view mercurial/demandimport.py @ 24735:07200e3332a1

tags: extract .hgtags filenodes cache to a standalone file

Resolution of .hgtags filenodes values has historically been a
performance pain point for large repositories, where reading individual
manifests can take over 100ms. Multiplied by hundreds or even thousands
of heads and resolving .hgtags filenodes becomes a performance issue.

This patch establishes a standalone cache file holding the .hgtags
filenodes for each changeset. After this patch, the .hgtags filenode
for any particular changeset should only have to be computed once
during the lifetime of the repository.

The introduced hgtagsfnodes1 cache file is modeled after the rev branch
cache: the cache is effectively an array of entries consisting of a
changeset fragment and the filenode for a revision. The file grows in
proportion to the length of the repository (24 bytes per changeset) and
is truncated when the repository is stripped. The file is not written
unless tag info is requested and tags have changed since last time.

This patch partially addresses issue4550. Future patches will split the
"tags" cache file into per-filter files and will refactor the cache
format to not capture the .hgtags fnodes, as these are now stored in
the hgtagsfnodes1 cache. This patch is capable of standing alone. We
should not have to wait on the tags cache filter split and format
refactor for this patch to land.

# demandimport.py - global demand-loading of modules for Mercurial
#
# Copyright 2006, 2007 Matt Mackall <[e-mail]>
#
# 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)
'''

import __builtin__, os, sys
_origimport = __import__

nothing = object()

try:
    # Python 3 doesn't have relative imports nor level -1.
    level = -1
    if sys.version_info[0] >= 3:
        level = 0
    _origimport(__builtin__.__name__, {}, {}, None, level)
except TypeError: # no level argument
    def _import(name, globals, locals, fromlist, level):
        "call _origimport with no level argument"
        return _origimport(name, globals, locals, fromlist)
else:
    _import = _origimport

def _hgextimport(importfunc, name, globals, *args):
    try:
        return importfunc(name, globals, *args)
    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)

class _demandmod(object):
    """module demand-loader and proxy"""
    def __init__(self, name, globals, locals, level=level):
        if '.' in name:
            head, rest = name.split('.', 1)
            after = [rest]
        else:
            head = name
            after = []
        object.__setattr__(self, "_data",
                           (head, globals, locals, after, level))
        object.__setattr__(self, "_module", None)
    def _extend(self, name):
        """add to the list of submodules to load"""
        self._data[3].append(name)
    def _load(self):
        if not self._module:
            head, globals, locals, after, level = self._data
            mod = _hgextimport(_import, head, globals, locals, None, level)
            # 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__))
                elif t:
                    subload(getattr(mod, h), t)

            for x in after:
                subload(mod, x)

            # are we in the locals dictionary still?
            if locals and locals.get(head) == self:
                locals[head] = mod
            object.__setattr__(self, "_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 __getattribute__(self, attr):
        if attr in ('_data', '_extend', '_load', '_module'):
            return object.__getattribute__(self, attr)
        self._load()
        return getattr(self._module, attr)
    def __setattr__(self, attr, val):
        self._load()
        setattr(self._module, attr, val)

def _demandimport(name, globals=None, locals=None, fromlist=None, level=level):
    if not locals or name in ignore or fromlist == ('*',):
        # these cases we can't really delay
        return _hgextimport(_import, 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 _import(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:
        if level != -1:
            # from . import b,c,d or from .a import b,c,d
            return _origimport(name, globals, locals, fromlist, level)
        # from a import b,c,d
        mod = _hgextimport(_origimport, name, globals, locals)
        # recurse down the module chain
        for comp in name.split('.')[1:]:
            if getattr(mod, comp, nothing) is nothing:
                setattr(mod, comp, _demandmod(comp, mod.__dict__, mod.__dict__))
            mod = getattr(mod, comp)
        for x in fromlist:
            # set requested submodules for demand load
            if getattr(mod, x, nothing) is nothing:
                setattr(mod, x, _demandmod(x, mod.__dict__, locals))
        return mod

ignore = [
    '_hashlib',
    '_xmlplus',
    'fcntl',
    'win32com.gen_py',
    '_winreg', # 2.7 mimetypes needs immediate ImportError
    'pythoncom',
    # imported by tarfile, not available under Windows
    'pwd',
    'grp',
    # imported by profile, itself imported by hotshot.stats,
    # not available under Windows
    'resource',
    # this trips up many extension authors
    'gtk',
    # setuptools' pkg_resources.py expects "from __main__ import x" to
    # raise ImportError if x not defined
    '__main__',
    '_ssl', # conditional imports in the stdlib, issue1964
    'rfc822',
    'mimetools',
    # setuptools 8 expects this module to explode early when not on windows
    'distutils.msvc9compiler'
    ]

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

def enable():
    "enable global demand-loading of modules"
    if os.environ.get('HGDEMANDIMPORT') != 'disable':
        __builtin__.__import__ = _demandimport

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