annotate mercurial/lsprof.py @ 43913:4b7d5d10c45d

exchange: ensure all outgoing subrepo references are present before pushing

We've run into occasional problems with people committing a repo, and then
amending or rebasing in the subrepo.  That makes it so that the revision in the
parent can't be checked out, and the problem gets propagated on push.  Mercurial
already tries to defend against this sort of dangling reference by pushing *all*
subrepo revisions first.  This reuses the checks that trigger warnings in
`hg verify` to bail on the push unless using `--force`.

I thought about putting this on the server side, but at that point, all of the
data has been transferred, only to bail out.  Additionally, SCM Manager hosts
subrepos in a location that isn't nested in the parent, so normal subrepo code
would complain that the subrepo is missing when run on the server.

Because the push command pushes subrepos before calling this exchange code, a
subrepo will be pushed before the parent is verified.  Not great, but no
dangling references are exchanged, so it solves the problem.  This code isn't in
the loop that pushes the subrepos because:

  1) the list of outgoing revisions is needed to limit the scope of the check
  2) the loop only accesses the current revision, and therefore can miss
     subrepos that were dropped in previous commits
  3) this code is called when pushing a subrepo, so the protection is recursive

I'm not sure if there's a cheap check for the list of files in the outgoing
bundle.  If there is, that would provide a fast path to bypass this check for
people not using subrepos (or if no subrepo changes were made).  There's
probably also room for verifying other references like tags.  But since that
doesn't break checkouts, it's much less of a problem.

Differential Revision: https://phab.mercurial-scm.org/D7616

from __future__ import absolute_import, print_function

import _lsprof
import sys

from .pycompat import getattr
from . import pycompat

Profiler = _lsprof.Profiler

# PyPy doesn't expose profiler_entry from the module.
profiler_entry = getattr(_lsprof, 'profiler_entry', None)

__all__ = [b'profile', b'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"""
        # profiler_entries isn't defined when running under PyPy.
        if profiler_entry:
            if crit not in profiler_entry.__dict__:
                raise ValueError(b"Can't sort by %s" % crit)
        elif self.data and not getattr(self.data[0], crit, None):
            raise ValueError(b"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 = b"% 12d %12d %11.4f %11.4f   %s\n"
        hcols = b"% 12s %12s %12s %12s %s\n"
        file.write(
            hcols
            % (
                b"CallCount",
                b"Recursive",
                b"Total(s)",
                b"Inline(s)",
                b"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,
                            b"    %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):
        if sys.version_info.major >= 3:
            code = code.encode('latin-1')
        return code
    try:
        mname = _fn2mod[code.co_filename]
    except KeyError:
        for k, v in list(pycompat.iteritems(sys.modules)):
            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

    res = '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)

    if sys.version_info.major >= 3:
        res = res.encode('latin-1')

    return res