view tests/test-filecache.py @ 24787:9d5c27890790

largefiles: for update -C, only update largefiles when necessary

Before, a --clean update with largefiles would use the "optimization" that it
didn't read hashes from standin files before and after the update. Instead of
trusting the content of the standin files, it would rehash all the actual
largefiles that lfdirstate reported clean and update the standins that didn't
have the expected content. It could thus in some "impossible" situations
automatically recover from some "largefile got out sync with its standin"
issues (even there apparently still were weird corner cases where it could
fail). This extra checking is similar to what core --clean intentionally do
not do, and it made update --clean unbearable slow.

Usually in core Mercurial, --clean will rely on the dirstate to find the files
it should update. (It is thus intentionally possible (when trying to trick the
system or if there should be bugs) to end up in situations where --clean not
will restore the working directory content correctly.) Checking every file when
we "know" it is ok is however not an option - that would be too slow.

Instead, trust the content of the standin files. Use the same logic for --clean
as for linear updates and trust the dirstate and that our "logic" will keep
them in sync. It is much cheaper to just rehash the largefiles reported dirty
by a status walk and read all standins than to hash largefiles.

Most of the changes are just a change of indentation now when the different
kinds of updates no longer are handled that differently. Standins for added
files are however only written when doing a normal update, while deleted and
removed files only will be updated for --clean updates.

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 behaviour 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())