view tests/test-lock.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

from __future__ import absolute_import

import copy
import errno
import tempfile
import types
import unittest

import silenttestrunner

from mercurial import (
    encoding,
    error,
    lock,
    vfs as vfsmod,
)

testlockname = b'testlock'

# work around http://bugs.python.org/issue1515
if types.MethodType not in copy._deepcopy_dispatch:

    def _deepcopy_method(x, memo):
        return type(x)(x.__func__, copy.deepcopy(x.__self__, memo), x.im_class)

    copy._deepcopy_dispatch[types.MethodType] = _deepcopy_method


class lockwrapper(lock.lock):
    def __init__(self, pidoffset, *args, **kwargs):
        # lock.lock.__init__() calls lock(), so the pidoffset assignment needs
        # to be earlier
        self._pidoffset = pidoffset
        super(lockwrapper, self).__init__(*args, **kwargs)

    def _getpid(self):
        return super(lockwrapper, self)._getpid() + self._pidoffset


class teststate(object):
    def __init__(self, testcase, dir, pidoffset=0):
        self._testcase = testcase
        self._acquirecalled = False
        self._releasecalled = False
        self._postreleasecalled = False
        self.vfs = vfsmod.vfs(dir, audit=False)
        self._pidoffset = pidoffset

    def makelock(self, *args, **kwargs):
        l = lockwrapper(
            self._pidoffset,
            self.vfs,
            testlockname,
            releasefn=self.releasefn,
            acquirefn=self.acquirefn,
            *args,
            **kwargs
        )
        l.postrelease.append(self.postreleasefn)
        return l

    def acquirefn(self):
        self._acquirecalled = True

    def releasefn(self):
        self._releasecalled = True

    def postreleasefn(self, success):
        self._postreleasecalled = True

    def assertacquirecalled(self, called):
        self._testcase.assertEqual(
            self._acquirecalled,
            called,
            'expected acquire to be %s but was actually %s'
            % (
                self._tocalled(called),
                self._tocalled(self._acquirecalled),
            ),
        )

    def resetacquirefn(self):
        self._acquirecalled = False

    def assertreleasecalled(self, called):
        self._testcase.assertEqual(
            self._releasecalled,
            called,
            'expected release to be %s but was actually %s'
            % (
                self._tocalled(called),
                self._tocalled(self._releasecalled),
            ),
        )

    def assertpostreleasecalled(self, called):
        self._testcase.assertEqual(
            self._postreleasecalled,
            called,
            'expected postrelease to be %s but was actually %s'
            % (
                self._tocalled(called),
                self._tocalled(self._postreleasecalled),
            ),
        )

    def assertlockexists(self, exists):
        actual = self.vfs.lexists(testlockname)
        self._testcase.assertEqual(
            actual,
            exists,
            'expected lock to %s but actually did %s'
            % (
                self._toexists(exists),
                self._toexists(actual),
            ),
        )

    def _tocalled(self, called):
        if called:
            return 'called'
        else:
            return 'not called'

    def _toexists(self, exists):
        if exists:
            return 'exist'
        else:
            return 'not exist'


class testlock(unittest.TestCase):
    def testlock(self):
        state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
        lock = state.makelock()
        state.assertacquirecalled(True)
        lock.release()
        state.assertreleasecalled(True)
        state.assertpostreleasecalled(True)
        state.assertlockexists(False)

    def testrecursivelock(self):
        state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
        lock = state.makelock()
        state.assertacquirecalled(True)

        state.resetacquirefn()
        lock.lock()
        # recursive lock should not call acquirefn again
        state.assertacquirecalled(False)

        lock.release()  # brings lock refcount down from 2 to 1
        state.assertreleasecalled(False)
        state.assertpostreleasecalled(False)
        state.assertlockexists(True)

        lock.release()  # releases the lock
        state.assertreleasecalled(True)
        state.assertpostreleasecalled(True)
        state.assertlockexists(False)

    def testlockfork(self):
        state = teststate(self, tempfile.mkdtemp(dir=encoding.getcwd()))
        lock = state.makelock()
        state.assertacquirecalled(True)

        # fake a fork
        forklock = copy.copy(lock)
        forklock._pidoffset = 1
        forklock.release()
        state.assertreleasecalled(False)
        state.assertpostreleasecalled(False)
        state.assertlockexists(True)

        # release the actual lock
        lock.release()
        state.assertreleasecalled(True)
        state.assertpostreleasecalled(True)
        state.assertlockexists(False)

    def testfrequentlockunlock(self):
        """This tests whether lock acquisition fails as expected, even if
        (1) lock can't be acquired (makelock fails by EEXIST), and
        (2) locker info can't be read in (readlock fails by ENOENT) while
        retrying 5 times.
        """

        d = tempfile.mkdtemp(dir=encoding.getcwd())
        state = teststate(self, d)

        def emulatefrequentlock(*args):
            raise OSError(errno.EEXIST, "File exists")

        def emulatefrequentunlock(*args):
            raise OSError(errno.ENOENT, "No such file or directory")

        state.vfs.makelock = emulatefrequentlock
        state.vfs.readlock = emulatefrequentunlock

        try:
            state.makelock(timeout=0)
            self.fail("unexpected lock acquisition")
        except error.LockHeld as why:
            self.assertTrue(why.errno == errno.ETIMEDOUT)
            self.assertTrue(why.locker == b"")
            state.assertlockexists(False)


if __name__ == '__main__':
    silenttestrunner.main(__name__)