##// END OF EJS Templates
util: lower water mark when removing nodes after cost limit reached...
util: lower water mark when removing nodes after cost limit reached See the inline comment for the reasoning here. This is a pretty common strategy for garbage collectors, other cache-like primtives. The performance impact is substantial: $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! inserts w/ cost limit ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! wall 1.722122 comb 1.720000 user 1.720000 sys 0.000000 (best of 6) ! mixed w/ cost limit ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) ! wall 1.182513 comb 1.180000 user 1.180000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! inserts ! wall 0.679546 comb 0.680000 user 0.680000 sys 0.000000 (best of 15) ! sets ! wall 0.825147 comb 0.830000 user 0.830000 sys 0.000000 (best of 13) ! inserts w/ cost limit ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! wall 1.724397 comb 1.720000 user 1.720000 sys 0.000000 (best of 6) ! mixed ! wall 0.807096 comb 0.810000 user 0.810000 sys 0.000000 (best of 13) ! mixed w/ cost limit ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) ! wall 1.190563 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! inserts ! wall 0.711177 comb 0.710000 user 0.710000 sys 0.000000 (best of 14) ! sets ! wall 0.846992 comb 0.850000 user 0.850000 sys 0.000000 (best of 12) ! inserts w/ cost limit ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! wall 2.184311 comb 2.180000 user 2.180000 sys 0.000000 (best of 5) ! mixed ! wall 0.728256 comb 0.730000 user 0.730000 sys 0.000000 (best of 14) ! mixed w/ cost limit ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) ! wall 0.773186 comb 0.770000 user 0.770000 sys 0.000000 (best of 13) $ hg perflrucachedict --size 100000 --gets 1000000 --sets 1000000 --mixed 1000000 --mixedgetfreq 90 --costlimit 5000000 ! gets ! wall 1.191368 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) ! wall 1.195304 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) ! inserts ! wall 0.950995 comb 0.950000 user 0.950000 sys 0.000000 (best of 11) ! inserts w/ cost limit ! wall 1.589732 comb 1.590000 user 1.590000 sys 0.000000 (best of 7) ! sets ! wall 1.094941 comb 1.100000 user 1.090000 sys 0.010000 (best of 9) ! mixed ! wall 0.936420 comb 0.940000 user 0.930000 sys 0.010000 (best of 10) ! mixed w/ cost limit ! wall 0.882780 comb 0.870000 user 0.870000 sys 0.000000 (best of 11) This puts us ~2x slower than caches without cost accounting. And for read-heavy workloads (the prime use cases for caches), performance is nearly identical. In the worst case (pure write workloads with cost accounting enabled), we're looking at ~1.5us per insert on large caches. That seems "fast enough." Differential Revision: https://phab.mercurial-scm.org/D4505

File last commit:

r35854:d4e5b265 default
r39606:f296c0b3 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()