mercurial/lsprof.py
author Manuel Jacob <me@manueljacob.de>
Mon, 11 Jul 2022 01:51:20 +0200
branchstable
changeset 49378 094a5fa3cf52
parent 48946 642e31cb55f0
child 50929 18c8c18993f0
permissions -rw-r--r--
procutil: make stream detection in make_line_buffered more correct and strict In make_line_buffered(), we don’t want to wrap the stream if we know that lines get flushed to the underlying raw stream already. Previously, the heuristic was too optimistic. It assumed that any stream which is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there are buffered streams that aren’t instances of io.BufferedIOBase, like Mercurial’s own winstdout. The new logic is different in two ways: First, only for the check, if unwraps any combination of WriteAllWrapper and winstdout. Second, it skips wrapping the stream only if it is an instance of io.RawIOBase (or already wrapped). If it is an instance of io.BufferedIOBase, it gets wrapped. In any other case, the function raises an exception. This ensures that, if an unknown stream is passed or we add another wrapper in the future, we don’t wrap the stream if it’s already line buffered or not wrap the stream if it’s not line buffered. In fact, this was already helpful during development of this change. Without it, I possibly would have forgot that WriteAllWrapper needs to be ignored for the check, leading to unnecessary wrapping if stdout is unbuffered. The alternative would have been to always wrap unknown streams. However, I don’t think that anyone would benefit from being less strict. We can expect streams from the standard library to be subclassing either io.RawIOBase or io.BufferedIOBase, so running Mercurial in the standard way should not regress by this change. Py2exe might replace sys.stdout and sys.stderr, but that currently breaks Mercurial anyway and also these streams don’t claim to be interactive, so this function is not called for them.

import _lsprof
import sys

from .pycompat import getattr

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:
    """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):
        return code.encode('latin-1')
    try:
        mname = _fn2mod[code.co_filename]
    except KeyError:
        for k, v in list(sys.modules.items()):
            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)

    return res.encode('latin-1')