view mercurial/lsprof.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

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()