tests/test-filecache.py

revset: use localrepo revbranchcache for branch name filtering

Branch name filtering in revsets was expensive. For every rev it created a
changectx and called .branch() which retrieved the branch name from the
changelog.

Instead, use the revbranchcache.

The revbranchcache is used read-only. The revset implementation with generators
and callbacks makes it hard to figure out when we are done using/updating the
cache and could write it back. It would also be 'tricky' to lock the repo for
writing from within a revset execution. Finally, the branchmap update will
usually make sure that the cache is updated before any revset can be run.
The revbranchcache is used without any locking but is short-lived and used in a
tight loop where we can assume that the changelog doesn't change ... or where
it not is relevant to us if it does.

perfrevset 'branch(mobile)' on mozilla-central.
Before:
! wall 10.989637 comb 10.970000 user 10.940000 sys 0.030000 (best of 3)
After, no cache:
! wall 7.368656 comb 7.370000 user 7.360000 sys 0.010000 (best of 3)
After, with cache:
! wall 0.528098 comb 0.530000 user 0.530000 sys 0.000000 (best of 18)

The performance improvement even without cache come from being based on
branchinfo on the changelog instead of using ctx.branch().

Some tests are added to verify that the revbranchcache works and keep an eye on
when the cache files actually are updated.

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())