view mercurial/lsprof.py @ 18040:fe8caf28d580

strip: make query to get new bookmark target cheaper

The current query to get the new bookmark target for stripped revisions
involves multiple walks up the DAG, and is really expensive, taking over 2.5
seconds on a repository with over 400,000 changesets even if just one
changeset is being stripped.

A slightly simplified version of the current query is

max(heads(::<tostrip> - <tostrip>))

We make two observations here.

1. For any set s, max(heads(s)) == max(s). That is because revision numbers
   define a topological order, so that the element with the highest revision
   number in s will not have any children in s.

2. For any set s, max(::s - s) == max(parents(s) - s). In other words, the
   ancestor of s with the highest revision number not in s is a parent of one
   of the revs in s. Why? Because if it were an ancestor but not a parent of s,
   it would have a descendant that would be a parent of s. This descendant
   would have a higher revision number, leading to a contradiction.

Combining these two observations, we rewrite the revset query as

max(parents(<tostrip>) - <tostrip>)

The time complexity is now linear in the number of changesets being stripped.
For the above repository, the query now takes 0.1 seconds when one changeset
is stripped. This speeds up operations that use repair.strip, like the rebase
and strip commands.

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 % ("+%s" % 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()