view tests/test-demandimport.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

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)

# The demand importer doesn't work on Python 3.5.
if sys.version_info[0:2] == (3, 5):
    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 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 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')