(
    orig, repo, tr, names, rev=None, force=False, inactive=False
):
    if not rev:
        marks = repo._bookmarks
        for name in names:
            if name in marks:
                raise error.Abort(
                    _(
                        b"bookmark %s already exists, to move use the --rev option"
                    )
                    % name
                )
    return orig(repo, tr, names, rev, force, inactive)


def commands_commit(orig, ui, repo, *args, **opts):
    commit_hook(ui, repo)
    return orig(ui, repo, *args, **opts)


def commands_pull(orig, ui, repo, *args, **opts):
    rc = orig(ui, repo, *args, **opts)
    active = repo._bookmarks.active
    if active and not cwd_at_bookmark(repo, active):
        ui.warn(
            _(
                b"working directory out of sync with active bookmark, run "
                b"'hg up %s'"
            )
            % active
        )
    return rc


def commands_branch(orig, ui, repo, label=None, **opts):
    if label and not opts.get('clean') and not opts.get('rev'):
        raise error.Abort(
            _(
                b"creating named branches is disabled and you should use bookmarks"
            ),
            hint=b"see 'hg help bookflow'",
        )
    return orig(ui, repo, label, **opts)


def cwd_at_bookmark(repo, mark):
    mark_id = repo._bookmarks[mark]
    cur_id = repo.lookup(b'.')
    return cur_id == mark_id


def uisetup(ui):
    extensions.wrapfunction(bookmarks, b'update', bookmarks_update)
    extensions.wrapfunction(bookmarks, b'addbookmarks', bookmarks_addbookmarks)
    extensions.wrapcommand(commands.table, b'commit', commands_commit)
    extensions.wrapcommand(commands.table, b'pull', commands_pull)
    if not ui.configbool(MY_NAME, b'enable-branches'):
        extensions.wrapcommand(commands.table, b'branch', commands_branch)