##// END OF EJS Templates
upstream » mercurial-mirror
RSS

Clone from https://www.mercurial-scm.org/repo/hg-all

util: optimize cost auditing on insert...
util: optimize cost auditing on insert Calling popoldest() on insert with cost auditing enabled introduces significant overhead. The primary reason for this overhead is that popoldest() needs to walk the linked list to find the first non-empty node. When we call popoldest() within a loop, this can become quadratic. The performance impact is more pronounced on caches with large capacities. This commit effectively inlines the popoldest() call into _enforcecostlimit(). By doing so, we only do the backwards walk to find the first empty node once. However, we still may still perform this work on insert when the cache is near cost capacity. So this is only a partial performance win. $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.601993 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.614439 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) Differential Revision: https://phab.mercurial-scm.org/D4504
Gregory Szorc - - Load All Authors

File last commit:

r39604:842cd0bd default
r39605:cc23c09b default
Show More
test-lrucachedict.py
325 lines | 9.4 KiB | text/x-python | PythonLexer
/ tests / test-lrucachedict.py
History | Annotation | Raw |Copy content |Copy permalink
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 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), 3)
self.assertNotIn('a', d)
self.assertNotIn('b', d)
self.assertIn('c', d)
self.assertIn('d', d)
self.assertIn('e', d)
if __name__ == '__main__':
silenttestrunner.main(__name__)