##// END OF EJS Templates
util: optimize cost auditing on insert...
util: optimize cost auditing on insert Calling popoldest() on insert with cost auditing enabled introduces significant overhead. The primary reason for this overhead is that popoldest() needs to walk the linked list to find the first non-empty node. When we call popoldest() within a loop, this can become quadratic. The performance impact is more pronounced on caches with large capacities. This commit effectively inlines the popoldest() call into _enforcecostlimit(). By doing so, we only do the backwards walk to find the first empty node once. However, we still may still perform this work on insert when the cache is near cost capacity. So this is only a partial performance win. $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.601993 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.614439 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) Differential Revision: https://phab.mercurial-scm.org/D4504

File last commit:

r35854:d4e5b265 default
r39605:cc23c09b 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=r"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()