tests/test-doctest.py

util: lower water mark when removing nodes after cost limit reached

See the inline comment for the reasoning here. This is a pretty
common strategy for garbage collectors, other cache-like primtives.

The performance impact is substantial:

$ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100
! inserts w/ cost limit
! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7)
! wall 1.722122 comb 1.720000 user 1.720000 sys 0.000000 (best of 6)
! mixed w/ cost limit
! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9)
! wall 1.182513 comb 1.180000 user 1.180000 sys 0.000000 (best of 9)

$ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000
! inserts
! wall 0.679546 comb 0.680000 user 0.680000 sys 0.000000 (best of 15)
! sets
! wall 0.825147 comb 0.830000 user 0.830000 sys 0.000000 (best of 13)
! inserts w/ cost limit
! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3)
! wall  1.724397 comb  1.720000 user  1.720000 sys 0.000000 (best of 6)
! mixed
! wall 0.807096 comb 0.810000 user 0.810000 sys 0.000000 (best of 13)
! mixed w/ cost limit
! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3)
! wall  1.190563 comb  1.190000 user  1.190000 sys 0.000000 (best of 9)

$ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90
! inserts
! wall 0.711177 comb 0.710000 user 0.710000 sys 0.000000 (best of 14)
! sets
! wall 0.846992 comb 0.850000 user 0.850000 sys 0.000000 (best of 12)
! inserts w/ cost limit
! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3)
! wall  2.184311 comb  2.180000 user  2.180000 sys 0.000000 (best of 5)
! mixed
! wall 0.728256 comb 0.730000 user 0.730000 sys 0.000000 (best of 14)
! mixed w/ cost limit
! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4)
! wall 0.773186 comb 0.770000 user 0.770000 sys 0.000000 (best of 13)

$ hg perflrucachedict --size 100000 --gets 1000000 --sets 1000000 --mixed 1000000 --mixedgetfreq 90 --costlimit 5000000
! gets
! wall 1.191368 comb 1.190000 user 1.190000 sys 0.000000 (best of 9)
! wall 1.195304 comb 1.190000 user 1.190000 sys 0.000000 (best of 9)
! inserts
! wall 0.950995 comb 0.950000 user 0.950000 sys 0.000000 (best of 11)
! inserts w/ cost limit
! wall 1.589732 comb 1.590000 user 1.590000 sys 0.000000 (best of 7)
! sets
! wall 1.094941 comb 1.100000 user 1.090000 sys 0.010000 (best of 9)
! mixed
! wall 0.936420 comb 0.940000 user 0.930000 sys 0.010000 (best of 10)
! mixed w/ cost limit
! wall 0.882780 comb 0.870000 user 0.870000 sys 0.000000 (best of 11)

This puts us ~2x slower than caches without cost accounting. And for
read-heavy workloads (the prime use cases for caches), performance is
nearly identical.

In the worst case (pure write workloads with cost accounting enabled),
we're looking at ~1.5us per insert on large caches. That seems "fast
enough."

Differential Revision: https://phab.mercurial-scm.org/D4505

# this is hack to make sure no escape characters are inserted into the output

from __future__ import absolute_import

import doctest
import os
import re
import sys

ispy3 = (sys.version_info[0] >= 3)

if 'TERM' in os.environ:
    del os.environ['TERM']

class py3docchecker(doctest.OutputChecker):
    def check_output(self, want, got, optionflags):
        want2 = re.sub(r'''\bu(['"])(.*?)\1''', r'\1\2\1', want)  # py2: u''
        got2 = re.sub(r'''\bb(['"])(.*?)\1''', r'\1\2\1', got)  # py3: b''
        # py3: <exc.name>: b'<msg>' -> <name>: <msg>
        #      <exc.name>: <others> -> <name>: <others>
        got2 = re.sub(r'''^mercurial\.\w+\.(\w+): (['"])(.*?)\2''', r'\1: \3',
                      got2, re.MULTILINE)
        got2 = re.sub(r'^mercurial\.\w+\.(\w+): ', r'\1: ', got2, re.MULTILINE)
        return any(doctest.OutputChecker.check_output(self, w, g, optionflags)
                   for w, g in [(want, got), (want2, got2)])

def testmod(name, optionflags=0, testtarget=None):
    __import__(name)
    mod = sys.modules[name]
    if testtarget is not None:
        mod = getattr(mod, testtarget)

    # minimal copy of doctest.testmod()
    finder = doctest.DocTestFinder()
    checker = None
    if ispy3:
        checker = py3docchecker()
    runner = doctest.DocTestRunner(checker=checker, optionflags=optionflags)
    for test in finder.find(mod, name):
        runner.run(test)
    runner.summarize()

testmod('mercurial.changegroup')
testmod('mercurial.changelog')
testmod('mercurial.cmdutil')
testmod('mercurial.color')
testmod('mercurial.config')
testmod('mercurial.context')
testmod('mercurial.dagparser', optionflags=doctest.NORMALIZE_WHITESPACE)
testmod('mercurial.dispatch')
testmod('mercurial.encoding')
testmod('mercurial.fancyopts')
testmod('mercurial.formatter')
testmod('mercurial.hg')
testmod('mercurial.hgweb.hgwebdir_mod')
testmod('mercurial.match')
testmod('mercurial.mdiff')
testmod('mercurial.minirst')
testmod('mercurial.patch')
testmod('mercurial.pathutil')
testmod('mercurial.parser')
testmod('mercurial.pycompat')
testmod('mercurial.revlog')
testmod('mercurial.revsetlang')
testmod('mercurial.smartset')
testmod('mercurial.store')
testmod('mercurial.subrepo')
testmod('mercurial.templatefilters')
testmod('mercurial.templater')
testmod('mercurial.ui')
testmod('mercurial.url')
testmod('mercurial.util')
testmod('mercurial.util', testtarget='platform')
testmod('mercurial.utils.stringutil')
testmod('hgext.convert.convcmd')
testmod('hgext.convert.cvsps')
testmod('hgext.convert.filemap')
testmod('hgext.convert.p4')
testmod('hgext.convert.subversion')
testmod('hgext.fix')
testmod('hgext.mq')
# Helper scripts in tests/ that have doctests:
testmod('drawdag')