tests/test-rust-ancestor.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 05 Apr 2024 11:05:54 +0200
changeset 51576 de5bf3fe0233
parent 51244 03fdd4d7b5bd
permissions -rw-r--r--
revset: stop serializing node when using "%ln" Turning hundred of thousand of node from node to hex and back can be slow… what about we stop doing it? In many case were we are using node id we should be using revision id. However this is not a good reason to have a stupidly slow implementation of "%ln". This caught my attention again because the phase discovery during push make an extensive use of "%ln" or huge set. In absolute, that phase discovery probably should use "%ld" and need to improves its algorithmic complexity, but improving "%ln" seems simple and long overdue. This greatly speeds up `hg push` on repository with many drafts. Here are some relevant poulpe benchmarks: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 44.235070 after: 20.416329 (-53.85%, -23.82) ## benchmark.variants.revs = any-100-extra-rev before: 49.234697 after: 26.519829 (-46.14%, -22.71) ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 10.138396 after: 7.750458 (-23.55%, -2.39) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 1.263859 after: 0.700229 (-44.60%, -0.56) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 399.484481 after: 346.5089 (-13.26%, -52.98) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 4.540080 after: 3.401700 (-25.07%, -1.14) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 2.975765 after: 1.870798 (-37.13%, -1.10)

import sys
import unittest

from mercurial.node import wdirrev

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.RustRevlogBasedTestBase):
    """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.parserustindex()
        # 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.parserustindex()
        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.parserustindex()
        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.parserustindex()
        missanc = MissingAncestors(idx, [1])
        revs = {0, 1, 2, 3}
        missanc.removeancestorsfrom(revs)
        self.assertEqual(revs, {2, 3})

    def testrefcount(self):
        idx = self.parserustindex()
        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])

        # the index is not tracked by the GC, hence there is nothing more
        # we can assert to check that it is properly deleted once its refcount
        # drops to 0

    def testgrapherror(self):
        data = (
            revlogtesting.data_non_inlined[: 64 + 27]
            + b'\xf2'
            + revlogtesting.data_non_inlined[64 + 28 :]
        )
        idx = self.parserustindex(data=data)
        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
        idx = self.parserustindex()
        with self.assertRaises(rustext.GraphError) as arc:
            list(AncestorsIterator(idx, [wdirrev], -1, False))

        exc = arc.exception
        self.assertIsInstance(exc, ValueError)
        # rust-cpython issues appropriate str instances for Python 2 and 3
        self.assertEqual(exc.args, ('InvalidRevision', wdirrev))

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


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)