view tests/test-util.py @ 46607:e9901d01d135

revlog: add a mechanism to verify expected file position before appending If someone uses `hg debuglocks`, or some non-hg process writes to the .hg directory without respecting the locks, or if the repo's on a networked filesystem, it's possible for the revlog code to write out corrupted data. The form of this corruption can vary depending on what data was written and how that happened. We are in the "networked filesystem" case (though I've had users also do this to themselves with the "`hg debuglocks`" scenario), and most often see this with the changelog. What ends up happening is we produce two items (let's call them rev1 and rev2) in the .i file that have the same linkrev, baserev, and offset into the .d file, while the data in the .d file is appended properly. rev2's compressed_size is accurate for rev2, but when we go to decompress the data in the .d file, we use the offset that's recorded in the index file, which is the same as rev1, and attempt to decompress rev2.compressed_size bytes of rev1's data. This usually does not succeed. :) When using inline data, this also fails, though I haven't investigated why too closely. This shows up as a "patch decode" error. I believe what's happening there is that we're basically ignoring the offset field, getting the data properly, but since baserev != rev, it thinks this is a delta based on rev (instead of a full text) and can't actually apply it as such. For now, I'm going to make this an optional component and default it to entirely off. I may increase the default severity of this in the future, once I've enabled it for my users and we gain more experience with it. Luckily, most of my users have a versioned filesystem and can roll back to before the corruption has been written, it's just a hassle to do so and not everyone knows how (so it's a support burden). Users on other filesystems will not have that luxury, and this can cause them to have a corrupted repository that they are unlikely to know how to resolve, and they'll see this as a data-loss event. Refusing to create the corruption is a much better user experience. This mechanism is not perfect. There may be false-negatives (racy writes that are not detected). There should not be any false-positives (non-racy writes that are detected as such). This is not a mechanism that makes putting a repo on a networked filesystem "safe" or "supported", just *less* likely to cause corruption. Differential Revision: https://phab.mercurial-scm.org/D9952
author Kyle Lippincott <spectral@google.com>
date Wed, 03 Feb 2021 16:33:10 -0800
parents 2372284d9457
children 5aafc3c5bdec
line wrap: on
line source

# unit tests for mercuril.util utilities
from __future__ import absolute_import

import contextlib
import itertools
import unittest

from mercurial import pycompat, util, utils


@contextlib.contextmanager
def mocktimer(incr=0.1, *additional_targets):
    """Replaces util.timer and additional_targets with a mock

    The timer starts at 0. On each call the time incremented by the value
    of incr. If incr is an iterable, then the time is incremented by the
    next value from that iterable, looping in a cycle when reaching the end.

    additional_targets must be a sequence of (object, attribute_name) tuples;
    the mock is set with setattr(object, attribute_name, mock).

    """
    time = [0]
    try:
        incr = itertools.cycle(incr)
    except TypeError:
        incr = itertools.repeat(incr)

    def timer():
        time[0] += next(incr)
        return time[0]

    # record original values
    orig = util.timer
    additional_origs = [(o, a, getattr(o, a)) for o, a in additional_targets]

    # mock out targets
    util.timer = timer
    for obj, attr in additional_targets:
        setattr(obj, attr, timer)

    try:
        yield
    finally:
        # restore originals
        util.timer = orig
        for args in additional_origs:
            setattr(*args)


# attr.s default factory for util.timedstats.start binds the timer we
# need to mock out.
_start_default = (util.timedcmstats.start.default, 'factory')


@contextlib.contextmanager
def capturestderr():
    """Replace utils.procutil.stderr with a pycompat.bytesio instance

    The instance is made available as the return value of __enter__.

    This contextmanager is reentrant.

    """
    orig = utils.procutil.stderr
    utils.procutil.stderr = pycompat.bytesio()
    try:
        yield utils.procutil.stderr
    finally:
        utils.procutil.stderr = orig


class timedtests(unittest.TestCase):
    def testtimedcmstatsstr(self):
        stats = util.timedcmstats()
        self.assertEqual(str(stats), '<unknown>')
        self.assertEqual(bytes(stats), b'<unknown>')
        stats.elapsed = 12.34
        self.assertEqual(str(stats), pycompat.sysstr(util.timecount(12.34)))
        self.assertEqual(bytes(stats), util.timecount(12.34))

    def testtimedcmcleanexit(self):
        # timestamps 1, 4, elapsed time of 4 - 1 = 3
        with mocktimer([1, 3], _start_default):
            with util.timedcm('pass') as stats:
                # actual context doesn't matter
                pass

        self.assertEqual(stats.start, 1)
        self.assertEqual(stats.elapsed, 3)
        self.assertEqual(stats.level, 1)

    def testtimedcmnested(self):
        # timestamps 1, 3, 6, 10, elapsed times of 6 - 3 = 3 and 10 - 1 = 9
        with mocktimer([1, 2, 3, 4], _start_default):
            with util.timedcm('outer') as outer_stats:
                with util.timedcm('inner') as inner_stats:
                    # actual context doesn't matter
                    pass

        self.assertEqual(outer_stats.start, 1)
        self.assertEqual(outer_stats.elapsed, 9)
        self.assertEqual(outer_stats.level, 1)

        self.assertEqual(inner_stats.start, 3)
        self.assertEqual(inner_stats.elapsed, 3)
        self.assertEqual(inner_stats.level, 2)

    def testtimedcmexception(self):
        # timestamps 1, 4, elapsed time of 4 - 1 = 3
        with mocktimer([1, 3], _start_default):
            try:
                with util.timedcm('exceptional') as stats:
                    raise ValueError()
            except ValueError:
                pass

        self.assertEqual(stats.start, 1)
        self.assertEqual(stats.elapsed, 3)
        self.assertEqual(stats.level, 1)

    def testtimeddecorator(self):
        @util.timed
        def testfunc(callcount=1):
            callcount -= 1
            if callcount:
                testfunc(callcount)

        # timestamps 1, 2, 3, 4, elapsed time of 3 - 2 = 1 and 4 - 1 = 3
        with mocktimer(1, _start_default):
            with capturestderr() as out:
                testfunc(2)

        self.assertEqual(
            out.getvalue(),
            (b'    testfunc: 1.000 s\n' b'  testfunc: 3.000 s\n'),
        )


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)