view tests/test-simplemerge.py @ 47010:76ae43d5b1db stable

repoview: fix memory leak of filtered repo classes

The leak occurs in long-running server processes with
extensions, and is measured at 110kB per request.

Before this change, the contents of the `_filteredrepotypes`
cache are not properly garbage collected, despite it begin
a `WeakKeyDictionary`.

Extensions have a tendency to generate a new repository class
for each `localrepo` instantiation. Server processes based
on `hgwebdir_mod` will instantiate a new `localrepo` for each
HTTP request that involves a repository.

As a result, with a testing process that repeatedly opens a
repository with several extensions activated
(`topic` notably among them), we see a steady increase in
resident memory of 110kB per repository instantiation before this
change. This is also true, if we call `gc.collect()` at each
instantiation, like `hgwebdir_mod` does, or not.

The cause of the leak is that the *values* aren't weak references.
This change uses `weakref.ref` for the values, and this makes
in our measurements the resident size increase drop to 5kB per
repository instantiation, with no explicit call of `gc.collect()`
at all.
There is currently no reason to believe that this remaining leak
of 5kB is related to or even due to Mercurial core.

We've also seen evidence that `ui.ui` instances weren't properly
garbage collected before the change (with the change, they are).
This could explain why the figures are relatively high.

In theory, the collection of weak references could lead to
much more misses in the cache, so we measured the impact on
the original case that was motivation for introducing that cache
in 7e89bd0cfb86 (see also issue5043): `hg convert` of the
mozilla-central repository. The bad news here is that there is a
major memory leak there, both with and without the present changeset.
There were no more cache misses, and we could see no
more memory leak with this change: the resident size after importing
roughly 100000 changesets was at 12.4GB before, and 12.5GB after.
The small increase is mentioned for completeness only, and we
believe that it should be ignored, at least as long as the main
leak isn't fixed. At less than 1% of the main leak, even finding out
whether it is merely noise would be wasteful.

Original context where this was spotted and first mitigated:
  https://foss.heptapod.net/heptapod/heptapod/-/issues/466

The leak reduction was also obtained in Heptapod inner HTTP server,
which amounts to the same as `hgwebdir_mod` for these questions.

The measurements done with Python 3.9, similar figures seen with 3.8.
More work on our side would be needed to give measurements with 2.7,
because of testing server process does not support it.

# Copyright (C) 2004, 2005 Canonical Ltd
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>.

from __future__ import absolute_import

import unittest
from mercurial import (
    error,
    simplemerge,
    util,
)

from mercurial.utils import stringutil

TestCase = unittest.TestCase
# bzr compatible interface, for the tests
class Merge3(simplemerge.Merge3Text):
    """3-way merge of texts.

    Given BASE, OTHER, THIS, tries to produce a combined text
    incorporating the changes from both BASE->OTHER and BASE->THIS.
    All three will typically be sequences of lines."""

    def __init__(self, base, a, b):
        basetext = b'\n'.join([i.strip(b'\n') for i in base] + [b''])
        atext = b'\n'.join([i.strip(b'\n') for i in a] + [b''])
        btext = b'\n'.join([i.strip(b'\n') for i in b] + [b''])
        if (
            stringutil.binary(basetext)
            or stringutil.binary(atext)
            or stringutil.binary(btext)
        ):
            raise error.Abort(b"don't know how to merge binary files")
        simplemerge.Merge3Text.__init__(
            self, basetext, atext, btext, base, a, b
        )


CantReprocessAndShowBase = simplemerge.CantReprocessAndShowBase


def split_lines(t):
    return util.stringio(t).readlines()


############################################################
# test case data from the gnu diffutils manual
# common base
TZU = split_lines(
    b"""     The Nameless is the origin of Heaven and Earth;
     The named is the mother of all things.

     Therefore let there always be non-being,
       so we may see their subtlety,
     And let there always be being,
       so we may see their outcome.
     The two are the same,
     But after they are produced,
       they have different names.
     They both may be called deep and profound.
     Deeper and more profound,
     The door of all subtleties!
"""
)

LAO = split_lines(
    b"""     The Way that can be told of is not the eternal Way;
     The name that can be named is not the eternal name.
     The Nameless is the origin of Heaven and Earth;
     The Named is the mother of all things.
     Therefore let there always be non-being,
       so we may see their subtlety,
     And let there always be being,
       so we may see their outcome.
     The two are the same,
     But after they are produced,
       they have different names.
"""
)


TAO = split_lines(
    b"""     The Way that can be told of is not the eternal Way;
     The name that can be named is not the eternal name.
     The Nameless is the origin of Heaven and Earth;
     The named is the mother of all things.

     Therefore let there always be non-being,
       so we may see their subtlety,
     And let there always be being,
       so we may see their result.
     The two are the same,
     But after they are produced,
       they have different names.

       -- The Way of Lao-Tzu, tr. Wing-tsit Chan

"""
)

MERGED_RESULT = split_lines(
    b"""\
     The Way that can be told of is not the eternal Way;
     The name that can be named is not the eternal name.
     The Nameless is the origin of Heaven and Earth;
     The Named is the mother of all things.
     Therefore let there always be non-being,
       so we may see their subtlety,
     And let there always be being,
       so we may see their result.
     The two are the same,
     But after they are produced,
       they have different names.\
\n<<<<<<< LAO\
\n=======

       -- The Way of Lao-Tzu, tr. Wing-tsit Chan
\
\n>>>>>>> TAO
"""
)


class TestMerge3(TestCase):
    def log(self, msg):
        pass

    def test_no_changes(self):
        """No conflicts because nothing changed"""
        m3 = Merge3([b'aaa', b'bbb'], [b'aaa', b'bbb'], [b'aaa', b'bbb'])

        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 2, 0, 2, 0, 2), (2, 2, 2, 2, 2, 2)],
        )

        self.assertEqual(list(m3.merge_regions()), [(b'unchanged', 0, 2)])

        self.assertEqual(
            list(m3.merge_groups()), [(b'unchanged', [b'aaa', b'bbb'])]
        )

    def test_front_insert(self):
        m3 = Merge3([b'zz'], [b'aaa', b'bbb', b'zz'], [b'zz'])

        # todo: should use a sentinel at end as from get_matching_blocks
        # to match without zz
        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 1, 2, 3, 0, 1), (1, 1, 3, 3, 1, 1)],
        )

        self.assertEqual(
            list(m3.merge_regions()), [(b'a', 0, 2), (b'unchanged', 0, 1)]
        )

        self.assertEqual(
            list(m3.merge_groups()),
            [(b'a', [b'aaa', b'bbb']), (b'unchanged', [b'zz'])],
        )

    def test_null_insert(self):
        m3 = Merge3([], [b'aaa', b'bbb'], [])
        # todo: should use a sentinel at end as from get_matching_blocks
        # to match without zz
        self.assertEqual(list(m3.find_sync_regions()), [(0, 0, 2, 2, 0, 0)])

        self.assertEqual(list(m3.merge_regions()), [(b'a', 0, 2)])

        self.assertEqual(list(m3.merge_lines()), [b'aaa', b'bbb'])

    def test_no_conflicts(self):
        """No conflicts because only one side changed"""
        m3 = Merge3(
            [b'aaa', b'bbb'], [b'aaa', b'111', b'bbb'], [b'aaa', b'bbb']
        )

        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 1, 2), (2, 2, 3, 3, 2, 2)],
        )

        self.assertEqual(
            list(m3.merge_regions()),
            [(b'unchanged', 0, 1), (b'a', 1, 2), (b'unchanged', 1, 2)],
        )

    def test_append_a(self):
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'bbb\n', b'222\n'],
            [b'aaa\n', b'bbb\n'],
        )

        self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n')

    def test_append_b(self):
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'bbb\n', b'222\n'],
        )

        self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n')

    def test_append_agreement(self):
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'bbb\n', b'222\n'],
            [b'aaa\n', b'bbb\n', b'222\n'],
        )

        self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n')

    def test_append_clash(self):
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'bbb\n', b'222\n'],
            [b'aaa\n', b'bbb\n', b'333\n'],
        )

        ml = m3.merge_lines(
            name_a=b'a',
            name_b=b'b',
            start_marker=b'<<',
            mid_marker=b'--',
            end_marker=b'>>',
        )
        self.assertEqual(
            b''.join(ml),
            b'aaa\n' b'bbb\n' b'<< a\n' b'222\n' b'--\n' b'333\n' b'>> b\n',
        )

    def test_insert_agreement(self):
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'222\n', b'bbb\n'],
            [b'aaa\n', b'222\n', b'bbb\n'],
        )

        ml = m3.merge_lines(
            name_a=b'a',
            name_b=b'b',
            start_marker=b'<<',
            mid_marker=b'--',
            end_marker=b'>>',
        )
        self.assertEqual(b''.join(ml), b'aaa\n222\nbbb\n')

    def test_insert_clash(self):
        """Both try to insert lines in the same place."""
        m3 = Merge3(
            [b'aaa\n', b'bbb\n'],
            [b'aaa\n', b'111\n', b'bbb\n'],
            [b'aaa\n', b'222\n', b'bbb\n'],
        )

        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 2, 3), (2, 2, 3, 3, 3, 3)],
        )

        self.assertEqual(
            list(m3.merge_regions()),
            [
                (b'unchanged', 0, 1),
                (b'conflict', 1, 1, 1, 2, 1, 2),
                (b'unchanged', 1, 2),
            ],
        )

        self.assertEqual(
            list(m3.merge_groups()),
            [
                (b'unchanged', [b'aaa\n']),
                (b'conflict', [], [b'111\n'], [b'222\n']),
                (b'unchanged', [b'bbb\n']),
            ],
        )

        ml = m3.merge_lines(
            name_a=b'a',
            name_b=b'b',
            start_marker=b'<<',
            mid_marker=b'--',
            end_marker=b'>>',
        )
        self.assertEqual(
            b''.join(ml),
            b'''aaa
<< a
111
--
222
>> b
bbb
''',
        )

    def test_replace_clash(self):
        """Both try to insert lines in the same place."""
        m3 = Merge3(
            [b'aaa', b'000', b'bbb'],
            [b'aaa', b'111', b'bbb'],
            [b'aaa', b'222', b'bbb'],
        )

        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 1, 0, 1, 0, 1), (2, 3, 2, 3, 2, 3), (3, 3, 3, 3, 3, 3)],
        )

    def test_replace_multi(self):
        """Replacement with regions of different size."""
        m3 = Merge3(
            [b'aaa', b'000', b'000', b'bbb'],
            [b'aaa', b'111', b'111', b'111', b'bbb'],
            [b'aaa', b'222', b'222', b'222', b'222', b'bbb'],
        )

        self.assertEqual(
            list(m3.find_sync_regions()),
            [(0, 1, 0, 1, 0, 1), (3, 4, 4, 5, 5, 6), (4, 4, 5, 5, 6, 6)],
        )

    def test_merge_poem(self):
        """Test case from diff3 manual"""
        m3 = Merge3(TZU, LAO, TAO)
        ml = list(m3.merge_lines(b'LAO', b'TAO'))
        self.log(b'merge result:')
        self.log(b''.join(ml))
        self.assertEqual(ml, MERGED_RESULT)

    def test_binary(self):
        with self.assertRaises(error.Abort):
            Merge3([b'\x00'], [b'a'], [b'b'])

    def test_dos_text(self):
        base_text = b'a\r\n'
        this_text = b'b\r\n'
        other_text = b'c\r\n'
        m3 = Merge3(
            base_text.splitlines(True),
            other_text.splitlines(True),
            this_text.splitlines(True),
        )
        m_lines = m3.merge_lines(b'OTHER', b'THIS')
        self.assertEqual(
            b'<<<<<<< OTHER\r\nc\r\n=======\r\nb\r\n'
            b'>>>>>>> THIS\r\n'.splitlines(True),
            list(m_lines),
        )

    def test_mac_text(self):
        base_text = b'a\r'
        this_text = b'b\r'
        other_text = b'c\r'
        m3 = Merge3(
            base_text.splitlines(True),
            other_text.splitlines(True),
            this_text.splitlines(True),
        )
        m_lines = m3.merge_lines(b'OTHER', b'THIS')
        self.assertEqual(
            b'<<<<<<< OTHER\rc\r=======\rb\r'
            b'>>>>>>> THIS\r'.splitlines(True),
            list(m_lines),
        )


if __name__ == '__main__':
    import silenttestrunner

    silenttestrunner.main(__name__)