##// END OF EJS Templates
bdiff: don't check border condition in loop...
bdiff: don't check border condition in loop `plast = a + len - 1`. So, this "for" loop iterates from "a" to "plast", inclusive. So, `p == plast` can only be true on the final iteration of the loop. So checking for it on every loop iteration is wasteful. This patch simply decreases the upper bound of the loop by 1 and adds an explicit check after iteration for the `p == plast` case. We can't simply add 1 to the initial value for "i" because that doesn't do the correct thing on empty input strings. `perfbdiff -m 3041e4d59df2` on the Firefox repo becomes significantly faster: ! wall 0.072763 comb 0.070000 user 0.070000 sys 0.000000 (best of 100) ! wall 0.053221 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) For the curious, this code has its origins in 8b067bde6679, which is the changeset that introduced bdiff.c in 2005. Also, GNU diffutils is able to perform a similar line-based diff in under 20ms. So there's likely more perf wins to be found in this code. One of them is the hashing algorithm. But it looks like mpm spent some time testing hash collisions in d0c48891dd4a. I'd like to do the same before switching away from lyhash, just to be on the safe side.

File last commit:

r27617:b1a59b80 default
r30308:d500ddae default
Show More
lsprof.py
121 lines | 4.0 KiB | text/x-python | PythonLexer
from __future__ import absolute_import, print_function
import _lsprof
import sys
Profiler = _lsprof.Profiler
# PyPy doesn't expose profiler_entry from the module.
profiler_entry = getattr(_lsprof, 'profiler_entry', None)
__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"""
# profiler_entries isn't defined when running under PyPy.
if profiler_entry:
if crit not in profiler_entry.__dict__:
raise ValueError("Can't sort by %s" % crit)
elif self.data and not getattr(self.data[0], crit, None):
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("usage: lsprof.py <script> <arguments...>", file=sys.stderr)
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()