Mercurial > hg
view mercurial/lsprof.py @ 42743:8c9a6adec67a
rust-discovery: using the children cache in add_missing
The DAG range computation often needs to get back to very old
revisions, and turns out to be disproportionately long, given
that the end goal is to remove the descendents of the given
missing revisons from the undecided set.
The fast iteration capabilities available in the Rust case make
it possible to avoid the DAG range entirely, at the cost of
precomputing the children cache, and to simply iterate on
children of the given missing revisions.
This is a case where staying on the same side of the interface
between the two languages has clear benefits.
On discoveries with initial undecided sets
small enough to bypass sampling entirely, the total cost of
computing the children cache and the subsequent iteration
becomes better than the Python + C counterpart, which relies on
reachableroots2.
For example, on a repo with more than one million revisions with
an initial undecided set of 11 elements, we get these figures:
Rust version with simple iteration
addcommons: 57.287us
first undecided computation: 184.278334ms
first children cache computation: 131.056us
addmissings iteration: 42.766us
first addinfo total: 185.24 ms
Python + C version
first addcommons: 0.29 ms
addcommons 0.21 ms
first undecided computation 191.35 ms
addmissings 45.75 ms
first addinfo total: 237.77 ms
On discoveries with large undecided sets, the initial price paid
makes the first addinfo slower than the Python + C version,
but that's more than compensated by the gain in sampling and
subsequent iterations.
Here's an extreme example with an undecided set of a million revisions:
Rust version:
first undecided computation: 293.842629ms
first children cache computation: 407.911297ms
addmissings iteration: 34.312869ms
first addinfo total: 776.02 ms
taking initial sample
query 2: sampling time: 1318.38 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings: 143.062us
Python + C version:
first undecided computation 298.13 ms
addmissings 80.13 ms
first addinfo total: 399.62 ms
taking initial sample
query 2: sampling time: 3957.23 ms
query 2; still undecided: 1005013, sample size is: 200
addmissings 52.88 ms
Differential Revision: https://phab.mercurial-scm.org/D6428
author | Georges Racinet <georges.racinet@octobus.net> |
---|---|
date | Tue, 16 Apr 2019 01:16:39 +0200 |
parents | 56ea22fa55f0 |
children | 2372284d9457 |
line wrap: on
line source
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 = "% 12d %12d %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): if sys.version_info.major >= 3: code = code.encode('latin-1') 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] = r'<%s>' % code.co_filename res = r'%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name) if sys.version_info.major >= 3: res = res.encode('latin-1') return res 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()