This is an archive of the discontinued Mercurial Phabricator instance.

Differential D4347

demandimport: instrument python 2 code with trace events
ClosedPublic

Authored by durin42 on Aug 21 2018, 5:39 PM.

Details

Reviewers
None
Group Reviewers
hg-reviewers
Commits
rHG574e1d3bc667: demandimport: instrument python 2 code with trace events
Summary

This causes the evaluation of an import in Python 3 to emit some trace
data. There's some interesting wrinkles in here, like the fact that
before we even hit dispatch we've demand-imported sys several times,
despite the fact that sys was already fully loaded as one of the
first few statements in the hg script. I don't think that's actually
costing us a ton of performance, but it's probably something we should
investigate fixing some day.

Diff Detail

Repository
rHG Mercurial
Lint
Automatic diff as part of commit; lint not applicable.
Unit
Automatic diff as part of commit; unit tests not applicable.

Event Timeline

durin42 created this revision.Aug 21 2018, 5:39 PM
Closed by commit rHG574e1d3bc667: demandimport: instrument python 2 code with trace events (authored by durin42). · Explain WhyAug 24 2018, 1:14 PM
This revision was automatically updated to reflect the committed changes.

Revision Contents
Changeset List

PathPackages
Mhgdemandimport/demandimportpy2.py (87 lines)

Diff 10555

hgdemandimport/demandimportpy2.py

''' '''
from __future__ import absolute_import from __future__ import absolute_import
import __builtin__ as builtins import __builtin__ as builtins
import contextlib import contextlib
import sys import sys
from . import tracing
contextmanager = contextlib.contextmanager contextmanager = contextlib.contextmanager
_origimport = __import__ _origimport = __import__
nothing = object() nothing = object()
def _hgextimport(importfunc, name, globals, *args, **kwargs): def _hgextimport(importfunc, name, globals, *args, **kwargs):
try: try:
module is identical to the "head" name of this module. We don't 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 actually know if "as X" syntax is being used to change the symbol name
because this information isn't exposed to __import__. because this information isn't exposed to __import__.
""" """
self._data[5].add(name) self._data[5].add(name)
def _load(self): def _load(self):
if not self._module: if not self._module:
with tracing.log('demandimport %s', self._data[0]):
head, globals, locals, after, level, modrefs = self._data head, globals, locals, after, level, modrefs = self._data
mod = _hgextimport(_origimport, head, globals, locals, None, level) mod = _hgextimport(
_origimport, head, globals, locals, None, level)
if mod is self: if mod is self:
# In this case, _hgextimport() above should imply # In this case, _hgextimport() above should imply
# _demandimport(). Otherwise, _hgextimport() never # _demandimport(). Otherwise, _hgextimport() never
# returns _demandmod. This isn't intentional behavior, # returns _demandmod. This isn't intentional behavior,
# in fact. (see also issue5304 for detail) # in fact. (see also issue5304 for detail)
# #
# If self._module is already bound at this point, self # If self._module is already bound at this point, self
# should be already _load()-ed while _hgextimport(). # should be already _load()-ed while _hgextimport().
# Otherwise, there is no way to import actual module # Otherwise, there is no way to import actual module
# as expected, because (re-)invoking _hgextimport() # as expected, because (re-)invoking _hgextimport()
# should cause same result. # should cause same result.
# This is reason why _load() returns without any more # This is reason why _load() returns without any more
# setup but assumes self to be already bound. # setup but assumes self to be already bound.
mod = self._module mod = self._module
assert mod and mod is not self, "%s, %s" % (self, mod) assert mod and mod is not self, "%s, %s" % (self, mod)
return return
# load submodules # load submodules
def subload(mod, p): def subload(mod, p):
h, t = p, None h, t = p, None
if '.' in p: if '.' in p:
h, t = p.split('.', 1) h, t = p.split('.', 1)
if getattr(mod, h, nothing) is nothing: if getattr(mod, h, nothing) is nothing:
setattr(mod, h, _demandmod(p, mod.__dict__, mod.__dict__, setattr(mod, h, _demandmod(
level=1)) p, mod.__dict__, mod.__dict__, level=1))
elif t: elif t:
subload(getattr(mod, h), t) subload(getattr(mod, h), t)
for x in after: for x in after:
subload(mod, x) subload(mod, x)
# Replace references to this proxy instance with the actual module. # Replace references to this proxy instance with the
# actual module.
if locals: if locals:
if locals.get(head) is self: if locals.get(head) is self:
locals[head] = mod locals[head] = mod
elif locals.get(head + r'mod') is self: elif locals.get(head + r'mod') is self:
locals[head + r'mod'] = mod locals[head + r'mod'] = mod
for modname in modrefs: for modname in modrefs:
modref = sys.modules.get(modname, None) modref = sys.modules.get(modname, None)
if modref and getattr(modref, head, None) is self: if modref and getattr(modref, head, None) is self:
setattr(modref, head, mod) setattr(modref, head, mod)
object.__setattr__(self, r"_module", mod) object.__setattr__(self, r"_module", mod)
def __repr__(self): def __repr__(self):
if self._module: if self._module:
return "<proxied module '%s'>" % self._data[0] return "<proxied module '%s'>" % self._data[0]
return "<unloaded module '%s'>" % self._data[0] return "<unloaded module '%s'>" % self._data[0]
def __call__(self, *args, **kwargs): def __call__(self, *args, **kwargs):
raise TypeError("%s object is not callable" % repr(self)) raise TypeError("%s object is not callable" % repr(self))