Mercurial > hg
view mercurial/profiling.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 | 0ae593e791fb |
children | 2372284d9457 |
line wrap: on
line source
# profiling.py - profiling functions # # Copyright 2016 Gregory Szorc <gregory.szorc@gmail.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. from __future__ import absolute_import, print_function import contextlib from .i18n import _ from . import ( encoding, error, extensions, pycompat, util, ) def _loadprofiler(ui, profiler): """load profiler extension. return profile method, or None on failure""" extname = profiler extensions.loadall(ui, whitelist=[extname]) try: mod = extensions.find(extname) except KeyError: return None else: return getattr(mod, 'profile', None) @contextlib.contextmanager def lsprofile(ui, fp): format = ui.config('profiling', 'format') field = ui.config('profiling', 'sort') limit = ui.configint('profiling', 'limit') climit = ui.configint('profiling', 'nested') if format not in ['text', 'kcachegrind']: ui.warn(_("unrecognized profiling format '%s'" " - Ignored\n") % format) format = 'text' try: from . import lsprof except ImportError: raise error.Abort(_( 'lsprof not available - install from ' 'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/')) p = lsprof.Profiler() p.enable(subcalls=True) try: yield finally: p.disable() if format == 'kcachegrind': from . import lsprofcalltree calltree = lsprofcalltree.KCacheGrind(p) calltree.output(fp) else: # format == 'text' stats = lsprof.Stats(p.getstats()) stats.sort(pycompat.sysstr(field)) stats.pprint(limit=limit, file=fp, climit=climit) @contextlib.contextmanager def flameprofile(ui, fp): try: from flamegraph import flamegraph except ImportError: raise error.Abort(_( 'flamegraph not available - install from ' 'https://github.com/evanhempel/python-flamegraph')) # developer config: profiling.freq freq = ui.configint('profiling', 'freq') filter_ = None collapse_recursion = True thread = flamegraph.ProfileThread(fp, 1.0 / freq, filter_, collapse_recursion) start_time = util.timer() try: thread.start() yield finally: thread.stop() thread.join() print('Collected %d stack frames (%d unique) in %2.2f seconds.' % ( util.timer() - start_time, thread.num_frames(), thread.num_frames(unique=True))) @contextlib.contextmanager def statprofile(ui, fp): from . import statprof freq = ui.configint('profiling', 'freq') if freq > 0: # Cannot reset when profiler is already active. So silently no-op. if statprof.state.profile_level == 0: statprof.reset(freq) else: ui.warn(_("invalid sampling frequency '%s' - ignoring\n") % freq) track = ui.config('profiling', 'time-track', pycompat.iswindows and 'cpu' or 'real') statprof.start(mechanism='thread', track=track) try: yield finally: data = statprof.stop() profformat = ui.config('profiling', 'statformat') formats = { 'byline': statprof.DisplayFormats.ByLine, 'bymethod': statprof.DisplayFormats.ByMethod, 'hotpath': statprof.DisplayFormats.Hotpath, 'json': statprof.DisplayFormats.Json, 'chrome': statprof.DisplayFormats.Chrome, } if profformat in formats: displayformat = formats[profformat] else: ui.warn(_('unknown profiler output format: %s\n') % profformat) displayformat = statprof.DisplayFormats.Hotpath kwargs = {} def fraction(s): if isinstance(s, (float, int)): return float(s) if s.endswith('%'): v = float(s[:-1]) / 100 else: v = float(s) if 0 <= v <= 1: return v raise ValueError(s) if profformat == 'chrome': showmin = ui.configwith(fraction, 'profiling', 'showmin', 0.005) showmax = ui.configwith(fraction, 'profiling', 'showmax') kwargs.update(minthreshold=showmin, maxthreshold=showmax) elif profformat == 'hotpath': # inconsistent config: profiling.showmin limit = ui.configwith(fraction, 'profiling', 'showmin', 0.05) kwargs[r'limit'] = limit showtime = ui.configbool('profiling', 'showtime') kwargs[r'showtime'] = showtime statprof.display(fp, data=data, format=displayformat, **kwargs) class profile(object): """Start profiling. Profiling is active when the context manager is active. When the context manager exits, profiling results will be written to the configured output. """ def __init__(self, ui, enabled=True): self._ui = ui self._output = None self._fp = None self._fpdoclose = True self._profiler = None self._enabled = enabled self._entered = False self._started = False def __enter__(self): self._entered = True if self._enabled: self.start() return self def start(self): """Start profiling. The profiling will stop at the context exit. If the profiler was already started, this has no effect.""" if not self._entered: raise error.ProgrammingError() if self._started: return self._started = True profiler = encoding.environ.get('HGPROF') proffn = None if profiler is None: profiler = self._ui.config('profiling', 'type') if profiler not in ('ls', 'stat', 'flame'): # try load profiler from extension with the same name proffn = _loadprofiler(self._ui, profiler) if proffn is None: self._ui.warn(_("unrecognized profiler '%s' - ignored\n") % profiler) profiler = 'stat' self._output = self._ui.config('profiling', 'output') try: if self._output == 'blackbox': self._fp = util.stringio() elif self._output: path = self._ui.expandpath(self._output) self._fp = open(path, 'wb') elif pycompat.iswindows: # parse escape sequence by win32print() class uifp(object): def __init__(self, ui): self._ui = ui def write(self, data): self._ui.write_err(data) def flush(self): self._ui.flush() self._fpdoclose = False self._fp = uifp(self._ui) else: self._fpdoclose = False self._fp = self._ui.ferr if proffn is not None: pass elif profiler == 'ls': proffn = lsprofile elif profiler == 'flame': proffn = flameprofile else: proffn = statprofile self._profiler = proffn(self._ui, self._fp) self._profiler.__enter__() except: # re-raises self._closefp() raise def __exit__(self, exception_type, exception_value, traceback): propagate = None if self._profiler is not None: propagate = self._profiler.__exit__(exception_type, exception_value, traceback) if self._output == 'blackbox': val = 'Profile:\n%s' % self._fp.getvalue() # ui.log treats the input as a format string, # so we need to escape any % signs. val = val.replace('%', '%%') self._ui.log('profile', val) self._closefp() return propagate def _closefp(self): if self._fpdoclose and self._fp is not None: self._fp.close()