view tests/test-demandimport.py @ 49777:e1953a34c110

bundle: emit full snapshot as is, without doing a redelta

With the new `forced` delta-reused policy, it become important to be able to
send full snapshot where full snapshot are needed. Otherwise, the fallback delta
will simply be used on the client side… creating monstrous delta chain, since
revision that are meant as a reset of delta-chain chain becoming too complex are
simply adding a new full delta-tree on the leaf of another one.

In the `non-forced` cases, client process full snapshot from the bundle
differently from deltas, so client will still try to convert the full snapshot
into a delta if possible. So this will no lead to pathological storage
explosion.

I have considered making this configurable, but the impact seems limited enough
that it does not seems to be worth it. Especially with the current
sparse-revlog format that use "delta-tree" with multiple level snapshots, full
snapshot are much less frequent and not that different from other intermediate
snapshot that we are already sending over the wire anyway.

CPU wise, this will help the bundling side a little as it will not need to
reconstruct revisions and compute deltas. The unbundling side might save a tiny
amount of CPU as it won't need to reconstruct the delta-base to reconstruct the
revision full text. This only slightly visible in some of the benchmarks. And
have no real impact on most of them.

### data-env-vars.name      = pypy-2018-08-01-zstd-sparse-revlog
  # benchmark.name          = perf-bundle
  # benchmark.variants.revs = last-40000
before:          11.467186 seconds
just-emit-full:  11.190576 seconds   (-2.41%)
with-pull-force: 11.041091 seconds   (-3.72%)
  # benchmark.name          = perf-unbundle
  # benchmark.variants.revs = last-40000
before:     16.744862
just-emit-full:: 16.561036 seconds   (-1.10%)
with-pull-force: 16.389344 seconds   (-2.12%)
  # benchmark.name          = pull
  # benchmark.variants.revs = last-40000
before:     26.870569
just-emit-full:  26.391188 seconds   (-1.78%)
with-pull-force: 25.633184 seconds   (-4.60%)


Space wise (so network-wise) the impact is fairly small. When taking compression into
account.

Below are tests the size of `hg bundle --all` for a handful of benchmark repositories
(with bzip, zstd compression and without it)

This show a small increase in the bundle size, but nothing really significant
except maybe for mozilla-try (+12%) that nobody really pulls large chunk of anyway.
Mozilla-try is also the repository that benefit the most for not having to
recompute deltas client size.

### mercurial:
bzip-before:     26 406 342 bytes
bzip-after:      26 691 543 bytes  +1.08%

zstd-before:     27 918 645 bytes
zstd-after:      28 075 896 bytes  +0.56%

none-before:     98 675 601 bytes
none-after:     100 411 237 bytes  +1.76%


### pypy
bzip-before:    201 295 752 bytes
bzip-after:     209 780 282 bytes  +4.21%

zstd-before:    202 974 795 bytes
zstd-after:     205 165 780 bytes  +1.08%

none-before:    871 070 261 bytes
none-after:     993 595 057 bytes +14.07%


### netbeans
bzip-before:    601 314 330 bytes
bzip-after:     614 246 241 bytes  +2.15%

zstd-before:    604 745 136 bytes
zstd-after:     615 497 705 bytes  +1.78%

none-before:  3 338 238 571 bytes
none-after:   3 439 422 535 bytes  +3.03%


### mozilla-central
bzip-before:  1 493 006 921 bytes
bzip-after:   1 549 650 570 bytes  +3.79%

zstd-before:  1 481 910 102 bytes
zstd-after:   1 513 052 415 bytes  +2.10%

none-before:  6 535 929 910 bytes
none-after:   7 010 191 342 bytes  +7.26%


### mozilla-try
bzip-before:  6 583 425 999 bytes
bzip-after:   7 423 536 928 bytes +12.76%

zstd-before:  6 021 009 212 bytes
zstd-after:   6 674 922 420 bytes +10.86%

none-before: 22 954 739 558 bytes
none-after:  26 013 854 771 bytes +13.32%

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(
    [os.environ['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 'ftplib' not in sys.modules
zipfileimp = __import__('ftplib', globals(), locals(), ['unknownattr'])
assert f(zipfileimp) == "<module 'ftplib' from '?'>", f(zipfileimp)
assert not util.safehasattr(zipfileimp, 'unknownattr')


# test deactivation for issue6725
del sys.modules['telnetlib']
with demandimport.deactivated():
    import telnetlib
assert telnetlib.__loader__ == telnetlib.__spec__.loader
assert telnetlib.__loader__.get_resource_reader