Mercurial > hg
view tests/test-linerange.py @ 43198:c16fe77e340a
pathcopies: give up any optimization based on `introrev`
Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the
introduction revision during path copies. However, further checking show that
finding the introduction revision is still expensive and that we are better off
without it. So we simply drop it and only rely on the linkrev optimisation.
I ran `perfpathcopies` on 6989 pair of revision in the pypy
repository (`hg perfhelper-pathcopies`. The result is massively in favor of
dropping this condition. The result of the copy tracing are unchanged.
Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it
can return wrong result. The following changesets broke test-mv-cp-st-diff.t
- if not f.isintroducedafter(limit):
+ if limit >= 0 and f.linkrev() < limit:
return None
Here are various numbers (before this changeset/after this changesets)
source destination before after saved-time ratio
worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675
c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743
22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420
682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074
5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817
worse 1% dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320
worse 5% c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488
worse 10% 3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156
worse 25% 321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259
median 2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947
best 25% 915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673
best 10% ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278
best 5% d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126
best 1% 81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813
best cases c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483
c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508
058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442
9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463
442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487
As one can see, the average case is not really impacted. However, the worth case
we get after this changeset are much better than the one we had before it. We
have 30 pairs where improvements are above 10 minutes.
This reflect in the combined time for all pairs
before: 26256s
after: 1300s (-95%)
If we remove these pathological 30 cases, we still see a significant improvements:
before: 1631s
after: 1245s (-24%)
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Thu, 10 Oct 2019 03:49:33 +0200 |
parents | 2372284d9457 |
children | ee3a55c8fd0f |
line wrap: on
line source
from __future__ import absolute_import import unittest from mercurial import error, mdiff # for readability, line numbers are 0-origin text1 = b''' 00 at OLD 01 at OLD 02 at OLD 02 at NEW, 03 at OLD 03 at NEW, 04 at OLD 04 at NEW, 05 at OLD 05 at NEW, 06 at OLD 07 at OLD 08 at OLD 09 at OLD 10 at OLD 11 at OLD '''[ 1: ] # strip initial LF text2 = b''' 00 at NEW 01 at NEW 02 at NEW, 03 at OLD 03 at NEW, 04 at OLD 04 at NEW, 05 at OLD 05 at NEW, 06 at OLD 06 at NEW 07 at NEW 08 at NEW 09 at NEW 10 at NEW 11 at NEW '''[ 1: ] # strip initial LF def filteredblocks(blocks, rangeb): """return `rangea` extracted from `blocks` coming from `mdiff.blocksinrange` along with the mask of blocks within rangeb. """ filtered, rangea = mdiff.blocksinrange(blocks, rangeb) skipped = [b not in filtered for b in blocks] return rangea, skipped class blocksinrangetests(unittest.TestCase): def setUp(self): self.blocks = list(mdiff.allblocks(text1, text2)) assert self.blocks == [ ([0, 3, 0, 2], b'!'), ((3, 7, 2, 6), b'='), ([7, 12, 6, 12], b'!'), ((12, 12, 12, 12), b'='), ], self.blocks def testWithinEqual(self): """linerange within an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^ linerange2 = (3, 5) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (4, 6)) self.assertEqual(skipped, [True, False, True, True]) def testWithinEqualStrictly(self): """linerange matching exactly an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^^^ linerange2 = (2, 6) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (3, 7)) self.assertEqual(skipped, [True, False, True, True]) def testWithinEqualLowerbound(self): """linerange at beginning of an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^ linerange2 = (2, 4) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (3, 5)) self.assertEqual(skipped, [True, False, True, True]) def testWithinEqualLowerboundOneline(self): """oneline-linerange at beginning of an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^ linerange2 = (2, 3) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (3, 4)) self.assertEqual(skipped, [True, False, True, True]) def testWithinEqualUpperbound(self): """linerange at end of an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^^ linerange2 = (3, 6) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (4, 7)) self.assertEqual(skipped, [True, False, True, True]) def testWithinEqualUpperboundOneLine(self): """oneline-linerange at end of an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^ linerange2 = (5, 6) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (6, 7)) self.assertEqual(skipped, [True, False, True, True]) def testWithinFirstBlockNeq(self): """linerange within the first "!" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^ # | (empty) # ^ # ^^ for linerange2 in [ (0, 1), (1, 1), (1, 2), (0, 2), ]: linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (0, 3)) self.assertEqual(skipped, [False, True, True, True]) def testWithinLastBlockNeq(self): """linerange within the last "!" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^ # ^ # | (empty) # ^^^^^^ # ^ for linerange2 in [ (6, 7), (7, 8), (7, 7), (6, 12), (11, 12), ]: linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (7, 12)) self.assertEqual(skipped, [True, True, False, True]) def testAccrossTwoBlocks(self): """linerange accross two blocks""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^^^ linerange2 = (1, 5) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (0, 6)) self.assertEqual(skipped, [False, False, True, True]) def testCrossingSeveralBlocks(self): """linerange accross three blocks""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^^^^^^ linerange2 = (1, 8) linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, (0, 12)) self.assertEqual(skipped, [False, False, False, True]) def testStartInEqBlock(self): """linerange starting in an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^^^ # ^^^^^^^ for linerange2, expectedlinerange1 in [ ((5, 9), (6, 12)), ((4, 11), (5, 12)), ]: linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, expectedlinerange1) self.assertEqual(skipped, [True, False, False, True]) def testEndInEqBlock(self): """linerange ending in an "=" block""" # IDX 0 1 # 012345678901 # SRC NNOOOONNNNNN (New/Old) # ^^ # ^^^^^ for linerange2, expectedlinerange1 in [ ((1, 3), (0, 4)), ((0, 4), (0, 5)), ]: linerange1, skipped = filteredblocks(self.blocks, linerange2) self.assertEqual(linerange1, expectedlinerange1) self.assertEqual(skipped, [False, False, True, True]) def testOutOfRange(self): """linerange exceeding file size""" exctype = error.Abort for linerange2 in [ (0, 34), (15, 12), ]: # Could be `with self.assertRaises(error.Abort)` but python2.6 # does not have assertRaises context manager. try: mdiff.blocksinrange(self.blocks, linerange2) except exctype as exc: self.assertTrue('line range exceeds file size' in str(exc)) else: self.fail('%s not raised' % exctype.__name__) if __name__ == '__main__': import silenttestrunner silenttestrunner.main(__name__)