view mercurial/profiling.py @ 40626:87a872555e90

revlog: detect incomplete revlog reads

_readsegment() is supposed to return N bytes of revlog revision
data starting at a file offset. Surprisingly, its behavior before
this patch never verified that it actually read and returned N
bytes! Instead, it would perform the read(), then return whatever
data was available. And even more surprisingly, nothing in the
call chain appears to have been validating that it received all
the data it was expecting.

This behavior could lead to partial or incomplete revision chunks
being operated on. This could result in e.g. cached deltas being
applied against incomplete base revisions. The delta application
process would happily perform this operation. Only hash
verification would detect the corruption and save us.

This commit changes the behavior of raw revlog reading to validate
that we actually read() the number of bytes that were requested.
We will raise a more specific error faster, rather than possibly
have it go undetected or manifest later in the call stack, at
delta application or hash verification.

Differential Revision: https://phab.mercurial-scm.org/D5266

# profiling.py - profiling functions
#
# Copyright 2016 Gregory Szorc <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import contextlib

from .i18n import _
from . import (
    encoding,
    error,
    extensions,
    pycompat,
    util,
)

def _loadprofiler(ui, profiler):
    """load profiler extension. return profile method, or None on failure"""
    extname = profiler
    extensions.loadall(ui, whitelist=[extname])
    try:
        mod = extensions.find(extname)
    except KeyError:
        return None
    else:
        return getattr(mod, 'profile', None)

@contextlib.contextmanager
def lsprofile(ui, fp):
    format = ui.config('profiling', 'format')
    field = ui.config('profiling', 'sort')
    limit = ui.configint('profiling', 'limit')
    climit = ui.configint('profiling', 'nested')

    if format not in ['text', 'kcachegrind']:
        ui.warn(_("unrecognized profiling format '%s'"
                    " - Ignored\n") % format)
        format = 'text'

    try:
        from . import lsprof
    except ImportError:
        raise error.Abort(_(
            'lsprof not available - install from '
            'http://codespeak.net/svn/user/arigo/hack/misc/lsprof/'))
    p = lsprof.Profiler()
    p.enable(subcalls=True)
    try:
        yield
    finally:
        p.disable()

        if format == 'kcachegrind':
            from . import lsprofcalltree
            calltree = lsprofcalltree.KCacheGrind(p)
            calltree.output(fp)
        else:
            # format == 'text'
            stats = lsprof.Stats(p.getstats())
            stats.sort(pycompat.sysstr(field))
            stats.pprint(limit=limit, file=fp, climit=climit)

@contextlib.contextmanager
def flameprofile(ui, fp):
    try:
        from flamegraph import flamegraph
    except ImportError:
        raise error.Abort(_(
            'flamegraph not available - install from '
            'https://github.com/evanhempel/python-flamegraph'))
    # developer config: profiling.freq
    freq = ui.configint('profiling', 'freq')
    filter_ = None
    collapse_recursion = True
    thread = flamegraph.ProfileThread(fp, 1.0 / freq,
                                      filter_, collapse_recursion)
    start_time = util.timer()
    try:
        thread.start()
        yield
    finally:
        thread.stop()
        thread.join()
        print('Collected %d stack frames (%d unique) in %2.2f seconds.' % (
            util.timer() - start_time, thread.num_frames(),
            thread.num_frames(unique=True)))

@contextlib.contextmanager
def statprofile(ui, fp):
    from . import statprof

    freq = ui.configint('profiling', 'freq')
    if freq > 0:
        # Cannot reset when profiler is already active. So silently no-op.
        if statprof.state.profile_level == 0:
            statprof.reset(freq)
    else:
        ui.warn(_("invalid sampling frequency '%s' - ignoring\n") % freq)

    track = ui.config('profiling', 'time-track',
                      pycompat.iswindows and 'cpu' or 'real')
    statprof.start(mechanism='thread', track=track)

    try:
        yield
    finally:
        data = statprof.stop()

        profformat = ui.config('profiling', 'statformat')

        formats = {
            'byline': statprof.DisplayFormats.ByLine,
            'bymethod': statprof.DisplayFormats.ByMethod,
            'hotpath': statprof.DisplayFormats.Hotpath,
            'json': statprof.DisplayFormats.Json,
            'chrome': statprof.DisplayFormats.Chrome,
        }

        if profformat in formats:
            displayformat = formats[profformat]
        else:
            ui.warn(_('unknown profiler output format: %s\n') % profformat)
            displayformat = statprof.DisplayFormats.Hotpath

        kwargs = {}

        def fraction(s):
            if isinstance(s, (float, int)):
                return float(s)
            if s.endswith('%'):
                v = float(s[:-1]) / 100
            else:
                v = float(s)
            if 0 <= v <= 1:
                return v
            raise ValueError(s)

        if profformat == 'chrome':
            showmin = ui.configwith(fraction, 'profiling', 'showmin', 0.005)
            showmax = ui.configwith(fraction, 'profiling', 'showmax')
            kwargs.update(minthreshold=showmin, maxthreshold=showmax)
        elif profformat == 'hotpath':
            # inconsistent config: profiling.showmin
            limit = ui.configwith(fraction, 'profiling', 'showmin', 0.05)
            kwargs[r'limit'] = limit

        statprof.display(fp, data=data, format=displayformat, **kwargs)

class profile(object):
    """Start profiling.

    Profiling is active when the context manager is active. When the context
    manager exits, profiling results will be written to the configured output.
    """
    def __init__(self, ui, enabled=True):
        self._ui = ui
        self._output = None
        self._fp = None
        self._fpdoclose = True
        self._profiler = None
        self._enabled = enabled
        self._entered = False
        self._started = False

    def __enter__(self):
        self._entered = True
        if self._enabled:
            self.start()
        return self

    def start(self):
        """Start profiling.

        The profiling will stop at the context exit.

        If the profiler was already started, this has no effect."""
        if not self._entered:
            raise error.ProgrammingError()
        if self._started:
            return
        self._started = True
        profiler = encoding.environ.get('HGPROF')
        proffn = None
        if profiler is None:
            profiler = self._ui.config('profiling', 'type')
        if profiler not in ('ls', 'stat', 'flame'):
            # try load profiler from extension with the same name
            proffn = _loadprofiler(self._ui, profiler)
            if proffn is None:
                self._ui.warn(_("unrecognized profiler '%s' - ignored\n")
                              % profiler)
                profiler = 'stat'

        self._output = self._ui.config('profiling', 'output')

        try:
            if self._output == 'blackbox':
                self._fp = util.stringio()
            elif self._output:
                path = self._ui.expandpath(self._output)
                self._fp = open(path, 'wb')
            elif pycompat.iswindows:
                # parse escape sequence by win32print()
                class uifp(object):
                    def __init__(self, ui):
                        self._ui = ui
                    def write(self, data):
                        self._ui.write_err(data)
                    def flush(self):
                        self._ui.flush()
                self._fpdoclose = False
                self._fp = uifp(self._ui)
            else:
                self._fpdoclose = False
                self._fp = self._ui.ferr

            if proffn is not None:
                pass
            elif profiler == 'ls':
                proffn = lsprofile
            elif profiler == 'flame':
                proffn = flameprofile
            else:
                proffn = statprofile

            self._profiler = proffn(self._ui, self._fp)
            self._profiler.__enter__()
        except: # re-raises
            self._closefp()
            raise

    def __exit__(self, exception_type, exception_value, traceback):
        propagate = None
        if self._profiler is not None:
            propagate = self._profiler.__exit__(exception_type, exception_value,
                                                traceback)
            if self._output == 'blackbox':
                val = 'Profile:\n%s' % self._fp.getvalue()
                # ui.log treats the input as a format string,
                # so we need to escape any % signs.
                val = val.replace('%', '%%')
                self._ui.log('profile', val)
        self._closefp()
        return propagate

    def _closefp(self):
        if self._fpdoclose and self._fp is not None:
            self._fp.close()