view tests/test-demandimport.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

from __future__ import absolute_import, print_function

from mercurial import demandimport
demandimport.enable()

import os
import subprocess
import sys
import types

# Don't import pycompat because it has too many side-effects.
ispy3 = sys.version_info[0] >= 3

# Only run if demandimport is allowed
if subprocess.call(['python', '%s/hghave' % os.environ['TESTDIR'],
                    'demandimport']):
    sys.exit(80)

# We rely on assert, which gets optimized out.
if sys.flags.optimize:
    sys.exit(80)

if ispy3:
    from importlib.util import _LazyModule

    try:
        from importlib.util import _Module as moduletype
    except ImportError:
        moduletype = types.ModuleType
else:
    moduletype = types.ModuleType

if os.name != 'nt':
    try:
        import distutils.msvc9compiler
        print('distutils.msvc9compiler needs to be an immediate '
              'importerror on non-windows platforms')
        distutils.msvc9compiler
    except ImportError:
        pass

import re

rsub = re.sub
def f(obj):
    l = repr(obj)
    l = rsub("0x[0-9a-fA-F]+", "0x?", l)
    l = rsub("from '.*'", "from '?'", l)
    l = rsub("'<[a-z]*>'", "'<whatever>'", l)
    return l

demandimport.disable()
os.environ['HGDEMANDIMPORT'] = 'disable'
# this enable call should not actually enable demandimport!
demandimport.enable()
from mercurial import node

# We use assert instead of a unittest test case because having imports inside
# functions changes behavior of the demand importer.
if ispy3:
    assert not isinstance(node, _LazyModule)
else:
    assert f(node) == "<module 'mercurial.node' from '?'>", f(node)

# now enable it for real
del os.environ['HGDEMANDIMPORT']
demandimport.enable()

# Test access to special attributes through demandmod proxy
assert 'mercurial.error' not in sys.modules
from mercurial import error as errorproxy

if ispy3:
    # unsure why this isn't lazy.
    assert not isinstance(f, _LazyModule)
    assert f(errorproxy) == "<module 'mercurial.error' from '?'>", f(errorproxy)
else:
    assert f(errorproxy) == "<unloaded module 'error'>", f(errorproxy)

doc = ' '.join(errorproxy.__doc__.split()[:3])
assert doc == 'Mercurial exceptions. This', doc
assert errorproxy.__name__ == 'mercurial.error', errorproxy.__name__

# __name__ must be accessible via __dict__ so the relative imports can be
# resolved
name = errorproxy.__dict__['__name__']
assert name == 'mercurial.error', name

if ispy3:
    assert not isinstance(errorproxy, _LazyModule)
    assert f(errorproxy) == "<module 'mercurial.error' from '?'>", f(errorproxy)
else:
    assert f(errorproxy) == "<proxied module 'error'>", f(errorproxy)

import os

if ispy3:
    assert not isinstance(os, _LazyModule)
    assert f(os) == "<module 'os' from '?'>", f(os)
else:
    assert f(os) == "<unloaded module 'os'>", f(os)

assert f(os.system) == '<built-in function system>', f(os.system)
assert f(os) == "<module 'os' from '?'>", f(os)

assert 'mercurial.utils.procutil' not in sys.modules
from mercurial.utils import procutil

if ispy3:
    assert isinstance(procutil, _LazyModule)
    assert f(procutil) == "<module 'mercurial.utils.procutil' from '?'>", f(
        procutil
    )
else:
    assert f(procutil) == "<unloaded module 'procutil'>", f(procutil)

assert f(procutil.system) == '<function system at 0x?>', f(procutil.system)
assert procutil.__class__ == moduletype, procutil.__class__
assert f(procutil) == "<module 'mercurial.utils.procutil' from '?'>", f(
    procutil
)
assert f(procutil.system) == '<function system at 0x?>', f(procutil.system)

assert 'mercurial.hgweb' not in sys.modules
from mercurial import hgweb

if ispy3:
    assert not isinstance(hgweb, _LazyModule)
    assert f(hgweb) == "<module 'mercurial.hgweb' from '?'>", f(hgweb)
    assert isinstance(hgweb.hgweb_mod, _LazyModule)
    assert (
        f(hgweb.hgweb_mod) == "<module 'mercurial.hgweb.hgweb_mod' from '?'>"
    ), f(hgweb.hgweb_mod)
else:
    assert f(hgweb) == "<unloaded module 'hgweb'>", f(hgweb)
    assert f(hgweb.hgweb_mod) == "<unloaded module 'hgweb_mod'>", f(
        hgweb.hgweb_mod
    )

assert f(hgweb) == "<module 'mercurial.hgweb' from '?'>", f(hgweb)

import re as fred

if ispy3:
    assert not isinstance(fred, _LazyModule)
    assert f(fred) == "<module 're' from '?'>"
else:
    assert f(fred) == "<unloaded module 're'>", f(fred)

import re as remod

if ispy3:
    assert not isinstance(remod, _LazyModule)
    assert f(remod) == "<module 're' from '?'>"
else:
    assert f(remod) == "<unloaded module 're'>", f(remod)

import sys as re

if ispy3:
    assert not isinstance(re, _LazyModule)
    assert f(re) == "<module 'sys' (built-in)>"
else:
    assert f(re) == "<unloaded module 'sys'>", f(re)

if ispy3:
    assert not isinstance(fred, _LazyModule)
    assert f(fred) == "<module 're' from '?'>", f(fred)
else:
    assert f(fred) == "<unloaded module 're'>", f(fred)

assert f(fred.sub) == '<function sub at 0x?>', f(fred.sub)

if ispy3:
    assert not isinstance(fred, _LazyModule)
    assert f(fred) == "<module 're' from '?'>", f(fred)
else:
    assert f(fred) == "<proxied module 're'>", f(fred)

remod.escape  # use remod
assert f(remod) == "<module 're' from '?'>", f(remod)

if ispy3:
    assert not isinstance(re, _LazyModule)
    assert f(re) == "<module 'sys' (built-in)>"
    assert f(type(re.stderr)) == "<class '_io.TextIOWrapper'>", f(
        type(re.stderr)
    )
    assert f(re) == "<module 'sys' (built-in)>"
else:
    assert f(re) == "<unloaded module 'sys'>", f(re)
    assert f(re.stderr) == "<open file '<whatever>', mode 'w' at 0x?>", f(
        re.stderr
    )
    assert f(re) == "<proxied module 'sys'>", f(re)

assert 'telnetlib' not in sys.modules
import telnetlib

if ispy3:
    assert not isinstance(telnetlib, _LazyModule)
    assert f(telnetlib) == "<module 'telnetlib' from '?'>"
else:
    assert f(telnetlib) == "<unloaded module 'telnetlib'>", f(telnetlib)

try:
    from telnetlib import unknownattr

    assert False, (
        'no demandmod should be created for attribute of non-package '
        'module:\ntelnetlib.unknownattr = %s' % f(unknownattr)
    )
except ImportError as inst:
    assert rsub(r"'", '', str(inst)).startswith(
        'cannot import name unknownattr'
    )

from mercurial import util

# Unlike the import statement, __import__() function should not raise
# ImportError even if fromlist has an unknown item
# (see Python/import.c:import_module_level() and ensure_fromlist())
assert 'zipfile' not in sys.modules
zipfileimp = __import__('zipfile', globals(), locals(), ['unknownattr'])
assert f(zipfileimp) == "<module 'zipfile' from '?'>", f(zipfileimp)
assert not util.safehasattr(zipfileimp, 'unknownattr')