view tests/test-lrucachedict.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 2372284d9457
children 6000f5b25c9b
line wrap: on
line source

from __future__ import absolute_import, print_function

import unittest

import silenttestrunner

from mercurial import util


class testlrucachedict(unittest.TestCase):
    def testsimple(self):
        d = util.lrucachedict(4)
        self.assertEqual(d.capacity, 4)
        d.insert('a', 'va', cost=2)
        d['b'] = 'vb'
        d['c'] = 'vc'
        d.insert('d', 'vd', cost=42)

        self.assertEqual(d['a'], 'va')
        self.assertEqual(d['b'], 'vb')
        self.assertEqual(d['c'], 'vc')
        self.assertEqual(d['d'], 'vd')

        self.assertEqual(d.totalcost, 44)

        # 'a' should be dropped because it was least recently used.
        d['e'] = 've'
        self.assertNotIn('a', d)
        self.assertIsNone(d.get('a'))
        self.assertEqual(d.totalcost, 42)

        self.assertEqual(d['b'], 'vb')
        self.assertEqual(d['c'], 'vc')
        self.assertEqual(d['d'], 'vd')
        self.assertEqual(d['e'], 've')

        # Replacing item with different cost adjusts totalcost.
        d.insert('e', 've', cost=4)
        self.assertEqual(d.totalcost, 46)

        # Touch entries in some order (both get and set).
        d['e']
        d['c'] = 'vc2'
        d['d']
        d['b'] = 'vb2'

        # 'e' should be dropped now
        d['f'] = 'vf'
        self.assertNotIn('e', d)
        self.assertEqual(d['b'], 'vb2')
        self.assertEqual(d['c'], 'vc2')
        self.assertEqual(d['d'], 'vd')
        self.assertEqual(d['f'], 'vf')

        d.clear()
        for key in ('a', 'b', 'c', 'd', 'e', 'f'):
            self.assertNotIn(key, d)

    def testunfull(self):
        d = util.lrucachedict(4)
        d['a'] = 1
        d['b'] = 2
        d['a']
        d['b']

        for key in ('a', 'b'):
            self.assertIn(key, d)

    def testget(self):
        d = util.lrucachedict(4)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'

        self.assertIsNone(d.get('missing'))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.get('a'), 'va')
        self.assertEqual(list(d), ['a', 'c', 'b'])

    def testpeek(self):
        d = util.lrucachedict(4)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'

        with self.assertRaises(KeyError):
            d.peek('missing')
        self.assertEqual(list(d), ['c', 'b', 'a'])
        self.assertIsNone(d.peek('missing', None))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.peek('a'), 'va')
        self.assertEqual(list(d), ['c', 'b', 'a'])

    def testpop(self):
        d = util.lrucachedict(4)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'

        with self.assertRaises(KeyError):
            d.pop('missing')
        self.assertEqual(list(d), ['c', 'b', 'a'])
        self.assertIsNone(d.pop('missing', None))
        self.assertEqual(list(d), ['c', 'b', 'a'])

        self.assertEqual(d.pop('b'), 'vb')
        self.assertEqual(list(d), ['c', 'a'])

    def testcopypartial(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=4)
        d.insert('b', 'vb', cost=2)

        dc = d.copy()

        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 6)
        for key in ('a', 'b'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(len(d), 2)
        for key in ('a', 'b'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

        d['c'] = 'vc'
        del d['b']
        self.assertEqual(d.totalcost, 4)
        dc = d.copy()
        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 4)
        for key in ('a', 'c'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

    def testcopyempty(self):
        d = util.lrucachedict(4)
        dc = d.copy()
        self.assertEqual(len(dc), 0)

    def testcopyfull(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=42)
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy()

        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(d.totalcost, 42)
        self.assertEqual(dc.totalcost, 42)

        # 'a' should be dropped because it was least recently used.
        dc['e'] = 've'
        self.assertNotIn('a', dc)
        for key in ('b', 'c', 'd', 'e'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        self.assertEqual(d.totalcost, 42)
        self.assertEqual(dc.totalcost, 0)

        # Contents and order of original dict should remain unchanged.
        dc['b'] = 'vb_new'

        self.assertEqual(list(iter(d)), ['d', 'c', 'b', 'a'])
        for key in ('a', 'b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        d = util.lrucachedict(4, maxcost=42)
        d.insert('a', 'va', cost=5)
        d.insert('b', 'vb', cost=4)
        d.insert('c', 'vc', cost=3)
        dc = d.copy()
        self.assertEqual(dc.maxcost, 42)
        self.assertEqual(len(dc), 3)

        # Max cost can be lowered as part of copy.
        dc = d.copy(maxcost=10)
        self.assertEqual(dc.maxcost, 10)
        self.assertEqual(len(dc), 2)
        self.assertEqual(dc.totalcost, 7)
        self.assertIn('b', dc)
        self.assertIn('c', dc)

    def testcopydecreasecapacity(self):
        d = util.lrucachedict(5)
        d.insert('a', 'va', cost=4)
        d.insert('b', 'vb', cost=2)
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy(2)
        self.assertEqual(dc.totalcost, 0)
        for key in ('a', 'b'):
            self.assertNotIn(key, dc)
        for key in ('c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc.insert('e', 've', cost=7)
        self.assertEqual(dc.totalcost, 7)
        self.assertNotIn('c', dc)
        for key in ('d', 'e'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        # Original should remain unchanged.
        self.assertEqual(d.totalcost, 6)
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

    def testcopyincreasecapacity(self):
        d = util.lrucachedict(5)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        dc = d.copy(6)
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc['e'] = 've'
        dc['f'] = 'vf'
        for key in ('a', 'b', 'c', 'd', 'e', 'f'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        dc['g'] = 'vg'
        self.assertNotIn('a', dc)
        for key in ('b', 'c', 'd', 'e', 'f', 'g'):
            self.assertIn(key, dc)
            self.assertEqual(dc[key], 'v%s' % key)

        # Original should remain unchanged.
        for key in ('a', 'b', 'c', 'd'):
            self.assertIn(key, d)
            self.assertEqual(d[key], 'v%s' % key)

    def testpopoldest(self):
        d = util.lrucachedict(4)
        d.insert('a', 'va', cost=10)
        d.insert('b', 'vb', cost=5)

        self.assertEqual(len(d), 2)
        self.assertEqual(d.popoldest(), ('a', 'va'))
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 5)
        self.assertEqual(d.popoldest(), ('b', 'vb'))
        self.assertEqual(len(d), 0)
        self.assertEqual(d.totalcost, 0)
        self.assertIsNone(d.popoldest())

        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'

        self.assertEqual(d.popoldest(), ('a', 'va'))
        self.assertEqual(len(d), 3)
        for key in ('b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        d['a'] = 'va'
        self.assertEqual(d.popoldest(), ('b', 'vb'))

    def testmaxcost(self):
        # Item cost is zero by default.
        d = util.lrucachedict(6, maxcost=10)
        d['a'] = 'va'
        d['b'] = 'vb'
        d['c'] = 'vc'
        d['d'] = 'vd'
        self.assertEqual(len(d), 4)
        self.assertEqual(d.totalcost, 0)

        d.clear()

        # Insertion to exact cost threshold works without eviction.
        d.insert('a', 'va', cost=6)
        d.insert('b', 'vb', cost=4)

        self.assertEqual(len(d), 2)
        self.assertEqual(d['a'], 'va')
        self.assertEqual(d['b'], 'vb')

        # Inserting a new element with 0 cost works.
        d['c'] = 'vc'
        self.assertEqual(len(d), 3)

        # Inserting a new element with cost putting us above high
        # water mark evicts oldest single item.
        d.insert('d', 'vd', cost=1)
        self.assertEqual(len(d), 3)
        self.assertEqual(d.totalcost, 5)
        self.assertNotIn('a', d)
        for key in ('b', 'c', 'd'):
            self.assertEqual(d[key], 'v%s' % key)

        # Inserting a new element with enough room for just itself
        # evicts all items before.
        d.insert('e', 've', cost=10)
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 10)
        self.assertIn('e', d)

        # Inserting a new element with cost greater than threshold
        # still retains that item.
        d.insert('f', 'vf', cost=11)
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 11)
        self.assertIn('f', d)

        # Inserting a new element will evict the last item since it is
        # too large.
        d['g'] = 'vg'
        self.assertEqual(len(d), 1)
        self.assertEqual(d.totalcost, 0)
        self.assertIn('g', d)

        d.clear()

        d.insert('a', 'va', cost=7)
        d.insert('b', 'vb', cost=3)
        self.assertEqual(len(d), 2)

        # Replacing a value with smaller cost won't result in eviction.
        d.insert('b', 'vb2', cost=2)
        self.assertEqual(len(d), 2)

        # Replacing a value with a higher cost will evict when threshold
        # exceeded.
        d.insert('b', 'vb3', cost=4)
        self.assertEqual(len(d), 1)
        self.assertNotIn('a', d)

    def testmaxcostcomplex(self):
        d = util.lrucachedict(100, maxcost=100)
        d.insert('a', 'va', cost=9)
        d.insert('b', 'vb', cost=21)
        d.insert('c', 'vc', cost=7)
        d.insert('d', 'vc', cost=50)
        self.assertEqual(d.totalcost, 87)

        # Inserting new element should free multiple elements so we hit
        # low water mark.
        d.insert('e', 'vd', cost=25)
        self.assertEqual(len(d), 2)
        self.assertNotIn('a', d)
        self.assertNotIn('b', d)
        self.assertNotIn('c', d)
        self.assertIn('d', d)
        self.assertIn('e', d)


if __name__ == '__main__':
    silenttestrunner.main(__name__)