view tests/test-rust-discovery.py @ 51977:42a116f1cdc1

branchmap-v3: introduce a "stop_rev" argument to `headsrevs` The `headsrevs` method of the revlog already have a `revs` argument to compute the headrevs of a limited set of heads. However, it disable the use of the native compiled code to compute the heads, which slows down the branchmap v3 code a lot. The branchmap v3 usage is actually quite constrained as we will always only ignores a part at the top of the graph. So we could be significantly faster. We start by making small change to the python side to improve the situation and introduce the new API. More collaboration with the native code are coming later. This massively speedup operation and close most of the remaining gaps between branchmap-v3 and branchmap-v2. especially on repository with many revs like mozilla-try. A small overhead remains mostly because the `headrevs` logic currently has some inefficiently. We will look into them from there. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.368769 (+57.79%, +0.14) branch-v3 after: 0.239857 (+2.63%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.372460 (+58.34%, +0.14) branch-v3 after: 0.240972 (+2.44%, +0.01) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.318907 (+24.78%, +0.06) branch-v3 after: 0.268560 (+5.08%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.349752 (+3.17%, +0.01) branch-v3 after: 0.349389 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.354300 (+2.24%, +0.01) branch-v3 after: 0.355661 (+2.64%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.396293 (+4.23%, +0.02) branch-v3 after: 0.408851 (+7.54%, +0.03) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.424769 (+3.06%, +0.01) branch-v3 after: 0.427782 (+3.79%, +0.02) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.421796 (+2.28%, +0.01) branch-v3 after: 0.422354 (+2.41%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.443849 (+3.34%, +0.01) branch-v3 after: 0.443197 (+3.19%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.234055 (+83.18%, +2.83) branch-v3 after: 3.819477 (+12.23%, +0.42) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.307813 (+82.58%, +2.85) branch-v3 after: 3.590284 (+3.92%, +0.14) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.176076 (+49.36%, +1.71) branch-v3 after: 3.633278 (+4.84%, +0.17)
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 03 Sep 2024 11:11:17 +0200
parents 0b81440e2a73
children
line wrap: on
line source

import unittest

from mercurial import policy
from mercurial.testing import revlog as revlogtesting

PartialDiscovery = policy.importrust('discovery', member='PartialDiscovery')

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

# picked from test-parse-index2, copied rather than imported
# so that it stays stable even if test-parse-index2 changes or disappears.
data_non_inlined = (
    b'\x00\x00\x00\x01\x00\x00\x00\x00\x00\x01D\x19'
    b'\x00\x07e\x12\x00\x00\x00\x00\x00\x00\x00\x00\xff\xff\xff\xff'
    b'\xff\xff\xff\xff\xd1\xf4\xbb\xb0\xbe\xfc\x13\xbd\x8c\xd3\x9d'
    b'\x0f\xcd\xd9;\x8c\x07\x8cJ/\x00\x00\x00\x00\x00\x00\x00\x00\x00'
    b'\x00\x00\x00\x00\x00\x00\x01D\x19\x00\x00\x00\x00\x00\xdf\x00'
    b'\x00\x01q\x00\x00\x00\x01\x00\x00\x00\x01\x00\x00\x00\x00\xff'
    b'\xff\xff\xff\xc1\x12\xb9\x04\x96\xa4Z1t\x91\xdfsJ\x90\xf0\x9bh'
    b'\x07l&\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
    b'\x00\x01D\xf8\x00\x00\x00\x00\x01\x1b\x00\x00\x01\xb8\x00\x00'
    b'\x00\x01\x00\x00\x00\x02\x00\x00\x00\x01\xff\xff\xff\xff\x02\n'
    b'\x0e\xc6&\xa1\x92\xae6\x0b\x02i\xfe-\xe5\xbao\x05\xd1\xe7\x00'
    b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01F'
    b'\x13\x00\x00\x00\x00\x01\xec\x00\x00\x03\x06\x00\x00\x00\x01'
    b'\x00\x00\x00\x03\x00\x00\x00\x02\xff\xff\xff\xff\x12\xcb\xeby1'
    b'\xb6\r\x98B\xcb\x07\xbd`\x8f\x92\xd9\xc4\x84\xbdK\x00\x00\x00'
    b'\x00\x00\x00\x00\x00\x00\x00\x00\x00'
)


class fakechangelog:
    def __init__(self, idx):
        self.index = idx


class fakerepo:
    def __init__(self, idx):
        """Just make so that self.changelog.index is the given idx."""
        self.changelog = fakechangelog(idx)


@unittest.skipIf(
    PartialDiscovery is None or cparsers is None,
    "rustext or the C Extension parsers module "
    "discovery relies on is not available",
)
class rustdiscoverytest(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 provided
    methods. Hence the very simple embedded index data is good enough.

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

    def parseindex(self):
        return self.parserustindex(data=data_non_inlined)

    def repo(self):
        return fakerepo(self.parseindex())

    def testindex(self):
        idx = self.parseindex()
        # checking our assumptions 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)},
        )

    def testaddcommonsmissings(self):
        disco = PartialDiscovery(self.repo(), [3], True)
        self.assertFalse(disco.hasinfo())
        self.assertFalse(disco.iscomplete())

        disco.addcommons([1])
        self.assertTrue(disco.hasinfo())
        self.assertFalse(disco.iscomplete())

        disco.addmissings([2])
        self.assertTrue(disco.hasinfo())
        self.assertTrue(disco.iscomplete())

        self.assertEqual(disco.commonheads(), {1})

    def testaddmissingsstats(self):
        disco = PartialDiscovery(self.repo(), [3], True)
        self.assertIsNone(disco.stats()['undecided'], None)

        disco.addmissings([2])
        self.assertEqual(disco.stats()['undecided'], 2)

    def testaddinfocommonfirst(self):
        disco = PartialDiscovery(self.repo(), [3], True)
        disco.addinfo([(1, True), (2, False)])
        self.assertTrue(disco.hasinfo())
        self.assertTrue(disco.iscomplete())
        self.assertEqual(disco.commonheads(), {1})

    def testaddinfomissingfirst(self):
        disco = PartialDiscovery(self.repo(), [3], True)
        disco.addinfo([(2, False), (1, True)])
        self.assertTrue(disco.hasinfo())
        self.assertTrue(disco.iscomplete())
        self.assertEqual(disco.commonheads(), {1})

    def testinitnorandom(self):
        PartialDiscovery(self.repo(), [3], True, randomize=False)


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)