mercurial/lsprof.py

merge: make in-memory changes visible to external update hooks

51844b8b5017 (while 3.4 code-freeze) made all 'update' hooks run after
releasing wlock for visibility of in-memory dirstate changes. But this
breaks paired invocation of 'preupdate' and 'update' hooks.

For example, 'hg backout --merge' for TARGET revision, which isn't
parent of CURRENT, consists of steps below:

  1. update from CURRENT to TARGET
  2. commit BACKOUT revision, which backs TARGET out
  3. update from BACKOUT to CURRENT
  4. merge TARGET into CURRENT

Then, we expects hooks to run in the order below:

  - 'preupdate' on CURRENT for (1)
  - 'update'    on TARGET  for (1)
  - 'preupdate' on BACKOUT for (3)
  - 'update'    on CURRENT for (3)
  - 'preupdate' on TARGET  for (4)
  - 'update'    on CURRENT/TARGET for (4)

But hooks actually run in the order below:

  - 'preupdate' on CURRENT for (1)
  - 'preupdate' on BACKOUT for (3)
  - 'preupdate' on TARGET  for (4)
  - 'update'    on TARGET  for (1), but actually on CURRENT/TARGET
  - 'update'    on CURRENT for (3), but actually on CURRENT/TARGET
  - 'update'    on CURRENT for (4), but actually on CURRENT/TARGET

Root cause of the issue focused by 51844b8b5017 is that external
'update' hook process can't view in-memory changes (especially, of
dirstate), because they aren't written out until the end of
transaction (or wlock).

Now, hooks can be invoked just after updating, because previous
patches made in-memory changes visible to external process.

This patch may break backward compatibility from the point of view of
"scheduling hook execution", but should be reasonable because 'update'
hooks had been executed in this order before 3.4.

This patch tests "hg backout" and "hg unshelve", because the former
activates the transaction before 'update' hook invocation, but the
former doesn't.

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()