Mercurial > hg
view tests/test-simplemerge.py @ 49777:e1953a34c110
bundle: emit full snapshot as is, without doing a redelta
With the new `forced` delta-reused policy, it become important to be able to
send full snapshot where full snapshot are needed. Otherwise, the fallback delta
will simply be used on the client sideā¦ creating monstrous delta chain, since
revision that are meant as a reset of delta-chain chain becoming too complex are
simply adding a new full delta-tree on the leaf of another one.
In the `non-forced` cases, client process full snapshot from the bundle
differently from deltas, so client will still try to convert the full snapshot
into a delta if possible. So this will no lead to pathological storage
explosion.
I have considered making this configurable, but the impact seems limited enough
that it does not seems to be worth it. Especially with the current
sparse-revlog format that use "delta-tree" with multiple level snapshots, full
snapshot are much less frequent and not that different from other intermediate
snapshot that we are already sending over the wire anyway.
CPU wise, this will help the bundling side a little as it will not need to
reconstruct revisions and compute deltas. The unbundling side might save a tiny
amount of CPU as it won't need to reconstruct the delta-base to reconstruct the
revision full text. This only slightly visible in some of the benchmarks. And
have no real impact on most of them.
### data-env-vars.name = pypy-2018-08-01-zstd-sparse-revlog
# benchmark.name = perf-bundle
# benchmark.variants.revs = last-40000
before: 11.467186 seconds
just-emit-full: 11.190576 seconds (-2.41%)
with-pull-force: 11.041091 seconds (-3.72%)
# benchmark.name = perf-unbundle
# benchmark.variants.revs = last-40000
before: 16.744862
just-emit-full:: 16.561036 seconds (-1.10%)
with-pull-force: 16.389344 seconds (-2.12%)
# benchmark.name = pull
# benchmark.variants.revs = last-40000
before: 26.870569
just-emit-full: 26.391188 seconds (-1.78%)
with-pull-force: 25.633184 seconds (-4.60%)
Space wise (so network-wise) the impact is fairly small. When taking compression into
account.
Below are tests the size of `hg bundle --all` for a handful of benchmark repositories
(with bzip, zstd compression and without it)
This show a small increase in the bundle size, but nothing really significant
except maybe for mozilla-try (+12%) that nobody really pulls large chunk of anyway.
Mozilla-try is also the repository that benefit the most for not having to
recompute deltas client size.
### mercurial:
bzip-before: 26 406 342 bytes
bzip-after: 26 691 543 bytes +1.08%
zstd-before: 27 918 645 bytes
zstd-after: 28 075 896 bytes +0.56%
none-before: 98 675 601 bytes
none-after: 100 411 237 bytes +1.76%
### pypy
bzip-before: 201 295 752 bytes
bzip-after: 209 780 282 bytes +4.21%
zstd-before: 202 974 795 bytes
zstd-after: 205 165 780 bytes +1.08%
none-before: 871 070 261 bytes
none-after: 993 595 057 bytes +14.07%
### netbeans
bzip-before: 601 314 330 bytes
bzip-after: 614 246 241 bytes +2.15%
zstd-before: 604 745 136 bytes
zstd-after: 615 497 705 bytes +1.78%
none-before: 3 338 238 571 bytes
none-after: 3 439 422 535 bytes +3.03%
### mozilla-central
bzip-before: 1 493 006 921 bytes
bzip-after: 1 549 650 570 bytes +3.79%
zstd-before: 1 481 910 102 bytes
zstd-after: 1 513 052 415 bytes +2.10%
none-before: 6 535 929 910 bytes
none-after: 7 010 191 342 bytes +7.26%
### mozilla-try
bzip-before: 6 583 425 999 bytes
bzip-after: 7 423 536 928 bytes +12.76%
zstd-before: 6 021 009 212 bytes
zstd-after: 6 674 922 420 bytes +10.86%
none-before: 22 954 739 558 bytes
none-after: 26 013 854 771 bytes +13.32%
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Wed, 07 Dec 2022 20:12:23 +0100 |
parents | 6000f5b25c9b |
children | 493034cc3265 |
line wrap: on
line source
# 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/>. 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 ) 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( simplemerge.render_minimized(m3), ([b'aaa', b'bbb'], False) ) 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(simplemerge.render_minimized(m3)[0]), 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(simplemerge.render_minimized(m3)[0]), 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(simplemerge.render_minimized(m3)[0]), 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, conflicts = simplemerge.render_minimized( m3, 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, conflicts = simplemerge.render_minimized( m3, 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, conflicts = simplemerge.render_minimized( m3, 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, conflicts = simplemerge.render_minimized(m3, 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, conflicts = simplemerge.render_minimized(m3, b'OTHER', b'THIS') self.assertEqual( b'<<<<<<< OTHER\r\nc\r\n=======\r\nb\r\n' b'>>>>>>> THIS\r\n'.splitlines(True), 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, conflicts = simplemerge.render_minimized(m3, b'OTHER', b'THIS') self.assertEqual( b'<<<<<<< OTHER\rc\r=======\rb\r' b'>>>>>>> THIS\r'.splitlines(True), m_lines, ) if __name__ == '__main__': import silenttestrunner silenttestrunner.main(__name__)