view mercurial/policy.py @ 42743:8c9a6adec67a

rust-discovery: using the children cache in add_missing The DAG range computation often needs to get back to very old revisions, and turns out to be disproportionately long, given that the end goal is to remove the descendents of the given missing revisons from the undecided set. The fast iteration capabilities available in the Rust case make it possible to avoid the DAG range entirely, at the cost of precomputing the children cache, and to simply iterate on children of the given missing revisions. This is a case where staying on the same side of the interface between the two languages has clear benefits. On discoveries with initial undecided sets small enough to bypass sampling entirely, the total cost of computing the children cache and the subsequent iteration becomes better than the Python + C counterpart, which relies on reachableroots2. For example, on a repo with more than one million revisions with an initial undecided set of 11 elements, we get these figures: Rust version with simple iteration addcommons: 57.287us first undecided computation: 184.278334ms first children cache computation: 131.056us addmissings iteration: 42.766us first addinfo total: 185.24 ms Python + C version first addcommons: 0.29 ms addcommons 0.21 ms first undecided computation 191.35 ms addmissings 45.75 ms first addinfo total: 237.77 ms On discoveries with large undecided sets, the initial price paid makes the first addinfo slower than the Python + C version, but that's more than compensated by the gain in sampling and subsequent iterations. Here's an extreme example with an undecided set of a million revisions: Rust version: first undecided computation: 293.842629ms first children cache computation: 407.911297ms addmissings iteration: 34.312869ms first addinfo total: 776.02 ms taking initial sample query 2: sampling time: 1318.38 ms query 2; still undecided: 1005013, sample size is: 200 addmissings: 143.062us Python + C version: first undecided computation 298.13 ms addmissings 80.13 ms first addinfo total: 399.62 ms taking initial sample query 2: sampling time: 3957.23 ms query 2; still undecided: 1005013, sample size is: 200 addmissings 52.88 ms Differential Revision: https://phab.mercurial-scm.org/D6428
author Georges Racinet <georges.racinet@octobus.net>
date Tue, 16 Apr 2019 01:16:39 +0200
parents 810f66b468cd
children 57875cf423c9
line wrap: on
line source

# policy.py - module policy logic for Mercurial.
#
# Copyright 2015 Gregory Szorc <gregory.szorc@gmail.com>
#
# 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

import os
import sys

# Rules for how modules can be loaded. Values are:
#
#    c - require C extensions
#    rust+c - require Rust and C extensions
#    rust+c-allow - allow Rust and C extensions with fallback to pure Python
#                   for each
#    allow - allow pure Python implementation when C loading fails
#    cffi - required cffi versions (implemented within pure module)
#    cffi-allow - allow pure Python implementation if cffi version is missing
#    py - only load pure Python modules
#
# By default, fall back to the pure modules so the in-place build can
# run without recompiling the C extensions. This will be overridden by
# __modulepolicy__ generated by setup.py.
policy = b'allow'
_packageprefs = {
    # policy: (versioned package, pure package)
    b'c': (r'cext', None),
    b'allow': (r'cext', r'pure'),
    b'cffi': (r'cffi', None),
    b'cffi-allow': (r'cffi', r'pure'),
    b'py': (None, r'pure'),
    # For now, rust policies impact importrust only
    b'rust+c': (r'cext', None),
    b'rust+c-allow': (r'cext', r'pure'),
}

try:
    from . import __modulepolicy__
    policy = __modulepolicy__.modulepolicy
except ImportError:
    pass

# PyPy doesn't load C extensions.
#
# The canonical way to do this is to test platform.python_implementation().
# But we don't import platform and don't bloat for it here.
if r'__pypy__' in sys.builtin_module_names:
    policy = b'cffi'

# Environment variable can always force settings.
if sys.version_info[0] >= 3:
    if r'HGMODULEPOLICY' in os.environ:
        policy = os.environ[r'HGMODULEPOLICY'].encode(r'utf-8')
else:
    policy = os.environ.get(r'HGMODULEPOLICY', policy)

def _importfrom(pkgname, modname):
    # from .<pkgname> import <modname> (where . is looked through this module)
    fakelocals = {}
    pkg = __import__(pkgname, globals(), fakelocals, [modname], level=1)
    try:
        fakelocals[modname] = mod = getattr(pkg, modname)
    except AttributeError:
        raise ImportError(r'cannot import name %s' % modname)
    # force import; fakelocals[modname] may be replaced with the real module
    getattr(mod, r'__doc__', None)
    return fakelocals[modname]

# keep in sync with "version" in C modules
_cextversions = {
    (r'cext', r'base85'): 1,
    (r'cext', r'bdiff'): 3,
    (r'cext', r'mpatch'): 1,
    (r'cext', r'osutil'): 4,
    (r'cext', r'parsers'): 13,
}

# map import request to other package or module
_modredirects = {
    (r'cext', r'charencode'): (r'cext', r'parsers'),
    (r'cffi', r'base85'): (r'pure', r'base85'),
    (r'cffi', r'charencode'): (r'pure', r'charencode'),
    (r'cffi', r'parsers'): (r'pure', r'parsers'),
}

def _checkmod(pkgname, modname, mod):
    expected = _cextversions.get((pkgname, modname))
    actual = getattr(mod, r'version', None)
    if actual != expected:
        raise ImportError(r'cannot import module %s.%s '
                          r'(expected version: %d, actual: %r)'
                          % (pkgname, modname, expected, actual))

def importmod(modname):
    """Import module according to policy and check API version"""
    try:
        verpkg, purepkg = _packageprefs[policy]
    except KeyError:
        raise ImportError(r'invalid HGMODULEPOLICY %r' % policy)
    assert verpkg or purepkg
    if verpkg:
        pn, mn = _modredirects.get((verpkg, modname), (verpkg, modname))
        try:
            mod = _importfrom(pn, mn)
            if pn == verpkg:
                _checkmod(pn, mn, mod)
            return mod
        except ImportError:
            if not purepkg:
                raise
    pn, mn = _modredirects.get((purepkg, modname), (purepkg, modname))
    return _importfrom(pn, mn)

def _isrustpermissive():
    """Assuming the policy is a Rust one, tell if it's permissive."""
    return policy.endswith(b'-allow')

def importrust(modname, member=None, default=None):
    """Import Rust module according to policy and availability.

    If policy isn't a Rust one, this returns `default`.

    If either the module or its member is not available, this returns `default`
    if policy is permissive and raises `ImportError` if not.
    """
    if not policy.startswith(b'rust'):
        return default

    try:
        mod = _importfrom(r'rustext', modname)
    except ImportError:
        if _isrustpermissive():
            return default
        raise
    if member is None:
        return mod

    try:
        return getattr(mod, member)
    except AttributeError:
        if _isrustpermissive():
            return default
        raise ImportError(r"Cannot import name %s" % member)