view tests/test-lock.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

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 testinheritlock(self):
        d = tempfile.mkdtemp(dir=encoding.getcwd())
        parentstate = teststate(self, d)
        parentlock = parentstate.makelock()
        parentstate.assertacquirecalled(True)

        # set up lock inheritance
        with parentlock.inherit() as lockname:
            parentstate.assertreleasecalled(True)
            parentstate.assertpostreleasecalled(False)
            parentstate.assertlockexists(True)

            childstate = teststate(self, d, pidoffset=1)
            childlock = childstate.makelock(parentlock=lockname)
            childstate.assertacquirecalled(True)

            childlock.release()
            childstate.assertreleasecalled(True)
            childstate.assertpostreleasecalled(False)
            childstate.assertlockexists(True)

            parentstate.resetacquirefn()

        parentstate.assertacquirecalled(True)

        parentlock.release()
        parentstate.assertreleasecalled(True)
        parentstate.assertpostreleasecalled(True)
        parentstate.assertlockexists(False)

    def testmultilock(self):
        d = tempfile.mkdtemp(dir=encoding.getcwd())
        state0 = teststate(self, d)
        lock0 = state0.makelock()
        state0.assertacquirecalled(True)

        with lock0.inherit() as lock0name:
            state0.assertreleasecalled(True)
            state0.assertpostreleasecalled(False)
            state0.assertlockexists(True)

            state1 = teststate(self, d, pidoffset=1)
            lock1 = state1.makelock(parentlock=lock0name)
            state1.assertacquirecalled(True)

            # from within lock1, acquire another lock
            with lock1.inherit() as lock1name:
                # since the file on disk is lock0's this should have the same
                # name
                self.assertEqual(lock0name, lock1name)

                state2 = teststate(self, d, pidoffset=2)
                lock2 = state2.makelock(parentlock=lock1name)
                state2.assertacquirecalled(True)

                lock2.release()
                state2.assertreleasecalled(True)
                state2.assertpostreleasecalled(False)
                state2.assertlockexists(True)

                state1.resetacquirefn()

            state1.assertacquirecalled(True)

            lock1.release()
            state1.assertreleasecalled(True)
            state1.assertpostreleasecalled(False)
            state1.assertlockexists(True)

        lock0.release()

    def testinheritlockfork(self):
        d = tempfile.mkdtemp(dir=encoding.getcwd())
        parentstate = teststate(self, d)
        parentlock = parentstate.makelock()
        parentstate.assertacquirecalled(True)

        # set up lock inheritance
        with parentlock.inherit() as lockname:
            childstate = teststate(self, d, pidoffset=1)
            childlock = childstate.makelock(parentlock=lockname)
            childstate.assertacquirecalled(True)

            # fork the child lock
            forkchildlock = copy.copy(childlock)
            forkchildlock._pidoffset += 1
            forkchildlock.release()
            childstate.assertreleasecalled(False)
            childstate.assertpostreleasecalled(False)
            childstate.assertlockexists(True)

            # release the child lock
            childlock.release()
            childstate.assertreleasecalled(True)
            childstate.assertpostreleasecalled(False)
            childstate.assertlockexists(True)

        parentlock.release()

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

        def check():
            raise error.LockInheritanceContractViolation('check failed')

        lock = state.makelock(inheritchecker=check)
        state.assertacquirecalled(True)

        with self.assertRaises(error.LockInheritanceContractViolation):
            with lock.inherit():
                pass

        lock.release()

    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__)