view tests/test-wireproto-framing.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, print_function

import unittest

from mercurial import (
    util,
    wireprotoframing as framing,
)

ffs = framing.makeframefromhumanstring


class FrameHumanStringTests(unittest.TestCase):
    def testbasic(self):
        self.assertEqual(
            ffs(b'1 1 0 1 0 '), b'\x00\x00\x00\x01\x00\x01\x00\x10'
        )

        self.assertEqual(
            ffs(b'2 4 0 1 0 '), b'\x00\x00\x00\x02\x00\x04\x00\x10'
        )

        self.assertEqual(
            ffs(b'2 4 0 1 0 foo'), b'\x03\x00\x00\x02\x00\x04\x00\x10foo'
        )

    def testcborint(self):
        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:15'), b'\x01\x00\x00\x01\x00\x01\x00\x10\x0f'
        )

        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:42'), b'\x02\x00\x00\x01\x00\x01\x00\x10\x18*'
        )

        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:1048576'),
            b'\x05\x00\x00\x01\x00\x01\x00\x10\x1a' b'\x00\x10\x00\x00',
        )

        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:0'), b'\x01\x00\x00\x01\x00\x01\x00\x10\x00'
        )

        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:-1'), b'\x01\x00\x00\x01\x00\x01\x00\x10 '
        )

        self.assertEqual(
            ffs(b'1 1 0 1 0 cbor:-342542'),
            b'\x05\x00\x00\x01\x00\x01\x00\x10:\x00\x05:\r',
        )

    def testcborstrings(self):
        self.assertEqual(
            ffs(b"1 1 0 1 0 cbor:b'foo'"),
            b'\x04\x00\x00\x01\x00\x01\x00\x10Cfoo',
        )

    def testcborlists(self):
        self.assertEqual(
            ffs(b"1 1 0 1 0 cbor:[None, True, False, 42, b'foo']"),
            b'\n\x00\x00\x01\x00\x01\x00\x10\x85\xf6\xf5\xf4' b'\x18*Cfoo',
        )

    def testcbordicts(self):
        self.assertEqual(
            ffs(b"1 1 0 1 0 " b"cbor:{b'foo': b'val1', b'bar': b'val2'}"),
            b'\x13\x00\x00\x01\x00\x01\x00\x10\xa2' b'CbarDval2CfooDval1',
        )


class FrameTests(unittest.TestCase):
    def testdataexactframesize(self):
        data = util.bytesio(b'x' * framing.DEFAULT_MAX_FRAME_SIZE)

        stream = framing.stream(1)
        frames = list(
            framing.createcommandframes(stream, 1, b'command', {}, data)
        )
        self.assertEqual(
            frames,
            [
                ffs(
                    b'1 1 stream-begin command-request new|have-data '
                    b"cbor:{b'name': b'command'}"
                ),
                ffs(b'1 1 0 command-data continuation %s' % data.getvalue()),
                ffs(b'1 1 0 command-data eos '),
            ],
        )

    def testdatamultipleframes(self):
        data = util.bytesio(b'x' * (framing.DEFAULT_MAX_FRAME_SIZE + 1))

        stream = framing.stream(1)
        frames = list(
            framing.createcommandframes(stream, 1, b'command', {}, data)
        )
        self.assertEqual(
            frames,
            [
                ffs(
                    b'1 1 stream-begin command-request new|have-data '
                    b"cbor:{b'name': b'command'}"
                ),
                ffs(
                    b'1 1 0 command-data continuation %s'
                    % (b'x' * framing.DEFAULT_MAX_FRAME_SIZE)
                ),
                ffs(b'1 1 0 command-data eos x'),
            ],
        )

    def testargsanddata(self):
        data = util.bytesio(b'x' * 100)

        stream = framing.stream(1)
        frames = list(
            framing.createcommandframes(
                stream,
                1,
                b'command',
                {
                    b'key1': b'key1value',
                    b'key2': b'key2value',
                    b'key3': b'key3value',
                },
                data,
            )
        )

        self.assertEqual(
            frames,
            [
                ffs(
                    b'1 1 stream-begin command-request new|have-data '
                    b"cbor:{b'name': b'command', b'args': {b'key1': b'key1value', "
                    b"b'key2': b'key2value', b'key3': b'key3value'}}"
                ),
                ffs(b'1 1 0 command-data eos %s' % data.getvalue()),
            ],
        )

    if not getattr(unittest.TestCase, 'assertRaisesRegex', False):
        # Python 3.7 deprecates the regex*p* version, but 2.7 lacks
        # the regex version.
        assertRaisesRegex = (  # camelcase-required
            unittest.TestCase.assertRaisesRegexp
        )

    def testtextoutputformattingstringtype(self):
        """Formatting string must be bytes."""
        with self.assertRaisesRegex(ValueError, 'must use bytes formatting '):
            list(
                framing.createtextoutputframe(
                    None, 1, [(b'foo'.decode('ascii'), [], [])]
                )
            )

    def testtextoutputargumentbytes(self):
        with self.assertRaisesRegex(ValueError, 'must use bytes for argument'):
            list(
                framing.createtextoutputframe(
                    None, 1, [(b'foo', [b'foo'.decode('ascii')], [])]
                )
            )

    def testtextoutputlabelbytes(self):
        with self.assertRaisesRegex(ValueError, 'must use bytes for labels'):
            list(
                framing.createtextoutputframe(
                    None, 1, [(b'foo', [], [b'foo'.decode('ascii')])]
                )
            )

    def testtextoutput1simpleatom(self):
        stream = framing.stream(1)
        val = list(framing.createtextoutputframe(stream, 1, [(b'foo', [], [])]))

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo'}]"
                ),
            ],
        )

    def testtextoutput2simpleatoms(self):
        stream = framing.stream(1)
        val = list(
            framing.createtextoutputframe(
                stream, 1, [(b'foo', [], []), (b'bar', [], []),]
            )
        )

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo'}, {b'msg': b'bar'}]"
                )
            ],
        )

    def testtextoutput1arg(self):
        stream = framing.stream(1)
        val = list(
            framing.createtextoutputframe(
                stream, 1, [(b'foo %s', [b'val1'], []),]
            )
        )

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo %s', b'args': [b'val1']}]"
                )
            ],
        )

    def testtextoutput2arg(self):
        stream = framing.stream(1)
        val = list(
            framing.createtextoutputframe(
                stream, 1, [(b'foo %s %s', [b'val', b'value'], []),]
            )
        )

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo %s %s', b'args': [b'val', b'value']}]"
                )
            ],
        )

    def testtextoutput1label(self):
        stream = framing.stream(1)
        val = list(
            framing.createtextoutputframe(
                stream, 1, [(b'foo', [], [b'label']),]
            )
        )

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo', b'labels': [b'label']}]"
                )
            ],
        )

    def testargandlabel(self):
        stream = framing.stream(1)
        val = list(
            framing.createtextoutputframe(
                stream, 1, [(b'foo %s', [b'arg'], [b'label']),]
            )
        )

        self.assertEqual(
            val,
            [
                ffs(
                    b'1 1 stream-begin text-output 0 '
                    b"cbor:[{b'msg': b'foo %s', b'args': [b'arg'], "
                    b"b'labels': [b'label']}]"
                )
            ],
        )


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)