##// END OF EJS Templates
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

File last commit:

r38915:e79a69af default
r39605:cc23c09b default
Show More
minifileset.py
92 lines | 3.5 KiB | text/x-python | PythonLexer
# minifileset.py - a simple language to select files
#
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
from .i18n import _
from . import (
error,
fileset,
filesetlang,
pycompat,
)
def _sizep(x):
# i18n: "size" is a keyword
expr = filesetlang.getstring(x, _("size requires an expression"))
return fileset.sizematcher(expr)
def _compile(tree):
if not tree:
raise error.ParseError(_("missing argument"))
op = tree[0]
if op == 'withstatus':
return _compile(tree[1])
elif op in {'symbol', 'string', 'kindpat'}:
name = filesetlang.getpattern(tree, {'path'}, _('invalid file pattern'))
if name.startswith('**'): # file extension test, ex. "**.tar.gz"
ext = name[2:]
for c in pycompat.bytestr(ext):
if c in '*{}[]?/\\':
raise error.ParseError(_('reserved character: %s') % c)
return lambda n, s: n.endswith(ext)
elif name.startswith('path:'): # directory or full path test
p = name[5:] # prefix
pl = len(p)
f = lambda n, s: n.startswith(p) and (len(n) == pl
or n[pl:pl + 1] == '/')
return f
raise error.ParseError(_("unsupported file pattern: %s") % name,
hint=_('paths must be prefixed with "path:"'))
elif op in {'or', 'patterns'}:
funcs = [_compile(x) for x in tree[1:]]
return lambda n, s: any(f(n, s) for f in funcs)
elif op == 'and':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and func2(n, s)
elif op == 'not':
return lambda n, s: not _compile(tree[1])(n, s)
elif op == 'func':
symbols = {
'all': lambda n, s: True,
'none': lambda n, s: False,
'size': lambda n, s: _sizep(tree[2])(s),
}
name = filesetlang.getsymbol(tree[1])
if name in symbols:
return symbols[name]
raise error.UnknownIdentifier(name, symbols.keys())
elif op == 'minus': # equivalent to 'x and not y'
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and not func2(n, s)
elif op == 'list':
raise error.ParseError(_("can't use a list in this context"),
hint=_('see \'hg help "filesets.x or y"\''))
raise error.ProgrammingError('illegal tree: %r' % (tree,))
def compile(text):
"""generate a function (path, size) -> bool from filter specification.
"text" could contain the operators defined by the fileset language for
common logic operations, and parenthesis for grouping. The supported path
tests are '**.extname' for file extension test, and '"path:dir/subdir"'
for prefix test. The ``size()`` predicate is borrowed from filesets to test
file size. The predicates ``all()`` and ``none()`` are also supported.
'(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
example, will catch all php files whose size is greater than 10 MB, all
files whose name ends with ".zip", and all files under "bin" in the repo
root except for "bin/README".
"""
tree = filesetlang.parse(text)
tree = filesetlang.analyze(tree)
tree = filesetlang.optimize(tree)
return _compile(tree)