view mercurial/lsprof.py @ 25561:50a6c3c55db1 stable

parsers: do not cache RevlogError type (issue4451)

Index lookups raise RevlogError when the lookup fails. The previous
implementation was caching a reference to the RevlogError type in a
static variable. This assumed that the "mercurial.error" module was
only loaded once and there was only a single copy of it floating
around in memory. Unfortunately, in some situations - including
certain mod_wsgi configurations - this was not the case: the
"mercurial.error" module could be reloaded. It was possible for a
"RevlogError" reference from the first interpreter to be used by
a second interpreter. While the underlying thing was a
"mercurial.error.RevlogError," the object IDs were different, so
the Python code in revlog.py was failing to catch the exception! This
error has existed since the C index lookup code was implemented in
changeset e8d37b78acfb, which was first released in Mercurial 2.2 in
2012.
http://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/#static-variables-are-shared
contains more details.

This patch removes the caching of the RevlogError type from the
function.

Since pretty much the entire function was refactored and the return
value of the function wasn't used, I changed the function signature
to not return anything.

For reasons unknown to me, we were calling PyErr_SetObject()
with the type of RevlogError and an instance of RevlogError. This
was equivalent to the Python code "raise RevlogError(RevlogError)".
This seemed wonky and completely unnecessary. The Python code only
cares about the type of the exception, not its contents. So I got
rid of this complexity.

This is my first Python C extension patch. Please give extra scrutiny
to it during review.

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()