Mercurial > hg
view mercurial/lsprof.py @ 39872:733db72f0f54
revlog: move revision verification out of verify
File revision verification is performing low-level checks of file
storage, namely that flags are appropriate and revision data can
be resolved.
Since these checks are somewhat revlog-specific and may not
be appropriate for alternate storage backends, this commit moves
those checks from verify.py to revlog.py.
Because we're now emitting warnings/errors that apply to specific
revisions, we taught the iverifyproblem interface to expose the
problematic node and to report this node in verify output. This
was necessary to prevent unwanted test changes.
After this change, revlog.verifyintegrity() and file verify code
in verify.py both iterate over revisions and resolve their fulltext.
But they do so in separate loops. (verify.py needs to resolve
fulltexts as part of calling renamed() - at least when using revlogs.)
This should add overhead.
But on the mozilla-unified repo:
$ hg verify
before: time: real 700.640 secs (user 585.520+0.000 sys 23.480+0.000)
after: time: real 682.380 secs (user 570.370+0.000 sys 22.240+0.000)
I'm not sure what's going on. Maybe avoiding the filelog attribute
proxies shaved off enough time to offset the losses? Maybe fulltext
resolution has less overhead than I thought?
I've left a comment indicating the potential for optimization. But
because it doesn't produce a performance regression on a large
repository, I'm not going to worry about it.
Differential Revision: https://phab.mercurial-scm.org/D4745
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Mon, 24 Sep 2018 11:27:47 -0700 |
parents | d4e5b2653693 |
children | b25fbe7e494e |
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 = "% 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()