annotate hgext/split.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

# split.py - split a changeset into smaller ones
#
# Copyright 2015 Laurent Charignon <[e-mail]>
# 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,
    pycompat,
    registrar,
    revsetlang,
    rewriteutil,
    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 = b'ships-with-hg-core'


@command(
    b'split',
    [
        (b'r', b'rev', b'', _(b"revision to split"), _(b'REV')),
        (b'', b'rebase', True, _(b'rebase descendants after split')),
    ]
    + cmdutil.commitopts2,
    _(b'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(b'rev'):
        revlist.append(opts.get(b'rev'))
    revlist.extend(revs)
    with repo.wlock(), repo.lock(), repo.transaction(b'split') as tr:
        revs = scmutil.revrange(repo, revlist or [b'.'])
        if len(revs) > 1:
            raise error.Abort(_(b'cannot split multiple revisions'))

        rev = revs.first()
        ctx = repo[rev]
        # Handle nullid specially here (instead of leaving for precheck()
        # below) so we get a nicer message and error code.
        if rev is None or ctx.node() == nullid:
            ui.status(_(b'nothing to split\n'))
            return 1
        if ctx.node() is None:
            raise error.Abort(_(b'cannot split working directory'))

        if opts.get(b'rebase'):
            # Skip obsoleted descendants and their descendants so the rebase
            # won't cause conflicts for sure.
            descendants = list(repo.revs(b'(%d::) - (%d)', rev, rev))
            torebase = list(
                repo.revs(
                    b'%ld - (%ld & obsolete())::', descendants, descendants
                )
            )
        else:
            torebase = []
        rewriteutil.precheck(repo, [rev] + torebase, b'split')

        if len(ctx.parents()) > 1:
            raise error.Abort(_(b'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[b'.'].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
    def incomplete(repo):
        st = repo.status()
        return any((st.modified, st.added, st.removed, st.deleted))

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

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

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

    return committed[-1]


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