view mercurial/profiling.py @ 32697:19b9fc40cc51

revlog: skeleton support for version 2 revlogs

There are a number of improvements we want to make to revlogs
that will require a new version - version 2. It is unclear what the
full set of improvements will be or when we'll be done with them.
What I do know is that the process will likely take longer than a
single release, will require input from various stakeholders to
evaluate changes, and will have many contentious debates and
bikeshedding.

It is unrealistic to develop revlog version 2 up front: there
are just too many uncertainties that we won't know until things
are implemented and experiments are run. Some changes will also
be invasive and prone to bit rot, so sitting on dozens of patches
is not practical.

This commit introduces skeleton support for version 2 revlogs in
a way that is flexible and not bound by backwards compatibility
concerns.

An experimental repo requirement for denoting revlog v2 has been
added. The requirement string has a sub-version component to it.
This will allow us to declare multiple requirements in the course
of developing revlog v2. Whenever we change the in-development
revlog v2 format, we can tweak the string, creating a new
requirement and locking out old clients. This will allow us to
make as many backwards incompatible changes and experiments to
revlog v2 as we want. In other words, we can land code and make
meaningful progress towards revlog v2 while still maintaining
extreme format flexibility up until the point we freeze the
format and remove the experimental labels.

To enable the new repo requirement, you must supply an experimental
and undocumented config option. But not just any boolean flag
will do: you need to explicitly use a value that no sane person
should ever type. This is an additional guard against enabling
revlog v2 on an installation it shouldn't be enabled on. The
specific scenario I'm trying to prevent is say a user with a
4.4 client with a frozen format enabling the option but then
downgrading to 4.3 and accidentally creating repos with an
outdated and unsupported repo format. Requiring a "challenge"
string should prevent this.

Because the format is not yet finalized and I don't want to take
any chances, revlog v2's version is currently 0xDEAD. I figure
squatting on a value we're likely never to use as an actual revlog
version to mean "internal testing only" is acceptable. And
"dead" is easily recognized as something meaningful.

There is a bunch of cleanup that is needed before work on revlog
v2 begins in earnest. I plan on doing that work once this patch
is accepted and we're comfortable with the idea of starting down
this path.

# 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,
    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', default='text')
    field = ui.config('profiling', 'sort', default='inlinetime')
    limit = ui.configint('profiling', 'limit', default=30)
    climit = ui.configint('profiling', 'nested', default=0)

    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(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', default=1000)
    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', default=1000)
    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)

    statprof.start(mechanism='thread')

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

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

        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 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', 0.999)
            kwargs.update(minthreshold=showmin, maxthreshold=showmax)

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

@contextlib.contextmanager
def profile(ui):
    """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.
    """
    profiler = encoding.environ.get('HGPROF')
    proffn = None
    if profiler is None:
        profiler = ui.config('profiling', 'type', default='stat')
    if profiler not in ('ls', 'stat', 'flame'):
        # try load profiler from extension with the same name
        proffn = _loadprofiler(ui, profiler)
        if proffn is None:
            ui.warn(_("unrecognized profiler '%s' - ignored\n") % profiler)
            profiler = 'stat'

    output = ui.config('profiling', 'output')

    if output == 'blackbox':
        fp = util.stringio()
    elif output:
        path = ui.expandpath(output)
        fp = open(path, 'wb')
    else:
        fp = ui.ferr

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

        with proffn(ui, fp):
            yield

    finally:
        if output:
            if output == 'blackbox':
                val = 'Profile:\n%s' % fp.getvalue()
                # ui.log treats the input as a format string,
                # so we need to escape any % signs.
                val = val.replace('%', '%%')
                ui.log('profile', val)
            fp.close()

@contextlib.contextmanager
def maybeprofile(ui):
    """Profile if enabled, else do nothing.

    This context manager can be used to optionally profile if profiling
    is enabled. Otherwise, it does nothing.

    The purpose of this context manager is to make calling code simpler:
    just use a single code path for calling into code you may want to profile
    and this function determines whether to start profiling.
    """
    if ui.configbool('profiling', 'enabled'):
        with profile(ui):
            yield
    else:
        yield