view mercurial/lsprof.py @ 18792:10669e24eb6c

completion: add a debugpathcomplete command

The bash_completion code uses "hg status" to generate a list of
possible completions for commands that operate on files in the
working directory. In a large working directory, this can result
in a single tab-completion being very slow (several seconds) as a
result of checking the status of every file, even when there is no
need to check status or no possible matches.

The new debugpathcomplete command gains performance in a few simple
ways:

* Allow completion to operate on just a single directory. When used
  to complete the right commands, this considerably reduces the
  number of completions returned, at no loss in functionality.

* Never check the status of files. For completions that really must
  know if a file is modified, it is faster to use status:

  hg status -nm 'glob:myprefix**'

Performance:

Here are the commands used by bash_completion to complete, run in
the root of the mozilla-central working dir (~77,000 files) and
another repo (~165,000 files):

All "normal state" files (used by e.g. remove, revert):

                            mozilla    other
  status -nmcd 'glob:**'       1.77     4.10 sec
  debugpathcomplete -f -n      0.53     1.26
  debugpathcomplete -n         0.17     0.41

("-f" means "complete full paths", rather than the current directory)

Tracked files matching "a":

                            mozilla    other
  status -nmcd 'glob:a**'      0.26     0.47
  debugpathcomplete -f -n a    0.10     0.24
  debugpathcomplete -n a       0.10     0.22

We should be able to further improve completion performance once
the critbit work lands. Right now, our performance is limited by
the need to iterate over all keys in the dirstate.

import sys
from _lsprof import Profiler, profiler_entry

__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="inlinetime"):
        """XXX docstring"""
        if crit not in profiler_entry.__dict__:
            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 >> sys.stderr, "usage: lsprof.py <script> <arguments...>"
        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()