view tests/test-filecache.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
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 2372284d9457
children e01ea8325859
line wrap: on
line source

from __future__ import absolute_import, print_function
import os
import stat
import subprocess
import sys

if subprocess.call(
    ['python', '%s/hghave' % os.environ['TESTDIR'], 'cacheable']
):
    sys.exit(80)

print_ = print


def print(*args, **kwargs):
    """print() wrapper that flushes stdout buffers to avoid py3 buffer issues

    We could also just write directly to sys.stdout.buffer the way the
    ui object will, but this was easier for porting the test.
    """
    print_(*args, **kwargs)
    sys.stdout.flush()


from mercurial import (
    extensions,
    hg,
    localrepo,
    pycompat,
    ui as uimod,
    util,
    vfs as vfsmod,
)

if pycompat.ispy3:
    xrange = range


class fakerepo(object):
    def __init__(self):
        self._filecache = {}

    class fakevfs(object):
        def join(self, p):
            return p

    vfs = fakevfs()

    def unfiltered(self):
        return self

    def sjoin(self, p):
        return p

    @localrepo.repofilecache('x', 'y')
    def cached(self):
        print('creating')
        return 'string from function'

    def invalidate(self):
        for k in self._filecache:
            try:
                delattr(self, pycompat.sysstr(k))
            except AttributeError:
                pass


def basic(repo):
    print("* neither file exists")
    # calls function
    repo.cached

    repo.invalidate()
    print("* neither file still exists")
    # uses cache
    repo.cached

    # create empty file
    f = open('x', 'w')
    f.close()
    repo.invalidate()
    print("* empty file x created")
    # should recreate the object
    repo.cached

    f = open('x', 'w')
    f.write('a')
    f.close()
    repo.invalidate()
    print("* file x changed size")
    # should recreate the object
    repo.cached

    repo.invalidate()
    print("* nothing changed with either file")
    # stats file again, reuses object
    repo.cached

    # atomic replace file, size doesn't change
    # hopefully st_mtime doesn't change as well so this doesn't use the cache
    # because of inode change
    f = vfsmod.vfs(b'.')(b'x', b'w', atomictemp=True)
    f.write(b'b')
    f.close()

    repo.invalidate()
    print("* file x changed inode")
    repo.cached

    # create empty file y
    f = open('y', 'w')
    f.close()
    repo.invalidate()
    print("* empty file y created")
    # should recreate the object
    repo.cached

    f = open('y', 'w')
    f.write('A')
    f.close()
    repo.invalidate()
    print("* file y changed size")
    # should recreate the object
    repo.cached

    f = vfsmod.vfs(b'.')(b'y', b'w', atomictemp=True)
    f.write(b'B')
    f.close()

    repo.invalidate()
    print("* file y changed inode")
    repo.cached

    f = vfsmod.vfs(b'.')(b'x', b'w', atomictemp=True)
    f.write(b'c')
    f.close()
    f = vfsmod.vfs(b'.')(b'y', b'w', atomictemp=True)
    f.write(b'C')
    f.close()

    repo.invalidate()
    print("* both files changed inode")
    repo.cached


def fakeuncacheable():
    def wrapcacheable(orig, *args, **kwargs):
        return False

    def wrapinit(orig, *args, **kwargs):
        pass

    originit = extensions.wrapfunction(util.cachestat, '__init__', wrapinit)
    origcacheable = extensions.wrapfunction(
        util.cachestat, 'cacheable', wrapcacheable
    )

    for fn in ['x', 'y']:
        try:
            os.remove(fn)
        except OSError:
            pass

    basic(fakerepo())

    util.cachestat.cacheable = origcacheable
    util.cachestat.__init__ = originit


def test_filecache_synced():
    # test old behavior that caused filecached properties to go out of sync
    os.system('hg init && echo a >> a && hg ci -qAm.')
    repo = hg.repository(uimod.ui.load())
    # first rollback clears the filecache, but changelog to stays in __dict__
    repo.rollback()
    repo.commit(b'.')
    # second rollback comes along and touches the changelog externally
    # (file is moved)
    repo.rollback()
    # but since changelog isn't under the filecache control anymore, we don't
    # see that it changed, and return the old changelog without reconstructing
    # it
    repo.commit(b'.')


def setbeforeget(repo):
    os.remove('x')
    os.remove('y')
    repo.__class__.cached.set(repo, 'string set externally')
    repo.invalidate()
    print("* neither file exists")
    print(repo.cached)
    repo.invalidate()
    f = open('x', 'w')
    f.write('a')
    f.close()
    print("* file x created")
    print(repo.cached)

    repo.__class__.cached.set(repo, 'string 2 set externally')
    repo.invalidate()
    print("* string set externally again")
    print(repo.cached)

    repo.invalidate()
    f = open('y', 'w')
    f.write('b')
    f.close()
    print("* file y created")
    print(repo.cached)


def antiambiguity():
    filename = 'ambigcheck'

    # try some times, because reproduction of ambiguity depends on
    # "filesystem time"
    for i in xrange(5):
        fp = open(filename, 'w')
        fp.write('FOO')
        fp.close()

        oldstat = os.stat(filename)
        if oldstat[stat.ST_CTIME] != oldstat[stat.ST_MTIME]:
            # subsequent changing never causes ambiguity
            continue

        repetition = 3

        # repeat changing via checkambigatclosing, to examine whether
        # st_mtime is advanced multiple times as expected
        for i in xrange(repetition):
            # explicit closing
            fp = vfsmod.checkambigatclosing(open(filename, 'a'))
            fp.write('FOO')
            fp.close()

            # implicit closing by "with" statement
            with vfsmod.checkambigatclosing(open(filename, 'a')) as fp:
                fp.write('BAR')

        newstat = os.stat(filename)
        if oldstat[stat.ST_CTIME] != newstat[stat.ST_CTIME]:
            # timestamp ambiguity was naturally avoided while repetition
            continue

        # st_mtime should be advanced "repetition * 2" times, because
        # all changes occurred at same time (in sec)
        expected = (oldstat[stat.ST_MTIME] + repetition * 2) & 0x7FFFFFFF
        if newstat[stat.ST_MTIME] != expected:
            print(
                "'newstat[stat.ST_MTIME] %s is not %s (as %s + %s * 2)"
                % (
                    newstat[stat.ST_MTIME],
                    expected,
                    oldstat[stat.ST_MTIME],
                    repetition,
                )
            )

        # no more examination is needed regardless of result
        break
    else:
        # This platform seems too slow to examine anti-ambiguity
        # of file timestamp (or test happened to be executed at
        # bad timing). Exit silently in this case, because running
        # on other faster platforms can detect problems
        pass


print('basic:')
print()
basic(fakerepo())
print()
print('fakeuncacheable:')
print()
fakeuncacheable()
test_filecache_synced()
print()
print('setbeforeget:')
print()
setbeforeget(fakerepo())
print()
print('antiambiguity:')
print()
antiambiguity()