##// 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:

r34648:dacfcdd8 default
r39605:cc23c09b default
Show More
osutil.py
102 lines | 3.5 KiB | text/x-python | PythonLexer
# osutil.py - CFFI version of osutil.c
#
# Copyright 2016 Maciej Fijalkowski <fijall@gmail.com>
#
# 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
import os
import stat as statmod
from ..pure.osutil import *
from .. import (
pycompat,
)
if pycompat.isdarwin:
from . import _osutil
ffi = _osutil.ffi
lib = _osutil.lib
listdir_batch_size = 4096
# tweakable number, only affects performance, which chunks
# of bytes do we get back from getattrlistbulk
attrkinds = [None] * 20 # we need the max no for enum VXXX, 20 is plenty
attrkinds[lib.VREG] = statmod.S_IFREG
attrkinds[lib.VDIR] = statmod.S_IFDIR
attrkinds[lib.VLNK] = statmod.S_IFLNK
attrkinds[lib.VBLK] = statmod.S_IFBLK
attrkinds[lib.VCHR] = statmod.S_IFCHR
attrkinds[lib.VFIFO] = statmod.S_IFIFO
attrkinds[lib.VSOCK] = statmod.S_IFSOCK
class stat_res(object):
def __init__(self, st_mode, st_mtime, st_size):
self.st_mode = st_mode
self.st_mtime = st_mtime
self.st_size = st_size
tv_sec_ofs = ffi.offsetof("struct timespec", "tv_sec")
buf = ffi.new("char[]", listdir_batch_size)
def listdirinternal(dfd, req, stat, skip):
ret = []
while True:
r = lib.getattrlistbulk(dfd, req, buf, listdir_batch_size, 0)
if r == 0:
break
if r == -1:
raise OSError(ffi.errno, os.strerror(ffi.errno))
cur = ffi.cast("val_attrs_t*", buf)
for i in range(r):
lgt = cur.length
assert lgt == ffi.cast('uint32_t*', cur)[0]
ofs = cur.name_info.attr_dataoffset
str_lgt = cur.name_info.attr_length
base_ofs = ffi.offsetof('val_attrs_t', 'name_info')
name = str(ffi.buffer(ffi.cast("char*", cur) + base_ofs + ofs,
str_lgt - 1))
tp = attrkinds[cur.obj_type]
if name == "." or name == "..":
continue
if skip == name and tp == statmod.S_ISDIR:
return []
if stat:
mtime = cur.mtime.tv_sec
mode = (cur.accessmask & ~lib.S_IFMT)| tp
ret.append((name, tp, stat_res(st_mode=mode, st_mtime=mtime,
st_size=cur.datalength)))
else:
ret.append((name, tp))
cur = ffi.cast("val_attrs_t*", int(ffi.cast("intptr_t", cur))
+ lgt)
return ret
def listdir(path, stat=False, skip=None):
req = ffi.new("struct attrlist*")
req.bitmapcount = lib.ATTR_BIT_MAP_COUNT
req.commonattr = (lib.ATTR_CMN_RETURNED_ATTRS |
lib.ATTR_CMN_NAME |
lib.ATTR_CMN_OBJTYPE |
lib.ATTR_CMN_ACCESSMASK |
lib.ATTR_CMN_MODTIME)
req.fileattr = lib.ATTR_FILE_DATALENGTH
dfd = lib.open(path, lib.O_RDONLY, 0)
if dfd == -1:
raise OSError(ffi.errno, os.strerror(ffi.errno))
try:
ret = listdirinternal(dfd, req, stat, skip)
finally:
try:
lib.close(dfd)
except BaseException:
pass # we ignore all the errors from closing, not
# much we can do about that
return ret