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
# 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(m3.find_unconflicted(), [(0, 2)])
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(m3.find_unconflicted(), [(0, 1), (1, 2)])
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(m3.find_unconflicted(), [(0, 1), (1, 2)])
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(m3.find_unconflicted(), [(0, 1), (2, 3)])
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(m3.find_unconflicted(), [(0, 1), (3, 4)])
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__)