view hgdemandimport/demandimportpy2.py @ 42044:bb271ec2fbfb

compression: introduce a `storage.revlog.zstd.level` configuration This option control the zstd compression level used when compressing revlog chunk. The usage of zstd for revlog compression has not graduated from experimental yet, but we intend to fix that soon. The option name for the compression level is more straight forward to pick, so this changesets comes first. Having a dedicated option for each compression engine is useful because they don't support the same range of values. I ran the same measurement as for the zlib compression level (in the parent changesets). The variation in repository size is stay mostly in the same (small) range. The "read/write" performance see smallish variation, but are overall much better than zlib. Write performance show the same tend of having better write performance for when reaching high-end compression. Again, we don't intend to change the default zstd compression level (currently: 3) in this series. However this is worth investigating in the future. The Performance comparison of zlib vs zstd is quite impressive. The repository size stay in the same range, but the performance are much better in all situations. Comparison summary ================== We are looking at: - performance range for zlib - performance range for zstd - comparison of default zstd (level-3) to default zlib (level 6) - comparison of the slowest zstd time to the fastest zlib time Read performance: ----------------- | zlib | zstd | cmp | f2s mercurial | 0.170159 - 0.189219 | 0.144127 - 0.149624 | 80% | 88% pypy | 2.679217 - 2.768691 | 1.532317 - 1.705044 | 60% | 63% netbeans | 122.477027 - 141.620281 | 72.996346 - 89.731560 | 58% | 73% mozilla | 147.867662 - 170.572118 | 91.700995 - 105.853099 | 56% | 71% Write performance: ------------------ | zlib | zstd | cmp | f2s mercurial | 53.250304 - 56.2936129 | 40.877025 - 45.677286 | 75% | 86% pypy | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65% netbeans | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82% mozilla | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80% Raw data -------- repo alg lvl .hg/store size 00manifest.d read write mercurial zlib 1 49,402,813 5,963,475 0.170159 53.250304 mercurial zlib 6 47,197,397 5,875,730 0.182820 56.264320 mercurial zlib 9 47,121,596 5,849,781 0.189219 56.293612 mercurial zstd 1 49,737,084 5,966,355 0.144127 40.877025 mercurial zstd 3 48,961,867 5,895,208 0.146376 42.268142 mercurial zstd 5 48,200,592 5,938,676 0.149624 43.162875 mercurial zstd 10 47,833,520 5,913,353 0.145185 44.012489 mercurial zstd 15 47,314,604 5,728,679 0.147686 45.677286 mercurial zstd 20 47,330,502 5,830,539 0.145789 45.025407 mercurial zstd 22 47,330,076 5,830,539 0.143996 44.690460 pypy zlib 1 370,830,572 28,462,425 2.679217 460.721984 pypy zlib 6 340,112,317 27,648,747 2.768691 467.537158 pypy zlib 9 338,360,736 27,639,003 2.763495 476.589918 pypy zstd 1 362,377,479 27,916,214 1.532317 270.545409 pypy zstd 3 354,137,693 27,905,988 1.686718 294.951509 pypy zstd 5 342,640,043 27,655,774 1.705044 301.002219 pypy zstd 10 334,224,327 27,164,493 1.567287 285.186239 pypy zstd 15 329,000,363 26,645,965 1.637729 299.561332 pypy zstd 20 324,534,039 26,199,547 1.526813 302.149827 pypy zstd 22 324,530,595 26,198,932 1.525718 307.821218 netbeans zlib 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans zlib 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans zlib 9 1,197,135,671 155,034,586 141.620281 678.297064 netbeans zstd 1 1,259,581,737 160,840,613 72.996346 370.356311 netbeans zstd 3 1,232,978,122 157,691,551 81.622317 396.733087 netbeans zstd 5 1,208,034,075 160,246,880 83.080549 364.342626 netbeans zstd 10 1,188,624,176 156,083,417 79.323935 403.594602 netbeans zstd 15 1,176,973,589 153,859,477 89.731560 428.329652 netbeans zstd 20 1,162,958,258 151,147,535 82.842667 392.335349 netbeans zstd 22 1,162,707,029 151,150,220 82.565695 402.840655 mozilla zlib 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla zlib 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla zlib 9 2,587,542,494 287,018,264 163.622338 739.803002 mozilla zstd 1 2,723,159,348 286,617,532 91.700995 570.042751 mozilla zstd 3 2,665,055,001 286,152,013 95.240155 561.412805 mozilla zstd 5 2,607,819,817 288,060,030 101.978048 505.152906 mozilla zstd 10 2,558,761,085 283,967,648 104.113481 497.771202 mozilla zstd 15 2,526,216,060 275,581,300 105.853099 591.930683 mozilla zstd 20 2,485,114,806 266,478,859 95.268795 576.515389 mozilla zstd 22 2,484,869,080 266,456,505 94.429282 572.785537
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Wed, 27 Mar 2019 18:35:59 +0100
parents 574e1d3bc667
children 2372284d9457
line wrap: on
line source

# demandimport.py - global demand-loading of modules for Mercurial
#
# Copyright 2006, 2007 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''
demandimport - automatic demandloading of modules

To enable this module, do:

  import demandimport; demandimport.enable()

Imports of the following forms will be demand-loaded:

  import a, b.c
  import a.b as c
  from a import b,c # a will be loaded immediately

These imports will not be delayed:

  from a import *
  b = __import__(a)
'''

from __future__ import absolute_import

import __builtin__ as builtins
import contextlib
import sys

from . import tracing

contextmanager = contextlib.contextmanager

_origimport = __import__

nothing = object()

def _hgextimport(importfunc, name, globals, *args, **kwargs):
    try:
        return importfunc(name, globals, *args, **kwargs)
    except ImportError:
        if not globals:
            raise
        # extensions are loaded with "hgext_" prefix
        hgextname = 'hgext_%s' % name
        nameroot = hgextname.split('.', 1)[0]
        contextroot = globals.get('__name__', '').split('.', 1)[0]
        if nameroot != contextroot:
            raise
        # retry to import with "hgext_" prefix
        return importfunc(hgextname, globals, *args, **kwargs)

class _demandmod(object):
    """module demand-loader and proxy

    Specify 1 as 'level' argument at construction, to import module
    relatively.
    """

    def __init__(self, name, globals, locals, level):
        if '.' in name:
            head, rest = name.split('.', 1)
            after = [rest]
        else:
            head = name
            after = []
        object.__setattr__(self, r"_data",
                           (head, globals, locals, after, level, set()))
        object.__setattr__(self, r"_module", None)

    def _extend(self, name):
        """add to the list of submodules to load"""
        self._data[3].append(name)

    def _addref(self, name):
        """Record that the named module ``name`` imports this module.

        References to this proxy class having the name of this module will be
        replaced at module load time. We assume the symbol inside the importing
        module is identical to the "head" name of this module. We don't
        actually know if "as X" syntax is being used to change the symbol name
        because this information isn't exposed to __import__.
        """
        self._data[5].add(name)

    def _load(self):
        if not self._module:
            with tracing.log('demandimport %s', self._data[0]):
                head, globals, locals, after, level, modrefs = self._data
                mod = _hgextimport(
                    _origimport, head, globals, locals, None, level)
                if mod is self:
                    # In this case, _hgextimport() above should imply
                    # _demandimport(). Otherwise, _hgextimport() never
                    # returns _demandmod. This isn't intentional behavior,
                    # in fact. (see also issue5304 for detail)
                    #
                    # If self._module is already bound at this point, self
                    # should be already _load()-ed while _hgextimport().
                    # Otherwise, there is no way to import actual module
                    # as expected, because (re-)invoking _hgextimport()
                    # should cause same result.
                    # This is reason why _load() returns without any more
                    # setup but assumes self to be already bound.
                    mod = self._module
                    assert mod and mod is not self, "%s, %s" % (self, mod)
                    return

                # load submodules
                def subload(mod, p):
                    h, t = p, None
                    if '.' in p:
                        h, t = p.split('.', 1)
                    if getattr(mod, h, nothing) is nothing:
                        setattr(mod, h, _demandmod(
                            p, mod.__dict__, mod.__dict__, level=1))
                    elif t:
                        subload(getattr(mod, h), t)

                for x in after:
                    subload(mod, x)

                # Replace references to this proxy instance with the
                # actual module.
                if locals:
                    if locals.get(head) is self:
                        locals[head] = mod
                    elif locals.get(head + r'mod') is self:
                        locals[head + r'mod'] = mod

                for modname in modrefs:
                    modref = sys.modules.get(modname, None)
                    if modref and getattr(modref, head, None) is self:
                        setattr(modref, head, mod)

                object.__setattr__(self, r"_module", mod)

    def __repr__(self):
        if self._module:
            return "<proxied module '%s'>" % self._data[0]
        return "<unloaded module '%s'>" % self._data[0]

    def __call__(self, *args, **kwargs):
        raise TypeError("%s object is not callable" % repr(self))

    def __getattr__(self, attr):
        self._load()
        return getattr(self._module, attr)

    def __setattr__(self, attr, val):
        self._load()
        setattr(self._module, attr, val)

    @property
    def __dict__(self):
        self._load()
        return self._module.__dict__

    @property
    def __doc__(self):
        self._load()
        return self._module.__doc__

_pypy = '__pypy__' in sys.builtin_module_names

def _demandimport(name, globals=None, locals=None, fromlist=None, level=-1):
    if locals is None or name in ignores or fromlist == ('*',):
        # these cases we can't really delay
        return _hgextimport(_origimport, name, globals, locals, fromlist, level)
    elif not fromlist:
        # import a [as b]
        if '.' in name: # a.b
            base, rest = name.split('.', 1)
            # email.__init__ loading email.mime
            if globals and globals.get('__name__', None) == base:
                return _origimport(name, globals, locals, fromlist, level)
            # if a is already demand-loaded, add b to its submodule list
            if base in locals:
                if isinstance(locals[base], _demandmod):
                    locals[base]._extend(rest)
                return locals[base]
        return _demandmod(name, globals, locals, level)
    else:
        # There is a fromlist.
        # from a import b,c,d
        # from . import b,c,d
        # from .a import b,c,d

        # level == -1: relative and absolute attempted (Python 2 only).
        # level >= 0: absolute only (Python 2 w/ absolute_import and Python 3).
        # The modern Mercurial convention is to use absolute_import everywhere,
        # so modern Mercurial code will have level >= 0.

        # The name of the module the import statement is located in.
        globalname = globals.get('__name__')

        def processfromitem(mod, attr):
            """Process an imported symbol in the import statement.

            If the symbol doesn't exist in the parent module, and if the
            parent module is a package, it must be a module. We set missing
            modules up as _demandmod instances.
            """
            symbol = getattr(mod, attr, nothing)
            nonpkg = getattr(mod, '__path__', nothing) is nothing
            if symbol is nothing:
                if nonpkg:
                    # do not try relative import, which would raise ValueError,
                    # and leave unknown attribute as the default __import__()
                    # would do. the missing attribute will be detected later
                    # while processing the import statement.
                    return
                mn = '%s.%s' % (mod.__name__, attr)
                if mn in ignores:
                    importfunc = _origimport
                else:
                    importfunc = _demandmod
                symbol = importfunc(attr, mod.__dict__, locals, level=1)
                setattr(mod, attr, symbol)

            # Record the importing module references this symbol so we can
            # replace the symbol with the actual module instance at load
            # time.
            if globalname and isinstance(symbol, _demandmod):
                symbol._addref(globalname)

        def chainmodules(rootmod, modname):
            # recurse down the module chain, and return the leaf module
            mod = rootmod
            for comp in modname.split('.')[1:]:
                obj = getattr(mod, comp, nothing)
                if obj is nothing:
                    obj = _demandmod(comp, mod.__dict__, mod.__dict__, level=1)
                    setattr(mod, comp, obj)
                elif mod.__name__ + '.' + comp in sys.modules:
                    # prefer loaded module over attribute (issue5617)
                    obj = sys.modules[mod.__name__ + '.' + comp]
                mod = obj
            return mod

        if level >= 0:
            if name:
                # "from a import b" or "from .a import b" style
                rootmod = _hgextimport(_origimport, name, globals, locals,
                                       level=level)
                mod = chainmodules(rootmod, name)
            elif _pypy:
                # PyPy's __import__ throws an exception if invoked
                # with an empty name and no fromlist.  Recreate the
                # desired behaviour by hand.
                mn = globalname
                mod = sys.modules[mn]
                if getattr(mod, '__path__', nothing) is nothing:
                    mn = mn.rsplit('.', 1)[0]
                    mod = sys.modules[mn]
                if level > 1:
                    mn = mn.rsplit('.', level - 1)[0]
                    mod = sys.modules[mn]
            else:
                mod = _hgextimport(_origimport, name, globals, locals,
                                   level=level)

            for x in fromlist:
                processfromitem(mod, x)

            return mod

        # But, we still need to support lazy loading of standard library and 3rd
        # party modules. So handle level == -1.
        mod = _hgextimport(_origimport, name, globals, locals)
        mod = chainmodules(mod, name)

        for x in fromlist:
            processfromitem(mod, x)

        return mod

ignores = set()

def init(ignoreset):
    global ignores
    ignores = ignoreset

def isenabled():
    return builtins.__import__ == _demandimport

def enable():
    "enable global demand-loading of modules"
    builtins.__import__ = _demandimport

def disable():
    "disable global demand-loading of modules"
    builtins.__import__ = _origimport

@contextmanager
def deactivated():
    "context manager for disabling demandimport in 'with' blocks"
    demandenabled = isenabled()
    if demandenabled:
        disable()

    try:
        yield
    finally:
        if demandenabled:
            enable()