dirstate.walk: don't keep track of normalized files in parallel
Rev 2bb13f2b778c changed the semantics of the work list to store (normalized,
non-normalized) pairs. All the tuple creation and destruction hurts perf: on a
large repo on OS X, 'hg status' went from 3.62 seconds to 3.78.
It also is unnecessary in most cases:
- it is clearly unnecessary on case-sensitive filesystems.
- it is also unnecessary when filenames have been read off of disk rather than
being supplied by the user.
The only case where the non-normalized case is required at all is when the file
is unknown.
To eliminate most of the perf cost, keep trace of whether the directory needs
to be normalized at all with a boolean called 'alreadynormed'. Pay the cost of
directory normalization only when necessary.
For the above large repo, 'hg status' goes to 3.63 seconds.
from mercurial import demandimport
demandimport.enable()
import os
if os.name != 'nt':
try:
import distutils.msvc9compiler
print ('distutils.msvc9compiler needs to be an immediate '
'importerror on non-windows platforms')
distutils.msvc9compiler
except ImportError:
pass
import re
rsub = re.sub
def f(obj):
l = repr(obj)
l = rsub("0x[0-9a-fA-F]+", "0x?", l)
l = rsub("from '.*'", "from '?'", l)
l = rsub("'<[a-z]*>'", "'<whatever>'", l)
return l
import os
print "os =", f(os)
print "os.system =", f(os.system)
print "os =", f(os)
from mercurial import util
print "util =", f(util)
print "util.system =", f(util.system)
print "util =", f(util)
print "util.system =", f(util.system)
import re as fred
print "fred =", f(fred)
import sys as re
print "re =", f(re)
print "fred =", f(fred)
print "fred.sub =", f(fred.sub)
print "fred =", f(fred)
print "re =", f(re)
print "re.stderr =", f(re.stderr)
print "re =", f(re)
demandimport.disable()
os.environ['HGDEMANDIMPORT'] = 'disable'
demandimport.enable()
from mercurial import node
print "node =", f(node)