view tests/test-rust-discovery.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 unittest

from mercurial import policy

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(object):
    def __init__(self, idx):
        self.index = idx


class fakerepo(object):
    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(unittest.TestCase):
    """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 cparsers.parse_index2(data_non_inlined, False)[0]

    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__)