Mercurial > hg-stable
view tests/test-filecache.py @ 22778:80f2b63dd83a
parsers: add a function to efficiently lowercase ASCII strings
We need a way to efficiently lowercase ASCII strings. For example, 'hg status'
needs to build up the fold map -- a map from a canonical case (for OS X,
lowercase) to the actual case of each file and directory in the dirstate.
The current way we do that is to try decoding to ASCII and then calling
lower() on the string, labeled 'orig' below:
str.decode('ascii')
return str.lower()
This is pretty inefficient, and it turns out we can do much better.
I also tested out a condition-based approach, labeled 'cond' below:
(c >= 'A' && c <= 'Z') ? (c + ('a' - 'A')) : c
'cond' turned out to be slower in all cases. A 256-byte lookup table with
invalid values for everything past 127 performed similarly, but this was less
verbose.
On OS X 10.9 with LLVM version 6.0 (clang-600.0.51), the asciilower function
was run against two corpuses.
Corpus 1 (list of files from real-world repo, > 100k files):
orig: wall 0.428567 comb 0.430000 user 0.430000 sys 0.000000 (best of 24)
cond: wall 0.077204 comb 0.070000 user 0.070000 sys 0.000000 (best of 100)
lookup: wall 0.060714 comb 0.060000 user 0.060000 sys 0.000000 (best of 100)
Corpus 2 (mozilla-central, 113k files):
orig: wall 0.238406 comb 0.240000 user 0.240000 sys 0.000000 (best of 42)
cond: wall 0.040779 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
lookup: wall 0.037623 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
On a Linux server-class machine with GCC 4.4.6 20120305 (Red Hat 4.4.6-4):
Corpus 1 (real-world repo, > 100k files):
orig: wall 0.260899 comb 0.260000 user 0.260000 sys 0.000000 (best of 38)
cond: wall 0.054818 comb 0.060000 user 0.060000 sys 0.000000 (best of 100)
lookup: wall 0.048489 comb 0.050000 user 0.050000 sys 0.000000 (best of 100)
Corpus 2 (mozilla-central, 113k files):
orig: wall 0.153082 comb 0.150000 user 0.150000 sys 0.000000 (best of 65)
cond: wall 0.031007 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
lookup: wall 0.028793 comb 0.030000 user 0.030000 sys 0.000000 (best of 100)
SSE instructions might help even more, but I didn't experiment with those.
author | Siddharth Agarwal <sid0@fb.com> |
---|---|
date | Fri, 03 Oct 2014 18:42:39 -0700 |
parents | b3684fd2ff1a |
children | ce26928cbe41 |
line wrap: on
line source
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())