comparison mercurial/discovery.py @ 51594:e3a5ec2d236a

outgoing: rework the handling of the `missingroots` case to be faster

The previous implementation was slow, to the point it was taking a significant
amount of `hg bundle --type none-streamv2` call. We rework the code to compute
the same value much faster, making the operation disappear from the `hg bundle
--type none-streamv2` profile. Someone would remark that producing a streamclone
does not requires an `outgoing` object. However that is a matter for another
day. There is other user of `missingroots` (non stream `hg bundle` call for
example), and they will also benefit from this rework.

We implement an old TODO in the process, directly computing the missing and
common attribute as we have most element at hand already.

### benchmark.name                = hg.command.bundle
  # bin-env-vars.hg.flavor        = default
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.revs       = all
  # benchmark.variants.type       = none-streamv2
 ## data-env-vars.name            = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 7.750458
after:  6.665565  (-14.00%, -1.08)
 ## data-env-vars.name            = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 0.700229
after:  0.496050  (-29.16%, -0.20)
 ## data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 346.508952
after:  316.749699  (-8.59%, -29.76)
 ## data-env-vars.name            = pypy-2024-03-22-zstd-sparse-revlog
before: 3.401700
after:  2.915810  (-14.28%, -0.49)
 ## data-env-vars.name            = tryton-public-2024-03-22-zstd-sparse-revlog
before: 1.870798
after:  1.461583  (-21.87%, -0.41)



note: this whole `missingroots` of outgoing has a limited number of callers and
could likely be replace by something simpler (like taking an explicit
"missing_revs" set for example). However this is a wider change and we focus on
a small impact, quick rework that does not change the API for now.

51593:b5500857e173

from . import (
    bookmarks,
    branchmap,
    error,
    obsolete,
    phases,
    pycompat,
    scmutil,
    setdiscovery,

    by discovery."""

    def __init__(
        self, repo, commonheads=None, ancestorsof=None, missingroots=None
    ):
        # at least one of them must not be set
        assert None in (commonheads, missingroots)
        cl = repo.changelog
        if ancestorsof is None:
            ancestorsof = cl.heads()
        if missingroots:
            # TODO remove call to nodesbetween.
            # TODO populate attributes on outgoing instance instead of setting
            # discbases.
            csets, roots, heads = cl.nodesbetween(missingroots, ancestorsof)
            included = set(csets)
            discbases = []
            for n in csets:
                discbases.extend([p for p in cl.parents(n) if p != repo.nullid])
            ancestorsof = heads
            commonheads = [n for n in discbases if n not in included]
        elif not commonheads:
            commonheads = [repo.nullid]
        self.commonheads = commonheads
        self.ancestorsof = ancestorsof
        self._revlog = cl
        self._common = None
        self._missing = None
        self.excluded = []

    def _computecommonmissing(self):
        sets = self._revlog.findcommonmissing(
            self.commonheads, self.ancestorsof

51594:e3a5ec2d236a

from . import (
    bookmarks,
    branchmap,
    error,
    node as nodemod,
    obsolete,
    phases,
    pycompat,
    scmutil,
    setdiscovery,

    by discovery."""

    def __init__(
        self, repo, commonheads=None, ancestorsof=None, missingroots=None
    ):
        # at most one of them must not be set
        if commonheads is not None and missingroots is not None:
            m = 'commonheads and missingroots arguments are mutually exclusive'
            raise error.ProgrammingError(m)
        cl = repo.changelog
        missing = None
        common = None
        if ancestorsof is None:
            ancestorsof = cl.heads()
        if missingroots:
            # TODO remove call to nodesbetween.
            missing_rev = repo.revs('%ln::%ln', missingroots, ancestorsof)
            unfi = repo.unfiltered()
            ucl = unfi.changelog
            to_node = ucl.node
            ancestorsof = [to_node(r) for r in ucl.headrevs(missing_rev)]
            parent_revs = ucl.parentrevs
            common_legs = set()
            for r in missing_rev:
                p1, p2 = parent_revs(r)
                if p1 not in missing_rev:
                    common_legs.add(p1)
                if p2 not in missing_rev:
                    common_legs.add(p2)
            common_legs.discard(nodemod.nullrev)
            if not common_legs:
                commonheads = [repo.nullid]
                common = set()
            else:
                commonheads_revs = unfi.revs(
                    'heads(%ld::%ld)',
                    common_legs,
                    common_legs,
                )
                commonheads = [to_node(r) for r in commonheads_revs]
                common = ucl.ancestors(commonheads_revs, inclusive=True)
            missing = [to_node(r) for r in missing_rev]
        elif not commonheads:
            commonheads = [repo.nullid]
        self.commonheads = commonheads
        self.ancestorsof = ancestorsof
        self._revlog = cl
        self._common = common
        self._missing = missing
        self.excluded = []

    def _computecommonmissing(self):
        sets = self._revlog.findcommonmissing(
            self.commonheads, self.ancestorsof