view tests/test-rust-ancestor.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
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 8a8305f557d0
children 59fa3890d40a
line wrap: on
line source

from __future__ import absolute_import
import sys
import unittest

from mercurial import (
    error,
    node,
)

from mercurial.testing import revlog as revlogtesting

try:
    from mercurial import rustext

    rustext.__name__  # trigger immediate actual import
except ImportError:
    rustext = None
else:
    # this would fail already without appropriate ancestor.__package__
    from mercurial.rustext.ancestor import (
        AncestorsIterator,
        LazyAncestors,
        MissingAncestors,
    )
    from mercurial.rustext import dagop

try:
    from mercurial.cext import parsers as cparsers
except ImportError:
    cparsers = None


@unittest.skipIf(
    rustext is None,
    'The Rust version of the "ancestor" module is not available. It is needed'
    ' for this test.',
)
@unittest.skipIf(
    rustext is None,
    'The Rust or C version of the "parsers" module, which the "ancestor" module'
    ' relies on, is not available.',
)
class rustancestorstest(revlogtesting.RevlogBasedTestBase):
    """Test the correctness of binding to Rust code.

    This test is merely for the binding to Rust itself: extraction of
    Python variable, giving back the results etc.

    It is not meant to test the algorithmic correctness of the operations
    on ancestors it provides. Hence the very simple embedded index data is
    good enough.

    Algorithmic correctness is asserted by the Rust unit tests.
    """

    def testiteratorrevlist(self):
        idx = self.parseindex()
        # checking test assumption about the index binary data:
        self.assertEqual(
            {i: (r[5], r[6]) for i, r in enumerate(idx)},
            {0: (-1, -1), 1: (0, -1), 2: (1, -1), 3: (2, -1)},
        )
        ait = AncestorsIterator(idx, [3], 0, True)
        self.assertEqual([r for r in ait], [3, 2, 1, 0])

        ait = AncestorsIterator(idx, [3], 0, False)
        self.assertEqual([r for r in ait], [2, 1, 0])

    def testlazyancestors(self):
        idx = self.parseindex()
        start_count = sys.getrefcount(idx)  # should be 2 (see Python doc)
        self.assertEqual(
            {i: (r[5], r[6]) for i, r in enumerate(idx)},
            {0: (-1, -1), 1: (0, -1), 2: (1, -1), 3: (2, -1)},
        )
        lazy = LazyAncestors(idx, [3], 0, True)
        # we have two more references to the index:
        # - in its inner iterator for __contains__ and __bool__
        # - in the LazyAncestors instance itself (to spawn new iterators)
        self.assertEqual(sys.getrefcount(idx), start_count + 2)

        self.assertTrue(2 in lazy)
        self.assertTrue(bool(lazy))
        self.assertEqual(list(lazy), [3, 2, 1, 0])
        # a second time to validate that we spawn new iterators
        self.assertEqual(list(lazy), [3, 2, 1, 0])

        # now let's watch the refcounts closer
        ait = iter(lazy)
        self.assertEqual(sys.getrefcount(idx), start_count + 3)
        del ait
        self.assertEqual(sys.getrefcount(idx), start_count + 2)
        del lazy
        self.assertEqual(sys.getrefcount(idx), start_count)

        # let's check bool for an empty one
        self.assertFalse(LazyAncestors(idx, [0], 0, False))

    def testmissingancestors(self):
        idx = self.parseindex()
        missanc = MissingAncestors(idx, [1])
        self.assertTrue(missanc.hasbases())
        self.assertEqual(missanc.missingancestors([3]), [2, 3])
        missanc.addbases({2})
        self.assertEqual(missanc.bases(), {1, 2})
        self.assertEqual(missanc.missingancestors([3]), [3])
        self.assertEqual(missanc.basesheads(), {2})

    def testmissingancestorsremove(self):
        idx = self.parseindex()
        missanc = MissingAncestors(idx, [1])
        revs = {0, 1, 2, 3}
        missanc.removeancestorsfrom(revs)
        self.assertEqual(revs, {2, 3})

    def testrefcount(self):
        idx = self.parseindex()
        start_count = sys.getrefcount(idx)

        # refcount increases upon iterator init...
        ait = AncestorsIterator(idx, [3], 0, True)
        self.assertEqual(sys.getrefcount(idx), start_count + 1)
        self.assertEqual(next(ait), 3)

        # and decreases once the iterator is removed
        del ait
        self.assertEqual(sys.getrefcount(idx), start_count)

        # and removing ref to the index after iterator init is no issue
        ait = AncestorsIterator(idx, [3], 0, True)
        del idx
        self.assertEqual(list(ait), [3, 2, 1, 0])

    def testgrapherror(self):
        data = (
            revlogtesting.data_non_inlined[: 64 + 27]
            + b'\xf2'
            + revlogtesting.data_non_inlined[64 + 28 :]
        )
        idx = cparsers.parse_index2(data, False)[0]
        with self.assertRaises(rustext.GraphError) as arc:
            AncestorsIterator(idx, [1], -1, False)
        exc = arc.exception
        self.assertIsInstance(exc, ValueError)
        # rust-cpython issues appropriate str instances for Python 2 and 3
        self.assertEqual(exc.args, ('ParentOutOfRange', 1))

    def testwdirunsupported(self):
        # trying to access ancestors of the working directory raises
        # WdirUnsupported directly
        idx = self.parseindex()
        with self.assertRaises(error.WdirUnsupported):
            list(AncestorsIterator(idx, [node.wdirrev], -1, False))

    def testheadrevs(self):
        idx = self.parseindex()
        self.assertEqual(dagop.headrevs(idx, [1, 2, 3]), {3})


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)