cubicweb/_gcdebug.py
author Denis Laxalde <denis.laxalde@logilab.fr>
Tue, 04 Apr 2017 16:28:50 +0200
branch3.25
changeset 12142 db2fc87348ab
parent 11057 0b59724cb3f2
child 12232 24393ce335f5
permissions -rw-r--r--
[server] Make "sources_by_uri" and "sources_by_eid" properties of repository I.e. do not populate these dict as repo initialization (bootstrap step) but always use information from database. This is needed because when multiple instances of the same application run, if one instance adds a CWSource the other ones will not see it. In particular, when using a scheduler instance, new CWSource will be added by the web instance and not seen by the scheduler which is supposed to update them. We thus define properties for sources_by_eid and sources_by_uri instead attributes on repository instance. CWSource entities are thus retrieved from database every time these properties are accessed. We factor out initialization of the "source" instance (subclass of cubicweb.server.source.AbstractSource) in a _sources() method. Note that this method takes care of calling "init" method on the source as well as "set_schema" (previously done in repo.set_schema(), which now only touches system_source). Accordingly the "init_sources_from_database" method is dropped along with "add_source"/"remove_source" methods. In syncsources hook, we thus drop: * SourceAddedOp operation which called repo.add_source() so that the SourceAddedHook only cares about checking source configuration now; * SourceRemovedOp and SourceRenamedOp operations for the same reason; * SourceConfigUpdatedOp as updating the live config of source is meaningless once we rely on them being retrieved from the database; * SourceHostConfigUpdatedHook hook which is now useless without call to SourceConfigUpdatedOp; In 3.10 migration script, remove usage of sources_by_uri repo attribute which, unless I'm missing something, appears useless (at least now). In tests: * unittest_datafeed: remove test_update_url method since we dropped respective hook; * unittest_ldapsource: LDAPFeedUserDeletionTC.test_a_filter_inactivate() currently fails because it still relies on live config being updated, this will be fixed in the next changeset once all "live source" logic will be removed.

# copyright 2003-2010 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
# contact http://www.logilab.fr/ -- mailto:contact@logilab.fr
#
# This file is part of CubicWeb.
#
# CubicWeb is free software: you can redistribute it and/or modify it under the
# terms of the GNU Lesser General Public License as published by the Free
# Software Foundation, either version 2.1 of the License, or (at your option)
# any later version.
#
# CubicWeb is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public License for more
# details.
#
# You should have received a copy of the GNU Lesser General Public License along
# with CubicWeb.  If not, see <http://www.gnu.org/licenses/>.
from __future__ import print_function

import gc, types, weakref

from cubicweb.schema import CubicWebRelationSchema, CubicWebEntitySchema
try:
    from cubicweb.web.request import _NeedAuthAccessMock
except ImportError:
    _NeedAuthAccessMock = None

listiterator = type(iter([]))

IGNORE_CLASSES = (
    type, tuple, dict, list, set, frozenset, type(len),
    weakref.ref, weakref.WeakKeyDictionary,
    listiterator,
    property, classmethod,
    types.ModuleType, types.FunctionType, types.MethodType,
    types.MemberDescriptorType, types.GetSetDescriptorType,
    )
if _NeedAuthAccessMock is not None:
    IGNORE_CLASSES = IGNORE_CLASSES + (_NeedAuthAccessMock,)

def _get_counted_class(obj, classes):
    for cls in classes:
        if isinstance(obj, cls):
            return cls
    raise AssertionError()

def gc_info(countclasses,
            ignoreclasses=IGNORE_CLASSES,
            viewreferrersclasses=(), showobjs=False, maxlevel=1):
    gc.collect()
    gc.collect()
    counters = {}
    ocounters = {}
    for obj in gc.get_objects():
        if isinstance(obj, countclasses):
            cls = _get_counted_class(obj, countclasses)
            try:
                counters[cls.__name__] += 1
            except KeyError:
                counters[cls.__name__] = 1
        elif not isinstance(obj, ignoreclasses):
            try:
                key = '%s.%s' % (obj.__class__.__module__,
                                 obj.__class__.__name__)
            except AttributeError:
                key = str(obj)
            try:
                ocounters[key] += 1
            except KeyError:
                ocounters[key] = 1
        if isinstance(obj, viewreferrersclasses):
            print('   ', obj, referrers(obj, showobjs, maxlevel))
    garbage = [repr(obj) for obj in gc.garbage]
    return counters, ocounters, garbage


def referrers(obj, showobj=False, maxlevel=1):
    objreferrers = _referrers(obj, maxlevel)
    try:
        return sorted(set((type(x), showobj and x or getattr(x, '__name__', '%#x' % id(x)))
                          for x in objreferrers))
    except TypeError:
        s = set()
        unhashable = []
        for x in objreferrers:
            try:
                s.add(x)
            except TypeError:
                unhashable.append(x)
        return sorted(s) + unhashable

def _referrers(obj, maxlevel, _seen=None, _level=0):
    interesting = []
    if _seen is None:
        _seen = set()
    for x in gc.get_referrers(obj):
        if id(x) in _seen:
            continue
        _seen.add(id(x))
        if isinstance(x, types.FrameType):
            continue
        if isinstance(x, (CubicWebRelationSchema, CubicWebEntitySchema)):
            continue
        if isinstance(x, (list, tuple, set, dict, listiterator)):
            if _level >= maxlevel:
                pass
                #interesting.append(x)
            else:
                interesting += _referrers(x, maxlevel, _seen, _level+1)
        else:
            interesting.append(x)
    return interesting