tests/test-filecache.py

obsolete: order of magnitude speedup in _computebumpedset

Reminder: a changeset is said "bumped" if it tries to obsolete a immutable
          changeset.


The previous algorithm for computing bumped changeset was:

    1) Get all public changesets
    2) Find all they successors
    3) Search for stuff that are eligible for being "bumped"
       (mutable and non obsolete)

The entry size of this algorithm is `O(len(public))` which is mostly the same as
`O(len(repo))`. Even this this approach mean fewer obsolescence marker are
traveled, this is not very scalable.

The new algorithm is:

    1) For each potential bumped changesets (non obsolete mutable)
    2) iterate over precursors
    3) if a precursors is public. changeset is bumped

We travel more obsolescence marker, but the entry size is much smaller since
the amount of potential bumped should remains mostly stable with time `O(1)`.

On some confidential gigantic repo this move bumped computation from 15.19s to
0.46s (×33 speedup…). On "smaller" repo (mercurial, cubicweb's review) no
significant gain were seen. The additional traversal of obsolescence marker is
probably probably counter balance the advantage of it.

Other optimisation could be done in the future (eg: sharing precursors cache
for divergence detection)

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())