##// END OF EJS Templates
parsers: inline fields of dirstate values in C version...
parsers: inline fields of dirstate values in C version Previously, while unpacking the dirstate we'd create 3-4 new CPython objects for most dirstate values: - the state is a single character string, which is pooled by CPython - the mode is a new object if it isn't 0 due to being in the lookup set - the size is a new object if it is greater than 255 - the mtime is a new object if it isn't -1 due to being in the lookup set - the tuple to contain them all In some cases such as regular hg status, we actually look at all the objects. In other cases like hg add, hg status for a subdirectory, or hg status with the third-party hgwatchman enabled, we look at almost none of the objects. This patch eliminates most object creation in these cases by defining a custom C struct that is exposed to Python with an interface similar to a tuple. Only when tuple elements are actually requested are the respective objects created. The gains, where they're expected, are significant. The following tests are run against a working copy with over 270,000 files. parse_dirstate becomes significantly faster: $ hg perfdirstate before: wall 0.186437 comb 0.180000 user 0.160000 sys 0.020000 (best of 35) after: wall 0.093158 comb 0.100000 user 0.090000 sys 0.010000 (best of 95) and as a result, several commands benefit: $ time hg status # with hgwatchman enabled before: 0.42s user 0.14s system 99% cpu 0.563 total after: 0.34s user 0.12s system 99% cpu 0.471 total $ time hg add new-file before: 0.85s user 0.18s system 99% cpu 1.033 total after: 0.76s user 0.17s system 99% cpu 0.931 total There is a slight regression in regular status performance, but this is fixed in an upcoming patch.

File last commit:

r18642:a40d608e default
r21809:e250b830 default
Show More
lsprof.py
109 lines | 3.6 KiB | text/x-python | PythonLexer
import sys
from _lsprof import Profiler, profiler_entry
__all__ = ['profile', 'Stats']
def profile(f, *args, **kwds):
"""XXX docstring"""
p = Profiler()
p.enable(subcalls=True, builtins=True)
try:
f(*args, **kwds)
finally:
p.disable()
return Stats(p.getstats())
class Stats(object):
"""XXX docstring"""
def __init__(self, data):
self.data = data
def sort(self, crit="inlinetime"):
"""XXX docstring"""
if crit not in profiler_entry.__dict__:
raise ValueError("Can't sort by %s" % crit)
self.data.sort(key=lambda x: getattr(x, crit), reverse=True)
for e in self.data:
if e.calls:
e.calls.sort(key=lambda x: getattr(x, crit), reverse=True)
def pprint(self, top=None, file=None, limit=None, climit=None):
"""XXX docstring"""
if file is None:
file = sys.stdout
d = self.data
if top is not None:
d = d[:top]
cols = "% 12s %12s %11.4f %11.4f %s\n"
hcols = "% 12s %12s %12s %12s %s\n"
file.write(hcols % ("CallCount", "Recursive", "Total(s)",
"Inline(s)", "module:lineno(function)"))
count = 0
for e in d:
file.write(cols % (e.callcount, e.reccallcount, e.totaltime,
e.inlinetime, label(e.code)))
count += 1
if limit is not None and count == limit:
return
ccount = 0
if climit and e.calls:
for se in e.calls:
file.write(cols % (se.callcount, se.reccallcount,
se.totaltime, se.inlinetime,
" %s" % label(se.code)))
count += 1
ccount += 1
if limit is not None and count == limit:
return
if climit is not None and ccount == climit:
break
def freeze(self):
"""Replace all references to code objects with string
descriptions; this makes it possible to pickle the instance."""
# this code is probably rather ickier than it needs to be!
for i in range(len(self.data)):
e = self.data[i]
if not isinstance(e.code, str):
self.data[i] = type(e)((label(e.code),) + e[1:])
if e.calls:
for j in range(len(e.calls)):
se = e.calls[j]
if not isinstance(se.code, str):
e.calls[j] = type(se)((label(se.code),) + se[1:])
_fn2mod = {}
def label(code):
if isinstance(code, str):
return code
try:
mname = _fn2mod[code.co_filename]
except KeyError:
for k, v in list(sys.modules.iteritems()):
if v is None:
continue
if not isinstance(getattr(v, '__file__', None), str):
continue
if v.__file__.startswith(code.co_filename):
mname = _fn2mod[code.co_filename] = k
break
else:
mname = _fn2mod[code.co_filename] = '<%s>' % code.co_filename
return '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)
if __name__ == '__main__':
import os
sys.argv = sys.argv[1:]
if not sys.argv:
print >> sys.stderr, "usage: lsprof.py <script> <arguments...>"
sys.exit(2)
sys.path.insert(0, os.path.abspath(os.path.dirname(sys.argv[0])))
stats = profile(execfile, sys.argv[0], globals(), locals())
stats.sort()
stats.pprint()