Mercurial > hg
view tests/test-linerange.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
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Tue, 11 Feb 2020 11:18:52 +0100 |
parents | ee3a55c8fd0f |
children | 6000f5b25c9b |
line wrap: on
line source
from __future__ import absolute_import import unittest from mercurial import error, mdiff from mercurial.utils import stringutil # 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( b'line range exceeds file size' in stringutil.forcebytestr(exc) ) else: self.fail('%s not raised' % exctype.__name__) if __name__ == '__main__': import silenttestrunner silenttestrunner.main(__name__)