view tests/test-util.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

# unit tests for mercuril.util utilities
from __future__ import absolute_import

import contextlib
import itertools
import unittest

from mercurial import pycompat, util, utils


@contextlib.contextmanager
def mocktimer(incr=0.1, *additional_targets):
    """Replaces util.timer and additional_targets with a mock

    The timer starts at 0. On each call the time incremented by the value
    of incr. If incr is an iterable, then the time is incremented by the
    next value from that iterable, looping in a cycle when reaching the end.

    additional_targets must be a sequence of (object, attribute_name) tuples;
    the mock is set with setattr(object, attribute_name, mock).

    """
    time = [0]
    try:
        incr = itertools.cycle(incr)
    except TypeError:
        incr = itertools.repeat(incr)

    def timer():
        time[0] += next(incr)
        return time[0]

    # record original values
    orig = util.timer
    additional_origs = [(o, a, getattr(o, a)) for o, a in additional_targets]

    # mock out targets
    util.timer = timer
    for obj, attr in additional_targets:
        setattr(obj, attr, timer)

    try:
        yield
    finally:
        # restore originals
        util.timer = orig
        for args in additional_origs:
            setattr(*args)


# attr.s default factory for util.timedstats.start binds the timer we
# need to mock out.
_start_default = (util.timedcmstats.start.default, 'factory')


@contextlib.contextmanager
def capturestderr():
    """Replace utils.procutil.stderr with a pycompat.bytesio instance

    The instance is made available as the return value of __enter__.

    This contextmanager is reentrant.

    """
    orig = utils.procutil.stderr
    utils.procutil.stderr = pycompat.bytesio()
    try:
        yield utils.procutil.stderr
    finally:
        utils.procutil.stderr = orig


class timedtests(unittest.TestCase):
    def testtimedcmstatsstr(self):
        stats = util.timedcmstats()
        self.assertEqual(str(stats), '<unknown>')
        self.assertEqual(bytes(stats), b'<unknown>')
        stats.elapsed = 12.34
        self.assertEqual(str(stats), pycompat.sysstr(util.timecount(12.34)))
        self.assertEqual(bytes(stats), util.timecount(12.34))

    def testtimedcmcleanexit(self):
        # timestamps 1, 4, elapsed time of 4 - 1 = 3
        with mocktimer([1, 3], _start_default):
            with util.timedcm('pass') as stats:
                # actual context doesn't matter
                pass

        self.assertEqual(stats.start, 1)
        self.assertEqual(stats.elapsed, 3)
        self.assertEqual(stats.level, 1)

    def testtimedcmnested(self):
        # timestamps 1, 3, 6, 10, elapsed times of 6 - 3 = 3 and 10 - 1 = 9
        with mocktimer([1, 2, 3, 4], _start_default):
            with util.timedcm('outer') as outer_stats:
                with util.timedcm('inner') as inner_stats:
                    # actual context doesn't matter
                    pass

        self.assertEqual(outer_stats.start, 1)
        self.assertEqual(outer_stats.elapsed, 9)
        self.assertEqual(outer_stats.level, 1)

        self.assertEqual(inner_stats.start, 3)
        self.assertEqual(inner_stats.elapsed, 3)
        self.assertEqual(inner_stats.level, 2)

    def testtimedcmexception(self):
        # timestamps 1, 4, elapsed time of 4 - 1 = 3
        with mocktimer([1, 3], _start_default):
            try:
                with util.timedcm('exceptional') as stats:
                    raise ValueError()
            except ValueError:
                pass

        self.assertEqual(stats.start, 1)
        self.assertEqual(stats.elapsed, 3)
        self.assertEqual(stats.level, 1)

    def testtimeddecorator(self):
        @util.timed
        def testfunc(callcount=1):
            callcount -= 1
            if callcount:
                testfunc(callcount)

        # timestamps 1, 2, 3, 4, elapsed time of 3 - 2 = 1 and 4 - 1 = 3
        with mocktimer(1, _start_default):
            with capturestderr() as out:
                testfunc(2)

        self.assertEqual(
            out.getvalue(),
            (b'    testfunc: 1.000 s\n' b'  testfunc: 3.000 s\n'),
        )


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)