hgext/narrow/narrowdirstate.py

match: convert O(n) to O(log n) in exactmatcher.visitchildrenset

When using narrow, during rebase this is called (at least) once per directory in
the set of files in the commit being rebased. Every time it's called, we did the
set arithmetic (now extracted and cached), which was probably pretty cheap but
not necessary to repeat each time, looped over every item in the matcher and
kept things that started with the directory we were querying.

With very large narrowspecs, and a commit that touched a file in a large number
of directories, this was slow. In a pathological repo, the rebase of a single
commit (that touched over 17k files, I believe in approximately as many
directories) with a narrowspec that had >32k entries took 8,246s of profiled
time, with 5,007s of that spent in visitchildrenset (transitively). With this
change, the time spent in visitchildrenset is less than 34s (which is where my
profile cut off). Most of the remaining time was network access due to our
custom remotefilelog-based setup not properly prefetching.

Differential Revision: https://phab.mercurial-scm.org/D10294

# narrowdirstate.py - extensions to mercurial dirstate to support narrow clones
#
# Copyright 2017 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import error


def wrapdirstate(repo, dirstate):
    """Add narrow spec dirstate ignore, block changes outside narrow spec."""

    def _editfunc(fn):
        def _wrapper(self, *args, **kwargs):
            narrowmatch = repo.narrowmatch()
            for f in args:
                if f is not None and not narrowmatch(f) and f not in self:
                    raise error.Abort(
                        _(
                            b"cannot track '%s' - it is outside "
                            + b"the narrow clone"
                        )
                        % f
                    )
            return fn(self, *args, **kwargs)

        return _wrapper

    class narrowdirstate(dirstate.__class__):
        # Prevent adding/editing/copying/deleting files that are outside the
        # sparse checkout
        @_editfunc
        def normal(self, *args, **kwargs):
            return super(narrowdirstate, self).normal(*args, **kwargs)

        @_editfunc
        def add(self, *args):
            return super(narrowdirstate, self).add(*args)

        @_editfunc
        def normallookup(self, *args):
            return super(narrowdirstate, self).normallookup(*args)

        @_editfunc
        def copy(self, *args):
            return super(narrowdirstate, self).copy(*args)

        @_editfunc
        def remove(self, *args):
            return super(narrowdirstate, self).remove(*args)

        @_editfunc
        def merge(self, *args):
            return super(narrowdirstate, self).merge(*args)

        def rebuild(self, parent, allfiles, changedfiles=None):
            if changedfiles is None:
                # Rebuilding entire dirstate, let's filter allfiles to match the
                # narrowspec.
                allfiles = [f for f in allfiles if repo.narrowmatch()(f)]
            super(narrowdirstate, self).rebuild(parent, allfiles, changedfiles)

    dirstate.__class__ = narrowdirstate
    return dirstate