tests/test-filecache.py

streamclone: use backgroundfilecloser (issue4889)

Closing files that have been appended to is slow on Windows/NTFS.
CloseHandle() calls on this platform often take 1-10ms - and that's
on my i7-6700K Skylake processor with a modern and fast SSD. Contrast
with other I/O operations, such as writing data, which take <100us.

This means that creating/appending thousands of files can add
significant overhead. For example, cloning mozilla-central creates
~232,000 revlog files. Assuming 1ms per CloseHandle(), that yields
232s (3:52) of wall time waiting for file closes!

The impact of this overhead can be measured most directly when applying
stream clone bundles. Applying these files is effectively uncompressing
a tar archive (read: it's very fast).

Using a RAM disk (read: no I/O wait), the difference in wall time for a
`hg debugapplystreamclonebundle` for a ~1731 MB mozilla-central bundle
between Windows and Linux from the same machine is drastic:

Linux:    ~12.8s (128MB/s)
Windows: ~352.0s (4.7MB/s)

Windows is ~27.5x slower. Yikes!

After this patch:

Linux:    ~12.8s (128MB/s)
Windows: ~102.1s (16.1MB/s)

Windows is now ~3.4x faster. Unfortunately, it is still ~8x slower than
Linux. Profiling reveals a few hot code paths that could likely be
improved. But those are for other patches.

This patch introduces test-clone-uncompressed.t because existing tests
of `clone --uncompressed` are scattered about and adding a variation for
background thread closing to e.g. test-http.t doesn't feel correct.

import sys, os, subprocess

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

from mercurial import util, scmutil, extensions, hg, ui

filecache = scmutil.filecache

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

    def join(self, p):
        return p

    def sjoin(self, p):
        return p

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

    def invalidate(self):
        for k in self._filecache:
            try:
                delattr(self, 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 = scmutil.opener('.')('x', 'w', atomictemp=True)
    f.write('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 = scmutil.opener('.')('y', 'w', atomictemp=True)
    f.write('B')
    f.close()

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

    f = scmutil.opener('.')('x', 'w', atomictemp=True)
    f.write('c')
    f.close()
    f = scmutil.opener('.')('y', 'w', atomictemp=True)
    f.write('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(ui.ui())
    # first rollback clears the filecache, but changelog to stays in __dict__
    repo.rollback()
    repo.commit('.')
    # 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('.')

def setbeforeget(repo):
    os.remove('x')
    os.remove('y')
    repo.cached = '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.cached = '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

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